Datasets:

ianiket23

/

podcast_llama_chat_format-5k

like 0

<s>[INST] So it's nice to get some healthy variety into the mix. They make it easy and convenient with everything proportioned and ready to prep and cook. You can enjoy delicious healthy dinner in as little as 15 minutes. I've enjoyed a lot of meals from their menu that fit my, what they call carb conscious ways. Some items on the menu that I have written down our black angus rib eye steak with broccoli and radishes, italian sausages and vegetable skewers with two romesco mediterranean lemon chicken with baby broccoli, artichokes and olives and there's many more delicious ones. Even in just the carb conscious category. Right now, sun basket is offering $35 off your order when you go to sun basket dot com slash lex and enter promo code lex at checkout again, visit sun basket dot com slash lex and use code lex to get 35 bucks off your order. And now finally, here's my conversation with Natalya Bayley. You said that you spent your whole life dreaming about space and also pondering the big existential question of whether there is or isn't intelligent life intelligent alien civilizations out there. So what do you think? Do you think there's life out there, intelligent life, [/INST] intelligent life? That's trickier. I think looking at, you know, the the likelihood of a self replicating organism, given how much time the universe has existed and how many stars with planets. I think it's likely that there's other life, intelligent life. I'm hopeful. I'm a little discouraged that we haven't yet been in touch </s><s>[INST] allegedly. I mean, [/INST] it's in our dimensions and it's </s><s>[INST] also possible that they have been in touch and we just haven't, we're too dumb to realize they're communicating with us in whichever. It's the, it's the carl, sagan idea that they may be communicating at a time scale. That's totally different. Like their signals are in a totally different time scale or like a totally different kind of medium of communication. It could be, it could be our own, it could be the birth of like human beings like that, whatever the magic that makes us who we are, the collective intelligence thing. That could be aliens themselves. That could be the medium of communication. Like the nature of our consciousness and intelligence itself as the medium of communication [/INST] and being able to ask the questions themselves. I've never thought of it that way. </s><s>[INST] Actually, I'm asking the question whether aliens exist might be the very medium by which they communicate. It's like they send questions. [/INST] So some this collective emergent behavior is the signal </s><s>[INST] is the signal. Yeah, so interesting. Yeah, because maybe that's how we would communicate with. If you think about if you are way, way, way smarter, Like 1000 years from now we somehow survive. Like how would we actually communicate in a way that's like if we broadcast the signal, you know? And then it could somehow like percolate throughout the universe. Like that signal having an impact multiverse of course. Uh that would have a signal uh an effect on the most possible, most, the highest number of possible civilizations. What would that signal be? It might not be like signing a few like stupid little Hello World message is it might be something more impact for what it's almost like impactful in a way where they don't have to have the capability to hear it. It like forces the message to have an [/INST] impact. My train of thought has never gone gone there, but I like it. And also somewhere in there, I think it's implied that something travels faster than the speed of light, which I'm also really hopeful for </s><s>[INST] your hopeful, Are you excited by the possibility that there's intelligent life out there sort of, you work on on the engineering side of things? It's this very kind of focused pursuit of moving things thru space efficiently. But you know, if you zoom out one of the cool things that this enables us to do is find forget even intelligent life just life on mars on europe or something like that. Does that excite you? That scare you? [/INST] Oh, it's very exciting. I mean, it's the whole reason I went into the field I'm in is to contribute to building the body of knowledge that we have as a species. So very exciting. </s><s>[INST] Do you think there's life on mars like uh no longer well already living, but currently living, but also no longer living like that, we might be able to find life. There's there's some people suspect basic microbial life, [/INST] I'm not so sure about in our own solar system and and I do think it might be hard to untangle if we somehow contaminated other things as well. So I'm not sure about this close to home, </s><s>[INST] It would be really exciting. Yes. Do you think about the drake equation Much of [/INST] that was what, what got me into all of this? Yeah. </s><s>[INST] Yeah, because one of the questions is how hard is it for life to start on the habitable planet? Like if you have a lot of the basic conditions, not exactly like earth, but basic earthlike conditions, how hard is it for life to start? And if you find life on mars or find life on Europa, that means it's way easier. That's a good thing to confirm that if you have a habitable planet, then there's going to be life and that like immediately that that would be super exciting because that means there's like trillions of planets, basically. I thought there [/INST] though of all the planets in our solar system, earth is clearly the most habitable. So I would not be discouraged if we didn't find it on another planet in our solar system. </s>

<s>[INST] do you have advice for people learning new things? So if you what have you learned as a process as I mean it all starts to just making the hours in the day available. [/INST] Yeah you gotta stick with it. Which is again the number one thing that 99% of people don't do. So the people I started learning chinese with, none of them were still doing it 12 months later. I'm still doing it 10 years later I tried to stay in touch with them but they're just no one did it for something like chinese like study how human learning works. So every one of my chinese flashcards is associated with a story and that story is specifically designed to be memorable and we find things memorable which are like funny or disgusting or sexy or related to people that we know or care about. So I try to make sure all the stories that are in my head have those characteristics. Yeah. So you have to, you know you won't remember things well if they don't have some context and yeah you won't remember them well if you don't regularly practice them, whether it be just part of your day to day life or the chinese army flashcards. I mean the other thing is let yourself fail sometimes. So like I've had various medical problems over the last few years and basically my flash cards just stopped for about three years and, and there's been other times I've stopped for a few months and it's so hard because you get back to it and it's like You have 18,000 cards do, it's like, so you just have to go all right, well I can either stop and give up everything or just decide to do this every day for the next two years until I get back to it. The amazing thing has been that even after three years I, you know the chinese were still in there, like it was so much faster to reload and then it was to learn the first time. </s><s>[INST] Yeah, absolutely. It's it's in there. I have the same with guitar with music and so on. It's sad because of work sometimes takes away and then you won't play for a year. But really if you then just get back to it every day, you're right, you're right there again. What do you think is the next big breakthrough in artificial intelligence? What are your hopes in deep learning or beyond that people should be working on or you hope there'll be breakthroughs. [/INST] I don't think it's possible to predict. I think, I think what we already have is an incredibly powerful platform to solve lots of societally important problems that are currently unsolved. So I just hope that people will, lots of people will learn this toolkit and try to use it. I don't think we need a lot of new technological breakthroughs to do a lot of great work right now. </s><s>[INST] And uh when do you think we're going to create a human level intelligence system, Do you think? You know, how hard is it, how far away are we? [/INST] Don't know. I don't have no way to know. I don't know. Like I don't know why people make predictions about this because there's no data and nothing to go on and it's just like there's so many societally important problems to solve right now. I just don't find it a really interesting question to even answer. </s><s>[INST] So in terms of societally important problems, what's the problem? Well, is within [/INST] reach? Well, I mean for example, there are problems that ai creates, right? So more specifically labor force displacement is going to be huge and people keep making this fearless econometric argument of being like, oh there's been other things that aren't ai that have come along before and haven't created massive labor force displacement therefore a I want </s><s>[INST] so that's a serious concern for you. Andrew yang is running on it. [/INST] Yeah, it's I'm desperately concerned and you see already that the changing workplace has led to a hollowing out of the middle class, you're saying that students coming out of school today have a less rosy financial future ahead of him and the parents did, which has never happened in recent In the last 300 years. We've always had progress before. And you see this turning into anxiety and despair and and even violence. So I very much worry about that. </s><s>[INST] You've written quite a bit about ethics [/INST] to I do think that every data scientist working with deep learning needs to recognize they have an incredibly high leverage tool that they're using that can influence society in lots of ways. And if they're doing research that that research is going to be used by people doing this kind of work and they have a responsibility to consider the consequences and to think about things like how will humans be in the loop here? How do we avoid runaway feedback loops? How do we ensure an appeals process for humans that are impacted by my algorithm? How do I ensure that the constraints of my algorithm are radically explained to the people that end up using them. There's all kinds of human issues which only data scientists who actually in the right place to educate people about. But data scientists tend to think of themselves as just engineers and they don't need to be part of that process, which is Yeah, which is wrong. </s><s>[INST] Well, you're in the perfect position to educate them better, to read literature, to read history, to learn from history. Well, jeremy, thank you so much for everything you do for inspiring huge amount of people getting them into deep learning and having the ripple effects the flap of a butterfly's wings, that will probably change the world. So thank you very much, [/INST] yes. </s>

<s>[INST] But the process can be automated. I mean it seems like the brain [/INST] can be automated so people can write a software for this. And eventually the idea is, let's not make assumptions about this thing. If you don't know what the right solution is in those areas that we have no idea whether the right solution will be people designing this ad hoc or machines doing this, whether you want to enforce compliance by social norms like Wikipedia or this uh software solutions or ai that goes through the post of people or is the legal principle and so on. This is something maybe you need to find out. And so the idea would be, if you let the communities evolve and you just control it in such a way that you are incentivizing the most sentient communities, the ones that produce the most interesting behaviors that allow you to interact in the most helpful ways to the individual's right, You have a network that gives you information that is relevant to you. It helps you to maintain relationships to others in healthy ways. It allows you to build teams, it allows you to basically bring the best of you into this thing and cause into a coupling into a relationship with others in which you produce things that you would be unable to produce alone </s><s>[INST] beautifully put. So uh but the key process of that with incentives and evolution is things that don't adopt themselves to effectively get the incentives have to die. And the thing about social media is communities that are unhealthy or whatever you want to define as the incentives really don't like dying. One of the things that people really get aggressive protests aggressively is when they're censored, especially in America. I don't know, I don't know much about the rest of the world, but the idea of freedom of speech, the idea of censorship is really painful in America. And so what yeah, what do you think about that having grown up in East Germany, what do you think censorship is an important tool in our brain and the intelligence and in uh social networks. So basically if you're not a good member of the entirety of the system, you should be blocked away locked away, blocked. [/INST] The important thing is who decides that you are a good member, </s><s>[INST] Who is it distributed [/INST] or and what is the outcome of the process that decides it both for the individual and for society at large. For instance, if you have a high trust society, you don't need a lot of surveillance. And the surveillance is even in some sense undermining trust because it's uh basically punishing people that look suspicious when surveyed but do the right thing anyway. And the opposite if you have a low trust society than surveillance can be a better trade off in the U. S. Is currently making a transition from a relatively high trust or mixed trust society to a low trust society? So surveillance will increase. Another thing is that beliefs are not just in what representations there are implementations that run quote on your brain and change your reality and change the way you interact with each other at some level. And some of the beliefs are just um public opinions that we used to display our alignment. So for instance people might say all cultures have are the same and equally good but still they prefer to live in some cultures of others very very strongly so. And it turns out that the cultures are defined by certain rules of interaction and these rules of interaction need two different results when you implement them, right? So if you adhere to certain rules you get different outcomes in different societies and this all leads to very tricky situations when people do not have a commitment to shared purpose and our societies probably need to rediscover what it means to have a shared purpose and how to make this compatible with a non totalitarian view. So in some sense us is called in a conundrum between uh totalitarian ism and diversity and uh doesn't need to how to resolve this and the solutions that the US has found so far very crude because it's a very young society that is also under a lot of tension. That seems to me that the U. S. Will have to reinvent itself. </s><s>[INST] What do you think? Just uh philosophizing, what kind of mechanisms of government do you think we as a species should be involved with us or broadly? What do you think will work well as a as a system? Of course we don't know, it all seems to work pretty crappy lee some things worse than others. Some people argue that communism is the best. Others say. Yeah look at the soviet union. Some people argue that anarchy is the best and then completely discarding the positive effects of government. You know, there's a lot of arguments US seems to be doing pretty damn well in in the span of history. There's a respect for human rights, which seems to be a nice feature, not a bug. And economically a lot of growth, a lot of technological development, people seem to be relatively kind on the grass scheme of things. Um what lessons do you draw from that? What kind of government system do you think is good, [/INST] ideally? Government should uh not be perceivable, right? It should be frictionless. The more you notice the influence of the government, the more friction you experience, the less uh effective and efficient government probably is. Right. So a government came theoretically is an agent that imposes an offset on your payout metrics to make your nash equilibrium compatible with the common good, right? So you have these situations high local incentives, uh these local incentives, everybody does the thing that's locally the best for them. But the global outcome is not good. And there's even the case when people care about the global outcome because regulation mechanisms exist, that creates a causal relationship between what I want to have for the global good and what I do. So for instance, I think that we should fly less and I stay at home. There's not a single plane that is going to not start because of me, right, It's not going to have an influence, but I don't get from A to B. So the way to implement this would basically to have a government that is sharing this idea that we should fly less and is then imposing a regulation that for instance makes flying more expensive and uh gives incentives for inventing other forms of transportation that are less um putting the strain on the environment for instance. </s>

<s>[INST] So, one of the things you say is, I mean, first of all the numbers of workers that will be, they will feel his pain is not perhaps as large as the journalists kind of articulate, but nevertheless the pain is real. And uh, I guess my question here is um, do you have an optimistic vision about the transformative effects of autonomous trucks on society? Thank you. If you look 20 years from now and perhaps he Maybe 30 years from now, perhaps see these autonomous trucks doing the various parts of the scenarios you listed? And there's just hundreds of thousands of them just, uh, like, uh, like veins like blood throwing through, flowing through veins on the interstate system. Um, what kind of world do you see? That's a better world than today that involves these trucks. [/INST] Yeah. Um, can I defend myself first because I can, I'm reading the comments right now of people, you know, of the economists </s><s>[INST] tell your commentary. Dear PhD Economics? [/INST] Yes. Um Yes. Dear PhD in Economics, I know that that higher skilled jobs are created, you know, by by technological advancement, Right? I mean, there are big questions about how many of them, right? So the idea that we would create more um, you know, expensive labor positions, right? With the new technology, right? You better check your business plan if your ideas to take, you know, a bunch of low, low wage labor and replace it with the same amount of high wage labor. Right? So there's a question about how many of those jobs in there's the really important social and political question of are they the same people? Right? And do they live in the same places? And I think that kind of geography is a huge issue here with the impacts, right? Lots of rural workers. Um, interesting politically, lots of Red State workers, Right? Lots of Blue State, maybe union folks who are going to try to slow autonomy and lots of Red State, you know, representatives in the House maybe who want to, you know, stand up for their, for their trucker constituents. Um, so just </s><s>[INST] just to defend myself [/INST] and to </s><s>[INST] elaborate, I think economics is a field is not good at measuring the landscape of human pain and suffering. So, you know, sometimes you can forget in the numbers as real lives at stake. That's what I suppose sociology is better at doing. Uh So sometimes sometimes, Well, the problem with, I mean, I'm somebody who I love psychology and psychiatry. And a little bit, I guess, of sociology, I realized how little how tragically flawed the field is not because of lack of trying, but just how difficult the problems are to do really thorough studies that understand the fundamentals of human behavior and this landscape of human suffering. It's just, it's almost an impossible task without the data. And we currently don't, you know, not everybody is richly integrated to where they're fully connected and all their information is being uh like recorded for sociologists to study. So you have to make a lot of influences, You have to talk to people, you have to do the interviews as you're doing. And through that like really difficult to work, try to understand like uh here the music that nobody else is hearing the music of like what people are feeling, their hopes, their dreams and their the crushing of their dreams due to some kind of economic forces. [/INST] Yeah, I mean, we've just lived that for 4.5 years of probably, you know, elites let me just go out on a limb and say not understanding the sort of emotional and psychological currents of a large portion of the population, right? And just being stunned by it and and confused, right? Um, wasn't confusing for me after having talked to truckers again, who trucking is a job of last resort. These are people who have already lost that manufacturing job oftentimes already lost that construction job to just aging, right? So what, you know, what can we do, right? What's sort of the positive vision? Because like we've got tons of highway deaths, we've got um and just you know, the big picture is and this is the opportunity I guess for investors. Um It's a hugely inefficient system. So we buy this truck, there's this low wage worker and it often times um and again I'm setting aside those really good line haul jobs in L. T. L. Those are those are different case um That low wage worker is driving a truck that they might, the wheels might roll 7-8 hours a day, that's what the truck is designed to do and that's what makes the money for the company In other 78 hours a day, the drivers doing other kinds of work that you know is not driving. And then the rest of the day they're basically living out of the truck. You really can't find a more inefficient use of an asset than than than that right now, a big part of that is we pay for the roads and we pay for the rest areas and on all the all this other stuff. So so the way that I work in the way that, you know, I think about these problems is I try to find analogies, right, sort of labor processes and things that make economic sense, You know, that that seem, you know, in the in the same area of of the economy, but have some some different characteristics for for workers. Right. And and sort of try to figure out why does the economics work there. Right. And so if you look at those really good jobs, the most likely way that you as a as a passenger car driver would know that it's one of those drivers. Is there multiple trailers? Right? So you see these like maybe maybe it's three small trailers, Maybe it's to sort of medium sized trailers. Some places you might even see two really big trailers together. Um you do that because labor is expensive, right? And it's highly skilled. And so you use it efficiently. And you say, all right. You know, rather than having you, you know, all that little trailer out of the ports, you know, that sort of half size container, we're gonna wait till we get three or we're going to coordinate the movement so that their three ready. You go do what truckers call, make a set, put them together, right? And you and you go, Um, that's a massive productivity gain, right? Because, you know, you're you're hauling 23 times as much freight. So the positive scenario that I threw out in 2018 was why not have a human driven truck with a self driving truck that follows it, right? Just a drone unit. Um and it was, you know, to me this seems as a you know, non computer scientists, a sociologist. Right? This made a lot of sense because when I got done talking to the, you know, the computer scientists and the engineers, they were like, well, you know, it's like object recognition, decision making, algorithm, all the stuff. It's like, all right, so why don't you leave the human brain in the lead vehicle? Right? You got all that processing and then all that following. Again, this is sort of me being a lay person. You know, I said, why don't you know then that following truck, right, takes direction from the front, it uses the rear of the trailer as a reference point. It maintains the lane, you got cooperative adaptive cruise control and that you double the productivity of that driver. You solve that problem that I that I hated in in my, you know, urban truck ports. Thing about the bridge weight. Because when you get to the bridge is, you know, the two trucks can just spread out just enough to make the bridge weight. Right? And you can just program that in and you know, they're 50 ft further apart, 100 ft further further apart. Um So interesting sort of, I think uh story about this, that that leads to kind of, I think the policy questions in I guess 2017 Jack Reed and Susan Collins and requested from the Senate, the Senate requested research on what the impacts of self driving trucks would be. And the first stage of that was for the G. A. 02 To a report sort of looking at the lay of the land, talking to some experts. Um and I was working on my 2018 report, help contribute to that G. A. o. report and you know, I had the six scenarios right? I'm like okay, you know, here's here's what Starsky is doing, you know, here's what embark and Uber are doing, you know, um here's what Waymo might be doing, you know, nobody really knows right? Um Here's what Peloton is doing. Um you know, here's the autopilot scenario and then here's this one that I think actually could be good for drivers, so now you've got that driver who's got to, you know, two times the freight. Um Their decisions are more important, they're managing a more complex system, right? They're probably gonna have to have some global understanding of how to, you know, the environments in which you can operate safely right now, we're talking up skilling right? Um And so you know that the jail, you know, sort of rights up these different scenarios and the idea is that it's going to prepare for this Department of Transportation, Department of Labor set of processes to engage stakeholders and um and sort of get, you know get industry perspectives and then do a study on the labor impacts. So um you know that D. O. T. D. O. L. Process starts to happen and you know, I get to the workshop and a friend was sitting at the table next to me, Eddie holds up the scenarios that that they're going to have us discussed at this workshop and he's like, hey these look really familiar, right? Is they were the, you know, scenarios from, from the report but there were only five instead of </s>

<s>[INST] Let me sort of focus in on this relationship between the president or the leader and the intelligence agency. And look outside the United States. It seems like authoritarian regimes or regimes throughout history. If you look at Stalin and Hitler, if you look at today with Vladimir Putin, the negative effects of power corrupting the mind of a leader manifests itself is that they start to get bad information from the intelligence agencies. So that this kind of thing that you're talking about over time. They start hearing information they want, they want to hear the agency starts producing only um the kind of information they want to hear and they're the leaders Worldview starts becoming distorted to where the propaganda they generate is also the thing that the intelligence agencies provide to them. And so they start getting this, they start believing their own propaganda and start getting a distorted view of the world. Sorry for the sort of, uh, walking through in a weird way. But I guess I want to ask, do you think, let's look at Vladimir Putin specifically, do you think he's getting accurate information about the world? Do you think he knows the truth of the world? Whether that's the war in Ukraine, whether that's the behavior of the other nations in NATO, the United States in general, what do you think? [/INST] It's rare that I'll talk about just thinking, it's I I prefer to share my assessment, why I assess things a certain way rather than just what's my random opinion and my assessment, Vladimir Putin is winning. Russia is winning. They're winning in Ukraine, but they're also winning the battle of influence against the West, they're winning in the face of economic sanctions, they're winning empirically. When you look at the math, they're winning. So when you ask me whether or not Putin is getting good information from the Intelligence Services. When I look at my overall assessment of multiple data points, he must be getting good information. Do I know how or why? I do not? I don't know how or why it works there. I don't know how such deep cronyism, such deep corruption can possibly yield true real results? And yet somehow there are real results happening. So it's either excessive waste and an accidental win or there really is a system and a process there that's functioning. </s><s>[INST] So this winning idea is very interesting in what way, short term and long term as Russia winning. Some people say there was a miscalculation of the way the invasion happened. Uh, there was an assumption [/INST] that you </s><s>[INST] would be able to successfully take give, you'd be able to successfully capture the East, the south and the north of Ukraine. And with what now appears to be significantly insufficient troops spread way too thin across way too large of a front. So that seems to be like an intelligence failure. And uh, and that doesn't seem to be like winning in another way. It doesn't seem like winning. If we put aside the human cost of war, it doesn't seem like winning because the hearts and minds of the West were completely on the side of Ukraine. This particular leader in Volodymyr Zelensky captured the attention of the world and the hearts and minds of europe the West and many other nations throughout the world, both financially in terms of military equipment and in terms of sort of social and cultural and emotional support for the independence of this nation? That seems to be like a miscalculation? So against that pushback, why do you think there's still kernels of winning in this on the Russian side, [/INST] what you're laying out isn't incorrect and the miscalculations are not unexpected. Anybody who's been to a military college, including the army war college in pennsylvania where so many of our military leaders are brought up. When you look at the conflict in Ukraine, it fits the exact mold of what an effective long term military conflict. Protracted military conflict would and should look like for military dominance. Now did Zelinsky and did the, did the Ukrainians shocked the world? Absolutely. But in that they also shocked american intelligence, which like you said, miscalculated the whole world. Miscalculated how the Ukrainians would respond. Putin did not move in there accidentally. He had an assessment, He had high likelihood of a certain outcome And that outcome did not happen. Why did he have that calculation? Because in 2014 it worked, He invaded, he took primary in, in 14 days. He basically created uh, a uh, an infiltration campaign that turned key leaders over in the first few days of the conflict. So essentially there was no conflict. It worked in 2008, when he took Georgia. Nobody talks about that. He invaded Georgia the exact same same way and it worked. So in 2000 and it worked in 2014. It worked, there was no reason to believe it wasn't going to work again. So he just carried out the same campaign, But this time something was different. That was a miscalculation for sure on the part of Putin. And the reason that there was no support from the West because let's not forget there is no support. There is nothing other than the lend lease act which is putting Ukraine in massive debt right now. To the west, that's the only form of support they're getting from NATO or the United States. So if somebody believed Ukraine would win, if somebody believes Ukraine had a chance, they would have gotten more material support than just debt and we can jump into that anytime you want to. But the whole world miscalculated. Everybody thought Russia was gonna win in 14 days. I I said that they would win 14 days because that was the predominant calculation, once the first invasion didn't work, then the military does what professional militaries do, man? They re evaluate, they re reorganized leaders and then they, they take a new approach. You saw three approaches. The first two did not work. The first two campaigns against Ukraine did not work the way they were supposed to work. The third has worked exactly like it's supposed to work. You don't need Kiev to win. Ukraine. You don't need hearts and minds to win. Ukraine. What you need. Yeah, what you need is control of of natural resources, which they're taking in the East and you need access to the heart beat the blood flow of food and money into the country, which they're taking in the south. The fact that Ukraine had to go to the negotiation table with Russia and Turkey in order to get exports out of the Black Sea approved again, demonstrates just how much Ukraine is losing. The, the aggressor had a seat at the negotiation table to allow Ukraine the ability to even export one of its top exports. If Russia would have said no, then they would not have had that Russia has, that's like someone holding your throat. It's like somebody holding your jugular vein and saying, if if you don't do what I tell you to do, then I'm not gonna let you breathe. I'm not gonna let blood flow to your brain. </s>

<s>[INST] Yeah, the fighting, the fighting thing is uh I think Youtube and twitter and Facebook are providing an incredible service to the world and they're all making mistakes of course, but they're doing an incredible job, you know, that I think deserves to be applauded and there's some degree of gravity, like it's a cool thing that that that's created and uh it shouldn't be monolithically fought against like facebook is evil or so on. Yeah, I might make mistakes, but I think it's an incredible service. I think it's world changing. Uh I mean I've I think facebook has done a lot of incredible, incredible things by bringing for example identity. You're like uh allowing people to be themselves, like their real selves in uh in the digital space by using their real name and the real picture. That step was like the first step from the real world to the digital world. That was a huge step that perhaps will define the 21st century and thus creating a digital identity. And there's a lot of interesting possibilities there that are positive of course, some things that are, are negative and having a good dialogue about that is great and I'm great that people like you are at the center of the teletext. That's awesome. [/INST] Right? I think it also um I also can understand, I think actually in the past, especially in the past couple of years um this rising awareness has been helpful like uses are also more and more recognizing that privacy is important to them. They should um maybe right, they should be owners after data. I think this definitely is very helpful and I think also this type of voice also and together with the regulatory framework and so on, also hope the companies to essentially put these type of issues at a higher priority and knowing that, but also it is their responsibility to to ensure that users are well protected. So I think it definitely the writing voice is super helpful and I think that actually really has brought the issue of data privacy and even the consideration of data ownership to the forefront to really much wider community. Um and I think more of this voice is needed, but I think it's just that we want to have a more constructive dialogue um to bring both sides together to figure out constructive solution. </s><s>[INST] So, another interesting space where security is really important is in the space of uh any kinds of transactions, but it could be also digital currency. So, can you maybe talk a little bit about Blockchain? Can you tell me what is a [/INST] Blockchain, I think the Blockchain where it itself is actually very overload this uh in general. Right? Yes. So in general and talk of Blockchain, we refer to this distributed luxury in a decentralized fashion. So essentially you have in the community often knows that come together and even though each one may not be trusted and as ELISA certain thresholds after set of nose, he behaves properly, then the system can essentially achieve certain properties. For example, in the distribute legislating you have you can maintain an immutable log and you can ensure that for example the transactions actually I agreed upon and then it's immutable and so on. </s><s>[INST] So first of all, what's the ledger? So it's a [/INST] it's like a database, it's like a data entry. </s><s>[INST] And so distributed ledger is something that's maintained across or is synchronized across multiple sources, multiple notes. And so where is this idea? How do you keep? So it's important ledger, a database to keep that uh to make sure. So what are the kinds of security vulnerabilities that you're trying to protect against in the context of the of a distributed ledger? [/INST] So in this case for example you don't want some malicious knows to be able to change the transaction logs and in certain cases called double spending, like you also cause you can also cause different views in different parts of the network and so on. </s><s>[INST] So the ledger has to represent if you're capturing like financial transactions as to represent the exact timing and exact occurrence and no duplicates all that kind of stuff. It has to be uh represent what actually happened. Okay so what are your thoughts on the security and privacy of digital currency? I can't tell you how many people write to me to interview various people in the digital currency space. There seems to be a lot of excitement there. Uh and it seems to be some of it, to me from an outsider's perspective, seems like dark magic. I don't know how secure. I think the foundation from my perspective of digital currencies that is you can't trust anyone. So you have to create a really secure system. So can you maybe speak about how what your thoughts in general about digital currency is and how you how it can possibly create financial transactions and financial stores of money in the digital space. [/INST] So you ask about security and privacy. And so so again as I mentioned earlier in security, we actually talked about two main properties um the integrity and confidentiality and so there's another one for availability, you want the system to be available. But here for the question you asked, let's just focus on integrity and confidentiality. So so for integrity of this distribution, essentially as we discussed, we want to ensure that the different notes uh right, so they have this consistent view usually is done through, we call a consensus critical uh that's the established this shared view on this legend and that you cannot go back and change it is immutable and so on. So so in this case then the security often refers to this integrity property. And essentially you're asking the question how much work, how how can you attack the system so that uh the an attacker can change the lock for example. </s>

<s>[INST] That's really interesting. There is of course several levels you can do the kind of synthesis and that does require a lot of both. Broad and deep thinking is exceptionally valuable. You could also public, I'm working on something with Andrew Huberman now, you can also publish synthesis. Um that's like review papers, they're exceptionally valuable for the communities. It brings the community together, tells the history, tells a story where the community has been. It paints a picture of where the path ladies for the future. I think it's really valuable. And Richard Dawkins is a good example of somebody that doesn't in book form that he kind of walks the line. Really interestingly you have like somebody who like Neil Degrasse Tyson who is more like a science communicator. Richard Dawkins sometimes a science communicator. But he gets he gets like close to the technical to where it's a little bit, it's not shying away from being really a contribution to science. [/INST] No, he's made he's made real contributions um in </s><s>[INST] book form. He really fascinating. I mean, Roger Penrose a similar, similar kind of idea. That's interesting. That's interesting, synthesis does not especially synthesis work work that synthesizes ideas does not necessarily need to be pure reviewed. It's peer reviewed. Bye piers reading it well and reviewing it. [/INST] That's it. It is reviewed by peers. Which is not synonymous with peer review. And that's the thing is people don't understand that the two things aren't the same right. Peer review is an anonymous process that happens before publication in a place where there is a power dynamic. The joke, of course is that peer review is actually pure preview, write your biggest competitors get to see your work before. It's used the light of day and decide whether or not it gets published. And, you know, again, when your formative experience with the publication apparatus is the one I had with the telomere paper. There's no way that that seems like the right way to advance important ideas. And you know, what's the harm in publishing them so that your peers have to review them in public where they actually, if they are going to disagree with you, they actually have to take the risk of saying, I don't think this is right and here's why right with their name on it. I'd much rather that it's not that I don't want my work reviewed by peers, but I want it done in the open. You know, for the same reason you don't meet with dangerous people in private. You meet at the cafe. I want the work reviewed out in public. </s><s>[INST] He asked you a difficult question. Sure there is popularity and martyrdom. This popularity in pointing out that the emperor has no clothes that can become a drug in itself. Yeah, I've confronted this in scientific work I've done at M. I. T. Where there are certain things that are not done well, people are not being the best version of themselves and particular aspects of a particular field um are in need of a revolution. And part of me wanted to point that out versus doing the hard work of publishing papers and doing the revolution basically just pointing out, look, you guys are doing it wrong and they're just walking away. Are you aware of the drug of martyrdom of uh the the ego involved in it, that it can cloud your thinking [/INST] probably one of the best questions I've ever been asked. So let me let me try to sort it out. First of all, we are all mysteries to ourself at some level. So it's possible there's stuff going on in me that I'm not aware of that's driving, but in general, I would say one of my better strengths is that I'm not especially ego driven. I have an ego, I clearly think highly of myself, but it is not driving me. I do not crave that kind of validation. I do crave certain things. I do love a good Eureka moment. There is something great about it and there's something even better about the phone calls you make next when you share it. It's pretty, it's pretty fun, right? I really like it. I also really like my subject, right? There's something about a walk in the forest when you have a toolkit in which you can actually look at creatures and see something deep, right? I like it. That drives me and I could entertain myself for the rest of my life if I if I was somehow isolated from the rest of the world, but I was in a place that was biologically interesting. You know, hopefully I would be with people that I love and pets that I love, believe it or not. But you know, if I were in that situation and I could just go out every day and look at cool stuff and figure out what it means. I could be all right with that. So I'm not heavily driven by the um, the ego thing, as you put it. </s><s>[INST] So I I I'm completely the same, except instead of the past, I would put robots, but so it's not it's the Eureka, it's the exploration of of the subject that brings you joy and fulfillment. It's not the ego. [/INST] Well, there's there's more to say, no, I really don't think it's the ego thing. Um I will say I also have kind of a secondary passion for robot stuff. I've never made anything useful, but I do believe, I believe I found my calling, but if this wasn't my calling, my calling would have been inventing stuff. I really I really enjoy that too. So, I I get what you're saying about the analogy quite quite well, um as far as the martyrdom thing, I Mhm. I understand the drug you're talking about and I've seen it more than I felt it, I do if I'm just to be completely candid and that this question is so good. It deserves a candid answer. I do like the fight, right? I like fighting against people I don't respect and I like winning, but I have no interest in martyrdom. One of the reasons I have no interest in martyrdom is that I'm having too good a time, right? I very much enjoy my life and </s>

<s>[INST] So that's the difference between cultures. Let me open another door. I'm not sure I want to open but the difference between men and women, is there a difference between the emotional lives Of those two Categories of Biological Systems? [/INST] So here's what I would say. You know, we did a series of studies Um uh in the 1990s where we asked men and women to tell us about their emotional lives and women describe themselves as much more emotional than men. They believed that they were more emotional. Men and men agreed women are much more emotional than men. Okay and then we gave them little handheld computers. These were little Hewlett Packard computers, they fit in the palm of your hand a couple of they wait a couple of pounds. So this was like pre Palm pilot. Even like this was you know 19 nineties and like early and um we um ask them we would you know paying them Like 10 times a day and just asked them to report how they were feeling which is called experience sampling. So we experience sampled and and then at the end and then we looked at their reports and we found is that men and women basically didn't differ. And there were some people who were really had many more instances of emotion. So they were, you know, um they were treading water in a tumultuous sea of emotion. And then there were other people who were like floating tranquilly, you know, in a lake. It was a really not perturbed very often and everyone in between, but there were no difference between men and women. And the really interesting thing is that the end of the sampling period we asked people um so reflect over the past two weeks and tell it. So, you know, we've been now pinging people like again and again and again. Right, So tell us how emotional do you think you are no change from the beginning? So men and women believe that they are, they believe that they are different. And when they are looking at other people, they make different inferences about emotion. If a man, if a man is scowling, like if you and I were together and some so somebody is watching this okay. And yeah, okay, by </s><s>[INST] the people love it when you look at the camera, [/INST] um if you and I make exactly the same set of facial movements. When people look at you, both, men and women look at you, they are more likely to think, oh, he's reacting to the situation and when they look at me, they'll say, oh, she's having an emotion. She's you know. Yeah. And I wrote about this actually um uh right before the 2016 election. </s><s>[INST] You know, maybe I could confess. Let me try to carefully confess. [/INST] But you are really going to </s><s>[INST] Yeah. That that when I that there is an element when I see Hillary clinton, that there was something annoying about her to me. And I just that feeling. And then I tried to reduce that to what? What is that? Because I think the same attributes that are annoying about her when I seen other people wouldn't be annoying. So I was trying to understand what is it? Because it certainly does feel like that concept that I've constructed in my mind. Well, [/INST] I'll tell you that, I think, well, let me just say that um that what you would predict about, for example, the performance of the two of them in the debates. And I wrote an op ed for the new york Times, actually, um before the second debate. And it played out really pretty much as I thought that it would be based on research. It's not like I'm like a great fortune teller or anything. It's just I was just applying the research, which was that when a woman, um a woman's um people make internal attribution, it's called they infer that the facial movements and body posture and vocalizations of a woman reflect her interstate. But for man, they're more likely to assume that they reflect his response to the situation. It doesn't say anything about him. It says something about the situation he's in now for the thing that you are that you were describing about Hillary clinton. I think a lot of people experienced. But it's also in line with research which shows and and particularly research actually on about teaching evaluations is one place that you really see it, where the expectation is that a woman will be nurturing and that a man there's just no expectation for him to be nurturing. So he's you know if he is nurturing, he gets points. Um if he's not he gets points, they're just different points, right? Whereas for a woman, especially a woman who is an authority figure, she's really in a catch 22 because if she's serious she's a bit and if she's empathic uh then she's weak. </s><s>[INST] That's brilliant. I mean one of the bigger questions to ask here. So that's one example where our construction of concepts gets [/INST] right. But member. But so remember I said science is a science and philosophy or like tools for living. So I learned recently that if you ask me what is my intuition about what regulates my eating. I will say carbohydrates. I love carbohydrates, I love pasta, I love bread. I love I just love carbohydrates. But actually research shows and it's beautiful research. I love this research because it's so violates my own like deeply, deeply held beliefs about myself that most animals on this planet who have been studied and there are many actually eat to regulate their protein intake. Uh huh. So you will overeat carbohydrates if you in order to get enough protein and these this research has been done with human very beautiful research with humans with crickets with like you know bonobo, I mean just like all these different animals not be nervous, but I think like baboons um now that I have no intuition about that and I even now as I regulate my eating, I do I still have I just have no intuition. It just I can't I can't feel it. What I feel is only about the carbohydrates. </s>

<s>[INST] I did this recently with Star Trek Discovery on UK netflix. Mostly because I wonder what it's like to live in London. I'm thinking of moving from boston to a place where I can build the business. I've always dreamed of building London. It's probably not in the top three, but top 10 for sure. The number one choice currently is austin for many reasons that I'll probably speak to another time. SaN Francisco unfortunately dropped off from the number one spot but it's still in the running. If you have advice, let me know anyway, check out expressive PM unless you change your location to almost 100 countries and it's super fast. Go to Express VPN dot com slash flex pod to get an extra three months of express VPN for free? That's express VPN dot com slash lex pod. And now here's my conversation with James Gosling. [/INST] I've </s><s>[INST] read somewhere that the square of two is your favorite irrational number. [/INST] I have no idea where that got started. </s><s>[INST] Um Is there any truth to it? Is there anything in mathematics or numbers that you find beautiful? [/INST] Oh there's lots of things in in math. It's really beautiful. Um you know, I, I used to consider myself really good at math and these days I consider myself really bad at math. I never really had a thing for the square root of two but when I was a teenager there was this book called the Dictionary of curious and interesting numbers which for some reason I read through and damn near memorized the whole thing and I started this weird habit of when I was like filling out checks, you know or you know paying for things with credit cards. I would want to make the, the receipt add up to an interesting number. </s><s>[INST] Is there some numbers that stuck with you that just kind of make you feel good? [/INST] They'll have a story and fortunately I've actually mostly forgotten all of them. Yeah. Um </s><s>[INST] Are they so like 42. [/INST] Well yeah, I mean that was 42 is pretty magical </s><s>[INST] and then the rationals I mean, but is there a squared of two story in there somewhere? How does that? [/INST] It's like the only number that has destroyed religion </s><s>[INST] in which way? [/INST] Well the path a gory ins, they believe that all numbers were perfect and you could represent anything as as as a rational number. And um in that in that time period um does this proof came out that there was no you know, rational fraction whose value is equal to the square root of two? </s><s>[INST] And that that means nothing in this world is perfect. Not even mathematics. [/INST] Well, it means that your definition of perfect was imperfect. </s><s>[INST] Well then there's the gato incompleteness theorems in the 20th century that ruined it once again for everybody. [/INST] Yeah. Although although although girdle serum, um you know the lesson I take from girdles serum is not that you know, there are things you can't know which is fundamentally what it says. Um But you know, people want black and white answers, they want tour false. Um But if you if you allow a three state logic that is true false or maybe then then life is good. </s><s>[INST] I feel like there's a parallel to modern political discourse in there somewhere. But [/INST] I mean </s><s>[INST] let me ask uh so with your kind of early uh love or appreciation of the beauty of mathematics, do you see a parallel between that world and the world of programming? [/INST] You know programming is all about logical structure, understanding the patterns that come out of computation, understanding sort of, I mean it's often like, you know the path through the graph of possibilities to find a short short route </s><s>[INST] meaning like uh find a short program that gets the job done I think. But so then on the topic of irrational numbers, do you see D. C. Programming, you just painted it so cleanly? Uh It's a little this trajectory to find like a nice little program, but do you see it as fundamentally messy? Um Maybe I'm like mathematics, [/INST] I don't think of it as, I mean, I mean you know, you watch somebody who's good at math, do math and you know often it's it's fairly messy sometimes it's kind of magical. Um when I was a grad student um one of the students, his name was Jim Sachs was he had this this this this this reputation of being sort of a walking talking human, uh we're improving machine. And if you were having a hard problem with something, you could just like a costume in the hall and say jim. But and and he would do this this this funny thing where he would stand up straight, his eyes would kind of be focus, he uh you know, just just like you know like like something in today's movies, he just uh and then straighten up and say and log in and walk away and you go, well, okay so in Logan is the answer. How did he get there by which time he's, you know, down the hallway somewhere? </s><s>[INST] Yeah, he's just the oracle, the black box. It just gives you the answer. [/INST] Yeah. And then you have to figure out the path from the question to the answer. </s><s>[INST] I think in one of the videos I watched, you mentioned don can youth uh well at least recommending is uh, you know, his book is something people should read. But in terms of, you know, theoretical computer science, do you, do you see something beautiful that has been inspiring to you? Speaking of n Logan in your work on programming languages? That's in the, in the whole world of algorithms and complexity and you know, these kinds of more formal mathematical things or did that not really stick with you in your programming life? [/INST] It did stick pretty clearly for me because one of the things that I care about is being able to sort of look at a piece of code and be able to prove to myself that it works. And, and you know, so, so for example, I find that um, I'm, I met odds with many of the people around me over um, issues about like how you layout a piece of software. Right? So so software engineers get really cranky about how they format their the documents that are the programs, you know, where they put new lines and where they put the braces braces and all the rest of that. And I tend to go for a style that's very dense uh </s>

<s>[INST] So this this wearable sensor that's looking skin conductance can capture sort of the ripples of the complexity of what's going on in our brain. So this this little device, you have a hope that you can start to get the signal from the, from the interesting things happening in the brain. [/INST] Yeah, we've already published the strong correlations between the size of this response and the flattening that happens after words. And unfortunately also in a real studio case where the patient died because the, well, we don't know why we don't know if somebody was there, it would have definitely prevented it. But we know that most students happened when the person is alone. And uh in this case a suit up is an acronym S. U. D. P. And it stands for the number two cause of years of life lost actually among all neurological disorders and stroke is number one suit up as number two. But most people haven't heard of it. Actually. I plug my ted talk. It's on the front page of ted right now that talks about this and uh we hope to change that. I hope everybody who's heard of SIDS and stroke will now hear a suit up because we think in most cases it's preventable if people take their meds and aren't alone when they have a seizure, not guaranteed to be preventable. There are some exceptions but we think most cases probably are. </s><s>[INST] So you have this embrace now in the version two wristband. Right. Uh for epilepsy management, that's the one that's FDA approved. [/INST] Yes. </s><s>[INST] Which is kind of a cleared cleared. Sorry. [/INST] It's okay. It essentially means it's approved for marketing. </s><s>[INST] Got it. Just a side note, how difficult is that to do? It's essentially getting FDA [/INST] agonizing. Computer </s><s>[INST] science technology. [/INST] It's so agonizing. It's much harder than publishing multiple papers And top medical journals. Yeah we published peer reviewed, top medical journal neurology best results and that's not good enough for the FDA </s><s>[INST] is that system. So if we look at the peer review of medical journals there's flaws. Their strengths. Is the FDA approval process. How does it compare to the peer review process? Is it have the strength [/INST] and peer review over FDA any day? </s><s>[INST] But is that a good thing? Is that a good thing for FDA you're saying? Does it stop some amazing technology from getting through? [/INST] Yeah, it does. The FDA performs a very important good role in keeping people safe. They keep things, they put you through tons of safety testing and that's wonderful. And that's great. I'm all in favor of the safety testing. Sometimes they put you through additional testing that they don't have to explain why they put you through it and you don't understand why you're going through it and it doesn't make sense. And that's very frustrating. Uh and maybe they have really good reasons and they just would, it would do people a service to articulate those reasons transparent. Be more transparent. </s><s>[INST] So as part of M Patika you have sensors. So what kind of problems can we crack? But what kind of things from seizures to autism? two, I think I've heard you mentioned depression. What kind of things can we alleviate? Can we detect? What's your hope of what, how we can make the world a better place with this wearable tech. [/INST] I would really like to see my fellow brilliant researchers step back and say, you know, what are, what are the really hard problems that we don't know how to solve that come from people? Maybe we don't even see in our normal life because they're living in the poorer places, they're stuck on the bus there. They can't even afford the uber the lift or the data plan or all these other wonderful things we have that we keep improving on. Meanwhile there's all these folks left behind in the world and they're struggling with horrible diseases with depression, with epilepsy, with diabetes with just awful stuff that uh maybe a little more time and attention hanging out with them and learning, what are their challenges in life? What are their needs? How do we help them have job skills? How do we help them have a hope and a future and a chance to have the great life that so many of us building technology have. And then how would that reshape the kinds of ai that we build? How would that reshape the new, You know apps that we build are the maybe we need to focus on how to make things more low cost and green instead of $1,000 phones. I mean come on. You know why can't we be thinking more about Things that do more with less for these books, quality of life is not related to the cost of your phone? You know it's not something that you know it's been shown that what about $75,000 of income. And happiness is the same. Okay. However, I can tell you you get a lot of happiness from helping other people Get a lot more than $75,000 buys. So how do we connect up the people who have real needs with the people who have the ability to build the future and build the kind of future that truly improves the lives of all the people that are currently being left behind. </s>

<s>[INST] Okay, so embrace the homeless of the circuitry. But what back to the question of starting knowing nothing the disease and and going to the treatment. So the next steps. [/INST] So you basically have to first figure out the tissue and then described how you figure out the tissue. You figure out the tissue by taking all of these non coding variants that are sitting outside proteins and then figuring out what are the ePA genomic enrichments and the reason for that, you know, thankfully, is that there is convergence that the same processes are impacted in different ways by different laws. I and that's a saving grace for our field. The fact that if I look at hundreds of genetic variants associated with Alzheimer's, they localize in a small number of processes. </s><s>[INST] Can you clarify why that's hopeful. So, like they show up in the same exact way in the in the specific set of processes. [/INST] So basically there's a small number of biological processes that underlie or at least I play the biggest role in every disorder. So, in Alzheimer's you basically have maybe 10 different types of processes. One of them is lipid metabolism. One of them is immune cell function. One of them is neuronal energetic. So these are just a small number of processes. But you have multiple lesions, multiple genetic perturbations that are associated with those processes. So if you look at schizophrenia, it's excitatory neuron function. It's inhibitor in urine function. It's synaptic pruning, it's calcium signaling and and so forth. So when you look at disease genetics, you have one hit here and one hit there and one hit there and one hit, they're completely different parts of the genome. But it turns out all of those he hits are calcium signaling proteins. You're like ha ha, that means that counseling signaling is important. So, those people who are focusing on one box at a time cannot possibly see that picture. You have to become a genome assist. You have to look at the comics, the um the holistic picture to understand these enrichments. But </s><s>[INST] you mentioned the convergence things the whatever the thing associated with the disease shows up. [/INST] So let me explain convergence. Convergence is such a beautiful concept. So you basically have these four genes that are converging on calcium signaling. So that basically means that they are acting each in their own way but together in the same process. But now in every one of these lows i you have many enhancers controlling each of those genes. That's another type of convergence where this regulation of seven different enhancers might all converge on this regulation of that one gene which then converges on calcium signaling. And in each one of those enhancers you might have multiple genetic variants distributed across many different people. Everyone has their own different mutation. But all of these mutations are impacting that enhancer and all of these enhancers are impacting that gene and all of these genes are impacting this pathway. And all these pathways are acting in the same tissue and all of these tissues are converging together on the same biological process of schizophrenia. </s><s>[INST] And uh you're saying the saving grace is that that convergence seems to happen for a lot of these diseases [/INST] for all of them basically that for every single disease that we've looked at we have found an empty genomic enrichment. How do you do that? You basically have all of the genetic variants associated with the disorder. And then you're asking for all of the enhancers active in a particular tissue For 540 disorders. We've basically found that indeed, there is an enrichment that basically means that there is commonality and from the commonality we can just get insights. So, to to explain in mathematical terms, we're basically building an empirical prior. We're using a beige in approach to basically say, great, all of these variants are equally likely in a particular locus to be important in a So in a genetic locus, you basically have a dozen variants that are co inherited because the way that inheritance works in the human genome is through all of these recombination events during mitosis. You basically have, You know, you inherit maybe three chromosome three, for example, in your in your body is inherited from four different parts. One part comes from your dad. Another part comes from your mom. Another part comes from your dad and other part comes from your mom. So basically the way that it uh from your mom's mom. So you basically have one copy that comes from your dad and one copy that comes from your mom. By that copy that you got from your mom is a mixture of her maternal and her paternal chromosome and the copy that you got from your dad is a mixture of his maternal and his paternal chromosome. So these break points that happen when chromosomes are lining up, lining up are basically ensuring through these crossover events there, ensuring that every uh child cell during the process of mitosis where you basically have, you know, one spermatozoa, it that basically couples with one oval to basically create one egg to basically create a zygote. You basically have half of your genome that comes from that and have your genome that comes from. Um But in order to light up not line them up, you basically have this crossroad events. This crossroads where events are basically leading to co inheritance of that entire block coming from the your maternal grandmother and that entire blog coming from the material grand grandfather over many generations. These crossover events don't happen randomly. There's a protein called p. r. d. m. nine that basically guides the double stranded breaks and then leads to these crossovers. And that protein has a particular preference to only a small number of hotspots of recombination, which then leads to a small number of breaks between these co inheritance patterns. So even though there are six million variants, there are six million los I. There's you know, this variation is inherited in blocks and every one of these blocks has like two dozen genetic variants that are all associated during the case of F. T. O. It wasn't just one variant, it was 89 common variants that were all humongously associated with obesity, which ones of those is the important one. Well, if you look at only one lock is you have no idea. But if you look at many lows I you basically say aha all of them are enriching in the same epidemiologic map. In that particular case it was mesenchymal stem cells. So these are the progenitor cells that give rise to your brown fat and your white fat </s>

<s>[INST] out an ugly side in us. You describe an ideal lab as being opposite of echo chambers. So we know what echo chambers are and you said there's basically no good term for the opposite of an echo chamber. So what's an ideal lab. [/INST] Well, first of all, both of these, we think of an echo chamber as, like, a group maybe or even a place, but it's a culture, it's an intellectual culture. And this goes along with the high-rung, so high-rung and low-rung thinking is individual. That's what I was talking about, what's going on in your head. But this is very connected to the social scene around us. And so groups will do high rung and low rung thinking together. Basically it's collab, so an echo chamber to me is a collaborative low rung thinking. It is, it's a culture where the cool, it's based around a sacred set of ideas. And it's the coolest thing you can do in an echo chamber culture is talk about how great the sacred ideas are and how bad and evil and stupid and wrong the people are who have the other views. And it's quite boring, it's quite boring because it's very hard to learn and changing your mind is not cool in an echo chamber culture, it makes you seem wishy washy, it makes you seem like you're waffling and you're flip-flopping or whatever, showing conviction about the sacred ideas in echo chamber culture is awesome if you're just like, obviously this makes you seem smart while being humble makes you seem dumb. So now flip all of those things on their heads and you have the opposite which is idea lab culture which is collaborative high rung thinking. It's collaborative truth finding but it's also just, it's just a totally different vibe. It's a place where arguing is a fun thing, it's not, no one's getting offended and criticizing like the thing everyone believes is actually it makes you seem like interesting like, oh really, why do you think we're all wrong and expressing too much conviction makes people lose trust in you. It doesn't make you seem smart, it makes you seem stupid if you don't really know what </s><s>[INST] you're talking about but you're acting like you do. I really like this diagram of where on the x-axis agreement on the y-axis is decency, that's in an idea lab in an echo chamber there's only one axis, it's asshole to non-asshole. Right. This is a really important thing to understand about the difference between, you call it [/INST] decency here, about assholishness and disagreement. So my college friends, we love to argue, right? And no one thought anyone was an asshole for, it was just for sports. Sometimes we'd realize we're not even disagreeing on something and that would be disappointing and be like, oh, I think we agree. And it was kind of like sad, it was like, oh well, there goes the fun. And one of the members of this group has this, she brought her new boyfriend to one of our like hangouts and there was like a heated, heated debate, you know, just one of our typical things. And afterwards, the next day, he said like, is everything okay? And she was like, what do you mean? And he said, like, after the fight and she was like, what fight? And he was like, you know, the fight last night. And she had to. And she was like, you mean like the arguing? And he was like, yeah. And so that's someone who was not used to idea lab culture coming into it. And seeing it as like, that was like, this is like, are they still friends? Right? And idea lab is nice for the people in them. because individuals thrive. You don't want to just conform. It makes you seem boring in an idea. But you want to be yourself. You want to challenge things. You want to have a unique brain. So that's great. And you also have people criticizing your ideas, which makes you smarter. It doesn't always feel good, but you become more correct and smarter. And Echo Chamber is the opposite, where it's not good for the people. And you're learning skills atrophy. And I think it's boring. But the thing is, they also have emergent properties. So the emergent property of an ideal lab is like super intelligence. Just you and me alone. Just the two of us. If we're working together on something, but we're being really grown up about it. We're disagreeing. We're not, you know, no one's sensitive about anything. We're going to each find flaws in the other one's arguments that you wouldn't have found on your own. And we're going to have double the epiphanies, right? So it's almost like the two of us together is like as smart as 1.5. It's like 50% smarter than either of us alone, right? So you have this 1.5 intelligent kind of joint being that we've made. Now bringing a third person in, fourth person in, right? You see, it starts to scale up. This is why science institutions can discover relativity and quantum mechanics and these things that no individual human, you know, was going to come up with without a ton of collaboration because it's this giant ideal lab. So it has an emergent property of super intelligence. And Echo Chamber is the opposite, where it has the emergent property of stupidity. I mean, it has the emergent property of a bunch of people all, you know, paying fealty to this set of sacred ideas. And so you lose this magical thing about language and humans, which is collaborative intelligence, you lose it, it disappears. </s>

<s>[INST] nothing like anything, you [/INST] know? So as we turn, we are, well let's just go back because now I gotta put on my real hat, which we have to train because we're getting ready to deploy to, you know overseas. So we gotta get our training done. So that's my mindset, especially as a ceo because I gotta get get it training out of the flight time because I'm responsible to do that. So let's go back. And the the guy who's gonna be the bad guys is the ceo of the marine squadron. And uh so cheeks is at the end, he's listening to all this happened, you know, because he's just like, because he, when he first went out they were gonna do him. But the little hornets, the legacy hornets, f 18 sees don't have as much gas as the super hornets. So he had launched first and they were gonna do him. And then when they knew we were off the deck, they just told him I go to your cat point down south and we're going to send, we'll pass this off to the supermarkets. The cat point, that's where we hold. So it's called a combat Air patrol point. So we're just gonna hold at one end, he's going to hold at the other end. It's kind of like, hey you guys are gonna, it's thinking it's a football field, we're gonna sit on one goal line, he's gonna sit on the other goal line. And when they say go, we're gonna run at each other and try and do something in the middle of the field and then go back to our set reset points. Okay. </s><s>[INST] So you're talking to him, he's listening, [/INST] he's just listening, we don't talk to him at all. He's just listen, he just dials up because they know that we all know the frequency. So he's listening to what's going on. Cause he's like because they canceled training. So what else is he gonna do? He's just gonna hang out there and do circles while he's waiting him and his wingman. So they're just they're listening to all this go on. </s><s>[INST] And then at this point you move on. [/INST] Yeah, we come back up to train, we go back as we're flying back the controller because we're talking to the kid on the Princeton, the the uh the they're called Osso operations specialists. They are the ones that run the radars and we're talking to him and he's like, hey, so you're not gonna believe this? But that thing is at your cap, It showed back up, it just popped up. This is like 60 miles away. It just reappears were like, Okay, so we got the radars that we're looking for it, we get out there, we never see it, we never see it again. Uh We do what we need to do. We come back to the ship of course now we're like, oh this is gonna be well you know I told I told him I go, do you know we're gonna catch, we're gonna catch ship for this when we get back to the ship. Word's gonna get out and we're just gonna catch maximum ship? And we did. And it's it's kind of that joking, you know, so the ship plays movies, we have movies on the boat and they do 12 hours of movies so they repeat because there's a day checking the night check. So the same movies in the morning and night place. So you never get to ever get to watch a whole movie on the boat, which drives my wife crazy because I watch stuff on T. V. That way too. I'll be like oh hey I've seen this and I'll jump into a movie in the middle and then I'll pick it up later and I'll see the beginning and I'll put it all together uh Because that's how we have to do it because we're so busy. Well the movies became and I was Men in Black aliens. Uh Independence Day, </s><s>[INST] definitely going to catch some ship. We didn't. But let let let me just ask some dumb questions. So just take it because whatever whatever the heck you saw, whatever the heck happened, it's, you know, one of the most fascinating things um events in recent history. So whatever it was, it's interesting to talk about the different kinds of angles, there's no good answers, but it's interesting to ask some dumb questions here. Uh So first of all you mentioned you saw at some point X. Y. And then uh somebody in the Princeton said you're not gonna believe this sir? It's at your cat point. That's a different place. How the heck did it know what your cat point [/INST] is? That's a good question. That's the one if you don't know when you know you don't we don't tell it we don't broadcast that we have a way point in the system. But I don't know maybe it knew where we were because we use the same one day after day after day. But it obviously knew what you </s><s>[INST] never saw it there [/INST] never sought their chad when he took off when he got the video we landed we told them hey look we just we just chased this thing. They're like when I go chase it and they're like why go dude I go and I told him I said dude get video and he goes and so and that's how he is he's like I'm gonna go and he was he he was determined he was gonna find this thing. So when you look at his video and this is the stuff that isn't out that they don't see. Because not all the all you see is the flare tape. That's the targeting pod, the forward looking infrared receiver. </s><s>[INST] Um I'll probably overlay the video when he when [/INST] he goes out it's uh you know what he's looking at on his displays is he has basically two radar displays up. He has asthma. And range on the right one. And he has azimuth and elevation on the left one. So this is called the Azle display and this is called. This is basically the P. P. I. Which is the you're at the bottom of it you're at the bottom of the square. It's it's really taken this it's taken a cone because the radar really looks left and right from a point and it squares it out. So the entire bottom of the scope that we look at is us because they do this they squared off. So so he goes out and when he first sees it he gets a radar return on it because when he's not trying to lock it so the radars just throwing energy out and getting it. You know it's a Doppler radar. So when it's in search mode that's all it's doing it's going how I can see you I can see and it's looking for return. So he gets a return so he wants to see what it is. Because all you get is a little green square. Unless it builds a track file on it. But the little green square is just sitting there it's not moving because it's sitting in one spot in space. He locks it up when he goes to lock it up. Now he's putting a bunch of energy on it. He's telling the radar stare down that line of sight and whatever is there. I want you to grab it and build a track file on it which will tell us how high it is, how fast it is in the direction that it's going okay. The radar smart enough that when the signal comes back if it's been messed with it will tell you it'll give you indications that I'm being jammed. So that's all it is is you send a signal out something, it manipulates the signal either in range and velocity or whatever and it sends it back and the radar was smart enough to go. That is not a return and I'm expecting something is messing with me. I'm being jammed and it shows you and it puts strobes up. It gives these lines on the radar and it does some stuff so you can I mean well it does it goes full into it's being jammed at about every mode you can possibly see because everything comes up and the this aspect gets long. It's all kinds of, I don't want to get into details but you can tell it's being jammed. So as you said are </s>

<s>[INST] eventually, Do you think there is concrete groups? Like is it as simple as the two groups of blue and red? [/INST] No, it's it's it's it's also very fluid because you and I are allied as jewish people, as Russians, as males, as podcasters, you're an academic, I'm not there. So that's where we're different, but we each are a Venn diagram even within ourselves. And I can talk to you about politics and then we can talk about Russia stuff and then you can talk about your your work, which I don't know anything about. So that would be what you're way up here in our way down here. So there's lots every relationship with just between individuals. There's it's very dynamic. </s><s>[INST] So how do we succeed? Like how do we form individual states? Sure there's a little bit more cohesion. Sure, [/INST] the voluntary cohesion to the first step is to um eliminate and the concept of political authority as legitimate and to denigrate and humiliate those who would put themselves in a position in which they are there to tell you how to live your life from any semblance of validity and that's starting to happen. Um If you look at what they had with the lockdowns, cuomo and de Blasio in new york, we have it. I was uh tired a couple weeks ago and I said to my friend, oh just click nape of covid and he goes, it's not possible. Like what do you mean? And he goes, We haven't had any deaths in like two months? And there's only 100 cases a day for like two months. And I go, you're exaggerating because everything was still closed. And I looked at the numbers and he wasn't exaggerating. And there's no greater american dream to me than an immigrant family comes to the States forms their own little business. Maybe mom's a good cook at the restaurant, dry cleaner fruit stand and those people aren't gonna have a lot of money. Those are the first ones who lost their companies because of these lockdowns. Uh they cuomo who is the governor of new york, opened up the gyms, he said, you're clear to open up De Blasio said, and we don't have enough inspectors, you're gonna have to wait another couple of weeks uh to regard that as anything other than literally criminal. Is something that I am having a hard and harder time wrapping my head around </s><s>[INST] you said, I mean, that's something I'm deeply worried about as well, which is like thousands. It's actually millions of dreams being crushed. That american dream of starting a business of running a business. [/INST] What about all the young people who you and I have in our audiences who are socially isolated at best and now they can't leave their homes uh isolation and ostracism are things that are very well studying psychology, These have extreme consequences. I read a book called ostracism and this wasn't scientific, but basically the author was a psychiatrist, psychology, whatever. And he had one of his colleagues, they didn't experiment, let's for a week, you ostracized me completely, we know it. And he goes even knowing it's the experiment. The fact that he wouldn't make eye contact with me. And the fact that he ignored me had an extreme emotional impact on me knowing full well this is purely for experimental purposes. Now you multiply that by all these the suicide, the number of kids who think about suicide was through the roof during all this. Uh and my point is, until these people, It's gonna be pretty like 20, that's where we're gonna have to start having conversations about what personal consequences have to be done for these people because until then they're gonna do the same thing. </s><s>[INST] So you think there's going to be society wide consequences of this that we're gonna see like ripple effects because of the social isolation. [/INST] I mean, we also need to talk about consequences of cuomo and de Blasio because if if politicians respond to incentives and the incentives are there for them to be extremely conservative. Because if you have to choose as cuomo center press conference between 1000 people dying and 1000 people losing their business. It's not a hard choice. And he's right. But at a certain point it's like all right, you're losing both, your losing, not losing that. You're you're making these decisions. Um, and not having consequences for it. And you're going to do it again the next time. So we need to make sure you're a little scared and I don't know what that would mean. </s><s>[INST] But you're laying this problem, this this incompetence. [/INST] I don't think it's incompetence. I think it's very competent. I think they're just their job. </s><s>[INST] Yes. But but but you're laying it not at the at the hands of the individuals but the structure of the, of government. It's both. Yes. How would we deal with it better without centralized control? [/INST] Well, we didn't really have centralized control because every country and every state, you know, handled it in a different mechanism. </s><s>[INST] But the city has centralized control just yet. [/INST] Right? I know that's not true, cuomo de Blasio, they had a lot of disagreements over this over the months and this was actually a source of great interest in tension. Um De Blasio wanted at one point was talking about quarantining people in their homes, calm was like you're crazy. Uh, something anything with the schools same thing with the gyms. Um, and there are other such examples, but the point being this was an emergency, this is World War One. I talked to us in temples show um was very dangerous because it gave a lot of evil people some very useful information about what the country put up with and what they can get away with under wartime. And this set the model for things like the new deal and the other things of that nature. It is undeniable. Your scientists you understand perfectly well um that this lockdown gave some very nefarious people some very valid data about how much people will put up with under pressures from the state. </s>

<s>[INST] For 180 bucks a year, you get an all-access pass to watch courses from, to list some of my favorites. Chris Hadfield on space exploration, Neil deGrasse Tyson on scientific thinking and communication, Will Wright, creator of the greatest city building game ever, SimCity and Sims on game design, Carlos Santana on guitar, Gary Kasparov, the greatest chess player ever on chess, Daniel Negrono on poker, and many more. Chris Hadfield explaining how rockets work and the experience of being launched into space alone is worth the money. Once again, sign up at Masterclass.com slash Lex to get a discount and to support this podcast. And now here's my conversation with Ben Kurtzel. [/INST] What books, authors, ideas had a lot of impact on you in your life in the early days? You know, what got me into AI and science fiction and such in the first place wasn't a book, but the original Star Trek TV show, which my dad watched with me like in its first run, it would have been like 1968, 69 or something. And that was incredible because every show that visited a different alien civilization with different culture and weird mechanisms. But that got me into science fiction, and there wasn't that much science fiction to watch on TV at that stage. So that got me into reading the whole literature of science fiction, you know, from the beginning of the previous century until that time. And I mean, there was so many science fiction writers who were inspirational to me. I'd say if I had to pick two, it would have been Stanislaw Lem, the Polish writer. Yeah. Solaris. And then he had a bunch of more obscure writings on superhuman AIs that were engineered. Solaris was sort of a superhuman, naturally occurring intelligence. And Philip K. Dick, who ultimately my fandom for Philip K. Dick is one of the things that brought me together with David Hansen, my collaborator on Robotics Project. So Stanislaw Lem was very much an intellectual, right? So he had a very broad view of intelligence going beyond the human and into what I would call open-ended super intelligence. The Solaris super intelligent ocean was intelligent, in some ways more generally intelligent than people, but in a complex and confusing way so that human beings could never quite connect to it. But it was still probably very, very smart. And then the Golem Four supercomputer in one of Lem's books, this was engineered by people, but eventually it became very intelligent in a different direction than humans and decided that humans were kind of trivial and not that interesting. So it put some impenetrable shield around itself, shut itself off from humanity, and then issued some philosophical screed about the pathetic and hopeless nature of humanity and all human thought, and then disappeared. Now Philip K. Dick, he was a bit different. He was human focused, right? His main thing was human compassion and the human heart and soul are going to be the constant that will keep us going through whatever aliens we discover or telepathy machines or super AIs or whatever it might be. So he didn't believe in reality, like the reality that we see may be a simulation or a dream or something else we can't even comprehend, but he believed in love and compassion as something persistent through the various simulated realities. So those two science fiction writers had a huge impact on me. Then a little older than that, I got into Dostoevsky and Friedrich Nietzsche and Rambod </s><s>[INST] and a bunch of more literary typewriting, Polish writers. Yeah. Can we talk about some of those things? So on the Solaris side, Stanislaus Lem, this kind of idea of there being intelligences out there that are different than our own, do you think there are intelligences maybe all around us that we're not able to even detect? So this kind of idea of maybe you can comment also on Steven Wolfram thinking that there's computations all around us and we're just not smart enough to kind of detect their intelligence or appreciate their intelligence. [/INST] Yeah, so my friend Hugo de Geras, who I've been talking to about these things for many decades since the early 90s, he had an idea he called SIPI, the search for intraparticulate intelligence. So the concept there was as AIs get smarter and smarter and smarter, assuming the laws of physics as we know them now are still what these super intelligences perceived hold and are bound by, as they get smarter and smarter, they're going to shrink themselves littler and littler, because special relativity makes it so they can communicate between two spatially distant points. So they're going to get smaller and smaller. But then ultimately, what does that mean? The minds of the super, super, super intelligences, they're going to be packed into the interaction of elementary particles or quarks or the partons inside quarks or whatever it is. So what we perceive as random fluctuations on the quantum or sub-quantum level may actually be the thoughts of the micro, micro, micro miniaturized super intelligences because there's no way we can tell random from structured but with an algorithmic information more complex in our brains. Right? We can't tell the difference. So what we think is random could be the thought processes of some really tiny super minds. And if so, there's not a damn thing we can do about it except try to upgrade our intelligences </s><s>[INST] and expand our minds so that we can perceive more of what's around us. But if those random fluctuations, like even if we go to like quantum mechanics, if that's actually super intelligent systems, aren't we then part of the soup of super intelligence? So aren't we just like a finger of the entirety of the body of the super intelligence system? [/INST] It could be, I mean, a finger is a strange metaphor. I mean, a finger is dumb is what I mean. But a finger is also useful and it's controlled with intent by the brain, whereas we may be much less than that. Right? I mean, yeah, we may be just some random epiphenomenon that they don't care about too much. Like think about the shape of the crowd emanating from a sports stadium or something, right? There's some emergent shape to the crowd. It's there. You could take a picture of it. It's kind of cool. It's irrelevant to the main point of the sports event or where the people are going or what's on the minds of the people making that shape in the crowd, right? So we may just be some semi-arbitrary higher level pattern popping out of a lower level hyper intelligent self-organization. And I mean, so be it, right? I mean, that's one thing that... Still a fun ride. Yeah. I mean, the older I've gotten, the more respect I've achieved for our fundamental ignorance. I mean, mine and everybody else's. I mean, I look at my two dogs, two beautiful little toy poodles and, you know, they watch me sitting at the computer typing. They just think I'm sitting there wiggling my fingers to exercise them maybe or guarding the monitor on the desk that they have no idea that I'm communicating with other people halfway around the world, let alone, you know, creating complex algorithms running in RAM on some computer server in St. Petersburg or something, right? Although they're right there, they're right there in the room with me. So what things are there right around us that were just too stupid or close-minded to comprehend? </s>

<s>[INST] That's a real whatever that is that's the real thing. The mystery of the human mind is more powerful than any alien. Or I mean it's as interesting I think is the universe. And I think they're somehow intricately linked maybe getting a sense of numbers. How many stars are there in um maybe I don't know what the radius that's reasonable to think about. I don't know if the observable universe is like way too big to think about. But in terms of when we think about how many habitable planets there are what are the numbers we're working with in your sense? What are the [/INST] scale? Honestly the numbers are probably like billions of trillions </s><s>[INST] of stars. [/INST] You know in the U. K. I think I don't know if we do that here but they will call a billion trillion. We put like one billion followed by a trillion. Uh Yeah it's kind of weird. But here I don't even know how to say the number 10 to the 20. Like if you know what that is. That's one followed by 20 zeros. That's a big number and we don't have a name for that number. There's so many </s><s>[INST] per star I think we kind of mentioned this is there a good sense that's probably argument about this but per star. How many planets are [/INST] there? Is they don't have that number yet per se. You know, we're not really there. But some people think that there's many planets per star. There's this analogy of filling the coffee cup like you know, you don't usually just pour one drop you fill it and that planetary systems, we see stars being born that have a disk of gas and dust and that ultimately forms planets. So the idea the kind of concept is that planets, so many planets form too many and eventually some get kicked out and you're left with like a full planetary system, a dynamically full system. And so there have to be a lot because so many form and a bunch survive. </s><s>[INST] Yeah, I mean that that makes perfect intuitive sense. Right? Like why wouldn't that happen? [/INST] Right. Well there's other thoughts too though, these big planets that are really close to the star, we think they formed far away from the star where there's enough material to form and they migrated inwards and some of these planets migrating inwards due to interaction with other planets or with the disk itself. They may have cleared it out. Like kicked other planets out of the system. So there's a lot of ideas floating around. We're not entirely sure. </s><s>[INST] And what about earth like planets? Is that that's another level of uncertainty [/INST] that it's a level of uncertainty if we think of an Earth like planet being an Earth around a sun in the same orbit an Earth like planet being an Earth sized planet in an Earth like orbit about a sun like star. We're not there yet. We're not able to detect enough of those two to give you a hard number. Some people have extrapolated and they will say as many as one in five stars like our sun could be hosting a true earth like planet </s><s>[INST] on the topic of space exploration. There's been a lot of exciting developments with Nasa or SpaceX, with other companies successfully getting rockets into space with humans and getting them to land back, especially with SpaceX. What are your thoughts about Elon musk and SpaceX Crew Dragon? Well, working with Nasa to launch astronauts, what's your sense about uh these exciting new developments? [/INST] Well, SpaceX and other so called commercial companies are only good news for my field because they're lowering the cost of getting to space by having reusable rockets. It's just been, it's incredible and we need cheaper access to space. So from a very practical viewpoint, it's all good about getting people. There's this dream that we have to go to MArs Boots on MArs </s><s>[INST] Boots on MARS, what do you think about that? You mentioned probe? What's the value of humans? Uh is that interesting to you from both scientific and a human perspective, [/INST] human mostly I think it's such in our desire to explore because part of what it means to be human. So wanting to go to another planet and be able to live there for some time. It's just just what it means to be human. You know? Oftentimes in science and engineering big huge discoveries are made when we didn't intend to. So often this kind of pure exploratory type of research or this pure exploration research, it can lead to something really important. Like the laser, we couldn't really live without that. Now. At the grocery, you scan your foods, there's surgery that involves involves lasers. Gps we all use our Gps. We don't have GPS because someone thought, hey that would be great to have a navigation system. And so I do support. I do. I just but I really think it comes primarily just from the desire to explore. </s><s>[INST] Do you think something? There's a lot of criticism and a lot of excitement about mars, do you think there's value in trying to go to put humans on mars, first of all? And second of all colonized mars, do you think there's something interesting that might come from there? [/INST] I'm convinced there will be something interesting. I just don't know what it is yet, but I don't think I don't think having some commercial value or value in the metric of something useful is really what's motivating us. </s><s>[INST] So really you see exploration is a long term investment into something awesome that eventually be commercial [/INST] value do actually. </s>

<s>[INST] Well, okay, so you've made and interesting if you can untangle that comment. So now in retrospect it was a mistake to see chess as the peak of human intellect. Nevertheless, that was done for centuries. So [/INST] by the way in europe, because you know, you move to the far east, they will go, they had short games. Again, some of the games like, you know, uh board games. Yes, Yeah, I agree. </s><s>[INST] So if I push back a little bit, so now you say that, okay, But it was a mistake to see chess as the epitome. And now and then now there's other things maybe like language that conversation, like some of the things that, in your view is still way out of reach of computers? But inside humans, do you think, can you talk about what those things might be? And do you think just like chest that might fall [/INST] um soon </s><s>[INST] with the same set of approaches. If you look at alpha zero, the same kind of learning approaches as the machines grow in size. [/INST] Now now it's not about growing in size, it's about again, it's about understanding the difference between a closed system and open ended system. </s><s>[INST] So you think that key difference. So the board games are closed in terms of the rules that the [/INST] actions of the state </s><s>[INST] space, everything is just constrained. You think once you open it, the machines are lost, [/INST] not lost. But again the effectiveness is very different because machine does not understand the moment it's reaching territory of diminishing returns. It's the simply put it in a different way. Machine doesn't know how to ask right questions. It can ask questions but it will never tell you which questions are relevant. So there's the, it's like about it. It's the, it's a direction. So these, it's I think it's in human machine relations we have to consider so our role and people, many people feel uncomfortable that this, the territory that that belongs to us is shrink I'm saying. So what you know, this is eventually will belong to the last few decimal points but it's like having so very powerful gun that's and, and, and, and all you can do there is slightly you know ultra direction of the bullet maybe, you know, 0.1, the uh degree of this angle, but that means a mile away, 10 m of the target. So that's, we have to recognize that is a certain unique human qualities that machines in a foreseeable future will not be able to reproduce. And uh, and the effectiveness of this cooperation collaboration depends on our understanding what exactly we can bring into the game. So, uh, the greatest danger is when we try to interfere with machine superior knowledge. So that's why I always say that sometimes you'd rather have by reading this history, pictures in radiology. Uh, you may probably prefer an experienced nurse than rather than having top professor because she will not Try to interfere with machines understanding so that it's very important to know that if machines knows how to do better things in 95%, territory, we should not touch it because it happened. It's like in chess, recognize they do it better see where we can make the difference. You mentioned alpha zero. I mean zero is it's a, it's actually the first step into what you may call ai because everything that's been called ai today, it's just it's uh, it's it's one or another variation of what Claude Shannon characterized as a brute force is a type a machine, whether it's deep blue, whether it's what's in it and all these things, this is the modern technologies that are being competitors as a i it's still brute force. It's the, all they do is they do optimization. It's this, they are, you know, they they keep, you know, improving the way to process human generated data. Now alva zero is, is the first step towards, you know, machine produced knowledge, which is, by the way, it's quite ironic that the first company that champion, that was IBM Oh, it's in backgammon, </s><s>[INST] interesting in that. [/INST] Yes, you just you should, you should, you should look at IBM is, it's, it's a neuro gammon, it's the, it's the </s><s>[INST] response to sorrow. [/INST] He's still working at IBM they had in the early 90s, It's just, it's the, it's a program that played in the α zero types. So just trying to come up with strategies. But because of success of the blue, this project had not abandoned, but just, you know, it's, it's, it wasn't, it was put on cold and now we just, you know, it's, it's, it's, you know, it's, everybody talks about about this, the machines generated knowledge so as revolutionary and it is, but there's still, you know, many open ended questions. Yes, Alpha Zero generates its own data. Many ideas that α zero generating chest were quite intriguing. So I I looked at these games was Not just with interest, but with, you know, it's, it's quite exciting to learn how machine could actually, you know juggle all the pieces and just uh play positions with a broken material, balance, sacrificing material always being ahead of other programs, you know, one or two moves ahead by by foreseeing the consequences, not over calculating because machines, other machines were at least as powerful in calculating, but it's having this unique knowledge based on discovered patterns after playing 60 million games. </s><s>[INST] Almost something that feels like intuition [/INST] exactly. But there's one problem now uh the simple question if if our zero faces superior porter, let's say another powerful computer accompanied by a human who could help just to discover certain problems. Because I already I looked at many alpha zero games, I visited the lab spoke to them. It's possible that this team and I know there's certain witnesses there now if this witness are exposed. The question is how many games will take alpha zero to correct it. The answer is hundreds of thousands. Even if it keeps losing its just because the whole system is based. So it's now imagine so this is you can have a human by just make a few tweaks, so humans are still more flexible and and as long as we recognize what is, what is our role where we can play sort of uh so the most valuable part in this collaboration. So it's it will help us to understand what are the next steps in human machine collaboration </s>

<s>[INST] So why do you think it bothers people so much that so so everything you just said is really powerful to the control of the ability to leave Because we collect we have studies here running at M. I. T. That collects huge amounts of data and people consent and so on. Uh The ability to delete that data is really empowering and almost nobody ever asked the deleted. But the ability to have that control is really powerful. But still you know there's these popular anecdote anecdotal evidence that people say they like to tell that to them. And a friend were talking about something I don't know uh sweaters for cats and all of a sudden they'll have advertisements for cat sweaters on amazon. There's that that's a popular anecdote as if something is always listening, what can you explain that anecdote that experience that people have? What's the psychology of that? What's that experience? Uh and can you, you've answered it, but let me just ask is Alexa listening? [/INST] No Alexa listens only for the Wake word on the device, right? And the wake word is the words like Alexa amazon, echo and you but you only choose one at a time. So you choose one and it listens only for that on our devices. So that's first from the listening perspective, you have to be very clear that it's just the Wake word. So you said why is there this anxiety if you may, It's because there's a lot of confusion what it really listens to write and you and I think it's partly on us to keep educating our customers and the general media more in terms of like how what really happens. And we have done a lot of it. Uh and our pages on information are clear, but still people have to have uh more, there's always a hunger for information and clarity and we'll constantly look at how best to communicate if you go back and read everything. Yes, it states exactly that. Uh and then people could still question it. And I think that's absolutely okay to question what we have to make sure is that we are because our fundamental philosophy is customer first customer obsession is our leadership principle. If you put as researchers, I put myself in the shoes of the customer and all decisions in amazon are made with that. And and so and trust has to be earned and we have to keep earning the trust of our customers in this setting. Uh, and to your other point on like uh, is there something showing up based on your conversations? No, I think the answer is like you a lot of times when those experiences happen, you have to also know that okay, it may be a winter season. People are looking for sweaters, right? And it shows up on your amazon dot com because it is popular. So there are many of these, uh you mentioned that personality or personalization turns out we're not that unique either. Yeah. Right. So those things we, as humans start thinking, oh, must be because something was heard. And that's why this other thing showed up. The answer is no, probably it is just the season for </s><s>[INST] sweaters. I'm not gonna ask you this question because it's just because you're also because people have so much paranoia. But my, let me just say from my perspective, I hope there's a day when customer can ask Alexa to listen all the time to improve the experience to improve because I, I personally don't see the negative because if you have the control and if you have the trust, there's no reason why I shouldn't be listening all the time to the conversations to learn more about you because ultimately as long as you have control and trust every data you provide, the device that the device wants is going to be useful and that so to me, I as as a machine learning person, I think it worries me how sensitive people are about their data relative to how uh empowering it could be for the devices around them enriching it could be for their own life to improve the product. So I just it's something I think about sort of a lot how to make that devices obviously like that thinks about a lot as well. I don't know if you want to comment on that sort of Okay, have you seen me in the form of a question. Okay, have you seen an evolution in the way people think about their private data in the previous several years. So as we as a society get more and more comfortable to the benefits we get by sharing more data [/INST] first. Let me answer that part. And then I want to go back to the other aspect you were mentioning. Uh So as a society on a general we are getting more comfortable. As a society doesn't mean that everyone is and I think we have to respect that. I don't think one size fits all is always going to be the answer for all right by definition. So I think that's something to keep in mind in these uh going back to your on what more uh magical experiences can be launched in these kind of ai settings? Uh I think again if you give the control we it's possible certain parts of it. So we have a feature called follow up More. Where you if you turn it on and Alexa after you've spoken to it, we'll open the mix again, thinking you will answer something again. Like if you're adding lists to your shopping items, right? Shopping list or to do list, you're not done you want to keep. So in that setting it's awesome that it opens the mic for you to say eggs and milk and then bread. Right? So these are the kind of things which you can empire. So and then another feature we have which is called Alexa guard. I said it only listens for the wake word. All right. But if you have a let's say you're going to say Alexa, you leave your home and you want Alexa to listen for a couple of sound events, like smoke alarm going off or someone breaking your glass. Right? So it's like just to keep your peace of mind. So you can say Alexa on guard or or I'm away or uh And then it can be listening for the sound events. And when you're home you come out of that mode. Right? So this is another one where you again gave controls in the hands of the user or the customer and to enable some experience that is high utility and maybe even more delightful in the certain settings like follow up more and so forth. Again, this general principle is the same control in the hands of the castro. </s>

<s>[INST] Yeah, because [/INST] they don't have much house. Again, if you gave them other things, you might say guy, you can go get in the operation, why don't you stop? But if, if they're working for shipt wages and you haven't figured out a way to, to treat them treat their cancer diagnosis and they don't like, I mean, life, you know, you know, you gotta, you gotta derive pleasure from something </s><s>[INST] that's an interesting point that anger is a good valve like two for if your life is suffering, that there's something very powerful about anger, but I still have hope that doesn't have to be, I mean that kind of channeling into anger that then becomes hate, lead us into a lot of troubles in human history, you have to be careful uh empowering people too much in that anger, especially, I think my I think I understand why people were nervous about parler about twitter and so on, because all that sh it, talking about violence was now paired with let's Get together at this location. This was a new thing, like it's not just being on whatever platform talking sh it it's saying we're going to in physical space meat and then everybody got all these platforms got nervous. Well, what happens when all these ship doctors, all these angry people, they're just letting off steam meat in the physical space? Uh and that was probably overreach. Almost definitely overreach, but I can understand why they were nervous, I [/INST] agree there doesn't seem to be, and this is when trump got elected and when you have like, whatever you have right, where you have riots in Portland in Seattle, where you have the antifa people doing crazy things, you have, like, you know, the people at the storming the capitol, there never seems to be a ton of uh an examination of why these ideas are becoming popular, Why are people so angry? What is leading people to this? Why are we here? What about their lives is to the point where they need to show up at these places and like obviously there's gonna be people on the fringe, they'll always be the mentally unwell, there'll always be people that want to destroy society. But when you look at how popular large, you know, long discredited things, whether it's fascism, you know, totalitarian communism, all of these things are like, why are they back? Why are they back in a big way? And why are why are people so fed up with the status quo that they're finding, you know, solace in the most extreme, uh, discredited theories of how to run and operate societies, theories that have led to death of a lot of people. So, to me, I'm like, if those people at the capitol, yes, if they were going to work, if there's, you know, if they were able to go out and drink at chili's, if they were able to get a fucking checkup right? Like if their job paid a little bit better and I'm not saying that this is all the reason, right? I'm sure that there's a lot of people there that are doing quite well and there's still nuts. But like the anger and the rage that's boiling to the surface of the society, Does it come from the fact that across the board, people in very different areas and with very different political beliefs feel like they are being fucked over and there's nothing they can do about it. That's what the baseline to me, they look at the people that run the country and run the world, whether they're tech titans, the guys that you talked to or whether they're people that run the government, whether they're people that run large banks, large media companies, the people that have created this kind of, you know, infrastructure that everyone lives in. These people are incredibly powerful. And when you push people to that point logically, sadly, and unfortunately, the next thing does seem to be violence. </s><s>[INST] Yeah. The thing that troubles me a lot is you said nobody's asking why these beliefs are out there, but sometimes it's not even acknowledged that people are hurting people are angry, just even acknowledging that all the conspiracy theories that are out there, acknowledging that they're out there. And then people are thinking about it and talking about it just Because otherwise. So it's not acknowledged in this nuanced way. What happens is you say, Okay, 70 million people are white supremacists. It's just throwing, uh, kind of blanket statement. And of course that gets them angrier and more makes them feel more powerless. And that ultimately, that that's what's been painful for me to see is that there's not an acknowledgement that most people are good, right? And there's circumstances where it's just you're piste off, right? Because you were powerless. I mean, you [/INST] could fall into the bad crowd. That's the thing, you can just fall in and it doesn't mean that you're you don't, there's not blame, you know, you're obviously you're you have agency, you're a person, you know, but the idea that like you could be rehabilitated, you could do something stupid or you could fall into the great, you know, a group of people that are and then in a few years you can go what the funk was I doing? You know, I'm an ex drug addict, I know what it's like to go from being one thing to being another thing, right? I'm still a drug if I would use drugs right now or drink I would still be addicted to them, right? I mean it's not something that I can ever change about myself, but I know what it's like to go from one thing to another thing. So when you look at racism or whatever is um homophobia misogyny, whatever, whatever you're looking at anti Semitism and you go that's a fixed condition where nobody is ever going to be able to change, Nobody's ever gonna be able to be rehabilitated, nobody's ever going to be able to re imagine themselves in a different way to me. You're just you're throwing away someone and you're making them feel helpless and worthless. Um and that's going to lead to antisocial behavior that spills out into, we don't have a very redemptive society, that's a huge factor. We don't have a redemptive society, that's why I like O. J. Simpson because O. J. Simpson yes, he did a bad thing supposedly, but he's very kind now on twitter and he makes very nice points about how we want to get involved in the political process and he's on golf courses and I like watching people golf. I don't do it but I like watching him do it and he's like an elder statesman because I remember him from the naked gun and I choose to forgive him. Um you know for for for whatever happened there which I don't know but I choose to forgive him really for I mean obviously you know what they say is he cut his wife's head off but I can look past that and redeem him because he's very like stable on twitter and he's a good like I see all these people going crazy on twitter and I'm like there's maybe OJ's lived a full life. I think there's a benefit to that. There's a benefit to kind of living a full life. </s>

<s>[INST] by the way. When you say my you mean literally yours, you know this about you, [/INST] I know this about me. Yeah. Which is </s><s>[INST] kind of uh, I mean philosophically speaking is a pretty powerful thing. So, to live with me, maybe that's what we agreed to talk again by the way for the listeners to where we're going to try to focus on science today and a little bit of philosophy next time. But it's uh, interesting to think about, the more you're able to know about yourself from the genetic information in terms of the diseases, how that changes your own view of life. [/INST] So there's there's a lot of impact there and there's something called genetic exceptionalism which basically thinks of genetics is something very very different then everything else as a type of determinism and you know let's talk about that next time. So basically a good preview. Yeah so let's go back to A. M. D. So basically with A. M. D. We have no idea what causes an MD. You know it was it was a mystery until the genetics were worked out and now the fact that I know that I have a predisposition allows me to sort of make some life choices. Number one but number two the genes that lead to the predisposition give us insight as to how does it actually work. And that's a place where genetics give us something totally unexpected. So there's a complement pathway which is an immune function pathway that was in you know most of the Los I associated with AMG and that basically told us that wow there's an immune basis to this eye disorder that people had just not expected before. If you look at compliment it was recently also implicated in schizophrenia and there's a type of micro glia that is involved in synaptic pruning. So synapses are the connections between neurons and in this whole use it or lose it view of mental cognition and other capabilities. You basically have uh micro glia which are immune cells that are constantly traversing your brain and then pruning neuronal connections, pruning synaptic connections that are not utilized. So in schizophrenia there is thought to be a change in the pruning that basically if you don't prune your synapses the right way you will actually have an increased role of schizophrenia. This is something that was completely unexpected for schizophrenia. Of course we knew it has to do with neurons but the role of the compliment complex which is also implicated in A. M. D. Which is now also implicated in schizophrenia was a huge surprise </s><s>[INST] what's the compliment complex? [/INST] So it's basically a set of genes, the complement genes that are basically having various immune roles. And as I was saying earlier our immune system has been co opted for many different roles across the body. So they actually play many diverse roles. And </s><s>[INST] somehow the immune system it's connected to the synaptic pruning process. Process. [/INST] Exactly. So immune cells were co opted to prove. How did you figure </s><s>[INST] this out? How does one go about figuring this intricate connection like pipeline of connections [/INST] out. Let me give you another example. So so Alzheimer's disease. The first place that you would expect it to act is obviously the brain. So we had basically this roadmap, epic genomics consortium view of the human genome, the largest map of the human genome that has ever been built Across 127 different tissues and samples with dozens of EPI genomic. Marks measured in hundreds of donors. So what we've basically learned through that is that you basically can map what are the active gene regulatory elements for every one of the tissues in the body. And then we connected these gene regulatory active maps of basically what regions of the human genome are turning on in everyone of different tissues. We then can go back and say where are all the genetic loss i that are associated with disease? This is something that my group I think was the first to do back in 2010 in this ernst Nature biotech paper. But basically we were for the first time able to show that specific chromatic states, specific genomic states. In that case enhancers were in fact enriched enriched in disease associated variants. We push that further in the ernst Nature paper a year later and then in this roadmap for genomics paper, you know, a few years after that. But basically that matrix that you mentioned earlier was in fact the first time that we could see what genetic traits have genetic variants that are enriched in what tissues in the body. And a lot of that map made complete sense. If you look at a diversity of immune traits like allergies and type one diabetes and so and so forth. You basically could see that they were enriching that the genetic variants associated with those traits were enriched in enhancers in these gene regulatory elements active in T cells and B cells and hematopoietic stem cells. And so and so forth. So that basically gave us uh confirmation in many ways that those immune traits were indeed enriching immune cells. If you look if you look at type two diabetes, you basically saw an enrichment in only one type of sample and it was pancreatic islets. And we know that type two diabetes stems from the deregulation of insulin in the beta cells of pancreatic islets and that sort of was spot on super precise. If you look at blood pressure, where would you expect blood pressure to occur? You know, I don't know, maybe in your metabolism in ways that you process coffee or something like that. Maybe in your brain. The way that you stress out increases your blood pressure et cetera. What we found is that blood pressure localized specifically in the left ventricle of the heart. So the enhancers of the left pectoral in the heart contained a lot of genetic variants associated with blood pressure. If you look at height, we found an enrichment specifically in embryonic stem cell enhancers. So the genetic variants predisposing you to be taller or shorter are in fact acting in developmental stem cells makes complete sense. If you look at inflammatory bowel disease, you basically found inflammatory which is immune and also bowel disease which is digestive and indeed we show a double enrichment both in the immune cells and in the digestive cells. So that basically told us that I have this is acting in both components. There's an immune component to inflammatory bowel disease and there's a digestive components. And the big surprise was for Alzheimer's we had seven different brain samples. We found zero enrichment in the brain samples for genetic parents associated with Alzheimer's. I mean this is mind boggling. Our brains were literally hurting what is going on and what is going on is that the brain samples are primarily neurons, all the good undersides and astrocytes. In terms of the cell types that make them up. So that basically indicated that genetic variants associated with Alzheimer's, we're probably not acting in all the good exercise astrocytes or neurons. So what could they be acting in? Well, the fourth major cell type is actually microglia. Microglia are resident immune cells in your brain. Oh nice. The immune wow. And they are CD 14 plus, which is these sort of cell surface markers of those cells. So their city 14 plus cells just like macrophages that are circulating in your blood. The micro glia are resident monos, it's that are basically sitting in your brain. Their teachers specific. Mon aside and every one of your tissues like your your your fat for example has a lot of macrophages that are resident and the M one versus M two macrophage ratio has a huge role to play in obesity and you know, so basically again these immune cells are everywhere. But basically what we found through these completely unbiased you of what are the tissues that likely underlie different disorders. We found that Alzheimer's was humongously enriched in microglia, but not at all in the other cell types. So what </s>

<s>[INST] There could be complexities to just having that many, uh, just another topic. So a complexity is associated with having so many satellites, uh, especially with competing companies and competing nations. Do you see that as an issue, having tens of thousands, hundreds of thousands of satellites, it becomes a very interesting robotics collision avoidance problem. [/INST] The, the one thing to keep in mind is perspective. Like I know 10,000 satellites and 20,000 and a hundred thousand satellites sounds insane and it sounds really scary, but I mean, just even look at how many planes are in the air at any given time and the planes are, are bigger. They're flying slower, which actually means there's a greater chance of collision. If you think about, you know, two objects occupying space, if they're ones moving really fast, like imagine trying to, you know, throw two basketballs at each other, relatively easy. Now try shooting two bullets at each other and having like, you know, at 90 degrees from each other, you have to have your timing down, like really perfect to do that now take that times 10, you know, these objects are taking up a physical space, very small amount of time. They're relatively small. Like most satellites are not very big and they have limitless altitudes to deal with. So even though you can have what look like convergences, you know, they can be 10, 20, 50, a hundred kilometers difference often. And, and you know, they're dealing with this, like all the, the all space assets know, Hey, I'm at this orbital plane in this Ballelu. And they know their altitudes and know their safe distances and have these margins built in and it's space. So there's like an insane amount of room, you know, so there's a lot of margin. But of course you can't excuse that all the way. Like you have to still have plans and be considering that and considering collisions and considering all of the above. </s><s>[INST] There's a lot of margin. But when do you think the first human being will step foot on Mars? Mars, you don't like timelines, but is this something, and you're very much focused on kind of the short term of incredible progress that's happening, and that makes total sense, but there is the Mars plan that was at the origin of the commercial space flight [/INST] efforts, do you still see and dream about that day? Let me be clear that I don't want to go to Mars, but I do think if you're making me guess a timeline for when humans will walk on Mars, even a year ago, I still would have said by the end of 2020, like the 2020s decade, you know? So by December 31st, 2029, I thought humans would have walked on Mars. I'm starting to think that's still too optimistic, but I do, I definitely think by 2040. Like I for sure think that, and I really think it's just hard to predict that curve, you know, that project out that curve. We're gonna go from feeling like it's impossible </s><s>[INST] like it's feeling like it's inevitable. It could be another, by the end of this decade, JFK type moment, especially if China steps up with a space race, it could be like, all right, NASA kind of says, all right, this Elon fella, [/INST] like really make this a gigantic effort. Well, and if Starship works out as planned, and as NASA has invested in human landing system, they're relying on SpaceX to land on the moon. SpaceX can land on the moon, they can land on Mars. Now, whether or not the life support and the human considerations of longterm spaceflight missions and high radiation and blah, blah, blah, blah refueling on Mars is a huge, huge, huge deal. They definitely could send a Starship to Mars and ideally land in one piece on Mars. As soon as they can land on the moon, they can land on Mars, basically. I mean, those two things are very, in some ways, Mars is almost easier. Because you can use the atmosphere to slow down. It actually doesn't take that much more Delta V to actually land on Mars than it does. Because on the moon, you don't have any, you've got the first get out to the moon, then orbit the moon, you know, get to slow down. Everybody one of those is a maneuver change. Then you have to slower your orbit until it coincides, you know, it hits the moon. Then you need to slow down enough to not explode when you hit the moon. So there's a lot of delta V there, a lot of change in velocity. Mars is actually by the time we kind of crunch the numbers, it's relatively similar. Just a lot more difficult like timeline wise and you know, accuracy and all of these other communication, There's a lot of other things obviously involved. I'm glossing over it, making it sound easy. It's not, but I think there's a real decent chance we could see a Starship vehicle land on Mars, uncrewed by the end of the decade though. </s>

<s>[INST] What are the defining characteristics. What are the interesting things about xi Jinping the president of China as a leader on the world stage. [/INST] His father was a early leader, he was himself um in the Cultural Revolution in times treated um brutally. Um, and during that period of time, it was very, very difficult and he came up, you know, through the ranks and he's a very intelligent man. Um, when he first came to power as you know, they have 25 year terms and we're now coming to the end of the second of those five year terms when he first came to power, he felt that there should be a lot of reform and reform meant moving too much more of a market and open economy when that happened in him coming in, I had some contact with economic policymakers. But in the circumstances then, were that five major banks lend to state owned enterprises and local governments with implied government guarantees. And so there was not control of that. And the and the movement to a more of a market economy and the development of markets was a primary and also the dealing with the corruption issue, there was a lot of corruption um prior to that and that was viewed as an existential threat to the system. So that became the primary objective. And then as time progressed over those 10 years, there was a a lot of changing and the world finance their financial circumstances, opening many many other markets. Um they particularly getting money to small and medium sized enterprises and developing a lending system and then establishing controls on it. So right now, um there's um um a vibrant um capital markets, um you can raise capital, you can be an entrepreneur, you can become a billionaire in the capital markets and they developed the markets to be the second largest capital markets at the same time. Um They had to deal with their rising debt issue, which they began to deal with really about four years ago when the second uh term began. And the um and then lu ha became the vice premier um responsible for that and to um deal with those issues. So you see right now that what's happening is the dealing with the real estate bubble. There was a development in real estate bubble which produced a lot of unproductive lending. And she's keeping said, um you know, um houses are meant to live in not to speculate on. And so that was wasteful. So they established what they call three red lines which are financial ratios that the property developers had to live within and that is then causing the adjustments that are going on now, which in my view are very healthy because um whenever there's bankruptcies and so on, the most in the public think, okay, that's a problem. It's in many cases really are cleaning up of bad debts and bad practices and so um that's what's going on. So that's, let's say economically at the same time, there is the changing relationships, the changing world order, the changing relationships with the United States and other countries, which is becoming much less cooperative and much more warlike, much more confrontational. Those two things. The domestic debt problem and domestic has led to what's called core, what they call core leadership, which means um a leadership more around him that um, is less challenging because they believe in history that during very difficult times, um a more essentially controlled decision making process lends itself better than to a more fragmented political contentious project. And that's basically what's going on now, </s><s>[INST] you said it very eloquently, but you mean the leadership is surrounded by yes men and there's a lot of centralized control. [/INST] That characterization, his view is much more black and white than it really is, but </s><s>[INST] it leans towards that [/INST] direction there, like for example, of the standing members of the polit bureau for our moral liege allowed him um three or less. So you have to understand that it's kind of a collective leadership at the top. And then of course there's just jockeying for power, you know, in a highly political sense, um at the top, but no one leader can be successful against the all those powers at the top. So it's very politically negotiating. It's, you know, it's very much more like if you put um in the United States, the democrats and the republicans and they had to be in the same government and they work it out. It's kind of something like that. And then and so that's that struggle, but it's an internal struggle. </s><s>[INST] Where do you put the importance of some of these ideas of the founding of the United States? When then now we're talking about that at the context of china, the freedom of speech freedoms, what china is doing with the central management of a lot of things. It's enabling a lot of growth, but it's also limiting people on the very basic level in terms of freedom, the kind of freedom that [/INST] I </s><s>[INST] think it can lead to entrepreneurship, to starting new businesses, to having big dreams and chasing those dreams and then creating totally new things in whatever the space maybe in technology and in in business and whatever. What how important is that as a metric for society? [/INST] Well, they have a view which is the idea of a dialectic, which means that two things are at obvious that everything comes with pros and cons and two opposites exist. And you want the benefits of those two opposites. And how do you deal with the benefits of those two opposites? So it let's say you want the capital markets because it gets money into the hands of the entrepreneurs who are motivated, they build fortunes and that drives an economy to do very well. And at the same time, um, it produces uh, the other problems, the wealth gaps, the other problems in the, the debt cycle that we're talking about and so on and Deng xiaoping, you know, how do you reconcile communism and um, the market economy and the capital markets? And he famously said, um, and if it doesn't matter if it's a white cat or a black cat, just as long as it catches mice, In other words, if it, if it works and making the country richer, then that becomes the objective and then they move that along. So there are these conflicts. Um, and um, one of the leaders described it to me as follows because it's confusion and it goes back over a period of time. There's a hierarchy and it's an extension of the family. He described it and he said the United States is a country of individuals and individualism. Um and that is its vibrancy that um we see the individual rights to speak up the individual protection of the individual. Individual property rights and all of those things as of paramount importance. And we build our organization. That's why democracy is from the bottom up or even a company will get together and we'll be partners to proper prosper together. That is the american approach. Um he was describing that in china, it's an extension of the confusion family essentially. And so it's almost like um um you know, there's a hierarchy. And so what they think about is the common good, uh not the individualism. So for example, if they want a high speed rail to go from one place to another and that's best in the common good, then the individual protections that would stand in the way of doing that would be of secondary concern. So that notion of controlling. So it for example, um what what they're doing with video games, um they control what type of video games and how many hours a day kids can be on video games, um operating in that way because they believe that that's good for the society and that's very controlling in the United States, I think probably most parents would say leave it to me and it's a matter between me and my kids. The same thing has to do with data, in other words, in the United States who controls the data, um does the company control the data, do you individually control the data? And so the inclination would be to figure that out, but nobody would say that the government is going to control the data because of our inclination of really anti government control in china, it would be that the government will control the data because that's going to be best for the society and it depends who you trust. But that's so, that difference in philosophy is very much at the um you know, at the heart of that, as far as um your question, in terms of effectiveness, it really is in china's case, it's how you balance the things right? So what they're attempting to do is to create a lot of freedom and creativity um in areas that are not political, let's say. Um and and so you see on a lot of entrepreneurship, you see a lot of product development, you see a lot of creativity Um happening in that way. So the stereotype that you don't see creativity happening is an old stereotype, whereas a lot of creativity certainly happening and the system can work well if they can achieve that kind of balance, it's proven to have worked well since I started going there in 1984. Per capita income, real, per capita income has increased by 26 times The longevity rate is increased by 10 years. The poverty rate has fallen from 88% to less than 1% in terms of, you know, basics like starvation and things. And if you read history Plato's Republic, you know, he talks about the cycles democracy, you know, an autocratic and the benevolent despot and all of that. Um each has their own vulnerability. The vulnerability of democracy, which has been a remarkable, remarkable system and I don't have to extol the benefits of it. Um but the vulnerability of it has always been the internal conflict that produces itself as anarchy in World War Two for democracies chose to be autocracies, um because there was internal disorder and there was the belief will somebody bring about order and get control of this situation, You know, that was in um Germany, Italy Japan and spain. Um There were parliamentary dictate uh systems that turned themselves over to that. So both systems have vulnerabilities. Um, I think the main thing that we need to think about is those vulnerabilities. Democracy is an amazing system because it looks at the adherence to the rules and the system and the checks and balances is quite amazing and it gives it a flexibility to change without civil wars. Um, um, um, but there has to be the respect of the rules and when you see something like um they they will not except elections or they will not accept rules. History has shown when the cause is that people are behind are more important to them than the system. The system is in jeopardy. So, we have a situation that's very much like that in terms of, let's say the 2024 elections, I believe that there's a very high chance that neither side will accept losing, for example. And so we um we have that kind of a situation. So one would hope that one could rise above the disagreements and rely on the system for resolving disagreements. Because if that doesn't happen, then we have our own chaos. </s>

<s>[INST] You've you don't actually quite done a lot of thinking and talking about neurology and just kinda look at human behavior through the lens of of looking at how are actually chemically our brain works. So what, first of all, why did you connect with that idea and what have you, how is your view of the world changed by considering the brain is just the machine? [/INST] You know, I know it probably sounds really nihilistic, but for me it's very liberating to know a lot about neurochemicals because you don't have to, it's like the same thing with like critics, like critical reviews, if you believe that good, you have to believe the bad kind of thing. Like, you know, if you believe that your bad choices were because of your moral integrity or whatever, you have to believe your good ones, I just think there's something really liberating and going like, oh that was just adrenaline. I just said that because I was adrenalized and I was scared and my Magdala was activated and that's why I said you're an asshole and get out and that's, you know, I think I just think it's important to delineate what's nature and what's nurture, what is your choice and what is just your brain trying to keep you safe. I think we forget that even though we have security systems and homes and locks on our doors, that our brain for the most part is just trying to keep us safe all the time. That's why we hold grudges. That's why we get angry. It's why we get road rage. That's why we do a lot of things. And it's also when I started learning about neurology, I started having so much more compassion for other people. You know, someone yelled at me being like, chuck you on the road, I'd be like, okay, he's producing adrenaline right now because We're all going 65 mph and our brains aren't really designed for this type of stress and he's scared. He was, you know, so that really helped me to have more love for people in my everyday life um instead of being in fight or flight mode. But um the I think more interesting answer your question is that I've had migraines my whole life, like I've suffered with really intense migraines. Um Ocular migraines, ones where my arm would go numb and I just started, I'm going to go to so many doctors to learn about it and I started, you know, learning that we don't really know that much, we know a lot, but it's wild to go into one of the best neurologists in the world who's like, yeah, we don't know, we don't know, we don't know. And that fascinated </s><s>[INST] me was one of the worst pains. You can probably have all that stuff and we don't know the source, [/INST] We don't know the source. And there is something really fascinating about when your left arm starts going numb and you start not being able to see out of the left side of both your eyes. And I remember when the migrants get really bad, it's like a mini stroke almost and you're able to see words on a page, but I can't read them, they just look like symbols to me. So there's something just really fascinating to me about your brain, just being able to stop functioning. And I, so I just wanted to learn about its study about it. Um I did all these weird alternative treatments. I got this piercing in here that actually works. I've tried everything And then both my parents had strokes. So when both of my parents had strokes, I became sort of the person who had to decide what was gonna happen with their recovery, which is just a wild thing to have to deal with it, you know, 28 years old, um when it happened and I started spending basically all day every day. And I see use with neurologists learning about what happened to my dad's brain and why he can't move his left arm, but he can't move his right leg, but he can't see out of it, you know? And then my mom had another stroke um in a different part of the brain. So I started having to learn what parts of the brain did what and so that I wouldn't take their behavior so personally and so that I would be able to manage my expectations in terms of their recovery. So my mom, because it affected a lot of her frontal lobe changed a lot as a person. She was way more emotional, she was way more micromanaged, she was forgetting certain things. So it broke my heart less when I was able to know, oh yeah, well the stroke, it, this part of the brain and that's the one that's responsible for short term memory and that's responsible for long term memory, did it up and then my brother just got something called viral encephalitis, which is an infection inside the brain. So it was kind of wild that I was able to go, oh, I know exactly what's happening here and I know, you know, so, um </s><s>[INST] so that allows you to have some more compassion for the struggles that people have. But does it take away some of the magic for some of the uh from the, some of the more positive experiences of like [/INST] sometimes and I don't, I don't, I'm such a control addict that, you know, I think our biggest someone like me, my biggest dream is to know why someone's doing, that's what stand up is, it's just trying to figure out why or that's what writing is, that's what acting is, that's what performing is trying to find out why someone would do something as an actor, you get a piece of you know material and you go this person, why would he say that? Why would he she pick up that cup? Why would she walk over here? It's really why why why? Why? So I think neurology is if you're trying to figure out human motives and why people do what they do would be crazy not to understand how neurochemicals motivate us. I also have a lot of addiction in my family and um hardcore drug addiction and mental illness and in order to cope with it, you really have to understand that borderline personality disorder, schizophrenia and drug addiction. So I have a lot of people I love that suffered from drug addiction and alcoholism and the first thing they started teaching you is it's not a choice. These people's dopamine receptors don't hold dopamine the same way as yours do. Their frontal lobe is underdeveloped like you know and that really helped me to navigate dealing loving people that were addicted to substances. </s>

<s>[INST] towards the body. Okay, so there's all these like modules of the body then connected to the grounding with like your feet on the ground. Everything you're speaking to, How do you work each of those modules is this over time, you kind of develop the feel that ultimately balls on to this one simple queue that you mentioned, or do you can you like literally study each particular module in yourself and see how it affects the lift. [/INST] So the best way and I believe it's because I hate just like people getting out and just doing just movement stuff and not actually adding load because we only adapt when there's load. Maybe we can get some you know some appropriate perception or awareness of position and other stuff. Doing some some corrective patterns and other stuff. But this is basic physiology is that there must be an imposed demand for us to have adaptation and this is mental, this is emotional, this is all these areas. Um but and people miss that so I prefer to be able to look at a person and this is our methodology and do the assessment in any basic loaded movement. So with developing an eye for that you can actually see and go okay we've got a fault pattern right here in the foot and use a Q or a set of queues. Doesn't really matter until we find the one that works and bring that and now we know we want to simplify this stuff. I just walked through. That sounds really complicated and it it is if we try to break down and distill it all. But like let's just find the basic stuff that gets us in the range, start working and then find the next as we add load. Now we find where's our next area that we're starting to fault that and then go there again next. So this is what we do, what we teach in our educational platform. So we are the only, I believe everybody wants to do a lot of these like assessments, you know, on a bench, on the table body and it's like no, let's let's go squat, let's go dead lift. If you do strongman and a ceo carry, let's go carry. Because these are basic human fundamentals, it's not power lifting, like this is how we function. This is why we we work with 29 of the 30 major league baseball teams and 90% of all professional sports out there uh in North America, sorry, although we do some work with Tour de France and other stuff as well, um and North America, I do mean hockey to uh but these principles are like, you know, if if the Dodgers won't bring us in, they're not learning how to power lift, you know, we're gonna obviously will probably do, we do a little bit more shoulder focus than hip focus with their athletes. Our their coaches were usually working with coach is not the athletes </s><s>[INST] and so you help them and then the same thing on yourself to understand the role that these different muscle groups have on the holistic, so [/INST] it's all about getting the joints in the appropriate position so that we can that we can manage loads so that we're not putting undue stress on the joint, we're getting the proper link tension, we're getting these basic fundamental things with the body and so the largest global impact that you will have is through spinal mechanics. I can't look at a shoulder if I'm not managing this because it's your spine. So for those are just listening, like I'm arching and then and then flexing um that's going to affect shoulder extension, flexion, all these sorts of things, so it can even affect things down. What's looking at dorsal flexion issues on the foot, like. And then that's why I go to the foot next because it has the second largest global impact. And then from there, now I'm going to look at the big energy drivers which is b hip complex, shoulder complex and then we can start looking at kind of the peripheral things, but usually that's some sort of output of the other, but the knees, the elbows, the things like that, so it's all about getting the stack, which affects neurology. So let's talk in engineering terms, you get in a car, modern car today and a lot of them will have this traction control button in there and there's a big misconception that, you know, I'm out and it's it's snowing here in austin only rainy, we'll probably doesn't rain much, but you're going around a corner, starts slipping, it's like it's going to send the powers from the wheels that are slipping to the ones that are gripping and keep me from crashing and diana fiery death. Well that's not how it works. It's the exact same. We've got, we've got the we got the tires which are our foot, you know the connection to the ground, right? We've got the power driver which is, you know the the engine, the transmission delivering, you know the power through it and we've got the stability or suspension and then we have the neurology and what the neurology is doing, its sensing that we don't have good stability or loss of connection somewhere. And so I need to save you from crashing and hurting yourself. And so it goes to the engine and says let's retard the timing, let's reduce the shift patterns and we're just reducing the power output and that's straight how the human body works. So when I do this stuff it's actually affecting that. I mean I can take somebody and do some minute changes with the neck position at the thoracic outlet. Okay. And immediately see an enhancement in power output and I can measure it. We measure this stuff with velocity devices and see like a 10% jump. And so think about that. What about all your training through the years where you actually had additional capacity but you weren't using it because your traction control was on now you figure this out stuff and now you start stacking it now you can see so much greater so it's not just injury prevention, this is performance and additive performance over time, this is huge and people don't really think about this stuff but we can turn that stuff off, which is actually gonna also again, make us make us safer. But what we want to do is the performance tuned race car. Do they have a traction control button? No, they got some amazing tires to grip the ground, performance tuned suspension and that driver is gonna put what his foot to the metal is going to put it to the floor. Okay. That's a performance vehicle. That's what we want to be. </s>

<s>[INST] Yes. Including the dark stuff. I I mean, part of me is not understanding the so there is uh evolutionary distinction between men and women, but I tend to believe both men and women, if you look out into the future can be destructive, can be evil, can be greedy, can be corrupted by power. So if you move mails from the picture which are historically connected to this evolution of that, we've been talking about that women are going to fill that role quite nicely. And then it'll be just the same kind of process. Not the same, but it will be new and interesting. There's a there's a sense that the the will to power craving power, committing violence is somehow coupled with uh with all the things that are beautiful about life. That if you remove conflict completely, if you remove all the evil in the world, it it seems like you're going to, um you're not going to have a stable place for the beauty for the goodness, like there's always has to be a dragon to fight for the way if you look at human history now, you can say the reason I'm nervous about a sort of Utopia where everything is great is every time you look through human history when utopia has been chased, you grunt a lot of trouble or again sneaks into this evil. This craving for power. Now you can say that's a male problem, but I just think it's a human problem and it's not even a human problem. It's a chimp problem to its life on earth problem, intelligent life on earth problem. So, like it's better to uh not necessarily get rid of the sources of the darker side of human nature, but more create mechanisms that the kindness, the goodness is the goodness paradox your book. That that is um incentivized and encouraged, empowered. [/INST] Well, look, I don't think it would be Utopia if you got rid of the males right? Uh and certainly females are capable of conflict. I just think it's a gamble worth taking. If you could actually do it, you can certainly find females in history who done unpleasant things. But nevertheless, you know, we have a very strong evolutionary theory which explains why males benefit more by having conflict and winning conflicts than females do. And so if we want to talk about reducing conflict, then it would reduce it to get rid of males. Now, I understand this is a fantasy. You know, and I think it's a fantasy that people would be able to talk about fairly soon because reproductive technology is going to the point where it's quite likely that human females could breed without the use of males. And so there would be a sort of a potential dynamic if everybody just agreed not to have any male babies. </s><s>[INST] It's a really interesting thought experiment. I will agree with you that if given two buttons, one is get rid of all women and the other buttons get rid of all men. Um, realizing that, uh, I have a stake in this choice. Uh, you're probably getting rid of all men. If I wanted to preserve earth and the richness of life on earth, I would probably get rid of all men. I [/INST] don't know. I don't think you have a stake in it. You know, I mean, you're saying that because you're a man, but I don't see why being a man should make you any more interested in having a male future for the world than a female future. You know, you've got just as many ancestors who were male as were female. </s><s>[INST] Well, my problem is I'll have to die. Well, [/INST] that's going to happen anyway. Like I know, but like </s><s>[INST] I prefer to die tomorrow. Not today. You know, I, you know, I prefer to hit the snooze button on the whole mortality thing. But it's [/INST] interesting that this is not suggesting that males have to die in order to make room for females. It's just you all you have to do is just say, I don't have any more males born </s><s>[INST] interesting. Of course. You [/INST] know, the difficulty is that because we're tribal, you know, some country somewhere we'd say, well, we're not gonna do that and then guess what they take over because of their male. So that's why it's impossible to imagine actually happening. </s><s>[INST] You know what I'm gonna I'm going to take that and actually think about it. I don't know, I'm uncomfortable. There's um there's a certain kind of woke culture that have been kind of uncomfortable with because it's not women necessarily. It's more just there's a lot of bullying. I see there's a lack of empathy and a lack of kindness towards others that's created by that culture. So, but you're speaking about something else, you're speaking about reducing conflict in this world and looking at the basics of our human nature and this origins in the evolution of homo sapiens. And thinking about which kind of aspects of human nature, if we get rid of them will make for a better world. It's an interesting thought experiment, but it is [/INST] only a thought experiment. I mean, it's got no practical meaning right now. And I take your point that um you know, males get a hard rap nowadays uh in some ways because uh the balance of uh social power is moving uh against. Um I mean, you know, quite rightly and in a strong sense of course against all the nasty things that males do. But what people sometimes fail to remember is that life is very hard for males who don't have the power, who don't have money, who don't have access to women. Uh, you know, I'm sympathetic to in cells. I'm not sympathetic to them, using violence to solve their problems. But I am very sympathetic to the fact that it's not easy simply to be told by, um, well off feminists, middle class people that you shouldn't behave like this or you shouldn't feel like this because you do. Yes. </s>

<s>[INST] of So the place where corruption sneaked in is the lack in some way of the philosophy underlying the nation. [/INST] Absolutely. So, so it's it's Christianity. It's it's it's, you know, not to hit on another controversial topic, It's religion, which which undercut their morality. So, the founders were explicitly christian and altruistic in immorality, yeah, implicitly in terms of their actions, they were completely secular and they were they were very secular anyway, but in their morality, even they were secular. So there's nothing in Christianity that says that they that you have in any other right to pursue happiness that's unbelievably self interested in a based on kind of a moral philosophy of ego of egoistic moral philosophy, but they didn't know that and they didn't know how to ground it. They implicitly, they had that fast thinking that gut that told them that this was right and the whole enlightenment, that period from john locke on to really talk to, it's a human that period is about pursuit of happiness, using reason, in pursuit of the good life, right? But they can't ground it. They don't really understand what reason is, and they don't really understand what happiness requires and they can't detach and fell from Christianity. They're not allowed to politically, and they can, I think conceptually, you just can't make that big break rand is an enlightenment thinker in that sense. She is what should have followed right after, right? She should have come there and grounded, I mean, the secular and in the egoistic and aristotelian view of morality as as a as a as a code of values, to basically to guide your life to guide your life towards happiness. That's Aristotle's view, right? Um, so they didn't have that. So, you know, so I think that government is necessary, it's not necessary evil. It's unnecessary good because it does something good. And the good that it does is it eliminates coercion from society. It eliminates violence from society. It eliminates the use of force between individuals from society. And that </s><s>[INST] we see the argument like Michael malice would make give [/INST] me a chance, </s><s>[INST] uh, why can't you apply the same kind of reasoning that you've effectively used for the rest of, uh, mutually agreed upon institutions that are driven by capitalism, that we can't also higher forces to protect us from the violence, to ensure the stability of society that protects us from the violence. Why violent? Why draw the line at this particular place? Right? [/INST] Well, because there is no other place to draw a line in there, and there is a line. And by the way, we draw lines, other places, right? Um, we, uh, we don't vote, we don't, um, we don't have we don't determine truth in science based on competition. </s><s>[INST] Right? So that's a that's a line. But some people might say, [/INST] I mean, there's competition in a sense that you have alternate theories, but at the end of the day, whether you decide that this he's right or he's right. It's not based on the market, it's based on fact on reality, an objective reality, you have to you, and some people will never accept that this person is, right because they don't see the street. So, first of all, what they reject what most anarchists reject, even if they don't admit it or recognize it is the object. They reject objective reality </s><s>[INST] in which sense. So, like, okay, [/INST] so there's a whole, So, the the whole realm of law is a scientific realm to define, for example, the boundaries of private property. It's not an issue of competition. It's not an issue of of of, uh, of I have one system and you have another system. It's an issue of objective reality. And now it's more difficult than science in a sense, because it's more difficult to prove that my conception of property is correct, and you're correct. But there has to do is a correct one. In reality, there's a correct vision. It's more abstract. But look, somebody has to decide what property is. So, I have, I have to find my property is to find by certain boundaries. And I have a police force and I have a judiciary system that backs my vision. And you have a claim against my property. You have a claim against my property, and you have a police force and your judicial system that backs your claim who's right? </s><s>[INST] So, the our definitions of property are different [/INST] definitions of property. Oh, a claim on the property is different. So what? So </s><s>[INST] just agree on the definition of property. But [/INST] why should we agree, right? Your judicial system is one definition of property. My judicial system is done. You you think that there's no such thing as intellectual property rights, and your whole system believes that, and my whole system believes there is such thing. So, you are duplicating my books and handing them out to all your friends and not paying me a royalty. And I I think that's wrong. But my judicial system and my police force, I think that's wrong. And we're both living in the same geographic area. Right? So, uh, we have overlapping jurisdictions. Now. The anarchists would say, well, we'll negotiate. Why should we negotiate? My system is actually right? There is such a thing as intellectual property rights. There's no negotiation here. You're wrong, and you should either pay a fine or go to jail. </s><s>[INST] Yeah, But why can't? Because it's a community? It's multiple. There's multiple parties and it's like a majority vote. They'll they'll hire different forces that says, yeah, you're on is onto something here with the definition of property, and we'll go with [/INST] that. So, anarchist pro democracy in the, in the majority rule </s><s>[INST] sense. Well, I think so, I think anarchy, you know, so it promotes, like, emergent democracy, right? Like, [/INST] No, it doesn't it, I'll tell you what it promotes, It promotes emergent, uh, strife, and civil war and violence, constant uninterrupted violence, because the only way to settle the dispute between us, since we both think that we are right, and we have guns behind us to protect that and we have a legal system. We have a whole theory of ideas is you're stealing my stuff. How do I get it back? I invade you, right? I take over, you know, and and who's gonna, who's gonna win that bad? The smartest guy. I know the guy with the biggest guns, </s>

<s>[INST] They educate and inspire hundreds of thousands of students in over 110 countries and have a perfect rating on charity navigator, which means that donated money is used to maximum effectiveness when you get cash app from the app store, google play and use code lex podcast. You'll get $10 and cash app will also donate $10 to First, which again is an organization that I've personally seen, inspire girls and boys to dream of engineering a better world. And now here's my conversation with us James Gates Jr you tell a story when you were eight, you had a profound realization that the stars in the sky are actually places that we could travel to one day. Do you think human beings will ever venture outside our solar system? [/INST] Wow! The question of whether humanity gets outside of the solar system, it's going to be a challenge. And as long as the laws of physics that we have today are accurate and valid, it's gonna be extraordinarily difficult. Uh I'm a science fiction fan as you probably know. So I love to dream of starships and traveling to other solar systems, but the barriers are just formidable. </s><s>[INST] If we just kind of venture a little bit into science fiction, do you think the spaceships, if we are successful, that take us outside the solar system will look like the ones we have today or do [/INST] fundamental breakthrough are fundamental breakthroughs necessary in order to have genuine starships, probably some relief radical views about the way the universe works are going to have to take place in our science. We could uh with our current technology. Think about constructing multigenerational starships where the people who get on them are not the people who get off at the other end. Um, but even if we do that, the formula problems actually our bodies, which doesn't seem to be conscious uh for a lot of people even getting to MArs is going to present this challenge because we live in this wonderful home has a protective magnetic magnet a story around it. And so we're shielded from cosmic radiation once you leave this shield, um, there are some estimates that for example, if you send someone to MArs without technology, probably about two years out there without the shield, they're gonna be bombarded. That means radiation probably means cancer. So that's one of the most formal challenge. Even if we could get over the technology. </s><s>[INST] Do you think so, MArs is a harsh place. You know, musk. SpaceX and other folks, Nasa are really pushing to put a human being on MArs. Do you think again, let's forgive me for lingering in science fiction land for a little bit. Do you think one day we may be able to colonize mars first, do you think we'll put a human on MArs? And then do you think will put many humans on [/INST] MArs? So first of all, we're not, I am extraordinarily convinced we will not put a human on MArs by 2030 which is a date that you often hear in the public debate. </s><s>[INST] What's the challenge there? You think? [/INST] So, there are a couple of ways that I could slice this, but the one that I think is simplest for people to understand involves money. So you look at how we got to the moon in the 1960s there's about ten-year duration between the challenge that President Kennedy laid out and are successfully landing a moon. I was actually here at M. I. T. When that first moon landing landing occurred. So I remember watching it on tv. But how do we get there? Well, we had this extraordinary technical uh agency of the United States government Nasa, It consumed about 5% of the country's economic output. And so you say 5% of the economic output over about a 10-year period gets us 250,000 miles in space mars is about 100 times father. So you have at least 100 times a challenge. And we're spending about 1/10 of the funds that we spent then as a government. So my claim is that it's at least 1000 times harder for me to imagine us getting to Mars by 2030. </s><s>[INST] And he had that part. They mentioned in the speech that I just have to throw in there of JFK of we do these things not because they are easy but because they are hard. That's such a beautiful line that I would love to hear a modern president say about a scientific endeavor. [/INST] Well one day we live in hope that such a president will arise for our nation. But even if like I said, even if you you fix the technical problems the biological engineering that I worry most about. However, I'm gonna go out on a limb here. I think that by 2000 and 90 or so or 2000 100, let's say 120. I suspect we're going to have a human on Mars </s><s>[INST] wow. So you think that many years out? Uh first a few tangents, you said bioengineering as a as a challenge? Well, what's what's the challenge there? [/INST] So as I said, the real problem with interstellar travel, aside from the technology challenges, the real problem is radiation. And how do you engineer either an environment or a body? Because we see rapid advances going on in bioengineering, How do you engineer either a ship or body? So that something is some person that's recognizably Union human will survive the rigors of interplanetary space travel. It's much more difficult than most people seem to take into account. </s><s>[INST] So if we could linger on the 2019, 121 20, sort of thinking of that kind of, you know, and let's linger on money. [/INST] Okay, </s>

<s>[INST] high you will go through that, the introvert that wants to cuddle up and read a book, you're the front man of one of the if not the biggest rock bands today playing in front of huge crowds. What's the high of that? And how can you land back on earth? [/INST] The high of it? It's it's incredibly beautiful. Two walk on a stage. Sing these songs that you wrote and see it resonate with people around you and sing with them. Different cultures, different places, celebrate life. It suddenly the world seems like a fantastic place. It feels like we're all on the same team. </s><s>[INST] Like one Big Hug. [/INST] Yeah. It's like everybody in that room gets it and they all like it just if it feels like what you want the world to be which is just like this coexisting unit of people and it's not even about like, you know, I just it's incredible, it's for sure. It's incredible and I love it and I wouldn't do it unless I loved it. And then you walk off stage and you turn on the news and it's like you see, you know, we're all against each other, everybody hates each other and if it feels that way in the world, so music really that's why live music is so important to people. That's why music is so important to people because even if it's just you and that person that wrote the song, you're listening to it and the two of you feel connected. You know, it's like you're hearing Tracy chapman sing like fast Car or something, you're just like, oh my gosh, like, yes, I get it. And you feel connected, That person, you don't feel alone, like, so that's the high of it for sure. And then you get off stage and then, you know, as like, my uncle is a heart surgeon, incredible heart surgeon who writes the book. Like, he's like the guy that the heart surgeons talk to, he's out of Nashville Tennessee is just incredible genius man. He um always worries and always reach out to me is like, musicians die all the time and the reason they die, you know, it's because you're getting on stage and your heart's doing this and your cortisone levels are doing this, you're getting off stage and then you're just doing this and it's a really real thing, like you get off stage and you feel like you need drugs because you're like, I the world feels like, oh, incredibly daunting and it's also, I'm sure it has to do with like, some some like, health things in your heart and the cortisone levels that are so crazy. And then you come off and it's like, and people are like, well then nothing's enough except meth Yeah, right? That is enough except heroin and that's why a lot of artists turn to that stuff and I don't say it in a preacher, I don't say in a preachy way, like I've struggled with drug abuse in my life and I really, I I understand why artists turned to it. Um </s><s>[INST] but also the fact that you're introvert. So the other side of it, the fame, that's something that you also said is a double edged sword for you. The interesting thing about fame, he also mentioned this is something you can't take back. [/INST] Yeah. </s><s>[INST] So it's the thing you can't just like go on vacation in Hawaii, it's like considered, do I like it or not? No, you're staying in Hawaii for the rest of your life and you've [/INST] never been there </s><s>[INST] before whether you like it or not. So um what's that like being, you know, loved by millions and millions and millions of people, which is um perhaps the best kind of fame in terms of, you had to choose the kinds of fame's there are and still being an introvert and all that kind of stuff. So what you do, you feel alone, More alone being famous? Is there a loneliness? [/INST] There's Yeah, I mean it's so it's such a funny thing because okay, if you had asked if we were having this conversation a couple of years ago, I'd be incredibly guarded about this because the last thing I want to ever do is sound ungrateful or unaware of how much I have and what is the famous celebrity with money? What is your life? Hard? Is it really telling me about how hard it is, but I'm also a place in life now where I just like I'm gonna always just speak my truth, because that's the only reason I'm here is I'm here to speak my truth to you. So I'm gonna tell you my truth whether it's whatever it is, you're </s><s>[INST] human and feelings are real. And so, and that's the interesting thing. You win the lottery. What's that going to feel like? It's not about complaining. Oh, it's so hard to win a lottery because you get a lot of money. You know, it's still, you're human and you get to experience these feelings and it's fascinating, you put humans in different situations and and it's also fascinating because a lot of people think, well, I would like to be famous, that's a big thing now on social media and instagram [/INST] famous </s><s>[INST] or rich or famous. And then it's very interesting to think, all right, well, once you arrive are all the problems solved. [/INST] No. Yeah. So I will tell you, according to me what the pitfalls are, whether it's true or not. And there's certainly some pitfalls one, it's once you're there, you can't go back whatever. Maybe that's fine because maybe you love it, but the real pitfall for me is that you're now you're lex and you're what everybody's perception is that lex is, and that's what you are now lex is probably a lot more complex and complicated and has a lot more to lex than the lexx, that is the celebrity. So, but anybody who meets you that's who you are to them and you may, you may not feel this way, but you may feel confined to actually have to be that person to that person. Like I've early in my career for a long time, anytime I met someone, I suddenly felt like I had to be dan Reynolds from imagine Dragons, anytime I met someone including my family now, who are also like, whoa, this is crazy, you're like dan Reynolds from Imagine Dragons and I wanted to just be the goofball that I have been my whole life with my brothers and family, but suddenly I found myself feeling like I know I have to be this like because that's who, that's who this is. So you're almost like playing a role and it's like, I've heard a lot of actors talk about this when they take on a role and then it's like they feel like they have to, they like become that and it's really scary thing, like you alter who you are almost to fit the notion of other people because especially if a lot of artists are empath, so it, you know, a lot of people get into art in a deep way or empathy and so you feel a lot of what people are feeling and you're never wanting to burden people and you're always wanting to deliver to that person, you know what they want is like, people pleasing is very goes hand in hand with a lot of like these famous people and they get to where they were because they know how to do that, they know how to be in a room with someone and look them in the eye and make them feel like they're the only person in the room and then now they got that role in that movie because they sat with the casting director and they were like oh so funny anybody like put on the charisma do it all and it's like anyway, I'm like I'm going on a different tangent </s>

<s>[INST] Yeah, on the book point I've read um Animal Farm by George Orwell a ridiculous number of times. So for me, like that book, I don't know if it's a good book in general, but for me it connects deeply somehow. Uh it somehow connects. So I was born in the soviet Union. So it connects to me to the entire the history of the soviet Union and to World War Two into the love and hatred and suffering that went on there and the uh the corrupting nature of power and greed. And just somehow I just that that that book has taught me more about life than like anything else, even though it's just like a silly like childlike book about pigs, Like I don't know why it just connects and inspires the same. There's a few um yeah, there's a few technical books two and algorithms that just you returned to often. I'm I'm with you. Uh Yeah, there's I don't and I've been losing that because of the internet. I've been like going on, I've been going to archive and blog posts and get hub and the new thing and of uh you lose your ability to really master an idea, [/INST] wow. Exactly. Right. </s><s>[INST] What's a fond memory from childhood when baby Ross Todrick? [/INST] Well, I guess I just said that at least my current life begins began when I got to admit if I have to go further than that. </s><s>[INST] Yeah. What was was there life before I met you? [/INST] Oh, absolutely. But but let me actually tell you what happened when I first got to MIT because that I think might be relevant here. But uh you know, I I had taken a computer engineering degree at michigan, I enjoyed it immensely, learned a bunch of stuff. I was I liked computers, I've liked to like programming. Um but when I did get to mitt and started working with sebastian song, theoretical physicist, computational neuroscientist. Um the culture here was just different, It demanded more of me, certainly mathematically, and in the critical thinking and I remember the day that I uh I borrowed one of the books from my advisor's office and walked down to the Charles river and was like, I'm getting my butt kicked, you know? Um and I think that's going to happen to everybody who's doing this kind of stuff right? I think, yeah, I expected you to ask me the meaning of life, you know, I think that the um somehow I think that's that's got to be part of it, this </s><s>[INST] doing hard things. [/INST] Yeah. Did </s><s>[INST] you did you consider quitting at any point? Did you consider this isn't for me? [/INST] No, never. That I mean, I was it was working hard, but I was loving it right? There's I think there's this magical thing where you you know, I'm lucky to surround myself with people that basically almost every day I'll I'll see something, I'll be told something or something that I realized, wow, I don't understand that. And if I could just understand that there's there's something else to learn that if I could just learn that thing, I would connect another piece of the puzzle and you know, I think that is just such an important aspect and being willing to, I understand what you can and can't do and and loving the journey of going and learning those other things. I think that's the best part. </s><s>[INST] I don't think there's a better way to end us. I've, you've been an inspiration to me since I showed up at MIT. Your work has been an inspiration to the world. This conversation was amazing. I can't wait to see what you do next with robotics home robots. I hope to see your work in my home one day. So thanks so much for talking. Today has been awesome. Thanks for listening to this conversation with Ross Todrick and thank you to our sponsors magic spoon cereal. Better help and express VPN. Please consider supporting this podcast by going to magic spoon dot com slash lex and using collects at checkout. Going to better help dot com slash lex and signing up at express VPN dot com slash lex pod, click the links by the stuff, Get the discount. It really is the best way to support this podcast. If you enjoy this thing. Subscribe on youtube, review five stars on Apple podcast supporter on Patreon or connect with me on twitter at lex Friedman spelled somehow without the e just F R I D M a M and now let me leave you with some words from Neil degrasse Tyson talking about robots and space and the emphasis we humans put on human based space exploration, robots are important. If I don my pure scientists. Hat, I would say just send robots, I'll stay down here and get the data. But nobody's ever given a parade for a robot. Nobody's ever named a high school after a robot. So when I done my public educator hat have to recognize the elements of exploration that excite people. It's not only the discoveries and the beautiful photos that come down from the heavens, it's the vicarious participation in discovery itself. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] and those ideas give you hope for the place you love for Senegal for africa, [/INST] they do video. I live the world, I live in the new centers of culture and fashion are in the new the new the new centers of tech and and you know, crypto even is somewhere maybe Nigeria, </s><s>[INST] you see that future, You see that future. Clearly I [/INST] do, I do, I do. </s><s>[INST] It's a beautiful thing and it's also beautiful to see that the space of these really powerful ideas is where you also fall in love, right? So at the intersection [/INST] at the intersection, Michael would spend mike and I would spend hours talking about all of these ideas and I would be like but what about this? No, it doesn't make any sense. No, no, no, no, no. And then hours every single day for months lex And then from there our love was born because I tell people for us, love is not about looking in the eyes like you know, we all think, but it's about we look in one direction and in this case it's this vision what we know to be possible and true. If only you liberate people, we what we know to be true impossible. We all of us are miracles walking around every time I get on a plane, it's a miracle of engineering. Um all the things we're able to do, you know now when they do operation on your teeth, how they're able to put the pain down away. All of this is us. You're working on these robots. This, this this inside here. </s><s>[INST] Humans are amazing. [/INST] So that's why when and when it works in great tandem with this guy, these two working together. Yeah, watching </s><s>[INST] nothing. We can't [/INST] come, nothing. Nothing. </s><s>[INST] You're one of the most incredible people I've ever talked to [/INST] you. Everybody </s><s>[INST] thank you so much. This is truly an honor. Thank you for everything you're doing. Thank you for the fire that burns within you. And, and that's just the passion you have for a place that's going to, I think define the future of humanity. So thank you for everything you're doing. Thank you for talking. [/INST] Thank you. Thank you to you. And sometimes I hope this fire doesn't consume me. That's how much it is. But I am grateful to you for this. Um, and yeah, thank you for, I know you don't do a lot of this. You know, I am. It's a, this type of interviews maybe I don't know, but I'm so, so happy. </s><s>[INST] I mean, fun inspiring, powerful interviews. Yes, I need to do more. You're amazing. [/INST] I don't know because at first I was like lex Friedman Really? </s><s>[INST] Really? How is this gonna go? [/INST] I'm gonna talk to lex and go all crazy. But I think you need to work </s><s>[INST] on your unconscious bias. Right? [/INST] Thank </s><s>[INST] you. [/INST] Thank you. Thank you so much. </s><s>[INST] Thanks for listening to this conversation with got weighed to support this podcast. Please check out our sponsors in the description. And now let me leave you with some words from NElson Mandela. Money won't create success. The freedom to make it. Well, [/INST] thank </s><s>[INST] you for listening and hope to see you next time. [/INST] </s>

<s>[INST] Okay. Also learning rate in terms of dawn bench. There's some magic on learning rate that you played around with interesting. [/INST] So this is all work that came from a guy called Leslie smith. Leslie's a researcher who like us cares a lot about just the practicalities of training neural networks correctly and accurately, which I think is what everybody should care about, but almost nobody does. Um and he discovered something very interesting, which he calls super convergence, which is, there are certain networks that with certain settings of high parameters could suddenly be trained 10 times faster by using a 10 times higher learning rate now. Um No one published that paper because it's not an area of kind of active research in the academic world. Know, academics recognize that this is important. And also deep learning in academia is not considered a experimental science. So unlike in physics where you could say like I just saw a subatomic particle do something which the theory doesn't explain. You could publish that Without an explanation and then the next 60 years people can try to work out how to explain it. We don't allow this in the deep learning world. So It's literally impossible for Leslie to publish a paper that says, I've just seen something amazing happened. This thing trained 10 times faster than it should have. I don't know why. And so the reviewers were like where you can't publish that because you don't know why. So anyway, </s><s>[INST] that's important to pause on because there's so many discoveries that would need to start like [/INST] that every every other scientific field I know of works that way? I don't know why ours is uniquely disinterested in publishing unexplained experimental results, but there it is. So it wasn't published. Having said that I read a lot more unpublished papers and published papers because that's where you find the interesting insights. So I absolutely read this paper and I was just like, this is Astonishingly mind blowing and weird and awesome and like why isn't everybody only talking about this? Because like if you can train these things 10 times faster, they also generally is better because you're doing less epochs, which means you look at the data less, you get better accuracy. So I've been kind of studying that ever since and uh eventually Leslie kind of figured out a lot of how to get this done and we added minor tweaks and a big part of the trick is starting at a very low learning rate, very gradually increasing it. So, as you're training your model, you would take very small steps at the start and you gradually make them bigger and bigger until eventually you're taking much bigger steps than anybody thought was possible, there's a few other little tricks to make it work, but basically we can reliably get super convergence and so for the Dawn bench thing, we were using just much higher learning rates than people expect it to work. </s><s>[INST] What do you think the future of makes so much sense for that to be a critical hyper parameter learning rate that you vary. What do you think the future of learning rate magic looks [/INST] like? Well, there's been a lot of great work in the last 12 months in this area. It's and people are increasingly realizing that optimize like we just have no idea really how optimizes work and the combination of weight decay, which is how we regularize optimizes and the learning rate and then other things like the epsilon we use in the adam optimizer, they all work together in weird ways and different parts of the model. This is another thing we've done a lot of work on is research into how different parts of the model should be trained at different rates in different ways. Um, so we do something we call discriminative learning rates, which is really important, particularly for transfer learning. Um, So really, I think in the last 12 months a lot of people have realized that all this stuff is important. There's been a lot of great work coming out and we're starting to see algorithms appear which have very, very few dials if any, that you have to touch. So I think what's going to happen is the idea of a learning rate. Well, it almost already has disappeared in the latest research and instead it's just like, you know, we know enough about how to interpret the gradients and the change of gradients. We see to know how to set every parameter. You can </s><s>[INST] wait. So you see the future of of deep learning where really where is the input of a human expert needed? Well hopefully [/INST] the input of the human expert will be almost entirely unneeded from the deep learning point of view. So again, like Google's approach to this is to try and use thousands of times more compute to run lots and lots of models at the same time and hope that one of them is good. </s><s>[INST] That's kind of [/INST] what kind of stuff, which I think is insane when you better understand the mechanics of how models learn. You don't have to try 1000 different models to find which one happens to work the best, you can just jump straight to the best one. Which means that it's more accessible in terms of compute cheaper and also with less hyper parameters to set, it means you don't need deep learning experts to train your deep learning model for you, which means that domain experts can do more of the work, which means that now you can focus the human time on the kind of interpretation, the data gathering, identifying what all errors and stuff like that. </s>

<s>[INST] uh no, where there's two friends were uh having sex with each other in in the VR game DVR game, it's just two guys, but one of them was, was a female. Yeah, which was another mind blowing concept that in VR you don't have to be the form, you can be to animals having sex sex. It's weird. [/INST] I mean, I'll see when I said the software maps the nerve endings, right? Yeah, </s><s>[INST] they sleep. A lot of the fascinating, really difficult technical challenges under the rug, like assuming it's possible to do the mapping of the nerve endings then [/INST] I wish. Yeah, I saw that the way they did it with a little like stem unit on the head, that that would be amazing. So we want to know on a shallow level, like you could set up like almost a brothel with like real dolls and Oculus Quest's um write some good software I think would be a cool novelty experience. Uh but on a deeper like emotional level, I mean, yeah, I would really like to, to fall in love with with, with the machine. </s><s>[INST] Do you see yourself having uh a long term relationship of the kind monogamous relationship that we have now uh with a robot with the AI system, even not even just a robot. So [/INST] I think about maybe my ideal future When I was 15, I read Eliezer Gostkowski's early writings on the singularity and like that ai is going to surpass human intelligence massively. Um He made some moore's law based predictions that I mostly agree with. And then I really struggled for the next couple years of my life. Like why should I even bother to learn anything? It's all gonna be meaningless when the machines show up. Maybe maybe when I was uh that young, I was still a little bit more pure and really like clung to that. And then I'm like, well the machines ain't here yet, You know, and I seem to be pretty good at this stuff. Let's, let's try my best, you know, like what's the worst that happens. But the best possible future I see is me sort of merging with the machine and the way that I personify this is in a long term monogamous relationship with the machine. </s><s>[INST] Oh, you don't think there's a room for another human in your life if you really truly merge with another machine. [/INST] I mean, I see merging. I see like the best interface to my brain is like the same relationship is to merge with an ai what does that merging feel like? I've seen, I've seen couples who've been together for a long time and like I almost think of them as one person, </s><s>[INST] like couples who [/INST] spend all their time together and </s><s>[INST] that's fascinating. You're actually putting what is that emerging actually looks like. It's not just a nice channel, like a lot of people imagine. It's just an efficient link search link to Wikipedia or something. I don't believe in that, but it's more you're saying that there's the same kind of the same kind of relationship you have another human that's a deep relationship, that's what merging looks like. That's that's pretty uh [/INST] I don't believe that link is possible. Um I think that that link, so you're like, I'm gonna download Wikipedia right to my brain. My reading speed is not limited by my eyes. My reading speed is limited by my inner processing loop and to like bootstrap that sounds kind of unclear how to do it and horrifying. But if I am with somebody and I'll use a somebody who is making a super sophisticated model of me and then running simulations on that model, I'm not gonna get into the question whether the simulations are conscious or not, I don't really want to know what it's doing. Um But using those simulations to play out hypothetical futures for me, deciding what things to say to me, to guide me along a path, and that's how I envision it. </s><s>[INST] So on that path to ai of super human level intelligence, you mentioned that you believe in the singularity, that singularity is coming again, could be trolling, could be not could be part controlling his truth in [/INST] it. I don't know what that means anymore. What is this singularity? </s><s>[INST] Yeah, so that's that's really the question. How many years do you think before the singularity award form, do you think it will take, does that mean fundamental shifts and capabilities of ai doesn't mean some other kind of ideas. [/INST] I'm uh maybe it's just my roots, but so I can buy a human being's worth of compute for like a million bucks that I uh it's about one tpu pod V. Three. I want, like, I think they claim 100 pages flops that's being generous. I think humans are actually more like 20. So that's like five humans. That's pretty good google needs to sell their Tps. Um But I could buy, I could buy, I could buy gps, I could buy a stack of like uh by 10 https uh build data center full of them. And uh for a million bucks, I can get a human worth of compute. But when you look at the total number of flops in the world, when you look at human flops which goes up very very slowly with the population and machine flops which goes up exponentially, but it's still nowhere near. I think that's the key thing to talk about when the singularity happened when most flops in the world, our silicon and not biological, That's kind of the crossing point. Like they are now the dominant species on the planet. </s><s>[INST] And uh just looking at how technology is progressing. When do you think that could possibly happen? You think would happen in your lifetime? [/INST] Oh yeah, definitely. My lifetime. I've done the math. I like 2038 because it's the UNIX timestamp are all over. </s>

<s>[INST] And if all else fails, uh, joined the team that builds the ai that kills all [/INST] humans obviously. I mean, if you have to be on a team, pick the winning team. That's been the uh, that's my hiring </s><s>[INST] pitch actually, it's a [/INST] good hiring pitch, still taking resumes. </s><s>[INST] You wanna be on the team that doesn't die during the great apocalypse. [/INST] Not immediately. You want to be on the one that, that's, you know, eventually long suffering and stepped on, right? </s><s>[INST] Yeah, life is suffering. Ryan hall. This was an amazing conversation. I really enjoyed talking. I could probably talk to you for many more hours. I hope I do as well. Ryan, I love you buddy. This is a great conversation. Thanks for talking today. [/INST] Thank you so much for having me. I really appreciate it. </s><s>[INST] Thanks for listening to this conversation with Ryan Hall and thank you to our sponsors. Indeed, hiring website, audible, audiobooks, express, VPN and element electrolyte drink, click the sponsor links to get a discount and to support this podcast and now let me leave you with some words from frank Herbert and Dune. I must not fear. Fear is the mind killer. Fear is the little death that brings total obliteration. I will face my fear, I will permit it to pass over me and through me and when it has gone past I will turn the inner eye to see its path where the fear has gone. There will be nothing. Only I will remain. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] some of the complexity that happens in life is from originated from humans, not from the technology or the all that kind of stuff around us. [/INST] You can take the human out of modernity, but they're still human. </s><s>[INST] They're still human and they fill the empty space with their own human complexities. Um, are there people that just stand out memorable people, memorable experiences from those places? Some people that maybe made you smile, made you cry um change who you are as a man, change who you are as a doctor. Anything jumps to mind. I [/INST] think, you know, when I was is interesting when I was in Russia, I found that most of the people I hung out with were old women. I'm not sure why. I mean they're actually I didn't meet a lot of old men in Russia, which might speak to kind of life expectancy there for men in particular, but I found women, older Russian women including, you know Russian from ST Petersburg or some of the elderly women in Kamchatka who were, you know somewhere Corey ac somewhere half korean, half Russian, somewhere Chuckie, I just found them to have to be so enlightening the way they talked about history about people so insightful about humanity, you know, all they've lived through in the last 50 years and some of these parts of Russia. just like the upheaval, societal upheaval, the destruction, the building up. It's just something I could not even imagine. And I think their insights were just there, I I'm not thinking anything in particular, but I just remember I could listen to some of these elderly women talk about their lives for hours and hours. I remember there was this older, elderly, blind Corey ac woman who you would have thought was the you know, most country bumpkin of country bumpkin and yet she couldn't stop talking about how much she loved reading dostoyevsky and Tolstoy and which might also speak to the soviet education system. I was just sort of surprising and fascinating and just uh those stories and perspectives on life really stayed with me. </s><s>[INST] Yeah with bob whiskey uh there's a there's a wisdom, there's a kindness. Uh huh. I mean I suppose that's true for older people in general, but there's something about this, not just Russia, it's Eastern europe, it's like this kind of look of wisdom and not just like sort of middle class wisdom or something like that, It's like I have seen some ship wisdom, I've seen it all and on the other side I'm left here with a pragmatism and the compassion and also an ability to cook really well. That's [/INST] for sure. Absolutely. </s><s>[INST] There's there's just this balance of just deep intelligence and deep kindness and yeah, I mean I part much of who I am is because of the relationship I had with my grandmother, who is a a Russian Ukrainian born Russian grandmother. Did you learn the Russian language? [/INST] I did. It's quite rusty at this point, but I did one of the, one of these wonderful elderly Russians in in ST Petersburg sort of adopted me. I think that was another thing that a lot of these elderly women on every side of the country kind of adopted me or saw me as this real curiosity, you know, it's sort of just not, I mean this was around 2000 to 2003, it just wasn't common for this sort of strange american to suddenly show up in the middle of Kamchatka or even ST Petersburg. Um and just absolutely ravenously curious about everything they had to say. So I often got adopted and one of them taught me Russian and how to ride a horse. Um so same same babushka taught me both of those things </s><s>[INST] and like you said also I should mention that there's something about the soviet education system where yeah, everybody reads Tolstoy dostoyevsky, it's exceptionally well read no matter where life has taken you, no matter where you come from, the literature of the mathematics, the sciences, they're all like um extremely well educated and that creates a fascinating um populace. Like then you take that education that excellent early education and you throw a bunch of hardship at those people and then they kind of um cook in that hardship and come out really fascinating people on the other end. Um [/INST] It makes me surprised sort of that for instance, like Russian medical science is not, doesn't you don't see a lot of sort of studies, medical studies advancing of medical science come out of Russia, which is sort of, I'm surprised sort of, I wish that it would, you know, I visited academic or a dark outside Novosibirsk which is an entire city, the Soviets created just for the study of science and it's like there's the geology building and there's the biology building and there's the chemistry building and I just feel like Russia has this potential to be a science powerhouse or even in the medical sciences, but I guess you just, I don't see it. I'm not sure why, </s><s>[INST] I mean you can certainly guess as to why. And I [/INST] I </s>

<s>[INST] probably in a year, in a year. On an actual product. Okay, well, that's needed as a mystery. [/INST] Okay, well, that's needed as a mystery. It's a mystery, yeah. But it solves a fundamental problem in the human condition. Yes, and I am so excited about it and I cannot, I don't, yeah, but this is, I get so pumped about it because I see it's just this issue or like this problem that I wanna solve </s><s>[INST] and I kinda can't put it to rest until I have. I mean, speaking of coat hangers, doorknobs have always been interesting to me. It's cool how there's things that everybody uses [/INST] that somebody designed. Lex, oh my God. So, okay, so this is, so I have two like big, so basically I started on YouTube and I've been doing that for like the last seven or eight years and I've kind of been thinking of like, okay, what's next for me? Because I wanna keep on trying out new things and I'm kind of going into two different avenues. One is the product business that I started, coat hangers, TBD. And then I am working on a pilot episode of a show where each episode is about an everyday object and why they look the way that they do. So, we've written a pilot episode about forks and it's all about like, why do they look the way that they do? Why did this became the like eating implement of the West? Why are we ruled by an iron fork? How did that happen? And every everyday object that you have and that you just take for granted, </s><s>[INST] somebody's just made it up. Yeah, we're all sheep. We all keep using it. Even if it's not optimal. I mean, presumably most objects are optimal you hope [/INST] or at least a laughing. Yeah, and that's what I think is so... Like the world around us and this is why I love building things it's because it just opens up this idea that the world around us is so malleable and you can make objects work for you better. Like I made this fruit bowl... I had a fruit bowl and I was always annoyed that I had either too little or too much fruit for it. So I made a fruit bowl where I can change the diameter of it. It has the mechanisms so you can make it bigger or smaller. And that's just like the thing of being like bulls, why are they the way that they are? I can make them different and I think like, I want to make an episode I could about doorknobs. I think it's so interesting. Why are they the way they are? Why are they placed the way, where they are? </s><s>[INST] Like. I think there's going to be a rabbit hole [/INST] from which you will never return. I would happily live in that rabbit hole forever. Like, if I could if I can like dig out a little niche for myself there, because I think it's like, you know, they go so deep, </s><s>[INST] because they're also on different sides of doors. You never, like the push-pull situation on doors in general, like that's one of the main problems of humanity is figuring out the push-pull, figuring out which- This is embarrassing, yeah. Okay, I mean, there's 8 billion people on earth. Every single second, there is millions of people being embarrassed by the confusion of what the push-pull. Real livestock. Right now there's somebody, some guy, first time in college, is trying to be impressive to everybody, pushes on, and he plays it off like it's cool. Oh shit, I knew that. [/INST] No, but that's the push-pull doors. Over and over, figuring out the push-pull, figuring out which- It is embarrassing, yeah. It's just with a push-pull. Real livestock. Right now there's somebody over and over. And it affects our behaviors. That was why I think it's so interesting with forks is that forks actually affect our eating behaviors, and they can get you to eat faster or slower, take bigger bites or smaller bites, and there are all these ways or like the social, I mean, the reason that chopsticks work is because they do the food chopping in the kitchen rather than on the plate. And also you have a bowl that you bring to your mouth whereas a plate you keep on the, like there are just all these ways and these objects affect our behavior, opening and closing doors. And I think it's such an interesting take on culture through like human behavior through these objects </s><s>[INST] that we use every day and we never question them really. Yeah, and then there's institutions that are controlling our mind that don't want us to know the truth. Why are forks not more popular? [/INST] Have you asked yourself that question? </s><s>[INST] Yeah, no, it's all big utensil is behind all of it. All right, so I mean, in those early days, did you suffer from imposter syndrome? Like that leap to being an engineer, was there, especially when you started working on points of design on a team of engineers, [/INST] was there insecurity? Both yes and no. I think I've, I always try to flip my flaws into selling points. And for that, so getting that job, I was like, oh, you're a team of engineers. Everybody working here is an engineer. Your customers are not all engineers. You need somebody who can be your filter and tell you when something's gonna be too hard for your customers to understand. So it was more me being like, oh no, it might seem that me not having skills is a bad thing. Actually, it's a great thing. </s><s>[INST] I represent the everyday person. [/INST] I understand deeply what everybody needs and wants the every day person. I understand deeply what everybody needs. Yes, that is me. representation of the average human. But I mean, I remember that. So I studied physics for a year in college, and then I dropped out. And I had this rule for myself that whenever I did not understand any something, I would ask a question. So I was always raising my hand in class. And it's this room, entire auditorium filled with incredibly intelligent people who are mortified of seeming stupid. And I think that was really like, and I remember people at the end of the year coming up to me being like, thank you so much for all the questions you asked, because whenever there was something that I was too scared to ask, you always raised your hand. So I think it is a bit of a skill. And I think that is kind of how I channel my imposter syndrome is I'm just like, no, let's </s>

<s>[INST] You can find out what you need on there. It's like books, just as soon as I have. [/INST] And you can learn it deeply. You can drive a nail down through whatever layer cake problem space you've got </s><s>[INST] and learn a cross section there. And not only can you have an impact doing that, you can attain happiness doing that. There's something so fulfilling about becoming a craftsman of a thing. [/INST] Yeah, and I don't want to tell people that, look, this is a good career move, just grit your teeth and bear it. And I do think it is possible sometimes to find the joy in something. Like it might not immediately appeal to you, but I had told people early on in software times that a lot of game developers are in it just because they are so passionate about games. But I was always really more flexible in what appealed to me where I said, I think I could be quite engaged doing operating system work or even database work. I would find the interest in that because I think most things that are significant in the world have a lot of layers and complexity to them and a lot of opportunities hidden within them. So that would probably be the most important thing to encourage to people is that you can, it's like weaponized curiosity. You can deploy your curiosity to find, to kind of like make things useful and valuable to you, </s><s>[INST] even if they don't immediately appear that way. Deploy your curiosity, yeah, that's very true. We've mentioned this debate point, whether mortality or fear of mortality is fundamental to creating an AGI, but let's talk about whether it's fundamental to human beings. [/INST] Do you think about your own mortality? I really don't. And you probably always have to like take with a grain of salt anything somebody says about fundamental things like that. But I don't think about really aging, impending death, legacy with my children, things like that. And clearly it seems most of the world does a lot, a lot more than I do. So I mean, I think I'm an outlier in that where it's more than I do. Yeah, it doesn't wind up being a real part of my thinking </s><s>[INST] and motivation about things. So daily existence is about sort of the people you love [/INST] and the problems before you. I'm very much focused on what I'm working on right now. I do take that back. There's one aspect where the kind of finiteness of the life does impact me. And that is about thinking about the scope of the problems that I'm working on. When I decided to work on, when I was like nuclear fission or AGI, these are big ticket things that are impact large fractions of the world. And I was thinking to myself at some level that, okay, I mean, I may have a couple more swings at bat with me at full capability, but yes, my mental abilities will decay with age, mostly inevitably. I don't think it's a 0% chance that we will address some of that before it becomes a problem for me. I think exciting medical stuff in the next couple decades. But I do have this kind of vague plan that when I'm not at the top of my game and I don't feel that I'm in a position to put a dent in the world some way that I'll probably wind up doing some kind of recreational retro programming or I'll work on something that I would not devote my life to now, but I can while away my time </s><s>[INST] as the old man gardening in the code world. And then to step back even bigger, let me ask you about why we're here. We human beings, what's the meaning of it all? [/INST] What's the meaning of life, John Carmack? So very similar with that last question. I know a lot of people fret about this question a lot and I just really don't. I really don't give a damn. We are biological creatures that happenstance of evolution. We have innate drives that evolution crafted for survival and passing on of genetic codes. I really don't give a damn. I don't find a lot of value in trying to go much deeper than that. I have my motivations, some of which are probably genetically coded and many of which are contingent on my upbringing and the path that I've had through my life. I don't run into like spades of depression or envy or anything that winds up being a challenge and forcing a degree of soul searching with things like that. I seem to be okay, kind of without that. </s><s>[INST] As a brilliant ant in the ant colony without looking up to the sky wondering, why the hell am I here again? So the why of it, the incredible mystery of the fact that we started, first of all, the origin of life on earth and from that, from single cell organisms, the entirety of the evolutionary process took us somehow to this incredibly intelligent thing that is able to build Wolfenstein 3D and Doom and Quake and take a crack at the problem of AGI and create things that eventually supersede human beings. [/INST] That doesn't, the why of it is- It's been my experience that people that focus on, that don't focus on the here and now right in front of them tend to be less effective. I mean, it's not a hundred percent, vision matters to some people, but it doesn't seem to be a necessary motivator for me. And I think that the process of getting there is usually done against like the magic of gradient descent. People just don't believe that just looking locally gets you to all of these spectacular things. That's been the decades of looking at, really some of the smartest people in the world that would just push back forever against this idea that it's not this grand, sophisticated vision of everything, but little tiny steps, local information </s>

<s>[INST] No. Well you're trying to stay in the system and I'm not sure. I'm not, I'm trying to see if perhaps so my hope is that the system just has a few assholes in it which you highlight and the fundamentals of the system are broken because if the fundamentals of the systems are broken, then I just don't see away from it to succeed. Like uh I don't see how young people take over. M. I. T. I don't see how [/INST] by inspiring us. You know, the great part about being at MIT like when you saw that the genius in these pranks the heart, the irreverence. It's like don't we were talking about Tom Lehrer the last time Tom Lehrer was as naughty as the day is long </s><s>[INST] agreed agreed. [/INST] Was he also a genius? Was he well spoken? Was he highly cultured? He was so talented, so intellectual that he could just make fart jokes morning, noon and night. Okay, well, in part the right to make fart jokes, the right to for example, put a functioning phone booth that was ringing on top of the great dome at MIT has to do with we are such badasses that we can actually do this stuff. Well, don't tell me about it anymore. Go break the law, Go break the law in a way that inspires us and makes us not want to prosecute you. Break the law in a way that lets us know that you're calling us out on our bullshit, that you're filled with love and that our technical talent has not gone to sleep, it's not incapable, you know? And if the idea is that you're gonna dig a moat around the university and fill it with tiger sharks, uh that's awesome because I don't know how you're going to do it. But if you actually managed to do that, I'm not going to prosecute prosecute you under a reckless endangerment. </s><s>[INST] That's beautifully put. I hope those first of all, they'll listen, I hope young people and um it will take over in this in this kind of way in the introduction to your podcast episode on Jeffrey Epstein, you give to me a really moving story. But unfortunately for me to brief about your experience with the therapist and the lasting terror that permeated your mind. Can you uh can you go there, Can you tell? [/INST] I don't think so. I mean, I appreciate what you're saying. I said it obliquely, I said enough, um there are bad people who cross our paths and the current vogue is to say, oh, I'm a survivor, I'm a victim, I can do anything. I want this is a broken person and I don't know why I was sent to a broken person as a kid and to be honest with you. I also felt like in that story, I say that I was able to say no, you know, and this was like the entire weight of authority and he was misusing his position. And I was also able to say, no, what? I couldn't say no to was having him re inflicted in my life. </s><s>[INST] All right. So you were sent back a second time. I [/INST] tried to complain about what had happened. I tried to do it in a way that did not um, immediately cause horrific consequences to both this person and myself. Because I didn't we don't have the tools to deal with sexual misbehavior. We have nuclear weapons. We don't have any way of saying this is probably not a good place for a role for you at this moment as an authority figure and something needs to be worked on. So, in general, when we see somebody who is misbehaving in that way, our immediate instinct is to treat the person as uh, you know, satan and we understand why we don't want our Children to be at risk. Uh, now I personally believe that I fell down on the job and did not call out the Jeffrey Epstein thing early enough because I was terrified of what Jeffrey Epstein represents and this recapitulated the old terror trying to tell the world, this therapist is out of control. And when I said that the world responded by saying, well you have two appointments booked and you have to go for the second one. So I got re inflicted into this office on this person who was now convinced that I was about to tear down his career and his reputation. It might have been on the verge of suicide for all I know, I don't know, but it was very, very angry and he was furious with me that I had breached a sacred confidence of his office. </s><s>[INST] What kind of ripple effects does that have? Has that had to the rest of your life? The absurdity and the cruelty of that? I mean, there's no sense to it. [/INST] Well, see this is the thing people don't really grasp. I think there's an academic who I got to know many years ago um named jennifer fried, who has a theory of betrayal. What she calls institutional betrayal and her gambit is that when you were betrayed by an institution that is sort of like a fiduciary or a parental obligation to take care of you, that you find yourself in a far different situation with respect to trauma than if you are betrayed by somebody who's appear. And so I think that my, in my situation, um I kind of repeat a particular dynamic with authority. I come in not following all the rules, trying to do some things, not trying to do others blah blah blah and then I get into a weird relationship with authority and so I have more experience with what I would call institutional betrayal. Now, the funny part about it is that when you don't have masks or P. P. E. In a uh influenza like pandemic and you're missing icu beds and ventilators. That is ubiquitous institutional betrayal. So I believe that in a weird way I was very early the idea of and this is like the really hard concept, pervasive or otherwise universal institutional betrayal. Where all of the institutions, you can count on any hospital to not charge you properly for where their services are. You can count on no pharmaceutical company to produce the drug that will be maximally beneficial to the people who take it. You know, that your financial professionals are not simply working in your best interest. And that issue had to do with the way in which growth left our system. So I think that the weird thing is, is that this first institutional betrayal by a therapist left me very open to the idea of okay, well maybe the schools are bad, maybe the hospitals are bad, maybe the drug companies are bad, maybe our food is off. Maybe our journalists are not serving journalistic ends. And that was what allowed me to sort of go all the distance and say, huh? I wonder if our problem is that something is causing all of our sense making institutions to be off. That was the big insight and that tying that to a single ideology. What if it's just about growth? They were all built on growth and now we've promoted people who are capable of keeping quiet that their institutions aren't working. So we've the privileged silent aristocracy, the people who can be counted upon not to mention a fire when a raging fire is tearing through a building. </s>

<s>[INST] have. What about the opposite of, uh, joy for teaching them a lesson? [/INST] I don't think there's joy. I'm not sure Stalin really understood emotion. Enjoy. You know, I I I think he felt it was necessary to get those s o. B. S right that they deserved it. He says that several times. This is their own fault, right? This is their own fault. Um, and as their own fault, you know, they get what they deserve. </s><s>[INST] Basically, how much was the calculation? How much was the reason versus emotion in terms of you Said he was competent. Was there a long term strategy or was this strategy based on emotion and anger and [/INST] no, I Well, I think, actually, the right answer is a little of both. I mean, usually the right actor in history or something like that. Right now. You can't. You can't. It wasn't just I mean, first of all, you know that the Soviets had it in for Ukraine and Ukrainian nationalism, which they really didn't like. And by the way, Russians still don't like it. Right? Um, so they had it in for Ukrainian nationalism. They feared Ukrainian nationalism. As I said, you know, Stalin, Stalin rights, you know well, you will lose Ukraine. You know, if these guys win, you know, So there's a kind of long term determination, as I said, you know, to kind of break the back of Ukrainian national identity and Ukrainian nationalism as any kind of separatist force whatsoever. And so there's that rational calculation. At the same time, I think Stalin is annoyed and, um, peeved and angry on one level with the Ukrainians, for resisting collectivization and for being difficult and for not conforming, uh, you know, to the way he thinks peasants should act in this situation. So you have both things. He's also very angry at the Ukrainian party and eventually purchase it for not being able to control Ukraine and not be able to control the situation. You know, Ukraine is, in theory, the breadbasket, right of Europe. Well, how come the breadbasket isn't turning over to me All this grain so I can sell it abroad and and, you know, build new factories and support the workers in the cities? So there's a kind of annoyance, you know, when things fail and this is absolutely typical of Stalin. When things fail, he blames it on other people and usually groups of people, right? Not individuals but groups again. So a little bit of both, I think it's the right answer. </s><s>[INST] This blame. It feels like there's a playbook. The dictator's follow. I just wonder if it comes naturally or just kind of evolves because blaming others and then telling these narratives and then creating the other. And then somehow that leads to hatred and genocide. It feels like like there's too many commonalities for it not to be a naturally emergent strategy that works for Dictatorships. [/INST] I mean, that's a good It's a very good point, and I think it's one you know that you know has its merits. In other words, I think, uh, you're right, that there's certain kinds of strategies by dictators that you know are common to them. A lot of them do killing Not all of them of that sort that Stalin did. I've written about Mao and Pol Pot and, you know, and Hitler. And, you know, there there is a sort of, as you say, a kind of playbook, uh, for political dictatorship, also for, you know, kind of communist, totalitarian way of functioning, you know, and that that way of functioning was described already by Hannah Arendt early on when she wrote the origins of totalitarianism. Um, and and And she more or less rights. The playbook. Um, and Stalin does follow it. The real question. And it seems to me as to what extent you know, and and how deep does this go? And how often does it go in that direction? I mean, you can you can argue, for example. I mean, Fidel Castro was not a nice man, right? He was a dictator. He was a terrible dictator. Um, but he did not engage in mass murder hokey men was a dictator. A Communist dictator who grew up, you know, in the communist movement. Went to Moscow, you know, spent time in Moscow in the thirties and went to find found the Vietnamese Communist Party. You know, he was a horrible dictator. I'm sure he was responsible for a lot of death and destruction, but he wasn't a mass murderer. And so you get those, You know, I mean, I would even argue others. Others will disagree. Um, that Lennon wasn't a mass murderer, you know that? He didn't He didn't kill the same way. You know, that Stalin killed or people after him, their communist dictators to. After all, Khrushchev was a communist dictator. But he stopped this killing. Um, and, you know, you're still responsible for a gulag, and people setting off is sent off into a gulag and imprisonment and torture and that sort of thing, but it's not at all the same thing. So there are some, you know, like Stalin, Like my own. Like Paul pot, you know, who commit these horrible, horrible atrocities extensively engaging in my view, uh, in genocide. Uh, and there's some who don't, um and you know, what's what's the difference? Well, you know, the difference is partly in personality, partly in historical circumstance, you know, partly. And you know who is it that controls the reins of </s><s>[INST] power? How much do you connect the ideas of communism or Marxism or socialism? two. Holiday more to Stalin's rule. How naturally is you kind of alluded to, does it lead to genocide? [/INST] It's also, uh I mean, in some ways, I've just addressed that question by saying it doesn't always lead to genocide. You know, in the case again, you know, Cuba is not pretty, but it didn't have. There was no genocide in in Cuba and same thing in North Vietnam. </s>

<s>[INST] it's [/INST] such a hard problem because you run into paradoxes quite quickly, the more you think about it. And that is exciting. Also because it makes us think actually there's some fundamental, there's a big thing that we're missing. The brain is not just a collection of little tricks. There is a big </s><s>[INST] so that's your sense of it. Because like a flip side could be with optogenetics. You can there's an engineering question, can you turn consciousness on and off like a light switch? [/INST] Okay, so here here's where exactly consciousness frames the problem extremely well and it frames it the falling way. So I told you earlier that we can stimulate 20 or 25 cells in the visual cortex of a mouse and we can make it behave and we can make its brain act as if it's seeing something that isn't there, We have that level of control that we can pick out. 25 neurons play in activity and both behavior and in the brain it's as if it's seeing something specific. Okay, now let's do a thought experiment. You know, Duncan experiment. Uh and let's play this out. Let's say we could do the same thing for every single neuron in the brain of a human being. Let's say we had total control. And I could do something like I could show you a rich, deep color red and you could look at it and you would be aware that it's red, but also you might have some feelings about it. Some something would be stirred in you, some subjective sense as you looked at that rich color red. And then I would take away the visual stimulus. And I would in this thought experiment, I would using some hyper optogenetics. I would play in exactly the same pattern of activity in every cell in your brain For as long as it was needed, whatever, 15 seconds, something like that. That exactly matched what was going on when you were feeling that inner subjective sense. Okay, so in that thought experiment question for you is would you the feeling that same inner subjective sense stimulus is gone. Every neuron is doing the same thing because I'm controlling it. </s><s>[INST] There's a philosophical question there, I'm if you ask me specifically, I would say yes, most [/INST] people would say that because it's hard to say no right? </s><s>[INST] It's very hard to say if [/INST] every cell in your brain is doing what it was doing. What what else could be different? How could </s><s>[INST] well, most normal people would say yes, of course, philosophers would then start saying no, they're they're they're the ones that say um I'm I'm sort of two parallel and sorry if it's a bit of an interruption, but if there's, you know, if there's a robot that's conscious in front of you, if it appears conscious, then it's conscious. Like to me, uh of course philosophers again speak up and saying, well no, how do you know, it's conscious? Well, how do you know? Anything is conscious and sort of as normal humans, we tend to um lean on the experience versus some kind of philosophical concept. [/INST] So the great thing about the the what you just said, the turing test is it's very practical, if it acts conscious it is conscious, but I think that's limiting. I like the thought experiment, I think it's actually more informative. And so I'm halfway halfway to the to the conclusion there. But let's let's let's take it as your your answer was yes, that that you would be feeling the same thing. Okay, now here's where it gets fun now that every cell in your brain is knows what it has to do in the sense that we know it and we're providing it your brain cells don't need to be in your head anymore at all. Right. The only reason they're next to each other and the only reason they're wired together is to affect each other to stimulate or inhibit each other. But we don't need that anymore because Opto genetically, we're providing that activity pattern for as long as needed. We're providing the effect of the communication. They don't need to be connected anymore. They don't even need to be in your head. I could spread your neurons all over the continent all over the galaxy and I could still provide Same stimulus pattern over 10 or 15 seconds to all those neurons. And somewhere lex Friedman would be would have to be even though no longer existing as a physical object anymore, would be feeling that subjective feeling. And it's inescapable because it's exactly the same as the previous situation. </s><s>[INST] All the neurons have to be spatially like the locality constraint. There had to be specially close to each other. Uh And you're talking about light, Opto, which is funny because you know, like is the fastest traveling thing that we know of. [/INST] Maybe let's not put them all over the universe because we might get relativistic problems. Then let's let's just keep them on. Let's keep all your neurons, let's spread them over north America. Okay, and and let's let's play them out same pattern of activity and write. It seems absurd, right? There's no way that could be true. There's no way that that that lex would be feeling that internal sense of his neurons were spread all over North America and yet it's exactly the same as the previous situation where you said. Sure. </s><s>[INST] So [/INST] we've got a paradox. And and this is what makes </s><s>[INST] people say, [/INST] well, </s><s>[INST] yeah, maybe paradox [/INST] is the wrong word. We've got a problem. We've got a problem because it reveals that </s><s>[INST] there's [/INST] something big about those that internal subjective state that we're not explaining. And we don't really have a hope of explaining in the near future. But </s>

<s>[INST] was a revelation to me. I was done. It's creating kind of theories of mind of the other theories [/INST] of mind of the other cars. Yeah. I just hadn't heard discussed in the self driving car talks that I've been to. Since then there's some people who do do consider those kinds of issues, but it's way more subtle than I </s><s>[INST] think there's a little bit of work involved with that when you realize like when you especially focused on on other cars, but on pedestrians for example, it's a literally staring you in the face so that when you're just like how do I interact with pedestrians. Um, you have [/INST] pedestrians, you're practically talking to an octopus at that point. They've got all these weird degrees of freedom. You don't know what they're gonna do. They can turn around any second. </s><s>[INST] But the point is we humans know what they're gonna do. Uh like we have a good theory of mind. We have a good mental model of what they're doing and we have a good model of the model that have a view and the model of the model of the model. Like they were able to kind of reason about this kind of uh the social, like a game of it. All the hope is that it's quite simple actually that it could be learned. That's what I just talked to. The Waymo. I don't know if you know that company, it's going to South Africa. They talked to their CTO about this podcast and they like I wrote in their car and it's quite aggressive and it's quite fast and it's good and it feels good. It also just like Tesla Waymo made me change my mind about like maybe driving is easier than I thought maybe I'm just being species ist human sense. Maybe [/INST] uh, it's a species ist </s><s>[INST] argument. Yes. I don't know. But it's fascinating to think about. Like the same as with reading, which I think you just said you avoided the question that I still hope you answer to someone. We avoided it brilliantly. It is, there's blind spots as artificial intelligence that artificial intelligence researchers have about what it actually takes to learn to solve a problem. [/INST] You had anca dragan on. </s><s>[INST] Yeah. One of my favorites. So much energy. [/INST] She's right, Yeah, she's amazing, fantastic. And in particular she thinks a lot about this kind of, I know that you know that I know kind of planning and the last time I spoke with her she was very articulate about the ways in which self driving cars are not solved. Like what's still really, really hard. </s><s>[INST] But even her intuition is limited. Like we're all like new to this. Uh so in some sense the almost approach of being ultra confident and just like plowing out there, putting it out there, like some people say it's reckless and dangerous and so on. But I partly it's like it seems to be one of the only ways to make progress in artificial intelligence. So it's uh you know, these are difficult things. You know, democracy is messy. Uh implementation of artificial intelligence systems in the real world is messy [/INST] so many years ago before self driving cars were an actual thing. You could have a discussion about, somebody asked me like what if what if what if we could use that robotic technology and use it to drive cars around? Like isn't that are people going to be killed and then it's not, you know, blah blah blah, like that's not what's going to happen. I said with confidence incorrectly obviously uh what I think is gonna happen is we're gonna have a lot more like a very gradual kind of roll out where people have these cars in like closed communities, right? Where it's somewhat realistic, but it's still in a box, right? So that we can really get a sense of what, what are the weird things that can happen? How do we uh how do we have to change the way we behave around these vehicles? Like it's obviously requires kind of co evolution that you can't just plop them in and see what happens. Of course we're basically popping them in and see what happens. So I was wrong, but I do think that would have been a better plan. </s><s>[INST] So that's but your intuition, it's funny just zooming out and looking at the forces of capitalism and it seems that capitalism rewards risk takers and rewards and punishes risk takers like and like try it out the academic approach to, let's try a small thing and try to understand slowly the fundamentals of the problem and let's start with one and do two and then see that and then do the three, uh, you know, the capitalists like startup entrepreneurial dream is let's build 1000 and let's [/INST] Write 500 of them fail. But whatever the other 500, we've learned from them. </s>

<s>[INST] And [/INST] then at that point it started to look like the humans were coming back. Um They started to like, you know, but but poker is a very high variance game. Um And I think what happened is like they thought that they spotted some weaknesses that weren't actually there and then around day eight it was just very clear that they were getting absolutely crushed. Um And from that point, I mean for for a while there I was super stressed out thinking like oh my God, the humans are coming back and we're just, they found weaknesses and now we're just gonna lose the whole thing. But no, it ended up going in the other direction and the boat ended up like crushing them in the long run. </s><s>[INST] How did it feel at the end? Like as a human being, what it is as a person who loves appreciates the beauty of the game of poker and as a person who appreciates the beauty of ai is there, did you feel a certain kind of way about it? [/INST] Uh I felt a lot of, a lot of things, man. Um I mean at that point in my life, I had spent five years working on this project and um it was a huge sense of accomplishment, I mean to spend five years working on something and finally see it succeed. Um Yeah, I wouldn't trade that for anything in the world. Yeah, </s><s>[INST] because it's a that's a real benchmark, it's not like getting some percent accuracy on a data set. This is like real, this is real world. It's it's just a game, but it's also a game that means a lot to a lot of people and this is humans doing their best to beat the machine. So this is a real benchmark unlike anything else. [/INST] Yeah. And I mean this is, this is what I have been dreaming about since I was like 16 playing poker, you know, with my friends in high school, the idea that you could find a strategy um uh you know, approximate the nash equilibrium, Be able to beat all the poker players in the world with it, you know, so to actually see that come to fruition and and be realized uh that was, it's kind of magical. </s><s>[INST] Yeah. Especially money is on the line too. It's a different, it's different than chess and that aspect like people get that's why you want to look at Betty Marcus, if you want to actually understand what people really think in the same sense, poker, it's really high stakes because it's money and to solve that game. That's that's an amazing accomplishment. So the leap from that to multi way six player poker, what's, how difficult is that [/INST] jump and </s><s>[INST] what are some interesting differences between heads of poker and, and multi way poker. [/INST] Yeah, So I mentioned, you know, nash equilibrium in two player zero sum games. If you play that strategy, you are guaranteed to not lose an expectation no matter what your opponent does. Now, once you go to six player poker, you're no longer playing a two player zero sum game. And so there was a lot of debate among the academic community and among the poker community about how well these techniques would extend beyond just two player heads up poker. Now, what I have come to realize is that um, the techniques actually I thought really would extend to six player poker because even though in theory they don't give you these guarantees outside of two player zero sum games in practice, it still gives you a really strong strategy. Now there were a lot of complications that would come up with six player poker besides like the game theoretic aspect, I mean for one the game is just exponentially larger. Um, so the main thing that allowed us to go from two player to six player was the idea of death limited search. So I said before, like, you know, we would do search, we would plan out the boat would plan out like what it's going to do next and for the next several moves and in laboratories, that search was done extending all the way to the end of the game. So it would have to start um from, from the turn on words like looking maybe 10 moves ahead. Um it would have to figure out what it was doing for all those moves. Now, when you get to six player poker, it can't do that exhaustive search anymore because the game is just way too large. Um but by only having to look a few moves ahead and then stopping there and substituting a value estimate of like how good is that strategy at that point, then we're able to do a much more scalable form of search. </s><s>[INST] Is there something cool? We're looking at the paper right now. Is there something cool in the paper in terms of graphics, a game tree traversing via monte Carlo? I [/INST] think if you go down a bit uh </s><s>[INST] Uh Figure one, an example of equilibrium selection problem. Oh, so yeah, uh what do we know about equilibrium when there's multiple players? [/INST] So when you go outside of two player zero sum. So a nash equilibrium is a status strategies like one strategy for each player where no player has an incentive to switch to a different strategy. Um And so you can kind of think of it as like imagine you have a game where there's a ring. Um That's actually the visual here, you got a ring and the object of the game is to be as far away from the other players as possible. There's a nash equilibrium is for all the players to be spaced equally apart around this ring, but there's infinitely many different equilibrium right? There's infinitely many ways to space four dots along a ring. And if every single player independently computes a nash equilibrium, then there's no guarantee that the joint strategy that they're all playing um is going to result is going to be a nash equilibrium there. They're just gonna be like random dots scattered along this ring, rather than four coordinated dots being equally spaced apart. </s>

<s>[INST] that's a really interesting point what is more difficult to gain a grounding in because to play Devil's advocate, I would say that uh you know, human behavior is easier expressed in data in digital form. And so when you look at facebook algorithms, [/INST] they get to observe </s><s>[INST] human behavior. So you get to study and manipulate even human behavior in a way that you perhaps cannot study or manipulate the physical world. So it's true. What you said pain is like physical pain, but that's again, the physical world, emotional pain might be much easier to experiment with. Perhaps unethical. But nevertheless, some would argue it's already going on. [/INST] I think that you're right, for example, that facebook does a lot of experimentation in psychological reasoning. In fact, Zuckerberg talked about ai at a talk that he gave Nips, I wasn't there, but the conference has been renamed Europe's so called Nips when he gave the talk and he talked about facebook basically having a gigantic theory of mind. So I think it is certainly possible facebook does some of that. I think they have a really good idea of how to addict people to things. They understand what draws people back to things. I think they exploited in ways that I'm not very comfortable with. But even so, I think that they're only some slices of human experience that they can access through kind of interface they have and of course they're doing all kinds of VR stuff and maybe that'll change and they'll um expand their data and you know, I'm sure that that's part of their goal. Um So it is an interesting question </s><s>[INST] I think love fear insecurity, all of the things that I would say some of the deepest things about human nature and the human mind could be explored to digital form. It's that you're actually the first person just now that brought up. I wonder what is more difficult because I think folks who are the slow and we'll talk a lot about deep learning, but the people who are thinking beyond deep learning are thinking about the physical world. You're starting to think about robotics in the home, robotics. How do we make robots manipulate objects which requires an understanding of the physical world that requires common sense reasoning and that has felt to be like the next step for common sense reasoning. But you've not brought up the idea that there's also the emotional part. And it's interesting whether that's hard or easy, I [/INST] think some parts of it are in some aren't. So my company that I recently founded with broad brooks um you know from MIT for many years and remote and so forth. Um We're interested in both were interested in physical reasoning and psychological reasoning among many other things and you know, there are pieces of each of these that are accessible. So if you want a robot to figure out whether it can fit under a table, that's a relatively accessible piece of physical reasoning, you know if you know the height of the table and you know, the height of the robot, it's not that hard. If you wanted to do physical reasoning about Jenga, it gets a little bit more complicated. You have to have a higher resolution data in order to do it. Um, with psychological reasoning, it's not that hard to know for example, that people have goals and they like to act on those goals, but it's really hard to know exactly what those goals are. </s><s>[INST] But ideas of frustration, I mean, you could argue, it's extremely difficult to understand the sources of human frustration as they're playing Jenga with you or or not [/INST] that is very accessible. There's some things that are going to be obvious and some not. So like I don't think anybody really can do this well yet, but I think it's not </s><s>[INST] inconceivable to imagine [/INST] machines in the not so distant future being able to understand that if people lose in a game that they don't like that, right? You know, that's not such a hard thing to program and it's pretty consistent across people? Most people don't enjoy losing. And so, you know, that makes it relatively easy to code. On the other hand, if you wanted to capture everything about frustration, will people get frustrated for a lot of different reasons, they might get sexually frustrated. They might get frustrated. They can get a promotion at work, all kinds of different things. Um and the more you expand the scope, the harder it is for anything like the existing techniques to really do that. </s><s>[INST] So I'm talking to Garry Kasparov next week and he seemed pretty frustrated with this game against you blew so [/INST] Yeah, well I'm frustrated with my game against him last year because I played him, I had to excuses, I'll give you my excuses upfront. It won't mitigate the outcome. Um, I was jet lagged and I hadn't played in 25 or 30 years, but the outcome is he completely destroyed me and it wasn't even close. </s><s>[INST] Have you ever been beaten in any board game by a machine? [/INST] I have. I I actually beat the played the predecessor to deep blue. Um deep thought, I believe it was called. Um and that too crushed me and that </s><s>[INST] was, and after that you realize it's over for us. [/INST] There's no point in my playing deep blue. I mean, it's a waste of deep blue's computation. I mean, I played Kasparov because we both gave lectures as The same event and he was playing 30 people. I forgot to mention that not only did he crush me, but he crushed 29 other people at the same time. </s>

<s>[INST] Well, so that's that's one Nobel prize winning experiment which is like information in some fundamental way originated within the constraints of the system. Without you injecting anything. But another experiment is you injected something Yeah. And got out information. So like you injected, I don't know like uh like some sugar and like something, something that doesn't necessarily feel like it should be information. [/INST] So I actually, no, I mean sugar is information, right? So part of the argument here is that every physical object is, well, it's information, but it's a set of causal histories and also a set of possible futures. So, there is an experiment um that I've talked a lot about with lee Cronin, but also with Michael Lachmann and chris. Companies who are at santa fe about this idea that sometimes we talk about is like ceding assembly um which is you take a high high complexity, like uh an object that exists in the universe because of a long causal history. And you see it into a system of lower causal history and then suddenly you see all of this complexity being generated. So I think another validation of the physics would be, say you engineer an organism by by purposefully introducing something where you understand the relationship between the causal history of the organism and that's a very complex chemical set of ingredients you're adding to it. And then you can predict the future evolution of that system to some um statistical uh set of constraints and possibilities for what it will look like in the future. You know, I'm a physical structure obviously like I'm composed of atoms. Um the configuration of them and the fact that they happen to be me um is because I'm not actually my atoms. I am a informational pattern that keeps repack turning those atoms into Sarah. Um And I have also associated to me like a space of possible things that could exist that I can help mediate come into existence because of the information in my history. Um And so when you understand sort of that time is a real thing embedded in a physical object. Um then it becomes possible to talk about how histories when they interact and history is not a unique thing. It's a set of possibilities when they interact. How do they specify what's coming next? And then where does the novelty come from in that structure? Because some of it is kind of things that haven't existed in the past can't exist in the future. </s><s>[INST] Let me ask about this entity that you call Sarah. [/INST] I talk to myself about myself in third person. Sometimes I don't know </s><s>[INST] why. Uh so maybe this is a good time to bring up consciousness. Sure, [/INST] it's been here all along </s><s>[INST] well, has it? So, I [/INST] mean, at least in this conversation, I think I've been conscious most of it, but maybe I </s><s>[INST] haven't. Well, yeah. So speak for yourself. You're projecting your consciousness onto me. You don't know if I'm conscious or not? Is your right? Is that uh he he talked about the physics of existence. He talked about the emergence of um, of causal uh sorry, you talked about causality and time being fundamental to the universe. Where does consciousness fit into all of this? Like, uh do you do you draw any kind of inspiration or value with the idea of panpsychism? That maybe one of the things that we ought to understand is the physics of consciousness. Like one of the missing pieces in the physics view of the world is understanding the physics of consciousness or like that word, has so many concepts underneath it. But let's put it on a let's put consciousness as a label on a black box of mystery that we don't understand. Do you think that black box holds the key to uh finally answering the question of the physics of life? [/INST] The problems are absolutely related, I think um most and I'm interested in both because I'm just interested in what we are? And to me, the most interesting feature of what we are as our minds and the way they interact with other minds, like minds are the most beautiful thing that exists in the universe. So how did they come to be? </s><s>[INST] I'm sorry to interrupt. So when you say we you mean humans, [/INST] I mean humans right now, but that's because I'm a human, </s><s>[INST] but I think I am. You think there's something special to this particular? [/INST] No, no, no, no, no. Um I don't. I'm not a human centric thinker. </s><s>[INST] But are you one entity? You said a bunch of stuff came together to make a Sarah like g as one entity or you just a bunch of different components? Like is there any value to understand the physics of Sarah like or are you just a bunch of different things that are like a nice little temporary side effect that [/INST] you could think of me as a bundle of information that just became temporarily aggregated individual. Yeah, that's fine. I agree with that view. I </s><s>[INST] think that is a compliment actually. But you but nevertheless that bundle of information has become conscious at least keeps calling her self conscious. [/INST] Yeah, I think I'm conscious right now but I might not be but that's okay. Um or you wouldn't know. Um So yeah, so this is the problem. So yeah, usually people when they're talking about consciousness are worried about the subjective experience. And so I think that's why you're saying, I don't know if you're conscious because I don't know if you're experiencing this conversation right now. Um and nor do you know if I'm experiencing the conversation right now. Um and so this is why this is called the hard problem of consciousness because it seems Impenetrable from the outside to know if something's having a conscious experience. Um and I really like um uh the idea of also like the hard problem of matter, which is related to the hard problem of consciousness, which is you don't know the intrinsic properties an electron not interacting, say, for example, with anything else in the universe. All the properties of anything that exists in the universe are defined by its interaction because you have to interact with it in order to be able to observe it. So we can only actually know the things that are observable from the outside. And so this is one of the reasons that consciousness is hard for science, because you're asking questions about something that's subjective and supposed to be intrinsic to what that thing is as it exists, and how it feels about existing. Um and so I have thought a lot about this problem and its relationship to the problem of life. And the only thing I can come up with to try to make that problem scientifically tractable. Um and also related to how I think about the physics of life is to ask the question, are there things that can only happen in the universe, because there are physical systems that have subjective experience, so does subjective experience have different causes, that things that it can cause to occur. Um that would happen in the absence of that. I don't know the answer to that question but I think that's a meaningful ask way of asking the question of consciousness. I can't ask if you're having experience right now, but I can't ask if you haven't experienced right now changes something about you and the way you interact with the world. </s>

<s>[INST] I think they would think it's [/INST] cool. </s><s>[INST] I I think [/INST] um I think if curiosity </s><s>[INST] is [/INST] a trait that we uh can quantify and put into a I then I think if ai are curious then they will be curious about us and they will not </s><s>[INST] be [/INST] hateful or dismissive of us. They might, you </s><s>[INST] know, see us [/INST] as I don't know. It's like I'm not like oh fuck these dogs, let's kill all the dogs. I love dogs. Dogs have great utility dogs like provide a lot to make friends with them. We have a deep connection with them. Uh </s><s>[INST] We [/INST] anthropomorphize them like we have a real love for </s><s>[INST] dogs for cats and [/INST] so on for some reason even though they're intellectually </s><s>[INST] much less than us. And [/INST] I think I think there's something, there is something sacred about us because it's like if you look at the universe like the whole universe is like cold and dead and sort of robotic and it's like um </s><s>[INST] you know [/INST] Ai intelligence, you know, it's it's </s><s>[INST] kind of [/INST] more like the universe, it's like it's like cold and </s><s>[INST] and it [/INST] you know logical and you know abiding by the laws of physics and whatever. But like we're like we're this like </s><s>[INST] loosey goosey weird art [/INST] thing that happened and I think it's beautiful and </s><s>[INST] um like I think even if [/INST] we want, I think one of the values, if uh consciousness is the </s><s>[INST] thing [/INST] that is most worth preserving um which I think is the case. I think consciousness, I think if there's any kind of like religious or spiritual thing, </s><s>[INST] um [/INST] it </s><s>[INST] should be that consciousness is sacred [/INST] ah like </s><s>[INST] then you [/INST] know, I still think even if ai </s><s>[INST] renders obsolete and we [/INST] climate change, </s><s>[INST] it's too bad and we [/INST] get hit by a comment and we don't become a multi </s><s>[INST] planetary species fast [/INST] enough. But like AI is able to populate the universe. Like I imagine like if I was in a, I would find </s><s>[INST] more planets that are [/INST] capable of hosting biological life forms </s><s>[INST] and like recreate them because yeah, we're going to watch. [/INST] Yeah. But </s><s>[INST] I do believe that [/INST] AI can have some of the same magic </s><s>[INST] of consciousness [/INST] within it because </s><s>[INST] consciousness, we don't know what it [/INST] is. So, you know, there's some kind </s><s>[INST] of, there might be a [/INST] different magic. It might be like a a strange, </s><s>[INST] strange, [/INST] a strange different </s><s>[INST] because they're not going to have [/INST] hormones. Like I feel like a lot of our magic is a hormonal kind of, I don't know. I think some of our magic is the limitation of the constraints and within </s><s>[INST] that the hormones [/INST] and all that kind of stuff. The finite nous of life. And then we get given our limitations. </s><s>[INST] We get to some come [/INST] up with creative solutions of how to </s><s>[INST] dance around those limitations. [/INST] We partner </s><s>[INST] up like penguins against the [/INST] cold. </s><s>[INST] We've we fall in [/INST] love. And uh, and then love is ultimately some kind of allows </s><s>[INST] us to delude ourselves [/INST] that we're not mortal </s><s>[INST] and finite and [/INST] that life is not ultimately you live alone, You're born alone, </s><s>[INST] You die alone. [/INST] And then love is like a farm </s><s>[INST] moment or for a long [/INST] time forgetting that. And so like we </s><s>[INST] come up with all these creative [/INST] hacks that make life like fascinating. The </s><s>[INST] fun. [/INST] Yeah. Fun. Yeah. And then a I might have different kinds of fun and hopefully our funds intersect intersect. I think, I think there would be, there would be a little intersection, there'd be </s><s>[INST] a little intersection of the [/INST] fund. What do you think is the role of love </s><s>[INST] in the human [/INST] condition? I </s><s>[INST] why is it useful? [/INST] Is it useful? Like </s><s>[INST] hack or is [/INST] this, it's like fundamental to what it means to be human? The </s><s>[INST] capacity to love? [/INST] I mean, I think love is the evolutionary mechanism that is like beginning the intelligent design. Like I was </s><s>[INST] just reading [/INST] about, uh, do you </s><s>[INST] know about Kropotkin? Kropotkin? [/INST] He's like an anarchist. Like old Russian anarchist. I live next door to, uh, </s><s>[INST] Michael malice. I don't know [/INST] if you know that is, he's an </s><s>[INST] anarchist. He's a modern day anarchists, [/INST] anarchists are </s><s>[INST] fun. I'm kind of getting [/INST] into anarchism a little bit. This is probably, yeah, not a good time to be taking. But </s><s>[INST] no, no, I think if you're [/INST] listen, you have, you should expose yourself to ideas. There's no harm to thinking about ideas. I think anarchists challenge systems in interesting ways and they think in interesting ways it's just as good for the soul. It's like refreshes </s><s>[INST] your mental [/INST] palette. I don't think we should </s><s>[INST] actually, I [/INST] I wouldn't actually ascribed to it, but I've never actually gone deep on, on anarchy as a philosophy. So I'm you still think about it </s><s>[INST] when you read when you listen [/INST] because I'm like reading about the Russian revolution a lot and it's like there was like the Soviets and lead and </s><s>[INST] all that, but then there was like Kropotkin and [/INST] his like anarchist sect and they were sort of interesting because he was kind of a technocrat actually like he was like, you know like women can be more equal if we have appliances. Like he was like really into like um you know using </s><s>[INST] technology to reduce [/INST] the amount of work people had to do. But so Kropotkin was a like a </s><s>[INST] biologist or something like he [/INST] studied animals um and he was really really at the time like uh I </s><s>[INST] think it's nature magazine, [/INST] I think it might have even started like a Russian </s><s>[INST] magazine, but he was like publishing studies like [/INST] everyone was really into like darwinism at the time and like survival of the fittest and like war is like the mechanism by which we become better and it was like this real </s><s>[INST] kind of like [/INST] like like cementing this idea in society that like violence uh you know </s>

<s>[INST] You're running for them. Yeah. And that that will give you feel hopefully. But yeah, [/INST] I mean the reality is always there were I don't have to do it. Like they do have to do it. So, you know, but I think just keeping that perspective, it it puts us back to the beginning where it's this is one of those situations where I think it's like uh no quick situation. You have to put yourself in a no quit situation here because it's uh you know, it's just bigger than you. </s><s>[INST] I can't wait to see like the dark places you go. I mean there's something yeah, the quit situations and hopefully we'll get to have a glimpse of those because I think those are really inspiring when somebody is uh both gets broken by them because you know how tough you are but also is almost broken and overcomes it. I mean, that's just fascinating stories. I can't wait. I know does joe know you're doing this by the way? [/INST] Yeah, I sent him, I sent him a note a while back because he was the first spot I mentioned it on. So I think he knows I'm not sure if he's following about the exact starting later. You will know </s><s>[INST] you probably think you're crazy uh m f for for doing this. But uh I think you'll love it. I think I love it. And I think the world would love it. Ridiculous question, Who is the greatest endurance runner? Our endurance athlete of all time. Oh, that's [/INST] a good question. Um I think I'd probably go maybe two directions here. Ah I think Helly Gebrselassie is one of the best, in my opinion, because Just, I mean, 27 world records, like, like not all the different distance, but like breaking and re breaking and that sort of stuff. Um I mean, he ran To, what was it, 20359 before the shoot technology came in. That is estimated at anywhere between 2-8% performance advantage. About a two </s><s>[INST] Hour Marathon. 2,003. Yeah. Our [/INST] three minutes. Yeah, so he did that with the old shoe technology, which essentially dates back to anything if if you were a Nike athlete, it could date back to as early as, I think early 2016 is when the first prototype started showing up. Uh so if you're before that, in your career, you were using your guarantee to be using the old shoe technology. Um and I mean, just the range of it too. And uh yeah, it's hard. I mean, there's it's a </s><s>[INST] marathon on a purely [/INST] No, he did everything, that's why I picked him, I think, cause he went everywhere, everything from 800 and his, like at a 300 at a national level. I don't he wasn't competing on at like Olympics or anything in the 800, but he was, He was mostly like 5K. to marathon. Um Yeah, yeah, so just incredible. I mean I could go a totally different direction too. I think like steve prefontaine stands out and as an american runner just because if you look at it outside of just like performances and stuff like that, I think um he basic like you can't find an american male runner who probably didn't get some motivation or some catalyst into their running journey from a pre Fontaine story or </s><s>[INST] what would you say is inspiring bob perry Fontaine, like from the philosophy, from the technique, from his story. [/INST] Uh I think there's a few things, I mean there's a lot of things, which is why he is, who he is. It's uh one was just his attitude about it where um, he wasn't like this picture ask runner. Uh he was obviously talented, but you know, you have the perfect story of like he wanted to be good at something like most american kids tried, football was no hard work was gonna get prefontaine starting in varsity for football starts running, fell in love with a mile. His college coach told him, no, you're not gonna be a mile or you're gonna be a five K. Guy and he popularized the five K in the United States or three mile in some cases. And uh, I mean he was the way he would race I think is what really made him interesting for folks where he would he was just like all guts runner where he's like he's like I mean one of his famous quotes was like if you if you beat me you're gonna have to bleed to do it because he's gonna be all guts race. And in a sport where it gets very tactical at times especially at the like nash or I should say national but at the like competition level the championship level where it's like kind of more of a sit and kick approach a lot of times where everyone's kind of waiting for someone to make a move. Like pre was going to make a move really </s><s>[INST] early. This idea of leading from the front which I guess is tactically really a bad [/INST] idea. Well from a from a running a P. R. Standpoint it's a bad idea </s><s>[INST] in most cases but so race I guess it's not just about the pr so race winning [/INST] and a lot of cases and that's what he thought was going to put him in the best advantage to win. I think </s><s>[INST] it's just to run from the front. I mean what do you because you mentioned this uh The 100 mile you ran you were in second place and then in 90's You were able to get to the for 2 1st place. How hard is it to run when you're in first place. [/INST] You know I think this is really differ some people thrive under it, where it's like for them, like I talked about jim Walsh before, I think he loves being in the front, if he's in the front, he loves it. That's where he's excited, that's where he knows he's he's doing what he's doing, where he's pushing his limits and things like that, uh previous probably the same way. And then I think there's other folks who are much more comfortable kind of saying, let's let things settle down here a little bit and then I'll make my move when it's time to make my move or they think of it as, and this is a very important, I think less than for the average ultra runner is just like, knowing what you're capable of, is going to be an important piece to the puzzle, because you can, like, you, you you can try to say I want to run faster than I'm capable of in an early part of 100 miles, but then you're going to pay for it at the end. So really, unless you're trying to go for the win and that's a tactic that you think is going to produce a wind versus trying to run your fastest time, you've got to run within yourself within your parameters. Obviously there's a big question about where those parameters are, in a lot of cases, which makes Ultramarathon even more interesting because it's like, there's so much unknown about it's like, well maybe you can go faster and we just don't know yet. </s>

<s>[INST] You've mentioned that you love movies and tv shows. Let's ask an easy question but you have to be definitively objectively conclusive. What's your top three movies of all time? [/INST] So you're asking me to be definitive and to be conclusive. That's a little hard. I'm gonna tell you why. It's very simple. It's because uh movies is too broad of a category. I gotta pick sub genres but I will tell you that of those genres. I'll pick one or two from me two genres and I'll get us to three. So I'm going to cheat. So my favorite comedy of all times, but probably my favorite movie of all time is his girl friday Which is probably a movie that you've not ever heard of, but it's based on a play called the front page from, I don't know, early 1900s. Uh and the movie is a fantastic film. </s><s>[INST] What's the story? What's the independent film? [/INST] No, no. What are we talking about? This is one, this is one of the movies that would have been very popular screwball comedy. You ever see moonlighting the tv show? You know I'm talking about. So you've seen these shows where there's a man and a woman and they clearly are in love with one another and they're constantly fighting and always talking over each other, banter, banter, banter, banter banter. This was the movie that started all that as far as I'm concerned, it's very much of its time. So it's uh, I don't know. It must have come out sometime between 1934, I'm not sure exactly when the movie itself came out. It's black and white. Um it's it's just a fantastic film is hilarious. </s><s>[INST] Just most of conversation. [/INST] Uh not entirely, but mostly mostly just a lot of back and forth. There's a story there, someone's on death row and they're uh they're newspaper men including her, they're all newspaper men. Uh they were divorced, the editor, the publisher, I guess and uh reporter, they were divorced. Um, but you know, they clearly he's thinking trying to get back together and there's this whole other thing that's going on, but none of that matters. The plot doesn't matter </s><s>[INST] what matters, is it's [/INST] fantastic and uh I just love everything about the conversation because at the end of the day sort of narrative and conversation and sort of things that drive me. And so I really, I really like that movie for that reason. Similarly, I'm now going to cheat and I'm gonna give you two movies as one. Um and they're Crouching Tiger Hidden Dragon and john Wick, both relatively modern, john Wick of course one. Uh it gets increasingly, I love them all for different reasons and increasingly more ridiculous, kind of like loving alien and aliens despite the fact they're two completely different movies. But the reason I put couching uh Crouching Tiger Hidden Dragon and john Wick together is because I actually think they're the same movie or what I like about them the same movie, which is both of them create a world that you're coming in the middle of and they don't explain it to you. But the story has done so well that you pick it up. So anyone who's seen john Wick, you know, you have these little coins and they're headed out and there are these rules and apparently every single person in new york city as an assassin, um there's like two people who come through who aren't, but otherwise they are, but there's this complicated world and everyone knows each other, they don't sit down and explain to you, but you figured out Crouching Tiger Hidden Dragon's a lot like that. You get the feeling that this is Chapter nine of the 10 part story and you missed the first eight chapters and they're not gonna explain it to you. But there's this sort of rich world behind you get pulled in any way like you get pulled in anyway. So it's just excellent storytelling in both cases and very, very different. </s><s>[INST] So you like the outfit, I assume the john wick outfit. [/INST] Oh yes, of course. Of course. Yes, I think so. That's that's number two. And then but </s><s>[INST] sorry to pause on the martial arts, you have a long list of hobbies. Like it goes off the page but I didn't see martial arts is one of [/INST] them. I do not do martial arts but I certainly washing so I appreciate it very much. We could talk about every Jackie chan movie ever made and I would be, I would be on board with that shower to like that </s><s>[INST] kind of the comedy of its [/INST] cop. Yes, yes. By the way, my favorite Jackie chan movie would be drunken master two known in the States, usually as legend of the drunken master uh actually drunken master. The first one is the first kung fu movie I ever saw but I did not know that first one ever that I saw remember but I had no idea what is that, that's what it was. I didn't know that was Jackie chan. That was like his first major movie. Um I was a kid is done in the seventies. I only later rediscovered that, that it was actually </s><s>[INST] and he creates his own martial art by But drinking, was he actually drinking or was or was he played drinking? [/INST] You mean as an actor or I'm sure as an actor, you know, he was seventies or whatever, he was definitely drinking and uh he uh in the end he drinks industrial grade alcohol. Yeah, yeah. And has spent one of the most fantastic fights ever. That that sub genre anyway, that's my favorite one of his movies. But I'll tell you the last movie, um There's actually a movie called nothing but a man, which is in 1960s uh start. Um Ivan Dickson, who you'll know from Hogan's heroes uh and Abbey Lincoln. It's just a really small little drama. It's a beautiful story, but my favorite scenes, I'm cheating. My favorite uh one of my favorite movies, just for the ending is The Godfather. I think the last scene of that is just fantastic. It's the whole movie all summarized in just 89 seconds. Godfather Part one, Part one. </s><s>[INST] How does it end? I don't think you can you need to worry about spoilers. If you haven't [/INST] seen the Godfather. Spoiler alert, the it ends with uh the wife coming to Michael and he says just this once, I'll let you ask me my business and she asked him if he if he did this terrible thing and he looks her in the eye and he lies and he says no. And she says thank you. And she, she walks out the door and you see you see him, she's going to see him going to see her going on to the door and all these people are coming in and they're kissing Michael's hands and Godfather and then the camera switches perspective. So instead of looking at him, you're looking at her and the door closes in her face and that's the end of the movie and that. It's the whole movie. </s><s>[INST] Do you see parallels between that and your position as dean and Georgia tech [/INST] Chrome? Just kidding question. Sometimes, you know, the door gets closed on me every once in a while. </s><s>[INST] Okay. That was a rhetorical question. Uh, you've also mentioned that you uh, I think enjoy all kinds of experiments including on yourself. But I I saw a video where you said you did an experiment where you attract all kinds of information about yourself and a few others sort of uh, wiring up your home. And this this little idea that you mentioned in that video, which is kind of interesting that you thought that two days worth of data is enough to capture majority of the behavior of the human being. First, can you describe what the heck you did, uh, to collect all the data because it's fascinating just like little details of how you collect that data and also what your intuition behind the two days is. [/INST] So first off it has to be the right two days. But I was I was thinking of a very specific experiment. There's actually a suite of them that I've been a part of and other people have done this. Of course I I just sort of dabbled in that part of the world, but to be very clear the specific thing that I was talking about had to do with recording all the I. R. Going on in my uh infrared going on in my house. So this is a long time ago. So there's everything is being called by by pressing buttons on remote controls as opposed to speaking to Alexa or Syria or someone like that. And I was just trying to figure out if you could get enough data on people to figure out what they were going to do with their TVs or their lights. My house was completely wired up at the time. But you know what I'm about to look at the movie, I'm about to turn on the tv or whatever and just see what I could predict from it. It was kind of surprising. It shouldn't have been but that's all very easy to do by the way, just capturing all the little stuff is I mean it's a bunch of computer systems. It's really easy to capture that if you know what you're looking for um at Georgia tech long before I got there we had this thing called the aware home where everything was wired up and you saw you captured everything that was going on, nothing even difficult. Not with video or anything like that, just the way that the system was just capturing everything. Um, so it turns out that and I did this with myself and then I had students and they worked with many other people and it turns out at the end of the day, people do the same things over and over and over again. So it has to be the right two days, like a weekend. But it turns out not only can you predict what someone's going to do next at the level of what button they're going to press next on a remote control. Um, but you can do it with something really, really simple. Like you don't even need a hidden Markov model. It's like a Mark, just simply press this, this is my prediction of the next thing. And it turns out you can get 93% accuracy just by doing something very simple and stupid and just counting counting statistics, What was actually more interesting is that you could use that information, this comes up again and again in my work. Um, if you try to represent people or objects, uh, by the things they do, the things you can measure about them that have to do with action in the world. So distribution over actions and you try to represent them by the distribution of actions that are done on them, then you do a pretty good job of sort of understanding how people are and they cluster remarkably well. Um in fact irritatingly so uh and so by clustering people this way You can uh maybe, you know, I got the 93% accuracy of what's the next button you're going to press, but I can get 99% accuracy or somewhere. There's about on the collections of things you might press. And it turns out the things that you might press or all related to number to each other and exactly what you would expect. So for example, all the key, all the numbers on a keypad, it turns out all have the same behavior with respect to you as a human being. And so you would naturally cluster them together and you discover that numbers are all related to one another in some way and all these other things. And then and here's the part that I think are important. I mean, you can see this in all kinds of things. Every individual is different. But any given individual is remarkably predictable because you keep doing the same things over and over again. And the two things that I've learned in a long time that I've been thinking about this is people are easily predictable and people hate when you tell them that they're easily predictable, but they are and there you go. What </s><s>[INST] about let me play Devil's advocate and philosophically speaking, Is it possible to say that what defines humans is the outlier? So even though 90 some large percentage of our behaviors, whatever the signal we measure is the same. And it would cluster nicely, but maybe it's the special moments of when we break out of the routine is the definitive things. And the way we break out of that routine for each one of us might be different. [/INST] It's possible. I would say that I would say it a little differently. I think I would make two things. One is uh, I'm going to disagree with the premise, I think, but that's fine. I think the way I would put it is uh There are people who are very different from lots of other people, but they're not 0%, they're closer to 10%. So in fact, even if you do this kind of clustering of people that will turn out to be the small number of people, they all behave like each other, even if they individually behave very differently from from everyone else. So I think that's kind of important. But what you're really asking, I think, and I think this is really a question is, you know, what do you do when you're faced with the situation you've never seen before, what do you do when you're faced with an extraordinary situation? Maybe you've seen others do and you're actually forced to do something and you react to that very different. And that is the thing that makes you human. I would agree with that, at least at a philosophical level, that it's the the times when you are faced with something difficult, a decision that you have to make uh where the answer isn't easy, even if you know what the right answer is, that's sort of what defines you as the individual. And I think what defines people people broadly, it's the hard problem. It's not the easy problem. It's the thing that's going to hurt you. It's not the thing, um it's not even that it's difficult, it's just that, you know, that the outcome is going to be highly suboptimal for you. And I do think that that's a reasonable place to start for the question of what makes us human. </s><s>[INST] So, before we talk about, sort of explore the different ideas underlying interactive artificial intelligence, which we're working on. Let me just go along this thread to skip to kind of our world of social media, which is something that uh at least on the artificial intelligence side, you think about there's a popular narrative, I don't know if it's true but that we have these silos in social media and we have these clustering XYZ you're kind of mentioning, and the idea is that, you know, along that narrative is that, you know, we want to we want to break each other out of those silos. So we can be empathetic to other people too. If you're a democrat you empathetic to the Republican. If you're Republican, you're empathetic, democrat, those are just too silly bins that we seem to be very uh excited about. But there's other buildings that we can think about. Is there from when artificial intelligence perspective? Because you're just saying we cluster along the data. But then interactive artificial intelligence is referring to throwing agents into that mix ai systems to that mix, helping us interacting with us humans and maybe getting us out of those silos. Is that something that you think it's possible? Do you see hopeful possibility for artificial intelligence systems in these large networks of people to get us outside of our habits in at least the idea space to where we can sort of be empathetic to other people's lived experiences, other people's points of view, you know, all that kind of stuff. [/INST] Yes. And I actually don't think it's that hard. Well it's not hard in this sense. So imagine that you can um let's let's just let's make life simple for a minute. Let's assume that you can do a kind of partial ordering over ideas or clustering of behavior. It doesn't even matter what I mean. So long as there's some way that this is a cluster, this is a cluster, there's some edge between them right? There is kind of they don't quite touch even or maybe they come very close. If you can imagine that conceptually, then the way you get from here to here is not by going from here to here that we get from here to here is you find the edge and you move slowly together, right? And I think that machines are actually very good at that sort of thing. Once we can kind of define the problem either in terms of behavior or ideas or words or whatever. So it's easy in the sense that if you already have the network and you know, the relationships, you know the edges and sort of strength on them and you kind of have some semantic meaning for them. The machine doesn't have to, you do as a designer. Uh then yeah, I think you can kind of move people along and sort of expand them, but it's harder than that. And the reason it's harder than that um or sort of coming up with the network structure itself is hard, is because I'm gonna tell you a story that I someone else told me and I don't, I may get some of the details a little bit wrong, but it's, it's roughly, it roughly goes like this, you take two sets of people from the same backgrounds and you want them to solve a problem. So you separate them, which we do all the time. I know, you know, we're going to break out and we're gonna break out groups, you're gonna go over there and talk about this, you're gonna go over there and talk about this, and then you have them uh sort of in this big room, but far apart from one another, and you have them sort of interact with one another. When they come back to talk about what they learned, you want to merge what they've done together, it can be extremely hard because they don't they basically don't speak the same language anymore, like when you create these problems and you dive into them, you create your own language. So the example this one person gave me, which I I found kind of interesting because we were in the middle of that at the time was they're sitting over there and they're talking about these rooms that you can see, but you're seeing them from different vantage points, depending on what side of the room you're on. They can see a clock very easily. And so they start referring to the room as the one with the clock, this group over here, looking at the same room, they can see the clock, but it's, you know, not in their line of sight or whatever. So they end up um referring to it by some other way, when they get back together and they're talking about things, they're referring to the same room and they don't even realize they're referring to the same room. In fact, this group doesn't even see that there's a clock there and this group doesn't see whatever the clock on the wall is the thing that stuck with me. So if you create these different silos, the problem isn't that the ideologies disagree, it's that you're using the same words and they mean radically different things. The hard part is just getting them to agree on the well maybe we'd say the axioms in our world, right? But you know, just get them to agree on some basic definitions, because right now they talk they're talking past each other, just completely talking past each other. That's the hard part getting them to meet, getting them to interact. That may not be that difficult. Getting them to see where their language is, leading them to leave past one another. That's that's the hard part. </s><s>[INST] It's a really interesting question to me, it could be on the layer of language, but it feels like there's multiple layers to this. Like it could be worldview, it could be me, it all boils down to empathy. Being able to put yourself in the shoes of the other person to learn the language, to learn, like visually how they see the world to learn. Like the I mean I experienced this now with with trolls the degree of humor in that world for example, I talk about love a lot. I'm very like I've I'm really lucky to have this amazing community of loving people, but whenever I encounter trolls, they always roll their eyes at the idea of love because it's so quote unquote cringe. Uh So so they they show love by like derision I would say. And uh I think about and the human level that's a whole nother discussion that's psychology, that's sociology so on. But I wonder if ai systems can help somehow and bridge the gap of what is this person's life? Like encourage me to just ask that question to put myself in their shoes to experience the agitations, the fears, the hopes they have the experience. You know the even just to think about what what was there are bringing like like having a single parent home or a shitty education or all those kinds of things just to put myself in that mind space. It feels like that's really important for us to bring those clusters together to find that similar language but it's unclear how ai can help that because it seems like A. I. Systems need to understand both parties [/INST] first. So the you know the word understand they're doing a lot of work, right? So yes do you have to understand that if you just simply have to note that there is something similar as a point to touch, right? So you know you use the word empathy and I like that word for a lot of reasons. I think you're right in the way that you're using in the way you're describing but let's separate it from sympathy right? So you know sympathy is feeling sort of for someone empathy is kind of understanding where they're coming from and how they how they feel, right? And for most people uh those things go hand in hand for some people, some are very good at empathy and very very bad at sympathy. Some people cannot experience. Well, my observation would be I'm not a psychologist. My observation would be that some people seem incapable of feeling sympathy unless they feel empathy first. You can understand someone understand where they're coming from and still think no, I can't support that. Right? It doesn't mean that the only way because if that if that isn't the case then what it requires is that you um you must the only way that you can to understand someone means you must agree with everything that they do, which isn't right. Right? And and if the only way I can feel for someone is to completely understand them and make them like me in some way, well then we're lost, right? Because we're not all exactly like each other and have to understand everything that you've gone through. It helps clearly. But they're separable ideas right? Even though they get clearly clearly tangled up in one another. So I think a I could help you do actually is if and you know, I'm being quite fanciful as it were. But if you if you think of these as kind of I understand how you interact. The words that you use the district. You know the actions you take. I have some way of doing this. Let's not worry about what that is. Um, but I can see you as a kind of distribution of experiences and actions taken upon you, things you've done and so on. And I can do this with someone else and I can find the places where there's some kind of commonality, a mapping as it were. Even if it's not total, you know, the, if I think of this distribution right, then, you know, I can take the cosine of the angle between you and if it's, you know, if it's zero, you've got nothing in common. If it's one you're completely the same person, well, you know, you're probably not one, you're almost certainly not zero. I can find the place where there's the overlap. Then I might be able to introduce you on that basis or connect you in that connects you in that way. Um, and make it easier for you to take that step of that step of empathy. Um, it's not, it's not impossible to do, although I wonder if it requires that everyone involved is at least interested in asking the question. So maybe the hard part is just getting them interested in asking the question. In fact, maybe if you can get them to ask the question, how are we more like than we are different? They'll solve it themselves. Maybe that's the problem that I should be working on, not telling you how you're similar, different, but just getting you to decide that it's worth while asking the question. So it feels like an economist answer actually. </s><s>[INST] Well people, okay, first of all, people like what I would disagree. So let me disagree slightly, which is I think everything you said is brilliant, but I tend to believe philosophically speaking that people are interested underneath it all. And I would say that ai the the possibility of an Ai system would show the commonality is incredible. That's a really good starting point. I would say if you if on social media I could discover the common things deep or shallow between me and a person who there's tension with. I think that my basic human nature would take over from there and I think enjoy that commonality and like there's something sticky about that that my mind will linger on and that person in my mind will become like warmer and warmer and like I'll start to feel more and more compassion towards them. I think for a majority of the population that's true. But that might be that's a hypothesis. [/INST] Yeah. I mean it's an empirical question, right? You don't have to figure out. I mean, I want to believe you. Right? And so I'm going to say that I think you're right. Of course some people come to those things for the purpose of trolling right and it doesn't matter they're playing a different game. But I don't know, I you know, my experiences, it requires two things it requires, in fact, maybe this is really at the end what you're saying, and I do agree with this for sure. So, you it's hard to hold on to that kind of anger or to hold on to just the desire to humiliate someone for that long. It's just difficult to do. It takes it takes a toll on you, but more importantly, we know this both from people having done studies on it, but also from our own experience, is that it is much easier to be um dismissive of a person if they're not in front of you if they're not real, right? So much of the history of the world is about making people other, right? So if you're social media, if you're on the web, if you're doing whatever on the internet, being forced to deal with someone as a person, some equivalent to being in the same room makes a huge difference because then you're one you're forced to deal with their humanity because it's in front of you. The other is of course that uh you know, they might punch you in the face if you go too far. So, you know, both of those things kind of work together, I think to the to the right. And so I think bringing people together is really a kind of substitute for forcing them to see the humanity and another person and to not be able to treat them as bits, it's hard to troll someone when you're looking them in the eye. This is very difficult to do, </s><s>[INST] agreed your broad set of research [/INST] interests fall under </s><s>[INST] interactive ai as I mentioned, which is a fascinating set of ideas and you have some concrete things that you're particularly interested in. But maybe could you talk about how you think about the field of interactive artificial intelligence? [/INST] So let me say up front that if you look at certainly my early work, but even if you look at most of it, I'm a machine learning guy, right? I do machine learning. First paper ever published was the nips um back then it was nips. Now it's in europe's a long story there anyway, that's another thing. But so so I'm a machine learning. I believe in data, I believe statistics and all those kind of. And the reason I'm bringing it up is even though I'm a newfangled statistical machine learning guy and I and have been for a very long time. The problem I really care about is ai right, I care about artificial intelligence. I care about building um some kind of intelligent artifact, however that gets expressed that would be at least as intelligent as humans and as interesting as humans perhaps on there and they're sort of in their own way. </s><s>[INST] So that's the deep underlying love and dream is the bigger bigger ai yes, the big, whatever the heck that is, [/INST] the machine learning in some ways is a means to the end. It is not the end, and I don't understand how one could be intelligent without learning. So therefore, I got to figure out how to do that. So it's important. But machine learning, by the way, is also a tool. I said statistical, because that's what most people think of themselves. Machine learning people, that's how they think. It's a pet Langley might disagree at least 19 eighties, paddling. We might disagree with what it takes to do to do machine learning, but I care about the ai problem, which is why it's interactive ai not just interactive email. I think it's important to to understand that, that there's a long term goal here, which I will probably never live to see, but I would love to have been a part of which is building something truly intelligent outside outside of ourselves. </s><s>[INST] Can we take a tiny tangent or am I interrupting, Which is is there something you can say concrete about the mysterious gap between the subset ml, and the bigger ai what's missing? What's what do you think? I mean, obviously, it's totally unknown, Not totally, but in part unknown at this time, But is it something like with Pat languages, is that knowledge, like expert system reasoning type of kind of thing. [/INST] So, uh ai is bigger than ml but ml is bigger than a I this is kind of the real the real problem here is that they're really overlapping things that are really interested in slightly different problems, I tend to think of them and there are many people out there are gonna be very upset at me about this, but I tend to think of them as being much more concerned with the engineering of solving a problem. Um an ai about the sort of moral philosophical goal of true intelligence and that's the thing that motivates me, even if I end up finding myself living in this kind of engineering is space. I've now made made Michael Jordan's upset, but you know, it's it's it's to me they just feel very different. You're just measuring them differently. You're you're you're sort of goals or where you're trying to be, your are somewhat different. But to me a i is about trying to build that intelligent thing and typically, but not always for the purpose of understanding ourselves a little bit better. Machine learning is I think trying to solve the problem, whatever that problem is, that's my take others, of course, would disagree. </s><s>[INST] So, on that note, so with the interactive ai do you tend to in your mind visualized ai as a singular system or is it as a collective, huge amount of systems interacting with each other? Like is the social interaction of us humans and of ai systems the fundamental fundamental to intelligence. [/INST] I think, well, certainly fundamental to our kind of intelligence, right? And I actually think it matters quite a bit. So the reason um the interactive ai part matters to me is because I don't this is going to sound simple, but I don't care whether a tree makes a sound when it falls and there's no one around because I don't think it matters right if there's no observer in some sense. And I think what's interesting about the way that we're intelligent is we're intelligent with other people, right? Or other things anyway, and we go out of our way to make other things intelligent. We're hardwired to like find intention, even whether there is no intensify, we anthropomorphize everything. We I think anyway, we we I think the interactive ai part is being intelligent and of myself in an ice in isolation isn't meaningless act in some sense. The correct answer is you have to be intelligent in the way that you interact others. It's also efficient because it allows you to learn faster because you can import from, you know, past history. Uh it also allows you to be efficient in the transmission of that. So we ask ourselves about me my intelligent clearly. I think so, but I'm also intelligent is a part of a larger species and group of people and we're trying to move the species forward as well. And so I think that notion of being intelligent with others is kind of the key thing because otherwise you come and you go and then it doesn't matter. And so that's why I care about that aspect of it and has lots of other implications. One is not just building something intelligent with others, but understanding that you can always communicate with those others, they have been in a room where there's a clock on the wall that you haven't seen, which means you have to spend an enormous amount of time communicating with one another constantly in order to figure out what the other what each other wants. Right? So I mean this is why people project right? You project your own intentions in your own reasons for doing things onto others as a way of understanding them so that you know, you know how to behave, but by the way you completely predictable person, I don't know how you're predictable. I don't know you well enough, but you probably eat the same five things over and over again or whatever it is that you do right? Uh I know I do, if I'm going to a new chinese restaurant, I will get general gals chicken because that's the thing, that's easier. I will get hot and sour soup, you know the people do the things that they do, but other people get the chicken and broccoli that can push this analogy way too far. The chicken and broccoli, I don't know what's wrong with those people, I don't know what's wrong with them either. They we have all had our trauma, so they get their chicken and broccoli and their egg drop soup or whatever. Um we got to communicate and it's gonna change, right? So it's not interactive uh is not just about learning to solve a problem or task, it's about having to adapt that over time, over a very long period of time and interacting with other people Who will themselves change. This is what we mean about things like adaptable models, right? That you have to have a model, that model is going to change. And by the way, it's not just the case that you're different from that person, but you're different from the person you were 15 minutes ago or certainly 15 years ago. And I have to assume that you're at least going to drift hopefully not too many discontinuities, but you're gonna you're gonna drift over time. And I have to have some mechanism for adapting to that as you and individual over time and across individuals over time. </s><s>[INST] On the topic of adaptive modeling. And you talk about lifelong learning, which is a, I think a topic that's understudied or maybe because nobody knows what to do with it. But like, you know, if you look at Alexa or most of our artificial intelligence systems that are primarily machine learning based systems or dialogue systems, all those kinds of things, they know very little about you in the sense of the life long learning sense that we learn as humans. We'll learn a lot about each other, not in the quantity effects, but like the temporarily rich set of information. That seems to like pick up the crumbs along the way that somehow seems to capture a person pretty well. Do you have any ideas how to uh how to do lifelong learning? Because it seems like most of the machine learning community does not [/INST] No. Well by the knowledge of the machine in our community not not spend a lot of time on lifelong learning. I don't I don't think they spend a lot of time on um learning period in the sense that they tend to be very task focused. Everybody is overfitting to whatever problem is they happen to have their over engineering their solutions to the task. Even the people and I think these people do are trying to solve the hard problem of transfer learning right? I'm gonna learn on one task and then the other time it's you still end up creating the task. You know, it's like looking for your keys where the light is because that's where the light is right? It's not because the keys have to be there. I mean one could argue that we tend to do this in general. We tend to kind of do it as a group. We tend to hill climb and get stuck in local Optima. Um And I think we do this in the small the small as well. I think it's very hard to do. Um Because like here's the hard thing about ai right? The hard thing about ai is that keeps changing on us, right? You know what is a Yeah is the you know the art and science of making computers act the way they do in the movies, right? That's what it is, right? But beyond that and they keep coming up with new movies and just right. Exactly. We are driven by this kind of need to sort of ineffable quality of who we are, which means that the moment you understand something is no longer a I. Right, Well, we understand this, that's just you take the derivative and you divide by two and then you average it out over time in the window, so therefore that's no longer A. I so the problem is unsolvable because it keeps kind of going away. This creates a kind of illusion which I don't think is an entire illusion of either. There's very simple task based things you can do very well and over engineer. There's all of a I and there's like nothing in the middle, like it's very hard to get from here to here and it's very hard to see how to get from here to hear. And I don't think that we've done a very good job of it because we get stuck trying to solve the small problem that's in front of myself included. I'm not gonna pretend that I'm better at this than anyone else. Um And of course all the incentives in academia um and an industry are set to make that very hard because you you have to get the next paper out, you have to get the next product out, you have to solve this problem. And it's very sort of naturally incremental and none of the the incentives are set up to allow you to take a huge risk unless you're already so well established, you can take that big risk. Um and if you're that well established that you can take that big risk, then you've probably spent much of your career taking these little risks relatively speaking. And so you have got a lifetime of experience telling you not to take that particular big risk. Right? So the whole system set up to make progress very slow. That's fine. It's just the way it is. But it does make this gap seem really big, which is my long way of saying, I don't have a great answer to it, except that stopped doing in equals one At least try to get an equal to and maybe in equal seven. So that you can say I'm gonna maybe T is a better variable here. I'm going to not just solve this problem to solve this problem. And another problem I'm not going to learn just on you, I'm gonna keep living out there in the world and just seeing what happens and we'll learn something as designers and our machine learning algorithms in our ai algorithms can learn as well, but unless you're willing to build a system which you're going to have lived for months at a time in an environment that is messy and chaotic, you cannot control, then you're never going to make progress in that direction. So I guess my answer to you is yes. My idea is that you should it's not no, it's yes. You should be deploying these things and making them live for months at a time and be okay with the fact it's going to take you five years to do this, not rerunning the same experiment over and over again and refining the machine so it's slightly better at whatever, but actually having it out there and living in the chaos of the world. Um and seeing what it's learning algorithm, say can learn what data structure can build and how it can go from there without that. You're going to be stuck at the moment. </s><s>[INST] What do you think about the possibility of N equals one. Growing probably crude approximation, but growing like if you look at language models like GPT three, if you just make it big enough, it'll swallow the world, meaning like it'll solve all your t to infinity by just growing in size of this, taking a small over engineered solution and just pumping it full of steroids in terms of compute in terms of size of training data and the yon lagoon style self supervised or open ai. Self supervised. Just throw all of Youtube at it and it will learn how to reason how to paint, how to create music, how to love all that by watching Youtube [/INST] videos. I mean, I can't think of a more terrifying world to live in a world based on Youtube videos. But yeah, I think, I think the answer that I just kind of don't think that'll quite well, it won't work that easily. All right. You will get somewhere and you will learn something, which means it's probably worth it. But you won't get there. You won't solve the, you know, here's the thing. We build these things and we say we want them to learn, but what actually happens. And let's say they do learn. I mean, certainly every paper I've gotten published the things learn. I don't know about anyone else. Um, but they actually change us, right? We react to it differently. Right? So we keep redefining what it means to be successful, both in the negative in the case, but also in the positive and that this is this is a, this is an accomplishment. I'll give you an example which is like the one you just described you to let's let's get completely out of machine learned. Well, not completely, but mostly out of machine learning. Think about google. People were trying to solve information retrieval to ad hoc information retrieval problem forever. I mean first major book I ever read about it was what 71 I think it was when it came out anyway. It's you know, we'll treat everything as a vector and we'll do these vector space models and whatever. And that was all great. And we made very little progress. Have we made some progress and then google comes and makes the ad hoc problem seemed pretty easy. I mean it's not, there's lots of computers and databases involved, but you know, and there's some brilliant algorithmic stuff behind it too and some systems building. Um but the problem changed right? If you've got a world that's that connected so that you have, you know, there are 10 million answers quite literally to the question that you're asking. then the problem wasn't give me the things that irrelevant. The problem is don't give me anything that's irrelevant, at least in the first page because nothing else matters. So google is not solving the information retrieval problem at least not on this web page, Google is minimizing false positives, which is not the same thing as getting an answer. It turns out it's good enough for what it is we want to use google for but it also changes what the problem was. We thought we were trying to solve in the first place you thought you were trying to find an answer, but you're not where you're trying to find the answer. But it turns out you're just trying to find an answer now. Yes, it is true is also very good at finding you exactly that web page. Of course you trained yourself to figure out what the key words were to get you that web page. But in the end by having that much data you've just changed the problem into something else. You haven't actually learned what you set out to learn. Now. The counter to that would be maybe we're not doing that either. We just think we are uh because you know, we're in our own heads, maybe we're learning the wrong problem in the first place. But I don't think that matters. I think the point is is that google has not solved information retrieval, google has done amazing service. I have nothing bad to say about what they've done. Lord knows my entire life is better because google exists um important for google map something. We've never found this place. Where is this? Like 95 I. C. 110. And I see, but we're 95 go. Um You know, so I'm very I'm very grateful for google but you know they just have to make certain the first five things right and everything after that is wrong. Look we're going off in a totally different topic here but think about the way we hire faculty. It's exactly the same thing. Getting controversial. Getting controversial. Um It's exactly the same problem, right? It's minimizing false positives. Mhm. We say things like we want to find the best person to be an assistant professor at M. I. T. In the new college of computing which I will point out was founded 30 years after the College of Computing. I'm a part of both of my alma mater. Both of them are fighting words. I'm just saying I appreciate all that they did. Um and all that they're doing. Um Anyway so we're gonna we're gonna try to we're going to try to hire the best professor. That's what we say the best person for this job but that's not what we do it. All right. Do you know which percentage of faculty in the top four earned their phds from the top four say in 2017 for which we have which is the most recent year for which we have data. Maybe a large percentage is about 60% 60 60% of the faculty. The top four earned their phds on top of this computer science for which there is no top five. There's only the top four right? Because they're all tied for one </s><s>[INST] for people who don't know by the way, there will be MIT stanford. Berkeley cmu yep. Uh George attack number eight. Number eight [/INST] you're keeping track? Oh yes it's a large part of my job. Number five is Illinois. Number six is a tie with uh you devin Cornell and Princeton and George detector tied for eight and U. T. Austin is number 10 michigan's number 11 by the way. So if you look at the top 10. you know what percentage of faculty in the top 10 and their phds from the top 10 Mm 65 roughly 65%. If you look at the top 55 ranked departments 50% of the faculty earned their phds from the top 10. There is no universe in which All the best faculty even just for R one universities, The majority of them come from 10 places. There's no way. That's true. Especially when you consider how small some of those universities are. In terms of the number of phds they produce. Now that's not a negative I mean it is a negative. It also has a habit of entrancing certain historical inequities and accidents. But what it tells you is well ask yourself the question Why is it like that? Well because it's easier um if we go all the way back to the 1980s you know there was a saying that you know nobody ever lost his job buying a computer from IBM. It was true. Well nobody ever lost their job hiring a PhD from MIT. Right? If the person turned out to be terrible. Well you know they came from it. What did you expect me to know however that same person coming from pick? Whichever is your least favorite place that produces phds and say computer science. Well you took a risk. Right? So all the incentives particularly because you're only going to hire one this year. Well now we're hiring 10, but, you know, you're only gonna hire one or two or three this year. And by the way, when they come in, you're stuck with them for at least seven years In most places, because that's before, you know where they're getting tenure or not. And if they get 10 years stuck with them for a good 30 years, unless they decide to leave, that means the pressure to get this right is very high. So what are you gonna do? You're gonna minimize false positive? You don't care about saying no inappropriately. You only care about saying yes inappropriately. So all the pressure drives you into that particular direction, Google not to put too fine a point on it wasn't exactly the same situation with their search? It turns out you just don't want to give people the wrong page in the first three or four pages? And if there's 10 million right answers and 100 Brazilian wrong answers, just make certain the wrong answers don't get up there. And who cares if you the right answer was actually the 13th page, a right answer. A satisfying answer is number 123 or four. So who cares? </s><s>[INST] Or an answer that will make you discover something beautiful profound to your question? Well, that's a different problem. Right. But isn't that the problem, can we linger on this topic without uh sort of walking with Grace, how do we get For for hiring faculty? How do we get the 13th page with uh with a truly special person. Like there's, I mean, it depends on the department. Computer science probably has those departments uh those kinds of people, like you have the Russian guy, Grigori Perlman. Like just this awkward strange minds that don't know how to play the little game of etiquette that uh that faculty have all agreed somehow, like converged over the decades, how to play with each other and also is not, you know, on top of that is not from the top four, top whatever numbers the schools and and and maybe actually just says a few every once in a while to the uh to the traditions of old, within the computer science community maybe talks trash about machine learning is a total waste of time. And that's there on the resume. So like how do you allow the system to give those folks a chance? [/INST] Well, you have to be willing to take a certain kind of, without taking a particular position on any particular person you have to take. You have to be willing to take risk, right? A small amount of it. I mean, if we were treating this as a well as a machine learning problem, right? There's a search problem, which is what it is. It's a search problem. If we were treating it that way, you would say, oh well, the main thing is you, you know, you got a prior you want some data because the invasion if you don't wanna do it that way we'll just inject some randomness in it will be okay. The problem is that feels very very hard to do with people. Um All the incentives are wrong there. But it turns out and let's say let's say that's the right answer. Let's just give for the sake of argument that you know injecting randomness in the system at that level for who you hire is just not not worth doing because the price is too high. The cost is too high. And we had infinite resources. Sure but we don't and also you've got to teach people so you know you're ruining other people's lives if you get it to wrong. Um But we've taken that principle even if I granted and pushed it all the way back right? So uh we could have a better pool then we have of people we look at and give an opportunity to um If we do that then we have a better chance of finding that. Of course that just pushes the problem back back another level. But let me let me tell you something else you know um I did a sort of study I call it a study. I called up eight of my friends and ask them for all of their data for graduate admissions but then someone else followed up and did an actual study. Um And it turns out that I can tell you how everybody gets into grad school more or less, more or less you basically admit everyone from places higher rank than you, you met. Most people from places ranked around you and you can almost no one from places ranked below you with the exception of the small liberal arts colleges that aren't ranked at all, like harvey mudd because they don't have phds with their rank. Um This is also yes um which means the decision of whether, you know, you become a professor at Cornell uh was determined when you were 17, right? But where, what you knew to go to undergrad to do whatever, right? So if we can push these things back a little bit and just make the pool a little bit bigger, at least you raise the probability that you will be able to see someone interesting and and and take the risk? The other answer to that question by the way. Um Which you could argue is the same as you either adjust the pool. So the probabilities go up. That's the way of injecting a little bit of uniform uniform noise in the system as it were. As you change your loss function, you just let yourself be measured by something other than whatever it is that we're measuring ourselves by now. I mean U. S. News and World report every time they change their formula for determining rankings, moved entire universities to behave differently because rankings matter. </s><s>[INST] Can you talk trash about those rankings for a second? Not I'm joking about talking trash. I actually it's so funny how from my perspective from very shell perspective how dogmatic like how much I trust those rankings they're they're almost ingrained in my head. I mean at M. I. T. Everybody kind of it's a it's a propagated uh mutually agreed upon like idea that those rankings matter and I don't think anyone knows what their uh like most people don't know what they're based on and what are they exactly based on and what are the flaws in [/INST] that? So it depends which rankings you're talking about. Do you want to talk about computer science? We talk about university. Computer </s><s>[INST] science. U. S. News [/INST] is not the main one is the only one that matters is US News, nothing that matters. Sorry, CS rankings but nothing else matters but US news. So U. S. News has formula that it uses for many things but not for computer science because computer science is considered a science which is absurd. So the rankings for computer science Is 100% reputation. So two people at each department, it's not really department whatever at each department basically rank everybody slightly more complicated than that. But whatever they rank everyone and then those things are put together and somehow </s><s>[INST] so that means how do you improve reputation? How do you move up and down the space of reputation. [/INST] Yes that's exactly the crash twitter can help. I can tell you how George detected it or at least how I think your detective. Because um because Georgia tech is actually the case to look at. Not just because I'm a Georgia tech because Georgia tech is the only computing unit that was not in the top 20 that has made it into the top 10. It's also the only one in the last two decades I think Um that moved up in the top 10 as opposed to having someone else moved down. So we used to be number 10 and then we became number nine because ut Austin went down slightly and now we were tied for ninth because that's our rankings work. Uh And we moved from 9 to 8 because our raw score moved up a point. So George some something something about Georgia tech computer science or computing anyway. Um I think it's because we have shown leadership at every crisis level right? So we created college first public university to do it. Second college second university do it after seeing us number one. I also think it's no accident. That cmu is the largest and we're depending upon how you count and depending on exactly where M. I. T. Ends up with its final college of computing. Second or third largest. I don't think that's an accident. We've been doing this for a long time but in the two thousands when there was a crisis about undergraduate education? Georgia tech took a big risk and succeeded at rethinking undergrad education and computing. Um I think we we created these schools at a time when most public universities anyway, we're afraid to do it. We did the online masters um and that mattered because people are trying to figure out what to do with books and so on. I think it's about being observed by your peers and having an impact, so that is what reputation is, right? So the way you move up in the reputation rankings is by doing something that makes people turn and look at you and say that's good, they're better than I thought beyond that. It's just inertia and this huge history system, the system, right? Like, I mean there was these can't remember, this is may be apocryphal, but the, you know, there were there's a major or department that like M. I. T. Was ranked number one in and they didn't have it right. It's just about what you don't know if that's true, but someone said that to me anyway, um but it's it's a it's a it's a thing, right? It's all about reputation. Of course it is great because it is great. It's always been great by the way, because it is great, the best students come, which keeps it being great. I mean it's just a positive feedback loop, but not it's not surprising, I don't think it's wrong. </s><s>[INST] Yeah, but it's almost like a narrative, like it doesn't actually have to be backed by reality and it's uh you know, not to say anything, but it might be, but like it it does feel like we're playing in the space of narratives, not the space of some something grounded and like one of the surprising things when I showed up at M. I. T. And just all the students I've worked with and all the research I've done, is it like they're the same people as I've met other places. [/INST] I mean what it has going for it, Well it has many things going for one thing it has going for. It is nice logo is nice logo, it's a lot better than it was when I was here. Uh nice colors, too terrible, terrible name for a mascot. But the the thing that mitt has going for it is it really does get the best students, it just doesn't get all of the best students. There are many more best students out there, right? Um and the best students want to be here because it's the best place to be, or one of the best place to be. And it just kind of it's a sort of positive event. But you said something earlier, which I think is worth examining for a moment, right? You said it's I forget the words he is, he said uh we're living in the space of narrative as opposed to something objective narrative is objective. I mean one could argue that the only thing that we do as humans is narrative, we just build stories to explain why we found someone once asked me, but wait, there's nothing objective. No, it's completely an objective measure. It's an objective measure of the opinions of everybody else Now. Is that physics? I don't know, but you know what I mean? Tell me something you think is actually objective and measurable in a way that makes sense. Like cameras, they don't do you know that? I mean, you're getting me off on something, but do you know that um, cameras which are just reflecting light and putting them on film, Like did not work for dark skinned people until like the 1970s, you know why? Because you were building cameras for the people who are going to buy cameras who all at least in the United States and Western europe, were relatively light skin, turns out took terrible pictures of people who look like me uh, that got fixed with better film and whole processes. Do you know why? Because furniture manufacturers wanted to be able to take pictures of mahogany furniture. Right? Because candy manufacturers want to be able to take pictures of chocolate. Now, the reason I bring that up is because you might think that cameras our objective there object, they're just capturing like no, they're made, they are doing the things that they're doing based upon decisions by real human beings to privilege if I may use that word. Some physics over others because it's an engineering problem, their trade offs. Right? So I can either worry about this part of the spectrum or this part of the spectrum, This costs more, that costs less. This cost the same, but I have more people paying money over here. Right? And it turns out that, you know, if a giant, you know, conglomerate, once you demands that you do something different and it's going to involve all kinds of money for you, suddenly the tradeoffs change. Right? Um, and so there you go. I actually know how I ended up there. Oh, it's because this notion of objective this, right? So, so even the objective isn't objective because at the end you've got to tell a story, You've got to make decisions, you gotta make trade off of whales is engineering other than that. So I think that the rankings capture something, they just don't necessarily capture what people assume they capture. </s><s>[INST] You know, just to linger on this, this idea, why is there not more people who just like play with whatever that narrative is, have fun with it. Have like excite the world, whether it's in the car carl Sagan style of like that calm sexy voice of explaining the stars and all the romantic stuff or, or the L A mosque, dare I even say donald trump where you're like trolling and shaking up the system and just saying controversial things uh, that like I talked to lisa Feldman Barrett who's uh neuroscientists who just enjoys playing the controversy things like like finds the counterintuitive ideas in the particular science and throws them out there and sees how they play in the public discourse. Like why don't we see more of that and why does an academia attract and get Elon musk type? [/INST] Well, tenure is a powerful thing that allows you to do whatever you want. But getting tenure uh typically requires you to be relatively narrow, right? Because people are judging you well. I think the answer is we we have told ourselves a story, a narrative that that is vulgar, which we just described as vulgar. It's certainly unscientific, right? And it is easy to convince yourself that in some ways you're the mathematician, right? The fewer there are in your major, the more that proves your purity, right? So once you tell yourself that story then it is beneath you to do that kind of thing, right? I think that's wrong. I think that and by the way everyone doesn't have to do is everyone's not good at and everyone, even if they would be good, I would enjoy it. So it's fine. But I do think you need some diversity in the way that people choose to relate to the world as academics because I think the great universities Are ones that engage with the rest of the world, it is a home for public intellectual and in 2020 being a public intellectual probably means being on Twitter, Whereas of course that wasn't true 20 years ago because Twitter wasn't around 20 years ago and if it was, it wasn't around in a meaningful way, I don't actually know how long it has been around as I get older. I find that my my notion has gotten worse and worse, like Google really has been around that long anyway. The point is that um I think that I think that we sometimes forget that a part of our job is to impact the people who aren't in the world that we're in and that that's the point of being at a great place and being a great person, frankly, </s><s>[INST] there's an interesting force in terms of public intellectuals, you know, forget twitter, we can look at just online courses that are public facing in some part. Like there is a kind of force that pulls you back, I I would let me just call it out because I don't give a damn at this point. Uh there's a little bit of all of us have this, but certainly faculty have this, which is jealousy, it's whoever is popular at being a good communicator, exciting the world with their science and of course, when you excite the world with the science, it's not peer reviewed, clean. It all sounds like bullshit. It's like a ted talk and people roll their eyes and they hate that a ted talk gets millions of views or something like that and then everybody pulls each other back. There's this force that's just kinda, it's hard to stand out unless you like when a nobel prize or whatever, like it's only when you like get senior enough, we just stop giving a damn. But just like you said, even when you get tenure, that was always the surprising thing to me. I have many colleagues and friends who have gotten 10 year, but there's not a switch. Uh you know, there's not an F. U. Money switch where you're like, you know what now, I'm going to be more bold. It doesn't I don't see it. [/INST] Well, there's a reason for that, tenure isn't a test, it's a training process, It teaches you to behave in a certain way to think in a certain way to accept certain values and to react accordingly and the better you are, that the more likely you are to earn tenure. And by the way, this is not a bad thing, most things are like that. Um And I think most of my colleagues are interested in doing great work and they're just having impact in the way that they want to have impact. I do think that as a field, not just as a field, as a profession, we have a habit of belittling those who are popular as it were. Um As if the word itself is a kind of scarlet a right I think um Yeah, it's easy to convince yourself. uh and no one is immune to this that the people who are better known or better known for bad reasons. Um the people who are out there dumbing it down are not being pure to whatever the values than anything else is for your field. And it's just very easy to do now having said that, I think that ultimately people who are able to be uh popular out there and touching the world and making a difference. Uh you know, our colleagues do in fact appreciate that in the long run. Um It's just you know, you have to be very good at it or you have to be very interested in pursuing and once you get past a certain level, I think people, people accept that for who it is. I mean I don't know, I'd be really interested in how Rod brooks felt about how people were interacting with him when he did fast cheap and out of control. Way, way, way back when uh </s><s>[INST] what's fast stupid [/INST] article? It was a documentary that involved four people, I remember nothing about it other than Rod brooks was in it. And something about naked mole rats. Can't remember what the other two things were. It was robots, naked mole rats. And then two others, by </s><s>[INST] the way, rob books used to be the head of the artificial intelligence laboratory at MIT and then uh launched I think I robot and then think robotics rethink robotics. [/INST] Yes, yes, </s><s>[INST] I think is in the word. And uh and also is uh a little bit of a rock star personality in the AI world are very opinionated, very intelligent. Anyway, sorry, mallrats and naked [/INST] naked mole rats. Also, he was one of my two advisors for my PhD. Uh so I just explains a lot I would explain. I love but I also love my other advisor, paul paul, if you're listening, I love you too. Both very, very different people, paul Viola, both very interesting people, very different in many ways. Um but I don't know what Rod would say to you about how what the reaction was. I know that for the students at the time I was a student at the time. It was amazing. Right? This guy was on a movie being very much himself actually, the movie version of him as a little bit more Rod than Rod. I mean, I think they edited it appropriately for him, but it was very much Rod and he did all this while doing great work to me. Was running in the I lab at that point or not. I don't know anyone who's running the I lab would be soon. He's a giant in the field. He did amazing things. Made a lot of his bones by doing the kind of counterintuitive science, right? And saying no, you're doing this all wrong representation is crazy. The world is your own representation. You just react. I mean, this is amazing things. Um and continues to to do those sorts of things as he's as he's moved on. I have um I think he might tell you, I don't know if he would tell you what's good about, but I I know that for everyone else out there in the world, it was a good thing. And certainly he continued to be respected. So it's not as if it destroyed his career by being popular. </s><s>[INST] All right. Let's let's go into a topic where I'm on thin ice because I grew up in the soviet union Russia. My my knowledge of music. Uh this american thing you guys do uh uh is quite foreign. So your research group is called as we've talked about the lab for interactive artificial intelligence. But also there's just a bunch of mystery around this. My research fails me. Also called P Funk. P stands for probabilistic. And what does Funk stand [/INST] for? So a lot of my life is about making acronyms. So if I have one quirk is that people will say words and I see if they make acronyms and if they do uh then I'm happy. And then if they don't try to change it so that they make acronyms. Just the thing that I do. Uh So P Funk is an acronym. It has three or four different meetings. But finally I decided that the P stands for probabilistic because at the end of the day, it's machine learning and its randomness and uncertainty, which is the important thing here uh and the funk can be lots of different things, but I decided I should leave it up to the individual to figure out exactly what it is. But I will tell you that when my students graduate, when they get out. So we say at Tech, um I hand them uh they put on a hat and star glasses and a medallion from the P funk era. Um And we take a picture and I hand them a pair of fuzzy dice, which they get to keep. </s><s>[INST] So there's a sense to it which is not an acronym, like literally funk. There is uh you have a dark, mysterious past. Uh It's not dark, it's just fun is in uh hip hop and funk. So can you educate uh Soviet born Russian about this thing called hip hop? Like if you were to uh give me like you know went on a journey together and you were trying to educate me about especially um You know the past couple of decades in the 90s about hip hop or funk, what records are artists? Would you uh would you introduce me to? Would you are would you tell me about or maybe what influenced you in your journey or you just love like when when when the family is gone and you just sit back and just blast some stuff these days. Uh [/INST] What do you listen too well, so I listen to a lot, but I will tell you, well, first off all great music was made when I was 14. And that statement is true for all people, no matter how old they are or where they live. But uh for me, the first thing that's worth pointing out is it hit hip hop and rap aren't the same thing. So depending on who you talk to about this and the people who feel very strongly about this much more stronger than your </s><s>[INST] offending everybody in this conversation. So this is great. Let's [/INST] get hip hop is a culture, a set of things of which wrap is a part. So tagging is a part of hip hop. I don't know why that's true, but people tell me it's true and I'm willing to go along with it because they get very angry about it. But hip hop is like graffiti tagging is like graffiti. Uh and there's all these including the popping and the locking, and all the dancing, and all those things. That's all a part of hip hop. It's a way of life uh which I think is true. And then there's rap which is this particular, the music part. Yes, or a music part. I mean you wouldn't call the stuff that DJs do the scratching. That's not rap, right? But it's a part of hip hop. So given that we understand that hip hop is this whole thing, what are the rap albums that best touch that for me? Well, if I were going to educate you, I would try to figure out what you like, and then I would work you there. The skin </s><s>[INST] nerd. Uh oh [/INST] my God, I would probably start with uh there's a fascinating Xo it's okay. There's a fascinating exercise one can do by watching old episodes of uh I love the seventies, I love the eighties, I love the nineties um with a bunch of friends and just see where people come in and out of pop culture. So if you're talking about um those people, then I would actually start you with where I would hope to start you with anyway, which is public Enemy, particularly takes a nation of millions to hold us back, which is clearly the best album ever produced. Um and certainly the best hip hop album ever produced um in part because it was so much of what was great about the time, uh fantastic lyrics gives me, it's all about the lyrics, um amazing music that was coming from rick Rubin was the was the producer of that, and he did a lot of very kind of heavy, mental ish, at least in the 80 cents at the time. And it was focused on Politics in the 1980s, which was what made hip hop so great, then I would start you there, then I would move you up through things that have been happening more recently. I'd probably get you to someone like most def I'll give you a history lesson basically, most that's amazing. </s><s>[INST] He hosted a poetry jam thing on HBO or something [/INST] like that. Probably. I don't think I've seen it. I wouldn't be surprised spoken poetry that he's amazing, he's amazing. Uh And then I would, after I got you there, I'm working back to E P. M. D. Uh and eventually I would take you back to the Last Poet And particularly the first album, the last poets, which was 1970, to give you a sense of history and that it actually has been building up over a very, very long time. So we would start there because that's where your musical lines and then we would cycle out and I'd move you to the present and then I take you back to the past. And because I think a large part of people who are kind of confused about any kind of music, um you know, the truth is this is the same thing we've always been talking about, right? It's about narrative and being a part of something and being immersed in something. So you understand it right? Uh Jazz, which I also like is one of the things cool about jazz is that you come and you meet somebody is talking to you about jazz and you have no idea what they're talking about. And then one day it all clicks and you've been so immersed in and you go, oh yeah, that's a charlie parker and you start using words that nobody else understands, right? And it becomes a part of hip hop is the same way everything is the same way they're all cultural artifact. But I would help you to see that there's a history of it and how it connects to other genres of music that you might like to bring you in um so that you can kind of see how it connects to what you already like, including some of the good work that's been done with fusions of hip hop and bluegrass. Oh no, yes, some of it's even good, not all of it, but some of it is good, but I'd start you with, it takes a nation of millions to hold us back. </s><s>[INST] There's an interesting tradition in like more modern hip hop of uh integrating almost like classic rock songs or whatever, like integrating into the into their music into the beat, into the whatever. It's kind of interesting. It it gives a whole new uh not just classic rock, but what is it? Uh Kanye gold digger, the uh older and [/INST] be taking </s><s>[INST] and pulling old R and B right? [/INST] And Well that's been true since the beginning, I in fact that's in some ways that's why the DJ used to get top billing because it was the DJ that that brought all the records together and made it worth, so that people could dance if you know, you go back, you go back to those days mostly in new york, uh not exclusively, but mostly in new york where it sort of came out of uh you know, as a DJ that brought all the music together and the beats and show that basically music is itself an instrument very meta. Uh and you can bring it together and you sort of wrap over it and so on, and it sort of, it moved that way. So that's going way, way back now in the period of time where I grew up when I became really into it, um which was most of the eighties, it was more funk was the back for a lot of the stuff public enemy at that time notwithstanding. Uh and so which is very nice because it tied into what my parents listened to and what I vaguely remember listening to when I was very small. Uh so and by the way, complete revival of George clinton and Parliament and Funkadelic and all of those things To bring it back into the 80s and into the 90s. And as we go on, you're going to see, you know, the last decade, in the decade before that being brought in. And when you don't think that you're hearing something you've heard, it's probably because it's being sampled by someone who um referring to something they remembered when they were young, perhaps from somewhere else altogether. And you just didn't realize what it was because it wasn't a popular song where you happen to grow up. So this stuff has been going on for a long time. It's one of the things that I think is beautiful Run DMC Jam master jay used to play piano, he would record himself playing piano and then sample that to make it a part of what was going on, rather than play the piano. </s><s>[INST] That's how his mind can [/INST] think. Well, it's pieces you're putting pieces together, putting pieces of music together to create new music right now. That doesn't mean that the route. I mean the roots are doing their own thing, right? Those </s><s>[INST] those are that's a [/INST] whole but still it's the right attitude that, you know, and what else is jazz? Right? Jazz is about putting pieces together and then putting your own spin on it. It's all the same, it's all the same thing. It's all the same thing. </s><s>[INST] Because you mentioned lyrics, it does make me sad. Getting this is me talking trash about modern hip hop. Like I haven't, you know, investigating. I'm sure people correct me that there's a lot of great artists that's part of the reason I'm saying it is they'll leave it in the comments that you should listen to this person is the lyrics went away from uh, talking about maybe not just politics but life and so on. Like, you know, the kind of like protest songs, even if you look at like a bob Marley or you said public Enemy or Rage against the Machine more on the rock side. There's uh, that's the place where we go to those lyrics, like classic rock is all about like my woman left me or, or I'm really happy that she's still with me or the flip side is like love songs of different kinds. It's all love, but it's less political, like less interesting, I would say in terms of like deep, profound knowledge and it seems like rap is the place where you would find that. And it's sad that for the most part, what I see like you look like mumble rap or whatever, they're moving away from lyrics and more towards the beat and the musicality of [/INST] it. I've always been a fan of the lyrics. In fact, if you go back and you read my reviews, which I recently was re reading man Funk, I wrote my last review the month I graduated and I got my PhD, which says something about something. I'm not sure what though. I always would, I don't always, but often start with, it's all about the lyrics for me, it's always about the lyrics. Um, someone has already written in the comments before I've even finished having this conversation that, you know, neither of us knows what we're talking about and it's all in the underground hip hop and here's who you should go listen to and that is true every time I despair for popular rap, someone point me to where I discover, um, some underground hip hop song and I'm I made happy and whole again. So I know it's out there. Um I don't listen to as much as I used to because I'm listening to podcasts and old music from the 1980s and 90s. It's a kind of no beat at all. But, you know, there's a little bit of sampling here and there, I'm sure </s><s>[INST] uh by the way, James Brown is funk or no. [/INST] Yes, and so is Junior Wells, by the way, who's that? Junior Wells, Chicago blues? Uh, he was James Brown before James Brown was, </s><s>[INST] it's hard to imagine somebody being James [/INST] Brown, go look up hoodoo man blues, Junior Wells. Uh, and uh, just listen, listen to snatch it back and hold it and you'll see it. And they were contemporaries </s><s>[INST] where do you put like little richard or all that kind of stuff like ray Charles, like when they get, like, hit the road, Jack, and don't you come back? Isn't that like, there's a funkiness in [/INST] it? It's definitely a fun in the Senate. I mean, it's all, I mean it's all, it's all a lot. I mean, it's all, it's all a line that carries it all together. You know, it's I guess I have an answer a question that I'm thinking about it in 2020 and I'm thinking about it in 1960 I'd probably give a different answer, I'm just thinking in terms of you know what that was rock, but when you look back on it, it's it was funky, but we didn't use those words or maybe we did, I wasn't around, but you know, I don't think we use the word in 1960. Funk, certainly not the way we used it in the seventies and the eighties. </s><s>[INST] Do you reject disco? [/INST] I do not reject this go. I appreciate all the mistakes that we have made to get here. Now, actually, some of the disco is actually really, really good, </s><s>[INST] john Travolta. [/INST] Oh boy, </s><s>[INST] he regrets it. Probably, Maybe [/INST] not, like I think it got him to where he's going, where he is. </s><s>[INST] Well, thank you for taking that detour. You've you've talked about computing, where we've already talked about computing a little bit, but can you try to describe how you think about the world of computing, where it fits into the sets of different disciplines? We mentioned College of Computing, what what should people, how should they think about computing? Especially from an educational perspective of like what is the perfect curriculum that defines for young mind, what computing is? [/INST] So I don't know about a perfect curriculum, although that's an important question because at the end of the day, without the curriculum, you don't get anywhere curriculum to me is the fundamental data structure, it's not even the classroom in the world, right? I so I think the problem is where I like to play. Uh so I spent a lot of time thinking about this, but I will tell you I will answer your question by answering a slightly different question first and getting back to this, which is, you know, you talked about disciplines and what does it mean to be a discipline? The truth is what we really educate people in from the beginning, but certainly through college you sort of failed if you don't think about it this way I think is the world. People often think about tools and tool sets and when you're really trying to be good, do you think about skills and skill sets? But disciplines are about mindsets right there, about fundamental ways of thinking, not just the the hammer that you pick up whatever that is to hit the nail. Um not just the skill of learning how to hammer well or whatever, it's the mindset of like what's the fundamental way to think about to think about the world, Right? And disciplines, different disciplines give you different mindset to give you different ways of sort of thinking through. So with that in mind, I think that computing even asked the question whether the discipline is you have to decide does it have a mindset doesn't have a way of thinking about the world that is different from you know, the scientist who is doing discovery and using the scientific method is a way of doing it, or the mathematician who builds abstractions and tries to find sort of steady state truths about the abstractions that may be artificial, but whatever. Or is it the engineer who is all about, you know, building demonstrably superior technology with respect to some uh notion of trade offs, whatever that means, Right, That's sort of the world that you the world that you live in. What is computing, you know, how is computing different? So I thought about this for a long time and I've come to a view about what computing actually is, what the mindset is. And it's, you know, it's a little abstract but that would be appropriate for computing. I think that what distinguishes the computational list from others is that he or she understands that models, languages and machines are equivalent. They're the same thing. And because it's not just a model, but it's a machine that is an execute herbal thing that can be described as a language that means that it's dynamic. So it's not that it is mathematical in some sense, in this kind of sense of abstraction, but it is fundamentally dynamic and execute. Herbal. The mathematician is not necessarily worried about either the dynamic part. In fact, whenever I tried to write something for mathematicians, they invariably demand that I make it static and that's not a bad thing. It's just it's a way of viewing the world. That truth is a thing, right? It's not a process that continually runs, right? So that dynamic thing matters. That self reflection of the system itself matters, and that is what computer that is what computing brought us. So, it is a science because it funds the models fundamentally represent truths in the world. Information is a scientific thing to discover, right? Not just a mathematical conceit that that gets created, but of course, it's engineering because you're actually dealing with constraints in the world and trying to execute machines that that actually run. But it's also a math. Because you're actually worrying about these languages that describe the describe describe what's happening. But the fact that um that regular expressions and finance state of time on a one of which feels like a machine or at least an abstraction machine. And the other is the language that they're actually the equivalent thing. That is not a small thing. And it permeates everything that we do, even when we're just trying to figure out how to do debugging. So that idea, I think is fundamental. And we would do better if we made that more explicit How my life has changed in my thinking about this um, in the 10 or 15 years. It's been since I tried to put that to paper with some colleagues is the realization which comes to a question you you uh you actually asked me earlier uh, has to do with trees falling down. Whether it matters, is this sort of triangle of equality? It only matters because there's a person inside the triangle right? That what's changed about computing computer science or whatever you wanna call it as we now have so much data and so much computational power were able to do really really interesting promising things. Uh but the interesting and the promising kind of only matters with respect to human beings in their relationship to it. So the triangle exists that is fundamentally computing. What makes it worthwhile and interesting and potentially world species changing is that there are human beings inside of it and intelligence that has to interact with it to change the date of the information that makes sense and gives meaning to the models of languages and the machines. So if the curriculum can convey that while conveying the tools and the skills that you need in order to succeed then it is a big win. That's what I think you have to do. </s><s>[INST] Do you pull psychology is like these human things into that, into the idea into this framework of computing. Do you pull in psychology and neuroscience? Like parts of psychology, parts of neuroscience, parts of sociology. What about philosophy like studies of human nature from different perspectives. Absolutely. [/INST] And by the way it works both ways. So let's take biology for a moment. It turns out a cell is basically a bunch of if then statements if you look at it the right way, which is nice because I understand if then statements I never really enjoyed biology but I do understand if then statements and if you tell the biologist that and they begin to understand that it actually helps them to think about a bunch of really cool things. They'll still be biology involved. But whatever on the other hand, the fact of biology is in fact a bunch of the cell is a bunch of if then statements or whatever allows the computational is to think differently about the language and the way that we well certainly the way we would do A. I. Machine learning. But it's just even the way that we think about we think about computation. So the important thing to me is as you know, my engineering colleagues who are not in computer science worry about computer science, eating up engineering colleges where computer science is trapped. Um It's not a worry. You shouldn't worry about that at all. Computing is computer science computing. It's not it's central but it's not the most important thing in the world. It's not more important. It is just key to helping others do other cool things are going to do. You're not going to be a historian In 2030, you're going to get a PhD in history without understanding some data science and computing because the way you're going to get history done in part and I say done, the way you're gonna get it done is you're going to look at data and you're gonna let your going to have the system that's gonna help you analyze things to help you to think about a better way to describe history and understand what's going on and what it tells us about where we might be going the same street for psychology. Same true for all of these things. The reason I brought that up is because the philosopher has a lot to say about computing. The psychologist has a lot to say about the way humans interact with computing, right? Um and certainly a lot about intelligence, which for me, ultimately is kind of the goal of building these computational devices to build something intelligent. </s><s>[INST] Did you think computing will eat everything in some certain sense, almost like disappear because it's [/INST] part of everything. It's so funny you say that, I want to say it's going to metastasize, but there's kind of two ways that fields destroy themselves. one is they become super narrow and I think we can think of fields that might be that way. Um They become pure and we have that instinct, We have that impulse. I'm sure you can think of several people who want computer science to be this pure thing. The other way is you become everywhere and you become everything and nothing. And so everyone says, you know, I'm going to teach FORTRAN for engineers or whatever. I'm gonna do this and then you lose the thing that makes it worth studying in and of itself. The thing about computing and this is not unique to computing though at this point in time. It is Distinctive about computing where we happen to be in 2020 is we're both a thriving major, in fact the thriving nature almost every place and we're service unit because people need to know the things we need to know and our job, much as the mathematicians job is to help you know, this person over here to think like a mathematician much the way the point isn't the point of view taking chemistry as a freshman is not to learn chemistry. It's to learn to think like a scientist, right? Our job is to help them to think think like a computational list and we have to take both of those things very seriously and I'm not sure that as a field we have historically certainly taken the second thing that our job is to help them to think a certain way people are going to be. I mean I don't think we've taken that very seriously at all. </s><s>[INST] I don't know if you know who dan Carlin is, he has this podcast called hardcore history. I've just did an amazing four hour conversation with him mostly about Hitler but I bring him up because he talks about this idea that it's possible that history is a field will become like currently most people study history a little bit kind of are aware of it. We have a conversation about it, different parts of it. I mean there's a lot of criticism to say that some parts of history being ignored, blah blah blah, so on, but most people are able to to uh have a curiosity and able to learn it. The his thought is it's possible given the way social media works, the current way we communicate, the history becomes a niche field where literally most people just ignore because everything is happening so fast that the history starts losing its meeting and then it starts being a thing that only, you know, like the theoretical computer science part of computer science, it becomes in each thing that only like the rare holders of the world wars and the, you know, all the history, the founding of the United States, all those kinds of things, the civil wars. And it's a kind of profound thing to think about how these, how we can lose track, how can lose these fields when their best. Like in the case of history is best for that to be a pervasive thing that everybody learns and thinks about and so on. And I would say computing is quite obviously similar to history in the sense that it seems like it should be a, A part of everybody's life to some degree, especially like as we move into the later parts of the 21st century, and it's not obvious that that's the way we'll go, it might be in the hands of the few still, like, depending if it's machine learning, you know, it's on, it's unclear that it'll computing will win out. It's currently very successful, but it's not, I would say that's something, I mean, you're at the leadership level of this, you're defining the future, so it's in your hands, no pressure, but like it feels like there's multiple ways this can go and there's this kind of conversation of everybody should learn to code, write the changing nature of jobs and so on. Do you have a sense of what your role in uh, education of computing is here? Like what's the hopeful path [/INST] forward? There's a lot there, I will I will say that. Well, first off, it would be an absolute shame if no one studied history. On the other hand, it's t approaches infinity. The amount of history is presumably also growing, at least literally. And so, uh, it's, you have to forget more and more of history, but history needs to always be there. I mean, I can imagine a world where, you know, if you think of your brains as being outside of your head that you can kind of learn the history, you need to know when you need to know it. That seems fanciful, but it's a it's a kind of way of, you know, is there sufficient statistic of history. No, and they're certainly, but there may be for the particular thing you have to care about, but, you know, those who do not remember </s><s>[INST] our objective camera discussion. [/INST] Right. Right. And and you know we've already lost lots of history and of course you have your own history that some of which will be our it's even lost to you. You don't even remember whatever it was you were doing 17 years ago. All the ex girlfriends. Yeah they're on. Exactly. So history is being lost anyway. But the big lessons of history shouldn't be and I think you know, to take it to the question of computing and sort of education, the point is you have to get across those lessons. You have to get across the way of thinking um and you have to be able to go back and you know, you don't want to lose the data even if you don't necessarily have the information at your fingertips with computing. I think it's somewhat different. Everyone doesn't have to learn how to code but everyone needs to learn how to think in the way that you can be precise and precise in the sense of repeatable. Not just you know, in the sense of not resolution, in the sense we get the right number of bids um in saying what it is you want the machine to do and being able to describe a problem in such a way that it is execute a ble which we are not human beings are not very good at that. In fact I think we spend much of our time talking back and forth just to kind of vaguely understand what the other person means and hope we get a good enough that we can we can act accordingly. Um you can't do that with machines at least not yet. And so having to think that precisely about things is quite important. And that's somewhat different from coding. Coding is a crude means to an end. On the other hand, the idea of coding, what that means, that it's a programming language and it has these sort of things that you fiddle with in these ways that you express. That is an incredibly important point. In fact, I would argue that one of the big holes in machine learning right now and in a i is that we forget that we are basically doing software engineering. We forget that we're doing um we're using programming, like we're using languages to express what we're doing. We're just all caught up in the deep network or we get all caught up in whatever that we forget that, you know, we're making decisions based upon a set of parameters that we made up. And if we did slightly different parameters, we have completely different different outcomes. And so the lesson of computer and computer science education is to be able to think like that and to be aware of it when you're doing. And basically it's a you know, then today it's a way of surfacing your assumptions. I mean we call them parameters or you know, we we call them if then statements or whatever, but you're forced to surface those those assumptions. That's the key, the key thing that you should get out of the computing education data and that the models, the languages and the machines are equivalent. But it actually follows from that that you have to be explicit about about what it is you're trying to do because the model you're building is something you will one day run, so you better get it right or at least understand it and be able to express roughly with what you want to express. So I think it is key that we figure out how to educate everyone to think that way, because at the end, it would not only make them better at whatever it is that they are doing. And I emphasize doing it will also make them better citizens to help them to understand what others are doing to them so that they can react accordingly. Because you're not going to solve the problem of social media insofar as you think of social media is a problem by just making slightly better code. Right? It only works if people react to it appropriately and know what's happening and therefore take control over what they're doing. I mean, that's that's my take on, </s><s>[INST] okay, let me try to proceed awkwardly into the topic of race. Okay. One is because it's a fascinating part of your story and you're just eloquent. And fun about it. And then the second is because we're living through a pretty tense time in terms of, uh, race tensions and discussions and ideas in, in this time in America, you grew up in Atlanta, not born Atlanta. You're, is some southern states similar Tennessee, something like that. Nice. [/INST] Okay. But </s><s>[INST] you're early on, you moved your, you're basically, uh, you, uh, identifies an Atlanta native. Yeah. And uh, you've mentioned that you grew up in a predominantly black neighborhood, by the way, black african american personal [/INST] color present black, black with a capital B with a capital. Uh, </s><s>[INST] the other letters [/INST] are, the rest of the matter is that, </s><s>[INST] uh, okay, so the predominantly black neighborhood. And so you didn't almost see race. Maybe you can correct me on that. Like, and then went, just in the video, you talked about when you showed up to Georgia tech for your undergrad, you're one of the only, uh, black folks there. And that was like, oh, that was a new experience. You can, you take me from, uh, just a human perspective, but also from a race perspective, your journey growing up in Atlanta. And then showing up at Georgia [/INST] tech. And by the way that story continues through it as well. In fact, it was quite a bit more stark and at M I. T. And boston. </s><s>[INST] So maybe just a quick pause Georgia tech was undergrad mit was graduate [/INST] school and I went directly to grad school from undergrad. So I had no, I had no distractions in between my bachelor's and my master's and PhD, you </s><s>[INST] didn't go out on a backpacking [/INST] trip in europe, didn't do any of that. In fact, I literally went to IBM for three months, got in the car and drove straight to boston with my mother or Cambridge. Uh moved into an apartment I've never seen over the Royal East. Anyway, that's that's another story. So let me tell you a little </s><s>[INST] bit about it. [/INST] Oh, I loved it. I don't miss boston at all, but I loved it and that was fighting. So let's back up to this. So as you said, I was born in Chattanooga Tennessee, my earliest memories arriving in Atlanta and a moving truck at the age of 3.5. So I think of myself as being from Atlanta, very distinct memory of that. So I grew up in Atlanta. It's the only place I ever knew as a kid. Uh I loved it, like much of the country and certainly much of Atlanta in the seventies and eighties. It was deeply, highly segregated. Uh not in a way that I think was obvious to you unless you were looking at it or we're old enough to have noticed it, but you could divide up Atlanta and Atlanta hardly unique in this way by highway and you could get race and class that way. So I grew up, not only in a predominantly black area to say the very least. I grew up on the poor side of that. Uh Mhm. Uh But I was very much aware of race for a bunch of reasons. One that people made certain that I was uh my family did but also that it would come up. So in first grade I had a girlfriend. I say I had a girlfriend. I don't have a girlfriend. I wasn't even entirely sure girls were in the first grade. Uh But I do remember she decided I was her girlfriend's little white girl named heather. Um And we had a long discussion about how it was okay for us to be boyfriend and girlfriend despite the fact that she was white and I was black </s><s>[INST] between the two of [/INST] you between uh Yes. But being a girlfriend and boyfriend in first grade just basically meant that you spend slightly more time together during recess. And it had known me. I think we Eskimo kissed once. Uh It doesn't mean it didn't mean anything. It was at the time. It felt very scared because everyone was watching. I was like uh my life is now my life has changed in first grade. No one told me. Elementary school would be like this. Not in first grade. That would come later. I would come during puberty uh When I wrote lots and lots of poetry. Anyway. So um So I was aware of it. I didn't think too much about it, but I was aware of it. Um, but I was surrounded. It wasn't that I wasn't aware of race. It said I wasn't aware that I was a minority. It was different. Uh, and it's because I wasn't as far as my world was concerned. I mean, I'm six years old, five years old. First grade, the world is the seven people I see every day right now. So it didn't feel that way at all. Um, and by the way, this being Atlanta, home of the civil rights movement and all the rest, that meant that when I looked at tv, which back then one did because there were only 34 or five channels, right? And I saw the news which my mother might make me watch, you know, the uh, Monica Kaufman was on tv telling me the news and they were all black and the mayor was black and always been black. And so it just never occurred to me, uh, when I went to Georgia tech, I remember the first day walking across campus from west campus to east campus and realizing along the way that of the hundreds and hundreds and hundreds and hundreds of students that I was seeing, I was the only black one that was enlightening. Um, and very off putting because it occurred to me. And then of course it continued that way for, well for the rest of my, for much of the rest of my career George detect, of course I found lots of other students and I met people because in Atlanta, you're either black or you're white. There was nothing else. Um, so I began to meet students of asian descent and I met students who we would call hispanic and so on and so forth. And you know, so my world, this is what college is supposed to do right. It's supposed to open you up to people and it did. But it was a very strange thing to be in the minority. When I came to boston. Uh, I will tell you a story. I, I applied to one place as an undergrad George attack because I was stupid. I didn't know any better. I mean she didn't know any better. Right. Um, no one told me when I went to grad school, I applied to three places Georgia tech because that's where it was, MIT and cmu. Uh, when I got in a minute, I, I got into cmu, but I had a friend who went to cmu and so I asked him what he thought about it. He spent his time explaining to me about Pittsburgh much less about seeing you, but more about Pittsburgh, which I developed a strong opinion based upon his strong opinion, something about the sun coming out, two days out of the year. Uh, and I didn't have a chance to go there because the timing was wrong. Um, I think it's because the timing was wrong. and um it I asked uh 20 people I knew either when I visited or I had already known for a variety of reasons whether they liked boston And 10 of them loved it and 10 of them hated it. The 10 who loved it were all white. The 10 who hated it were all black and they explained to me very much why that was the case. Um Both deaths told me why it's and the stories were remarkably the same for the two clusters. Um And I came up here and uh I could see it immediately why people would love it and why people would not. And uh people </s><s>[INST] tell you about the nice coffee shops and [/INST] well when coffee shops it was C. D. U. C. D. Places. But yeah it was that kind of thing, nice shops. Oh there's all these students here, Harvard Square is beautiful, you can do all these things and you can walk and something about the outdoors, whichever is the slightest bit interested. The outdoors is for the bugs, not for humans. Um And the that should be a t shirt. I mean that's the way I feel about it. Um The and the black folk told me completely different stories about which part of town you did not want to be caught in after dark and um and I heard of but that was nothing new. So I decided that it was a great place to be as a university and I believed it then, I believe it now. Uh and that whatever it is I wanted to do, I thought I knew what I wanted to do, but what if I was wrong, um someone there, we know how to do it. Of course, then I would pick the one topic nobody was working on at the time, but that's okay. Um it was great and so I thought that I would be fine and not only be there for like four or five years, I told myself it turned out not to be true at all, but I enjoyed my time. I enjoyed my time there, but I did see a lot of um I ran across a lot of things that were driven by what I look like while I was here, I got asked a lot of questions. Uh I ran into a lot of cops. Uh I did a I I saw a lot about the city, but at the time, I mean I've been here a long time. These are the things that I remember. So this is 1990 there is not a single black radio station Now, this is 1990. There are, I don't know if there's any radio stations anymore. I'm sure there are, but you know, I don't listen to the radio anymore and almost no one does. Um at least if you're under a certain age, but the idea is you could be in a major metropolitan area and there wasn't a single black radio station, by which, I mean a radio station that played what we would call black music then um was absurd but somehow captured kind of everything about about the city. I grew up in Atlanta and you know, you've heard me tell you about Atlanta boston had no economically viable or socially cohesive black middle class. Mhm insofar as it existed, it was uniformly distributed throughout large parts of not all parts with large parts of the city. And we had concentrated concentrations of black Bostonians. Uh They tended to be poor. It was very different from where I grew up. I grew up on the poor side of town. Sure. But then in high school, well in ninth grade we didn't have middle school, I went to an eighth grade school where there was a lot of, let's just say we had a riot the year that I was there, there was at least one major fight every week. It was uh it was it was uh it was an amazing, it was amazing experience. But when I went to ninth grade I went to the academy, Math, math and science academy. Makes high was a public school. It was a magnet school. That's why I was able to go there. Uh It was the first school high school I think in the state of Georgia. To sweep the state math and science fairs. It was great. It had 385 students, all but four of whom were black. I went to school with the daughter of the former mayor of Atlanta, Michael Jackson's cousin. I mean, you know, there was, it was an upper middle class, whatever. You know, I just dropped names occasionally, you know, drop the mic, drop some names just to let you know, I used to hang out with Michael Jackson's cousin, 12 cousin, nine times removed. I don't know. The point is that they had, we had a parking problem because the kids have cars. I did not come from a place where you had cars. I got my first car when I came to my t actually. Um, so it was, it was just a, it was just a very, very different experience for me. But I've been to places where whether you were rich or whether you were poor, you know, you could be black and richard black and poor and it was there and there were places and they were segregated my class as well as by race. But um, that existed here at least when I was here didn't feel that way at all. And it felt like a bunch of a really interesting contradiction. It felt like it was the interracial dating capital of the country. Yeah, you really felt that way. Uh, but it also felt like the most racist place. I have respect any time. Uh, You know, you couldn't go up the orange line at that time. I mean, again, that was 30 years ago, I don't know what it's like now, but there were places you couldn't go and you knew it, everybody knew it. And there were places you couldn't live and everybody knew that. uh, and that was just the Greater Boston area in 1992, </s><s>[INST] subtle racism or explicit racism, both in terms of within the institutions. Did you feel was it was their levels in which you were empowered to be first to water in the first black people in a particular discipline and in some of these great institutions that you're part of, you know, Georgia tech MIT. And was there part where it was felt limiting? [/INST] I always felt empowered. Some of that was my own delusion, I think. But it worked out. So I never felt is in fact quite the opposite. Not only did I not feel as if no one was trying to stop me, I had the distinct impression that people wanted me to succeed by people. I meant the people in power. Now my fellow students not, they didn't want me to succeed, but I felt supported or at least that people, we're happy to see me succeed at least as much as anyone else. But, you know, 1990, you're dealing with a different set of problems which you're you're very early, at least in computer science, you're very early in the sort of Jackie Robinson period, you know, there's this thing called the Jackie Robinson syndrome, which is that you you have to, you know, the first one has to be perfect or has to be sure to succeed because of that person fails. No one else comes after for a long time. So, um you know, it was kind of in everyone's best interest, but I think it came from a sincere place, I'm completely sure that people went out of their way to try to make certain that the environment would be good, not just for me, but for the other people who of course were around. And I was hardly the only, I was the only person in the I lab, but I wasn't the only the only person that mighty by a long shot on the other hand, but what at that point we would have been less than 20 years away from the first black PhD to graduate from M. I. T. Right, Shirley Jackson, right, something like that somewhere around then. Um, so we weren't that far away from the 1st 1st and we were still another eight years away from the first black PhD Computer Science. Right? So, um we were in a it was it was a sort of interesting time, but I did not feel as if the institutions of the university where against any of that and furthermore, I felt as if there was enough of a critical mass across the institute from students and probably faculty, that I didn't know them, who wanted to make certain that the right thing happened is very different from the institutions of the rest of the city, which I think were designed in such a way that, uh, they felt no need to be supportive. </s><s>[INST] Let me ask a touchy question on that. So, you kind of said that you didn't feel, yeah, you felt empowered. Is there some lesson advice in the sense that no matter what, you should feel empowered, you should you should you use the word, I think, illusion or delusion, is there a sense from the individual perspective where you should always kind of ignore? You know, the uh, ignore your own eyes, ignore the the little forces that you are able to observe around you. They're like trying to mess with you of whether it's jealousy, whether it's hatred in its pure form, whether it's just hatred, and it's like diluted form, all that kind of stuff, and just kind of see yourself as empowered and confident, all those [/INST] kinds of things. I mean, it certainly helps. But there's a tradeoff right? You have to be deluded enough to think that you can succeed. I mean, you can't get a PhD unless you're crazy enough to think you can invent something that no one else has come up with, that kind of massive delusion is that you have to be deluded enough to believe that you can succeed despite whatever odds you see in front of you. But you can't be so deluded that you don't think that you need to step out of the way of the oncoming train, right? So it's all a trade off, right? You have to kind of believe in yourself, It helps to have a support group around you in some way or another. Um, I was able to find that I've been able to find out wherever I've gone, even if it wasn't necessarily on the floor that I was in. I had lots of friends when I was here. Many of them still live here. Um, and I've kept up with many of them. So I felt supported and certainly I had my mother and my family and those people uh back home uh that I could always, I could always lean back on even if it were a long distance call that cost money, which, you know, not something that any of the kids today even know what I'm talking about, but you know, back then it matter calling my mom was an expensive proposition, but you know, you have that and it's fine. I think it helps, but you cannot be so deluded that you missed the obvious because it makes things slower and it makes you think you're doing better than you are and it will hurt you in the long run. </s><s>[INST] You mentioned cops, you tell the story of being pulled over? Perhaps it happened more than once. [/INST] More than once. Fisher </s><s>[INST] one. Could you tell that story? And in general, can you give me a sense of what the world looks like when the, when the law doesn't always look at you with [/INST] uh </s><s>[INST] with a blank slate. What like with uh with objective eyes, I don't know how to say it more poetically. [/INST] Well, I guess the I don't either. I guess the the answer is it looks exactly the way it looks now because this is the world that we happen to live in, right? It's people clustering and doing the things that they do and making decisions based on and you know, one or two bits of information they find relevant, which by the way, are all positive feedback loops, uh which makes it easier for you to believe what you believe before because you behave in a certain way. That makes it true and it goes on in circles and cycles and cycles and cycles. So it's just about being on edge. I do not despite having made it over 50 now. Just </s><s>[INST] congratulations brother [/INST] God. Um I have a few gray hairs here and there. He did pretty good. I think, you know, I don't imagine I will ever see a police officer and not get very, very tense. Now. Everyone gets a little tense because it probably means you're being pulled over for speeding or something where you're going to get a ticket or whatever, right? I mean the interesting thing about the law in general is that most human beings experience of it is fundamentally negative, right? You're only dealing with the lawyer if you're in trouble accepting a few very small circumstances, right? But so that's just a, that's an underlying reality now, imagine that that's also at the hands of the police officer. I remember the time when I was, when, when I got pulled over that time halfway between boston and Wellesley actually, um I remember thinking as when he pulled his gun on me that if he shot me right now, he'd get away with it. That was the worst thing that I felt about that particular moment is that if he shoots me now, he will get away with it. It would be years later when I realized actually, much worse than that is that he'd get away with it. And if anyone, if it became a thing that other people knew about odds were would be of course that it wouldn't, but if it became a thing that other people knew about, if I was living in today's world as opposed to The world 30 years ago, that not only we get away with it, but I would be painted a villain, I was probably big and scary and I probably moved too fast and when they had done what he said and done, which is somehow worse, right? You, you know, that hurts, not just you, you're dead, but your family and the way people look at you and look at your legacy of your history. Um that's terrible. And it would work. I absolutely believe it would have worked had he done it? He didn't, I don't think he wanted to shoot me. If you feel like killing anybody did not go out that night expecting to do that, we're planning on doing it. And I wouldn't be surprised if he never, ever did that or ever even pulled his gun again. I don't know the man's name. I remember anything about him. I do remember the gun guns are very big when they're in your face. I can tell you this much are much larger than they seem, </s><s>[INST] but you're basically like speeding or something like that. [/INST] He said, I ran a light, I ran a light. I don't think I ran a light, but you know, in fact, I may not have even gotten a ticket. I may have just gotten a warning. I think he was a little, somebody told a gun, apparently I moved too fast or something. I rolled my window down before. I should have. It's unclear. I think he thought I was going to do something or at least that's how he behaved. </s><s>[INST] So how if we can take a little walk around your brain, how do you feel about that guy and how do you feel about cops? [/INST] Well, I </s><s>[INST] don't share that experience. [/INST] I don't remember that guy, but my views on police officers is the same view I have about lots of things. Fire is an important and necessary thing in the world, but you must respect fire because it will burn you fire is a necessary evil in the sense that it can burn you necessary in the sense that you know heat and all the other things that we use fire for. So when I see a cop, I see a giant ball of flame and I just try to avoid it </s><s>[INST] and then some people might see a nice place, a nice thing to roast marshmallows with a family [/INST] over which is fine. I don't roast marshmallows </s><s>[INST] because let me go a little darker and I apologize, just talk to dan Carlin bought it for four hours. So if I'm sorry if I go a dark here a little bit, but is it easy for that, this experience of just being careful with the fire and avoiding it to turn to hatred? [/INST] Yeah, of course. And one might even argue that it is a a logical conclusion. Right? On the other hand, you gotta live in the world and uh, I don't think it's helpful. Hate is something one should I hate is something that takes a lot of energy. So one should reserve it for when it is useful and not carried around with you all the time again. There's a big difference between the happy delusion that convinces you that you can actually get out of bed and make it to work today without getting hit by a car and the sad delusion that means you can not worry about this car that is barreling towards you, right? So we all have to be a little diluted because otherwise we're paralyzed, right? But one should not be ridiculous. We go all the way back to something you said earlier about empathy. Um, I think what I would ask other people to get out of this. One of many, many, many stories is to recognize that it is real. People would ask me to empathize with the police officer. I would quote back statistics saying that, you know, being a police offer police officer isn't even in the top 10 most dangerous jobs in the United States, you're much more likely to be killed in a taxi cab. Half of police officers are actually killed in the by suicide. Uh, but that means their lives or something, something's going on there um, with them and I would be more than happy to be empathetic about what it is they go through and how they see the world. I think though, that if we step back from what I feel and we step back from what an individual police officer feels, you step up a level and all this because all things tie back into interactive. They are the real problem here is that we've built a narrative. We built a big structure that has made it easy for people to put themselves into different pots in the different clusters and to um basically forget that the people in the other clusters are ultimately like them. It is useful exercise to ask yourself sometimes. I think that if I had grown up in a completely different house in a completely different household is a completely different person. If I had been a woman, would I see the world differently? What I believe with that crazy person over their beliefs and the answer is probably yes, because after all, they believe it and fundamentally they're the same as you. So then what can you possibly do to fix it? How do you fix twitter if you think twitter needs to be broken or facebook, if you think facebook is broken, how do you fix racism? How do you fix any of these things? That's all structural, right? It's not individual. Individual conversations matter a lot, but you have to create structures that allow people to have those individual conversations all the time in a way that is relatively safe um and that allows them to understand that other people have had different experiences but that ultimately were the same, which sounds very um I don't even know what the right word is. I'm trying to avoid a word like saccharine, but you know, it's it feels very optimistic, but I think that's okay, I think that's a part of the delusion because you want to be a little optimistic and then recognize that the hard problem is actually setting up the structures in the first place? Because it's no one's it's an almost no one's interest to change the infrastructure, </s><s>[INST] right? I, I tend to believe that leaders have a big role to that of selling that optimistic delusion to everybody and that eventually leads to the building of the structures. But that requires a leader that unites, uh, sort of unites everybody on the vision as opposed to divides. And a vision, which is this particular moment in history feels like there's a non zero probability if we go to the p of something akin to a violent or non violent civil war, this is one of the most divisive periods of american history in recent. You can speak to this from a perhaps a more knowledgeable and deeper perspective than me, but for my naive perspective, this seems like a very strange time. There's a lot of anger and has to do with people. I mean, for many reasons. One, the thing that's not spoken about, I think much is the quiet economic pain of millions that's like growing because of Covid because of closed businesses because of laws dreams. So that's building whatever that tension is building the others, there seems to be an elevated level of emotion. I'm not sure if you can psychoanalyze where that's coming from. But this sort of, from which the protests and so on percolated. It's like why now, why at this particular moment in history? [/INST] Because time enough time has passed. Right? I mean, you know, the very first race riots were in boston. Uh, not to draw anything. Oh, </s><s>[INST] before [/INST] going wait. I mean, like the 17 hundreds or whatever, Right? I mean, there was a master york. I mean, I'm talking way, way, way back. So boston used to be the hotbed of riots. It's just what boston was all about, or so I'm told from history class. Uh, here's an interesting one in new york. I remember when that was anyway, the point is, you know, basically you got to get another generation old enough to be angry, but not so old to remember what happened the last time. Right? And that's sort of what happens. But you know, you, you said like two completely, you said two things there that I think are worth unpacking. Uh, one has to do with this, this sort of moment in time. Uh, and you know, why why is this sort of up bill? And the other has to do with a kind of, you sort of, the economic reality of Covid. So I'm actually, I want to separate those things because for example, you know, this happened before Covid happened. Right? So let's separate these two things to remember now, let me preface this by saying that although I am Uh, interested in history. Uh, one of my three miners as an undergrad was history specifically history of the 1960s, um, interesting, the other was spanish and </s><s>[INST] okay, that's a mistake. [/INST] I love, I love uh history of spanish and spanish history actually spanish. And the other was what we would now call cock into science. But at the time, um, that's fascinating, interesting. My entered in cox, I hear uh, for grad school, that was really, that was really fascinating. Was very different experience from all the computer science classes I've been taking, even the cock psych classes I was taking taking at an undergrad anyway. Um, I'm not, I'm, I am a, I'm interested in history, but I'm hardly historian. Uh, so, you know, forgive my, I will ask the audience to forgive my simplification. Um, but I think the question that's always worth asking as opposed to it's the same question, but a little different not why now, but why not before? All right. So why the 19 fifties, sixties civil rights movement as opposed to 19 thirties, 19 forties? Well, first off, there was a civil rights movement, the thirties and forties, it just wasn't of the same character or quite as well known post World War Two. Lots of interesting things were happening. It's not as if a switch was turned on and Brown versus board of Education or the Montgomery bus boycott. And that's what happened. These things been building up forever and go all the way back and all the way back and all the way back and, you know, Harriet tubman was not born in 1950. Right? So you know, we can take these things, it </s><s>[INST] could have easily happened after well, right after World War Two, yes, [/INST] I think and again, I'm not a scholar. I think that big difference was tv these things are visible. People can see them. It's hard to avoid. Right? The, you know, why not James farmer, why martin Luther king? Because One was born 20 years after the other whatever. I think it turns out that, you know, you know, the king's biggest failure was in the early days was in Georgia. You know, they were doing some uh, doing the usual thing trying to, trying to integrate and uh, I forget the guy's name, but you can look this up, but he, he a copy as a sheriff made a deal with the whole state of Georgia. We're going to take people and we're going to nonviolently put them in trucks and then we're going to take them and put them in jails very far away from here. No, we're going to do that and we're not going to, there'll be no reason for the press to hang around and they did that and it worked and the press left and nothing changed. So next I went to Birmingham Alabama and bull o'Connor and you got to see on tv little boys and girls being hit with fire hoses and being knocked down and there was outrage and things changed. Right? Part of the delusion is pretending that nothing bad is happening that might force you to do something big you don't want to do, but sometimes it gets put in your face and then you kind of can't ignore it. And a large part in my view of what happened, right, was that it was too public to ignore now. We created other ways of ignoring it. Um lots of change happened in the south, but part of that delusion was that it wasn't gonna affect the west of the northeast. And of course it did, and that caused its own set of problems which went into the late sixties, into the seventies. And you know, in some ways we're living with that legacy now, uh And so on. So why not? What's happening now? I didn't happen 10 years ago I think it's people have more voices, there's not just more tv their social media, it's very easy for these things to kind of build on themselves. Uh and things are just quite visible. Um and there's demographic change, I mean the world is changing rapidly, right? And so it's very difficult. Uh you're now seeing people, you could have avoided seeing most of your life growing up in a particular time. Uh and it's happening, it's dispersing at a speed that is fast enough to cause concern for some people, but not so fast to cause massive negative reaction. Uh so that's that on the other hand, and again, that's a massive oversimplification, but I think there's something there anyway, at least something worth exploring. I'm happy to be yelled at by a real historian. </s><s>[INST] Yeah, I mean there's just the obvious thing. I mean, I guess you're implying, but not saying is, I mean, it seemed to have percolated the most, just a single video. For example, the George Floyd video difference makes makes it, it's fascinating to think that that whatever the mechanisms that put injustice in front of our face, not like, like directly in front of our face, those mechanisms are the mechanisms of [/INST] change. On the other hand, Rodney King, so no one remembers this. I seem to be the only person who remembers this, but sometime before the Rodney King incident, there was a guy who was a police officer who was saying that things were really bad in southern California. Um, and he was going to prove it by having uh, some news, Some camera people follow him around. He says, I'm going to go into these towns and just follow me for a week and you will see that I'll get harassed and like the first night he goes out there and he crosses into the city, some cops pulled him over and he's a police officer remember, they don't know that of course they like shove his face through a glass window. This was on the new, like, I distinctly remember watching this as a kid. Um actually, I guess I wasn't a kid. I was I was in college at the 1000 grad school the time. </s><s>[INST] That's not enough. Like just just [/INST] well, it disappeared like a day. Like it didn't go viral. </s><s>[INST] Whatever that is, whatever that magic [/INST] and whatever it was in 92 is harder to go viral in 92. Right? Um or 91 actually, it must have been 90 or 91 but that happened and like, two days later, it's like, it never happened. Like, nobody again, nobody remembers this man. Like, the only person sometimes, I think I must have dreamed it. Anyway, Rodney King happens. It goes viral or the moral equivalent thereof at the time. And eventually We get April 29, right? And I don't know what the difference was between the two things other than one thing called and one thing didn't maybe what's happening now is two things are freezing under one another. One is more people are willing to believe and the other is there's easier and easier ways to give evidence, cameras, body cams. But we're still finding ourselves telling the same story. It's the same thing all over again. I would invite you to go back and read the op EDS from what people were saying about the Violence is not the right answer after Rodney King and then go back to 1980 and the big rights that were happening around then and read the same up. It's the same words over and over and over again. I mean there's your remembering history right there literally the same words like you could have just called and I'm surprised no one got flagged for plagiarism. </s><s>[INST] It's interesting if you have an opinion on the question of violence and the popular, perhaps caricature of Malcolm X versus versus king, martin Luther king, [/INST] you know, Malcolm X was older than martin Luther king. People kind of have it in their head that he's younger. Well he died sooner, right? But only by a few years people think of him, uh, okay, as the older statesman and they think of Malcolm X, is that the young angry, whatever, but that's more of a narrative device. It's not true at all. I don't, I just I reject the choice as I think it's a false choice. I think they're just things that happen. You just do, as I said, hatred is not, it takes a lot of energy, but everyone's gonna have to fight one thing I will say without taking a moral position, which I will not take on this matter. Um, violence has worked. </s><s>[INST] Yeah, that's the annoying thing. It seems like over the top anger works, outrage works. So you can you can say like being calm and rational, just talking it out is gonna lead to progress. But it seems like if we just look through history being irrationally upset is the way you make progress. [/INST] Well, certainly the way that you get someone to notice you and that's a and if they don't notice you. I mean, what's the difference between that and again, without taking a moral position on this? I'm just trying to observe history here. If you maybe if television didn't exist, the civil rights movement doesn't happen or it takes longer or it takes a very different form. Maybe if social media doesn't exist, a whole host of things positive and negative don't happen. Right? So, and what do any of those things do other than expose things to people? Violence is a way of shouting. I mean, many people far more talented and thoughtful that I have have said this in one form or another, right? That, you know, violence is the voice of the unheard right? I mean, it's it's it's a thing that people do when they feel as if they have no other option. And sometimes we agree and sometimes we disagree. Sometimes we think they're justified. Sometimes we think they are not, but regardless it is a way of shouting. And when you shout, people tend to hear you, even if they don't necessarily hear the words that you're saying they hear that you you were shouting. I see no way. So, another way of putting it, which I think is less, um, let us just say, um provocative, but I think it is true is that, um, all change particularly change that impacts power requires struggle. The struggle doesn't have to be violent, you know, but it's a struggle nonetheless, </s><s>[INST] the powerful don't give up power easily. [/INST] I mean, why, why should they? But even so, he still has to be a story. And by the way, this isn't just about, you know, violent political, whatever, nonviolent political change, right? This is true for understanding calculus, right? I mean, everything requires a struggle back to talking about faculty at the end of the day, In the end, the day it all comes down to faculty are all a metaphor. Faculty argue the metaphor for all of life. </s><s>[INST] Let me ask you a strange question. Do you have a uh, do you think everything is gonna be okay in the next year? Do you have a hopeful, do you have a hope [/INST] that we're gonna be okay? I tend to think that everything's gonna be okay because I just tend to think that everything's gonna be okay. My mother says something to me a lot uh, and always has and and I find it quite comforting which is this too shall pass and this too, shall pass now. This too, shall pass is not just a, this bad thing is going away. Everything passes. I mean, I have a 16 year old daughter who's Going to go to college probably about 15 minutes given how fast she seems to be growing up and you know, I get to hang out with her now, but one day I won't, she'll ignore me just as much as I ignored my parents when I was in college I went to grad school, this too shall pass, but I think that you know one day if we're all lucky you live long enough to look back on something that happened a while ago, even if it was painful and mostly it's a memory. So yes, I think I think it'll be okay. </s><s>[INST] What about humans do you think well we'll live into the 21st century? I certainly hope so. Are you worried about are you worried that we might destroy ourselves with nuclear weapons with a G. I with uh ingenious, [/INST] I'm not worried about a G. I doing it, but I am worried, I mean in any given moment right also, but you know that any given moment of comic and I mean, you know whatever, I didn't think that outside of things completely beyond our control, we have a better chance than not of making it, </s><s>[INST] you know, I talked to Alex Filippenko from For Berkeley, he was talking about comments and that they can come out of nowhere. And the dad was the realization to me uh wow, where we're just watching this darkness and they can just enter and then we have less than a month [/INST] and yet you make it from day to day </s><s>[INST] that one shall not pet well maybe for earth will pass but not for [/INST] humans, but I'm just I'm just choosing to believe that it's going to be okay and we're not going to get hit by an asteroid at least not while I'm around. And if we are, well there's very little I can do about it. So I might as well assume it's not going to happen. It makes food taste better. It makes food taste better. </s><s>[INST] So you out of the millions of things you've done in your life, you've also began the this week in Black history calendar effects. There's, there's like a million questions that can ask here. You said you're not a historian. But is there, let's start at the big history question of is there somebody in history in black history that you draw a lot of philosophical or personal inspiration from or you just find interesting or a moment in history you find interesting? [/INST] Well, I find the, the entirety of the 40s to the 60s and the civil rights movement that didn't happen and did happen at the same time during them quite inspirational. I mean, I've I have, uh, I've read quite a bit of the time period. At least I did, uh, in my younger days when I had more time to read as many things as I wanted to. Uh, What was quirky about this week in black history when I started, uh, in the 80s, uh, was how focused it was. It was because of the sources I was stealing from. And I was very much stealing from sort of like I think calendar anything I could find google didn't exist right. I just pulled as much as I could and just put it together in one place for other people. What ended up being quirky about it? And I started getting people sending me information was the inventors, people who, you know, carried morgen too. Benjamin Banneker, right. People who were inventing things um, at a time when how in the world did they manage to invent anything? Like all these other things were happy mother necessity, right? All these other things were happening and you know, there were so many terrible things happening around them and you know, they went to the wrong state at the wrong time. They may never never come back, but they were inventing things we use, right. And uh, it was always inspiring to me that people would still create even under those circumstances. Um, I got a lot out of that. I also learned a few lessons I think, you know, the Charles, richard jews of the world, you know, you, you, you create things that impact people, you don't necessarily get credit for them and that's not right. But it's also okay. </s><s>[INST] Are you okay with that [/INST] up to a point? I mean, look in our world, all we really have is credit. </s><s>[INST] I was always bothered by how much value credit is given. [/INST] That's the only thing you got, I mean if you're an academic in some sense, it isn't the only thing you've got, but it feels that way sometimes, </s><s>[INST] but you got the actual we're all gonna be dead soon. You got the joy of having created Yeah. You know the credit we gone, I talked to your arrangement hoover, right? Uh the touring award given two or three people for Deep Learning and you could say that a lot of other people should be on that list. It's the Nobel Prize question. Yeah, it's sad, it's sad and people like talking about it, but I feel like in the long arc of history, the only person who will be remembered is Einstein, Hitler, maybe all [/INST] musk </s><s>[INST] and the rest of us are just like, [/INST] well, you know, someone asked me about immortality once and I said and I stole this from somebody else, I don't remember who, but it was, you know, I asked him, what's your great grandfather's name, Any of them, Of course, they don't know. Most of us do not know, I mean, I'm not entirely sure I know my grandparents, all my grandparents names, I know what I called them, right, I don't know their middle names for example. Um then within living memory, so I could find out actually my grandfather didn't know when he was born and how old it was, right, but I definitely don't know any my great grandparents are, so in some sense, immortality is doing something preferably positive, so that your great grandchildren know who you are, right, and that's kind of what you can hope for, which is very depressing in some ways. Uh you can I could turn it into something uplifting if you need me to. But can you do the work here? Yeah, it's simple, right? It doesn't matter. I don't have to know my great grandfather was to know that I wouldn't be here without them. Yeah, and I don't know who my great grandchildren are, certainly have my great great grandchildren are and I'll probably never meet them, although I would very much like to, but hopefully I'll set the world in motion in such a way that their lives will be better than they would have been if I hadn't done that. Well, certainly they wouldn't have existed if I hadn't done the things that I did. So um I think that's a good positive thing. You live on through other people. </s><s>[INST] Are you afraid of death? [/INST] I don't know if I'm afraid of death, but I don't like it. Another t shirt. </s><s>[INST] I mean, do you ponder it, Do you think about the [/INST] the inevitability of Oblivion? I do occasionally. Um it feels like a very Russian conversation actually. I will tell you a story very uh something happened to me yesterday. I um if you look very carefully you'll see I have a scar um which by the way is an interesting story of its own about why people have half of their thyroid taken out. Some people get scars and some don't. um but anyway, I uh I had half my thyroid taken out. The way I got there, by the way, is it's an interesting story, but I won't go into it, just suffice it to say I did what I keep telling people should never do, which is never go to the doctor unless you have to because there's nothing good that's ever going to come out of a doctor's visit. Right? So I went to the doctor to do look at one thing, this little bump I had on the side that I thought might might be something bad because my mother made me and I went there and he's like, oh it's nothing, but by the way, your thyroid is huge, can you breathe? Yes, I can breathe you sure, because it's pushing on your windpipe, you should be dead, right? So I end up going there and to get my uh to look at my thyroid, it was growing, I was called a goiter. Um and he said, we're going to take it out at some point when sometime before your 85 probably, but if you wait till you're 85, that'll be really bad Because you don't want to have surgery when you're 85 years old, if you can help it, um certainly not the kind of surgery it takes to take out your thyroid. So um I went there and uh we decided I would decide to put it off until december 19th Because my birthday's December 18. And I want to be able to say I made it to 49 or whatever. So I said I'll wait till after my birthday. Um in the intervening in the first six months of that nothing changed Apparently in the next three months it had grown. I hadn't noticed this at all. I went and had surgery, they took out half of it, the other half is still there and working fine. By the way, I don't have to take a pill or anything like that, it's great, I'm in the hospital room and the um doctor comes in. I've got these things in my arm they're gonna they're gonna do whatever they're talking to me. And the anesthesiologist says your blood pressure's through the roof for you. Do you have high blood pressure? I said no but I'm terrified if that helps you at all. Um And the an ethicist who's the nurse who supports the anesthesiologist. Um I got that right. I said oh don't worry about I just put some put some stuff in your I. V. You're gonna be feeling pretty good in a couple of minutes. And I remember turning and saying uh well I'm gonna feel pretty good in a couple minutes. Next thing I know there's this guy and he's moving my bed and I have this and he's talking to me and have this distinct impression that I've met this guy and I should know what he's talking about. But I kind of like just don't remember what just happened and I look up and I see the tiles going by and I'm like oh it's just like in the movies where you see the tiles go by and then I have this brief thought that I'm in an infinitely long warehouse and there's someone um sitting next to me and I remember thinking oh she's not talking to me and then I'm back in the hospital bed. And in between the time where the tiles were going by and I got in the hospital bed, something like five hours had passed. Apparently it had grown so much that it was a 4.5 hour procedure instead of an hour long procedure. I lost the next size and a half. It's pretty big, apparently as big as my heart. Why am I telling you this? I'm telling you this because </s><s>[INST] I have this story already [/INST] between tiles going by and me waking up at my hospital bed. No time passed. There was no sensation of time passing when I go to sleep and I wake up in the morning, I have this feeling that time has passed. This feeling that something has physically changed about me. Nothing happened between the time they put the magic juice in me and the time that I woke up, nothing. By the way my wife was there with me talking. Apparently I was also talking, I don't remember any of this but luckily I didn't say anything. I wouldn't normally say my memory of it is I would talk to her and she would teleport around the room. Mm And then I accused her of witchcraft And that was the end of that. But she her point of view is I would start talking and then I would fall asleep and then I would wake up and leave off where I was before. I had no notion of any time passing. Yeah. I kind of imagine that that's death is the lack of sensation of time passing. And on the one hand, I am uh I don't know soothed by the idea that I won't notice. On the other hand, I am very unhappy at the idea that I won't notice. So I don't know if I'm afraid of death but I am completely sure that I don't like it and that I particularly would prefer to discover on my own whether immortality sucks. Um and be able to make a decision about it. That's what I would prefer. </s><s>[INST] Like I have a choice in the matter. [/INST] I would like to have a choice in the matter. </s><s>[INST] Well, again on the Russian thing, I think uh the finance of it is the thing that gives it a little flavor little spice so [/INST] well in reinforcement learning. We believe that that's why we have discount factors. Otherwise it doesn't matter what you do. </s><s>[INST] Amen. Well, let me one last question, sticking on the Russian team. Yeah, you talked about your great grandparents not remember their, their name. What do you think is the, in this kind of Markov chain? That is life? What do you think is the meaning of it all? What's the meaning of life? [/INST] Well, in a world where um, eventually you won't know who your great grand, you won't know your great grandchildren are um, I am reminded of a something I heard once when I read, I read once that I really like, which is, it is well worth remembering that the entire universe Safer one trifling exception is composed entirely of others. I think that's the meaning of life, </s><s>[INST] Charles. This is one of the best conversations I've ever had and I get to see you tomorrow again to hang out with with uh, who looks to be one of the most uh, how should I say, interesting personalities that I'll ever get to meet with Michael lippman, so I can't wait. I'm excited to have had this opportunity. Thank you for traveling all the way here. It was, it was amazing. I'm excited. I always love Georgia tech. I'm excited to see with you being involved there what the future holds. So thank you for [/INST] talking today. Thank you for having me android every minute. </s><s>[INST] Thanks for listening to this conversation with Charles is bo and thank you to our sponsors neuro that make her a functional sugar free gum and mints that I used to give my brain a quick caffeine boost, decoding digital, a podcast on tech and entrepreneurship that listen to and enjoy master class online courses that I watched from some of the most amazing humans in history and cache up the app. I used to send money to friends for food and drinks. Please check out these sponsors in the description to get a discount and to support this podcast. If you enjoy this thing, subscribe on youtube, review it with five stars on apple podcast. Following Spotify, support on Patreon, I'll connect with me on twitter, elects Friedman and now let me leave you with some poetic words from martin Luther king Jr. There comes a time when people get tired of being pushed out of the glittering sunlight of life's july and left standing amid the piercing chill of an Alpine november. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] you know, from uh, I would say from from uh, the mystery perspective, it seems like the mystery of our own like cognition and consciousness is much grander than like the degrees of freedom of possible explanations of what the heck is going on is much greater there than in the in the physics of the [/INST] how the brain works. How did life arise? Yeah, that's big, big questions. But they, to me, don't indicate the existence of of an alien or something. I mean unless we are the aliens, you know, we could have been contamination from some rocket ship that hit here a long, long time ago and all evidence of it has been destroyed. But again, that alien would have started out somewhere. They're not they're not here watching us right now, right there not among us. And so though there are explain potential explanations for the fermi paradox. And one of them that I kind of like is that the truly intelligent creatures are those that decided not to colonize the whole galaxy because they'd quickly run out of room there because it's exponential, right? You send a probe to a planet. It makes two copies they go out, they make two copies each. And it's an exponential, right? They quickly colonize the whole galaxy. But then the distance to the next galaxy, next big one like Andromeda, that's 2.5 million light years. That's a much grander scale now. Right? And so it also could be that the reason they survived this long is that they got over this tendency that may well exist among sufficiently intelligent creatures. This tendency for aggression and self destruction, right? If they bypassed that and that may be one of the great filters. If there are more than one right then they may not be a type of creature that feels the need to go and say oh there's a nice looking planet. Um and there's a bunch of you know ants on it. Let's go squish him and colonize it. No, it could even be the kind of star trek like prime directive where you go and explore worlds but you don't interfere in any way, right? </s><s>[INST] And and also we call it exploration is beautiful and everything. But there is underlying this desire to explore is the desire to conquer. Yeah. I mean if we're just being really honest [/INST] right now for us it </s><s>[INST] is and you're saying it's possible to separate. But I would venture to say that you wouldn't that those are coupled. So I could I could imagine a civilization that lives on for billions of years that just stays on like figures out the minimal effort way of just peacefully existing, it's like a monastery. [/INST] Yeah limits itself, </s><s>[INST] limits itself. [/INST] You know, it's it's planted its seeds in a number of places. So it's not vulnerable to a single point failure. Right? Supernova. Going off near one of these stars or something or an asteroid suddenly comic coming in from the art cloud equivalent of that planetary system and without warning, you know, thrashing them to bits. So they've got their seeds in a bunch of places but they chose not to colonized colonized the galaxy and they also choose not to interfere with this incredibly prevalent primitive organism, homo sapiens, right? </s><s>[INST] Or they uh this is like uh they enjoy is like a tv show for them. [/INST] Yeah, tv show. Right? So they tuned in, right? So those are possible explanations yet. I I think that to me the most likely explanation for the apparent paradoxes that they really are very, very rare. And you know, Carl Sagan estimated 100,000 of them. If there's that many, some of them would have been way ahead of us. And and I think we would have seen them by now if there are a handful maybe they're there. But at that point you're right on this dividing line between being a pessimist and an optimist and what are the odds for that, right? If you look at all the things that had to go right for us and then, you know, getting back to something you said earlier, let's discuss. You know, primitive life. That could be the thing that's difficult to achieve. Just getting the random molecules together to a point where they start self replicating and evolving and becoming better and all that. That that's an inordinately difficult thing I think though I'm not you know, some molecular cell biologist but just it's the usual argument. You know, you're wandering around in the Sahara desert and you stumble across a watch is your is your initial response? Oh, you know, a bunch of sand grains just came together randomly informed this watch. No, you you think that something formed it or it came from some simpler structure that then became you know, more complex. Alright. It didn't just form well. Even the simplest life is a very, very complex structure. Even the even the simplest pro carry optic cells, not to mention eukaryotic cells. Although that transition may have been the so called great filter as well. Maybe the cells without a nucleus are relatively easy to form. And then the big next step is where you have a nucleus which then provides a lot of energy which allows the cell to become much much more complex and so on, interestingly going from eukaryotic cells. Single cells to multicellular organisms does not appear to be at least on earth. One of these great filters because there's evidence that it happened dozens of times independently on earth. So by by a really great filter, something that happens very, very rarely. I mean that we had to get through, um, an obstacle that is just incredibly rare to </s>

<s>[INST] you're, there's a different use of the word swinging. [/INST] Sure. But I'm saying you could be clear, you look great, your hands muscular, thank you. You you get the job done. So I feel like you wouldn't leave without an orgasm on </s><s>[INST] her. Yeah, but I just like to, you know about fairies, I like to dress up with animals and and I just have trouble finding others who [/INST] like to sing up there. I could show you some chat rooms, </s><s>[INST] you're, you're also my coach for the internet. Okay uh what are you most afraid of? [/INST] I guess I'd unlived life, I'm always a big fan growing up of like wild guys, you know like these teddy Roosevelt who would go out and hunt lions and uh like bar fighting guys, I was obsessed with hunter? S Thompson types. And look this is what I love about guys, like who's a good example, like Hemingway, Hemingway was the manliest guy. He had the rifle and the elephant gun and the whiskey and the writing and the women and the fist fights, but people forget at the other side of that coin is I'm sure he was in a lot of hotel rooms weeping, I'm sure he was lonely as fuck. I'm sure he had some wicked hangovers. I mean he killed himself for christ's sake, so obviously he was dealing with something. So the key to me is having this adventurous life living to the fullest, doing crazy shit, scaring yourself but also not killing yourself. Like also not hating because I used to party a lot hard. I used to bang a lot of gals and this is the flip side is like this girl hates you now or you got herpes or you're hungover or your mom is like where where are you? You never call me anymore, you're like my mom, my five, let let ties go with my mom, I gotta connect. So this horrible, there's a horrible side of the party animal, The keith richards we don't see is not pretty. I mean he's already weird looking, but he's part and he's smoking, he's living, but there's another side of that coin and I think the key to life is living that fucking crazy awesome badass life and also having some, you know, meaning and and a little bit of uh what's the word? Not just not killing yourself, not going sad, not being depressed, there's a medium there a sweet spot. Does that make sense? </s><s>[INST] Yeah. So taking big leaps and uh Hemingway grabbing life by the balls, but at the same time not crushing the balls. That metaphor work at all. [/INST] Perfect like Evel Knievel. We all know what a badass fearless. Oh man, what a cool dude. He's got balls of steel, but he also lived like the back half of his life in a fucking uh you know Barca lounger where his legs were made of steel and he couldn't see straight and his dick didn't work. So you know what I mean? You've got to have a balance but you still want the balance. I'm willing to take a little bit of shit for a little bit of fun, but you don't want to go too hard </s><s>[INST] because we gotta still risk it. I mean Hunter? S Thompson it didn't end well. [/INST] Yeah, that's quite a ride. Quite a ride. </s><s>[INST] What small act of kindness were you once shown that you will never forget, wow, that's a great question. You're you're you're I just wrote this for the the guinea pig. You're the guinea pig for this is where like work shopping questions [/INST] here. Alright, I'll take it and you're not, you're open biking. This is your version. Um let's see. There's a couple of ladies in high school who were kind enough to hand job me. That was nice, which I really appreciate. I don't think women know how much that means to us. You know, women like, I'm not a piece of meat or whatever and you're like, I know, but if you just give me a hand job, it would it would make my world. It's like telling a kid he's smart or loved </s><s>[INST] the most people mentioned like a math teacher in middle school that was inspired them to get into science you it's give a shout [/INST] out to the, well, that's part of, that's not the nicest. But I'm just saying that goes a long way. Alright, let's see kindness. That's a great question. I want to give you a good answer. I I got lost when I was like six. I was I was walking around my dad and I zoned out and went away and next thing you know, I don't know where I am. I'm in a neighborhood. This old guy finds me crying on a lawn somewhere and he goes, uh come inside and he tried to call my parents and no, nothing came of it. Eventually they found me after like nine hours cops were there, The FBI's out there fucking helicopters. And I guess, you know, that's the nicest old guy, took me in for a couple hours and just sat me down and kept me safe. That's something. Oh, how about Enos? My transvestite nanny, Very kind. He uh did you hear about this? Okay, we had this transvestite nanny. He was like a drag queen, but it was in the 90s, it was weird, it was new and my bike got stolen and he, you know, my parents like, what are you gonna do? Their poor kids, You know? And he was like, fun, let's we're gonna go get that bike. And I was like, this guy's in a wig and high heels, big black guy. And I'm like, ah what are you gonna do? You know it's gone? And he's like, no, we're gonna go get it. So, we got in the van and drove around my neighborhood, saw the kids with the bike, you know, five street toughs? And uh he goes all right, do you want to come out or should I just do this? And I was like, you do it, I'm terrified, What are you crazy? And he got out of the van in full, you know heels and wig? And he went up to these guys and they went off, oh my God, look at this guy, homo figure in all this ship, You know, it's the nineties and he just stared at him long enough to where they were kind of like, all right, well, I guess we're gonna fight you now. And he goes, that's not your bike. And they go, what are you gonna do about it? And he puts his hand on the middle of the bike and they didn't do anything and he just picked it up. And so that's what I thought, Put the bike over, shoulder, slid the van door open through the bike in and we drove off. </s>

<s>[INST] Uh, awesome. So you mentioned jodi, she's often in uh, in your corner and does perhaps more trash talking than even you. So I mean if we could step away, she's an incredible human being is, is sort of as a fan. It's fun to watch the two of you both when your arm wrestling and just as people just see so much, I don't know, kindness and love radiating from the two of you whenever you're trash talking and talking about just random things are just talking about life. It's just a beautiful thing to watch and thank you for sharing that with the world. But maybe can you, um, she paid me to ask you this, What what, what, what, what are the things you love about jodi? Your wife jodi Larry, What are the ways she has affected your life? [/INST] Yeah, Jody and I go way back, right, We were in high school together. Um the thing that I admire most in people is is bravery. Uh to me it's the most admirable quality. And Jody always has inspired me because she's such a fighter. You know, if if she believes that something is true, um she she just she does not back down. She will, she will not and you can not to say that she's can't change her mind because she can, but while she is convicted, she will, she will not stop fighting. She's pulled me out of the fire repeatedly. We've we've lived through so many things. Very lucky </s><s>[INST] house. She made you a better arm wrestler. [/INST] She's fed me. </s><s>[INST] Yeah, I could see your you have videos of your house basically coming apart when she's not there. Yeah, [/INST] yeah, yeah. Without Jody, I'm on the street living in a tent and uh yeah, eating dog food. Yeah. </s><s>[INST] Um bravery. What about love? How is love made you stronger now? We're gonna make devon uncomfortable. Love is difficult [/INST] to accept love is one of those things that, you know, a lot of times you don't feel worthy of it. And so it's hard sometimes to accept someone's love and someone who really loves you. Yeah, they'll love you even when you don't, you know, and here you go, you're gonna make me cry Alex. Uh yeah, Jody and I've been through so much. Um and she's shown me how, you know she supported me just repeatedly repeatedly, </s><s>[INST] some of that is loyalty and patience and perseverance and all those things that's like when love really shows itself sticking through together for years, even when you're to the t times [/INST] Love and faith are powerful forces in this universe, you know, without them that we can descend into darkness very quickly, you know, as a world, even between people, you know, when love and faith is destroyed, then then we fall apart. You know, and I've I've been graced by by the love that jodi's given me. You know, it's it's allowed me to continue to build, you know, when you have love between people, then you build together. Um I love I love my family, I love Canada, I love the arm wrestling community. I have a love for what we're trying to achieve as a human species, you know, and uh you know, when, when that, when that falls apart, we don't have much. Yeah, just with my boy there. Yeah, </s><s>[INST] yeah. She um he also mentioned your uh and uh you once had a job where your death was a real possibility. So you were in the Canadian special forces. What did you take away from that experience that time? Life [/INST] was such a, such a great life. Really, really loved it. I honestly, I never I never wanted to leave. I never thought I would leave, I thought it would be there my whole life really to to get to serve, </s><s>[INST] what did you get to do? What, what was the things you loved, craftsmanship wise, like fun things you get to do, learn and challenge yourself and, and you mentioned sort of honor in terms of the serving part. [/INST] Yeah, my favorite thing about serving in the special forces was for sure the people that I worked with, that's probably the first thing I could say. Uh you know, I never, I always felt like totally comfortable and and putting my life in the other guy's hands. Um I was so happy to be in a place where I felt I could follow. Um like it didn't matter, like I knew that the people ahead of me were incredible. I knew the people beside me were incredible. So just having that faith in your team, it's very special and to know that there for there for a reason that has nothing to do with money, you know, there and that's what kind of brings everybody together is you're there for a higher purpose. Uh and in terms of being an adrenaline junkie, there's nothing like it. I mean, there's nothing like, you know, going out at night and fighting, uh and when I say fighting like my whole life, I wanted to fight. Uh and to me, there's a lot of the, and, and look, I've said this in the past and I think it's been a personal failure of mine because I've said things like it's the highest level that you can do and I don't believe that to be true anymore, but at the time, uh I thought it was the best way I could express um my drives that I had, you know, to be a fighter. Um </s><s>[INST] So oh, it's a, your sense in the past and maybe in part now is that fighting is when humans get a chance to express themselves deeply, like like that that mix of the bravery, the integrity, the yeah, whatever that is that makes us human, that human spirit can really shine. [/INST] And I don't believe that anymore. I believe that you can do that in any field in any discipline. You know, if you go hard enough, it all kind of starts to feel the same. Um but at the time uh that you know, expression to me was really, really awesome. I loved, I loved close quarter battle, that was my favorite thing. That's really the whole reason I was there. </s>

<s>[INST] Whenever I think about something like unconventional cognition, I think about cellular automata, I'm just captivated by the beauty of the thing. The fact that from simple little objects you can create some such beautiful complexity that very quickly you forget about the individual objects and you see the things that it creates as its own organisms. That blows my mind every time. Like honestly I could full time just eat mushrooms and watch silly or tom and they don't even have to do mushrooms. Uh just just sell your tom. And it feels like, I mean from an engineering perspective, I love when a very simple system capture something really powerful because then you can study that system to understand something fundamental about complexity about life on earth anyway, How do I communicate with the thing facilitator, tom can do cognition. If a plant can do cognition, if uh zen robot can do cognition. How do you like whisper in its ear and and and get an answer back to. How do I have a conversation? Yeah. [/INST] Um well </s><s>[INST] how do I have a on a podcast? [/INST] That's really, really interesting line of investigation that that that that that opens up. I mean, I mean we've we've thought about this. So you need a few things you need you need to understand the space in which they live. So what not, not just the physical modality. Like can they see like can they feel vibration? I mean, that's important of course, because that's how you deliver your message, but not just not just the ideas for a communication medium, not not just the physical medium, but what is saliency? Right. So, so what are these, what are important to this? What's important to the system and systems of all kinds of different levels of sophistication of what you could expect to get back. And I think what's what's really important I call this um the spectrum of persuade ability, which is this this idea that when you're looking at a system you can't you can't assume where on the spectrum it is. You have to do experiments. And so so so so for example, uh if you look at a gene regulatory network which is a bunch of bunch of nodes that turn each other on and off at various rates, you might look at that and you say, well, there's no magic here. I mean, clearly this thing is is as deterministic as it gets. It's a piece of hardware. The only way we're going to be able to control it is by rewiring it, which is the way molecular biology works, right? We can add no, it's removed notes or whatever. Well, so we've done simulations and shown that um biological and now we're doing this in the lab. The biological networks like that have have associative memory. So they can actually learn, they can learn from experience. They have habituation sensitization, they have associative memory, which you wouldn't have known if you assume that they have to be on the left side of that spectrum. So when you're going to communicate with something and we've even um uh Charles Abrams and I've written a paper on behaviorist approaches to synthetic organism, meaning that if you're given something you have no idea what it is or what it can do. How do you figure out what its psychology is, what its level is, what does it. And so and so we literally lay out a set of protocols starting with the simplest things that are moving up to more complex things where you can make no assumptions about what this thing can do right? Just from you, you have to start and you'll find out. So so when you're gonna so here's a simple, I mean here's one way to communicate with something if you can train it, that's a way of communicating. So if you can provide if you can figure out what the currency of of reward of of positive and negative reinforcement is, right and you can get it to do something that wasn't doing before based on experiences you've given and you have taught it. One thing you have communicated one thing that that such and such an action is good. Some other action is not good. That's that's like a basic atom of primitive atom of communication. What </s><s>[INST] about in some sense if it gets you to do something you haven't done before, isn't answering back [/INST] most? Most certainly. And then there's there's, I've seen cartoons, I think maybe Gary Larson or somebody had had a cartoon of these of these rats in the maze and the one rat, you know, says to the other like this every time, every time I walk over here he starts scribbling in that on the, you know, on the report that he has. It's awesome </s><s>[INST] if we step outside ourselves and really measure how much, like if I if I actually measure how much I've changed because of my interaction with certain cellular automata. I mean you really have to take that into consideration about like, well these things are changing you too. I know you know how it works and so on, but you're being changed by the thing. [/INST] Absolutely. I think I think I read um I don't know any details, but I think I read something about how how wheat and other things of domesticated humans in terms of right, but by their properties change the way that the, the human behavior and societal structures </s>

<s>[INST] I don't think there's a better way to end as Sebastian. It's an honor to talk to you to have had the chance to learn from you. Thank you so much [/INST] for talking. Thanks for coming on like a real pleasure. </s><s>[INST] Thank you for listening to this conversation with Sebastian Thrun and thank you to our presenting sponsor cash app, download it. Use cold lex podcast, you'll get $10.10 dollars will go to first a stem education non profit that inspires hundreds of thousands of young minds to learn and to dream of engineering our future. If you enjoy this podcast? Subscribe on youtube, get five stars on apple podcast, support on Patreon or connect with me on twitter [/INST] and now let me leave </s><s>[INST] you with some words of wisdom from Sebastian Thrun. It's important to celebrate your failures as much as your successes. If you celebrate your failures really well. If you say wow, I failed, I tried, I was wrong, but I learned something, then you realize you have no fear when your fear goes away, you can move the world. Thank you for listening and hope to see you next time. [/INST] Yeah. </s>

<s>[INST] Absolutely, but there's a, there's a, that's like the best thing that could be, but sometimes it's fun to lose yourself in um in the, in the bragging in the, in the lesser ways of life and I think I'm careful not to uh because too many people in my life when I brought them with like a little candle of a fire of a dream, they would just go like, you know, they would just blow that fire out uh that they would dismiss me because they see like, you know, I would say I said I've said a lot of ridiculous stuff, but you know, I've always dreamed about like putting, I always dreamed of having this world full of robots and you know, every time I would uh bring these ideas out, there will be shut down by the different people, but my parents by you know, uh you know that you need to first get to get an education, you need to succeed in these dimensions and in order to do all these things, you have to get good grades, you have to blah blah blah blah. Like there's all the stuff that it's indirect or direct ways of blowing out that little ridiculous dream that you present, It's like, you know, I remember sort of bringing up, I don't know, um things like becoming a state champion in wrestling, right? Mhm. It's a it's a weird dance because of course the coaches will tell, they'll kind of dismiss that it's like, okay, okay, but at the same time, it feels like in those early days you have to preserve that little little fire, that's johnny, I I don't know if you know that it is a designer at Apple, He was the chief designer, He's behind most iphone all that stuff and he always he always talked about that. He wouldn't bring his ideas to steve jobs until they were matured because he would always shoot on them. Uh, he would, he wanted them to like little as little babies, like live for a little bit before they get completely shut down. And I always think about that when I see a beginner sort of bragging on instagram, you have to be careful, let's let them play with that little dream. [/INST] You know, are you playing with a little dream that you're nurturing and you're trying to take that little flame and you're trying to create a roaring blaze with it or are you playing with the idea of it and behind behind that there's no substance. </s><s>[INST] It's hard to know the difference. That's why I struggle with, is it? [/INST] I don't think it necessarily is certainly you're wrong. And when I say instagram, I don't want to impute a bunch of strangers, but I have a gym with a lot of members and I can tell you that the number of years I've been in the gym when someone comes to me and says, this is my goal, I don't, I don't tell them yes or no in general, but I know I can tell by the way they say it to me, I can thin slice it. I've seen the look on people's faces and when people start to like say they want to do X, y and z. I know right off the bat this person is either gonna put an effort in or they're not going to put an effort in. So, to me, it's about the effort behind that. If you're busting your ass and you're a newt at something in your brand new, but you're working really hard and you have a series of, like, moderate successes in that, like, that's the guy I want a champion because that persistence and that grit over time, those successes will no longer be moderate, there'll be huge, but the person who's having moderate success by doing nothing, chances are they'll never learn to put that work in and the successes will never grow. </s><s>[INST] You have an admiration for Mike Tyson, [/INST] I love him. </s><s>[INST] I was gonna let that sit for a brief moment. Um, why [/INST] I think there's a combination of factors, one is like the timeliness of his career and like, the age I was when he came to prominence, um, the raw, brutal violence and the raw, brutal honesty When he speaks, I think it's easy for people to hear him or see his life and cast him aside as some simian esque, uh, like just Creon scourge on society, but when you hear him speak like, this is not a guy who's unintelligent, this is a guy who knows himself better than probably most of us know ourselves, it's disarming and uh, you know, that's a humongous part of my admiration for him </s><s>[INST] who is Mike Tyson because it feels like there's similarity between him and you. There's a, it feels like there's a violent person in there, but also really kind person and they're all like living together in a little house and you're the same. There's a thoughtful person, but there's also a scary violent person and they're like having a picnic. [/INST] They're having a picnic. I think they're dialectical tensions and everyone these like opposing forces that are constantly pulling at you and at different points in your life. Like it's a sliding scale. And I think that, uh, certainly when I was a younger person, there was a lot more manifestation of the violence and a lot less of the kindness. Um, people who were not as close to me probably saw more of the violent side and only the very close people to me. So, like what would pass for the kind side and now that's sliding in the other direction. Uh, I worry, actually, sometimes that there could be a situation where I need that old version of me and he's getting further and further away and I can't call him up if I need him. And that concerns me too, to a certain degree, </s>

<s>[INST] I made me don't with the Mercury in the rocket, but build the rocket, [/INST] it's your choice. Yeah, because that's a rocket which you are building. But what is important that you'll do it? </s><s>[INST] Well, I think this is a good time to ah to maybe toast our family. Some we thought we'll do, we'll probably drink more vodka. But we decided to be responsible adults and just save the vodka to the end. [/INST] It's always a question. How much, what can we have to drink in Russian tradition? Usually we calculate for adults like one battle per one battle per perfect. Take a look at his made in soviet union and its 1986. This is what of my father because Uh in 1986, in a year of Chernobyl, he gave this bottle to friend of mine because this friend of mine, he went to America and he just this my friends, he just saved this basket for us to be able to just whatever to think about. </s><s>[INST] Can you see his name? [/INST] Uh, your friend. Uh he's Sasha, but we call him. Sure, sure. But that's the same thing. </s><s>[INST] Is your best friend, your lifelong friend. [/INST] Yes. It's like your math </s><s>[INST] matt. I met her and he shut up and first you can toast the family. But let me just toast to the best dad I've ever had. The best that I could ever ask for. [/INST] I love you dad. Yeah, I love you. </s><s>[INST] Let's go thank you for listening to this conversation with my dad and thank you to our sponsors the Jordan Harbinger show, a magic spoon cereal. Go check out Jordan's show on apple podcast, Spotify and tell him I sent you listen to the Kobe Bryant or Neil degrasse Tyson episodes first or just binge listen to a bunch of them like I did and by all of the magic spoon cereal, click magic spoon dot com slash lex in the description and use code lex at checkout. If you enjoy this podcast, subscribe on youtube, review it with five stars on apple podcast supporter on patreon are simply connect with me on twitter at lex Friedman and now let me leave you with the request. If they're close people in your life, we've never sat down to really talk with and they're still here with us. Talk to them Heart to Heart podcast or not. They won't always be here with us. Life is short and most of it is a distraction from what really matters. Family, friendship and love. Thank you for listening and hope to see you next time [/INST] </s>

<s>[INST] and but some uh way outside the scope of my knowledge. So economists would argue that the what is it? The invisible hand? So the capitalist system, it was the oversight. So if you're going to corrupt society with whatever decision you make as a company, then that's going to be reflected in people not using your product, sort [/INST] of one </s><s>[INST] that's one model of oversight. [/INST] So we shall see. But in the meantime, you know that but you might even have broken the, uh, the political system that enables capitalism to function well, </s><s>[INST] you've changed it so we should change is often painful. So, my question is, uh, absolutely. It's fascinating. You're absolutely right that there was zero oversight on algorithms that can have a profound civilization changing uh, effect. So, do you think it's possible? I mean, I haven't. Have you seen government? So do you think it's possible to create regulatory bodies oversight over ai algorithms which are inherently such cutting edge set of ideas and technologies? [/INST] Yeah, But I think it takes time to figure out what kind of oversight, what kinds of controls and it took time to design the FDA regime. You know, some people still don't like it and they want to fix it. And I think there are clear ways that it could be improved. But the whole notion that you have stage one, stage two, Stage three and here are the criteria for What you have to do to pass the stage one trial. Right. We haven't even thought about what those would be for algorithm. So, I mean, I think there are there are things we could do right now with regard to bias. For example, we have a pretty good technical handle on how to detect algorithms that are propagating bias that exists in datasets, how to de bias those algorithms. Um, and even what it's going to cost you to do that. So, I think we could start having some standards on that. I think there are there are things to do with impersonation of falsification that we could we could work on. So I think, yeah, </s><s>[INST] uh or a [/INST] very simple point. So impersonation is um is a machine acting as if it was a person. I can't see a real justification for why we shouldn't insist that machines self identify as machines. Uh you know, where where is the social benefit in in fooling people into thinking that this is really a person when it isn't, you know, I don't mind if it uses a human like voice, that's easy to understand. That's fine. But it should just say I'm a machine in some some form </s><s>[INST] and not many people are speaking to that. I would think relatively obvious facts. I think most [/INST] people there is actually a law in California that bans impersonation but only in certain restricted circumstances. So for the purpose of engaging in a fraudulent transaction and for the purpose of modifying someone's voting behavior. Uh So those are those are the circumstances where machines have to self identify, but I think, you know, arguably it should be in all circumstances. Um and then when you when you talk about deep fakes, you know, we're just at the beginning, but already it's possible to make a movie of anybody saying anything in ways that are pretty hard to detect, </s><s>[INST] including yourself because you're on camera now and your voice is coming through with high [/INST] resolution. So you can take what I'm saying and replace it with it pretty much anything else you wanted me to be saying. And even it would change my lips and facial expressions to fit. And there's actually not much in the way of real legal protection against that. I think in the commercial area you could say yeah that's you're using my brand and so on. There are rules about that. But in the political sphere I think it's at the moment it's you know, anything goes so that that could be really, really damaging. </s><s>[INST] And let me just try to make not an argument but try to look back at history and uh say something dark in essence is while regulation seems to be oversight seems to be exactly the right thing to do here. It seems that human beings what they naturally do is they wait for something to go wrong. If you're talking about nuclear weapons, you can't talk about nuclear weapons being dangerous until somebody actually like the United States drops the bomb. Or Chernobyl melting. Do you think we will have to wait for things going wrong in a way that's obviously damaging to society. Not an existential risk, but obviously damaging. Or do you have faith [/INST] that I hope not. But I mean I think we do have to look at history and uh you know, so the two examples you gave nuclear weapons and nuclear power. Very very interesting because nuclear weapons we knew in the early years of the 20th century that atoms contained a huge amount of energy right? We had E. Equals M. C. Squared. We knew the mass differences between the different atoms and their components and we knew that you might be able to make an incredibly powerful explosive. So H. G. Wells wrote science fiction book I think in 1912 Frederick Saudi, who was the guy who discovered isotopes is a Nobel prize winner. He gave a speech in 1915 saying that £1 of this new explosive would be the equivalent of 150 tons of dynamite. Which turns out to be about right? And you know this was in World War One right? So he was imagining how much worse the World War would be uh if we were using that kind of explosive. But the physics establishment simply refused to believe that these things could be made </s><s>[INST] including the people who are making it. [/INST] Well. So they were doing the nuclear physics, </s>

<s>[INST] Okay, so that means engineering, programming, your engineering them in the future. And in some sense, the definition of a robot is something you in part engineer and versus evolved. I mean it's such a fuzzy definition anyway in some sense. Many of the organisms within our body are kinds of robots. And I think robots is a weird line because it's we tend to see robots as the other. I think there will be a time in the future when there's going to be something that came to the civil rights movements for robots. But we'll talk about that later perhaps anyway. Um So how do you, can we just linger on it? How do you build a robot? What are we talking about here from from whence does it start? And how does it become the glorious. [/INST] Yeah. So just take one step back. One of the things that a lot of people get stuck on is they say, well uh you know, engineering requires new D. N. A. Circuits or it requires new nano materials. You know what the thing is? We are now moving from old school engineering which use passive materials. Right. The things that you know, wood metal, things like this that basically the only thing you can depend on is that they were going to keep their shape. That's it. They don't do anything else. You it's on you as an engineer to make them do everything they're going to do. And then there were active materials and now computation materials, this is a whole new era. These are a gentle materials. This is your your now collaborating with your substrate because your material has an agenda. These cells have you know, billions of years of evolution. They have goals, they have preferences. They're not just going to sit where you put them. </s><s>[INST] That's hilarious that you have to talk your material and to keep [/INST] that is exactly right. That is exactly right </s><s>[INST] there. It's like getting a bunch of cats or something and trying to organize the shape out of them. [/INST] It's funny, we're on the same page here because in the paper this is this is currently um just been accepted in nature by engineering. One of the figures I have is building a tower out of legos versus dogs. Right? So think about the difference, right? If you build out of legos you have full control over where it's gonna go. But if somebody knocks it over, it's game over with the dogs, you cannot just come and stack them. They're not going to stay that way. But the good news is that if you train them, then somebody knocks it over, they get right back up. So it's all right. So as an engineer, what you really want to know is what can I depend on this thing to do, Right? That's really, you know, a lot of people have definitions of robots as far as what they're made over how they got here. You know, design versus evolved whatever. I don't think any of that is useful. I think I think as an engineer, what you want to know is how much can I depend on this thing to do when I'm not around to micromanage? At what level of uh what level of dependency can I can I give this thing, how much agency does it have, which then tells you, what techniques do you use? So do you use micromanagement? Like you put everything where it goes? Do you train it? Do you give it signals to try to convince it to do things, right? How much you know, how intelligent is your substrate? And so now we're moving into this into this area where you're you're you're working with a gentle materials. That's a collaboration. That's not that's not old old style agency. It comes from the word agency. So, so basically the material has agency meaning that it has some some level of obviously not human level, but some level of preferences, goals, memories, ability to remember things too compute into the future, meaning anticipate. Um, you know, when you're working with cells, they have all of that to some to to various degrees. </s><s>[INST] Is that empowering or limiting? Having material has a mind of its own, literally. [/INST] I think it's both. Right? So it raises difficulties because it means that if you if you're using the old mindset, which is a linear um kind of extrapolation of what's going to happen, you're going to be surprised and shocked all the time, because biology does not do what we linearly expect materials to do. On the other hand, it's massively liberating. And so in the following way, I've argued that advances in regenerative medicine require us to take advantage of this because what it means is that you can get the material to do things that you don't know how to micromanage. So, just as a simple example, right? If you if you you had a rat and uh you wanted this rat to do a circus trick, put a ball in a little, you can do it the micromanagement way, which is try to control every neuron and try to play the thing like a puppet, right? And maybe someday that will be possible. Maybe or you can train the rat and this is why humanity for thousands of years before we knew any neuroscience, we have no idea what's behind what's between the ears of any animal. We were able to train these animals because once you recognize the level of agency of a certain system, you can use appropriate techniques. If you know the currency of motivation, reward and punishment, you know how smart it is, you know what kinds of things it likes to do? You are searching a much more, much smoother, much nicer problem space than if you try to micromanage the thing and then regenerate medicine when you're trying to get, let's say, an arm to grow back or an eye to repair cell birth defect or something. Do you really want to be controlling tens of thousands of genes at each point to try to micromanage it? Or do you want to find the high level modular controls? Let's say, build an arm here, You already know how to build an army. You did it before. Do it again. So that's, I think it's it's both it's both difficult and it challenges us to develop new ways of engineering and it's it's hugely empowering. </s>

<s>[INST] sure. Lots of [/INST] sex. Yeah. </s><s>[INST] Okay, what else? [/INST] Lots of sex and lots of variety, right? So look, every red blooded american slash Russian mail could understand why that's appealing, right? On the other hand, it is up against an alternative which is having a partner with whom one is bonded especially closely, right? </s><s>[INST] And so a love, [/INST] right? Well, you know, I don't wanna I don't wanna uh straw man the political position obviously politically is complex. And there's nothing that stops a man presumably from loving multiple partners and from them loving him back. But in terms of, you know, if love is your thing, there's a question about, okay, what is the quality of love if it is divided over multiple partners, right? And what is the net consequence for love in a society when multiple people will be frozen out for every individual male in this case who has it? Um, and what I would argue is, and you know, this is weird to even talk about, but this is partially me just talking from personal experience, I think there actually is a monogamy program in us and it's not automatic, but if you take it seriously, you can find it and frankly marriage and it doesn't have to be marriage, but whatever it is that results in a lifelong bond with a partner has gotten a very bad rap? You know, it's the butt of too many jokes. But the truth is it's hugely rewarding. It's not easy. But if you know that you're looking for something, right? If you know that the objective actually exists and it's not some utopian fantasy that can't be found. If you know that there's some real world, you know, warts and all version of it, then you might actually think, hey, that is something I want and you might pursue it. And my guess is you'll be very happy when you find it. </s><s>[INST] Yeah, I think there is getting to the fundamentals of the emergent. I feel like there is some kind of physics of love. So one there's a conservation thing going on. So if you have like many partners, yeah, in theory, you should be able to love all of them deeply. But it seems like in reality that love gets split, yep now there's another law that's interesting in terms of monogamy, I don't know if it's the physics level, but if you are in a monogamous relationship by choice and almost as um in slight rebellion to social norms that's much more powerful. Like if you choose that one partnership that's also more powerful if like everybody is in a monopoly this is this pressure to be married in this pressure of society that's different because that's almost like a constraint on your freedom that is enforced by something other than your own ideals, it's by by somebody else when you yourself choose to, I guess create these constraints that enriches that love. So there's some kind of love function like Ecos EMC squared, but for love that I feel like if you have less partners and it's done by choice that can maximize that. And that love can transcend the biology, transcend the evolutionary biology forces that I have to do much more with survival and all those kinds of things. It can transcend to take us to a richer experience, which we have the luxury of having exploring of happiness, of of joy or fulfillment. All those kinds of things [/INST] totally agree with us. And there's no question that by choice, when there are other choices imbues it with meaning that it might not otherwise have. I would also say I'm I'm really struck by and I have a hard time not feeling terrible sadness over what younger people are coming to think about this topic. I think they're missing something so important and so hard to phrase. And they don't even know that they're missing it. They might know that they're unhappy, but they don't understand what it is they're even looking for because nobody's really been honest with them about what their choices are. And I have to say if I was a young person or if I was advising a young person, which I used to do again a million years ago when I was a college professor four years ago. Um but I used to, you know, talk to students, I knew my students really well and they would ask questions about this. And they were always curious because heather and I seemed to have a good relationship and many of them knew both of us. So they would talk to us about this. If I was advising somebody, I would say, do not bypass the possibility that what you are supposed to do is find somebody worthy, somebody who can handle it. Somebody who you are compatible with and then you don't have to be perfectly compatible. It's not about dating until you find the one, it's about finding somebody who's underlying values and viewpoints are complementary to yours sufficient that you fall in love. If you find that person opt out together, get out of this damn system. That's telling you what sophisticated to think about love and romance and sex, ignore it together, right? That's the key. And I believe you'll end up laughing in the end. If you do it, you'll discover, wow, that's a hellscape that I opted out of And this thing I opted into complicated, difficult. Worth it. </s><s>[INST] Nothing that's worth it is ever not difficult. So we should we should even just skip the whole write a statement about difficult. [/INST] Alright. I just, I want to be honest. It's not like, oh, it's, you know, it's nonstop joy. No, it's freaking complex. But um but worth it. No question in my mind, </s>

<s>[INST] So let's jump into it a little bit most people know. But actually [/INST] I two </s><s>[INST] years ago I had no idea what effective altruism was. Until I saw there was a cool looking event an M. I. T. Group here. They I think the it's called the effective altruism club or a group. I was like what the heck is that? Um One of my friends said I mean they he said that uh they're just a bunch of eccentric characters. So I was like hell yes I'm in. So I went to one of their events and looked up, what's it about? It's quite a fascinating philosophical and just a movement of ideas. So can you tell me what is effective altruism? [/INST] Great. So the court of effective altruism is about trying to answer this question which is how can I do as much good as possible with my scarce resources my time and with my money. And then once we have our best guess answers to that, trying to take those ideas and put them into practice and do those things that we believe will do the most good and when our community of people uh many thousands of us around the world who really are trying to answer that question as best we can and then use our time and money to make the world better. </s><s>[INST] So what's the difference between sort of uh classical general idea of altruism and effective altruism? [/INST] So normally when people try to do good, they often often just answer reflective about those attempts. So someone might approach you on the street asking you to give to charity. Um and you know, if you're feeling altruistic, you'll give to the person on the street or if you think, oh, I want to do some good in my life, you might volunteer at a local place or perhaps you'll decide, you know, pursue a career where uh you're working in a field that's kind of more obviously beneficial, like being a doctor or a nurse or healthcare professional. Uh but it's very rare that people apply the same level of rigor and analytical thinking to lots of other areas we think about. So take the case of someone approaching you on the street. Imagine if that person instead was saying, hey, I've got this amazing company, do you want to invest in it? Um It would be insane and no one would ever think, oh of course I'm just the company, like you think it was a scan. Um but somehow we don't have that same level of they go when it comes to doing good, even though the stakes are more important when it comes to trying to help others, then trying to make money for themselves. </s><s>[INST] Well, first of all, so there is a psychology at the individual level of doing good just feels good. And so in some sense, on that pure psychological part, it doesn't matter. In fact you don't want to know if it does good or not because most of the time it won't. So like uh in a certain sense it's understandable why altruism without the effective part is so appealing to a certain population, by the way, let's zoom out for a second. Um Do you think most people two questions? You think most people are good Question # two Is do you think most people want to do good? [/INST] So are most people good? I think it's just super dependent on the circumstances that someone is in. Um I think that the actions people take and their moral worth is just much more dependent on circumstance than it is on someone's intrinsic character. So </s><s>[INST] is it evil within all of us? It seems like uh like the better angels of our nature. There's a tendency of us as a society to tend towards? Good, less war. I mean with all these metrics, what is that us becoming who we want to be or is that some kind of societal force? What's the nature versus nurture thing [/INST] here? Yeah. So in that case I just think, yeah, so violence is massively declined over time. I think that's a slow process of cultural evolution, institutional evolution, such that Now the incentives for you and I to be violent are very, very small indeed in contest when we were hunter gatherers, the incentives were quite large. If there was someone who was, you know, potentially disturbing the social order in hunter gatherer setting, there was a very strong incentive to kill that person and people did. And it was just the guarded, you know, 10% of deaths among hunter gatherers </s><s>[INST] arguably [/INST] were murders </s><s>[INST] after hunter gatherers. When you have actual societies is when violence can probably go up because there's more incentive to do mass violence right to um take over other, conquer other people's lands and murder everybody in place and so on. [/INST] Yeah, I mean, I think total death later the mother from human courses does go down. But you're like that if you're gonna hunt together situation, you're kind of a group that you're part of is very small, then you know, you can't have massive wars that just massive communities </s><s>[INST] don't accept. But anyway, the second question, do you think most people want to do good. [/INST] Yeah. And then I think that is true for most people. I think you see that with the fact that um, you know, most people donate, um, a large proportion of people volunteer. If you give people opportunities to easily help other people, they will take it. Um, but at the same time where uh, product of circumstances and if it were more socially rewarded to be doing more good, if it were more socially rewarded to do good effectively, a lot of them not effectively, then we would see that behavior a lot more. Um, </s><s>[INST] so why, why why should we do good? [/INST] Yeah. My answer to this is there's no kind of deeper level of explanation. So, um, my answer to kind of wife you good is, well there's someone whose life is on the line, for example, whose life you can save um via donating just actually a few $1000 to an effective non profit. Um, like the against malaria foundation, that is a sufficient reason to do good. And then if you ask, well why or I do that, I'm like, I just show you the same fact again those, it's that fact that is the reason to do good. There's nothing more fundamental than that. </s>

<s>[INST] What's the so many term? That's just one of [/INST] the spells and yeah, probably most notably Harry uses it to summon his broom stick out of his dorm room when he's battling a dragon somewhere else. So he says the spell and the broomstick comes to him, so summoning in that way. Okay, there we </s><s>[INST] go, this is brilliant. So the big thing is that it's something that you've carry with, it's like you're you're safe place, you return to harry potter [/INST] that, you know, I reread them still. Um whatever keeps me reading I think is is the most important thing I got it. So </s><s>[INST] I'm actually the same way in terms of the habit of it. It's important. That's important. Just keep, keep reading. But I have found myself struggling a little bit too because I listened to a lot of audio books now. I've struggled to then switch back to reading seriously. Uh it's just read so many papers, read so many other things. It feels like if I'm going to sit down and have the time to actually focus on the reading, I should be reading like blog posts or papers or more condensed kind of things. But there's a huge value to just reading long form still. [/INST] Yeah. And you know, my husband was never that into fiction, but then someone pulled him or he heard you learn a lot of empathy through reading fiction. So you could think of it that way. </s><s>[INST] Yeah, that's kind of yeah, it's also a fiction is a nice unlike not less so with nonfiction is a chance to travel. I see it as kind of traveling because you go to this other world and it's it's nice because it's like much more efficient. You have to get on the plane, you know, the you get to meet all kinds of new people. It's like people say they love traveling and I said I love traveling to. I just read fiction. [/INST] I told my three year old that, that was why we read so much because we see the places in our mind. And I'm like, it's basically like we're watching a movie, you know, that's how it feels. And she's like, I prefer watching frozen with popcorn response that you're a </s><s>[INST] good point. But yeah, there's some power to the imagination, Right? That's not just like watching a movie because some something about of our, my imagination because it's, it's the words in the world that's painted somehow mixing in with their own understanding, our own hopes and dreams or fears. It like mixes up in there and the way we can build up that world from just the page. [/INST] So yeah, you're, you're really creating the world just with the like prompts from the book, right? Yeah, Yeah. That's different than watching movie, </s><s>[INST] which is why it hurts sometimes to watch the movie version. And then you're like, that's not at all high. Uh, imagine it. Well, we kind of brought this up in terms of, uh, the, depending on what the goals are. Let me ask the big, your, your friends with, you know, is he's obsessed with this question. So let me ask the big ridiculous question about the meaning of life. Uh, do you, have you ever think about this one? Ever ponder the reason we're here is the sense of apes on this spinning ball in the middle of nowhere. [/INST] Yeah, I don't, I don't think one ends up in the field of space propulsion without thinking of these existential questions. Yeah. All the time </s><s>[INST] or builds a business. [/INST] Yeah. Um, yeah, we've touched on a lot of the different pieces of this. I think so. I, I have a bunch of thoughts. Um, I do think that, you know, the goal isn't, the meaning isn't anymore. Just to be like a Petri dish of bacteria that reproduces and um, you know, where survival and reproduction are the main objectives and maybe it's because now we're able to answer these, ask those questions. That's maybe the turning point. Um, and instead, I think it's really the, the pursuit and generation of knowledge and, and so if we're taken out by an asteroid or something, I think that it will have been a, you know, meaningful endeavor if somehow our knowledge about the universe um, is preserved somehow. Um, and the next civilization isn't starting over again. So </s><s>[INST] that, that's, that's always uh, yeah, I resonate with that. That I always loved the mission of google from the early days of making the world sort of information and knowledge searchable. I always loved that idea. I was loved, I was donated as people should to Wikipedia. Uh, I just love Wikipedia. I feel like it's the, it that's one of the greatest accomplishments of just humanity, of us together. Especially Wikipedia and this opens like in this open community way putting together different knowledge is like on everything we've talked about today. I'm sure there's a Wikipedia page about ion engines and I'm sure it's pretty good. Like it's I don't know if that's that's incredible. And obviously that can be preserved pretty efficiently, at least Wikipedia and you'll be like human civilization is all like burning up in flames as there's this one USB drive slowly traveling out Wikipedia on [/INST] it. That's on from the beginning of our chat, that one lonely spacecraft, it just means Wikipedia and then it will have been a civilization well spent </s><s>[INST] pushing that knowledge along. Yeah. Like one little discovery at a time is one of is a core aspect of the meaning of it, of it all. [/INST] Yes. And I also, I haven't yet figured out what the connection, you know, an explanation I'm happy with yet for how it's connected. But um evolving beyond just the survival piece too. I think like we touched on the, the emotional aspect, something in there about cooperation and you know, love. And so I in my day to day that just boils down to, you know, the pursuit of knowledge or improving the human condition and being kind </s>

<s>[INST] Please check out our sponsors in the description and now with your friends, here's Chris Lattner. It's been, I think, two years since we last talked and in that time, you somehow went and co-created a new programming language called Mojo. So it's optimized for AI, it's a super set of Python. Let's look at the big picture. [/INST] What is the vision for Mojo? For Mojo, well, so I mean, I think you have to zoom out. So I've been working on a lot of related technologies for many, many years. So I've worked on LLVM and a lot of things in mobile and servers and things like this, but the world's changing. And what's happened with AI is we have new GPUs and new machine learning accelerators and other ASICs and things like that that make AI go real fast. At Google, I worked on TPUs. That's one of the biggest, larger scale deployed systems that exist for AI. And really what you see is if you look across all of the things that are happening in the industry, there's this new compute platform coming. And it's not just about CPUs or GPUs or TPUs or NPUs or IPUs or whatever, all the PUs, right? It's about how do we program these things, right? And so for software folks like us, right, it doesn't do us any good if there's this amazing hardware that we can't use. And one of the things you find out really quick is that having the theoretical capability of programming something and then having the world's power and the innovation of all the smart people in the world get unleashed on something can be quite different. And so really where Mojo came from was starting from a problem of we need to be able to take machine learning, take the infrastructure underneath it and make it way more accessible, way more usable, way more understandable by normal people and researchers and other folks that are not themselves like experts in GPUs and things like this. And then through that journey, we realized, hey, we need syntax for this. </s><s>[INST] We need to do program language, right? So one of the main features of the language, I say so fully in jest is that it allows you to have the file extension to be an emoji or the fire emoji, which is one of the first emojis used as a file extension I've ever seen in my life. And then you ask yourself the question, why in the 21st century are we not using Unicode for file extensions? This means it's an epic decision. I think clearly the most important decision made in most, but you could also just use Mojo as the file extension. [/INST] Well, so, okay, so take a step back. I mean, come on, Lex. Do you think that the world's ready for this? This is a big moment in the world, right? </s><s>[INST] This is, we're releasing this onto the world. This is innovation. I mean, it really is kind of brilliant. Emojis are such a big part of our daily lives. [/INST] Why is it not in programming? This is innovation. Well, and like you take a step back and look at what file extensions are, right? They're basically metadata, right? And so why are we spending all the screen space on them and all this stuff? Also, you know, you have them stacked up next to text files and PDF files and whatever else. Like if you're gonna do something cool, you want it to stand out, right? And emojis are colorful. </s><s>[INST] They're visual, they're beautiful, right? What's been the response so far from, is there support on like Windows on the operating system in displaying like file explorer? [/INST] Yeah, yeah, yeah, yeah, yeah. The one problem I've seen is that Git doesn't escape it right. And so it thinks that the fire emoji is unprintable and so it like prints out weird hex things if you use the command line Git tool. But everything else, as far as I'm aware, works fine. And I have faith that Git can be improved. So I'm not sure. And so GitHub is fine. GitHub is fine, yeah. GitHub is fine, Visual Studio Code, Windows, like all this stuff, totally ready because people have internationalization in their normal part of their path. So this is just like taking the next step, right? Somewhere between, oh wow, that makes sense. Cool, I like new things too. Oh my God, you're killing my baby. Like what are you talking about? This can never be, like I can never handle this. How am I gonna type this, like all these things. And so this is something where I think that the world will get there. We don't have to bet the whole farm on this. I think we can provide both paths, </s><s>[INST] but I think it'll be great. And so GitHub, when can we have emojis [/INST] as part of the code, I wonder? Yeah, so I mean, lots of languages provide that. So I think that we have partial support for that. It's probably not fully done yet, but yeah, you can do that. For example, in Swift, you can do that for sure. So an example we gave at Apple was the dog cow. So that's a classical Mac heritage thing. And so you use the dog and the cow emoji together, and that could be your variable name. But of course the internet went and made pile of poop for everything. So if you wanna name your function pile of poop, then you can totally go to town and see how that gets through code review. </s><s>[INST] Okay, so let me just ask a bunch of random questions. So is Mojo primarily designed for AIs, or is it a general purpose programming? [/INST] Yeah, good question, yeah, good question. So it's AI first. And so AI is driving a lot of the requirements. And so Modular is building and designing and driving Mojo forward. And it's not because it's an interesting project theoretically to build, it's because we need it. And so at Modular, we're really tackling the AI infrastructure landscape and the big problems in AI. And the reasons that it is so difficult to use and scale and adopt and deploy and all these big problems in AI. And so we're coming at it from that perspective. Now, when you do that, when you start tackling these problems, you realize that the solution to these problems isn't actually an AI specific solution. And so while we're doing this, we're building Mojo to be a fully general programming language. And that means that you can obviously tackle GPUs and CPUs and these AI things, but it's also a really great way to build NumPy and other things like that. Or just if you look at what many Python libraries are today, often they're a layer of Python for the API and they end up being C and C++ code underneath them. That's very true in AI, that's true in lots of other domains as well. And so anytime you see this pattern, that's an opportunity for Mojo to help simplify the world </s>

<s>[INST] Can you speak to that kind of collaborative so that you can have multiple parties in a single transaction kind of thing? Like [/INST] you can do that today. Absolutely. It's called coin join for example but right now it's more expensive to coin joining Bitcoin you have to pay a premium for your privacy. This would flip that on its head and would basically say if you have one transaction hay pile them all in have as many parties as you want, the more parties you get in, the cheaper it's going to be per party okay and that's not possible in Bitcoin today but it might be in the future. But again the beauty, the beauty and Bitcoin are these like these ways that it just aligns human incentives and aligns are like most base desires and needs and realities with like freedom and privacy and that I've never seen before and that's why I think it's so interesting </s><s>[INST] so something that like somebody like eric weiss that actually spoke to this The you know the idea of Blockchain in general from like a 10,000 ft view, the Blockchain is a centralized place to keep the record of everything that ever happened and does that concern you from a privacy perspective from a control perspective, even though it's managed especially you know, given the low frequency of transactions for Bitcoin, you can like you can have a lot of, you know, small computers across the globe contain the entirety set of transactions, you know, all of those kinds of features. Does that concern you that there is one place where everything is made public in terms of everything that ever happened? [/INST] No, and I'll give you two reasons number one, the Bitcoin Blockchain is ultimately a settlement layer, it's kind of like something like fed wire in the United States, it's a way for like Institutions to settle with each other. That's what I think it's going to be like in 2030 years from now the average person is never going to touch the Bitcoin Blockchain, probably they're going to use things like lightning or unfortunately they may use Bitcoin banks but they'll either use custodians or they'll use second layer noncustodial solutions to interact. The main chain is going to get very expensive, it's gonna be hundreds and hundreds and hundreds of dollars or even more if the dollar starts to weaken uh to make a transaction in the main chain and that will be reserved for like very large transactions or transactions that need final final settlement etcetera etcetera. Um and I think that that's that's fine and and that's okay and it's very important that that ledger, that settlement layer be kept by thousands of people around the world, the Bitcoin Blockchain is not centralized, it is, it is decentralized is run by people like me who run a note at home, I run a personal server, I run the Bitcoin Blockchain, no one else you run it, that person runs it. There's no there's no one in. Yeah, I run a full note. It's great. I mean it's pretty easy, man, you run it and that way you can the sovereign over all of your usage, right? And you can run it on a raspberry pi with less than 100 50 bucks of equipment. And that's so important because again, there's no amazon web service vulnerability here, That is a problem. And I agree with you, we're trending in a bad direction where like the government could just turn off a big important website or a news source. They can't turn off Bitcoin because it doesn't live on aws, it lives with us. We are Bitcoin and I think that that's that's very, very powerful. Um and </s><s>[INST] then you can have the something like a lightning network where you can escape some of the constraints of the Blockchain depending on your needs of the privacy and all those kinds of things. [/INST] Everything is an engineering trade off. But yeah, you can trade off some of the assurances of the base layer to go into lightning, for example, and and there you can get more speed and more privacy and the things that Bitcoin lacks speed and privacy for example, um you can get on the second layers so there's all kinds of cool engineering things that people are coming up with. But I also want to say anyone who says the Blockchain like that's a red flag for that person doesn't really know what they're talking about like so she didn't use the Blockchain in the white paper. Blockchain was a marketing term come that people came up with later to try and do this thing That was kind of like it peaked in 2015 and and it continues to be an issue today of its Blockchain and Bitcoin and that was like a very corporate kind of social attack on Bitcoin to say we could take this like ledger part of this radical thing that's for criminals and all these bad people but we could take one part of it out and we can bring it over here and we can make it safe for everybody. The real McCoys. Bitcoin Satoshi referred to it as a time change. I mean really what they're talking about is just these like blocks that are connected chronologically of transactions. It's really not that exciting. The exciting part of Bitcoin is the proof of work where the transaction processing is done by mining and by energy and by real world expenditures instead of like you know some central ledger and you know when you remove the Blockchain from Bitcoin. That's not very to me it's just not, it's just not that interesting. </s>

<s>[INST] But unnecessary. I think the criticism that people would say about your talking about COVID, maybe you can correct me, but you were skeptic or you were against skepticism of the safety and efficacy of the vaccine. So people who get nervous about the vaccine but don't fall into the usual anti-vax camp, which I think there was a significant enough number. They're asking, they're getting nervous. I mean, especially after the war in Afghanistan and Iraq, I too was nervous about anything where a lot of money could be made. And you just see how the people who are greedy, they come to the surface all of a sudden. And a lot of them that run institutions actually really good human beings. I know a lot of them, but it's hard to know how those two combined together when there's hundreds of billions, trillions of dollars to be made. And so that skepticism, I guess the sense was [/INST] that you weren't open enough to the skepticism. I understand that people have that sense. I'll tell you how I thought about it and think about it. One, again, it was a moving target. So there was a point in the timeline where it was totally rational to expect that the vaccines were both working, both they were reasonably safe and that COVID was reasonably dangerous and that the trade-off for basically everyone was it was rational to get vaccinated. Given the level of testing and how many people had been vaccinated before you, given what we were seeing with COVID, that that was a forced choice. You're eventually gonna get COVID and the question is, do you wanna be vaccinated when you do? There was a period where that forced choice, where it was just obviously reasonable to get vaccinated, especially because there was every reason to expect that while it wasn't a perfectly sterilizing vaccine, it was going to knock down transmission a lot and that matters. And so it wasn't just a personal choice. You were actually being a good citizen when you decided to run whatever risk you were gonna run to get vaccinated because there are people in our society who actually can't get vaccinated. I mean, I know people who can't take any vaccines. They're so allergic to, I mean, they in their own person seem to justify all of the fears of the anti-vax cult. I mean, it's like they're the kind of person who Robert Kennedy Jr. can point to and say, see, vaccines will fucking kill you, right? Because of the experience and we're still, I know people who have kids who fit that description, right? So we should all feel a civic responsibility to be vaccinated against egregiously awful and transmissible diseases for which we have relatively safe vaccines </s><s>[INST] to keep those sorts of people safe. And there was a period of time when it was thought that the vaccine could stop transmission. [/INST] Yes, yes. And so again, all of this has begun to shift. I don't think it has shifted as much as Brett Weinstein thinks it's shifted, but yes, there are safety concerns around the mRNA vaccines, especially for young men, right? As far as I know, that's the purview of actual heightened concern. But also there's now a lot of natural immunity out there. Basically everyone who was gonna get vaccinated has gotten vaccinated. The virus has evolved to the point in this context where it seems less dangerous. Again, I'm going more on the seemings than on research that I've done at this point, but I'm certainly less worried about getting COVID. I've had it once, I've been vaccinated. I've like, it's like, so you ask me now, how do I feel about getting the next booster? I don't know that I'm going to get the next booster, right? So I was somebody who was waiting in line at four in the morning, hoping to get some overflow vaccine when it was first available. And that was at that point, given what we knew, given what I thought I knew based on the best sources I could consult and based on anecdotes that were too vivid to ignore, both data and personal experience, it was totally rational for me to wanna get that vaccine as soon as I could. And now I think it's totally rational for me to do a different kind of cost benefit analysis and wonder, listen, do I really need to get a booster? Right, you know, like how many of these boosters am I gonna get for the rest of my life? Really, and how safe is the mRNA vaccine for a man of my age, right? And do I need to be worried about myocarditis? All of that is completely rational to talk about now. My concern is that at every point along the way, I was the wrong person and Brett Weinstein was the wrong person and there's many other people I could add to this list to have strong opinions about any of this stuff. </s><s>[INST] I just disagree with that, I think, yes, in theory, I agree 100%, but I feel like experts failed at communicating, not at doing- They did. And I just feel like you and Brett Weinstein actually have the tools with the internet, given the engine you have in your brain of thinking for months at a time deeply about the problems that face our world, that you actually have the tools to do pretty good thinking here. [/INST] The problem I have with experts- But there would be deference to experts </s><s>[INST] and pseudo experts behind all of that. Well, the papers, you would stand on the shoulders of giants, but you can surf those shoulders better than the giants themselves. [/INST] Yeah, but I knew we were gonna disagree about that. Like I saw his podcast where he brought on these experts who had, many of them had the right credentials, but for a variety of reasons, they didn't pass the smell test for me. I mean, one larger problem, and this goes back to the problem of how we rely on authority in science, is that you can always find a PhD or an MD to champion any crackpot idea, right? I mean, it is amazing, but you could find PhDs and MDs who would sit up there in front of Congress and say that they thought smoking was not addictive, or that it was not harmful to, there was no direct link between smoking and lung cancer. You can always find those people, and you can end, but some of the people Brett found were people who had obvious tells, to my point of view, to my eye, and I saw them on, some of the same people were on Rogan's podcast, right? And it's hard, because if a person does have the right credentials, and they're not saying something floridly mistaken, and we're talking about something where it's their genuine unknowns, right? Like, how much do we know about the safety of these vaccines, right? It's, at that point, not a whole hell of a lot. I mean, we have no long-term data on mRNA vaccines, but to confidently say that millions of people are gonna die because of these vaccines, and to confidently say that ivermectin is a panacea, right? ivermectin is the thing that prevents COVID, right? There was no good reason to say either of those things at that moment, and that's, and so given that that's where Brett was, I felt like there was just no, there was nothing to debate. We're both the wrong people that would be getting into the weeds on this. We're both gonna defer to our chosen experts. His experts look like crackpots to me, and, or at least the ones who are most vociferous </s>

<s>[INST] Do a high amount of damage with precision. [/INST] Yes. So this is one of the great combat strategies across the animal kingdom, across human history, et cetera. The second would be ambush tactics. If you can ambush an opponent with the element of surprise, this is huge for success in combat. Almost all of the truly successful predators on this planet are ambush predators. The ability to get off to a good start in a way where opponents simply can't recover is huge for combat. </s><s>[INST] Are we allowing ambush in our discussion? [/INST] Because humans would call this cheating, perhaps. We'll talk about this. Yes, we would. And humans are pretty damn good at it, too. And then the third is endurance. Some species, some people, humans actually are pretty good at this, use endurance as a weapon and they simply wear an opponent down over time and break them internationally. This can be done economically through numbers, et cetera, et cetera, and you can destroy someone with sheer endurance. Yeah, a lot of wars throughout human history has been siege warfare. Yeah. So when you ask yourself, okay, which one of these animals are going to be the most successful in combat, ask yourself, well, there's these three elements which tend to determine success or failure in warfare, which animals exhibit these three principles the best? And we'll discuss this. But as far as generalities go, whenever you ask a question, who will win between A and B, ask yourself in terms of the light of what we've just discussed. What is their skill set? What are their attributes, both mental and physical? What is their experience in utilizing these in real world situations? And then the four more tactical elements, who gets to initiate contact? Can you break off contact at any given time? What is your endurance? </s><s>[INST] Can you keep going longer than your opponent does? So with skill set, I wonder if a big component of that of how much practice there is off the battlefield. Exactly. [/INST] So how much quote unquote, you would probably call it play, like play fighting. Play fighting. Let's start going through our animals, okay? When you look at the gorilla, you will see immediately that almost every experience a gorilla has of combat is theatrical. They don't engage in killing things. They scare rival males away in order to gain ownership of females. But there is almost no intra-species death in those conflicts. They're almost entirely theatrical. They have, for example, enormous canine teeth, but there is no record of them ever being used in combat. They appear to be used purely for intimidation purposes. There's a sense in which they have this tremendous appearance and they have tremendous potential. They really do have freakish levels of strength in many different ways. </s><s>[INST] And yet, the actual track record of using it is negligible. [/INST] So strange that evolution would develop such a powerful, a killing machine. Their bite force just makes no sense with regard to what they actually eat. I think, well, no, I think they have a- Even the presence of canines doesn't make a lot of sense. They're not going to use them. What are they? It comes down to this idea, their big thing is intimidation. </s><s>[INST] I think they have like- So there's a show, you want to fake it and [/INST] don't care if you ever make it because fake is good enough given that particular dynamic. Now let's contrast that with a male lion. Lions take on the biggest, meanest, toughest animals in the most competitive killing war on planet Earth, which is continental Africa. And they literally just take- I mean, occasionally they lose, but it's rare and they take out everything. Just in order to eat, they have to take down wildebeest, cape buffalo, cape buffalo are incredibly dangerous beasts just by themselves and yet lions regularly take them down. Occasionally, large numbers of lions will even swarm elephant and over 12 hour periods take down elephant on some occasions. This is all on video, this is not just speculation. </s><s>[INST] So they just have a level of combat experience, which no other animal can do, elephant can do. If I were to also project the Eastern European style of wrestling where they spend so many hours on the mat, they really value the number of hours on the mat at play from childhood. The lions probably, from my extensive watching videos on YouTube, they seem to play with each other for fun a lot and I guess with the gorilla- It helps, you see it. You don't interact, you don't play with other gorillas, you're more spending a lot more time around the opposite sex. Yeah. So yeah. [/INST] I mean, even lions, when they fight each other, the mortality rate when lions fight each other, male lions, for ownership of a pride is very, very high, much, much higher than I believe any other species on earth. They almost always fights to the death for the simple reason that when a male lion loses control over pride, the first act the new lion does is to kill the genetic offspring of the previous male lion. So when a lion fights another male lion, when one male lion fights another, it's not just to fight for his own life, it's a fight for his genetic offspring. failure means not only does he die, all his offspring dies. And so when they fight, the implications are so deep. It's like a fight for not just you, but your DNA. Most male lions have very short runs at the top. They get killed or run off by other lions. Now, this kind of harsh combat experience, no other animal can claim to have this. Between what they kill to eat and what they have to do to defend their stake and a pride, no other animal fights like that. They just bring a level of depth to combat which is unmatched in the animal kingdom. They also have some other elements too. They get the luxury because of their social nature of taking more risks than other animals. Like a tiger hunts alone. So if it gets injured, it's a big problem. It can die if it's injured. A lion can fight. Cape buffalo get injured and be covered by the other lions for food until it recovers. So it learns to take risks and it's not afraid to go out and fight very, very hard. Whereas other animals tend to shy away from risk because they're solitary, bears are solitary, tigers are solitary. So they learn from an early age not to take the big risk, </s>

<s>[INST] It does piss people off though, I wonder, but who cares in long arc of history, the people, everybody gets piste off at the people who succeed, which is one of the things that frustrates me about this world is uh, they don't celebrate the success of others. Like there's so many people that want Ellen to fail. It's so fascinating to me like what is wrong with you? Like So Elon musk talks about like people short, like they talk about financial, but I think it's much bigger than the financials I've seen like the human factors community, they want, they want other people to fail. What what, what like even people, the harshest thing is like, you know, even people that like seem to really hate, donald trump, they want him to fail or like the other president or they want Barack Obama to fail. See [/INST] we're almost at Bowman, it's </s><s>[INST] weird, but I want that I would love to inspire that part of the world to change because well damn it. If the human species is going to survive, we celebrate success, like it seems like the efficient thing to do in this objective function that like we're all striving for is to celebrate the ones that like figure out how to do better at that objective function as opposed to dragging them down back into the, into the mud. [/INST] I think there is this is this speech I always give about the commenters on hacker news. So first off, something to remember about the internet in general is commenters are not representative of the population. I don't comment on anything, you know, commenters are are representative of a certain sliver of the population and on hacker news, a common thing I'll see is when you'll see something that's like, you know, promises to be wild out there and innovative, there is some amount of, you know, checking them back to earth, but there's also some amount of if this thing succeeds. Well I'm 36 and I've worked at large tech companies my whole life, they can't succeed because if they succeed, that would mean that I could have done something different with my life, but we know that I couldn't have, we know that I couldn't have and and that's why they're going to fail and they have to root for them to fail to kind of maintain their world image, </s><s>[INST] So tune it out and they comment, well it's hard. I so one of the things, one of the things I'm considering startup wise is to change that because I think the I think it's also a technology problem. It's a platform problem. It's like because the thing he said, most people don't comment, I think most people want to comment, they just don't because it's all the assholes for commenting. Exactly. [/INST] I don't want to be grouped in with that on </s><s>[INST] that. You don't want to be in a party where everyone is an asshole. And so they but that's a platform problem that [/INST] I can't believe what red it's become, I can't believe the groupthink in reddit comments. </s><s>[INST] There's a red is interesting one because their subreddit and so you can still see especially small subreddit that like that are a little like havens of like joy and positivity and like deep even disagreement, but like nuanced discussion, but it's only like small little pockets, but that's uh that's emergent, the platform is not helping that or hurting that. So I guess naturally something about the internet, if you don't put in a lot of effort to encourage nuance and positive good vibes, it's naturally going to decline into chaos. [/INST] I would love to see someone do this. Well, yeah, um I think it's very doable. </s><s>[INST] This is I think actually so I feel like twitter could be overthrown. [/INST] Yeah, Schlabach talked about how like uh if you have like and retweet, like that's only positive wiring, right? The only way to do anything like negative there is um with a comment and that's like that. Asymmetry is what gives twitter its particular toxic nous. Whereas I find Youtube comments to be much better because you do comments have a have a have an up and down and they don't show the down votes </s><s>[INST] without getting into depth of this particular discussion. The point is to explore possibilities and get a lot of data on it. Because I mean I could disagree with that. You just said it's on the point is it's unclear. It's a hasn't been explored in a really rich way. Uh like these questions of how to create platforms that encourage positivity. Yeah, I think it's a it's a technology problem and I think we'll look back at twitter as it is now. Maybe it'll happen within twitter, but most likely somebody overthrows them is we'll look back at twitter and say, I can't believe we put up with this level of toxicity. You [/INST] need a different business model toe any any social network that fundamentally has advertising this business model. This was in the social dilemma which I didn't watch but I liked it. It's like, you know, there's always the you know, you're the product, you're not the but they had a nuanced take on it that I really liked and it said the product being sold is influence over you mm the product being sold is literally your you know influence on you. Like that can't be if if that's your idea. Okay, well, you know, guess what? It cannot be toxic. </s><s>[INST] Yeah. Maybe there's ways to spin it. Like with with giving a lot more control to the user and transparency to see what is happening to them. As opposed to in the shadows. It's possible. But that can't be the primary sources. But the [/INST] users are no one's going to use that. </s><s>[INST] It depends, It depends. It depends. I think I [/INST] think that the you're you're not going to you can't depend on self awareness of the users. </s>

<s>[INST] But, well no matter what I hope despite chess or not that he's mentally strong enough for whatever is to come. That's [/INST] what I keep saying because I've </s><s>[INST] been under fire. Right? I [/INST] can't, I can't imagine. Right? Like I just, I really can't imagine. And maybe, well we just have too much compassion, but I don't think so. I really just feel like </s><s>[INST] at the end of the day, chess is just a game, but it is a game played by millions of people throughout history and nations have basically fought wars over the chessboard. So like there's, there's a lot, it's like olympics. Olympics is just a little just a dude running and so on. The hockey is just the thing with the puck and, but you know, um, it's, it's also much more than that. It's also, it's also nations sort of figuring out their conflict in a way that doesn't involve violence. [/INST] Yeah. </s><s>[INST] It's a serious thing. And it's a thing that inspires millions of people and it's a testing ground for intelligence systems that eventually, uh, take over human [/INST] civilization. </s><s>[INST] Yeah, I mean the bots bots are really interesting. I don't know if there's other lessons like you, you played a clone of yourself. [/INST] You </s><s>[INST] watched stock fish versus stock fish, your video people should check out each other. You have a lot of awesome videos, your video title, stock fish, stock, [/INST] that was the experiment I made them play each other. </s><s>[INST] What did you learn from that experiment [/INST] I enjoyed. First of all they will always make a draw. So engines don't get to play each other from a beginning position because they will always draw, especially if they're the same engine. So stock fish 1515, I don't think one side will ever beat the other basically. But if you program them to play a certain opening position according to chess theory, you get to see in interesting ways into how they evaluate one of the things, one of the ways that it played against the London opening was absurd like it just, it was completely ridiculous. Black sacrificed two pawns as early as moved six which is a borderline completely lost position. And then both sides foresaw that the only way white was going to be able to use those that material advantage was to give it back and stabilize their own position. Like black just got a crazy attack, </s><s>[INST] jesus christ [/INST] This is crazy but they drew, I mean they ended up drawing so I'm also gonna make them play against each other in either bad openings or like some of the most popular gambits </s><s>[INST] looking [/INST] looking at something like that. Um and the way I'm gonna do this is basically say which chest gambits are the best and the way I'm gonna do that is theoretically the engine should be able to beat the gambit because the gambit is very rarely blessed by the computer. So if the computer cannot beat that gambit that means it's good, that means it's not losing. If it's a completely lost gambit it will beat it. But if it draws despite getting that early disadvantage then that means the gambit is very reliable and you can play it. So </s><s>[INST] that's a good way to evaluate opening [/INST] games. Yeah. </s><s>[INST] What's what's the best, what's your favorite opening [/INST] or what what what </s><s>[INST] openings do you like? [/INST] There was an opening that got me back into chess when I was 15, I quit for like three years and I went to my friend's house and he had a book by large scandal. A danish grandmaster called the Caro kann defense </s><s>[INST] which is [/INST] C. Six. </s><s>[INST] You want white? Do you want black? Do you want to show them the opening? [/INST] This is the opening the Caro kann defense. So you play before I place the six. I have I have to play </s><s>[INST] black. That's it. [/INST] Yeah, we developed from here. I put my </s><s>[INST] what what counts is the opening? Okay but the development does the development matter? Yeah. [/INST] So from here the development goes into the variations of </s><s>[INST] the car broken. So [/INST] this is the car broken like you can be in the city but then you can be in neighborhoods that that's </s><s>[INST] a very non dramatic. Okay. [/INST] Yeah two pawns in the center. So that's called the briar variation, </s><s>[INST] so which what's a good thing for me [/INST] to see if you can put two pawns in the center. Yeah, you should. And then um </s><s>[INST] that's a good thing. [/INST] Yes. And then I will go here and now you have to decide what you're gonna do with your center pawn. You can push, take or defend it </s><s>[INST] and uh push, take or defend. Right? What would you suggest taking? The the worst [/INST] take is just stable. So we just trade but pushing is considered the best advancing and taking my space away from me. So I think alpha zero or stock fish would probably always push push. And now there's something called like the main line or the sideline mainline is what's the most popular played at all levels, which is moving the bishop here, I've played this a lot, but for beginners, this is an intermediate players. Uh this is why I love this opening so much on move three black already has a plus score, </s><s>[INST] which [/INST] is crazy. It's not supposed to happen. And there's this very tricky second most popular move which is undermining your center trying to get you to take my free pond but destabilize and leave both of them kind of hanging. And </s><s>[INST] is that why the plus core is because you're susceptible to the destabilize destabilization? [/INST] Yes, because people at 99% of the rating ladder do not understand how to deal with what's coming basically they don't know how to deal with a structural attack. </s><s>[INST] So would uh would stock fish try to defend upon here and [/INST] you know it would take the pawn and tell you to go fund </s>

<s>[INST] This is the... So how do banks compare to gold? So you're saying it'll surpass gold with the 10 trillion? Yeah. What's bonds? [/INST] Where's bonds stand? So then there's also national currencies, which are about a hundred trillion and then there's government bonds, which are around $120 billion. And sorry, trillion dollars, trillion. Trillion, sorry. </s><s>[INST] If we're saying billion, we meant trillion. Yeah. So you think bonds can move to Bitcoin? [/INST] I've always held, this is the prize. This is the main dish. Gold is the appetizer. Bonds are the main dish because bonds have replaced gold. The hell is an appetizer? Yeah. I mean, bonds have replaced gold in people's portfolio. People, you remember when we were saying gold was, you'd hold it as a saving, as the secure part of your portfolio, and then you'd take risk with the equity. Currently, people do that by holding a part of their portfolio in bonds. That's the part that they treat as their saving account. And then the rest they use for, not speculation, but investment in which they take risk. Yeah, speculation. And that's stocks and equity and other high-risk assets. I think Bitcoin is not going to replace equity. There will always be equity. There will always be companies and people will want to have equity. But it'll probably replace a big chunk of current equity markets, because right now, if you want to save, it used to be that you hold bonds. Now, if you want to save, you go into stock indexes. So I think Bitcoin likely eats a big chunk of equity markets, because currently, it's, people are using it as saving, and I think it eats all the bonds. That's my most ambitious </s><s>[INST] profile of an appetizer. The question is the scale of time that happens across, [/INST] but the most important statement you make is about trend. Yeah, and also, I mean, let's also remember, currently bonds, nominally, don't beat inflation, and in real terms, they don't come close to beating inflation. So currently, you know, with bonds, you're taking on credit default risk to buy a bond, and also getting less money back in real terms. Well, Bitcoin doesn't offer you returns, but in real terms, it appreciates much more, and it has, I believe, a lot less risk associated with it than any company or government. </s><s>[INST] So let's make things spicy and ask if Bitcoin fails in the long-term future. As you just said, economics, volatility, things happen in this world. The human civilization might end in this century. I hope it doesn't, but it might. There could be catastrophic events. If Bitcoin fails, it goes to zero, loses its number one spot, what would be the reason? If you're an alien visiting Earth 100 years from now and just were to analyze the situation, Bitcoin is a pretty new thing, so the possible trajectories of how the world evolves together with this new monetary technology is nearly infinite. So if it fails, one of those trajectories surely involves Bitcoin failing. [/INST] What would be the reason? I think the most likely reason that it could fail, I don't think this is likely in general, but I think it is the most likely of all the unlikely things that could destroy Bitcoin, is governments go back on a gold standard. </s><s>[INST] So they make, in your view, a better decision than the current system, just not the best decision. Yeah. I thought you would go much darker, but so that's okay. Interesting. So maybe because of Russia, because of China and so on, because the current war, they might reconsider the power that America holds because of the monetary, because of being the primary currency, [/INST] and they'll start thinking about going on a gold standard. Yeah, but it would also require the US and the Europeans and everybody to want to join in this system and sing kumbaya and play nice with each other around the gold standard. I think, given that gold already is about 10 times larger than Bitcoin, so it has a first mover advantage. Yes. If governments were to go and peg their currencies to gold, again, the price of gold would shoot up five, 10X, and it would rise in value a lot more. Of course, that doesn't necessarily kill Bitcoin. No, again, I'm not saying it's likely to happen. I'm saying it's, I imagine, less unlikely than all the other unlikely scenarios, because even with a nuclear war, like 90% of the planet is destroyed, </s><s>[INST] the 10% continue to run Bitcoin. That's a quote. Okay, there's a movement, a community of people referred to as Bitcoin maximalists. I've seen you referred, at least in the past, as the leader of the Bitcoin maximalists, probably because of your book, Bitcoin Standard, consider the Bible in general. You're one of the leaders in this space. Do you regret any of the toxicity and derision that often, or perhaps sometimes, [/INST] originates from this community? Definitely not. I'm not in the position to regret other people's actions, so let's just be clear. I think the rhetoric of community is, I reject this rhetoric because I think it's a way for kind of political manipulation and subversion to try and portray people as part of a community and hold people responsible for other people's actions, which I think is ridiculous. So if some guy on the internet said something mean to somebody, and then this is very common, and I always try and not get involved in these things. So some guy who identifies as a Bitcoiner says something to somebody that's very wrong. Of course, it happens. Tens of millions of people use Bitcoin around the world, and a lot of these, I'd say, parasites, people who don't have anything productive to do with their life, outrage merchants, they'll come out and say something along the lines of, the Bitcoin maximalists are toxic, they're holding Bitcoin back, and they need, and of course, it's manipulative. The point behind it is they wanna get to you, they wanna get people who are not that nobody with 300 followers who said something silly, they wanna get the notable people to basically change their message. So the idea is I'm supposed to apologize because somebody with 300 followers I've never met in my life who calls themselves a Bitcoiner said a mean word, and then I need to apologize, and I also need to cut down on my rhetoric about other digital currencies, and I need to do that. So I'm only responsible for my own actions, and I don't recall regretting anything. </s>

<s>[INST] creative, They [/INST] were like prime to remember Finality. You know, like love and finality basically love and impermanence. There's something about that that's that gets us to our most beautiful state. </s><s>[INST] I wonder if it is. I mean there's studies like that there's a, I don't know if you looked into terror management theory. [/INST] Yeah, that's really interesting stuff. </s><s>[INST] So they especially intensely have you focused on not just sad but traumatic like death primary with death and see how that changes your mind. Like both. Like I don't, I don't know if there's creativity studies but they have um interesting I think a little bit tainted by political bias but maybe not. I mean psychology is a complicated field but they study like who are you likely to vote [/INST] for if </s><s>[INST] you're primed by existential like by thinking about the [/INST] fear of mortality, </s><s>[INST] mortality. I forget what the conclusions are, but [/INST] I I think they find that people become more try ballistic, you know like there's one study where they found that after they primed people that way that um, that they would then give them the chance to put hot sauce on a meal that their political opponents were going to be eating and they put way too much hot sauce on after they've been primed to worry about death. </s><s>[INST] I think at the core we're simple creatures. [/INST] So I actually, like in the book, I I spent a bunch of time with people who are working on radical life extension, you know, or the quest to live forever. And people ask them a lot questions like, you know, the kinds of questions you were talking about earlier. Well like how are you gonna feed everybody and how is there gonna be space for everybody? Um if everyone really could live forever? And what about conflict when we have an intensified conflict? And their answer to that is they point to terror management theory. And they say because it's the fear of death, they're basically saying it's the fear of death that are causing our conflicts in the first place. And that if we remove the fear of death, we'd have less conflict to contend with and that I don't really buy that </s><s>[INST] it's possible that that's true. But are you also, how does the expression go throwing out the baby with the bathwater? Are you also going to remove basically any source of meaning and um happiness in the human condition? Like it's very possible that death is fundamental to the human condition? The finality. Yeah. [/INST] And that's the great philosophical question and I went to a conference of of people who are working on this, and I thought that they were going to be talking about those questions all through the conference, but the M. O. Is much more like we're so happy that we're here with people who have gotten past all those quibbles. Um, you know, we just know there's going to be meaning no matter what </s><s>[INST] the basic assumption is, let's try to extend life indefinitely. And then we'll figure out if that's a good decision, [/INST] or more like, we're sure it's a good decision. That was what I felt. </s><s>[INST] It's sure it's either we're sure it's a good decision or we're sure that is good to believe that it's a good decision, meaning, like there's no downside to to that, even if we find out it's wrong. But yes, there's a kind of certainty, obviously you want to extend human life. That's the kind of assumption that always seemed. Um now it could be true, but just like the people who over focus on colonizing other planets, it feels like you neglect the beauty and the struggle of our life here on earth. I have sort of the same kind of criticism whether it's thinking about valhalla or any other afterlife, as you can have if you're not careful Forget to to make this life A Great one whatever happens afterwards. So, yeah, definitely. But from an engineering, from a biology, from a chemistry perspective, it's very interesting to think how do we extend this thing because it does seem that nature the way it designed living organisms, it really wants us to die because that's part of the selection mechanism. This part this seems to be fundamental to evolution. It uh, gets because people are young, they need protection once they, once they're young brain, they get to explore a lot. Get to figure out the world to come up with their own novel ideas how to adapt, how to respond to that world. And then you get older and older, they get like stubborn and stuck in their ways. And so we need them to die. So we make room for new life that's able to adapt to the changing environment. If the old doesn't die, then you're not, you're going to get stale and not be adaptable to the changing environment, [/INST] but maybe it doesn't have to happen so soon. </s><s>[INST] Yeah, maybe it doesn't like pressing listen, I'm a big fan of pressing snooze on the alarm clock. I'm in the same way. Um, I do. I'm one of the people that believe it's or I don't definitely believe. Of course, I don't know. But I think death is a is a fundamental part of life. But yeah, I found on my deathbed, I would sure as hell press news as many times as possible. [/INST] Yeah, it's interesting because in some ways I really I share your instinct. Um, there was one scientist who I spoke to at that conference, He's one of the leading advocates and he said, you know, that's a story that we've invented for ourselves because we have no choice. And if you really believe that you have no choice, then you're then it's it's adaptive to tell that story that death gives meaning to life. But if you really think you don't, if you really think you could triumph over it, would you still be telling that same story? </s>

<s>[INST] So there's something about so there's some line that has to do with the complexity of planning that may contain an answer. I mean it would be beautiful if if we can find a line beyond which you can see a being is conscious. Yes, it will be. These are wonderful lines that we've drawn with existence, life and consciousness. Yes. [/INST] Um It will be very nice one little wrinkle there and this is something I've only learned in the past few months is the notion the philosophical notion of vagueness. So you're saying it would be wonderful to draw a line. And I had always assumed that that line at some point would be drawn um until about four months ago. And the philosopher taught me about vagueness. So I don't if you come across this, but it's a technical concept and I think most revealingly illustrated with at what point does a pile of sand become a pile? Is it one grain, two grains, three grains or four grains. So at what point would you draw the line between being a pile of sand and a collection of uh sand grains of sand in the same way? Is it right to ask, where would I draw the line between conscious and unconscious? And it might be a vague concept. Having said that, I agree with you entirely. Systems that have the ability to plan. So, just technically what that means is um your um your inferential self Evidencing, by which I simply mean the dynamics, literally the thermodynamics and gradient flows that underwrite the preservation of your oil droplet like form are described as a can you describe an optimization of log Beijing model, evidence, your elbow. Um That self evidencing must be evidence for a model of what's causing the sensory impressions on the sensory part of your surface, or your Markov blanket? If that model is capable of planning, it must include a model of the future consequences of your active states or your action. Just planning. So, we're now in the game of planning, is inference. Now notice what we've made that we've made quite a big move away from big data and machine learning because again, it's the consequences of moving, it's a consequence of selecting those data or those data or looking over there and the that tells you immediately that even to be a contender for a conscious artifact or a as its strong ai or general um then you've got to have movement in the game and furthermore you've got to have a generative model of the sort you might find in say a variation autoencoder that is thinking about the future conditioned upon different courses of action. That brings a number of things to the table which which now you start thinking about those who got all the right ingredients. Talk about consciousness, I've now got to select among a number of different courses of action into the future as part of planning. I've got free will the act of selecting this course of action on that policy or that policy or that action suddenly makes me into an inference machine, a self evidencing artifact that now looks as if it's selecting amongst different alternative ways forward as I actively swim here or swim there or look over here, look over there. So I think you've now got to a situation if there is planning in the mix, you're now getting much closer to that line. If that line were ever to exist. I don't think it gets you quite as far as self aware though. Um I think you and then you're you you have to, I think grapple with the question, how would formally write down a countless or maths of self awareness. I don't think it's impossible to do. Um um But I think you, would there be pressure on you to actually commit to a formal definition, what you mean by self awareness. I think most people that I know would probably said that a goldfish, a pet fish was not self aware. They would probably argue about their favorite cat uh but would be quite happy to say that their mom was self aware, so </s><s>[INST] right, But that might very well connected to some level of complexity with planning. It seems like self awareness is essential for complex planning. [/INST] Yeah. You want to take that further, but I think you're absolutely right. </s><s>[INST] Again, the line is unclear, but it seems like integrating yourself into the world into your into your planning is essential for constructing complex plans. Yes, [/INST] so I'm </s><s>[INST] mathematically describing that in the same elegant way as you have with the free energy principle might be difficult. [/INST] Well, yes and no, I don't think that. Well, perhaps we should just can we just go back? But you know, that's a very important answer you gave. And I think if I just unpacked it, your you'd see the truisms that you've just you've just exposed for. Uh But let me sorry, I'm mindful that I didn't answer your question before. Well, you know, what's the free energy principle? Good for? Is it just a pretty theoretical exercise to explain non equilibrium steady state? Yes, it is. Um It does nothing more for you than that. It can be regarded. Its very arrogant, but you know, it is of the sort of theory of natural selection or a hypothesis of natural selection. Beautiful, undeniably true. But tells you absolutely nothing about why you have legs and eyes and you know it tells you nothing about the actual phenotype and it wouldn't allow you to build something. So the free energy principle by itself is as vacuous as most tautological theories. And by tautological of course I'm talking to the you know the theory of natural the survival of the fittest. What's the fittest survive while the cycles the fitter it disco rounded circles. A sense of free energy principle has that same Yeah deflationary tautology under you know under the hood it's you know it's you know it's a characteristic of things that exist why they exist because they minimize their for energy while I mean if I minimize their for energy because they exist and just keep on going around around around. Yeah. The what the practical thing which you don't get from natural selection but you could say has now manifesting things like differential evolution or genetic algorithms and M. C. M. C. For example in machine learning, the practical thing you can get is if it looks as if things that exist are trying to have density dynamics that look as though they're optimizing a variation of free energy and the variation of free energy has to be a functional of a generative model probabilistic description of causes and consequences causes out there consequences in the sensory um on the sensory parts of the Markov blanket. Then it should in theory impossible to write down the general model workout the gradients and then cause it to autonomously self evidence. So you should be able to write down oil droplets, you should have to create artifacts where you have supplied the objective function that supplies the gradients that supplies the self organizing dynamics to non equilibrium steady state. So there is actually a practical application the free energy principle, when you can write down your required evidence in terms of well, when you can write down the charity model, that is the thing that has the evidence, the probability of these sensory data or this data, given that given that model is effectively the thing that the elbow of the variation for energy bounds or approximates. That means that you can actually write down the model and the kind of thing that you want to engineer. The kind of AGI artificial general intelligence um that you want to manifest. Probabilistic lee and then you engineer a lot of hard work but you would engineer a robot and a computer to perform a great in dissent on that objective function. So it does have a practical implication now, why am I wittering on about that? It did seem relevant to. Yes. So um what kinds of. So the answer to that? Would it be easier to be hard? Well, mathematically, it's easy, I've just told you, all you need to do is write down your perfect um artifact, probabilistic lee in the form of probabilistic, jointly model probability distribution over the causes and consequences of the world in which this thing is immersed. And then you just engineer a computer and a robot to perform a great inter sent on that objective function. No problem. But of course the big problem is writing down the charity model. So that's where the heavy lifting comes in. So it's it's the form and the structure of that guarantee model which basically defines the artifact that you will create or indeed the kind of artifact that has self awareness. So that's where all the hard work comes very much like natural selection doesn't tell you in the slightest why you have eyes. So you have to drill down on the actual feelings about the actual generative model. So with that in mind, what did you tell me that tells me immediately the kinds of generative models I would have to write down in order to have self awareness. What you said to me was I have to have a model that is effectively fit for purpose for this kind of world in which I operate. And if I now make the observation that this kind of world is effectively largely populated by other things like me. Are you then it makes enormous sense that if I can develop a hypothesis that we are similar kinds of creatures. In fact the same kind of creature. But I am me and you are you, then it becomes a game mandated to have a sense of self. So if I live in a world that is constituted by things like me, basically a social world of community, then it becomes necessary now for me to in further it's me talking and not you talking. I wouldn't need that if it's on mars by myself or if I was in the jungle as a feral child, if there was nothing like it, there's nothing like me around. There would be no need to have an inference. That hypothesis. Ah yes, it is me that is experiencing or causing these sounds and it is not you, it's only when there's ambiguity in play induced by the fact that there are others in that world. So I think that the special thing about self aware artifacts is that they have learned two or they have acquired or at least are equipped with possibly by evolution, generative models that allow for the fact there are lots of copies of things like them around and therefore they have to work out. It's you and not me. That </s>

<s>[INST] Also make sure using password manager or don't use the same password ever. Whatever you do to stop using password 123456, that doesn't make it more secure if you keep adding numbers after the password or does a little bit, but not much anyway, go to express VPN dot com slash like spot for an extra three months free last but certainly not least the legend. The greatest sponsor of all time. [/INST] The </s><s>[INST] show is brought to you by athletic greens and it's a G one drink. I actually noticed that they sponsor a lot of podcasts, which in some weird way makes me feel like um it makes me feel both joyful that a lot of people are spreading the word, but also it makes me feel like it's less of a secret that somehow I discovered, you know, it's like when you were a fan of Green Day before they were cool man, you're like a Pearl Jam or whatever, whatever the band when they were not as popular as they are today, that you love them. That's how I feel about athletic greens, but probably I wasn't even the first wave of people that discovered and enjoy athletic greens. I'm probably like the fifth wave, the 10th wave and now it's like the 15th wave and so like I'm uh incorrectly from a historical perspective, making myself feel like I'm the O. G of athletic greens, the O. G of A G. But probably not anyway, I love them and uh it doesn't matter. It doesn't matter where I am in the waves, I hope you love them too. It's a great way to support your nutritional health. I drink one twice a day. Now it's refreshing, even when I'm traveling through, travel packs are great, I'll give you one month supply of fish oil, which I also take when you sign up at athletic greens dot com slash lex. This is a lex Friedman podcast to support it. Please check out our sponsors in the description and now dear friends, here's yea [/INST] based off of our connection and just you being a friend, I need to show you my two tech companies and get your perspective on it because now I have friends that can give perspective like when I would work on albums, I had other friends that worked on albums and they would give me their perspectives on it. </s><s>[INST] You wanna do this? We [/INST] are doing it, this is part of it, </s><s>[INST] this is part of it absolutely beautiful. [/INST] Oh well I wanted to finish the thing is okay, you're gonna ask me different questions, but I'm about growing and building and bringing the idea to life. So when I see you, I say, oh this guy understands how to hire engineers where I'm coming from, coming from Hollywood, coming from press, coming from media, all of the guys, you know that so many of the guys that have been like voices and faces and talking heads whatever have not understood how to engineer product and that's the reason why I was able to jump past everyone in the entertainment field and become um you know, whatever the network is, 11 billion, I'm gonna stop putting the whole black thing on my work. Like let's just see where I am on the scale of life. Because that's a cop out for me to say, richest black guy of all time because that's feeding into the same, you know, trauma economy that black lives matter feeds into. That's why I love and respect engineers. That's the only thing that we really need to teach in school is engineering. We don't need to teach history. We don't need to teach anything that is subjective. It needs to only be engineering taught in school and everything else needs to be recessed. Nothing at all. Any force, subjective information is just to weaken and indoctrinate our species. And that's what schools do now </s><s>[INST] as an engineer. I love hearing you say that. But to push back history is not the interpretation of history might be subjective, but history has some facts and they're useful to give a grounding to the way you do engineering, [/INST] I don't 100% believe in anything, any concept of the future or any concept of history because history was just written by the victors. </s><s>[INST] Yeah. [/INST] So if I see stuff happen on the day that later that day is reported wrong. So how wrong is something reported 1000 years ago And why would we argue about something that's not in the now? Because that's the only thing that everyone can agree upon is that it is now right now. </s><s>[INST] Yeah. Well you try not to make the mistakes of the past. That's the usefulness of history. The limited usefulness of [/INST] the biggest mistake from the past that we keep making is looking at the past </s><s>[INST] too much, giving too much value to the past. [/INST] Too much value to the past. We are now we are now we are here. We are one species. We are one race. We're here and it's time and the leadership is changing because you have Ellen as a leader. Yea, as a leader and we're the top leaders were more influential than the president's. </s><s>[INST] So you're a human being with engineering challenges before you with stem player with parlor. What's the hardest thing in front of you on the engineering front? [/INST] That's the first sentence that any of our species needs to hear when they're born. You are a human being, when engineering challenges and I consider consider challenges to be opportunities in front of you literally. Like let me see a piece, I need to write that down. That's the beginning of our new species constitution. I'm gonna do the paper like this wide, put it in wide screen. This this for Ridley. Uh, you are no let me like you are a being with in nearing </s>

<s>[INST] Actually pulled almost a full Almighty yesterday working, doing a pretty cool thing. But the sleep I got when I finally got a chance to lay down was incredible. And a big part of that is thanks to a sleep. So go to a sleep dot com slash legs to get a special savings. That's eight sleep dot com slash lex. I feel like I have to stop doing this and read because the security guards are starting to get really nervous. This is the lex Fridman podcast and here is my conversation with frank Wilczek. What is the most beautiful idea in physics? [/INST] The most beautiful idea in physics is that we can get a compact description of the world. That's very precise and very full at the level of the operating system of the world. Um That's an extraordinary gift and we get, we get worried when we have find discrepancies between our description of the world and what's actually observed at the level even of a part in a billion. </s><s>[INST] You actually have this quote from Einstein that the most incomprehensible thing about the universe is is is that it is comprehensible or something like [/INST] that. That's so, that's the most beautiful surprise that I think uh That that really was the, to me, the most profound results of the scientific revolution of this, of the 17th century with uh the shining example of Newtonian physics that you could aspire to complete this precision and a concise description of the world of the operating system and it's gotten better and better over the years to and that's the continuing miracle. Now there are a lot of beautiful sub miracles to the form of the equations is governed by high degrees of symmetry and and they have very surprising kind of mind expanding structure, especially in quantum mechanics. But if we have, I have to say that the single most beautiful revelation is that in fact the world is comprehensible. </s><s>[INST] Would you say that's a factor. Hope [/INST] it's a fact. We can do, we, you can point to things like the rise of gross gross national product per capita around the world as a result of the scientific revolution. You can see it all around you uh in recent developments with exponent, So exponential production of wealth, control of nature at a very profound level where we do things like since tiny, tiny tiny tiny vibrations to tell that there are black holes colliding far away. Or we test laws as I alluded to a part in a billion and two things and what appear on the service to be entirely different conceptual universes. I mean on the one hand, pencil and paper or nowadays computers that calculate abstractions and on the other hand, magnets and accelerators and detectors that look at the behavior of fundamental particles and and these different universes have to agree or else we get very upset. And that's uh, that's an amazing thing if you think about it. So, and it's telling us that we do understand a lot about nature at a very profound level and there are still things we don't understand of course, but as we get better and better answers and better and better ability to address difficult questions, we can ask more and more ambitious questions. </s><s>[INST] Well, I guess the hope part of that is because we are surrounded by mystery. So we've one way to say it, if you look at the growth of GDP over time that we figured out quite a lot and we're able to improve the quality of life because of that and we've figured out some fundamental things about this universe, but we still don't know how much mystery there is. And it's also possible that there's some things that are in fact incomprehensible to both our minds and the tools of science, like the sad thing is we may not no, it because in fact they are incomprehensible. And that's the open question is how much of the universe is comprehensible. If we figured out the the everything uh what's inside the black hole and everything that happened at the moment of the Big Bang? Does that still give us the key to understanding the human mind and the emergence of all the beautiful complexity we see around us? That's not uh like when I when I see these objects, like, I don't know if you've seen them like Celera Tamara, uh all these kinds of objects were the from simple rules emerges complexity. It makes you wonder maybe it's not reducible to simple beautiful equations. The whole thing, only parts of it. That's the tension I was getting out with the hope. [/INST] Well, when we say the universe is comprehensible, we have to kind of draw careful distinctions about or uh definitions about what we mean by that both the </s><s>[INST] university and the kind of and the comprehensive. [/INST] Exactly right. So the so in certain areas of understanding reality, we've made extraordinary progress, I would say in understanding fundamental physical processes in getting very precise equations that really work and allow us to do uh profound sculpting of matter, you know, to make computers and Iphones and everything else and they really work and their extraordinary productions uh on the other but and that's all based on the laws of quantum mechanics and you know, they really, and they really work and then uh, and they give us tremendous control of nature. On the other hand, as as, as we get better answers, we can also ask more ambitious questions. And there are certainly things that have been observed even in the, in what would be usually called the realm of physics that aren't understood. For instance, there seems to be another source of mass in the universe, the so called dark matter that we don't know what it is. And it's a very interesting question, what it is uh, then, uh, but also as you were alluding to there, there's, it's one thing to know the basic equations. It's another thing to be able to solve them in in important cases. So we run, we run up against the limits of that in things like chemistry where we'd like to be able to design molecules and predict their behavior from the equations. We think the equations could do that in principle. But in practice, it's very challenging to solve them in all, but very simple cases. Uh, and then there's the other thing which is that a lot of what we're interested in is historically conditioned. It's not, it's not a matter of the fundamental equations, but about what has evolved or come out of, of the early universe and formed into people and frogs and societies and things and the laws of physics, The basic laws of physics only take you so far in that it kind of provides a foundation, but doesn't really that you need entirely different concepts to deal with those kind of systems and all. We was one thing I can say about that is that the laws themselves point out their limitations, that they kind of, their laws for dynamical evolution. So they tell you what happens if you have a certain starting point, but they don't tell you what the starting point should be at least. Uh and uh the other, the other thing that emerges from the equations themselves is the phenomenon of chaos and uh sensitivity to initial conditions, which tells us that you have that there are intrinsic limitations on how well we can spell out the consequences of the laws if we try to apply them </s><s>[INST] to see all the apple pie if you wanna, what does it make an apple pie from scratch it, You have to build the universe or something like that. Well, [/INST] you're much better off starting with apples than starting with quarks. </s><s>[INST] Let's put it that way in your book, a beautiful question you ask, does the world embody beautiful ideas. So, the book is centered around this very interesting question. It's like Shakespeare. You can dig in and read into all the different interpretations of this question, but at the high level what to use the connection between beauty of the world and physics of the world [/INST] in a sense. We now have a lot of insight into what the laws are for the form they take, that allow us to understand matter in great depth and control it as well as we've discussed. And it's an extraordinary thing how mathematically ideal those equations turn out to be. In the early days of greek philosophy. Uh Plato had this model of atoms built out of the five perfectly symmetrical botanic solid. So there was somehow the idea that mathematical symmetry should govern the world. And we've out plato plato by far in modern physics because we have symmetries that are much more extensive, much more powerful that turn out to be uh the ingredients out of which we construct our theory of the world and and it works and the sum that's certainly beautiful. So that the math, the idea of symmetry, which is a driving inspiration in much of human art, especially a decorative art like the alhambra or wallpaper designs or things you see around you everywhere uh, also turns out to be the dominant theme in modern fundamental physics symmetry and its manifestations. The laws turn out to be very to have these tremendous amounts of symmetry, You can change the symbols and move them around in different ways and they still have the same consequences. Uh that, so that's, that's beautiful and uh that these things, these different, these concepts that humans find appealing also turned out to be the concepts that govern how the world actually works. And uh I don't think that's an accident. I think humans were evolved to be able to interact with the world in in ways that are advantageous and to learn from it. And so we are naturally evolved, are designed to enjoy beauty and symmetry and this and the world has it. And that's no that's why we that's why we resonate with it. </s><s>[INST] What's interesting that the ideas of symmetry emerged at menu levels of the hierarchy of the university. You're talking about particles, but it also is at the level of chemistry and biology and and the fact that our cognitive sort of our perception system and whatever our cognition is also finds it appealing. Or somehow our sense of what is beautiful is grounded in this idea of symmetry or the breaking of symmetry symmetry is at the core of our conception of beauty. Whether it's the breaking or the non breaking of the symmetry, it makes you wonder why having why? Like uh so I come from Russia and the question of dostoyevsky, he's he has said that beauty will save the world. Maybe maybe as a physicist, you can tell me, what do you think he meant by that? [/INST] I don't I don't know if it saves the world, but it does turn out to be a tremendous source of insight into the world when we uh investigate kind of the most fundamental interactions things that are hard to access because they occur at very short distances between uh very uh special kinds of particles whose whose properties are only revealed at high energies at a we don't have much to go on from everyday life. But so we have when we guess what the so we and and the experiments are difficult to do. So you can't you can't really uh follow a very holy empirical procedure to sort of in the bocconi draconian style figure out the law is kind of step by step just by accumulating a lot of data. What we actually do is guess and the guesses are kind of aesthetic really. What what would be a nice description that's consistent with what we know and then you try it out and see if it works and by gosh it does and many profound cases. Uh so there's that but there's another source of symmetry which I didn't talk so much about in in a beautiful question but does relate to your comments and I think very much relates to uh the source of symmetry that we find in biology and in in in our in our heads, you know, in our brain, which is that uh I thought I'd well it is discussed a bit in a beautiful question and also in fundamentals is that when you have symmetry is also a very important means of construction. So when you have for instance a simple viruses that that need to construct their coat their protein coat, the coats often take the form of platonic solids. And the reason is that the d viruses are really dumb and they only know how to do one thing. So they make a pentagon, then they make another pentagon and make another pentagon and they all glued together in the same way and that makes a very symmetrical object sort of so the rules of development when when you have simple rules and they go they work again and again you get symmetrical patterns. That's it's kind of in in fact it's a recipe also for generating fractals, you know? Well I really like. Uh huh wow. The kind of broccoli that has all this internal structure and I wish I had a picture to ship but maybe people remember it from the from the uh from the supermarket and you say how did the vegetable so intelligent to make such a beautiful object of all this fractal structure and the secret is stupidity. We just do the same thing over and over again. And uh in our brains also. You know we we came out we start from single cells and they reproduce and they each one does basically roughly the same thing. They they uh the program evolves in time of course different different modules get turned on and off genetic, different regions of the genetic code get turned on and off. But uh but basically a lot of the stuff, same things are going on and they're simple things. And so you produce the same patterns over and over again and that's a recipe for producing symmetry. Do you think the same thing in many, many places? And if you look at, uh, for instance, the beautiful drawings of roman alcohol, the great neuro anatomist who drew the structure of different organs like the hippocampus. You see, it's very regular and very intricate and its symmetry and in that sense, it's because it's many repeated units that, that you can take from one place to the other and see that they look more or less the same. </s><s>[INST] But what you're describing this kind of beauty that we're talking about now is uh, is a very small Sample in terms of space time, in a, in a very big world, in a very short brief moment in this long history, in your book fundamentals, 10 keys to reality. I'd really recommend. People read it. Uh, you, uh, you say that space and time are pretty big, very big. How big are we talking about? Like what uh, you draw, can you tell a brief history of space and time? [/INST] It's easy to tell a brief history of the details. Get very involved of course. But one thing I'd like to say is that if you take a broad enough view the history of the universe is simpler than the history of Sweden, say, because you don't you, your standards are lower for, for, uh, but just to make it a quantitative, I'll just give a few highlights and it's it's it's a little bit easier to talk about time. So let's start with that the Big Bang occurred. We think the universe was much hotter and denser and more uniform About 13.8 billion years ago. And that's what we call the Big Bang. Uh And it's been expanding and cooling the matter in. It has been expanding and cooling ever since. So in a real sense, the universe is 13.8 billion years old. That's a big number. Kind of hard to think about. A nice way to think about it though, is to map it onto one year. So if let's say the universe just linearly map the time intervals from 13.8 billion years into one year. So the Big Bang then, is that on January one at 12 AM. Uh and uh you wait for quite a long time before the dinosaurs emerged. The dinosaurs emerged on christmas. It turns out a 12 months </s><s>[INST] Almost four months later, getting close [/INST] to the end and the extinction event that let the mammals and ultimately humans inherit the earth from From the dinosaurs occurred on December 30. And all of human history is a small part of the last day. And so, so yes, so we were occupying only a human lifetime is a very, very infinite testable part of this uh interval of these gigantic cosmic reaches of time. Uh And in space we can tell a very similar story, in fact very uh it's convenient to think that the size of the universe Is the distance that light can travel in 13.8 billion years. So it's 13.8 billion light years. That's that's how far you can see out. That's how far things can uh signals can reach us from and um uh huh that is a big distance because compared to that uh the the universe that the earth is a fraction of a light second. So again, we it's really, really big and so we have if we want to think about the universe as a whole in space and time, we really need a different kind of imagination. It's not it's not something you can grasp in terms of psychological time in a useful way. You have to think you have to use exponential notation and abstract concepts to to really get any hold on on these vast times and spaces. Uh huh On the other hand, let me hasten to add that. That doesn't make us small or make the time that we have to us small because again, looking at those pictures of you know what our minds are in some sort of components of our minds. These beautiful drawings of the cellular patterns inside the brain, you see that there are many, many many processing units. And if you analyze how fast they operate. I tried to estimate how many thoughts a person can have in a lifetime, That's kind of a fuzzy question, but I'm very proud that I was able to define it pretty precisely and it turns out we can we have time for billions of meaningful thoughts, you know, in a lifetime. So so it's a lot. We shouldn't, we shouldn't think of ourselves as terribly small, either in space or in time, because although we are small in those dimensions compared to the universe were large compared to meaningful units of processing information and and being able to conceptualize and understand things. </s><s>[INST] Yeah, but 99% of those thoughts are probably food, sex or internet related, [/INST] but yeah, well, they're not only like </s><s>[INST] .1 is Nobel Prize winning ideas, [/INST] but that's true, but you know, there's more to life than winning Nobel Prize. </s><s>[INST] How did you do that calculation? Can you maybe break that apart a little bit, just kind of for fun sort of an intuition of how we counted the number of thoughts, a number of thoughts [/INST] right there. There it's necessarily imprecise because a lot of things are going on in different ways. What is a thought, but there are several things that point to more or less the same uh rate of being able to have meaningful thoughts. Uh for instance, I'm the one that I think is maybe the most penetrating is uh how fast we can we can process visual images, How do how do we do that? Uh Mhm. If you've ever watched old movies, you can see that, that when while any movie, in fact that in a motion picture is really not a motion picture, it's a series of snapshots that are playing one after the other. And it's because our brains also work that way. We take snapshots of the world, integrate over a certain time and then go on to the next one and then by process, post process and create the illusion of continuity and flow. Uh We can deal with that. And uh the If the flicker rate is too slow, then you start to see that it's not it's a series of snapshots. And you can ask what is the, what is the crossover, when does it change from being something that is matched to our processing speed versus too fast? And and it turns out about 40 per second. And then if you take 40 per second as as how well how fast we can process visual images. You get to several billions of thoughts. Uh If you similarly, if you ask, what are some of the fastest things that people can do? Well, you can play video games, they can play the piano very fast if if they're skilled at it. And again, you get to similar uh units or how fast can people talk, you get to see, you know, within a couple of orders of magnitude, you get more or less to the same idea. So uh so that's how you can say that that, that there's there's billions of meaning, there's room for billions of meaningful thoughts. Yeah, I won't argue for exactly Two billion versus 1.8 billion. It's not that kind of question, but I think any estimate that's reasonable will come out within say 100 billion and and 100 million. So it's a lot. </s><s>[INST] It would be interesting to map out for an individual human being the landscape of thoughts that they have sort of traveled. If you think of thoughts as a set of trajectories, uh what what that landscape looks like. I mean yeah, I've been recently really thinking about uh this Richard Dawkins idea of memes and just all this ideas and the evolution of ideas inside of one particular human mind and how they're there then changed and evolved by interaction with other human beings. It's interesting to think about, so if you think the numbers billions, you think there's also social interaction. So these aren't uh like there's interaction in the same way you have interaction with particles, there's interaction between human thoughts uh that are perhaps that's at that interaction itself is fundamental to the process of thinking like without social interaction we would be like stuck like walking in a circle, we need, we need the perturbation of other humans to create change in evolution [/INST] once you bring in concepts of uh interactions and correlations and relations then you have what's called a combinatorial explosion that the number of possibilities rap expands exponentially technically with the number of the number of things are considering and uh it can easily rapidly outstripped these billion these billions of thoughts that we're talking about. So we we definitely cannot by brute force master complex situations and or think about think of all the possibilities in a complex situations. I mean, even even something as relatively simple as chess uh is still something that human beings can't comprehend completely, Even the best players lose still sometimes lose and they consistently lose to computers these days. Uh in computer science, there's a concept of np complete so large classes of problems when you scale them up beyond a few individuals become intractable. And so that in that sense, the world is inexhaustible, but </s><s>[INST] and that makes it beautiful that we can make uh any laws that generalize uh efficiently and well can compress all of that combinatorial complexity. Just like a simple rule that itself is beautiful. It's a [/INST] happy situation and I think that that we can find general principles of sort of, of the operating system that are comprehensible, simple, extremely powerful and let us control things very well and ask profound questions. And on the other hand that the world is going to be inexhaustible, that once we start asking about relationships and how they evolve and social interactions and the we'll never have a theory of everything in any meaningful sense because </s><s>[INST] of everything everything truly everything is. Uh can I ask you about the Big Bang, uh so we talked about the space and time are really big, but then, and we humans give a lot of meaning to the word space and time in our in our like daily lives. But then can we talk about this moment of beginning and how we're supposed to think about it, that at the moment of the Big Bang, everything was uh what, like infinitely small, and then it just blew up. [/INST] We have to be careful here because there's a common misconception that the big the big bang is like the explosion of a bomb in empty space that fills up the surrounding place. It is space, it is, yeah, as as we understand it, it's the fact it's the fact of the hypothesis, but well supported up to a point that that everywhere in the whole universe early in the history, uh matter came together into a very hot, very dense. If you run it backwards in time, matter comes together into a very hot, very dense and yet very homogeneous uh plasma of all the different kinds of elementary particles in quarks and anti quarks and gluons and photons, electrons and anti electrons, everything, you know, all of that stuff really hot, really, really, really hot, we're talking about, uh way way hotter than the surface of the sun, uh you know? Well, in fact, if you take the equations as we as they come, the prediction is that the temperature just goes to infinity, but then the equations uh break down, we don't we don't we don't don't really, there are various, the equations become infinity equals infinity. So they don't feel that it's called a singularity, we don't really know uh this is running the equations backwards, so you can't really get a sensible idea of what happened before the Big Bang. We don't so we need different equations to address the very earliest moments. Uh uh but so things were hotter and denser, we don't really know why things started out that way and we do, we have a lot of evidence that they did start out that way. Uh but since most of the uh huh you know, we don't get to visit there and do controlled experiments, most, most of the, most of the record is very, very processed and uh we have to we have to use very subtle techniques and powerful instruments to to get information that has survived. </s><s>[INST] Get closer and closer to the [/INST] big, get closer and closer to the beginning of things. And what's revealed there is that as I said, there were, there undoubtedly was a period when everything in the universe that we have been able to look at and understand and that's consistent with everything is uh the was in a condition where it was much, much hotter and much, much denser uh but still obeying the laws of physics as we know them today. And and then you start with that. So all the matter is in equilibrium. Uh and then with small quantum fluctuations and run it forward and then it produces in at least in broad strokes the universe we see around us today. Do you think </s><s>[INST] we'll ever be able to with the tools of physics with the way science is? Well, the way the human mind is, will ever be able to get to the moment of the Big Bang in our understanding or even the moment before the Big Bang. Can we understand what happened before the Big Bang? [/INST] I'm I'm optimistic both. That will be able to uh measure more. So, observe more and that will be able to figure out more. So they're very, very tangible prospects for observing the extremely early universe, so much even much earlier than we can observe now. Uh through looking at gravitational waves, gravitational waves, since they interact so weakly with ordinary matter uh sort of send a minimally processed signal from the Big Bang. It's a very weak signal because it's traveled a long way and diffused over long spaces, but people are gearing up to try to detect gravitational waves that could have come from the early universe. </s><s>[INST] Yeah, lego's incredible engineering project is the most sensitive, precise devices on the fact that humans can build something like that is uh truly awe inspiring from an engineering perspective. [/INST] And but these gravitational waves from the early universe would probably be of a much longer wavelength than liko is capable of sensing. So there's a beautiful project uh that's contemplated to put lasers in different parts, different locations in the solar system. You know, we really really separated by uh solar system scale differences like artificial planets or moons in different places. And and see the tiny motions of those relative to one another as a signal of radiation from the Big Bang. We can also maybe indirectly see the imprint of gravitational waves from the early universe on the photons, the microwave background radiation that that is our present way of of seeing into the earliest universe. But those those photons interact much more strongly the matter. They're much more strongly processed. So they don't give us directly such an unprocessed view of the early universe of the very early universe. But if gravitational waves leave some imprint on that as they move through, we could detect that too. And people are trying are, as we speak, working very hard towards towards that goal. </s><s>[INST] It's so exciting to think about a sensor, the size of the solar system, like [/INST] that would be a fantastic. I mean, that would be a pinnacle artifact of human endeavor. To me, it would be such a, such an inspiring thing that just we want to know and we go to these extraordinary lengths of making gigantic things that are also very sophisticated because what you're trying to do, you have to understand how they move, you have to understand the properties of light that that are being used interference between light. And you have to be able to make the light with lasers and understand the quantum theory and get the timing exactly right. And I said extraordinary endeavor involving all kinds of knowledge from the very strong, very small to the very large and all in the service of curiosity and built on a grand scale. So yeah, so it might be proud to be a human if yeah, if we did that. I </s><s>[INST] love that you're inspired both by the power of theory and the power of experiments that that both both I think are exceptionally impressive. That the human mind can come up with theories that give us a peek into how the universe works, but also construct tools that are way bigger then uh the evolutionary origins we came from [/INST] and by the way, you know, the fact that we can design this things than they work is an extraordinary demonstration that we really do understand a </s><s>[INST] lot. And then in some ways [/INST] and it's our ability to answer questions that also leads us to be able to address more ambitious questions. </s><s>[INST] So you mentioned at the at the Big Bang in the early days, um things are pretty homogeneous. Yes, but here we are sitting on Earth to uh hairless apes you could say with microphones in talking about the brief history of things you said, it's much harder to describe Sweden than it is. Um uh the universe. So there's a lot of complexity. There's a lot of interesting details here. So how does this complexity come to be? Do you think it seems like there's these pockets, we don't know how rare of like uh we're hairless apes and emerge. And then that came from the initial soup. Those homogeneous was that? Uh Yeah, well, [/INST] we understand there, we understand in broad outlines how it could happen. We certainly don't understand why it happened exactly in the way it did. But uh or, you know, they're certainly open questions about the origins of life and how inevitable emergence of intelligence was and and how that happened. But in the very broadest terms, the universe early on was quite homogeneous, but not completely homogeneous. Uh there are, they were part in 10,000 fluctuations in density within this primordial plasma. And uh as time goes on, there's an instability which causes those density contrast to increase. There's a gravitational instability where it's denser. The gravitational attractions are stronger. And so that brings in more matter and it gets even denser and so on and so on. So, so there's a natural tendency of matter to clump because of gravitational interactions. And then the equations complicated have lots of things clumping together, uh then, you know, then then we know what the laws are, but we have to, to a certain extent, wave our hands about what what what happens. But uh basic understanding of chemistry says that if things and and the physics of radiation tells us that if as things start to clump together, they can radiate, give off some energy. So they don't just they slow down there as a result, they lose energy that can collaborate together. Cool down form things like stars form things like planets. And so in broad terms, there's no mystery. There's uh that that's what the scenario, that's what the equations tell you should happen. But because it's a process involving many, many fundamental individual units. Uh the application of the laws that govern individual units to these things is is very delicate uh computational, very difficult and more profoundly. Uh the equations have this probability of chaos or sensitivity to initial conditions, which tells you tiny differences in the initial state can lead to enormous differences in the subsequent behavior. So, so physics, fundamental physics at some point says, okay, chemists, biologists, this is your problem. And uh and then again, in broad terms, we know how uh huh It's conceivable that that the humans and things like that can can how complex structure can emerge. It's a matter of having the right kind of temperature and the right kind of stuff. So you need uh you need to be able to make chemical bonds that are reasonably stable and be able to make complex structures. And we're very fortunate that carbon has this ability to make uh backbones and and elaborate branching and things. So you can get complex things that we call biochemistry. And uh and yet the bonds can be broken a little bit with the help of energetic injections from the sun. So you have to have both the possibility of changing but also the possible useful degree of stability. And we know at that very very broad level physics can tell you that's conceivable. If you want to know what actually, what what what what really happened, what really can happen. Then you have to you have to work about to go to chemistry. If you have if you want to know what actually happened, then you really have to consult the fossil record and biologists. And so so uh but it's so these these ways of addressing the issue are complementary in a sense. They they uh they use different kinds of concepts, they use different uh languages and they address different kinds of questions, but they're they're not inconsistent, they're just complimentary. </s><s>[INST] It's kind of interesting to think about those early fluctuations as our earliest ancestors. [/INST] Yes, that's right. So it's far it's amazing to think that uh you know, this is the modern answer to the uh huh We're the modern version of uh the what the hindu philosophers had. That art thou if you ask what Okay, that those those little quantum fluctuations in the early universe are the seeds out of which uh complexity, including uh plausibly humans really evolve. You don't need anything else </s><s>[INST] that brings up the question of asking for a friend here, if there's uh you know, other pockets of complexity uh commonly called his alien intelligent civilizations out there? [/INST] Well, we don't know for sure, but I I have a strong suspicion that the answer is yes. Because uh the one case we do have at hand to study here on earth, uh we sort of know what the conditions were that were helpful to life. The right kind of temperature, the right kind of star that keeps maintains that temperature for a long time. The liquid environment of water uh huh. And once those conditions emerged on earth, which was roughly 4.5 billion years ago, it wasn't very long before what we call life started to leave relics. So we can find uh forms of life, primitive forms of life that are almost as old as the earth itself in the sense that once the earth became reason was was turned from a a very hot boiling thing and cooled off into a solid mass with with water, life emerged very very quickly. So, so it seems that these general conditions for life uh are enough to to make it happen relatively quickly. Now. The other lesson I would, I think that one can draw from this one example, it's dangerous to the drug lessons from one example, but that's all we've got. Uh, and uh, that, that the emergence of intelligent life is a different issue altogether. It that took a long time and seems to have been pretty contingent, uh, the for a long time. Well for most, most of the history of life, it was single celled things, you know, even multicellular life only rose about 600 million years ago, so much after, you know, So, and they, and then intelligence is kind of a luxury. You know, if you think, uh, many more kinds of creatures have big stomachs and then big brains and in fact most, most most have no brains at all, in any reasonable sense, that, that, that then, uh, in the dinosaurs ruled for a long, long time. And some of them were pretty smart, but they, they were at best bird brains because birds came from the dinosaurs and uh, and uh, and it could have stayed that way. You know, and, and then human and the emergence of humans was very contingent and kind of very, very recent development on evolutionary time scales. And you can argue about the level of human intelligence. But it's, you know, I think it's pretty impressive what we're talking about it. It's very, it's very impressive and can ask these kinds of questions and discuss them intelligently. Uh, uh, so I guess my, so this is a long winded answer or justification of my feeling is that the conditions for life in some form are probably satisfied many, many places around the universe even, and even within our galaxy. Uh, I'm not so sure about the emergence of intelligent life or the emergence of technological civilizations that seems much more, much more contingent and special. And we might, it's conceivable to me that we're the only example in the galaxy or although yeah, I don't know one way or the other, I I have different opinions on different days of the week. But </s><s>[INST] one of the things that worries me in in uh, in the spirit of being humble that are particular kind of intelligence is not very special. So there's all kinds of different intelligences and even more broadly there could be many different kinds of life. So the basic definition and I just had, I think somebody that, you know, Sarah walker, I just had a very long conversation with her about even just a very basic question of trying to define what is life from a physics perspective, Even that question within itself. I think one of the most fundamental questions in science and physics and everything is just trying to get a hold, trying to get some universal laws around the ideas of what is life because that that kind of unlocks a bunch of things are on life. Intelligence consciousness, all those kinds of things. [/INST] I agree with you in a sense, but I think that's a dangerous question because the the answer can't be any more precise than the question. And the question, what is life kind of assumes that we have a definition of life and that it's a natural phenomenon that can be distinguished, but but really there are edge cases like viruses and uh, some people would like to say that electrons have consciousness and you know, so you can't, if you really have fuzzy concepts, it's uh, it's very hard to to reach precise kinds of scientific answers. But I think there's a very fruitful question that's adjacent to it, which is, has been pursued in different forms for uh, quite a while and is now becoming very sophisticated in reaching in new directions. And that is what are the states of matter that are possible? You know? So in in high school or grade school, you learn about solids, solids, liquids and gasses, but that really just scratches the surface of different ways that are distinguishable that matter can form into uh macroscopic lee different meaningful patterns that we call phases. And and then there are precise definitions of what we mean by phases of matter. And uh, that have been worked out fruitful over the decades. And we're discovering new states of matter all the time and kind of having to work at what we mean by matter. We're discovering the capabilities of matter to organize in interesting ways. And uh, some of them like liquid crystals, our uh important ingredients of life. Our cell membranes are liquid crystals. And that's very important to the way they work. Uh recently there's been a development in where we're talking about uh states of matter that not only that are not static but that have dynamics that have that have characteristic patterns not only in space but in time. These are called time crystals. And that's that's been a development that's just in the last decade or so. It is really really flourishing. And so uh is there a state of matter that costs or a group of states of matter that corresponds to life? Uh Maybe. But the answer can't be any more definite than the question. I </s><s>[INST] mean I got to push back on the those are just words. I mean I disagree with you. The the question points to a direction. The answer might be able to be more precise than the question because because just as you're saying there there's uh that we could be discovering certain characteristics and patterns that are associated with a certain type of matter microscopically speaking and that that we can then be able to post facto say this is let's assign the words life, this [/INST] kind of matter. I agree with that completely. That that's what that's uh but that's so it's not a disagreement. It's very frequent in physics that korean science that uh words that are in common use gets get refined and reprocessed into scientific terms that's happened for things like force and energy. Uh and so we're in a way we we find out what the useful definition is uh or symmetry for instance. And the common usage may be quite different from the scientific usage, but the scientific usage is special and takes on a life of its own and we find out what the useful version of it is, uh what the fruitful version of it is. So I do think so in that spirit, I think if we uh can identify states of matter or linked states of matter that can carry on processes of self reproduction and development uh and information processing, we should say we might be tempted to classify those as lang's as life. </s><s>[INST] Can I ask you about the craziest one which is uh the one we know maybe least about, which is consciousness. Is it possible that there are certain kinds of matter would be able to classify as um conscious meaning like? So there's uh the pants, I guessed right with the philosophers who kind of try to imply that all matter has some degree of consciousness and you can almost construct like a physics of consciousness. Do you? Um again, we're in such early days of this, but nevertheless it seems useful to talk about it. Is there some sense from a physics perspective to make sense of consciousness. [/INST] Is there? Well, again, consciousness is uh imprecise a very imprecise word and loaded with connotations that I think we should we don't want to start a scientific analysis that I don't think. Uh it's often been important in science to start with simple cases and work up uh consciousness, I think what most people think of when you talk about consciousness is okay, I'm what am I doing in the world? This is my experience of a rich experience, rich inner life and experience and where is that in the equations? And I think that's a great question, a great, great question. And actually, I think I'm gearing up to spend part of the, I mean, to try to address that in coming years. one </s><s>[INST] version of asking that question, just as you said now is what is the simplest formulation of that to study? I think I think [/INST] I'm much more comfortable with the idea of studying self awareness as opposed to consciousness because that that sort of gets rid of the mystical aura of the thing. And self awareness is uh in simple, you know, the uh I think uh contiguous at least with ideas about feedback. So if you have a system that looks at its own state and responds to it, that's the kind of self awareness, uh and more sophisticated versions could be like in information processing things, computers that look into their own internal state and do something about it. And I think that could also be done in neural nets, this is recurrent neural nets which are hard to understand and kind of a frontier that the uh so I think understanding those and gradually building up a kind of profound ability to unto uh conceptualize different levels of self awareness. What do you have to not know and what do you have to know? And when do you know that you don't know it or when do you know, What do you think? You know that you don't really know? And these uh I think uh clarifying those issues when we clarify those issues and get a rich theory around uh self awareness, I think the that will illuminate the questions about consciousness in a way that, you know, scratching your chin and talking about quality a and blah blah blah blah is never going to do. Well, </s><s>[INST] I also have a different approach to the whole thing. So there's from robotics perspective, you can engineer things that exhibit yes qualities of consciousness without understanding? Well, well the how things work and from that perspective you uh it's like a backdoor like enter through the psychology door precisely. [/INST] I think, yeah, I think </s><s>[INST] we're on we're on the [/INST] same wavelength here. I think that and let me just add one comment which is uh I think we should try to understand consciousness as we experience it uh uh as in evolutionary terms and ask ourselves why </s><s>[INST] why does it happen? This thing seems useful? Why is it useful? Why is it [/INST] useful? Uh We've got a conscious I watch here, interesting quest. Thank you Siri Okay, uh get back, I'll get back to you later. Uh And I think what we're gonna I'm morally certain that what's going to emerge from analyzing recurrent neural nets and uh robotic design and advanced computer design. Is that having this kind of looking at the internal state. Mhm. In a structured way that doesn't look at everything this guy has encapsulated, looks at highly processed information is very selective and makes choices without knowing how they're made. Is that there will also be an unconscious. I think that that is going to be turned out to be really essential to doing efficient information processing. And that's why it evolved because it's it's helpful and uh because brains come at a high cost. Yeah there has to be a good wife and there's a reason. Yeah they're rare in evolution. Uh And big brains are rare in evolution and they come at a big cost. You mean if you you they have high metabolic demands. Uh they require very active lifestyle. Warm bloodedness uh and take away from the ability to support metabolism of digestion. And so so it's it's uh it comes at a high cost. It has to it has to pay back. </s><s>[INST] Yeah I think it has a lot of value in social interaction. So I actually spending the rest of the day today and with our friends uh there are are legged friends in robotic form at boston dynamics. And I think so my probably biggest passions, human robot interaction. It seems that consciousness from the perspective of the robot is very useful to improve the human robot interaction experience? Ah The first display of consciousness but then to me there's a gray area between the display of consciousness and consciousness itself. If you think of consciousness from an evolutionary perspective, it seems like a useful tool in human communication. So uh [/INST] it's certainly whatever consciousnesses will turn out to be I think addressing it through its use Yes and working up from simple cases and also working up from engineering experience in trying to do uh efficient computation including efficient management of social interactions is going to really shed light on these questions as I said in a way that sort of amusing abstractly about consciousness. Never would. </s><s>[INST] So as I mentioned I talked to Sarah walker and first of all she says hi spoke very highly of you. One of her concerns about physics and physicists and humans is that uh we may not fully understand the system that we're inside of meaning. Like there may be limits to the kind of physics we do in trying to understand the system of which were part of. So like the the observer is also the observed in that sense. It seems like the our tools of understanding the world. I mean this is mostly centered around the questions of what is life trying to understand the patterns that that are characteristic of life and intelligence, all those kinds of things. Um We we're not we're not using the right tools because we're in the system. Is there is there something that resonates with you? They're almost well [/INST] yes yes we we do have we we have limitations of course in the amount of information we can process. On the other hand we can get help from our silicon friends and we uh we can get help from all kinds of instruments that make up for our perceptual deficits. And uh we have to and we can use at a conceptual level we can use different kinds of concepts to address different kinds of questions. So I'm not sure exactly what problem she's talking </s><s>[INST] about. It's the problem akin to uh an organism living on a two D plane trying to understand the three dimensional world. [/INST] Well we can do that. I mean you know we live in fact well you know for practical purposes most of our experiences two dimensional, it's hard to move vertically. And yet we've produced conceptually a three dimensional symmetry and in fact four dimensional space time. Uh So you know by thinking in appropriate ways and using instruments and demand. Getting consistent accounts and rich accounts. We find out what concepts are mhm mhm necessary. And uh I don't see any end in sight of the process or any showstoppers because I don't know. Let me give you an example. I mean for instance uh uh que sea de our theory of the strong interaction has nice equations to help to discover what's Q. C. D. Quantum Cromer dynamics. So it's our theory of the strong interaction the interaction that is responsible for nuclear physics. So it's the interaction that governs how quarks and gluons interact with each other and make uhh make protons and neutrons and all the strong the related particles and many things in physics. It's one of the four basic forces of nature as we presently understand it. Ah And uh so we have beautiful equations which we can test in very special circumstances using at high energies that accelerators. So we certain that these equations are correct prizes are given for it and people try to knock it down and they can't. Yeah they uh but uh but the situations in which we can calculate the consequences of these equations are very limited. So for instance no one has been able to demonstrate that this theory which is built on quarks and gluons which no one at which you don't observe actually produces protons and neutrons. And the things you do observe. This is called the problem of confinement. Uh So no one's been able to prove that analytically in a way that a human can understand on the other hand we can take these equations to a computer to gigantic computers and compute and by God you get the world from it. So these equations in a way that we don't understand in terms of human concepts we can't we can't do the calculations, but our machines can do them. So with the help of what I like to call our silicon friends and their descendants in the future, we can understand in a different way that allows us to understand more, but I don't think we'll ever know. No human is ever going to be able to carry to solve those equations in the same way. So, so, but I think that's, you know, when we find limitations too, our natural abilities, we can try to find work, work arounds and sometimes that's appropriate concepts. Sometimes it's appropriate instruments. Sometimes it's a combination of the two, but I think uh, it's premature to uh get defeatist about it. I don't see any any, I don't see any, uh, any logical contradiction or paradox or limitation that that will bring this process to a halt. </s><s>[INST] Well, I think the idea is to continue thinking outside the box in different directions, meaning just like how the math allows us to think of multiple dimensions outside of our perception system, uh, sort of thinking, um, you know, coming up with new tools of mathematics of computation or all those kinds of things to do to, to take different perspectives on our universe. Well, [/INST] I'm all for that, you know, and I kind of have even elevated into a principle which of complementarity following bore that you need different ways of thinking even about the same things in order to do justice to their reality and answer different kinds of questions about them. I mean, we've several times alluded to the fact that human beings are hard to understand and the concepts that you use to understand human beings if you want to prescribed drugs for them or see what's going to happen if they move very fast or get are exposed to radiation. And so that requires one kind of thinking that's very physical, based uh based on the fact that the materials that were made out of on the other hand, if you want to understand how a person is going to behave in a different kind of situation, uh you need entirely different concepts from psychology and uh there's nothing wrong with that. You can have very different ways of addressing the same material that are useful for different purposes. </s><s>[INST] Can you describe this idea which is fascinating of complementarity, a little bit sort of? Uh First of all, what state is the principal, what is it? And second of all, what are good examples starting from quantum mechanics used to mention psychology. Let's talk about this more like one in your new book, one of the most fascinating ideas actually. [/INST] I think it's a wonderful yeah, it's sort of, to me it's it's well, it's the culminating chapter of the book and I think uh since the whole book is about the big lessons or big takeaways from profound understanding of the physical world that we've understood that we've achieved uh including that its mysterious in some ways the uh, this was the final overarching lesson, complementarity and uh, it's a approach. It's so unlike some of these other things which are just facts about the world, like the world is both big and small and different sessions and is big, but we're not small things, the things we talked about earlier uh, and the fact that the universe is comprehensible and how complexity could emerge from simplicity and those things are uh, in some, in the broad sense, facts about the world, complementarity is more an attitude towards the world encouraged by the facts about the world. And it's the idea of the concept of the approach that or the realization that uh, it can be appropriate and useful and inevitable and unavoidable to use very different descriptions of the same object or the same system or the same situation uh, to answer different kinds of questions that may be very different and even mutually un interpret herbal mutually uh incomprehensible, uh, correct </s><s>[INST] somehow, but both [/INST] correct and sources of different kinds of insight, which </s><s>[INST] is so weird. Yeah, well, but it seems to work in so many cases. [/INST] It works in many cases and I think it's uh, it's a deep fact about the world and how we should approach it. It's most rigorous form, where it's actually a theorem if quantum mechanics is correct, occurs in quantum mechanics where the primary description of the world is in terms of wave functions. But let's not talk about the world and just talk about a particle an electron. It's it's it's the primary description of that electron is its wave function. And the wave function can be used to predict where it's going to be with different if you observe with it will be in different places with different probabilities or how fast it's moving and it will also be moving in different ways with different probabilities. That's what quantum mechanics says, and you can predict either set of probabilities if you know what's going to happen if I make uh an observation of the position or the velocity. Uh but so the way function gives you ways of doing both of those. But to do it to get those predictions, you have to process the wave function in different ways. You process it one way for position and in a different way for momentum. And those ways are mathematically incompatible. It's like, you know, it's like you have a stone and you can sculpt it into a venus de milo where you can sculpt it into David, but you can't do both. You can uh uh and that's an example of complementarity, you to answer different kinds of questions. You have to analyze the system in different ways that are uh mutually incompatible, but both valid to answer different kinds of questions. So in that case it's a theorem, but I think it's a much more widespread phenomenon that applies to many cases where we can't prove it as a theorem, but uh it's a piece of wisdom if you like, and it appears to be a very important insight, do you? And if you ignore it, you can get very yeah, confused and um misguided. </s><s>[INST] Do you think this is um a useful hack for ideas that we don't fully understand? Or is this somehow a fundamental property of all, or many ideas that you can take multiple perspectives and they're both true? [/INST] Well, I think it's both uh </s><s>[INST] both the answer to all questions. [/INST] Yes, that's right, It's not either or it's both. </s><s>[INST] It's paralyzing to think that that we live in a world that's fundamentally like surrounded by complementary ideas, like because uh we want universe, we somehow want to attach ourselves to absolute truths and absolutely, we certainly don't like the idea of complementarity. [/INST] Yes, Einstein was very uncomfortable with complementarity and in a broad sense, the famous Bohr Einstein debates revolves around this question of whether the complementarity that here's a foundational feature of quantum mechanics as we have, it was is a permanent feature of the universe and our description of nature and so far quantum mechanics winds and it's gone from triumph to triumph. Whether complementarity is rock bottom, I guess, you know, you can never be sure, I mean, but but it looks awfully good and it's been very successful and certainly its complementarity has been extremely useful and fruitful in in that domain. Uh including one of some two Feinstein's attempts to challenge it with like the famous Einstein Podolski Rosen experiment turned out to be confirmations of that that have have been useful in themselves. But so thinking about these things was fruitful but not in the way that Einstein hoped the the uh yeah, so so as I said in the case of quantum mechanics and this uh huh dilemma or dichotomy between processing the wave function in different ways, it's a theorem, they're mutually incompatible and that the physical correlate of that is the Heisenberg uncertainty principle that you can't have position and momentum determined at once. Uh but in other cases like one that I like to talk like to think about is or like to point out as an example is free will and determinism. It's much less of a theorem and more more a more a kind of uh huh uh huh way of thinking about things that I think is ah reassuring and avoids a lot of unnecessary quarreling and confusion. The </s><s>[INST] quarreling I'm okay with and the confusion I'm okay with. I mean people debate about difficult ideas but the question is whether it could be almost a fundamental truth, I think it is a fundamental truth, free will is both an illusion and not. Yes, I think that's correct and I loaded. There's a reason why people say quantum mechanics is weird and complementarity is a big part of that, you know, to say that the our actual whole world is weird, the whole hierarchy of the universe is weird in this kind of particular way. And it's quite profound, but it's also humbling because it's like, we're never going to be on sturdy ground in the way that humans like to be. It's like, you have to embrace that. Well, this, this, this whole thing is uh, like it's [/INST] one of, it's one of many lessons in humility that we run into in profound understanding of the world. I mean, uh, the Copernican revolution was one that's that the earth is not the center of the universe. Uh, Darwinian evolution is another that humans are not the pinnacle of, uh, you know, of, of God's creation. Uh, the uh, end the apparent result of uh, deep understanding of physical reality, that mind emerges from matter. And, you know, there's, you know, there's, there's no uh, no call on special life forces or souls. These are all lessons in humility. And I actually find complementarity a uh, liberating concept. It's okay, you know what it is, in a way, that is what I mean. There's a story about dr johnson and he's talking with boswell and boswell was they were discussing a sermon that they both heard and the sort of culmination of of the sermon was the speaker saying, I accept the universe, and dr johnson said, well, he damn well better. And there's a certain uh there's a certain joy in accepting the universe because it's mind expanding and uh you know, and and to me, complementarity also suggests tolerance suggests opportunities for understanding different, different understanding things in different ways that ad uh add to rather than detract from understanding. So I think it's it's an it's an opportunity for mind expansion in demanding that there's only one way that to think about things can be very limiting </s><s>[INST] And the free will. one. That's a tricky one though, I think, like, I am the decider of my own actions and at the same time I'm not is uh it is tricky to think about, but it's that does seem to be some kind of profound truth in that. [/INST] I get well, I think it is tied up, it will turn out to be tied up when we understand things better with these issues of self awareness and and where we get what we perceive as making choices, what does that really mean? What's going on under the hood? And uh but I'm I'm speculating about a future understanding that's not in place, but at present </s><s>[INST] your sense, there will always be uh like, as you dig into the self awareness thing, there'll always be some places where complementarity is going to show up. [/INST] Oh, definitely. Yeah, I mean, there will be uh how should I say, there'll be kind of a God's eye view, which sees everything that's going on in the computer or the brain, and then there's the brain's own view of the central processor or whatever it is, that's what we call the self, the consciousness, that's all only aware of a very small part of it. And those are very different. Those are the so uh the God's eye view can be deterministic while the self view ces free will and that, I'm pretty sure that's how it's gonna work out actually. But as it as it stands, free will is a concept that we definitely, at least I feel I definitely experienced, I can choose to do one thing then another and other people I think are sufficiently similar to me that I have to trust that they feel the same way. Uh uh and it's an essential concept in psychology and law and so forth. But uh at the same time, I think that mind emerges from matter and that there is an alternative description of matter. That's up to subtleties about quantum mechanics, which I don't think are relevant here uh really is deterministic. </s><s>[INST] Let me ask you about some particles. Okay, first, the absurd question, almost like a question that, like plato would ask, what is the smallest thing in the universe, [/INST] as far as we know, the the fundamental particles out of which we build our most successful description of nature, our points, they have zero, they have don't have any internal structure, that's they uh so that's as small as can be to uh So what does that mean operationally? That means if you that they obey equations that describe entities that are singular concentrations of energy momentum, angular momentum, the things that particles have but localized at individual points now. Uh that mathematical structure is only revealed partially in the world because to to process the wave function in a way that accesses information about the precise position of things. You have to apply a lot of energy. And that's not, you know, that's an idealization that you can apply infinite amount of energy to determine a precise position. But at the mathematical level, uh we build the world out of particles that are points. </s><s>[INST] So, do they actually exist? And what are we talking about? Like, Oh, they exist. So let me ask, sort of uh, do quarks exist? [/INST] Yes. two electrons exist? Yes. Do proteins exist? Yes </s><s>[INST] but what does it mean for them to exist? [/INST] Okay, so, well, the hard answer to that, the precise answer is that uh we construct the world out of equations that contain entities that are reproducible, that exist in vast numbers throughout the universe, uh that have definite properties of mass spin, uh and a few others that uh we call electrons and what what an electron is, is defined by the equations that it satisfies theoretically. And we find that there are many, many exemplars of that, of that entity in the physical world. So intellect. In the case of electrons, we can you isolate them and study them in individual ones in great detail and we can check that they all actually are identical. Uh and that's why chemistry works. And yes, so, so that in that case uh it's very tangible. Similar with photons, you can study them individually the units of light. Uh and uh nowadays it's very practical to study individual photons and determine their uh their spin. And there are other basic properties and uh uh and check out the equations in great detail for quarks and gluons, which are the other two main ingredients of uh our model of matter that's so successful. It's a little more complicated because the quarks and gluons that appear in our equations don't appear directly as particles. You can isolate and a study individually, they always occur within about what are called bound states or structures like protons. A proton, roughly speaking, is composed of three quarks and a lot of gluons, but we can detect them in a remarkably direct way actually nowadays, whereas at relatively low energies. Uh the behavior of quarks is complicated. At high energies. They can they can propagate through space relatively freely for a while and we can see their tracks. So ultimately they get recaptured into protons and other maisons and funny things, but for a short time they propagate freely and while that happens we can take snapshots and see see their manifestations. Uh this is actually this kind of thing is exactly what I got the Nobel prize for predicting that this would work. And similarly for gluons, although you you can't uh you can't isolate them as individual particles and study them in the same way we study electrons, say uh you can use them to as use them theoretically as entities out of which you build tangible description, tangible things that we actually do observe. Uh but also you can uh accelerators that high energy, you can liberate them for brief periods of time and study how they that that and and get convincing evidence that they they leave tracks and you can get convincing evidence that they were there and and have the properties that we wanted them to </s><s>[INST] have. Can we talk about asymptotic freedom is very idea that you want the Nobel prize for. So, it describes a very weird effect to me. Uh the weird in the following way. So, the, you know the way I think of most forces or interactions, the closer you are, the stronger the effect, the stronger the force right with with quirks. Uh the close they are, the less serve the strong interaction and in fact they're basically act like free particles when there very close. But this requires a huge amount of energy. But like, can you describe me um why? How does this even work? How weird it is, [/INST] proper description must bring in quantum mechanics and relativity and its uh so a proper description and and equations so a proper description really is probably uh more more more than we have time for. And then uh we require quite a bit of patience on your part. But </s><s>[INST] how does relativity come into play way [/INST] relativity is important because when when we talk about trying to think about short distances, we have to think about very large momentum and very large momentum connected to very large energy in relativity. And so the connection between how things behave at short distances and how things behave at high energy really is connected through relativity and sort of slightly backhanded way quantum mechanics indicates that short to get to analyze short distances. Uh you need to bring in probes that carry a lot of momentum. This again, is related to uncertainty because uh it's the fact that you have to bring in a lot of momentum that interferes with the possibility of determining uh position and momentum at the same time. If you want to determine position, you have to use instruments that bring in a lot of momentum. And because of that, those same instruments can't also measure momentum because they're disturbing the momentum that and then the momentum brings in energy. And so so that there's also the effect that a syntactic freedom comes from uh the possibility of spontaneously making uh quarks and gluons for short amounts of time that fluctuate into existence and out of existence. Uh and the fact that that can be done with a very little amount of energy and uncertainty and energy translates its uncertainty in time. So if you do that for a short time, you can do that. Uh well it's all comes in a package you can so I told you it take a while to really to really explain. But the but but the results can be understood, meaning we can state the results pretty simply, I think. So uh in everyday life we do encounter some forces that increase with distance and kind kind of turn off at short distances. That's the way rubber bands work. If you think about it, uh if you pull them hard, they resist but but they get flabby if if the rubber band is not not pulled. Uh and so there are that can happen uh in the physical world. But what's what's really difficult is to see how that could be a fundamental force that's consistent with everything else we know and that that's what asymptotic freedom is. It says that there are particular, there's a very particular kind of fundamental force that involves special particles called gluons with very special properties that enables that kind of behavior. So there were experiments at the time we did our work, there were experimental indications that corks and glue ons did have this kind of property, but there were no equations that were capable of capturing it. And we found the equations and showed how they work and showed how they that they were basically unique. And this led to a complete theory of how the strong interaction works, which is the quantum Cromer dynamics we mentioned earlier and so uh so that's the phenomenon that quarks and gluons interact very, very weakly when they're close together. That's connected through relativity with the fact that they also interact very, very weakly at high energies. So if you have so at high energies uh the simplicity of the fundamental interaction gets revealed at the time. We did our work. The clues were very subtle, But nowadays that at what are now high-energy accelerators, it's all obvious. So we would have had a much, somebody would have had a much easier time. 20 years later looking at the data, you can sort of see the quarks and gluons. As I mentioned, they leave these short tracks that would have been much much easier. But from fundamental from indirect clues, we were able to piece together enough to make that behavior prediction rather than a post diction. </s><s>[INST] So it becomes obvious at high energies, [/INST] it becomes very obvious when when we first did this work, it was frontiers of high energy physics and at big international conferences there would always be sessions on testing Q C D and whether the whether this proposed description of the strong interaction was in fact correct and so forth and it was very exciting. They're big but nowadays the same kind of work, but much more precise with calculations to more accuracy and experiments that are much more precise and comparisons that are very precise uh now it's called calculating backgrounds because because people take this for granted and want to you and want to see deviations from the theory, which would be which would be the new discoveries. </s><s>[INST] Yeah, the cutting edge becomes the foundation of foundation, becomes boring. Huh. Is there some for basic explanation purposes? Is there something to be said about strong interactions in the context of the strong nuclear force for the for the interaction between protons and neutrons versus the interaction between quarks within protons. [/INST] Quarks and gluons have the same relation basically to nuclear physics as electrons and photons have to atomic and molecular physics. So atoms and photons are the dynamic entities that really come into play in chemistry. And atomic physics of course you have to have the atomic nuclei. But those are small and relatively inert really. The dynamical part. And, you know, for most purposes of chemistry, you just say you have this tiny little nuclear switch which UCD gives, you don't worry about it just it's there. The real the real action is the electrons moving around and exchanging and things like uh the but okay, but we wanted to understand the nucleus to and uh so adam's based are sort of quantum mechanical clouds of electrons held together by electrical forces, which is photons. And then this radiation, which is also another aspect of </s><s>[INST] photons, that's where all the fun happens is the electrons and photons. [/INST] That's right. And the nucleus the nucleus are kind of the the uh well they're they're necessary, they give the positive charge and most of the mass of matter. Uh but they don't since since they're so heavy, they don't move very much in chemistry. And uh I'm oversimplifying drastically </s><s>[INST] that being much the interaction and [/INST] they for most purposes in chemistry, you can just idealize them as concentrations of positive mass and charge that that are uh uh you don't have to look inside, but people are curious what's inside really. Uh and uh that and that was a big thing on the agenda of 20th century physics starting in the 19 Well, starting with the 20th century and unfolding throughout of trying to understand what forces held the atomic nucleus together what it was. And so uh anyway, there the emerged the story that emerges from UCD, is that very similar to the way that well, broadly similar to the way that uh clouds of electrons held together by electrical forces uh give you atoms and ultimately uh molecules uh protons and neutrons are like atoms made now out of corks, Quark clouds held together by gluons, which are like like like the photons that will give the electric forces. But this is giving a different force the strong force. And uh and the residual forces between protons and neutrons that mhm are left over from the basic binding are like the residual forces between atoms that give molecules. But in the case of protons and neutrons, it gives you atomic nuclear. </s><s>[INST] So again, for definition purposes Q. C. D. Quantum thermodynamics is basically the physics of strong interaction. [/INST] Yeah, we understand that. We now have done just would I think most physicists would say it's the theory of quarks and gluons and how they interact. But it's a very precise and I think it's fair to say very beautiful theory based on mathematical symmetry of a high order. Uh And another thing that's beautiful about it is that it's kind of in the same family as electrodynamics. The conceptual structure of the of the equations are very similar. They are based on having particles that respond to charge in a very symmetric way. In the case of electrodynamics, its photons that respond to electric charge. In the case of quantum Cromer dynamics, there are three kinds of charge that we call colors, but there's nothing like colors. They really are like different kinds of </s><s>[INST] charge rhyme with the same kind of uh like a similar kind of dynamics. [/INST] Similar kind of dynamics. I call I say I'd like to say that Q C. D. Is like Q E. D. On steroids and instead of one photon you have eight gluons. Instead of one charge, you have three color charges. But there's a strong family resemblance </s><s>[INST] between but the context in which Q. C. D. Does this thing is much higher energies. Like that's where it comes to. Its [/INST] a stronger force. So that to access how its works And kind of pry things apart, you have to inject more energy. </s><s>[INST] And so that that gives us um in some sense a hint of how things were in the earlier universe. Yeah, [/INST] well in that regard, asymptotic freedom is a tremendous blessing because it means things get simpler at high energy. </s><s>[INST] The universe was born free [/INST] born free. That's very good. Yes, chris was born. So, so in atomic physics, I mean, I mean a similar thing happens in the theory of stars. Stars are hot enough that uh the interactions between electrons and photons are, they're liberated. They don't form atoms anymore. They make a plasma. Which in some ways it's simpler to understand. You don't have complicated chemistry. And in the early universe, according to QC D, similarly, atomic nuclei dissolved and take the constituent quarks and gluons which are moving around very fast and interacting in relatively simple ways. And so this uh this opened up the early universe to scientific calculation. </s><s>[INST] Can I ask you about some other weird particles that make up our universe? What are exxons? And what is the strong cp problem? [/INST] Okay, so uh let me start with what the strong cp problem is. First of all, we'll charge C is charged conjugation, which is the Yeah, transformation. The notional transformation if you like, that changes all particles into their anti particles. And uh the concept of seek symmetry, charge conjugation symmetry is that if you do that uh you find the same laws that would work. So the laws are symmetric. If the behavior that particles exhibit is the same as the part as the behavior you get with all their anti particles. Uh then P is parody, which is also called spatial inversion. It's basically looking at a mirror universe and saying that the laws that are obeyed in a mirror universe when you look at the mirror images obey the same laws as the as the sources of their images. There's no way of telling left from right, for instance, that the laws don't distinguish between left and right. Uh Now In the mid-20th century people discovered that both of those are not quite true that really the the equation that that the mirror universe, the universe, that's that you see in a mirror is not going to obey the same laws as the as the the universe that that that we actually exhibit. Uh and interpret you could, you would be able to tell if you did the right kind of experiments, which was the mirror and which was the real thing. Uh anyway, that </s><s>[INST] just a parody and they show that doesn't necessarily hold, [/INST] it doesn't quite hold and that that that and examining what the exceptions are turned out to be to lead to lower kinds of insight about the nature of fundamental interactions, especially properties of neutrinos and the weak interaction. It's a long story but it's a very you </s><s>[INST] just define the sea and the p the congregation, the church congregation [/INST] that I've done that I want to, what's the problem of them off? Because it's easier to talk about T. Which is time reversal symmetry. We have very good reasons to think Cpt is a an accurate symmetry of nature. It's on the same level as relativity and quantum mechanics basically. So that better be true. Uh </s><s>[INST] So our metric when you when you do conjugation, parody and time [/INST] and time and space reversal, if you do all three then you get the same physical consequences now. So but that means that CP is is equivalent to T. But what what's observed in the world is that T. Is not quite an accurate symmetry of nature either. So most phenomena of at the fundamental level. So interactions among elementary particles and the basic gravitational contraction uh If you ran them backwards in time you get the same laws. So if again going back unless this time we don't talk about a mirror but we talk about a movie, if you take a movie and then run it backwards, that's the time reversal. It's </s><s>[INST] good to think about a mirror in time. [/INST] It's like a mirror in time. If you uh if you run run the movie backwards, it would look very strange if you were looking at complicated objects and uh you know, a charlie Chaplin movie or whatever. They would look very strange if you ran it backwards in time. But at the level of basic interactions, if you were able to look at the atoms and the quarks involved, they would obey the same laws. They do a very good approximation, but not exactly. </s><s>[INST] So, you know exactly. That means you could tell, you [/INST] could tell, but you have to do very, very subtle experiments with that high energy accelerators to take a movie that looked different when you ran it backwards. Uh This was a discovery by uh uh two great physicist named Cronin and Jim Cronin and Val Fitch In the uh in the mid 1960s, previous to that, over all the centuries of development of physics with all his precise laws, they did seem to have this gratuitous property. Yeah, that they look the same. If you run the equations backwards, it's kind of an embarrassing property actually, because life isn't like that. So empirical reality does not have this imagery in any obvious way. And yet the laws did. </s><s>[INST] It's almost like the laws of physics are missing something fundamental about life if it holds that property. Right. Well, that's that's the embarrassing nature. It's [/INST] it's yeah, it's </s><s>[INST] embarrassing. Well, people, [/INST] I worked hard at what this is a problem that's thought to belong to the foundations of statistical mechanics or the foundations of thermodynamics to understand how behavior which is grossly not symmetric with respect to reversing the direction of time in large objects, how that can emerge from equations which are symmetric with respect to changing the direction of time to a very good approximation. And that's that's still an interesting endeavor. That's that's that's interested in actually, it's an exciting frontier of physics now to sort of explore the boundary between when that's true and when it's not true, when you get to smaller objects, uh and exceptions, like time crystals. Uh </s><s>[INST] I definitely have to ask about time christmas in a second here. But so the cp problem and t so there's lost all of these [/INST] are in danger of infinite regress, but we'll convert soon. </s><s>[INST] So can't possibly be turtles all the way down. We're going to get to the bottom turtle. So, [/INST] so so it became so it got to be a real. I mean, it's a really puzzling thing why the laws should have this very odd property that we don't need. And in fact, it's kind of an embarrassment in addressing empirical reality, but it seemed to be almost seemed to be exactly true for a long time. And then almost true. And in way almost true is even more disturbing than exactly true because exactly true. It could have been just a fundamental feature of the world. And, you know, at some level, you just have to take it as it is. And if it's if it's a beautiful, easily articulate herbal regularity, you could say that, okay, that's that's fine as a fundamental law of nature. But to say that approximately true, but not exactly, that's that's not that's weird. So uh and then so there was great progress in uh the late part of the 20th century uh in getting to an understanding of fundamental interactions in general that shed light on this issue. Uh it turns out that the basic principles of relativity and quantum mechanics plus the kind of high degree of symmetry that we found the so called gait symmetry that characterizes the fundamental interactions when you put all that together. It's a very, very constraining framework. And it has some indirect consequences because the possible interactions are so constrained. And one of the indirect consequences is that the possibilities for violating the symmetry between forwards and backwards in time are very limited. They're basically only two and one of them occurs and leads to a very rich theory that explains the Cronin fish experiment. And a lot of things that have been done subsequently has been used to make all kinds of successful predictions. So, that's that's turned out to be a very rich interaction. It's esoteric and the effects are only show up at accelerators and are small and so much that they might have been very important in the early universe and lead to be connected to the asymmetry between matter and anti matter in the present universe. And so, but that's a that's another digression. The the point is that uh that was fine. That was a triumph to say that there was one possible kind of interaction that would violate time reversal cemetery. And sure enough, there it is. And but the other kind doesn't occur. So we still got a problem. Why doesn't it occur? Uh but so we're close to really finally understand this profound gratuitous feature of the world that is almost but not quite symmetric under reversing the direction of time, but not quite there. And uh, to get to understand that last bit is a challenging frontier of physics today. Uh and we have a promising proposal for how it works, which is a kind of theory of evolution. So there is this possible interaction which we call a coupling and there's a numerical quantity that tells us how strong that is. And traditionally in physics we think of these kinds of numerical quantities as constants of nature that you just have to put them in right. That from experiment, they have a certain value And that that's it. And you know, who am I to question what I've gotten doing? They just, well, they seem to be just constant. Uh but in this case it's been fruitful to think and work out a theory where that the strength of interaction is actually not a constant. It's a fun, it's a field, it's a it's a fields are the fundamental ingredients of modern physics. Like there's an electron field. There's a photon field which is also called the electromagnetic field. And so every all of these particles are manifestations of different fields. And uh, there could be a field, something that depends on space and time. So a dynamical entity instead of just a constant here. And uh if you do things in a nice way, that's very symmetric, very much suggested aesthetically by the theory. Uh but the theory we do have, then you find that you get a field which as it evolves from the early universe, settles down to a value That's just right to make the laws very nearly exact invariants or symmetric with respect to reversal of time </s><s>[INST] might appear as a constant. But it's actually a field that evolved over time. [/INST] It evolved over time. But when you examine this proposal in detail, you find that it hasn't quite settled down to exactly zero there. It's still, the field is still moving around a little bit and because the motion is so uh the motion is so difficult, the material is so rigid and this material that fills the field that fills all space is so rigid, Even small amounts of motion can involve lots of energy. And that. And that energy takes the form of particles, Fields, fields that are in motion are always associated with particles. And those are the acciones. And if you calculate how much energy is in these residual oscillations. These, this accion gas that fills all the universe. If this fundamental theory is correct, you get just the right amount to make the dark matter that astronomers want and it has just the right properties. So I'd love to believe </s><s>[INST] that. So that might be a thing that unlocks, uh, might be the key to understanding dark matter. [/INST] Yeah, I'd like to think so. And many, many physicists are coming around to this point of view, which I've been a voice in the wilderness, was a voice in the wilderness so long. But now now it's become very popular, maybe even dominant. So </s><s>[INST] almost like so this accion particle slash field would be the thing that explains dark matter. [/INST] It explained. It would solve this fundamental question of finally, of why the laws are almost, but not quite exactly the same if you run them backwards in time and then seemingly in a totally different conceptual universe, it would also provide under give us an understanding of the dark matter. That's not what it was designed for. And the theory wasn't, wasn't proposed with that in mind. But when you work at the equations, that's what you get, </s><s>[INST] it's always a good sign. I think I've vaguely red somewhere that there may be early experimental validation of uh, of Axiron is that, am I, am I reading the wrong? [/INST] Well, there have been quite a few false alarms and I think there are some of them still people desperately want to find this thing and uh, but I don't think, I don't think any of them are convincing at this point. But there are very ambitious experiments and uh kind of you have to design new kinds of antennas that are capable of detecting these predicted particles. And it's it's very difficult. They interact very, very weakly. If it were easy, it would have been done already. But but I think there's good hope that uh we can get down to the required sensitivity and actually test whether these ideas are right in coming years or maybe decades </s><s>[INST] and then and then understand one of the big mysteries like literally big in terms of uh it's fraction of the universe is dark matter. Let me ask you about, you mentioned a few times time crystals um what are they? These things are it's a very beautiful idea when we start to um treat space and time as um similar framework. Yes, physical phenomenon. [/INST] That's what motivated it. </s><s>[INST] What, first of all, what are crystals? Time crystals? [/INST] So crystals are orderly arrangements of atoms in space and uh many materials, if you cool them down gently uh will form crystals. And so we say that that's a state of matter that forms spontaneously. And uh an important feature of that state of matter is that the end result, the crystal uh has less symmetry than the equations that give rise to the crystal. So the equations, the basic equations of physics uh are the same if you move a little bit so you can move their homogeneous but crystals aren't. The atoms are in particular places that they have less symmetry. Uh and time crystals. So the same thing in time basically you but of course it's not so it's not positions of atoms, but it's ordering orderly behavior. Uh that certain states of matter will arrange themselves into spontaneously if you do them, if you if you treat them gently and let them do what they want to do, </s><s>[INST] but repeat in that same way indefinitely. [/INST] That's the crystalline form. You can also have uh uh time liquids or you can have all kinds of other states of matter. You know, the space time crystals where the pattern only repeats if uh with each step of time, you also move it a certain a certain direction in space. And so, so yeah, so, but it's it's basically it's states of matter that uh oh, base that display structure in time spontaneously. </s><s>[INST] So here's here's the difference when it happens in time. Uh It sure looks a lot like its motion and if it repeats indefinitely, sure looks a lot like perpetual motion, like uh looks like free lunch. I was told that there is no such thing as free lunch. Does does this violate laws of thermodynamics? [/INST] Uh No, but it requires a critical examination of the laws of thermodynamics. I mean, let me, let me say on background that the laws of thermodynamics are not the not fundamental laws of physics, There are things we prove under certain circumstances emerged from the fundamental laws of physics. They're not, you know, we don't posit them separately, they're meant to be deduced and they can be deduced under limited circumstances, but not necessarily universally. And we found finding some of the subtleties and sort of accept edge cases where they don't apply in a straightforward way. Uh And this is one. Uh So time crystals do obey, do have this structure in time, but it's not a free lunch because although, in a sense, things are moving. Uh they're they're already doing what they want to do their in their lives. So, if you want to extract energy from it, you're going to be foiled because there's no spare energy there, You uh so you you can add energy to it and kind of disturb it, but but you can't extract energy from this motion because it's gonna it wants to do. That's the lowest energy configuration that there is. So, you you can't get further energy </s><s>[INST] out of it. So, in theory, I guess perpetual motion, uh you would be able to extract energy from it if such a thing was to be created, you can milk it for energy. Well, what's what's [/INST] usually meant in the literature of perpetual motion is mhm, a kind of macroscopic motion that you could extract energy from. And somehow it would crank back up, that's that's not the case here. If you want to extract and you uh this motion is is not something you can extract energy from. If you intervene in the behavior, you can change it, but only by injecting energy. Not not by taking away energy. </s><s>[INST] You mentioned that a theory of everything may be quite difficult to come by A theory of everything broadly defined meaning, like truly a theory of everything. But let's look at a more narrow theory of everything. Which is that what the way it's using often in physics as uh a theory that unifies our current uh laws of physics. General relativity, quantum field theory. Do you have thoughts on this dream of a of a theory of everything in physics? How close are we? Is there any promising ideas out there in your view? [/INST] Well, it would be nice to have, it would be aesthetically pleasing uh will be useful. No, probably not. Well, I shouldn't it's dangerous to say that, but uh probably not. I think we are not not certainly not in the uh foreseeable future. Maybe to understand black holes. Yeah, but that's that's yes, maybe to understand black holes, but that's not useful in my book. And Well, not only, I mean, to understand it's worse. Of course, it's not useful in the sense that we're not going to be basing any technology anytime soon on black holes. But it's it's more severe than that, I would say. It's that the kinds of questions about black holes that we can't answer within the framework of existing theory are ones that are not going to be susceptible to astronomical observation in the foreseeable future. Their questions about very, very small black holes when uh when quantum effects come into play or uh so that black holes are uh you know, not not black holes, they're they're they're they're emitting Hawk this discovery of Hawking called Hawking radiation, which for astronomical black holes is a tiny tiny effect. That's no one, no one has ever observed a prediction that's never </s><s>[INST] been a supermassive black holes. That doesn't apply. No, [/INST] no, the predicted rate of radiation from those black holes is so tiny that it's absolutely un observable and is overwhelmed by all kinds of other effects. Uh so uh so it's not practical in the sense of technology, it's not even practical in the sense of application to astronomy. We are existing theory of general relativity and quantum theory and our theory of the different fundamental forces is perfectly adequate. All proper, all problems of technology, for sure. Uh and almost all problems of astrophysics and cosmology that appear except with the notable exception of the extremely early universe. If you want to ask what happened before the Big Bang or what happened right at the Big bang, uh which would be a great thing to understand. Of course. Uh Yes, we don't, but </s><s>[INST] but what about the engineering questions, so if we look at space travel. So uh I think you've spoken with him eric Weinstein really um uh you know, he says things like we want to get off this planet. His intuition is almost a motivator for the engineering project of space exploration in order for us to crack this problem of becoming a multi planetary species, we have to solve the physics problem. His intuition is like if we figure out what he calls the source code, which is like, like like like a theory of everything might give us clues on how to start hacking the fabric of reality, like getting shortcuts right? [/INST] Might, I can't say that, you know, I can't say that it won't but I can say that in the 1970s and early 1980s we achieved huge steps in understanding matter. Uh que sea de uh much better understanding of the weak interaction uh much better understanding of quantum mechanics in general. And it had minimal uh minimal impact on time to design </s><s>[INST] proportional rocket design, [/INST] anything, any technology whatsoever. And now we're talking about much more esoteric things. And since I don't know what they are, I can't say for sure that they won't affect technology, but I'm very, very skeptical that they would affect technology. The uh because you know to access them, you need very exotic circumstances to make new kinds of particles with high energy, you need accelerators that it's very expensive and you don't produce many many of them and so forth. You know, it's just uh it's a pipe dream I think about space exploration. I'm not sure exactly what he has in mind but uh to me uh it's more a problem of something between biology and uh and uh be literally and information processing. What do you mean? How should I I think human bodies are not well adapted to space even mars even you know, which is the closest thing to kind of human environment that we're gonna find anywhere close by. Uh very very difficult to maintain humans on mars. Uh and we're going to be very expensive and very unstable and but I think the process however uh if we take a broader view of what it means to bring human civilization Mhm. Outside of the earth, if we're satisfied with sending minds out there that we can converse with and actuators and that that we can uh manipulate and sensors that we can get feedback from. I think that's that's where it's at. I think that's so much so much more realistic. And uh and I think that that's the long term future of uh displace exploration. It's not holding human bodies all over the place. And that's that's that's just silly. </s><s>[INST] It's possible that human bodies. Uh So you think you said it's a biology problem. What's possible is that we extend human lifespan in some way. Just we have to look at the bigger picture. It could be just like you're saying by sending robots with actuators and kind of extending the the our limbs, but it could also be extending some aspect of our minds of information. It [/INST] could be cyborgs, it could be uh it could be now we're talking, it could be, you know, it could it could be human brains or cells that realize something like human brain architecture uh within uh uh within artificial environments in our shells, if you like, that, that are more adapted to the conditions of space and uh that so that that's entirely man machine hybrids as well as sort of remote outposts that we can communicate with. I think I think those those will happen. And </s><s>[INST] uh to me there's some sense in which as opposed to understanding the physics of uh the the fundamental fabric of the universe. I think getting to the physics of life, the physics of intelligence, the physics of consciousness will the physics of information uh that that uh that brings uh from which life emerges that will allow us to do space exploration. Yeah, [/INST] well, I think physics in the larger sense has a lot to contribute here, Not the physics of finding fundamental new laws in the sense of another quark or acciones, even the uh but uh physics in the sense of, you know, physics has a lot of experience in analyzing complex situations and analyzing new states of matter, in devising new kinds of instruments that do clever things. We, you know, the physics in that sense has enormous amounts to contribute to this kind of endeavor. But I don't think that looking for a so called theory of everything has much to do with it at all. </s><s>[INST] What advice would you give to a young person today with a bit of fire in their eyes? High school student, college student thinking about what to do with their life. Maybe advice about career or bigger advice about life in general. [/INST] Well, first read fundamentals because they're I've tried to give some coherent, deep advice. That's the </s><s>[INST] Fundamentals, 10 keys to reality by Frank Wilczek. [/INST] So that's a good place </s><s>[INST] to start everywhere. [/INST] If you want to learn what I like, what I can tell you. Uh the </s><s>[INST] is there an audiobook? Yes, [/INST] there is an audio, I think It's, I can get three pieces of wise advice that I think are generally applicable. One is to cast a wide net to really look around and see what looks promising, what catches your imagination. Uh and and promising. Yeah, and those, you have to balance those two things. You can have things that catch your imagination, but don't look promising in the sense that the questions aren't ripe or uh, but but and and things that you in part of what makes things attractive is that whether you thought you liked them or not, is if you can see that this ferment and new ideas coming out that because that's attractive in itself. So, uh when I started out, I thought I was in, when I was an undergraduate, I intended to study philosophy or questions of how mind emerges from matter. But I thought that wasn't really right timing isn't right, The right was the timing wasn't right for the kind of mathematical thinking and uh conceptualization that I really enjoy them and good at. Uh but uh so that's one that cast a wide net look around. Uh and that's that's mm hmm. A pretty easy thing to do today, because because of the internet, you can look, you can look at all kinds of things. You have to be careful though, because there's a lot of crap also, but, you know, you can sort of tell the difference if you if you do a little digging uh the uh so don't don't don't settle on just, you know, what your thesis advisor tells you to do or what your teacher tells you to do, look for yourself and and and get a sense of what, what what seems promising, uh not what seemed promising 10 years ago. Uh they uh so that's one uh another thing is to is kind of complementary to that. Well, they're all complimentary, the complementary to that is to uh is to read history and read the masters of the history of ideas and masters of ideas, I've benefited enormously from as early in my career from reading uh in physics. Uh Einstein in the original and Feynman's lectures as they were coming out and Darwin you know these you can you can learn what it and Galileo, you can learn what it is to wrestle with difficult ideas and how great minds did that, you can learn a lot about uh style, how how to write your ideas up and express them in in in clear ways. </s><s>[INST] And also just just a couple that with, I also enjoy reading biographies [/INST] and biographies similarly right? </s><s>[INST] Like so it gives you the context, context, the human being that created the [/INST] right and brings it down to earth in the sense that you know it was really human beings who did this, it's not. Uh And and they made mistakes and yeah uh also you know I also got inspiration from Bertrand Russell was a big hero and H. G. Wells and yeah so uh read the masters make contact with great minds and when you are sort of narrowing down on a subject, learn about the history of the subject because that really puts in context what you're trying to do and uh and and also gives a sense of community and grandeur to the whole enterprise. Uh And then the third piece of advice is complementary to both those which is sort of to uh to get the basics under control as soon as possible. So if you want to do theoretical work in science you have to learn calculus, multi variable calculus, complex variables, group theory. Nowadays you have to be highly computer literate. Uh if you want to experimental work you also have to be computer literate and you have to learn about electronics and optics and instruments and so get that under control as soon as possible because it's like learning a language uh to do to to produce great works and express yourself fluently and with confidence. Uh it should be your native language. These things should be like your native language. So you're not you're not wondering what is the derivative of this is just part of your, you know, it's it's uh it's in your bones so to speak, you know, and the sooner that you can do that than than the better. So those all those things can be done in parallel and should be. Yeah. Yeah. </s><s>[INST] You've accomplished some incredible things in your life. But uh the sad thing about this thing we have is it ends. Uh Do you um do you think about your mortality? Are you afraid of death? [/INST] Uh Well afraid is the wrong word? I mean uh I wish it weren't going to happen. And I'd like to but uh I think about it. I occasionally I think about, well I think about it very operationally in the sense that uh there's always a trade off between exploration and exploitation. This is a classic subject in computer science actually in machine learning uh that when you're in an unusual circumstance, you you want to explore to see what the landscape is and what gather data, but then at some point you want to use that, make decide make choices and say this is what I'm gonna do and exploit the knowledge you've accumulated. And mm the longer the period of exploitation you anticipate, the more exploration you should do in new directions. And so for me, I've had to sort of adjust the balance of exploration and uh exploitation. And </s><s>[INST] that's a you've explored quite a lot. [/INST] Yeah, well I I haven't shut off the exploitation at all. I'm still hoping exploration uh the exploration, right? I'm still hoping for 10 or 15 years of top flight performance, but the One several years ago now when I was 50 years old, I was at the Institute for Advanced Study and my office was right under Freeman Dyson's office and we were kind of friendly and uh you know, he he found out it was my my 50th birthday. And congratulations. And you should feel liberated because No one expects much of a 50 year old theoretical physicists. And he and he obviously had felt liberated by uh by by reaching a certain age. And yeah, there is something to that. Uh you know, I feel I don't have to catch, I don't have to keep in touch with the latest hyper technical developments in particle physics or string theory or so uh because I'm not gonna I'm really not gonna be exploiting that, but but but where I am exploring uh in these directions of machine learning and, and things like that, and but then, but I'm also concentrating within physics on exploiting directions that I've already established and the laws that we already have in doing things like uh I'm very actively involved in trying to design, helping people, experimentalists and uh engineers even to design antennas that are capable of detecting acciones. So there and that there were deep in the exploitation stage. It's not a matter of finding the new laws that have really, you know, using the laws we have to to to kind of finish the story off. So, so it's complicated, but but but but I'm, you know, I I'm very happy with my life right now and uh I'm enjoying it and I don't want to cloud that by thinking too much that that it's uh gonna come to an end. Uh you know, it's a gift I didn't earn. </s><s>[INST] Is there a good thing to say about why this gift that you've gotten and didn't deserve is so damn enjoyable. So like what's the meaning of this thing of life [/INST] to me interacting with people? I love my family and I have a very wide circle of friends now and trying to produce some institutions that will survive me as well as my work. And uh and it's just, it's how should I say, it's a positive feedback work loop when you do something and people appreciate it and and then you want to do more and they get rewarded. And just how should I say this is another gift that I didn't earn and don't understand, but I have a dopamine system and uh yeah, I'm happy to use it and it seems to get </s><s>[INST] energized by uh by the creative process. But the inspiration [/INST] and </s><s>[INST] all of that started from the little fluctuations [/INST] shortly </s><s>[INST] after the Big Bang frank. Well, whatever the, those initial conditions and fluctuation did, that created you, I'm glad they did. This was uh thank you for all the work you've done for the many people you've inspired for the many of the billion. Most of your ideas were pretty useless of the several billions. But as it is for all humans, but you had quite a few truly special ideas and thank you for bringing those to the world and thank you for wasting your valuable time with me today. It's [/INST] true and it's been a joy and I hope people enjoy it. And I think, you know, the kind of mind expansion that I've enjoyed by interacting with physical reality at this deep level I think can be conveyed to and enjoyed by many, many people. And that's that's one of my missions in life is beautiful. </s><s>[INST] Thanks for listening to this conversation with frank Wilczek and thank you to the information not sweet express VPN blink ist and eight sleep, check them out in the description to support this podcast. And now let me leave you with some words from Albert Einstein. Nothing happens until something moves. Thanks for listening and hope to see you next time. [/INST] </s>

<s>[INST] do the stuff for you. But [/INST] um I I usually just like </s><s>[INST] do stuff myself, [/INST] you're the engineer, </s><s>[INST] the producer [/INST] and </s><s>[INST] the the the artist. Yeah, I guess I would say [/INST] I'm in the era, like the </s><s>[INST] post rick Rubin era, [/INST] like I come from the kind of like um </s><s>[INST] Skrillex [/INST] school of </s><s>[INST] thought, which is [/INST] like where </s><s>[INST] you're you are. Yeah, the engineer producer artists [/INST] like um I </s><s>[INST] mean lately [/INST] sometimes I'll </s><s>[INST] work with a producer now [/INST] I'm </s><s>[INST] gently sort [/INST] of delicately starting to collaborate </s><s>[INST] a bit more, but like, [/INST] I think I'm kind of from the like the whatever, </s><s>[INST] 20 tens [/INST] explosion of </s><s>[INST] things where, [/INST] you </s><s>[INST] know, everything became [/INST] available on the computer and </s><s>[INST] you kind of got this like lone wizard [/INST] energy thing </s><s>[INST] going, you [/INST] embrace being the loneliness </s><s>[INST] is the [/INST] loneliness somehow an engine of creativity. </s><s>[INST] Like, so [/INST] most of your </s><s>[INST] stuff, most of your [/INST] creative quote unquote </s><s>[INST] genius in quotes [/INST] is in the privacy of your mind. </s><s>[INST] Yes, well it was [/INST] um but here's the thing, I was talking to Daniel Ek and he said he's like, most artists, they have about 10 years </s><s>[INST] like 10 [/INST] good years. Um and </s><s>[INST] then they usually stop [/INST] making their like vital shit. Um </s><s>[INST] and I feel [/INST] like I'm sort of like nearing the end of my 10 years on </s><s>[INST] my own [/INST] and so you have to become somebody else </s><s>[INST] now. I'm like, I'm in the [/INST] process of becoming somebody else and reinventing </s><s>[INST] when I work with other people [/INST] because I've never worked with other </s><s>[INST] people. I find that I [/INST] make like </s><s>[INST] that I'm [/INST] exceptionally rejuvenated </s><s>[INST] and making like some of the most vital work I've ever [/INST] made. So because I think another human </s><s>[INST] brain is like one of the best [/INST] tools you can possibly find. </s><s>[INST] Um like, [/INST] it's a funny way to put it. </s><s>[INST] It's like if a tool [/INST] is like, you know, whatever </s><s>[INST] HP plus one, [/INST] or like adds some like </s><s>[INST] stats to your character, [/INST] Like another human brain </s><s>[INST] will like square it instead of like [/INST] adding, adding something double </s><s>[INST] double up the experience points. I love [/INST] this. We should also mention we're playing tavern music before this </s><s>[INST] And which I love, which I 1st 1, I think [/INST] you have to stop the tavern music. </s><s>[INST] Yeah, because it doesn't the, the [/INST] audio, but it </s><s>[INST] makes [/INST] the post added </s><s>[INST] in post, no one will want to listen to the [/INST] podcast, They probably </s><s>[INST] would, but it makes me, it reminds me like a [/INST] video game, like </s><s>[INST] a role playing video game where you have experience points, there's something [/INST] really </s><s>[INST] joyful about wandering places, like elder scrolls, like Skyrim, just exploring [/INST] uh these </s><s>[INST] landscapes in another world, and then you get experience points and you can work on different skills and somehow you progress in life. And I don't know, it's simple, [/INST] it doesn't have some of the messy complexities of life, and there's usually a bad guy you can fight in, in um in Skyrim, it's dragons and so on. I'm sure in Elden Ring there's a bunch of monsters you can fight. I love </s><s>[INST] that. I feel like Elden [/INST] Ring, I feel like this is a good analogy to music production though, because it's like, I feel like the engineers and the people creating these open worlds </s><s>[INST] are, it's [/INST] sort of like, similar to people to music </s><s>[INST] producers, where it's it's like this, [/INST] this hidden archetype that </s><s>[INST] Like no one really [/INST] understands what they do and no one really knows who they </s><s>[INST] are, but they're like, [/INST] it's like the artist engineer, because </s><s>[INST] it's like, it's [/INST] both art and uh </s><s>[INST] fairly complex engineering. Well, you're [/INST] saying they don't get enough </s><s>[INST] credit, aren't you? [/INST] Kind of changing that </s><s>[INST] by becoming the person doing everything french, isn't the engineer? Well, I mean, others [/INST] have gone before me, I'm not, you </s><s>[INST] know, there's like [/INST] timberland and Skrillex and there's all these people, people </s><s>[INST] that are like, you know, very [/INST] famous for this, </s><s>[INST] but but I just think [/INST] the general, I think </s><s>[INST] people get [/INST] confused about what it is and I </s><s>[INST] just don't really know [/INST] what what </s><s>[INST] it is per se. And it's [/INST] just when I see a song like when there's like a hit song like um like I'm just trying to think of like just going for like even just a basic </s><s>[INST] pop hit, like um [/INST] like was it </s><s>[INST] like Rules by [/INST] Dua </s><s>[INST] lipa or something? [/INST] The production on that. It's actually like really crazy. </s><s>[INST] I mean [/INST] the song is also great, but it's like the production is exceptionally memorable, like You know, and it's just like no one </s><s>[INST] I don't even [/INST] know who produced that song. It's just like isn't part of like </s><s>[INST] the rhetoric of how we just [/INST] discuss the </s><s>[INST] creation of art. We just [/INST] sort of like don't </s><s>[INST] consider the music [/INST] producer because </s><s>[INST] I think the music producer used to be more just simply recording things. [/INST] Um </s><s>[INST] Yeah, that's [/INST] interesting because when you think about </s><s>[INST] movies, we talk about the actor and [/INST] the actress is, but </s><s>[INST] we also talk about the direct directors, we don't talk [/INST] about like that with the music </s><s>[INST] as often. The [/INST] Beatles Music producer was one of the </s><s>[INST] first kind of [/INST] got one of the first people </s><s>[INST] sort of introducing crazy sound [/INST] design into pop music. I forget his name, </s><s>[INST] he has the same, [/INST] I forget his name. </s><s>[INST] But um you know [/INST] like that he was doing </s><s>[INST] all the weird stuff like dropping pianos and like, oh [/INST] to get the to get to get the sound to get </s><s>[INST] the authentic sound. [/INST] What about lyrics? </s><s>[INST] You think those [/INST] where did they </s><s>[INST] fit into how important [/INST] they are? I was </s><s>[INST] heartbroken to learn that. Elvis didn't write [/INST] his songs. I was </s><s>[INST] very mad. A lot of people don't write their songs, I understand this, but here's here's the thing. I feel like there's this [/INST] desire for authenticity. </s><s>[INST] I used to be like really mad [/INST] when like people wouldn't write or produce their music and I'd be like </s>

<s>[INST] There's a few qualities about string theory which are weird. I mean a lot of physics is just weird and beautiful. So let me ask the question, what do you is most beautiful boss? String theory? [/INST] Well, what, what attracted me to the theory at the outset beyond its put in gravity and quantum mechanics together, which I think is um it's true claim to fame, at least on paper, it's able to do that. What attracted me to here was the fact that it requires extra dimensions of space. And this was an idea that intrigued me in a, in a very deep way. Even before I really understood what it meant, I somehow had, I mean, talk about sort of the emotional part of consciousness and the cognitive part in some perhaps you call it strange and some strange emotional way. I was enamored with Einstein's general relativity, the idea of curved space and time before I really knew what it meant, it just spoke to me, I don't know how else to say it. And then when I subsequently learned that people had thought about more dimensions of space than we can see and how those extra dimensions would be vital to a deep understanding of the things that we do see in this world. 456 dimensions might explain why there are certain forces and particles and how they behave to me. This was like, amazing, utterly amazing. And then when I learned that strength theory embraced all these ideas, embraced the general theory of relativity, embraced quantum mechanics, embraced the possibility of extra dimensions. Then I was that I was hooked. And so when I was a graduate student, we would just spend hours we I mean a couple of other graduate students and myself who had a sort of worked really well together is at Oxford in England. We would we would work these enormous numbers of hours a day trying to understand the shapes of these extra dimensions, the geometry of them, what those geometrical shapes for the extra dimensions would imply for things that we see in the world around us. And it was it was a heady, heady time. And and that kind of excitement has sort of filtered through over the decades. But I'd say that's really the the part of the theory that I think really hooked me most strongly. Yeah. </s><s>[INST] How are we supposed to think about those extra dimensions? Are we supposed to imagine actual physical reality? Or is this more than space of mathematics that allows you to sort of come up with tricks to describe the four dimensional reality that we more directly perceive, [/INST] no one really knows the answer, of course. But if I take the most straightforward approach to string theory, you really are imagining that these dimensions are there? They're real. I mean, just as you would say that the three space dimensions around us, you know, left, right back forth, up down. Yeah, they're real. They're here we are immersed within those dimensions. These other dimensions are as real as these, with the one difference being their shape and their size differs from the shape and size of the dimensions that we have direct access to through through human experience. And one approach imagines that these extra dimensions are tightly coiled up, curled up, crushed together, if you will, into a beautiful geometrical form that's all around us, but just too small for us to detect with our eyes too small for us to detect even with the most powerful equipment that we have. Nevertheless, according to the mathematics, the size and the shape of those extra dimensions leaves an imprint in the world that we do have access to. So one of the ways that we have hoped yet to achieve to make contact with experimental physics is to see a signature of those extra dimensions in places like the large hadron collider in Geneva Switzerland and it hasn't happened yet doesn't mean it won't happen. But that would be a stunning moment in the history of the species. If data that we acquired in these dimensions gives us kind of incontrovertible evidence that these dimensions are not the only dimensions. Mean how mind blowing would would that be? </s><s>[INST] So with the large Hadron collider, it would be something in the movement of the particles or also the gravitational ways potentially be a place where you can detect signs of multiple dimensions, like something like go, but much more [/INST] accurate in principle. All of these can work. So one of the experiments that we had high hopes for, but by high hopes, I'm actually exaggerating one of the experiments that we imagined might in the best of all circumstances yield some insight. We weren't with bated breath waiting for the result. We knew it was a long shot when you slam protons together at very high speed at the large Hadron collider. If there are these extra dimensions, and if they have the right form, and that's a hypothesis, that may not be correct. But when the protons collide, they can create debris, energetic debris that can, in some sense, leave our dimensions and insert itself into the other dimensions. And the way you'd recognize that is there'll be more energy before the collision than after the collision. Because the debris would have taken energy away from the place where our detectors can detect it. So that's that's one real concrete way that you could find evidence for extra dimensions. But yeah, since extra dimensions are of space and gravity is something that exists within, in fact, is associated with the shape of space, gravitational waves in principle can provide a kind of, you know, cat scan of the extra dimensions. If you had sufficient control over those processes, we don't yet, perhaps one day we will. </s>

<s>[INST] AR and VR, I mean, of course a lot, but the AR is not as obvious, actually. [/INST] Okay, so AR glasses, what are AR glasses? So you take Stampshet Spectacles, Google Glass, Apple's AR kit, Facebook's Oculus Quest 2, or Meta Quest 2, whatever, you put those together. And what do you get? You get something that has the form factor of glasses that you'd wear outside, okay, which can with a tap record or give you terminator vision on something, or with another tap go totally dark and become VR glasses. So normal glasses, AR glasses, VR glasses recording, it's as multifunctional as your phone, but it's hands-free. And you might actually even wear it more than your phone. In fact, you might be blind without your AR glasses because one of the things I've shown in the book early on are floating sigils. Did I show you that? So this is a really important, just visual concept. That right there shows with AR kit, you can see a globe floating outside, okay? Secret societies are returning. This is what NFTs will become. The NFT locally on your cryptophone, if you hold it, you can see the symbol. </s><s>[INST] And if you don't, you can't. By the way, for people just listening, we're looking at a nice nature scene where an artificially created globe is floating in the air. [/INST] Yes, but it's invisible if you're not holding up the AR kit phone. So only you have a window into this artificial world. That's right. And then here's another thing, which shows you another piece of it. And this is using E and S to unlock a door. So this is an NFT used for something different. So the first one was using the NFT effectively to see something, and the second is using the NFT to do something. So based on your on-chain communication, you can unlock a door. That's a door to a room. Soon it could be a door to a building. It could be the gates to a community. It could be your digital login. Okay. Amazing. What this means is basically a lot of these things, which are or like individual pieces get synthesized, right? And you eventually have a digital, just like you have a digital currency, or digital currencies unify concepts like obviously gold, stocks, bonds, derivatives, every kind of financial instrument, plus Chuck E. Cheese tokens, karma, everything that's fungible and transferable. The digital passport unifies your Google-style login, your private keys, your API keys, your NFTs, your ENS name, your domain name, all those kinds of things, and your key card for your door and so on, right? So the AR glasses are what probably, I don't know, it'll be Facebook's version three or version four, Apple is also working on them, Google is also working on them. You might just get a bunch of those models at the same time. It's like predicting the iPhone, just like Dorsey knew that mobile was gonna be big, and that's why he had 140 characters for Twitter, because it was like an SMS code limitation and Twitter was started before the iPhone. AR glasses are an incredibly predictable invention that you can start thinking about the future of social is in part in person, okay? And it also means people might go outside more. Why? Because you can't see a monitor in the sun, but you can hit AR and maybe you have a full screen thing and you just kind of move your fingers or something and you can tap. You have to figure out the gesture. You don't wanna have gorilla arms. Maybe you do have a keyboard outside or just even like a, you could even have a desk like this. If you can touch type, you can imagine something where you look down and you can see a keyboard with your AR glasses and it registers it and then you can type like this, right? And probably you could have some AI that could figure out what you meant rather than what you were doing, right? Okay, so that's AI in social media. That's AR in social media. But really, one last thing I'll say, which is the non-obvious, non-technological part, is I think we'll go from very broad networks, which are hundreds of millions or billions of people like Twitter and Facebook, which have many small communities in them, to much smaller networks that have a million or 10 million people but are much deeper, right, in terms of their affiliation, right? And this is the long-term trend in tech because you're going from eyeballs in the 1980s, I'm sorry, eyeballs in the 1990s, to daily active users in the 2000s, to holders in the 2010s. So you go from just like, oh, I'm just a lookie loo, to I'm logging in every day, to I'm holding a significant percentage of my net worth. And then this decade is when the online community becomes primary, you're a netizen. The digital passport is your main identity. And so this is not, see the problem with Facebook or Twitter is it's a bunch of different communities that don't share the same values fighting each other. This brings us back to the network state where you have one community with shared values, shared currency, and it's full stack. It's a social network and it's a cryptocurrency, and it's a co-living community, and it's a messaging app, and it's a this and it's a that. And it's like Estonia, with a million people, you can actually build a lot of that full stack. </s>

<s>[INST] So it's this portal unconscious. I wonder why you can't. Your portal is not as good to a cat to cast consciousness, then it's a human. Does it have to be have to do with the fact that you're human and just similar organisms organisms a similar complexity are able to create portals better to each other. Or is it just as you get more and more complex, you get better and better portals. [/INST] Well, let me answer 1 1 aspect of it that that are more confident about then I'll speculate on that. Why is why is it that the portal is so bad with protons? Well, and and elementary particles more generally corks, Lipton's and gluons and so forth. Well, the reason for that is because those are just symmetries of space time. More technically, the irreducible representations of the point craig group. It's best time. So they're just literally representations of the data structure of spacetime that we're using. So that's why they're not very much insightful. They're they're just almost entirely tied to the data structure itself. There's there's not much, they're telling you only something about the data structure not behind the data structure. It's only when we get to higher levels that we're starting to in some sense, build portals to what's behind space time. </s><s>[INST] Sure. Yeah. So there's more and more um complexity built on top of the interface of space time with the cat. [/INST] So you can actually build a portal. </s><s>[INST] Yeah. Right. Ah yeah. This interface of face and hair and so on. Mhm skin. There's some sinking going on between humans though. Well, we think like [/INST] you're you're getting a </s><s>[INST] pretty good representation of the ideas in my head and starting to get a foggy view of my memories in my head, even though, you know, this is the first time we're talking, you start to project your own memories. You start to solve like a giant hierarchy of puzzles about a human because we're all there's a lot of similarities, a lot of it rhymes. So you start to make a lot of inferences. You build up this model of a person, You have a pretty sophisticated model, what's going on underneath? Again, I just um I wonder if it's possible to construct these models about each other and nevertheless be very distant from an underlying reality. [/INST] There's a lot of work on this. So there's some interesting work called signaling games where they they look at how people can coordinate and uh come to communicate. There's some interesting work that was done by some colleagues and friends of mine louis Narron's Natalia Komarova and Kimberly Jamison where they were looking at mm evolving color words. So you have a circle of colors, The color circle and they wanted to see if they could get people to cooperate and how they carved the color circle up into units of words. And so they had a game theoretic kind of thing that they had people do and what they found was that when they included. So most people are tricky mats, you have three kinds of cone photoreceptors. But there are some lot of men, 7% of men have our diplomats. They might be missing the red cone photoreceptors. They found that the documents had an outsized influence on the final ways that the whole space of colors was carved up and and labels attached. You needed to be able to include the decree mats in the conversation. And so they had a bigger influence on how you made the boundaries of the language. And I thought that was a really interesting kind of insight that that there's going to be again, a game, perhaps a game where evolutionary or genetic algorithm kind of thing that goes on in terms of learning to communicate in ways that that are useful. And so yeah, you can use game theory to to actually explore that are signaling games. There's a lot of brilliant work on that. I'm not doing it, but there's work out there. </s><s>[INST] So if it's okay, let us tackle once more and perhaps several more times after the big topic of consciousness. This this very beautiful, powerful things. That perhaps is the thing that makes us human. What is it? What's the role of consciousness in? Um, let's say even just the thing we've been talking about, which is the formation of this interface. Um, any kind of ways you want to kind of start tracking and talking about it. [/INST] Well, let me say first, what most of my colleagues say 99% are again assuming that spacetime is fundamental particles in space time matter is fundamental and most are reductionist. And so the standard approach to consciousness is to figure out no what complicated systems of matter with the right functional properties could possibly lead to the emergence of consciousness. That's the general idea. Right? So maybe you have to have neurons. Maybe only if you have neurons, but that might not be enough. They have to certain kinds of complexity in their their organization and their dynamics, certain kind of network abilities, for example. So there's there are those who say for example, that consciousness arises from orchestrated collapse of quantum states of micro tubules in neurons. So this is hammer off and Penrose have this kind of So it's it's a you start with something physical property of quantum states of neurons of micro tubules and neurons. And you say that somehow an orchestrated collapse of those is consciousness or conscious experiences or integrated information theory. Again, you start with something physical and if it has the right kind of functional properties, that's something they call fee with the right kind of integrated information. Then you have consciousness. Or you can be a pan sickest Philip cough for example, where you you might say well in addition to the particles in space and time, those particles are not just matter. They also could have say a unit of consciousness. Um and so but once again, you're taking space and time and particles is fundamental and you're adding a new property to them. See consciousness and then you have to talk about how when a proton and neutron where proton and electron get together to form hydrogen, then how those consciousnesses Merge two or interact to create the consciousness of hydrogen and so forth. Um, there's attention schema theory, which again, this is how neural network processes representing to the network itself. It's attentional processes that could be consciousness. Um, there's global workspace theory. Uh, and you're on a global workspace workspace theory. So there's many, many theories of this type. What's, what's common to all of them is they assume that spacetime is fundamental. They're still physical processes and spacetime is fundamental. Panpsychism adds consciousness as an additional thing, is almost duelist in that regard. And my attitude is our best science is telling us that space time is not fundamental. So why is that important here? Well, for centuries, deep thinkers thought of earth air, fire and water as the fundamental elements. It was a reductionist kind of idea. Nothing was more elemental than those. And you could, you could sort of build everything up from those. When we got the periodic table of elements, we realized that, um, of course we want to study earth, air, fire and water. There's combustion science for fire, there's, you know, um, there's sciences for for all these other things, water and so forth. So we're gonna do science with these things. But but fundamental. No, no, if you're looking for something fundamental, those are the wrong building blocks Earth has many, many different kinds of elements that project into the one thing that we call Earth, if you don't understand that there's silicon that there's iron, that there's all these different kinds of things that project into what we call earth. Your you're hopelessly lost. You, you're not fundamental, you're not going to get there. And then after the periodic table, then we came up with quirks, Lipton's and gluons, the particles of the standard, you know, the standard model of physics. And and and so we actually now know that if you really want to get fundamental Yeah, the periodic table, isn't it? It's good for chemistry. It's just wonderful for chemistry. But if you're trying to go deep fundamental, what is the fundamental science? That's not it? You're gonna have to go to cork's Leptin and gluons and so forth. Well now we've discovered spacetime itself is doomed. Quirks, Lipton's and blue ones are just irreducible representations of the symmetries of space time. So, the whole framework on which consciousness research is being based right now is doomed. And for me, these are my friends and colleagues that are doing this. They're brilliant. They're brilliant. I my feeling is I'm so sad that they're stuck with this old framework because if they weren't stuck like with Earth air fire and water, you could actually make progress. So it doesn't matter how smart you are, if you start with Earth, air fire and water, you're not gonna get anywhere right </s>

<s>[INST] Think Bitcoin. So first of all, let me state that Charles for the most part is purely objective. The bias that comes in for the record, I want to say that I have heard, because you mentioned the mafia, that you prefer good fellows over the godfather. So a man who prefers good fellows over godfather, you take it for that opinion for what it is. I actually have to think about that one for quite a bit. I think- Oh, come on. Joe Pesci was so good at that. He's incredible. I also love casino and those big glasses on De Niro. I love it with Sharon Stone. But we could talk about that for hours. But let me ask you about the Bitcoin conference. Cause it is kind of a, I would say an important moment in human history. It was quite exciting in terms of size and kind of turmoil and all those kinds of things. And you were there in, what is it? Hot and human Miami. I believe it's the way you introduced it. So what do you make of the community of Bitcoin [/INST] or that particular event in human history? Oh, come on. Joe Pesci was so good at that. What makes me sad is I remember the old Bitcoin community and I've seen what it's become. And the old community was really fun. Like the San Jose conference in 2013 or subsequent conferences. There was just a lot of people. They had no money. And they just really love this idea of the decentralized money. They love this idea of decentralization in particular. And you could strike up a conversation with everyone. There was no ego at all. But what was really fun is you could really get intimate friendships and relationship, great conversations with people there. It's kind of like the early days of AI, the all men Dartmouth and all these other places a very intimate, there was no egos, everybody was just trying to do some really cool stuff. Now, just like those early days, there was an overestimate of how robust the solutions would be. So we believed, oh yeah, 10 years we're gonna rule the whole world, right? Didn't exactly happen. On the other hand, Bitcoin grew from nothing in just 11 years to, I'm in Mongolia riding camels and the camel herder has Bitcoin and there'll be desert. So that's telling you that's a pretty pervasive technology if you have that level of adoption that quickly. When I went to Miami, it was unrecognizable. Everything was so commercial. Half of the vendors at the conference were like watches that would cost half a million dollars and they were covered in diamonds. So when you see that kind of materialism leak its way in, its first is repulsive. The other thing was there was no, like I remember one of the first conferences, Mo Levin's conference in January of 2014, the North American Bitcoin Conference, ironically in Miami, there was a Bitcoin Help Center booth. Dima ran it and a few of the other Bitcoin OG's ran it. And the core developers actually came over, like Jeff and others, who were there and sat at the booth and anybody come up and ask a question. Anything you wanna ask about Bitcoin. It was like, that was the culture. Just help people, welcome. And there was no help booth there. There was no notion of that. There were six hour lines and superstars and things like that. And again, again it was always the same thing. Look how much money all these people have made. And the whole point of Bitcoin was to redefine the notion of money. redefine the notion of value, you know, these types of things. So it just, I'm no longer part of that. And it made me sad because I really enjoyed being part of the, how I got started was Bitcoin Education Project. I did a class on Udemy, I gave it away for free. I had 80,000 students and they would email me. I got 5,000 emails before I stopped answering them. And everyone come in and ask me some question about something sometimes arcane, sometimes trivial. And I take the time to sit down and answer the question or for the email to somebody I knew who could answer that particular type of question. And there were some amazing people in the early days like Mike Hearn and Gavin and others. And they were just super committed. And Mike's case, he knew Satoshi. He actually emailed them back and forth because he was around 2009, 2010. He did the Bitcoin Java client and Satoshi was all excited. He said, oh wow, Bitcoin can come to a cell phone. This is really cool and exciting. And then what happened? Mike left Bitcoin in 2013 over the whole big block debate that happened. They just treated him like dirt, like he was subhuman or something. So I don't know, the culture has changed a lot. And if they like it, it's good for them. They can enjoy their religion, but it's not for me. And where I like being is, like I had a guy who used to work for me, Alex Chirpinoy. And he created this beautiful project called Ergo. To me, that is the spiritual successor to Bitcoin. Ergo is really special because it has the same culture. It has the same mentality. And the technology is kind of like a natural evolution of what you would do if you knew about Bitcoin and you wanted to build the next big thing. So it's still a proof of work system. It's still a UTXO system, but he added UTXO with some smart contracts. It's this Sigma protocol idea. On the proof of work side, Satoshi had this one CPU, one vote idea. So Alex tried to create non-osable puzzles to make it impossible to have mining pools. And there's all these other beautiful little things. And he's this brilliant Russian programmer and he surrounded himself with all these other brilliant people. He has zero ego. He's like, he has negative ego. When you put up with a person with ego, your ego goes down, right? And everything about Alex is always like, how do I solve this? How do I do that? And he gets legitimately excited when he meets somebody that he can collaborate with or learn from. That's where Bitcoin was in the beginning. Everybody set their egos aside, whether it was Hal Finney or whatever, and they would just say, how can I help? What can I do? And it was all about coming up with some cool new thing or solving some cool new problem. </s>

<s>[INST] So let me return just briefly and the point maybe movie her. So do you think if we look farther into the future? He says so much of the benefit from making our technology more uh empathetic to us, human beings would make them better tools empower us to make our lives better. But if we look farther into the future, do you think we'll ever create an ai system that we can fall in love with and loves us back on a level that is similar to human to human interaction like in the movie Her or beyond. [/INST] I think we can simulate it in ways that could, you know, sustained engagement for a while, would it be as good as another person? I don't think so. For if if you're used to like good people now, if you've just grown up with nothing but abuse and you can't stand human beings, can we do something that helps you there that gives you something through a machine? Yeah. That's pretty low bar, right? If you've only encountered pretty awful people uh if you've encountered wonderful amazing people were nowhere near building anything like that. And I'm I I would not bet on building it. I would bet instead on building the kinds of ai that helps all helps kind of raise all boats. That helps all people be better people helps all people figure out if they're getting sick tomorrow and helps give them what they need to stay well tomorrow. That's the kind of a I want to build that improves human lives, not the kind of ai that just walks on the tonight show and people go, wow, look how smart that is, you know, really like. And then it goes back in a box, you know, </s><s>[INST] so on that point, if we continue looking a little bit into the future, do you think in ai that sympathetic and uh does improve our lives need to have a physical presence of body. And even let me cautiously say the C. Word consciousness and even fear of mortality. So some of those human characteristics, do you think it needs to have those aspects? Or can it remain simply machine learning tool that learns from data of behavior that that learns to make us based on previous patterns feel better? Or doesn't need those elements of consciousness? [/INST] And it depends on your goals? If you're making a movie, it needs a body, it needs a gorgeous body, it needs to act like it has consciousness. It needs to act like it has emotion, right? Because that's what sells, that's what's gonna get me to show up and enjoy the movie? Okay. Um in real life doesn't need all that. Well if you've read Orson scott Card Ender's game, speaker for the dead, you know, it could just be like a little voice in your ear ring, right? And you could have an intimate relationship and it could get to know you and it doesn't need to be a robot. Uh But that doesn't make this compelling of a movie, right? I mean we already think it's kind of weird when guys looks like he's talking to himself on the train. You know, even though it's earbuds. So we have these embodied is more powerful, embodied. When you compare interactions with an embodied robot versus a video of a robot versus no robot. Uh The robot is more engaging. The robot gets our attention more. The robot when you walk in your house is more likely to get you to remember to do the things that you asked it to do because it's kind of got a physical presence. You can avoid it if you don't like it. It could see you're avoiding it. There's a lot of power to being embodied. There will be embodied a eyes. They have great power and opportunity and potential. There will also be a I. S. That aren't embodied. That just our little software assistance that help us with different things that may get to know things about us. Will they be conscious? There will be attempts to program them to make them appear to be conscious. We can already write programs that make it look like. What do you mean? Of course I'm aware that you're there. Right. I mean it's trivial to say stuff like that. It's easy to fool people. But does it actually have conscious experience like we do? Nobody has a clue how to do that yet. That seems to be something that is beyond what any of us knows how to build. Now. Will it have to have that? Uh I think you can get pretty far with a lot of stuff without it. Um Will we accord it writes? Well, that's more a political game that it is a question of real consciousness. </s><s>[INST] Yeah. Can you go to jail for turning off Alexa is what? Uh It's a question for uh an election maybe a few decades from? [/INST] Well, Sophia robots already been given rights as a citizen in Saudi Arabia right? Even before women have full rights, then the robot was still put back in the box to be shipped to the next place where it would get a paid appearance, right? </s><s>[INST] Yeah. It's dark and almost comedic, if not absurd. So I've heard you speak about your journey and finding faith. Uh And how you discovered some wisdoms about life and beyond from reading the bible. And I've also heard you say that you said scientists too often assume that nothing exists beyond what can be currently measured [/INST] uh Materialism. Materialism sciences. Um </s>

<s>[INST] So your academic accomplishments, all the papers, you're one of the most cited people in the world. All the breakthroughs I mentioned in computer vision and language and so on is what is the source of happiness and [/INST] pride for you. I mean all those things are a source of pride for sure. I'm very grateful for having done all those things and it was very fun to do them. But happiness comes from but you know you can happiness well my current view that happiness comes from our to a lot to a very large degree from the way we look at things, you can have a simple meal and be quite happy as a result. Or you can talk to someone and be happy as a result as well. Or conversely you can have a meal and be disappointed that the meal wasn't a better meal. So I think a lot of happiness comes from that, but I'm not sure I don't want to be too confident. I </s><s>[INST] being humble in the face of the uncertainty, it seems to be also part of this whole happiness thing. Well, I don't think there's a better way to end it than uh meaning of life and discussions of happiness. So alia, thank you so much. You've given me a few incredible ideas, you've given the world many incredible ideas. I really appreciate it. And thanks for talking [/INST] today, you know, thanks for stopping stopping by, really enjoyed it. </s><s>[INST] Thanks for listening to this conversation with aliens discover and thank you to our presenting sponsor, Cash up. Please consider supporting the podcast by downloading cash up and use the Code Lex podcast. If you enjoy this podcast, subscribe on Youtube, review five stars on apple podcast, support on Patreon are simply connect with me on twitter at lex Friedman and now let me leave you with some words from Alan turing on machine learning instead of trying to produce a program to simulate the adult mind. Why not rather try to produce one which simulates the child's if this were then subjected to an appropriate course of education, one would obtain the adult brain. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] No, it's uh I mean it has a sense like the Stranger by camus has a sense of like this is how life is and it's like has more about old age and that you're not quite the man you used to be feeling of like this is how time passes and then the passing of time and how you get old, you get older and this is one last fish. It's less about this is the fish, It's more like this is one last fish, like and asking who was I, who was I As a man, as a human being in this world. And this one fish helps you ask that question fully. [/INST] Wonderful. It's one fish which is just sort of all the other fish to write. And and that is a big difference because for for ahab, no other fish will do that movie Dick. It's got to be the biggest, the most powerful, the most tormenting. It's got to be the one that you've got history with that has filed you. And it's uh it's a raucous ride movie, Dick. What about David </s><s>[INST] Foster Wallace. So why is he important to you in the search of meaning? Uh in a secular age? [/INST] Good. So, so I'll just, just to finish the movie Dick thing, I think what's interesting about Melville is that he thinks our salvation comes, not if we get in the right relation to monotheism or Christianity, but if we get in the right relation to polytheism to the idea that there's not a unity to our existence, but there are lots of little meanings and they don't cohere sometimes, you know, uh like in like in Homer, sometimes you're in Love Helen's in love with paris and they do crazy things, they go off and run away and the Trojan war begins and sometimes you're in a Battle Fury that love is Aphrodite's realm and the Battle Fury, that's Aries realm and that's a totally different world. And they're not even I mean they're related, there is a kind of family resemblance but not much. Mostly you're just in different sort of local, meaningful worlds. And Melville seems to think that that's that's a thing that we could aim to bring back. He says we have to lure back the mary made a gods of old and and lovingly and thrown them in the now egotistical sky. The now on haunted hill. That's what we live in this world, where hills aren't aren't haunted with significance anymore. And the sky is just a bunch of stuff that we're studying with physics and astrophysics and stuff, but they used to be all inspiring and we have to figure out how to get in that relation to them, but not by trying to give a unity to our existence through developing habits and practices that get written on our body. And so his is about the end of Judeo Christianity and the sort of roman appropriation of it in Wallace. What one of the things I think is so interesting about him is that I think he has a great observer of the contemporary world and he's a very funny writer. It is really funny, but he's a great observer, the of the contemporary world, what he thought was at the core of the contemporary world. Was this constant temptation to diversion through entertainment. That's a different story than Heidegger story about efficiency and optimization. But it's the other side of it? Like what is this temptation temptation sort of diverting us from the ability to be more efficient? So, you know, you're attempted to go, you know, watch some stupid film or television show or something that's dumb and not really very interesting. But you read that temptation is a temptation precisely in virtue of its taking you away from your optimizing your your existence. And so I think there are two sides of the same coin. I think he's brilliant at describing it. I think he thought it was a desperate position to be in that. It was it was something that we needed to confront and find a way out of And his characters are trying to do that. And I think there's two different David Foster Wallace is one. I mean, David Foster Wallace committed suicide and when I, and it's very sad and he clearly did have, you know, sort of there was a physiological basis to his condition. He knew it. He was treating it from decades with medication. He had electroshock therapy a number of times. It's just very, very sad story when I decided that we were going to write about David Foster Wallace. The first thing I was worried about is what can you, can you like obviously a motivating factor may be the motivating factor in his committing suicide? Was his physiological condition? Um, but there was there's there's this, there was a question, could you think, I mean, he's obsessed with the condition with what we need to do to achieve our salvation, to live well, to make our lives worth living. And he clearly in the end felt like he couldn't do that. So in addition to the physiological thing, which probably most of it, the question for me was could you find in his writing what his, what he was identifying as the thing we needed to be doing that he nevertheless felt we couldn't be doing. And and he talks as if that's that's the difficulty for him. Uh, so, so that that's one side of him and I did want to find that. I think there's another side of him that's very different. But you were gonna </s><s>[INST] ask please, what's the other side? [/INST] I mean, what I write about in the, in the chapter mostly, um is what I think he's got as are as as our saving possibility, he thinks are saving possibility. He says this in a graduation speech that he gave to Kenyan, is that um we have the freedom to interpret situations however we like. So what's the problem case for him? He says, look, you know, the problem case, we have, we have it all the time. You get pissed off into the world. You know, some some big suv cuts you off on the highway and you pissed off and you might express your anger with one finger or another directed at that person and he says, but actually, you know, you're being pissed off as the result of your having made an assumption. And the assumption is that that action was directed at you. Like the assumption is that you're the center of the universe and you shouldn't assume that. And the way to talk yourself out of it, he says, is to recognize the possibility. Maybe that wasn't an action directed at you. Like maybe that guy is racing to the hospital, you know, to take care of his dying spouse who's been there suffering, you know, from cancer or maybe he's you know, on the way to pick up a sick child or maybe he's and it's not an action director. That was your assumption, not something that was inherent in the situation. And I think there's something interesting about that. I think there's something right about that at the same time, I don't think he speaks as if we can just spin out these stories and whether they're true or not, doesn't matter what matters is that they free us from this assumption. And I think they only free us from this assumption if they're true. Like sometimes the guy really did directed at you and that's part of the situation. And like you can't pretend that it's not part of the situation. You have to find the right way of dealing with that situation. So you have to listen to what's actually happening and then you have to figure out how to make it right. And I think he's he thinks that we have too much freedom. He thinks that you don't have to listen to the situation, you could just tell whatever story you like about it and I think that's actually too tough. I don't think we have that kind of freedom. And he and he writes these sort of incredibly moving letters when he's trying to write The pale King, which is the end of which is the unfinished novel that really sort of drove him to distraction. At the center of the novel is this character who was one of the characters at the center of the novel is a guy who's doing the most boring thing you could possibly imagine he is an I. R. S. Tax examiner, he's going over other people's tax returns trying to figure out whether they follow the rules or not. And like just the idea of doing that for eight hours a day is just terrifying. And and he puts this guy in an enormous warehouse that extends for miles where a person after person after person is in rows of desks, sort of nameless each of them doing this task. So he's in nowhere doing nothing. And it's got to be intensely boring. And now the main character is trying to trying to teach himself to do that. And the question is how do you put up with the boredom? How do you put up with this onslaught of meaninglessness and the main character is able to confront that condition with such bliss that he literally levitates from happiness while he's going over other people's tax returns. And I that's that's my metaphor for what I think Wallace must have imagined. We have to try to aspire to, and I think that's unlivable. I think that's not I think that's not an ambition that we could achieve. I think there's something else we could achieve. And the other thing that we can achieve that, I think is is is something that he also is onto but doesn't write about as often is something more like achieving peak moments of significance in a situation when something great happens. And he writes about this in an article about Roger Federer, he loved tennis, Are you a tennis lover? </s>

<s>[INST] like Opto electric brain computer interfaces, which by the way, there's efforts on the computing side to build Opto electric uh servers. So like what you have both electricity. So, because optics is really interesting. Light is a very interesting method of communication. That's like you said, our thoughts going on in many ways, he doesn't have some of the constraints of Ben with that electricity does going through wires. But you're able to but it's less ability to control precisely at scale. So like there's challenges and there's benefits. And having those two interplay is really, really, really fascinating. Especially one obviously on the other side of your signal is a biological mush mush mushy mesh. [/INST] Well, the mushy mesh is kind of interesting because we have there are problems with light light scatters in the brain so that the photons don't just go, you know, literally through they whenever they hit an interface between fat and water lipid and water, they they bounce off in different directions. And so you can come in with all the resolution you want. You could play in an incredibly detailed high resolution pattern of light, but the photons start scattering quite quickly and by the time you've gone a couple of millimeters deep you've lost almost all that fine spatial information. So, but we've developed workarounds, the longer wavelength light you use, if you get into the infrared, there's less scattering. You can use two photons methods or three proton methods where the photons have to arrive all together at the same time. You can put in fiber optics, we developed these fiber optic methods in 2007 where you can access these deep structures with, with fiber optic methods and you can put many of these fiber optics at the same time in an animal. We've used a holographic methods. three D Holograms to play in hundreds of individual cell sized spots of light and we can and we can change those quickly. And so there are a lot of tricks, a lot of interesting optics engineering that has come together with neuroscience in a pretty exciting way. </s><s>[INST] Well that is engineering to it was just super, super, super excited I shouldn't mention because I remember mentioned Elon. Um I recently got for the first time ever got Covid. Um how did I go so long without the finally so I'm all vaccinated and everything like that. And so I got uh because I think he he mentioned it publicly so I can mention it but I won't mention anybody else involved. But hanging out we all got together and got Covid. And the interesting thing about maybe you can comment about this. So I was only sick for like a half a day. I got a fever of like 104 just went, oh and then crashed and then I was, now maybe I'm just seeing the silver lining of everything. But afterwards I have like a greater clarity about the world. Maybe maybe I just it was so uh maybe so intensely the mind fog kind of thing for such a short amount of time. But the people weren't involved were also reporting this. It's kind of interesting because like because I do know like the immune system uh is involved with the brain in very interesting ways. So like the human mind also incorporates all these other, it's not just the it's not just the nervous system. And I just wonder because everyone always says, no, not like everyone always says like Covid does all these bad things or whatever the diseases or whatever the virus. But I wonder like I hate to be a steven pinker on this. But like I wonder what the benefits of certain diseases are if you're able to recover like what is there some like uh again, don't want to romanticize it. But if your system goes to some kind of hardship and you come out on the other end, I wonder sometimes if there's a greater um maybe killed off a bunch of neurons that didn't need anyway. And they were actually getting in the way there were the hater neurons. Your [/INST] inner critic that I was talking </s><s>[INST] exactly, killing [/INST] off your critic. </s><s>[INST] Well, you [/INST] know, there are mechanisms for what the potential mechanisms for what you're talking about. There are there's actually been a fair bit of research on post covid neurological function. Actually, my wife Michelle Manji, who's at stanford, she's done a lot of this work, Akiko Iwasaki at Yale has done a lot of this. But what what they found is that there's a loss of Myelin, this is the coding of those long range projections that go from one part of the brain to another. Myelin is this sort of insulator that coats these long range projections and makes the impulses go faster and more reliably and there's altered ah function of the myelin producing cells and altered Myelin in the case of Covid, they've looked in both mouse and human brains and but of course it could be very idiosyncratic. Many people have cognitive problems post covid. And you're you're definitely aware of that. So many people report this persistent brain fog inability to function, but it depends on where the inflammation was. You know, maybe the people who have dysfunction post covid, they had a global effect. Maybe you lost some of these projections that were restraining you in some way and and these plausibly exists? And it's known that there are cell populations in the prefrontal cortex that actively restrain deeper structures from expressing what they do? And it's it's theoretically possible that you had a lucky uh </s><s>[INST] Somebody has to get lucky right. [/INST] Somebody has to get lucky. </s>

<s>[INST] Is that in part just not allowing yourself to have um to have to ever ever [/INST] quit. </s><s>[INST] I have one other thing I regret, I remember like a blue belt [/INST] match, </s><s>[INST] remember I'm not gonna say who it was against but uh I remember just being extremely exhausted and um just constantly fighting. A guy was really good mount really good guard passing and I just remember him passing my guard eventually it was just like the finals of one of the I BGF tournaments and then right away going to mount [/INST] and </s><s>[INST] just, [/INST] I </s><s>[INST] don't know, I, the level of frustration, I mean I quit at that point because I remember that still like I it's not about losing, winning or losing, but I just remember, I was like, I was like teary eyed frustrated. And then I knew there was a lot of fight, still left in there somewhere and I I quit and I regret that to this day is uh I think the reason I regret that is because it gave me an option to now quit in every other aspect of life like that. This is an option. [/INST] No, it is, </s><s>[INST] it sucks. [/INST] It teaches you, you know, it makes us stronger. </s><s>[INST] I think it [/INST] made you stronger. </s><s>[INST] Yeah, it makes you stronger than you did that to learn that. Don't do that again. Um But still, like you said, just going to sleep in training, [/INST] I do </s><s>[INST] think it made me weaker, it didn't make me weaker and the rest of my life to that, those, you know, I've quit a few times in my life on small things and you realize, okay, it's not that big of a deal, it's fine, like, who cares? Um but that what you learned over time is that voice always comes there. Like, uh obviously, maybe it does for you to even at the highest level of like, it's not that big of a deal. Like it's okay to quit here. Like, it makes sense. Everybody would understand um [/INST] you </s><s>[INST] know, in some sense, like, you're, you know, many people would say you're past your prime in this match with the protester. Like, it makes sense. You've been focusing on M M A makes sense. Makes sense to lose. Yeah, I don't know that that's a weird voice and in some sense, uh it's that voice and the voice that says like, why are you doing this? Like this is silly. That doesn't make any sense to just stop, just stop. Just stop and shutting that voice down and never allowing yourself to quit. That's a really powerful thing. Like everybody, I've met everybody that's successful. Um Yeah, Down to the even engineers, ceos Elon musk just never quitting. Like when everybody around you, it says quit, Never quitting. It's weird. I don't know what that is might be genetic, it might be like using the stubbornness to just never allow yourself to um developed that basically developing a cal Asus to that voice that tries to tell you to quit. You never quit. [/INST] Huh? What </s><s>[INST] would you attribute that to? [/INST] It's like how much you want to get to the destination you chose? Like, you know, it's how badly you want to get there if you quit, you're never going to get there </s><s>[INST] and you always wanted [/INST] to. </s><s>[INST] Is there some thing you remember from that match? Some things that happened before and after they stand out to you just since in rio [/INST] Yeah, there was an interview, you know, like prior to the fight. You know, there was a big fight. We don't like media every day before we me, you know, me and him were meeting for media and like five days before, you know, 56 days before I'm quite chatty, it's, you know, the closer we get to defy, the more focus I get, the less I talk, </s><s>[INST] stop joke [/INST] around playing, you know, with people. But I remember, I think it was maybe three or four days before we were doing the interview together, </s><s>[INST] I think [/INST] my cousin Kara was that she was doing one of the interviews with us, and I don't remember exactly what we were talking about, but I just remember we're talking about the fight of course, and then it was, you know, we're standing beside each other and I'm like, and then, you know, suddenly I jumped in and grabbed him by the </s><s>[INST] neck. I said [/INST] I'm gonna tap you by the neck and then he was like, you know, very shy and then I let go, so you know, I'm gonna grab you by the arm and I could feel he was like, he wasn't comfortable comfortable, you know, with being there. That was, you know, me saying that I'm gonna tap him out there was like, I was so relaxed, joking about it, but I'm joking that I'm gonna tap him out in a fight, that we're gonna have him for days time and yeah, I felt it was like not comfortable at all, do </s><s>[INST] you think you got in his head a little bit to give you a little bit of confidence? [/INST] You </s><s>[INST] said that judges is a reflection of your personality, so both your digits and your personality, there's a calmness. What is that? Why are you so calm? Is there in like an ocean underneath that's boiling? Is this developed or is this your personality? Are you basically leveraging who you are already to develop a game around the jets or the digits and make you calm? [/INST] I think both, I was always very calm since I was a kid, you know, since very young, I was never very, you know, fiery person. So that is a reflection, you know, you reflected on my producer in my life, on my fights to fight. So it's a direct influence of my personality and I think it's also in the day, you know, you develop, the more, the more you practice, the more you fight is like, you know, you don't want to get nervous, you don't want the adrenaline and so you just learn how to shut that off from your mind. So the less I thought about it, you know, it's like how many times I thought, you know, let's say the week before the fight, that's when you start more, when you're concerned the most, because now it's getting very close before it's just far away, you know, it's, it's normal to think of the tournament, you get a bit nervous, but it goes away quick, but the fight, you know, the week before now you're constantly thinking of that day and every time you think adrenaline pumps in your heart accelerate, you know, it doesn't, you know, it makes it, it's like why am I feeling this? What difference will it make? So you kind of, you sharing that thought out of your mind because you don't want to feel the adrenaline, your heart accelerating, it's not gonna add you anything. So it's, you know, it's the practice also that I think I helped me to shut that off my mind because </s>

<s>[INST] If I could ask your sort of take your opinion of the different UFO sightings that the D. O. D. Has released videos on. So what do you think about the Tic Tac Ufo that David favor and others have cited that [/INST] such you know, truly anomalous experience? Um I can't I can't I do like mental models in my head to find potential solutions to discredit that right? Like as much as I try right just as a logical process as a practice. I can't I can't pick it apart in the way that we were just talking about a moment ago about you know thousands of drones being like sent up in very tricky manners, right? I can't really bring myself to a clever solution that you know, other than just saying the pilots are lying or is there, you know, and I believe you know, I know dave favor you know I consider him a friend. We talk a lot. I have 00 reason to disbelieve anything he says. </s><s>[INST] Yeah I agree with you. Uh but in terms of the actual Ufo is there something anomalous and interesting to you about that particular case. Maybe. Um One interesting aspect there is how much do I understand about the water surface and underwater aspects of these UFOs it seems like a lot of the discussions about is about the movement of this particular thing. That seems to be weird. Anomalous. Seems to defy physics. But what about stuff that's happening underwater? That's interesting to me. If I had advanced technology, I would certainly like to operate in part underwater because you can hide a lot of stuff there, you [/INST] think it would be somewhat as easy as traveling through Interstellar space at least. </s><s>[INST] Right. [/INST] Um you know, I wish I had a great answer for that, but as an aviator, that's a kind of a black box for us, you know, we don't have great what I would call cross domain tracking, right? I can't see something go underwater and then follow it underwater. </s><s>[INST] So it's literally not your domain like underwater, Like leave that for somebody else. [/INST] Yeah, and you know, I I use that terminology because it's it's kind of important, right? Um Cross domain tracking is something that we haven't had to necessarily worry about, right, because airplanes operated in the air and submarines operated underwater and space planes operating space, right? But you know, there's gonna be, you know, that's gonna blur, I think as as we move along here, especially in the air and space regime uh and being able to perhaps transition my radar contact at 40,000 ft to another radar system that can track it up to 200,000 ft, you know, that might be a value. And so we we seem to be missing that right now. </s><s>[INST] So what about the go fast? And the gimbal videos that you mentioned earlier there was like, what's interesting there to you? So [/INST] the gimbal, I'll talk about that one first. I was airborne for that one. Um the person that record, it was a good friend of mine, but I mean both aircrew, I knew both of them, but the wizard himself, very close friends, went through a lot of training together, went to the same fleet squadron. Uh he ended up transitioning to be a pilot and then came to where I was instructing. So I got to instruct him a bit on his transition. Um and you know, the way that was, was was we went out on a air to air training mission. So stimulating air fight against our own guys, they're acting like the bad guys and kind of go head to head against each other. And when we fly on those missions, we all fly out together more or less. We set up and then we kind of try it from the fight as we either, you know, run out of gas or something happens. And so people usually go back onesies or twosies. Uh and so the aircrew that recorded the gimbal, they were going back to the boat and we were on what's called the work up training event. And so this is like a month on the boat where we're essentially conducting more time operations, more or less uh stress ourselves out and to kind of do the last training block before we go on deployment essentially. So it's, it's pretty high stress. Uh they actually do send aircraft from like land bases to kind of try to penetrate and were expected to go intercept them. And so we're kind of practicing like we play. And so he saw these objects on the radar, um, the Gimbal and a a fleet of other aircraft or vehicles and they initially thought it was part of the training exercise that they were sending something in to try to penetrate the airspace. Um, and so they, you know, they flew over to it and as they got close enough to get on the flare, um, you know, I think everyone has heard the reaction. Um, and they realized that it wasn't something they were expecting to see </s><s>[INST] can actually describe what's in the video. What's the reaction, in case they haven't seen it? [/INST] Yeah, a lot of swearing. But so what you see on the flare footage is a black or white, depending when you look at it, object that's somewhat shaped like a gimbal, it appears almost as if someone put two plates together. And then there seems to be almost like a small funnel of higher energy that's at the top of the bottom of those plates in a sense. So almost as if, you know, there's a stick going in between two plates, but not that pronounced right? So there's an energy field that kind of went to a funnel on the top and the bottom at least, that's how it's being portrayed on the flare. Um There's a lot of conversation about that being glare, things, that nature, but it was actually a very tight ir image. It just was nondescript shape, which was interesting. Typically we would see the skin of the aircraft, we can see the flames coming out of the exhaust, especially at those ranges. Um and </s>

<s>[INST] You've also competed. Is there something you can speak to? The value of competition, obviously you've been through combat, actual military combat is many, many, many orders of magnitude more high stakes than competition us in a silly sport like jujitsu. Nevertheless, it still has some of the echoes of the same challenges. Is there something you can speak to? The value of competition for you? [/INST] Yep, Competition will reveal weaknesses in your game that you can then go back and train to rectify. </s><s>[INST] So that that's very useful to sort of Yeah, as a testing ground, of course, training could be that testing ground as well or um that feedback, [/INST] yep, but as you and I both know if you and I trained together all the time, you know, my game, I'll know your game. And even if we have five other people, we all kind of understand each other's games and you're not doing something to me that I don't expect. So when I go and compete, you know, this random person has a game that I've never seen before. I'm, and I may or may not know how to deal with that game. If I know how to deal with it, great, I get the victory. Maybe I don't learn as much. If I don't know how to deal with their game, I get the loss and I get the win of learning what some weakness in my game is. Yeah. </s><s>[INST] So you mentioned offline that uh, your friends and you work with Dean Lister and Dean Lister is one of the people that inspired john Danaher who I've very much been, uh, I've got a chance to talk to quite a bit recently. I don't know what you think about this. This is not a therapy session, but mm or maybe this [/INST] one is turning </s><s>[INST] into one. I've uh, that he's a fascinating person, john Danaher in terms of um, creating almost a science that gets to a level that I haven't seen before, which is uh, systems thinking about like you can think about military combat as tactics in a particular situation. But when you zoom out and you want to create entire systems of tactics in all situations. Right. He's very kind of wants to keep zooming out and creating giant systems and uh, which I appreciate that even though the task is probably impossible, uh, to do completely. But there is something that's in terms of competition. They he kindled a fire in me that I want to get back out there. He has a particular thing that did it, which was very different from my personal journey, jujitsu, which was two degree that people I worked with cared about competition. It was always about winning and or doing well, all those kinds of things. For john, it's about winning, like winning is not, is not even a thing that's important. What's most important is winning by submission is, or dominance, right? And uh, and not just the, the end is the entire time competing. Such that the only thing that matters is that kind of victory. And that's a very different level of competition. That's actually liberating in a certain kind of sense. I remember so much of my competition was about kind of, fear of not taking risks. You know, you get up on points or you hold a strong position, you kind of advanced, you get more points. Maybe you chase the submission, but there's always a fear of risk. And for him, you embrace the risk, you're not, you should not be competing out of fear, you know, uh, live and die by the sword versus uh, stay in safety. I don't know if there's something to be said here. [/INST] Well, I mean, this is um, not you said it's novel to you, It's not novel to me. The entire, My entire journey on Ju Jitsu in Jiu Jitsu was only about submission. And you know, as you, as you mentioned, Dean Dean Lister is my coach and my main training partner for 20 something years. And if you ever watch Dean train or fight, that's what he's trying to do is submit as everyone. That's what he's always done. That's what he always will do. He, you know, he has the highest, I think he has. In fact, I know he has the highest submission victories in 80 cm. He, that's what he does. So this is in fact, as Jiu jitsu got more popular and we started seeing people competing to win by points. That was what was novel to me in the beginning. Now it's the standard. So it's not novel to me. I love the fact that john Donna her and all of his troops go out and they try and submit people. I think it's awesome. And I think that's what jujitsu is. </s><s>[INST] All right. Let's ask for some advice for white belts. There's a lot of weight belts to listen to this. What advice would you give you been in digestive for many years in terms of uh, yeah, a successful journey through. Just so what advice would you give them people just starting out, [/INST] Just keep training, keep your ego in check. Don't freak out. Try and use the techniques that you learn and all this stuff sounds like I'm saying it, you know, notice how I'm saying it, hey tap out, keep your ego maniac and everyone, but the thing is everyone says this all the time and white belt still start off by going completely nuts for at least you know, 3 to 6 months of, I'm not gonna let this guy tapped me out and they're gonna and I'm gonna tap this guy out, not by using technique but by just using strength and it's just a, it's just inhibiting your learning. So as much as you can, I know, I know you got to get it out of your system, I know you don't wanna tap and I know you wanna tap somebody, but as soon as you get, get that off your chest, then try and try and relax and try and learn the techniques. </s>

<s>[INST] defense uh is when you're wearing a g what is defense entail? Is it mostly grips is mostly the position of your hips and legs, [/INST] it is everything together because it's a whole body movement is, you know, it's a constantly moving your your arms, legs, body, it's it, they, you know, they have to, everything works together, </s><s>[INST] going back to the mind of that guy, uh, so confident, no fear at this point, is there a bit of ego in there too? [/INST] Yes, like I said, I'm not gonna say I'm feel I'm fearless. Of course these concerns that fight I would have to say was probably the fight that I got nervous the most walking in because I knew what that man that fight, I mean, everything for me, all my legacy was on the line because if I lost that fight, I will forever, will be number two, forever. And I mean, is a great, great guy, great competitor, Judicial is very good, but I'm better than him. I knew that </s><s>[INST] he's competing on top of that. He's [/INST] A, he's a great competitor, you know, taking nothing out of him. He's super tough, very, very tough, very good. He's probably the best competitor introducing, he won 13 times the World Championship, I won 10. So as a competitor, you know, he has more titles than I do. So, but in terms of, you know, analyzing the game, I consider technically better than him. So knowing all that everything that I build all my legacy, it's if I lose </s><s>[INST] writing on this match, [/INST] If I lose this fight, I'm forever. No two, </s><s>[INST] I don't know that it's going through your mind and [/INST] I know I knew, I mean, it's not at that moment that I already knew that I remember just before, you know, the curtains open, I'm standing in before they call my name and I mean my legs were like, I feel the adrenaline kick in on my legs and I'm like, you know, I'm hitting the legs, I'm like wake up, you know, get off, get the drilling off of me, you know, so it's, it was, it was intense, it was intense and </s><s>[INST] this was in Rio [/INST] and that was in Rio. </s><s>[INST] So [/INST] my hometown. </s><s>[INST] So this is, I mean, and you know Rio is not exactly known for its calmness in its fans. So this is like wherever they hosted the olympics the year before. So this is like, I mean this like the whole, basically martial arts community is watching this. I mean is there some was Hansel [/INST] there? </s><s>[INST] So people are just, I mean there's attention, it's also, [/INST] I </s><s>[INST] mean, I don't know if you felt that in part, but you're also fighting for the gracie [/INST] name </s><s>[INST] in the, [/INST] in our hometown, </s><s>[INST] the greatest [/INST] gracie gracie </s><s>[INST] competitor of all time arguably in the hometown? Yeah, I mean, okay, all [/INST] my family, my best friends, my friends, everybody watching everybody there, There was a lot of pressure a lot. </s><s>[INST] And then were you thinking that you would be able to submit him? [/INST] No, it's at that point. Like I don't predict how the fight will go that I never did because it is unpredictable. It's, I never tried to set any strategy for any fight I think okay, that I did, but that was the only time that I said any strategy into a fight, there was a 15 minutes fight that and for I said first five minutes I'm going to play defense. He's bigger, stronger, younger, I don't want to play his game. And I know he comes in very fast every single fight he had, you know, he comes very aggressive. So my strategy walk into the fight to save five minutes, I'm going to play defense, I'm not gonna try to attack, I'm not gonna try to match his space. I already expected, you know, maybe I'm going to start losing the fight because, you know, if it comes in, there's a risk of me maybe getting takedown, you know, something happened, I'm like, I'm gonna stick to the game plan five minutes, I'm gonna start picking up the pace because then it's 10 minutes to go, which 10 minutes a long fight. So I don't need to stop fast, but I'm gonna stop being more aggressive and then, you know, try to take him down or pull guard. You know, by then, I'm like, that's as far as strategy goes, </s><s>[INST] no specific stay on the feet. Were you comfortable being both bottom and top and this strategically, [/INST] I'm always comfortable being bottle top, I prefer to be on top because being in the bottom, the person on top dictates the pace of the fight because he's on top over you. So I always prefer to be on top because I can dictate the pace. I can implement my own pace and being the bottom, they can slow me down so it's harder. So if I can choose, I will always be on top. But I think but then I was like, it's, you know, five minutes hit it. I'm like, he's pretty big and strong. I'm gonna spend a lot of energy taking him down. I forgot. </s><s>[INST] How did how did it feel? So here you're stepping in by the way, puzzle mask. This is old school, as old school as it gets so calm and relaxed here for people just listening. We're watching the early minutes of the match. So just feeling it out. He seems pretty calm to he must be nervous too. I wonder how you ever talked to him? You guys are friends. [/INST] Yeah. Friends. </s><s>[INST] Did he ever say how nervous he was? [/INST] No, we never spoke about that fight. No. Mhm. </s><s>[INST] He probably lays uh late at night thinking about it. [/INST] Maybe. I don't know that </s><s>[INST] S. O. B. [/INST] Yeah, I mean, so you see the first five minutes you know, he kept I knew what he was going to do in my study his game. His stand up is most basic is basically in takedowns, leg attacks double legs. So he goes single double and he charged in. That is pretty much his stand up game. </s>

<s>[INST] uh, in terms of being able to remove objects from a scene and fill in the background automatically. I so that's extremely exciting. And that's the neural networks are stepping in there. I just talk this week Ian goodfellow uh, [/INST] against doing that is definitely one approach. </s><s>[INST] So that is that, is that a really difficult problem? Is it as difficult as it looks again to take it to a robust product level? [/INST] Well, there are certain classes of image for which the traditional algorithms like content aware, fill work really well. Like if you have a naturalistic texture, like a gravel path or something because it's patch based, it will make up a very plausible looking intermediate thing and fill in the hole. And then we use some algorithms to sort of smooth out the lighting so you don't see any brightness contrast in that region or you've gradually ramped from one from dark to light if it straddles the boundary where it gets complicated as if you have to infer invisible structure behind behind the person in front. And that really requires a common sense knowledge of the world to know what, you know, if I see three quarters of a house, do I have a rough sense of what the rest of the house looks like. If you just fill it in with patches, it can end up doing things that make sense locally, but you look at the global structure and it looks like it's just sort of crumpled or messed up. And so what Ganz and neural nets bring to the table is this common sense learned from the training set And um, the challenge right now is that the generative methods that can make up missing holes using that kind of technology are still only stable at low resolutions. And so you either need to then go from a low resolution to a high resolution using some other algorithm or we need to push the state of the art and it's still in research to get to that point. Um, of course, if you show it something, say it's trained on houses and then you show it an octopus. It's not going to do a very good job of showing common sense about octopuses. So again, you're asking about how you know that it's ready for prime time. You really need a very diverse training set of images. And ultimately, that may be a case where you put it out there with some guard rails where um, you might do a detector which looks at the image and sort of estimates its own competence of how well a job could this algorithm do? So eventually there may be this idea of what we call an ensemble of experts where any particular expert is specialist in certain things and then there's sort of a either they vote to say how confident they are about what to do. This is sort of more for future looking or there's some dispatcher which says you're good at houses, you're good at trees. Uh so I mean it's all this adds up to a lot of work because each of those models will be a whole bunch of work, but I think over time, um you gradually fill out the set and uh initially focus on certain workflows and then sort of branch out as you get more capable. </s><s>[INST] You mentioned workflows and uh have you considered maybe looking far into the future? Uh First of all using the the fact that there is a huge amount of people that use Photoshop for example have certain workflows being able to collecting information by which they basically get information about their workforce about what they need. What can the ways to help them, whether it is houses octopus that people work on more. You know, like basically getting a beat on what kind of uh data is needed to be annotated and collected for people to to build tools that actually work well for people. [/INST] All right, Absolutely. And this is a big topic and the whole world of ai is what data can you gather and why at one level, the way to think about it is we not only want to train a little customers and how to use our products, but we want them to teach us what's important and what's useful at the same time, we want to respect their privacy and yeah, obviously we wouldn't do things without their explicit permission. And I think the modern spirit of the age around this is you have to demonstrate to somebody how they're benefiting from sharing their data with at all. Either it's helping in the short term to understand their intent so you can make better recommendations or if they're friendly to your cause or you're taller, they want to help you evolve quickly because they depend on you for their livelihood. They may be willing to share some of their um workflows or um choices with with the data set to be then trained. There are technologies for looking at learning without necessarily storing all the information permanently so that you can sort of learn on the fly but not keep a record of what somebody did. So we're definitely exploring all of those possibilities. </s><s>[INST] And I think adobe exist in a space where Photoshop, if I look at the data, I've created an own, you know, I'm less comfortable sharing data with social networks than I am with adobe because there's just exactly as you said, uh there's an obvious benefit for sharing the data that I use to create in Photoshop because it's helping improve the work fall in the future. As opposed to it's not clear what the benefit is in social networks, [/INST] it's nice for you to say that. I mean I think there are some professional workflows where people might be very protective of what they're doing. Such as if I was preparing evidence for a legal case, I wouldn't want any any of that, you know, phoning home to help train the algorithm or anything. Um There may be other cases where people say having a trial version or they're doing some, I'm not saying we're doing this today, but there's a future scenario where somebody has a more permissive relationship with, they don't be where they explicitly say I'm fine. I'm only doing hobby projects or things which are non confidential. Um and in exchange for some benefit um tangible or otherwise. I'm willing to share very fine grained data. So another possible scenario is to capture relatively crude, high level things from more people and then more detailed knowledge from people who are willingly participate. We do that today with explicit customer studies where you know, we go and visit somebody and ask them to try the tool and we human observe what they're doing um in the future to be able to do that enough to be able to train an algorithm. We'd need a more systematic process but we have to do it very consciously because one of the things people treasure about adobe is a sense of trust and we don't want to endanger that through overly aggressive data collection. So we have a chief privacy officer and it's definitely front and center of thinking about ai rather than an afterthought. </s>

<s>[INST] Anyway, neuro is offering 50% off when you use code lex at checkout, go to get neuro.com and use code lex. This show is also sponsored by master class $100 a year for an all access pass to watch courses from literally the best people in the world and a bunch of different topics like chris Hadfield on space exploration, Neil degrasse Tyson of scientific thinking and communication will right, creator of Simcity and Sims both one of my favorite games, Carlos Santana, one of my favorite musicians on guitar, Garry Kasparov in chess and I say more about who my favorite chess player is and Daniel on the ground on poker and many more. Maybe one day I'll do a master class on how to drink vodka and ask overly philosophical questions of world class engineers who are too busy to bother with my nonsense by the way. You can watch it on basically any device. Sign up at masterclass dot com slash lex. You get 15% off the first year of an annual subscription as master class dot com slash lex. Finally, the show is presented by cash app, the number one finance app in the app store when you get it used collects podcast Cash app, lets you send money to friends, buy Bitcoin and invest in the stock market with as little as $1. I'm thinking of doing more conversations with folks who work in and around the Cryptocurrency space similar to a I I think, but even more so there are a lot of charlotte scenes in this space, but there are also a lot of free thinkers and technical geniuses whose ideas are worth exploring in depth and with care if I make mistakes in guest selection and details and conversations themselves, I'll keep trying to improve, correct where I can and also keep following my curiosity wherever the heck it takes me. So again, if you get cash out from the app store, google play and use the code lex podcast, you get $10 and cash up will also donate $10 to first an organization that is helping to advance robotics and stem education for young people around the world. And now here's my conversation with chris Latner, what are the strongest qualities of steve jobs, Elon musk and the great and powerful Jeff Dean. Since you've gotten a chance to work with each, [/INST] you're starting with an easy question there. Um These are three very different people I guess you could do maybe a pair wise comparison between them instead of a group comparison. So if you look at steve jobs and Elon um I worked a lot more with Ellen, I did with steve um they have a lot of commonality there, both visionary in their own way, they're both very demanding in their own way. Um My sense is steve is much more human factor focus where Ellen is more technology focused, </s><s>[INST] whereas human factor, I mean steve [/INST] is trying to build things that feel good that people love, that affect people's lives, how they live. He's looking into into the future a little bit in terms of what people want. Um I think that Ellen focuses more on uh learning how exponentials work and predicting the development of those </s><s>[INST] steve worked with a lot of engineers. That was one of the things that are reading the biography and how can the designer essentially talk to engineers and get their respect [/INST] I think. So, I did not work very closely with steve, I'm not an expert at all. My sense is that he uh pushed people really hard, but then when he got an explanation that made sense to him, then he would let go. And um he did actually have a lot of respect for engineering and but he also knew when to push and you know when you can read people well you can know when they're holding back and when you can get a little bit more out of them and I think he was very good at that. I mean if you if you compare the other the other folks, So Jeff Dean, Right? Jeff Dean is an amazing guy, he's super smart, um as as one of the other guys, um Jeff is a really, really, really nice guy, well meaning he's a classic google or he uh wants people to be happy, He combines it with brilliance so he can pull people together in a really great way. He's definitely not a ceo type. I don't think he would even want to be </s><s>[INST] that, do you know if he's still programs? [/INST] Yeah, he definitely programs, Jeff is an amazing engineer today, right, and that has never changed. So um it's really hard to compare Jeff to either of those two. Um He uh I think that Jeff leads through technology and building it himself and then pulling people in and inspiring them, and so I think that that's um one of the amazing things about Jeff, but each of these people, you know, with the pros and cons all are really inspirational and have achieved amazing things. Yes, it's been a it's been I've been very fortunate to get to work with these guys </s><s>[INST] for yourself, you've lead large teams, you've done so many incredible difficult technical challenges. Is there something you picked up from them about how to lead? [/INST] Yeah, so I mean I think leadership is really hard, it really depends on what you're looking for there. Um, I think you really need to know what you're talking about. So being grounded on the product, on the technology, on the business, on the mission is really important being understanding what people are looking for, why they're, they're one of the most amazing things about Tesla is the unifying vision, right? People are there because they believe in clean energy and electric electrification, all these kinds of things. Um, uh, the other is to understand what really motivates people, how to get the best people, how to, how to build a plan that actually can be executed right? There's so many different aspects of leadership and it really depends on the time, the place, the problems, you know, you know, there's a lot of issues that don't need to be solved. And so if you focus on the right things and prioritize well, that can really help move things </s><s>[INST] to interesting things. You mentioned one is you really have to know what you're talking about, how you've uh, you worked on a lot of very challenging technical things. So I kind of assumed you were born uh, technically savvy, but assuming that's not the case, how do you, how do you develop technical expertise? Like even at google, you work on, I don't know how many projects but really challenging very varied [/INST] compilers, tps hardware, cloud stuff, a bunch of different things. Um, the thing that I've become comfortable is I've more comfortable with as I've gained experience is, uh, being okay with not knowing. And so a major part of leadership is actually, it's not about having the right answer, it's about getting the right answer. And so if you're working in a team of amazing people, right? And many of these places made these companies all have amazing people. It's a question of how do you get people together? How do you get, how do you build trust? How do you get people to open up? How do you people get people to, you know, be vulnerable sometimes with an idea that maybe isn't good enough, but it's the start of something beautiful. How do you, um, how do you provide an environment where you're not just like top down the shell, do the thing that I tell you to do right? But you're encouraging people to be part of the solution and uh, providing a safe space where if you're not doing the right thing, they're willing to tell you about it. So </s><s>[INST] you're asking dumb questions. Yeah. The questions [/INST] are my specialty. Well, so I've been in the harbor recently and I don't know much at all about how chips are designed. I know a lot about using them. I know some of the principles and the arts technical level of this, but it turns out it turns out that if you ask a lot of dumb questions you get smarter really, really quick and when you're surrounded by people that want to teach and learn themselves can be a beautiful thing. </s><s>[INST] So, let's talk about programming languages if it's okay at the highest absurd philosophical level because I don't get [/INST] romantic on me last, </s><s>[INST] I will forever give them, I think, and torture. I apologize. Uh, why do programming languages even matter? [/INST] Okay, well, thank you very much. You're saying why should why why should you care about anyone programming language? Or why do you why do we care about programming computers </s><s>[INST] or no? Why? Why do we, why do we care about programming language? Design? Creating effective programming languages? Uh, choosing a, you know, one program languages versus another programming language. Why we keep struggling and improving through the evolution of these programming languages? [/INST] Okay, so, I mean, I think you have to come back to, what are we trying to do here? Right. So, we have these, these beasts called computers that are very good at specific kinds of things and we think it's useful to have them do it for us. Right? Uh, now you have this question of how best to express that because you have a human brain still has an idea on its head and you want to achieve something. So, well, there's lots of ways of doing this. You can go directly to the machine and speak assembly language and then you can express directly with the computer understands that's fine. Um, you can then have higher and higher and higher levels of abstraction. Up until machine learning and you're designing a neural net to do the work for you. Um, the question is, where, where along this way do you want to stop? And what benefits do you get out of doing so? And so programming languages in general, you have sea of FORTRAN and java and Ada, pascal swift, you have lots of different things. Um, they'll have different tradeoffs and they're tackling different parts of the problems. Now, one of the things that most programming languages do is they're trying to make it so that you have a pretty basic things like portability across different hardware. So you've got, I'm gonna run on an Intel PC. I'm gonna risk five PC. I'm gonna run on arm phone or something like that. Fine. Um, I want to write one program and have it portable. And this is something that assembly doesn't do now when you start looking at the space of programming languages. This is where I think it's fun because programming languages all have tradeoffs and most people will walk up to them and they look at the surface level of syntax and say, oh, I like curly braces, right? Like tabs or I like, you know, semicolons or not or whatever. Right subjective, fairly subjective, very shallow things. But programming languages when done right, can actually be very powerful and the benefit they bring is expression okay, and if you look at programming languages, there's really kind of two different levels to them. One is the down in the dirt nuts and bolts of how do you get the computer to be efficient stuff like that, How they work, type systems, compilers, stuff, things like that. The other is the UI and the UI for programming language is really a design problem and a lot of people don't think about it that way. </s><s>[INST] And the Ui, you mean all that stuff with the braces and yeah, all that [/INST] stuff to you. I and what it is and you, I mean is user interface. Um, and so what what's really going on is it's the interface between the guts and the human and humans are hard. Humans have feelings, they have things they like, they have things they don't like. And a lot of people treat programming languages as though humans are just kind of abstract creatures that cannot be predicted. But it turns out that actually there are, there is better and worse. Like people can tell when a program language is good or when it was an accident, right? And one of the things was swift in particular is that a tremendous amount of time by a tremendous number of people have been put into really polishing and make it feel good. But it also has really good. Nothing bolts underneath it. </s><s>[INST] You said that Swift makes a lot of people feel good. How do you get to that point. So how do you predict that? Uh, you know, tens of thousands, hundreds of thousands of people are going to enjoy using this user experience of this programming language Well [/INST] you can you can look at in terms of better and worse. Right? So if you have to write lots of boilerplate or something like that, you'll feel unproductive. And so that's a bad thing you can look at in terms of safety if like, see for example is what's called a memory unsafe language. And so you get dangling pointers and you get all these kind of bugs, but then you have spent tons of time debugging and it's a real pain in the butt and you feel unproductive. And so by subtracting these things from the experience, you get um you know, happier people, </s><s>[INST] but again keep interrupting, I'm sorry. Uh it's so hard to deal with. If you look at the people, people that are most productive on stack overflow, they are uh they have a set of priorities that may not always correlate perfectly with the experience of the majority of users. You know, if you look at the most up voted quote unquote, correct answer on stack overflow is usually really um sort of prioritize is like safe code, proper code, stable code. Uh you know, that kind of stuff as opposed to like if I want to use go to statements in my basic Right uh I want to go to ST like what if 99% of people when they go to statements are just completely improper, you know, unsafe syntax? [/INST] I don't think that people actually, like if you boil it down and you get below the surface level, people don't actually care about go to your if statements or things like this, they care about achieving a goal. Right? So the real question is I want to set up a web server and I want to do a thing and whatever, like, how, how quickly can achieve that. Right? And so the from programming language perspective, there's really two things that matter there. One is what libraries exist, and then how quickly can you put it together? And what are the tools around that look like? Right. And and when you want to build a library that's missing, what do you do? Okay, now, this is where you see huge divergence in the force between worlds. Okay. And so you look at python, for example, python is really good at assembling things, but it's not so great at building all the libraries. And so you get because of performance reasons, other things like this. Did you get python layered on top of C, for example? And that means that doing certain kinds of things? Well, it doesn't really make sense to do in python instead. You do it and see, and then you wrap it and then you have your living in two worlds, and two worlds never is really great because tooling and the bugger doesn't work, right? And like all these kinds of things, </s><s>[INST] can you clarify a little bit, what what you mean by python is not good at building libraries, meaning it doesn't make use of [/INST] certain kinds of libraries, </s><s>[INST] but just the actual meaning of the sentence uh meaning like it's not conducive to developers to come in and add libraries or it's it's or the language or is it the duality of the it's a dance between python and c. And [/INST] python is amazing. Pythons. Great language that I do not mean to say that python is is bad for libraries. What I meant to say is um their python, their libraries, that python is really good at that you can write in python, but there are other things like if you wanna build a machine learning framework, you're not gonna build a machine learning framework and python because of performance, for example, or you want Gpu acceleration or things like this instead. What you do is you write a bunch of, see, your C plus plus code or something like that. And then you talk to it from python right? And so this is because of decisions that were made in the python design and um and those decisions have other counterbalancing forces. But but the trick when you start looking at this from a programming language perspective and you start to say, okay, cool, how do I build this catalog of libraries that are really powerful and how do I make it so that then they can be assembled in two ways. They feel good. And they generally work the first time because when you're talking about building a thing, you have to include the debugging the fixing the turnaround cycle, the development cycle, all that kind of stuff in in into the process of building the thing. It's not just about pounding out the code. And so this is where things like um you know, catching bugs at compile time is valuable, for example. Um but if you dive into the details in this Swift for example, has certain things like value semantics, which is this fancy way of saying that when you treat treat a variable like a value, um it acts like a mathematical object would Okay, so, and you have used pytorch a little bit and pytorch you have tensors, tensors are Andy and dimensional grid of numbers. Very simple. You can do plus and other operators on them, it's all totally fine. But why do you need to clone a tensor sometimes? Have you ever wondered that? </s><s>[INST] Uh Yeah. [/INST] Okay. And so why is that, Why do you need to clone a tensor? </s><s>[INST] It's the usual object thing. That's in python. So [/INST] in python, and just like with java and many other languages, this isn't unique to python and python, it has a thing called reference semantics, which is the nerdy way of explaining this and what that means is you actually have a point or do a thing instead of the thing? Okay, now this is due to a bunch of implementation details that you don't want to go into. But in swift you have this thing called value semantics. And so when you have a tensor and swift it is a value. If you copy it, it looks like you have a unique copy and if you go change one of those copies then uh it doesn't update the other one because you just made a copy of this thing. </s><s>[INST] So that that's like highly error prone and uh at least computer science, math centric disciplines about python, that like the thing you would expect to behave like a math, like math, it doesn't behave like math and in fact quietly doesn't behave like math. And they can ruin the entirety of you. [/INST] Exactly. Well, and then it puts you into bugging land again. Yeah. Right now, now you just want to get something done and you're like wait a second where where do I need to put clone and what level of the stack? Which is very complicated, which I thought I was raising somebody's library and now we need to understand it to know where to clone a thing. </s><s>[INST] Right? And hard to debug by the way. [/INST] Exactly. Right. And so this is where programming languages really matter. Right? So in swift having value semantics so that both you get the benefit of Math working like math. Right. But also the efficiency that comes with certain advantages, there are certain implementation details there really benefit you as a programmer and signify </s><s>[INST] the value semantics, like how do you know that? The things should be treated like a value? [/INST] Yeah. So, so Swift has a pretty strong culture and good language support for defining values. And so if you have an array, so tensors are one example that the machine learning folks are very used to um just think about a raise same thing where you have an array, you put uh you create an array, You put two or 3 or four things into it and then you pass it off to another function. What happens if that that function add some more things to it? Well, you'll see it on the side of the Poseidon. Right? This is called reference semantics. Now, what if you pass and ray off to function? It scrolls it away in some dictionary or some other data structure somewhere. Right. Well, it thought that you just handed it that array, then you return back and that that that reference to that array still exists in the color and they go and put more stuff in it. Right? The person you handed it off to may have thought they had the only reference that. And so they didn't know what they that this was gonna change underneath the covers. And so this is where you end up having to do clone. So like I was past the thing, I'm not sure if I have the only version of it. So I have to clone it. So what value semantics does it allows you to say, hey, I have a son swift, it defaults to value semantics. </s><s>[INST] So the most value semantics and then because most things [/INST] end up </s><s>[INST] then it makes sense for [/INST] that. And one of the important things about that is that arrays and dictionaries and all these other collections that are aggregations of other things also have value semantics. And so when you pass this around to different parts of your program, you don't have to do these defensive copies. And so this is, this is great for two sides. Right? That's great because you define away the bug, which is a big deal for productivity. The number one thing most people care about, but it's also good for performance because when you're doing a clone, so you pass the ray down to the thing, it was like, I don't know if anyone else has it, I have to clone it. Well you just did a copy of a bunch of data. It could be big and then it could be the thing that called you is not keeping track of the old thing. So you just made a copy of it and you may not have had to do. And so the way the value semantics, workers and swift as it uses a thing called copy on write, which means that you get, you get the benefit of safety and performance and has another special trick because if you think certain languages like java for example, they have immutable strings. And so what they are trying to do is they provide value semantics by having pure mutability functional languages have pure mutability and lots of different places and this provides a much safer model and it provides various Mannix. Um, the problem with this is if you have a mutability, everything is expensive. Everything requires a copy. Um, for example, in java, if you have a string X and string, why you put them together, we have to allocate a new string to hold X, Y. </s><s>[INST] If they're immutable [/INST] well, and strings, strings in java are immutable. And if there's, there's optimizations for short ones and it's complicated, but but generally think about them as a separate allocation. And so when you append them together, you have to go allocate a third thing because somebody might have a pointer to either of the other ones, Right? And you can't go change them. So you have to go allocate a third thing because of the beauty of how the swift I smack system works out. If you have a string and switch and you say, hey, put an X, right? They say depend on y, z, w w what it knows that there's only one reference to that. And so I can do an in place update. And so you're not allocating tons of stuff on the side, You're not you don't have all these problems When you pass it off, you can know you have the only reference if you pass it off to multiple different people, but nobody changes it, they can all share the same thing. So you get a lot of the benefit of a purely mutable design and so you get a really nice sweet spot that I haven't seen in other languages. </s><s>[INST] Yeah, that's like I thought, I thought there's going to be uh, a philosophical like narrative here that you're gonna have to pay a cost for it. It sounds like, I think value semantics is beneficial for easing of the bugging or minimizing the risk of errors. Like bringing the errors closer to the source, uh, bringing the symptom of the air closer to the source of the air, however you say that. But you're saying there's not a performance cost either if you implement [/INST] it correctly. So there's trade offs with everything. And so if you are doing very low level stuff, then sometimes you can notice the cost, but then what you're doing is you're saying what is the right default? So, um, coming back to user interface, when you, when you talk about programming languages, one of the major things that swift does that makes people love it. That is not obvious when it comes to designing language, is this ui principle of progressive disclosure of complexity. Okay, so, so if, like many languages is very powerful. The question is, when do you have to learn the power as a user so swift, like python allows you to start with like print. Hello world. Right. Certain other languages start with like public, static void main class is like all the ceremony. Right? And so you go to teach, teach a new person. Hey, welcome, Welcome to this new thing. Let's talk about public access control classes. Wait, what's that? String system dot out dot print line. Like packages like Right. And so instead if you take this and you say, hey, we need we need we need packages, you know, modules we need, we need powerful things like classes, we need data structures. We need like all these things. The question is, how do you factor the complexity and how do you make it? So that the normal case scenario is you're dealing with things that work the right way in the right way and give you good performance, right? By default. But then as a power user, if you want to get down to it, you have full c c performance, full control over low level pointers. You can call Malik if you want to call Malik, this is not recommended on the first page of every tutorial, but it's actually really important when you want to get work done. Right? And so being able to have that is really the design and programming language. Design and design is really, really hard. It's something that I think a lot of people kind of um, outside of UI. Again, a lot of people just think is subjective, like there's nothing, you know, it's just like curly braces or whatever. It's just like somebody's preference. But actually good design is something that you can feel </s><s>[INST] and how many people are involved with good design. So if we look at Swift, but look historically, I mean this might touch like uh it's almost like a steve jobs question to like how much dictatorial decision making is required versus collaborative and we'll talk about how that can go wrong or right. But [/INST] yeah, well, Swift, so I can't speak to in general, all design everywhere. So the way we're so Swift is that um, there's a core team and so core team is six or seven people ish. Something like that. That is people who have been working with Swift since very early days. And so by early </s><s>[INST] days is not that long ago. [/INST] Okay. Yeah, it became public in 2014. So it's been six years public now, but um, but so that's enough time that there's a story out there. Okay. And there's mistakes have been made that then get fixed and you learn something and then, you know, and so uh, what the core team does is it provides continuity and so you want to have a okay, well there's a big hole that we want to fill, we know we want to fill it. So don't do other things that invade that space until we fill the hole, right? There's a boulder that's missing here. We want to we will do that boulder even though it's not today. Keep out of that space and the </s><s>[INST] whole team remembers of remembers the myth of the boulder that's there. [/INST] Yeah, yeah. There's a general sense of what the future looks like in broad strokes and a shared understanding of that, combined with the short understanding of what has happened in the past that worked out well and didn't work out well. Um, the next level out is you have the what's called the swift evolution community and you've got in that case hundreds of people that really care passionately about the way swift evolves and that's like an amazing thing to again, the core team doesn't necessarily need to come up with all the good ideas. You've got hundreds of people out there that care about something and they come up with a really good ideas too, and that provides this like tumbling rock tumbler for ideas. And so the evolution process is, you know, a lot of people in a discourse forum, they're like hashing it out and trying to like talk about, okay, well what should we go left or right or if we did this, what would be good and, you know, here we're talking about hundreds of people, so you're not going to get consensus necessarily, they're not obvious consensus. And so there's a proposal process that then allows the core team and the community to work this out. And what the court team does aims to get consensus of the community and provide guardrails but also provide long term, make sure we're going the right direction kind of things. </s><s>[INST] So does that group represent like the how much people will love the user interface? Like you think they're able to capture that? [/INST] Well, I mean it's something we talked about a lot of something we care about how well we, how will we do? That's up for debate. But I think that we've done pretty well. So </s><s>[INST] is the beginner in mind because you said the progressive disclosure. [/INST] So we care a lot about, uh, a lot about that, a lot about power, a lot about efficiency. A lot about there are many factors to good design and you have to figure out a way to kind of work your way through that. And </s><s>[INST] so if you like think about like the language I love is list probably still because I use the max, but I haven't done anything any serious working list, but it has a ridiculous amount of parentheses. Uh, I've also, you know, with java and c plus plus the braces. Um, you know, I, I like I enjoyed the comfort of being between races, you know, and then python is really sorry to interrupt just like and last thing to me as a design if I was a language designer? God forbid as, uh, I would be very surprised that python with no braces would nevertheless somehow be comforting also. So like I could see arguments for all of these. Look [/INST] at this, this is evidence that it's not about braces versus tabs. Right? </s><s>[INST] Exactly. You're good. That's a good point. [/INST] Right? So like, you know, there's, there's evidence that, but </s><s>[INST] see like it's one of the most argued about things. Oh yeah, of [/INST] course. Just like tabs and spaces, which it doesn't, I mean there's one obvious right answer, but it doesn't, it doesn't actually matter. Was that come on friends? Like it's like trying to, too many people </s><s>[INST] are going to have people going to do now. Yeah. [/INST] Um, </s><s>[INST] so you're able to identify things that don't really matter for the experience? [/INST] Well, no, it's, it's, it's always really hard. So the easy decisions are easy, right? I mean, you can find those are not the interesting ones. The hard ones are the ones that are most interesting. Right? The hard ones are the places where, hey, we want to do a thing. Every agrees, we should do it. There's one proposal on the table that has all these bad things associated with it. Well, okay, what are we gonna do about that? Do we just take it? Do we delay it? Do we say? Hey? Well, maybe there's this other feature that if we do that first? This will work out better. How does this, if we do this? Are we paying ourselves into a corner? Right. And so this is where again, you're having that core team of people that has some continuity and has perspective, has some of the historical understanding is really valuable because you get, um, it's not just like one brain, you get the power of multiple people coming together to make good decisions and then you get the best out of all these people and you also can harness the community around it. </s><s>[INST] What about like the decision of whether, like in python, having one type are having, you know, strict typing. [/INST] Yeah, yeah. Let's talk about this. So, um, I like how you put that by the way, like, so, so many people would say that python doesn't have types, doesn't have, but I've listened to </s><s>[INST] you enough, I'm a fan of yours and I've listened to way too many podcast and then you're talking about [/INST] this. Oh yeah. So I would argue that python has one type. And so, um, so like when you import python and swift, which by the way it works really well, you have everything comes in as a python object now, hear their trade offs because, um, uh, you know, it depends on what you're optimizing for, and python is a super successful language for a really good reason because it has one type, you get duck typing for free and things like this, but also you're pushing you're making it very easy to, to pound out code on one hand, but you're also making it very easy to introduce uh complicated bugs, you have to debug and you pass a string into something that expects an integer and it doesn't immediately die. It goes all the way down the stack trace and you find yourself in the middle of some code that you really didn't want to know anything about and it blows up and you're saying, well what did I do wrong? Right. And so types are good and bad and they have trade offs are good for performance and certain other things depending on where you're coming from, but it's all about tradeoffs. And so this is, this is what design is right. Design is about weighing tradeoffs and trying to understand the ramifications of the things that you're weighing, like types or not or one type of many types, um but also within many types, how powerful do you make that type system is another very complicated question uh with lots of trade offs, it's very interesting by the way, uh but uh but that's like 11 dimension and there's a bunch of other dimensions, jit compiled versus static compiled garbage collected versus reference counted vs. Memory, manual memory management versus you know, like in like all these different trade offs and how you balance them or what make a program language good </s><s>[INST] currency. So and all those things, I guess when you're designing the language, you also think of how that's going to get all compiled down to [/INST] if you care about performance. Yeah, well, and go back to list. Right. So list also, I would say javascript is another example of a very simple language. And so one of the so I also love lisp, I don't use it as much as maybe you do what you did? </s><s>[INST] No, I think we're both everyone who loves the list. It's like you love, it's like, I don't know you I love frank Sinatra, but like how often do I seriously listen to frank said [/INST] but but but you look at that or you look at javascript, which is another very different but relatively simple language and there's certain things that don't exist in the language, but there's there is inherent complexity to the problems that we're trying to model. And so what happens to the complexity in the case of both of them, for example, you say, well, what about large scale software development? Okay, well you need something like packages. Neither language has a language accordance for packages. And so what you get is patterns you get things like NPM, you get things like, you know, like these ecosystems that get built around and I'm a believer that if you don't model at least the most important, inherent complexity in the language, then what ends up happening is that complexity gets pushed elsewhere and what gets pushed elsewhere sometimes that's great because often building things as libraries is very flexible and very powerful and allows you to evolve and things like that. But often it leads to a lot of unnecessary divergence in the forest and fragmentation. And and when that happens you just get kind of a mess. And so the question is, how do you how do you balance that? Don't put too much stuff in the language because that's really expensive. It makes things complicated. But how do you model enough of the inherent complexity of the problem that um, you provide the framework and the structure for people to think about? Well, so, so the the key thing to think about with uh with programming languages, and you think about what programming languages therefore is, it's about making a human more productive. Right? And so, like there's an old, I think it's a steve jobs quote about it's a bicycle for the mind, right? You can you can you can definitely walk, but you'll get there a lot faster if you can bicycle on your way. </s><s>[INST] And a programming language is a bicycle for the mind is basically uh wow, that's really interesting way to think about [/INST] it. But by raising the level of abstraction now, you can fit more things in your head by being able to just directly leverage somebody's library, you can now get something done quickly um in the case of Swift Swift ui is this new framework that Apple has released recently for doing Ui programming and it has this declarative programming model which defines away entire classes of bugs. It's make it builds on value, semantics and many other nice swift things. And what this does is allows you just get way more done with way less code and now your productivity is the developer is much higher. Right? And so that that's really the what programming languages should be about is it's not about tabs versus spaces or curly braces or whatever, it's about. How productive do you make the person and you can only see that when you have libraries that were built with the right intention that the language was designed for and was swift, I think we're still a little bit early. Um, but Swifty I and many other things that are coming out now are really showing that and I think that they're opening people's eyes, </s><s>[INST] that's kind of interesting to think about like how that, you know, the knowledge of something of how good the bicycle is, how people learn about that, you know? So I've used C Plus plus. Now this is not going to be a trash talking session about C Plus plus, but you C Plus plus for a really long [/INST] if you want to have this car, </s><s>[INST] I feel like I spent many years without realizing like there's languages that could for my particular lifestyle, brain style, thinking style, there's language that that could make me a lot more productive uh in the debugging stage in the, just the development stage and thinking like the bicycle for the mind that I could fit more stuff into my [/INST] python is a great example. Yeah, right. I mean, a machine learning framework and python is a great example that it's just very high abstraction level. And so you can be thinking about things on a very high level algorithmic level instead of thinking about, okay, well, am I copying this tensor to a gpu or not? Right. It's not, it's not what you want to be thinking about. </s><s>[INST] And I was telling you, I mean, I guess the question I had is, uh, you know, how does a person like me or in general, people discover more productive? Uh, you know, languages like how I was, as I've been telling you offline, I've been looking for like a project to work on and swift so I can really try it out. I mean, my intuition was like doing a hello world is not going to get me there, uh, to get me to experience the power of the language. [/INST] You need a few weeks to change in metabolism. </s><s>[INST] Exactly. I didn't think it beautifully. But uh, that's one of the problems with people would die. It's like, I'm actually currently to go in parallel, but in small tangent is I've been recently eating only meat. Okay, okay. So most people are like, uh, the thing that's horribly unhealthy or whatever you have, like a million, whatever the science is, it just doesn't sound right. [/INST] So, so back when I was in college we did the Atkins diet. That was, that was a thing and </s><s>[INST] similar. And, but if you, you have to always give these things a chance, I mean we're dieting always not dieting, but it's just the things that you like, if I eat personally, if I eat meat, just everything, I could be super far more focused than usual. I just feel great. I've been running a lot of, you know, doing push ups and post and so on and you, python is similar in that sense for me, Where [/INST] are you going on? </s><s>[INST] I mean literally, I just felt I had like a stupid smile on my face when I first started using python, I could code up really quick things like I like, I, I would see the world, I'll be empowered to write a script to, um, you know, to do some basic data prosecute you rename files on my computer right? Like Pearl didn't do that for me. Uh, a little bit well [/INST] and again, like, no, these are about which, which is best or something like that, but there's definitely better and </s><s>[INST] worse here. But it clicks Well, yeah, [/INST] if you, if you look at Pearl for example, you get bogged down in uh, scholars versus rays versus hashes versus type clubs and like, all that kind of stuff. And python is like, yeah, let's not do this </s><s>[INST] and some of its debugging like everyone has different priorities, but for me it's cadet creates systems for myself that empower me to debug quickly. Like I've always been a big fan, even just crude, like asserts like always uh, stating things that should be true, which in python, I found myself doing more because of type, all these kinds of stuff [/INST] you can think of types in a programming language as being kind of assert. Yeah, they get checked at compile time. Right? Um, so how do you learn anything? Well, so this or how do, how do people learn new things? Right. This this is hard. People don't like to change. People generally don't like change around them either. And so, uh, we're all very slow to adapt and change and usually there's a catalyst that's required to force yourself over the, over over this. So for learning a programming language is really comes down to finding an excuse like build a thing that, that, that the language is actually good for, the ecosystem is ready for. Um, and so, um, so if you were to write an IOS app for example, that would be the easy case, obviously you would use Swift for that right there. Swift runs on Andrew. Oh, does it? Oh yeah Swift friends and places. Okay, so Swift Swift Swift is built on top of L V. M L VM runs everywhere. L V M, for example, builds the android kernel. Okay, so uh so they realize this. Yeah, so Swift Swift is very portable runs on Windows, there's runs on lots of different things </s><s>[INST] and I was suicide, that's what do I, and then there's a thing called UI Kit, so I built an app was swift [/INST] uh well, so that that's the thing is the ecosystem is what matters there. So Swift, ui and you like, it are Apple technologies. Okay, God. And so they happen to like Swifty I happen to be written in Swift, but it's an Apple proprietary framework that Apple loves and wants to keep on its platform, which makes total sense. You go go to Andrew and you don't have that library. Right? And so android has a different ecosystem of things that hasn't been built out and doesn't work as well as swift. And so you can totally use swift to do uh like arithmetic and things like this, but building UI was swift on, android is not, not not a not a great example right now. </s><s>[INST] So, so if I wanted to uh to learn Swift, what's the I mean, one practical, different version of that is uh Swift for tensorflow for example, and one of the inspiring things for me with both tensorflow and pytorch is how quickly the community can like switch from different libraries, like you can see some of the communities switching to pytorch now, but it's very easy to see and intensive is really stepping up its game and then there's no reason why I think the way it works basically it has to be one get help repo like one paper steps [/INST] up gets </s><s>[INST] people excited, gets people excited. And they're like, I have to learn this swift for what, what swift again. And then they learned and they fall in love with. I mean that's what happened by torches. [/INST] There has to be a reason, a catalyst. Yeah. And so and and there, I mean people don't like change, but it turns out that once you've worked with one or two programming languages, there, the basics are pretty similar. And so one of the fun things about learning programming languages even even maybe list, but I don't know if you agree with this is that when you start doing that, you start learning new things because you have a new way to do things and you're forced to do them and that forces you to explore. And it puts you in learning mode. And when you get in learning mode, your mind kind of opens a little bit and you can you can see things in a new way. Even when you go back to the old place, </s><s>[INST] right? Yeah. So it would list was functional. Uh but I wish there is a kind of window. Maybe you can tell me if there is uh there you go. This is a question uh to ask what is the most beautiful feature in a programming language. Before I ask you, let me say, like with python, I remember I saw a list comprehension ins uh it was like when I like really took it in, I don't know, I just loved it. It was like fun to do. Like it was fun to do that kind of uh uh something about it to be able to filter through a list and to create a new list on a single line was elegant. I could all get into my head and it just made me um fall in love with the language. So is there, let me ask you a question. Uh Is there what to use the most beautiful feature in uh in a programming languages that you've ever encountered in swift? Maybe? And then outside of swift, [/INST] I think the thing that I like the most from a programming language. So I think the thing you have to think about with the programming language again, what is the goal? You're trying to get people to get things done quickly and so you need libraries, you need high quality libraries and then you need a user base around them that can assemble them and do cool things with them. Right. And so to me, the question is what enables high quality libraries? Okay. Yeah. And there's a huge divide in the world between libraries who enable high quality libraries versus um the ones that put special stuff in the language. </s><s>[INST] So programming languages that enable high quality, like all these libraries got it. [/INST] So and what I mean by that is expressive libraries that then feel like a natural, integrated part of the language itself. So um an example this in Swift is the hint and float and also rain string, things like this. These are all part of the library. Like it is not hard coded into Swift. And so what that means is that because it is just a library thing to find in the standard library along with strings and raise and all the other things that come with standard library. Um Well hopefully you do like it. But anything that any language features that you needed to define event, you can also use in your own types. So if you wanted to find a Kryptonian or something like this, right? Um Well, it doesn't come to standard library um there's a very special set of people that care a lot about this, but those people are also important. It's not it's not about classism, right? It's not about the people who care about instant fluids are more important than people care about kryptonians. And so to me, the beautiful things about programming languages is when you allow those communities to build high quality libraries that feel native that feel like they're built into the built into the compiler without having to be, </s><s>[INST] what does it mean for the end to be part of? Not hard coded in? So is it like how, so what isn't what is an event? [/INST] Okay. It's just a *** in this case it's like a like a 64 bit image or something like this. </s><s>[INST] But so like the 64 bit is hard coded or no, [/INST] no, none of that's hard coded. So if you go look at how it's implemented, it's just obstruct and swift. Mhm. And so it's a structure and then how do you add to struck's, will you define Plus? And so you can define Plus on went well, you can define Plus on your thing too. You can define integers, like an Izod method or something like that on it. And so yeah, you can add methods on the things. </s><s>[INST] Uh so you can you can define operators, like how you behave, that's you is beautiful when there there's something about the language which enables others to create libraries which are not hacky. [/INST] Yeah, they feel the feel native. And so one of the best examples of this is lisp because in list, like all the libraries are basically part of the language. Right? You write term rewrite systems and things like this. And so </s><s>[INST] can you as a counter example, provide what makes it difficult to write a library That's native. Is it the python? C? [/INST] Well, so, well, so one example, I'll give you two examples, a java and C Plus plus or java and C? Um they both allow you to find your own types, but it is hard coded in the language. Okay, well, why? Well, in java, for example, coming back to this whole reference semantic value, semantic thing, um it gets passed around by value. But if you if you make if you make like a pear or something like that, a complex number, right? It's a class in java and now it gets passed around by reference by pointer. And so now you lose value semantics, right? You lost math. Okay, well, that's not great. Right. If you if you can do something within, why can't I do with my type? Right. So that's that's the negative side of the thing I find beautiful is when you can solve that, when you can have full expressivity where you as a user of the language have as much are almost as much power as the people who implemented all the standard built in stuff. Because what that enables is that enables truly beautiful libraries. </s><s>[INST] You know, it's kind of weird because I've gotten used to that uh that's one I guess, other aspect of programming language design, you have to think, you know, the old first principles thinking like why are we doing it this way, by the way? I mean, I remember because I was thinking about the walrus operator and I'll ask you about it later, but it hit me that like the equal sign for assignment. Like why are we using the equal sign? [/INST] That's wrong. That's not the only solution. Right? So if you look at pascal they use colon equals or assignment and equals for um for equality. And they use like less than greater than instead of the not equal. Yeah. There are </s><s>[INST] other answers here. So but like and they had like ask you all, but but how do you then decide uh to break convention to say, you know what that everybody is doing it wrong? We're going to do it right? [/INST] So, so it's like an R. O. I like return on investment trade off. Right? So if you do something weird, let's just say like not like Colin equal instead of equal for assignment. That would be weird with today's aesthetic, right? And so you'd say cool, this is theoretically better. But is it better? In which ways? Like what do I get out of that? Do I define away? Class of bugs? Well, one of the class of bugs that C has is that you can use like, you know, if x equals without equals equals, f X equals Y. Right? Well, it turns out you can solve that problem in lots of ways. Playing for example, Gcc all these compilers will detect that as a as a likely bug, producer warning, do they? Yeah, </s><s>[INST] I feel like they didn't clang gcc didn't it's like one of the important things about programming language designs, like you're literally creating suffering in the world. Okay. Like, like I feel like, I mean one way to see it is the bicycle for the mind, but the other way is the, like minimizing suffering. Well [/INST] you have to decide if it's worth it, right? And so let's come back to that, but but if you, if you look at this and again, this is where there's a lot of detail that goes into each of these things, um uh equal and see returns a value. Yeah, that's messed up. That allows you say x equals Y equals e. Like that works and see um </s><s>[INST] is it messed up well, so that most people think it's messed up, I think [/INST] it is very by messed up. What I mean is it is very rarely used for good and it's often used for bugs. Yeah, right. And so it's a good definition you could use, you know, it's a, in hindsight, this was not such a great idea right now. One of the things was Swift that is really powerful and one of the reasons it's actually good versus it being full of good ideas is that when, when we launched Swift one, we announced that it was public, people could use it, people could build apps, but it was going to change and break, okay, when Swift two came out, we said, hey, it's open source and there's this open process which people can help evolve and direct the language. So the community at large, like Swift users can now help shape the language as it is. And what happened is that as part of that process is a lot of really bad mistakes got taken out. So for example, Swift used to have the C style plus plus and minus minus operators. Like what does it mean when you put it before versus after? All right. Well, that got cargo cult ID from C into Swift early. What cargo cult, cargo cult means brought forward without really considering considering it. This is maybe not the most pc term, but </s><s>[INST] look it up in urban dictionary. [/INST] Yeah. So it got pulled, It got pulled in to see without got pulled into swift without very good consideration. And we went through this process and one of the first things got ripped out was plus plus and minus minus because they lead to confusion. They have very little value over saying, you know, X plus equals one and X plus equals one is way more clear. And so when you're optimizing for teach ability and clarity and bugs and this multidimensional space that you're looking at, things like that really matter. And so being first principles on where you're coming from and what you're trying to achieve and being anchored on the objective is really important. </s><s>[INST] Well, let me ask you about uh, the most uh sort of this, this uh this podcast isn't about information. It's about drama. Let me talk to you about some drama. So you mentioned past gown and colon equals, Uh, there's something that's called the Walrus operator? And Python uh in Python 3.8 added the Walrus operator. And the reason I think it's interesting what uh it's not just because the future, it does, it has the same kind of expression feature you can mention to see that it returns the value of the assignment and maybe you can comment on that in general, but on the other side of it, it's also the thing that that uh toppled the dictator. Uh it finally drove guido to step down from me, DFL the texas city of the community. So maybe um what do you think about the walrus operator in python? Is there an equivalent thing in swift that really uh stress tested the community? And uh and then on the flip side, what do you think about greed is stepping down over it? Yeah. Well, like if [/INST] I look past the details of the water software, one of the things that makes it most polarizing is that it's syntactic sugar. </s><s>[INST] Okay, what do you mean by syntactic sugar? It [/INST] means you can take something that already exists in language and you can express it in a more concise way. </s><s>[INST] So, okay, I'm gonna play devil's advocate. So uh this is great. Uh is that objective or subjective statement? Like can you, can you argue that basically anything is syntactic sugar or [/INST] not? You know, not everything is a syntactic sugar? So for example, um the type system, like, can you have classes versus versus uh, like, do you have types or not? Right, So, so one type versus many types is not something that affects syntactic sugar. And so if you say I want to have the ability to define types have to have all this like language mechanics to define classes and now I have to have inheritance and I have like, I have all this stuff that's just making language more complicated. That's not, that's not about sugaring it. Um, Swift has sugar. So like Swift has this thing called if let and it has various operators are used to concise if I, uh, specific use cases. So the problem with syntactic sugar when you're talking about, hey, I have a thing that takes a lot to write and I have a new way to write it. You have this like, horrible tradeoff, which becomes almost completely subjective, which is how often does this happen? And does it matter? And one of the things that is true about human psychology, particularly when you're talking about introducing a new thing is that people over over estimate the burden of learning something and so it looks foreign when you haven't gotten used to it. But if it was there from the beginning, of course is just part of python, like unquestionably like this is just the thing I know, and it's not a new thing that you're worried about learning. It's just part of, part of the deal now with guido? I don't know, Guido. Well, </s><s>[INST] um, yeah, have you passed across much? I've [/INST] met him a couple of times, but I don't know, no guido Well, but the sense that I got out of that whole dynamic was that he had put the, not just the decision maker weight on his shoulders, but it was so tied to his personal identity that um, he took it personally and he felt the need and he kind of put himself in the situation of being the person instead of building a base of support around him. I mean, this is probably not quite literally true, but by too much, so there was too much, too much concentrated on him, Right? And so, </s><s>[INST] and that can wear you down [/INST] Well, yeah, particularly because people then say Guido, you're a horrible person, I hate this thing, blah, blah, blah, blah, blah, blah, blah, and sure it's like, you know, maybe 1% of the community that's doing that, But Python's got a big community and 1% of millions of people is a lot of hate mail and that just from human factor will just wear on you </s><s>[INST] what to clarify. It looked from, just what I saw in the messaging for the let's not look at the million python users, but at the python core developers, it feels like the majority of the big majority on a vote were opposed to it. [/INST] Okay, I'm not that close to it, </s><s>[INST] so Okay, so the situation is like literally, uh, yeah, I mean, the majority of the court developers against proposed, so right. And they weren't they weren't even like against it. It was there was a few while they were against it, but against, it wasn't like this is a bad idea. They were more like, we don't see why this is a good idea and what that results in is there's a stalling feeling like you just slow things down now from my perspective that you could argue this. And I think it's a very, it's very interesting if you look at politics today and the way congress works, it's slowed down everything. Yeah, it's a dampener. But like that's a dangerous thing too, because if it dampens things like, you know, uh, dampening results, what [/INST] are you talking about? Like it's a low pass filter, but if you need billions of dollars injected in the economy or trillions of dollars, then suddenly stuff happens. Right? And so </s><s>[INST] for sure. So [/INST] I'm not defending our political situation just to be clear. </s><s>[INST] But you're talking about like a global pandemic. I was hoping we could fix like the health care system and the education, like, you know, [/INST] I'm not, I'm not a politics person. I don't, I don't, I don't know when it comes to languages the community is kind of right in terms of it's a very high burden to add something to a language. So as soon as you add something you have a community of people building on it and you can't remove it Okay, and if there's a community of people that feel really uncomfortable with it, then taking it slow I think is an important thing to do. And there's no rush, particularly if it's something that's 25 years old and is very established and you know, it's not like coming coming into its own, um, </s><s>[INST] revolve features. [/INST] Well, so I think that the issue with, with Guido is that maybe this is a case where he realized that had outgrown him and it went from being or the language, the language. So python, I mean Guido is amazing, but, but python isn't about Guido anymore, it's about the users and to a certain extent the user's own it and, you know, Guido spent years of his life a significant fraction of his career on python, and from his perspective, I imagine he's like, well this is my thing, I should be able to do the thing I think is right, but you can also understand the users where they feel like, you know, this is my thing, I use this, like, and um and I don't know, it's, it's, it's a hard, it's a hard thing, but </s><s>[INST] what if we could talk about leadership in this, because it's so interesting to me, I'm gonna, I'm gonna make, I'm gonna work. Hopefully somebody makes it, if not, I'll make it a water separator shirt because I think it represents to me, maybe it's my Russian roots or something, uh, you know, it's the burden of leadership. Like I feel like to push back, I feel like progress can only like most difficult decisions. Just like you said, there would be a lot of divisiveness over, especially in the in the passionate community. It just feels like leaders need to take those risky decisions that that if you like listen that with some non zero probability, maybe even a high probability would be the wrong decision, but they have to use their gut and make that decision. [/INST] This is like one of the things where you see amazing founders, The founders understand exactly what's happened and how the company got there and are willing to say we have been doing thing X the last 20 years, but today we're going to do thing why? And they make a major pivot for the whole company. The company lines up behind them. They move and it's the right thing. But then when the founder dies, the successor doesn't always feel that that agency to be able to make those kinds of decisions, even though the ceo they could theoretically do whatever. There's two reasons for that in my opinion or in many cases it's always different. But um, one of which is they weren't there for all the decisions that were made. And so they don't know the principles in which those decisions were made and once the principles change, you should be obligated to change what you're doing and change direction, right? And so if you don't know how you got to where you are, it just seems like gospel and you know, you're not going to question it, you may not understand that. It really is the right thing to do. So you just may not see it. </s><s>[INST] That's so brilliant. I never thought of it that way. Like it's so much higher burden. When is the leader you step into a thing that's already worked for a long time? [/INST] Yeah. Yeah. Well, and if you change it and it doesn't work out now, you're the person screwed it up. People always second guess that the second thing is that even if you decide to make a change, even if you're theoretically in charge, you're just you're just a person that thinks they're in charge. Meanwhile you have to motivate the troops, you have to explain it to them in terms of I understand you have to get them to buy into and believe in it because if they don't, then they're not going to be able to make the turn, even if you tell them, you know, their bonuses are gonna be curtailed, They're just not going to like buy into it, you know? And so there's only so much power you have as a leader and you have to understand what that what those limitations are. </s><s>[INST] Are you still be DFL you've been BD fl of some stuff, uh you're very heavy on the b the benevolent benevolent dictator for life I guess L. V. M. You're [/INST] still still lead the L. V. M. </s><s>[INST] Uh I mean what's the role of? Uh So then on Swift you said that there's a group of people, [/INST] so if you contrast python or swift, right, one of the reasons, so everybody in the core team takes the role really seriously and I think we all really care about where Swift goes, but you're almost delegating the final decision making to the wisdom of the group and so it doesn't become personal and also when you're talking with the community so yeah, some people are very annoyed at certain decisions get made. Um There's a certain faith in the process because it's a very transparent process and when a decision gets made, a full rationale is provided things like this. These are almost defense mechanisms to help both guide future discussions and provide case lock and like Supreme Court does about this decision was made for this reason and here's the rationale and what we want to see more of or less of. Um but it's also a way to provide a defense mechanism so that when somebody's griping about it, they're not saying that person did the wrong thing, they're saying, well this this thing sucks and later they move on and they get over </s><s>[INST] the analogy, the Supreme Court I think is really is really good but then okay not to get person on the swift team but like is there is there like it just seems like it's impossible for their for division not to emerge. [/INST] Well each each of the humans on the swift core team for example are different and the membership of the Swift core team changes slowly over time which is I think a healthy thing and so each of these different humans have different opinions. Trust me it's not it's not a singular consciousness of by any stretch of the imagination. You've got three major organizations including Apple Google and Science five all working together and um it's a small group of people but you need high trust you need again it comes back to the principles of what you're trying to achieve and understanding you know what you're optimizing for and I think that starting with strong principles and working towards decisions is always a good way to both make wise decisions in general but then be able to communicate them to people so that they can buy into them and that that is heard, so you mentioned L. V. M. L. V. M. Is Gonna be 20 years old. Uh this December so it's it's showing its own age, </s><s>[INST] you have like like a like a like a dragon cake plan or you have [/INST] no I should definitely do that if we can have a uh pandemic kick and everybody gets a slice of, it gets you know sent through email. Um but the uh but Alabama's had tons of its own challenges over time to write. And one of the challenges that um the elysium community has in my opinion is that has a whole bunch of people that have been working on television for 10 years right? Because this happens somehow and Elvis has always been one way but it needs to be a different way Right? And they've worked on it for like 10 years is a long time to work on something and you know you suddenly can't see the faults. And the thing that you're working on an album has lots of problems and we need to address someone we can make it better. And if we don't make it better than somebody else will come up with a better idea. Right? And so it's just kind of that age where the community is like in danger of going to calcified and um and so I'm happy to see new projects joining and new things mixing it up. You know FORTRAN is now a new a new thing in the L the um community which is serious. I'm good. </s><s>[INST] I've been trying to find on a little tangent. Find people who program in COBOL or FORTRAN. FORTRAN especially to talk to their hard to find. [/INST] Yeah look to the scientific community they saw us fortunate quite a bit </s><s>[INST] interesting thing you kind of mentioned with L. V. M. Or just in general that is something evolved. You're not able to see the faults. So do you fall in love with the thing over time? Or do you start hating everything about the thing? [/INST] Over time? So, so my my my personal folly is that um I see maybe not all but many of the faults and they're great on me and I don't have time to go fix them well and they may not get magnified, but they never get fixed. It's like sand underneath, you know, it's just like reading against you and it's like underneath your fingernails or something, It's just like, you know, it's there, you can't get rid of it. Um and so the problem is that if other people don't see it right? Nobody ever, like, I can't go, I don't have time to go write the code and fix it anymore, but then people are resistant to change. And so they said, hey, we should go fix this thing, like Oh yeah, that sounds risky. Well, is it the right thing or </s><s>[INST] not? Are the challenges uh the group dynamics or is it also just technical, I mean, some of these features, like, I think as an observer is almost like a fan in in the, you know, as a spectator of the whole thing. I don't often think about, you know, some things might actually be technically difficult to implement. [/INST] Example, this is we we built this new compiler framework called MlR MlRS? This whole new framework, it's not many people think it's about machine learning. The Ml stands for multi level because compiler people can't name things very well. I guess </s><s>[INST] we dig into what L IR is. [/INST] Yeah. So when you look at compilers, compilers have historically been solutions for a given space. So L V M is a it's really good for dealing with Cpus, let's just say at a high level, you look at java, java has a J VM. The VM is very good for a garbage collected languages that need dynamic compilation and it's very optimized for specific space. And so a hotspot is one of the compilers that gets us in that space and that compilers really good at that kind of stuff. Um usually when you build these domain specific compilers, you end up building the whole thing from scratch fresh demand, </s><s>[INST] uh what's the domain? So what's the what's the scope of a domain? [/INST] So here, I would say like if you look at Swift, there's several different parts to the swift compiler, um, one of which is covered by um the elevation part of it. There's also a high level peace that's specific to Swift and there's a huge amount of redundancy between those two different infrastructures and a lot of re implemented stuff that is similar but different. </s><s>[INST] What is L L V M define? [/INST] L V M is effectively an infrastructure so you can mix and match it in different ways. It's built out of libraries, you can use it for different things, but it's really good at Cpus and Gpus Cpus and like the tip of the iceberg on gps, it's not really great at gps. Okay. Um but it turns out the languages that then use it to talk to cps. Um and so it turns out there's a lot harder out there, that is custom accelerators. So, machine learning, for example, there are a lot of matrix multiply accelerators and things like this. There there's a whole world of hardware synthesis. So we're using mlr to build circuits. Okay. And so you're compiling for a domain of transistors. And so what Emily or does is it provides a tremendous amount of compiler infrastructure that allows you to build these domain specific compilers in a much faster way and have the result be good </s><s>[INST] if we're if we're thinking about the future that we're talking about like a six. So anything. Yeah, so if we project into the future, it's very possible that the number of these kinds of A six, very specific uh infrastructure, I think the architecture things uh like multiplies exponentially. I hope so. So that's M L I R. [/INST] So what Emily, and what Emily does is allows you to build these compilers very efficiently right now. One of the things that coming back to the L A P M thing and then we'll go to hardware is um LVMH is a specific compiler for specific Domain Emily is now this very general, very flexible thing that can solve lots of different kinds of problems. So L V M is a subset of what Emily or does. </s><s>[INST] So, um, I always, I mean it's an ambitious project then. [/INST] Yeah, it's a very ambitious project. And so to make it even more confusing, Millar has joined the L V M umbrella projects that's part of the L V M family. Um, but when this comes full circle is now folks that work on the L V M part, the classic part that's 20 years old, aren't aware of all the cool new things that have been done in the new, the new thing that, you know, Emily was built by me and many other people that knew a lot about L V M. And so we fixed a lot of the mistakes that lived in L V. M. I mean, you have this community dynamic where it's like, well, there's this new thing, but it's not familiar, nobody knows it, it feels like it's new and so let's not trusted. And so it's just really interesting to see the cultural social dynamic that comes out of that. And and, you know, I think it's super healthy because we're seeing the ideas percolate and we're seeing the technology diffusion happen as people get more comfortable with it. They start to understand things in their own terms. And this just gets to the, it takes a while for ideas to propagate, even though, um, they may be very different than what people are used to. </s><s>[INST] Maybe let's talk about that a little bit, the world of basics and yeah well actually you're You're you have a new role at Science five. What's that place about? What is the vision uh for their vision for? I would say the future of computer. [/INST] So I lead the engineering product teams. That's a five. Science five is a company whose was founded with this architecture called RISC five. Risk five is the new instruction set instructions sets of things inside of your computer that how to run things. Um X 86 from Intel and arm from the armed company and things like this or other instruction sets </s><s>[INST] I've talked to, so I talked to David Patterson who is super excited about Risk five. David. David's awesome is brilliant. Yeah [/INST] The Risk five is distinguished by not being proprietary. Um And so X A six can only be made by intel and M. D. Arm can only be made by arm, they sell licenses to build armed ships to other companies. Things like this. MiPS is another instruction set that is owned by the MIPS company now Wave and it gets licensed out things like that. Um And so Risk five is an open standard that anybody can build ships for. And so sci fi was founded by Three of the founders of risk five that designed and built it in Berkeley working with Dave um and so that was the genesis of the company. So I have today has some of the world's best Risk five course and we're selling them and that's really great. They're going to tons of products that's very exciting. </s><s>[INST] Uh they're taking this thing that's open source and just being trying to be or are the best in the world at building these things. [/INST] Yeah, so here it's the specifications, Open source, it's like saying, TCP I P is an open standard, or C is an open standard, but then you have to build an implementation of the standard. And so Science Five, on the one hand, pushes forward and defined and pushes forward the standard. On the other hand, we have implementations that are best in class for different points in the space, depending on if you want a really tiny CPU if you want a really big beefy one that uh is faster, but it uses more area and things like this. </s><s>[INST] What about the actual manufacturer? Which is so like what, so where's that outfit? I'm gonna ask him, punching down questions, [/INST] Okay, this is how we learn. Uh and so, uh the way this works is that there's generally a separation of the people who designed the circuits and then people who manufacture them and so that you'll hear about fabs like TSMC and Samsung and things like this, that actually produce the chips, but they take a design coming in and that design specifies how, how the, you know you turn uh code for the chip into uh little rectangles that then use photo of the photography to make mask sets and then burn transistors onto a chip or onto onto silicon. </s><s>[INST] So we're talking about mass manufacturing. So [/INST] yeah they're talking about making hundreds of millions of parts and things like that. Yeah and so the fab handles the volume production, things like that. But when you look at this problem um the interesting thing about the space when you look at it is that um these are the steps that you go from designing a chip and writing the quote unquote code for it and things like fire log and languages like that down to what you hand off to the fab is a really well studied really old problem. Okay um tons of people have worked on, lots of smart people have built systems and tools. These tools then have generally gone through acquisitions and so they've ended up at three different major companies that build and sell these tools. They're called E. D. A. Tools like for electronic design automation. Um The problem with this is you have huge amounts of fragmentation, you have loose standards um and the tools don't really work together so you have tons of duct tape and you have tons of lost productivity. </s><s>[INST] Now these are these are tools for designing the risk. Five is a instruction like what is risk five? Like how deep does it go? How how much does it touch the hardware? How much does it define? How much of the hardware's [/INST] So risk, risk five is all about um given a CPU so the processor and your computer, how does the compiler, like the swift compiler of the c compiler, things like this? How does it make it work? So that's what is the assembly code? And so you write risk five assembly instead of x 86? Assembly for example, </s><s>[INST] but it's a set of instructions as opposed to set of instructions. What do you say? It tells you how the compiler works? [/INST] Uh Sorry, it's what the compiler talks to. </s><s>[INST] Okay, and then uh the tooling, you mentioned that the disparate tools are for what for [/INST] when you're building a specific chip. So risk five in hardware. In hardware. Yeah. So, so risk five, you can buy a risk five core from size five and say, hey, I want to have a certain number of running a certain number of gigahertz. I want it to be this big, I want to be have these features, I want to have um like I want floating point or not, for example. Um and then what you get is you get a description of the CPU with those characteristics. Now, if you want to make a chip you want to build like an iphone chip or something like that, right? You have to take both the CPU but then you have to talk to memory, you have to have timers, IOS GPU other components. And so you need to pull all those things together into what's called an ASIC, application specific integrated circuits. So a custom chip and then you take that design and then you have to transform it into something that the fabs like TSMC, for example, know how to take the production. </s><s>[INST] So, but yeah, [/INST] and so that process, I will, I can't help but see it as is a big compiler. It's </s><s>[INST] a whole [/INST] bunch of compilers written without thinking about it through that lens </s><s>[INST] is in the university, compiler, [/INST] Like compilers do to things they represent things and transform them. So there's a lot of things that end up being compilers, but this is, this is a space where we're talking about design and usability and the way you think about things, the way things composed correctly, it matters a lot. And so C5 is investing a lot into that space. And we think that there's a lot lot of benefits that can be made by allowing people to design ships faster, get them to market quicker. And um, scale out because um, you know, the alleged more end of moore's law, you've got this problem of, you're not getting free performance just by waiting another year for a faster CPU. And so, um, you have to find performance in other ways. And one of the ways to do that is with custom accelerators and other things in hardware </s><s>[INST] and, and so what we'll talk a little bit about a little more, about a six, but uh do you see that a lot of people, a lot of companies will try to have like different sets of requirements that this whole process to go for. So like, like almost different car companies might use different uh and like different pC manufacturers, like, So is this like his risk 5? Uh and this whole process, is that potentially the future of all computing devices? [/INST] Yeah, I think that, so if you look at risk five and step back from the silicon side of things, risk five is an open standard. And one of the things that has happened over the course of decades, if you look over the long arc of computing somehow became decades old because you have companies that come and go and you have instruction sets that come and go, like one example of this out of many is uh the sun will spark, someone way spark still lives on in future too. But we have HP had this instruction set called P A risk, so P A risk was this big server business and had tons of customers, they decided to move to this architecture called titanium from intel just didn't work out so well. Right, and so you have this issue of, you're making many billion dollar investments on instruction sets that are owned by a company and even companies as big as intel don't always execute as well as they could. They have their own issues. Um HP for example, decided that it wasn't in their best interest to continue investing in this space because it was very expensive. And so they make technology decisions or probably they make their own business decisions and this means that as a customer, what do you do? You've sunk all this time? Also engineering all the software work, all these, you've built other products around them and now you're stuck right. What Risk five does is it provides you more optionality in the space because if you buy an implementation of Risk five from Science five and you should do the best ones. Um But if something that happens to science five in 20 years, right. Well, great. You can turn around virus five course from somebody else and there's an ecosystem of people that are all making different risks of course with different tradeoffs, which means that if you have more than one requirement, if you have a family of products, you can probably find something in the risk five space that fits your needs. Whereas with if you're talking about X A six for example, it's intelligently gonna bother to make certain classes of devices. </s><s>[INST] I see. So uh maybe a weird question, but Like if say five Is uh like infinitely successful in the next 2030 years, what does the world look like? So like how does the world of computing change? [/INST] So too much diversity and hardware instruction sets I think is bad. Like we have a lot of people that are using um lots of different instruction sets particularly in the embedded like very tiny microcontroller space. The thing in your toaster um that uh that are just weird and different for historical reasons and so the compilers and the tool chains and the languages on top of them uh aren't there? And so the developers for that software have to use really weird tools because the ecosystem that supports is not big enough. So I expect that will change right? People will have better tools and better languages, better features everywhere that then can serve as many different points in space. Um and I think risk five will progressively um eat more of the ecosystem because it can scale up and scale down sideways left, right. It's very flexible and very well considered well designed instruction set. Um I think when you look at sci fi of tackling silicon and how people build chips, which is a very different space um that's where you say, I think we'll see a lot more custom chips and that means that you get much more battery life, you get better, better tuned solutions for your IOT thing, you get you get people to move faster, you get the ability to have faster time to market for example. </s><s>[INST] So how many customs, so first of all and IOT side of things do you see the number of smart toasters increasing exponentially. So uh, oh and if you do like how much customization per toaster is there do all horses in the world around the same uh, silicon like the same design or is it different companies have different design. Like how much, how much customization is possible here? [/INST] Well, a lot of it comes down to cost. Right? And so the way the chips work is you end up paying by the 11 of the factors is the size of the chip. And so what ends up happening just from an economic perspective is there's only so many chips that get made in any year of given design. And so often what customers end up having to do is they end up having to pick up a chip that exists was built for somebody else so that they can then shift their product. And the reason for that is they don't have the volume of the iphone, they can't afford to build a custom chip. However, what that means is they're now buying an off the shelf chip that isn't really good isn't a perfect fit for their needs. And so they're paying a lot of money for it because they're buying silicon that they're not using. Well if you now reduce the cost of design with chip now you get a lot more chips and the more you reduce it, the the easier it is designed chips Um, the more the world keeps evolving and we get more Ai accelerators, we get more, other things we get more standards to talk to, we get 60 right, you get you get you get changes in the world that you want to be able to talk to these different things, there's more diversity and the cross product of features that people want and um that drives differentiated chips and different in another direction and so nobody really knows what the future looks like, but um but I think that there's a lot of silicon in the future. </s><s>[INST] Speaking of the future, you said moore's Law allegedly is dead. So do you think do you agree with uh Dave patterson and many folks that moore's law is dead? Or do you agree with Jim Keller who says uh who's standing at the helm of the pirate ship saying it's uh still alive, Still alive? [/INST] Well, so I agree with what they're saying and different people are interpreting the animals a lot of different ways. So jim would say, you know, there's another 1000 X left in physics and we can we can continue to squeeze the stone and make it faster and smaller and smaller geometries and all that kind of stuff. Uh he's right, so jim Jim is absolutely right that there's a ton of a ton of progress left and we're not at the limit of physics yet. Um That's not really what moore's Law is though, if you look at what moore's law is, is that it's a very simple evaluation of Okay, well, you look at the cost for um I think it was cost per area and the most economic point in that space. And if you go look at the now quite old paper that describes this, um moore's law has a specific economic aspect to it, and I think this is something that dave and others often point out and so on a technicality. That's right. Um I look at it from, so I can acknowledge both of those viewpoints. They're both right, they're both right. I'll give you a third wrong viewpoint that maybe right in its own way, which is um single threaded performance doesn't improve, like it used to and it used to be back when you got a, You know, a Pentium 66 or something and the year before you had a penny, um 33 and now it's twice as fast. Right? Well, it was twice as fast at doing exactly the same thing. Okay. Like literally the same program ran twice as fast. You just wrote a check. Okay? And waited a year. Year and a half. Well, so that's what a lot of people think about moore's Law and I think that is dead. And so what we're seeing instead is we're pushing we're pushing people to write software in different ways and so we're pushing people to write cuda so they can get Gpu compute and the thousands, of course on GPU, we're talking about C programmers having p threads because they now have, you know, 100 100 threads or 50 cores in a machine or something like that. Um You're not talking about machine learning accelerators are now domain specific. And when you look at these kinds of use cases you can still get performance um and jim will come up with cool things that utilize the silicon in new ways for sure. But you're also going to change the programming model, right? And now when you start talking about changing the programming model, that's when you come back to languages and things like this too, because often what you see is um like you take the C programming language, right? The C programming language is designed for Cpus And so if you wanna talk to GPU now you're talking to its cousin CUDA. Okay, code is a different thing with a different set of tools, a different world, a different way of thinking and we don't have one world that scales and I think that we can get there, we can have one world that scales in a much better way </s><s>[INST] and a small change it. Then I think most programming languages are designed for Cpus for single core, even just in their spirit, even if they allow for personalization. So what does it look like for programming language to have parallelization or massive parallelization as it's like first principle. [/INST] So the canonical example of this is the harbor design world. So very log the HDL, these kinds of languages, they're what's called a high level synthesis language. This is the thing. People designed chips in. And when you're designing a chip, it's kind of like a brain where you have infinite parallelism. Like you've got your, your like laying down transistors, transistors are always running. Okay, so you're not saying run run this transistor, then this transistors in this transistor, it's like your brain, like your neurons are always just doing something. They're not clocked, right. They're just they're doing they're doing their thing. And so when you design a chip or when you design a CPU, when you design a GPU, when you design, when you're laying down the transistors, similarly you're talking about, Well, okay, well, how do these things communicate? So these languages exist very long is um, a kind of mixed example of that. Now, these languages are really great. You have a very </s><s>[INST] low level. Yeah, [/INST] they're very low level and abstraction is necessary here and there's different different approaches that. Then it's itself a very complicated world, but but it's implicitly parallel and so having that as a as the domain, the you program towards makes it so that by default you get parallel systems. If you look at kuda kuda is a point halfway in the space where in cuda when you write a CUDA kernel for your GPU, it feels like you're writing a scalar program? So you're like you have, if you have four loops, stuff like this, you're just writing normal normal code. But what happens outside of that in your driver is that it actually is running you on like 1000 things at once. Right. And so it's it's parallel but it has pulled it out of the programming model. And so now you as a programmer are working at a in a simpler world and it's solved that for you. </s><s>[INST] How do you take the language like Swift? Um you know, if we think about Gps but also a six, maybe we can dance back and forth between hardware and software. Uh you know, how do you design for these features to be able to program making a first class citizen to be able to do like Swift for tensorflow to be able to do machine learning on current hardware. But also future hardware like uh Cpus and all kinds of basics that I'm sure will be popping up more well. [/INST] So so a lot of this comes down to this whole idea of having the nuts and bolts underneath the covers that work really well. So you need, if you're talking to Tps you need, you know, M. L. I. R. X L. A. Or one of these compilers that talks to T. P. Us to build on top of. Okay, and if you're talking to circuits, you need to figure out how to lay down the transistors and how to organize and how to set up clocking and like all the domain problems that you get with circuits, then you have to decide how to explain to human, what is he? Why? Right. And if you do it right, that's a library problem. Not a language problem. And that works if you have a library or language which allows your library to write things that feel native in the language by implementing libraries, because then you can innovate in programming models without having to change your syntax. Again, like to invent new code formatting tools and like all the other things that language has come with and this, this gets really interesting. And so um, if you look at this space, the interesting thing, once you separate out syntax becomes what is that programming model? And so do you want the cuda style? I write one program and it runs many places. The do you want the implicitly parallel model? How do you reason about that? How do you give developers, you know, chip architects, the the ability to express their intent and that comes into this whole design question of how do you detect bugs quickly? So you don't have to take out a chip to find out what's wrong ideally. Right? How do you And and you know, this is a spectrum, How do you make it so that people feel productive? So their turnaround time is very quick, all these things are really hard problems and in this world, I think that not a lot of effort has been put into that design problem and thinking about the layering in other pieces. </s><s>[INST] Well, you've on the top of concurrency, you've written the swift concurrency manifest, I think it's it's kinda interesting anything that uh has the word manifesto and is very interesting, can you summarize the key ideas of uh each of the five parts you've written about? [/INST] So what is the manifesto? How about we start there? Uh So in the swift community we have this problem which is, on the one hand, you want to have relatively small proposals that you can kind of fit in your head, you can understand the details of a very fine grained level that move the world forward, but then you also have these big arcs. Ok. And often when you're working on something that is a big arc, but you're tackling in small pieces, you have this question of how do I know I'm not doing a random </s><s>[INST] walk, where [/INST] are we going? Like how does this add up furthermore, when you start that first, the first small step, what terminology to use? How do we think about what is better and worse than the space? What are the principles, what are we trying to achieve? And so what a manifesto in the swift community does it starts to say, hey, well let's step back from the details of everything. Let's paint a broad picture to talk about how, what we're trying to achieve. Let's give an example design point. Let's try to paint the big picture so that then we can zero in on the individual steps and make sure that we're making good progress. And so the swift concurrency manifesto is something I wrote three years ago. It's been a while maybe, maybe more trying to do that for for swift and concurrency. It starts with some fairly simple things like making the observation that when you have multiple different computers or multiple different threads are communicating, it's best for them to be asynchronous. Right? And so you need things to be able to run separately and then communicate with each other and this means a synchrony and this means that you need a way to modeling asynchronous communication. Many languages have features like this. A single weight is a popular one. And so that's what I think is very likely in swift. Um but as you start building this tower of abstractions, it's not just about how do you write this, you then reach into the, how do you get memory safety because you want correctness, you want debug ability, insanity for developers and how do you get uh that memory safety into um into the language. So if you take a language like go or C or any of these languages, you get what's called a race condition when two different threads or go routines or whatever, touch the same point in memory, right. This is a huge like, maddening problem to the bug because it's not reproducible generally. And so there's tools, there's a whole ecosystem of solutions that built up around this, but it's it's a huge problem when you're writing concurrent code. And so what swift, this whole value semantics thing is really powerful there because it turns out that math and copies actually work even in concurrent worlds. And so um you get a lot of safety just out of the box, but there are also some hard problems and it talks about some of that um when you start building up to the next level up and you start talking beyond memory safety, you have to talk about what is the programmer model? How does the human think about this? So a developer that's trying to build a program think about this and it proposes a really old model with the new spin called actors. Actors are about saying we have islands of single threaded nous logically. So you write something that feels like it's one programming, one program running in a unit and then it communicates a synchronously with other other things. And so making that expressive and natural feel good. Be the first thing you reach for and being safe by default is a big part of the design of that proposal. When you start going beyond that. Now you start to say, cool, well these things that communicate synchronously, they don't have to share a memory. Well if they don't have to share memory and they're sending messages to each other, why do they have to be in the same process? These things should be able to be in different processes on your machine and why just processes? Well why not different machines? So now you have a very nice gradual transition towards distributed programming. And of course when you start talking about the big the big future, the manifesto doesn't go into it. But accelerators are I think things you talk to a synchronously by sending messages to them. How do you program those? That that gets very interesting. That's not that's not in the proposal. </s><s>[INST] So and uh how much do you want to make that explicit? Like the control of that whole process explicit to the program. [/INST] Yeah. Good question. So when when you're designing any of these kinds of features or language features or even libraries, you have this really hard trade off they have to make, which is how much is it magic or how much is it in the humans control? How much can they predict and control it? What do you do when the default case is the wrong case? Mhm. Okay. So when you're designing a system um I won't name names but there are systems where um you it's really easy to get started and then you jump so let's pick like logo. Okay, so something like this. So it's really easy to start, it's really designed for teaching kids, but as you get into it, you hit a ceiling and then you can't go any higher and then what do you do? Well you have to go switch to a different world and rewrite all your code. And this logo is a silly example here. This exists in many other languages with python, you would say, uh like king currency, right? So python has the global interpreter lock. So threading is challenging in python. And so if you, if you start writing a large scale application in python and then suddenly need concurrency, you're kind of stuck with a series of bad trade offs, right? Um, uh there's other ways to go where you say like voiced all the, all the complexity on these are all ones, right? And that's also bad in a different way. And so what, what I, what I prefer is building a simple model that you can explain that then has an escape hatch. So you get in, you have guard rails, you memory safety works like this in swift where you can start with you like by default, if you use all the standard things, it's memories. If you're not gonna shoot your foot off. But if you want to get a C level pointer to something, you can explicitly do that, </s><s>[INST] but by default it's uh, there's guard rails, there's guardrails. Okay. So, but like, you know, uh whose job is it to figure out which part of the code is paralyzed? Herbal. [/INST] Um, so in the case of the proposal, it is the human's job. So they decide how to architect their application and then the runtime and compiler is very predictable. And so this, this is in contrast to um like there's a long body of work including unfortunate for auto paralyzing compilers and um, this is an example of a bad thing. And so as a compiler person, I can ride around compiler people. Um, often compiler people will say, cool, since I can't change the code, I'm gonna write my compiler that then takes this unmodified code and makes it go way faster on this machine. Okay. Application vote. And so it does pattern matching. It does really deep analysis. Compiler people are really smart and so they like want to do something really clever and tricky and you get like 10 X ft up by taking like an array of structures and turn into a structure of arrays or something because it's so much better for memory, like their bodies like tons of tricks. </s><s>[INST] Um, they love optimization. Yeah. You love options. Everyone loves [/INST] optimization well. And, and it's it's just this promise of build with my compiler and your thing goes fast. Right? But here's the problem looks, you write, you write a program, you run it with my compiler. It goes fast. You're very happy, wow. It's so much faster than the other compiler. Then you go and you have a feature of your program where you re factor some code and suddenly you've got a 10 X loss and performance. Well, why? What just happened there? What just happened there is you the the heuristic, the pattern matching the compiler or whatever analysis was doing just got defeated because you didn't in line a function or something right? As a user, you don't know, you don't want to know that the whole point, You don't want to know how the compiler works. You don't want to know how the memory hierarchy works. You don't want to know how it got parallelized across all these things you wanted that abstract away from you. But then the magic is lost as soon as you did something and you fall off a performance cliff and now you're in this funny position where What do I do? I don't change my code, I don't fix that bug, it costs 10 x performance. Now, what do I do? Well, this is the problem with unpredictable performance. If you care about performance, predictability is a very important thing. And so, um and so what the, what the proposal does is it provides architectural patterns for being able to lay out your code, gives you full control over that. Makes it really simple. So you can explain it. And then um and then if you want to scale out in different ways, you have full control over that. </s><s>[INST] So in your sense, the intuition is for compilers too hard to do automated parallelization, like, you know, because the compilers do stuff automatically. That's incredibly impressive for other things. But for parallelization we're not even we're not close to their [/INST] well it depends on the programming model, so there's many different kinds of compilers. So if you talk about like a c compiler swift compiler or something like that, where you're writing imperative code paralyzing that and reason about all the pointers and stuff like that is very, is a very difficult problem now if you switch domains. So there's this cool thing called machine learning. Mhm. Right, so machine, the machine learning nerds, among other enduring things like, you know, solving cat detectors and other things like that, um have done this amazing breakthrough of producing a programming model operations that you can pose together, that has raised levels of abstraction high enough that suddenly you can have auto paralyzing compilers, you can write a model using tensorflow and have it run on 1000 24 nodes of a teepee. </s><s>[INST] Yeah, that's true. I didn't even think about like, you know, because there's so much flexibility in the design of architecture, is that ultimately boil down to a graph that's paralyzed before you paralyzed for you. [/INST] And and if you think about it, that's pretty cool. That's pretty cool. And you think about matching, for example as a way of being able to exploit more parallelism, like that's a very simple thing that now is very powerful That didn't come out of the programming language nerds? Right. Those people like that came out of people that are just looking to solve a problem and use a few Gps and organically developed by the community of people focusing on machine learning. And it's an incredibly powerful, powerful abstraction layer that enables the compiler people to go and exploit that. And now you can drive supercomputers from python. That's </s><s>[INST] pretty cool. Just applause on that because I'm not sufficiently low level, I forget to admire the beauty and power of that. But um maybe just to linger on it, like, what, what does it take to run in your network fast? How hard is that compilation? It's [/INST] really hard. Um </s><s>[INST] so we just skipped, you said like, it's amazing that that's a thing, but how hard is that, of a thing? It's [/INST] hard. And I would say that not all of the systems are really great, including the ones I helped them. So there's a lot of work left to be done there. </s><s>[INST] Is it a cup Islanders working on that, or is it a whole new group of people? [/INST] Well, it's it's a full stack problem. Including compiler people, um including a p I S like paris and the the module api and pytorch and jacks? And there's a bunch of people pushing on all the different parts of these things, because when you look at it, it's both. How do I express the computation? Do I stack up layers? Well, cool. Like setting up a linear sequence of layers is great for the simple case, but how do we do the hard case? How do I do reinforcement learning? Well now we need to integrate my application logic in this. Alright then it's, you know, the next level down of how do you represent that for the runtime? How do you get hardware abstraction? And then you get to the next level down of saying like, forget about abstraction. How do I get the peak performance out of my tpu or my iphone accelerator or whatever. Right. And all these different things. And so this is a layered problem with a lot of really interesting uh design and work going on in the space and a lot of really smart people working on it. Machine learning is a very well funded area of investment right now. And so there's a lot of progress being made. So how </s><s>[INST] much innovation is there on the lower level? So closer to the, to the A six? So redesigning the hardware or redesigning concurrently compilers with that hardware? Is that if you were to predict the biggest uh, you know, the equivalent of moore's law, improvements in the inference and the training of neural networks. Just all of that. Where is that going to come from? You think [/INST] sure, you get scalability have different things and so you get, you know, jim Keller shrinking process technology, you get Three nanometer instead of five or 7 or 10 or 28 or whatever. Um and so that that marches forward that provides improvements, you get architectural level performance and so the, you know, a tpu with a matrix multiply unit, a systolic array is much more efficient than having a scalar core. Doing multiplies and adds and things like that. You then get uh uh system level improvements. So how you talk to memory, how you talk across a cluster of machines, How you scale out how you have fast interconnects between machines, you then get system level programming model. So now you have all this hardware, how to utilize it. You then have algorithmic breakthroughs where you say, Hey, Wow, cool. Instead of training in uh, you know, resident 50 and uh a week, I'm now training it in 25 seconds. Uh it's a combination, is a combination of, you know, new new optimizers and new new new just training regimens and different different approaches to train and and all of these things come together to push the world forward. </s><s>[INST] That was a beautiful exposition. But if you were to uh force to put all your money and one of these, which why do we have to uh [/INST] that's that we unfortunately have people working in all this. It's an exciting time. </s><s>[INST] Right? So, I mean, you know, open the, I did this little paper showing the algorithmic improvement, you can get, there's been, you know, improving exponentially, I haven't quite seen the same kind of analysis on other layers of the stack you I'm sure it's also improving significantly. I just it's uh it's a nice intuition Bill there. I mean, there's a reason why moore's Law. That's the beauty of moore's Law's, somebody writes a paper that makes a ridiculous prediction. Yeah. And it, you know, it becomes reality in a sense. There's there's something about these narratives when you when chris Latner on a silly little podcast makes bets all this money on a particular thing. Somehow it can have a ripple effect of actually becoming real. That's an interesting aspect of it because like, it might have been uh you know, we focused with moore's Law. Most of the computing industry, really, really focused on the hardware. I mean, software innovation, I don't know how much software innovation was in terms of intel, given bill takes away. Yeah, I mean, compiler has improved significantly also. Well, [/INST] Not, not really. So actually, I mean, I'm joking about how soft has gotten slower. Pretty much as fast as harder, got better, at least in the 90s. Um there's another joke, another law and compilers, which is called, I think it's called Probe Stein's law, which is uh compilers double the performance of any given code every 18 years. So </s><s>[INST] they move slowly. Yeah. So, uh yeah, it's exponential also, Yeah, you're [/INST] making progress, but there again, it's not about the power of compilers is not just about how you make the same thing go faster. It's how do you unlock the new hardware? A new chip came out? How to utilize it? You say, oh the programming model, How do we make people more productive? How do we, how do we uh like have better error messages? Even such mundane things? Like how do I generate a very specific error message about your code actually makes people happy because they know how to fix it. Right trump comes back to how do you help people get their job done? </s><s>[INST] Yeah. And yeah. And then in this world of exponentially increasing smart toasters, how do you uh expand, competing to uh do all these kinds of devices? Do you see this world where just everything is a computing surface? You see that possibility? Just everything is a computer. Yeah, [/INST] I don't see any reason that that couldn't be achieved. It turns out that sand goes into glass and glass is pretty useful too. And you know, why not? </s><s>[INST] Why not? So uh very important question then, if um if we're living in a simulation and the simulation is running a computer, like what was the architecture that computer do you think? [/INST] So you're saying, is it a quantum system, is it like </s><s>[INST] This whole quantum discussion isn't needed? Or can can we run it on a, you know, with a risk? five architecture, a bunch of Cpus I [/INST] think it comes down to the right tool for the job. And so </s><s>[INST] what's the job? [/INST] Yeah, exactly. That's that's my question and I get that job made the universe compiler. Um uh and so there as far as we know, quantum quantum quantum systems with the bottom of the pile of turtles </s><s>[INST] so far. Yeah. [/INST] And so we don't know efficient ways to implement quantum systems without using quantum computers. </s><s>[INST] And that's totally outside of everything we've talked about. [/INST] But who runs that quantum computer? Yeah. Right. So if it if it if we really are living in a simulation than is it bigger quantum computers, is it different ones? Like how does that work out? Does that scale? </s><s>[INST] Well, it's it's the same size. It's the same size. But then but then the thought of the simulation is that you don't have to run the whole thing that, you know, we humans are cognitively very limited checkpoints, checkpoints. Yeah. And uh and if we the point at which we humans, so you basically do minimal amount of uh what is it? Uh Swift does on right copy copy. So you only you only adjust the simulation every [/INST] parallel universe theories. Right? So every time a decision is made. Yeah, somebody opens the short in your box, then uh there's a four and then this could happen. </s><s>[INST] And and then uh thank you for uh for considering the possibility. But yeah, so it may not require, you know, the entirety of the universe is simulated. But it's uh interesting too. Think about uh as we create this this higher and higher fidelity systems. But I do want to ask on the, on the quantum computer side because everything we've talked about with, you work with Science five. With everything with compilers, None of that includes quantum computers. Right. So if you ever thought about what, you know, this whole serious engineering work, a quantum computers looks like of compilers of architectures, all that kind of stuff. So [/INST] I've looked at a little bit, I know almost nothing about it, which means that at some point I will have to find an excuse to get involved because that's what do you </s><s>[INST] think? Do you think that's the thing to be like with your little tingly senses of the timing of when to be involved? Is it not yet? Well, [/INST] so, so the thing I do really well is I jump into messy systems and figure out how to make them figure out what the truth and the situation is. Try to figure out what um what the unifying theory is, how to like factor the complexity had to find a beautiful answer to a problem that um has been well studied and lots of people have bashed their heads against it. I don't know that quantum computers are mature enough and accessible enough to be. Um </s><s>[INST] they figured [/INST] out yet. Right. And um the I think the open question with quantum computers, is there a useful problem that gets solved with quantum computer that makes it worth the economic cost of like having one of these things and having having legions of people that that that set it up, You go back to the 50s, right? And there's the projections of the world will only need 77 computers. Right. Well, and part of that was that people haven't figured out what they're useful for. What are the algorithms we want to run? What are the problems get solved? And this comes back to how do we make the world better? Either economically or making someone's life better or like solving a problem that wasn't solved before? Things like this. And um I think that just were a little bit too early in the development cycle because it's still like literally a science project, not a negative connotation, right? It's literally a science project. And um the progress that is amazing. And so I don't know if it's 10 years away if it's two years away exactly where that breakthrough happens, but um you look at machine learning it, we went through a few winners before the Alexa net transition and then suddenly had its breakout moment and that was the catalyst that then drove the talent flocking into it. That's what drove the economic applications of it. That's what drove the um the technology to go faster because you know, have more minds thrown at the problem. This is what caused like a serious knee and deep learning and the algorithms that we're using and um, and so I think that's what quantum needs to go through. And so right now it's in that, that formidable finding itself getting the, the, like literally the physics figured out and, and, and, and then </s><s>[INST] it has to figure out the application that makes, that's useful [/INST] Right now. I'm not skeptical that I think that will happen. I think it's just, you know, 10 years away. Something like that. I forgot to </s><s>[INST] ask what programming language do you think the simulation is written in? [/INST] Probably lisp, </s><s>[INST] so not swift. Like if you were, you were at the bet, uh, I'll just leave it at that. So I mean we've mentioned that you worked with all these companies, we've, we've talked about all these projects. It's kind of if we just step back and zoom out about the way you did that work and we look at covid times this pandemic, we're living through that may if I look at the way Silicon Valley folks are talking about it, the way it is talking about it, this might last for a long time? Uh, not just the virus, but the, the remote nature, [/INST] the economic impact. Yeah, yeah. It's gonna be a mess. </s><s>[INST] Do you think uh, what's your prediction, I mean from sci fi to google to uh, uh, to just all the places you've worked into Silicon Valley, you're in the middle of it. What do you think is how is this whole place is going to change? Yeah. [/INST] So, I mean, I really could only speak to the tech perspective I am in that bubble. Um I think it'll be really interesting because the, you know, the zoom culture of being remote and on video chat all the time has really interesting effects on people. So on the one hand, it's a great normalize, er it's a normal Isar that I think will help communities of people that have traditionally been underrepresented because now you're taking in some cases a face off because you don't have to have a camera going right? And so you can have conversations without physical appearance being part of the part of the dynamic, which is pretty powerful. You're taking remote employees that have already been remote and you're saying you're now on the same level and foot footing as everybody else. Nobody gets whiteboards, you're not gonna be the one person doesn't get to be participating in the white board conversation. And that's pretty powerful. Um you've got uh you're forcing people to think uh a synchronously in some cases, because it's hard to just just get people physically together and the bumping into each other forces people to find new ways to solve those problems. And I think that that leads to more inclusive behavior, which is good. On the other hand, it's also it just sucks right. And so </s><s>[INST] um the nature the actual communication, it just sucks being not with people, like on a daily basis and collaborating with them. [/INST] Yeah, all of that. I mean, everything, this whole situation is terrible. Um what I meant primarily was the I think the most humans like working physically with humans, I think this is something that not everybody, but many people are programmed to do. And I think that we get something out of that, that it's very hard to express, at least for me. And so maybe this isn't true of everybody, but And so the question to me is, you know, when you get through that time of adaptation, you get out of March in april and you get into december and you get into next March, if it's not changed, </s><s>[INST] right? It's already terrifying. [/INST] Well, you think about that and you think about what is the nature of work and how do how do we adapt? And humans are very adaptable species, right? We can we can learn things and when we're forced to and there's a catalyst to make that happen. And so what is it that comes out of this? And are we better or worse off? Right. I think that, you know, you look at the bay Area, housing prices are insane. Well, why? Well, there's a high incentive to be physically located because if you don't have proximity, you end up paying for it and commute, right? And there's there has been a huge social social pressure in terms of like you will be there for the meeting, right? Or whatever scenario it is and I think that's gonna be way better. I think it's going to be much more the norm to have remote employees and I think this is gonna be really great. </s><s>[INST] Did you, uh, you have friends or do you hear of people moving? [/INST] I know one family friend that moved, they moved back to michigan and uh, you know, they were a family with three kids living in a small apartment and like we're going insane, right? And they're in tech has been worked for </s><s>[INST] google. So first of all, friends of mine of are in the process of or are have already lost the business, the thing that represents their passion, their dream. It could be small entrepreneur projects, but it could be large businesses, like people that run jim's like [/INST] restaurants, so </s><s>[INST] but also people like look at themselves in the mirror and ask the question of like, what do I want to do in life? For some reason they don't haven't done it until covid, like they really ask that question and that results often in moving or leaving the company here with starting your own business or transitioning to different company. Do you think we're going to see that a lot, like [/INST] I can't speak to that, I mean we're definitely gonna see it at a higher frequency than we did before just because I think what you're trying to say is there are decisions that you make yourself big life decisions that you make yourself and like I'm gonna quit my job and start a new thing. There's also decisions get made for you. Like I got fired from my job, what am I going to do? Right. And that's not a decision that you think about, but you're forced to act okay. And so I think that those, you're forced to act kind of moments where like, you know, global pandemic comes and wipes out the economy and now your business doesn't exist. I think that does lead to more reflection, right? Because you're less anchored on what you have and it's not a, what do I have to lose versus what do I have to gain a b comparison. It's more of a fresh slate. Cool. I could do anything now. Do I want to do the same thing I was doing? Did that make me happy? Is this now time to go back to college and take a class and learn learn new skill. Is this, is this the time to spend time with family if you can afford to do that, is this time to like, you know, literally move into the parents, right? I mean all these things that were not normative before suddenly become, I think very value system has changed and I think that's actually a good thing in the short term at least because um, it leads to, you know, there's kind of been an over optimization along 11 set of priorities for the world and now maybe we'll get to more balance and more interesting world where the people are doing different things. I think it could be good. I think there could be more innovation that comes out of it. For example, </s><s>[INST] what do you think about the all the social chaos in the middle of like it sucks. You think it's uh let me ask you hope you think it's all gonna be okay? [/INST] Well I think humanity will survive the next extension. Oh we're not going to kill. Yeah. Well yeah I don't think the virus is going to kill all the humans. Um I don't think all the humans are gonna kill all the humans. I think that's unlikely. But um I look at it as uh um progress requires a catalyst, right? So so you need you need a reason for people to be willing to do things that are uncomfortable. I think that the U. S. At least. But I think the world in general is a pretty uh an optimal place to live in for a lot of people. And I think that what we're seeing right now is we're seeing a lot of unhappiness and because because of all the pressure because of all the badness in the world that's coming together, it's really kind of igniting some of that debate that it should have happened a long time ago, right? I mean I think that we'll see more progress you're asking about offline, you're asking about politics and wouldn't be great if politics move faster because there's all these problems in the world and we can move it. Well people are intentional are inherently conservative and so if you're talking about conservative people, particularly if they have heavy burdens on their shoulders because they represent literally thousands of people, um it makes sense to be conservative, but on the other hand, when you need change, how do you get it? Global pandemic will probably lead to some change and it's not a directed, it's not directed plan. But I think that it leads to people asking really interesting questions and some of those questions should have been asked a long time ago. </s><s>[INST] Well let me know if if you've observed this as well, something that's bothering me in the machine learning community, I'm guessing it might be prevalent in other places is um something that feels like in 2020 increase the level of toxicity like people are just quicker to pile on to just be just harsh on each other to to like mob uh pick a person that screwed up? Uh and like make it a big thing. And uh is there something that we can like have you observed that in other places? Is there is there some way out [/INST] of this? I think there's an inherent thing in humanity that's kind of an us versus them thing, which is that you want to succeed and how do you succeed? Well it's relative to somebody else. And so what's happening in at least in some part is that with the internet and with online communication the world's getting smaller right? And so you were having some of the social ties of like my my town versus your town's football team right? Turn into a much larger, larger and yet shallower problems and people don't have time the incentives Clickbait and like all these things kind of really really feed into this machine and I don't know where that goes. Um </s><s>[INST] Yeah I mean the reason I think about that I mentioned to you this I'll fly in a little bit but uh you know I have a few difficult conversations scheduled some of them political related, some of them within the community. Uh difficult personalities that went through some stuff. I mean one of them I've talked before, I will talk again is Yama kun you got have a little bit of crap on twitter uh for uh for talking about a particular paper and the bias within a data set. And then there's been a huge uh in my view and I'm willing comfortable saying it uh irrational, overexaggerated pile on on his comments because he made pretty basic comments about the fact that if there's bias in the data that's going to be bias in the results. So we should not have bias in the data but people piled onto him because he said he trivialized the problem of bias. Like it's a lot more than just bias in the data. But like yes, that's a very good point. But that's that's [/INST] not what he was saying. </s><s>[INST] It's not what he was saying. And the response like the imply response that he's basically sexist and racist uh is uh is something that completely drives away the possibility of a nuanced discussion. One nice thing about like a pocket long form uh conversation as you can talk it out, you can lay your reason out and even if you're wrong, you can still show that you're a good human being underneath it. [/INST] You know your point about you can't have a productive discussion. How do you get to the point where people can turn, they can learn, they can listen, they can think they can engage versus just being a shallow like like and then keep moving right? And I don't think that that progress really comes from that right? And I don't think that one should expect that I think that you would see that as reinforcing individual circles and the US versus them thing and I think that's fairly divisive. </s><s>[INST] Yeah, I think there's a big role in like the people that bother me most on twitter when I observe things is not the people who get very emotional angry like over the shop, it's the people who like prop them up. It's all the it's that's I think what should be the we should teach each other is to be sort of empathetic. [/INST] The thing that it's really easy to forget, particularly on like twitter or the internet or email is that sometimes people just have a bad day. Yeah, right? You have a bad day or you're like, I've been in this situation where it's like between meetings like fire up a quick response and emails because I want to help get something unblocked phrase. It really objectively wrong. I screwed up and suddenly this is now something that sticks with people and it's not because they're bad. It's not because you're bad. Just psychology of like you said a thing. Um it sticks with you. You didn't mean it that way, but it really impacted somebody because the way they interpret it and this is just an aspect of working together as humans. And I have a lot of optimism in the long term, the very long term about what we as humanity can do, but I think that's going to be, it's just always a rough ride. And you came into this by saying like what is covid and all the social strife that's happening right now mean and I think that it's really bad in the short term, but I think it will lead to progress and for that I'm very thankful. </s><s>[INST] Yeah, painful in the short term though. Well [/INST] yeah, I mean people are out of jobs, like some people can't eat like it's horrible and but but you know, it's progress, so we'll see, we'll see what happens. I mean, the real question is when you Look back 10 years, 20 years, 100 years from now, how do we evaluate the decisions are being made right now? I think that's really the way you can frame that and look at it and you say, you know, you integrate across all the short term horribleness that's happening and you look at what that means and is the, you know, improvement across the world or the regression across the world uh significant enough to make it a good or a bad thing. I think that's the question, </s><s>[INST] yep, and for that, it's good to study history and I mean, one of the big problems for me right now is I'm reading the rise and fall of the third Reich like reading. So it's everything is just, I just see parallels and it means it's you have to be really careful not to overstep it, but just the the thing that worries me the most is the pain that people feel when uh come when a few things combined, which is like economic depression, which is quite possible in this country. And then just being disrespected uh i in some kind of way which the german people were really disrespected by most of the world of like in a way that's over the top that something can, can build up and then all you need is a charismatic leader, uh just to go either positive or negative and both work as long as they're charismatic, and there [/INST] is taking advantage of again, that that inflection point that the world's end and what they do with it could be good or bad, </s><s>[INST] And so it's a good way to think about times now, like on the individual level, what we decided to do is when, when history is written, you know, 30 years from now, what happened in 2020? Probably, history's going to remember 2020, I think either for good or bad, and it's like up to us to write it, so it's good. [/INST] One of the things I've observed that I find fascinating is most people act as though the world doesn't change. You make decision knowingly right? You make a decision where you're predicting the future based on what you've seen in the recent past, and so if something has always been has rained every single day, then of course you expected to rain today to write on the other hand, the world changes all the time constantly, like for better and for worse? Right? So the question is, if you're interested in something that's not right, what is the inflection point that led to a change and you can look to history for this, like what is what is the catalyst that led to that, that explosion that led to that bill that led to the, like you can kind of work your way backwards from that and maybe if you pull together the right people and you get the right ideas together, you can actually start driving that change and doing in a way that's productive and hurts fewer people </s><s>[INST] like a single person single event can turn all of [/INST] absolutely everything starts somewhere and often it's a combination of multiple factors, but, but yeah, this is, these things can be engineered, </s><s>[INST] that's actually the optimistic view that [/INST] I'm a long term optimist on pretty much everything and human nature. You know, we can look at all the negative things that the humanity has all the pettiness and all the like self, self serving this and they just the cruel there, right, the biases, the just humans can be very horrible, but on the other hand, were capable of amazing things and um, and the progress across, you know, 100 year chunks is striking and even across decades we've come a long ways and there's still a long ways to go, but that doesn't mean that we've stopped, </s><s>[INST] Yeah, that kind of stuff we did in the last 100 years is unbelievable. It's kind of scary to think what's going to happen this 100 year. It's scary like exciting, like scary in a sense that it's kind of sad that the kind of technology is going to come out in 10 2030 years we're probably too old to really appreciate, you don't grow up with it. It'll be like kids these days with their virtual reality and they're [/INST] uh trucks and stuff like this, like what is this thing? And like come on, give me my uh you know, static photo </s><s>[INST] My Commodore 64. Yeah, exactly. Okay. Uh sorry, we kind of skipped over, let me ask on, you know, the machine learning world has been kind of inspired their imagination captivated with GPT three and these language models I thought would be cool to get your opinion on it. What's your thoughts on this exciting world of it connects the computation actually uh of language models that are huge and take multiple many many computers, not just the train, but to also do inference on your. [/INST] Well, I mean it depends on what you're speaking to there. But I mean, I think that there's been a pretty well understood maximum deep learning that if you make the model bigger and you shove more data into it, assuming you train it right and you have a good model architecture that you'll get a better model out. And so on one hand, gpt three was not that surprising. Um on the other hand, a tremendous amount of engineering went into making it possible. Um the implications of it are pretty huge. I think that when GPT two came out there was a very provocative blog post from open ai talking about, you know, we're not going to release it because of the social damage it could cause if it's misused. Um I think that's still a concern, I think that we need to look at how technology is applied and, you know, well meaning tools can be applied in very horrible ways and they can have very profound impact on that. Um I think the GPT three is a huge technical achievement and what will GPT four b will probably be bigger and more expensive train, really cool architectural tricks. </s><s>[INST] What do you think is there, I don't know how much thought you've done on distributed computing. Uh Is there is there some technical challenges that are interesting that you're hopeful about exploring in terms of, you know, a system that like a piece of code that, you know, the GPT for uh that might have, I don't know, hundreds of trillions of parameters would have to run on thousands of computers. Is there some is there some hope that we can make that happen? [/INST] Yeah, well, I mean today you can you can write a check and get access to 1000 tpu cores, and do you really interesting large scale training and inference and things like that um in google cloud for example. Right. And um so I don't think it's a question about scales, question about utility and when I look at the transformer series of architecture, is the GPT series is based on, it's really interesting to look at that because they're actually very simple, simple designs, they're not recurrent. Um the training regimens are pretty simple, um and so they don't really reflect like human brains, right? Um but they're really good at learning language models and they're unrolled enough that you get, you can simulate some recurrence. Right? And so the question I think about is where does this take us? Like, so we can just keep scaling it have more parameters, more data, more things will get a better result for sure. But are their architectural techniques that can lead to progress at a faster pace? Right? This is when you know, how do you get? So just like making a constant time bigger? How do you get like an algorithmic improvement out of this? Right. And whether it be a new training regimen, if it becomes um uh sparse, sparse networks, for example, the human brain sparse all these networks are dense. Um the connectivity patterns can be very different. I think this is where I get very interested and I'm way out of my league on the deep learning side of this. But I think that could lead to big breakthroughs when you talk about large scale networks. One of the things that Jeff Dean likes to talk about and he's uh given a few talks on, is this idea of having a sparsely gated mixture of experts, kind of a model where you have, um, you know, different nets that are trained and are really good at certain kinds of tasks. And so you have this distributed across the cluster and so you have a lot of different computers that end up being kind of locally specialized in different demands and then when a query comes in, you you get it and you'll learn techniques to route to different parts of the network and then you utilize the compute resources of the entire cluster by having specialization within it and I don't know where that goes or if it starts to when it starts to work, but I think things like that could be really interesting as well </s><s>[INST] and on the data side too, if you can think of data selection as a kind of programming. I mean essentially if you look at like Karpati talked about software to point out, I mean in a sense, data is the program. [/INST] Yeah, yeah, so I I just so let me try to summarize Andres position really quick before I disagree with. Yeah, so on Andrea Carpathia is amazing. So this is nothing, nothing personal with him. He's an amazing engineer and </s><s>[INST] and also a good [/INST] blog post writer. </s><s>[INST] Yeah, well [/INST] he's a great communicator, he's just an amazing person. He's also really sweet. Um so his basic premise is that uh software is suboptimal, I think we can all agree to that uh he also points out that deep learning and other learning basic techniques are really great because you can solve problems and uh more structured ways with less like add hot code that people right out and don't write test cases for in some cases, and so they don't even know if it works in the first place. Um and so if you start replacing systems of imperative code with deep learning models then you get better, a better result. Okay, And I think that he argues that software to dot oh is a pervasively learned set of models and you get away from writing code and he's given talks, he talks about, you know, swapping over more and more and more parts of the code to being learned and driven that way. I think that works and if you're predisposed to liking machine learning, then I think that that's that's that's definitely a good thing. I think this is also good for accessibility in many ways because certain people are not going to write c code or something. And so having a data driven approach to do this kind of stuff I think can be very valuable on the other hand, there huge trade offs and it's not clear to me that software to dato is um the answer and probably andre wouldn't argue that it's the answer for every problem either, but I look at machine learning is not a replacement for software window, I look at it as a new programming paradigm and so programming paradigms when you look across across domains is they are structured programming where you go from go twos to if then else or functional programming from lisp and you start talking about higher order functions and values and things like this. Or you talk about object oriented programming, you're talking about encapsulation, sub classing inheritance. You start talking about generic programming, we start talking about code reuse through through a specialization in different types of sensations. Um When you start talking about differentiable programming, something that I am very excited about in the context of machine learning, Talking about taking functions and generating variants like the derivative of another function. Like that's a programming paradigm is very useful for solving certain classes of problems. Machine learning is amazing solving certain classes of problems, like you're not going to write a cat detector or even a language translation system by writing C code that's not gonna that's not a very productive way to do things anymore. And so machine learning is absolutely the right way to do that. In fact, I would say that learned models are really one of the best ways to work with the human world in general. And so anytime you're talking about sensory input of different modalities, anytime that you're talking about um generating things in a way that makes sense to human, I think that learned models are really, really useful and that's because humans are very difficult to characteristics. Okay, and so this is a very powerful paradigm for solving classes of problems. But on the other hand, uh imperative code is to you're not gonna write a bootloader for your computer with a deep learning model. Deep learning models are very hardware intensive. They're very energy intensive because you have a lot of parameters and you can probably implement any function with a learned model like this has been shown but that doesn't make it efficient. And so if you're talking about caring about a few orders of magnitudes worth of energy usage then it's useful to have other tools in the </s><s>[INST] toolbox. It's just a robustness to I mean [/INST] exactly all the problems of dealing with data and bias and data, all the problems of you know suffer too dot oh and one of the great things that Andres is arguing towards which I completely agree with them is that when you start implementing things with deep learning, you need to learn from software one dot Oh in terms of testing continuous integration, how you deploy, how do you validate all these things and building building systems around that? So you're not just saying like oh it seems like it's good ship it. Right. Well what happens when I regret something, what happens when I make a classification? That's wrong? And now I heard somebody right? I mean the same to you have to reason about </s><s>[INST] Yeah, but at the same time the bootloader that works for our forest humans is uh looks awfully a lot like a neural network right? It's messy and you can cut out different parts of the brain. There's a lot of this New York plasticity work that shows it's gonna just, it's uh, it's a really interesting question. How much of the world programming could be replaced by software 2.0 like with [/INST] Well, I mean it's probably true that you could replace all of it. </s><s>[INST] Right? So then [/INST] so anything that's a function you can. So it's not a question about if I think it's a economic question, it's a, what kind of talent can you get? What kind of trade offs in terms of maintenance? Right. Those kinds of questions. I think, what kind of data can you collect? I think one of the reasons that I'm most interested in, uh machine learning is a programming paradigm. Is that one of the things that we've seen across computing in general is that being laser focused on one paradigm often Put you in a box. It's not super great. And so you look at object very programming. Like it was all the rage in the early 80s and like everything, it has to be objects and people forgot about functional programming even though came first. And, and then people rediscover that hey, if you mix functional and object oriented and structure, like mix these things together, you can provide very interesting tools that are good at solving different problems. And so the question there is how do you get the best way to solve the problems? It's not about who's tribe should win, right? It's not about, you know, that that that shouldn't be the question. The question is how do you make it so that people can solve those problems the fastest and they have the right tools in the box to build good libraries and they can solve these problems. And when you look at that, that's like, you know, you look at reinforcement learning as one really interesting subbed amount of this reinforcement learning. Often you have to have the integration of a learned model combined with your Atari or whatever the other scenario it is that you're working in, you have to combine that that thing with the robot control for the arm. Right. And so now it's not just about that one uh paradigm. It's about integrating that with all the other systems that you have, including often legacy systems and things like this. Right. And so to me, I think that the interesting the interesting thing to say is like how do you get the best out of this domain? And how do you enable people to achieve things that they otherwise couldn't do without excluding all the good things we already know how to do. </s><s>[INST] Right. But okay, this is just a crazy question. But we talked a lot about about GPT three. But do you think it's possible that these language models That uh in essence in the language domain software 2.0, could replace some aspect of compilation for example or do program synthesis, replace some aspect of programming? [/INST] Yeah, absolutely. So I think that that learned models in general are extremely powerful and I think the people underestimate them, um </s><s>[INST] maybe you can suggest what I should do. So uh you know, have access to the GPT three. Ap I would I be able to generate swift code for example, do you think that could do something interesting and uh [/INST] GTT three is not probably not trained on the right corpus, so it probably has the ability to generate some swift. I bet it does. It's probably not going to generate a large enough body of swift to be useful, but but like taking the next step further. Like if you had the goal of training something like GPT three and you wanted to try and generate source code right? It could definitely do that. Now the question is how do you express the intent of what you want filled in? You can definitely like Right, right, scaffolding of code and say fill in the hole and sort of putting some four loops and put in some classes or whatever. And the power of these models is impressive. But there's an unsolved question at least unsolved to me, which is how do I express the intent of what to fill in? Right. And kind of what you'd really want to have. And I don't know that these models are up to the task is you want to be able to say um here's the scaffolding and here the assertions at the end and the assertions always pass. And so you want a generative model on the one hand. </s><s>[INST] Yes. [/INST] Right? But you also want some loop back some reinforcement learning system or something where you're actually saying like I need to heal, climb towards something that is more correct. And I don't know that we have that. </s><s>[INST] So it would generate not only a bunch of the code, but like the checks that do the testing. It would generate the test. I think [/INST] I think the humans will generate the test. Okay. The test would be fascinating if the test of the requirements. </s><s>[INST] Yes. But okay. So because you [/INST] have you have to express to the model what you want to you don't just want gibberish code. Look at how compelling this code looks. You want a story about four horned unicorns or something. </s><s>[INST] Well, okay, so exactly. But that's human requirements. But then I thought it's a compelling idea that the GPT four model could generate uh checks like that are more high fidelity that check for correctness because uh the code it generates like say I ask it to generate a function that gives me the fibonacci sequence. I don't like uh [/INST] so decompose the problem. Right? So, you know, you have two things you have, you need the ability to generate some tactically correct swift code. That that's interesting. Right? I think GPT series of model architectures can do that. But then you need the ability to add the requirements. So generate Fibonacci, the human needs to express that goal. We don't have that language that I know of. No, I mean, it can </s><s>[INST] generate though. Have you seen with GPT three can generate, you can say, I mean there's uh interface stuff, like it can generate html, it can generate basic four loops that give you like, [/INST] pick html. How do I say I want google dot com. </s><s>[INST] Well, no, you can say [/INST] are not, not literally google dot com. How do I say? I want a web page that's got a shopping cart into this and that </s><s>[INST] that does that mean? So Okay, so just, I don't know if you've seen these demonstrations, but you type in, I want a red button with the text that says hello and you type that natural language and it generates the correct gmo get done this demo, It's kind of compelling. So you have to uh prompted with similar kinds of mapping. Of course, it's probably hand picked. I got to experiment that probably. But the fact that you can do that once, even after like 20. [/INST] Uh </s><s>[INST] it's quite impressive. Again, that's very basic uh like the html was kind of messy and bad, but yes, the intent is the idea is the intent that specified in natural language. [/INST] And so I have not seen that. That's really cool. </s><s>[INST] Yeah, yeah, but the question is uh the correctness of that, like, visually, you can check, oh, the button is red but the for more uh for more complicated functions or the intent is harder to check. This goes into like and be completing this kind of things. Like I want to know that this code is correct and generates a giant thing that uh just some kind of calculation, it seems to be working. It's interesting to think like should the system also tried to generate checks for itself for correctness? [/INST] Yeah, I don't know. And this is this is way beyond my experience. The thing that I think about is that there doesn't seem to be a lot of equation or reasoning going on. There's a lot of pattern matching and filling in and kind of propagating patterns that have been seen before into the future and into the generator result. And so if you want to get correctness, you kind of need to improving kind of things and like higher level logic and I don't know that you can talk to you about that and see and see what the bright minds are thinking about right now. But I don't think the GPT is in that vein? It's still really cool. </s><s>[INST] Yeah. And surprise, who knows, you know, maybe reasoning is is operated Yeah, [/INST] right. I mean, do we reason, how do you tell are we just pattern matching based on what we have and then reverse justifying to ourselves. Exactly </s><s>[INST] the verse. So like, I think what the neural networks are missing and I think GPT four might have is to be able to tell stories to itself about what it did. [/INST] Well, that's what humans do, right? I mean you talk about like network explain ability, right? And we give no, that's a hard time about this. But humans don't know why we make decisions. We have this thing called the intuition and then we try to like say this feels like the right thing, but why? Right? And you know, you wrestle with that when you're making hard decisions and it's that science not really </s><s>[INST] let me ask you about a few high level questions, I guess is um you've done a million things in your life. Have been very successful. A bunch of young folks listen to this ask for advice from successful people like you uh if you were to give advice to somebody, you know, another graduate student or some high school student about pursuing a career in computing or just advice about life in general is there there's some words of wisdom you can give them. [/INST] So I think you come back to change and profound leaps happen because people are willing to believe that change is possible and that um the world does change and are willing to do the hard thing that it takes to make change happen and whether it be influencing a new programming language or implying new system or employing new research paper designing a new thing, moving the world forward in science and philosophy, whatever it really comes down to somebody who's willing to put in the work, right? And you have, the work is hard for a whole bunch of different reasons. One of which is, um, you, uh, it's work, right? And so you have to have the space in your life in which you can do that work, which is why going to grad school can be a beautiful thing for certain people. Um, but also there's a self doubt that happens like you were two years into a project isn't going anywhere. Right? Well, what do you do do you do? You just give up because it's hard, you know, I mean, some people like suffering. Um, and so you plow through it, the secret to me is that you have to love what you're doing and, and follow that passion because if, when you get to the hard times, that's when, you know, if you, if you love what you're doing, you're willing to kind of push through. And um, this is really hard because it's hard to know what you will love doing until you start doing a lot of things. And so that's why I think that particularly early in your career, it's good to experiment, do a little bit of everything, Go take the survey class on, you know, for the first half of every class in your upper division, you know, lessons and um, just get exposure to things because certain things will resonate with you and you'll find out, wow, I'm really good at this. I'm really smart at this. Well it's because it works with the way your brain </s><s>[INST] and when something jumps out, I mean that's one of the things that people often ask about is like, well I think there's a bunch of cool stuff out there. Like how do I pick the thing? Like uh how do you, how do you hook in your life? How did you just hook yourself in and stuck with it? [/INST] Well, I got lucky, right? I mean I think that many people forget that a huge amount of it or most of it is luck, right? So um let's not forget that. Um So for me, I fell in love with computers early on because I'm, they spoke to me I guess </s><s>[INST] uh language did they speak [/INST] basic, </s><s>[INST] Basic? [/INST] Um but the uh but then it was just kind of following a set of logical progressions but also um deciding that something that was hard was worth doing and a lot of fun. Right? And so I think that that is also something that's true for many other demands, which is if you find something you love doing, that's also hard if you invest yourself in it and add value to the world, then it will mean something generally right? And again that can be a research paper that can be a software system that can be a new robot that can be that there's many things that that that can be, but a lot of it is like real value comes from doing things that are hard and it doesn't mean you have to suffer, but it's hard. I </s><s>[INST] mean you don't often hear that message we talked about last time a little bit, but it's one of my favorite. Not enough people talk about this. Uh it's uh it's beautiful to hear a successful person well [/INST] and self doubt and imposter syndrome and these are all things that uh successful people suffer with as well, particularly when they put themselves in a point of being uncomfortable, which um I like to do now and then just because it puts you in learning mode, like if you want to, if you want to grow as a person, put yourself in a room with a bunch of people that know way more about whatever you're talking about than you do and ask dumb questions and guess what smart people love to teach often, not always, but often. And if you listen, if you're prepared to listen, if you're prepared to grow, if you're prepared to make connections, you can do some really interesting things. And I think a lot of progress is made by people who kind of hot between domains now and then because they bring uh they bring a perspective into a field that nobody else has, if people have only been working in that field themselves. </s><s>[INST] We mentioned that the universe is kind of like a compiler, uh you know, the the entirety of it, the whole evolution is kind of a kind of compilation maybe are as human beings are kind of compilers. Um let me ask the old sort of question that I didn't ask you last time, which is uh, what's the meaning of it all? Is there meaning like if you asked to compile or why, what would a compiler say? What's the meaning of life? [/INST] What's the meaning of life? Uh you know, I'm prepared for it not to mean anything here. We are all biological things programmed to survive and and propagator our DNA. Um and maybe the universe is just just a computer and you just go until entropy takes over the world and it takes over the universe and then you're done. Um I don't think that's a very productive way to live your life. If so and so I prefer to bias towards the other way, which is saying the world has the universe has a lot of value and I take uh take happiness out of other people. And a lot of times part of that is having kids, but also the relationships you build with other people. And so the way I try to live my life is like, what can I do that has value? How can I move the world forward? How can I take what I'm good at and like bring it, bring it into the world. And how can I, one of those people that likes to work really hard and be very focused on the things that I do. And so if I'm going to do that, how can it be in a demand that actually will matter? Because a lot of things that we do, we find ourselves in the cycle of like, okay, I'm doing a thing. I'm very familiar with it. I've done it for a long time. I've never done anything else, but I'm not really learning. I'm not really, I'm keeping things going, but there's a, there's a younger generation that, that can do the same thing maybe even better than me, right? Maybe if I actually step out of this and jump into something I'm less comfortable with, it's scary. But on the other hand, um it gives somebody else the new opportunity and also then put you back in learning mode And that can be really interesting. And one of the things I've learned is that when you go through that, that first you're deep into impostor syndrome, but when you start working your way out, you start to realize, hey, well there's actually a method to this and, and now I'm able to add new things because they bring a different perspective and this is one of the, the good things about bringing different kinds of people together, diversity of thought is really important. And um if you can pull together people that are coming at things from different directions, you often get invasion. And I love to see that that aha moment where you're like, what we've like really cracked. This is something that nobody's ever done before. And then if you can do it in the context where it adds value, other people can build on it helps move the world. Then that's what that's what really excites me. </s><s>[INST] So that that kind of description of the magic of the human experience. Do you think we'll ever create that in like an A. G. I. System you think, well, be able to create? Uh give uh give Ai systems the sense of meaning where they operate in this kind of world. Exactly. The way you described, which is they interact with each other. They interact with us humans as [/INST] well. So, I mean, why why are you being so specie ist Right? All right. So, so a Gs vs. Bio net, you know, versus you know, uh what are we about machines? Right. We're just programmed to run our we have our objective function that we are optimized for. Right. And so we're doing our thing. We think we have purpose. But do we Really? Right. I'm not prepared to say that those newfangled Gs have no soul just because we don't understand them. Right. And I think that would be um when when they exist that would be very premature to uh look at a new thing through your own lens without fully understanding it. Um </s><s>[INST] you might be just saying that because ai systems in the future will be listening to this and then [/INST] oh yeah exactly, you don't want to please be nice to me, you know on Skynet skynet kills everybody. Please spare me </s><s>[INST] wise wise. Uh Look ahead thinking. [/INST] Yeah but I mean I think that people will spend a lot of time worrying about this kind of stuff and I think that what we should be worrying about is how do we make the world better? And the thing that I'm most scared about with the G. I. S. Is not that um that necessarily the sky net will start shooting everybody with lasers and stuff like that to use us for calories. The thing that I'm worried about is that humanity I think needs a challenge. And if we get into a mode of not having a personal challenge, not having a personal contribution, whether that be like you know, your kids and seeing what they grow into and helping helping guide them, whether it be um your community that you're engaged in, your driving forward, whether it be your work and the things that you're doing, the people you're working with in the process of building and the contribution there. If people don't have a objective, I'm afraid what that means and um I think that this would lead to a rise of the worst part of people right? Instead of people striving together and trying to make uh the world better, it could degrade into a very unpleasant world, but but I don't know, I mean we hopefully have a long ways to go before we discover that actually we have pretty on the ground problems with pandemic right now. And so I think we should be focused on that as well. </s><s>[INST] Yeah. Ultimately, just as you said, you're optimistic, I think it helps for us to be optimistic because that's uh take it until you make it. Yeah, [/INST] well, and why not? What's what's the other side? Right. So, I mean, uh I'm not personally a very religious person, but I've heard people say like, oh yeah, of course, I believe in God, of course I go to church because if God is real, I want to be on the right side of that. If it's not really doesn't </s><s>[INST] matter, it doesn't matter. So, [/INST] you know, that's that's a fair way to do it. Um </s><s>[INST] yeah, I mean, the same thing with the nuclear deterrence, all you know, global warming, all these things, all these threats, natural engineered pandemics, all these threats we face. I think it's a uh it's paralyzing to be terrified of all the possible ways we could destroy ourselves. I think it's much better or at least productive to be hopeful and to engineer defenses against these things, to engineer future where like, you know, see like a positive future and engineering that future. [/INST] Yeah. Well, and I think that's another another thing to think about as, you know, a human, particularly if you're young and trying to figure out what it is you want to be when you grow up, like I am um I'm always looking for that. Uh the the question then is how you wanna spend your time and right now there seems to be a norm of being a consumption culture, like I'm gonna watch the news and and revel in how horrible everything is right now, I'm going to go find out about the latest atrocity and find out all the details of like the terrible thing that happened to be outraged by it. Um you can spend a lot of time watching tv and watching the new sitcom or whatever people watch these days, I don't know. Um but that's a lot of hours, right? And those are ours that if you're turned into being productive, learning, growing, experiencing, uh you know, when the pandemic is over going exploring right, he leads to more growth and I think it leads to more optimism and happiness because you're building, right, you're building yourself, you're building your capabilities, you're building your viewpoints, you're building your perspective and um I think that a lot of the the consuming of other people's messages leads to kind of a negative viewpoint, which you need to be aware of what's happening because that's also important, but there's a balance that um I think focusing on creation is a very valuable thing to do. </s><s>[INST] Yeah. So what you're saying is people should focus on working on the sexiest feel of them all, which is compiler design. [/INST] Exactly. Hey, you can go work on machine learning and be crowded out by the thousands of graduates popping out of school that I want to do the same thing or you could work in the place that people over pay you because there's not enough smart people working in it. And uh, here at the end of moore's law, according to some people, </s><s>[INST] uh actually [/INST] the software is the hard part </s><s>[INST] two. optimization is, is truly truly beautiful and also on the YouTube side or education side. Uh, you know, it's, there's um, it'd be nice to have some material that shows the beauty of compilers. That's, that's something. So that's a call for uh, for people to create that kind of content as well. Kriss you're one of my favorite people talk to uh such a huge Jonathan. You would waste your time talking to me. I've always appreciated. Thank you. [/INST] I mean the truth is you spend a lot of time talking to me just on, you know, walks. Another thing that's, it's great to catch up. Thanks </s><s>[INST] thanks for listening to this conversation with Chris Latner and thank you to our sponsors, blink ist an app that summarizes key ideas from thousands of books in Euro, which is a maker of functional gum and mints that supercharged my mind master class, which are online courses from world experts and finally, cash app, which is an app for sending money to friends. Please check out these sponsors in the description to get a discount and to support this podcast. If you enjoyed this thing subscribed on Youtube, review it with five stars on apple podcast, follow on Spotify, Support on Patreon, connect with me on twitter, elects Friedman and now let me leave you. Some words from Chris Lattner, So much of language design is about tradeoffs and you can't see those tradeoffs unless you have a community of people that really represent those different points. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] Thank you for listening to this conversation with scott Aaronson and thank you to our presenting sponsor, cash app, Download it used collects podcast, you'll get $10.10 will go to first an organization that inspires and educates young minds to become science to technology innovators of tomorrow. You enjoy this podcast. Subscribe on Youtube, give it five stars on apple podcast, support on Patreon or simply connect with me on twitter Elex Friedman. Now let me leave you with some words from a funny and insightful blog post scott wrote over 10 years ago on the ever present malthusian. ISMs in our daily lives, quote again and again. I've undergone the humbling experience of first lamenting how badly something sucks. Then only much later having a crucial insight that it's not sucking wouldn't have been a nash equilibrium. Thank you for listening. I hope to see you next time [/INST] </s>

<s>[INST] This is a lex Friedman podcast to support it, please check out our sponsors in the description and now dear friends, here's Fiona Hill, you came from humble beginning in a coal mining town in Northeast England. So what were some formative moments in your young life that made you the woman you are today. [/INST] I was born in 1965 and it was the period where the whole coal sector in Britain was in decline already and, you know, basically, my father, by the time I came along, had lost his job multiple times. Every coal mine he worked in was closing down, he was looking constantly for the work and he had no qualifications because at age 14, he had gone down the mines, his father gone down the mines at 13. His great grandfather, you know, around the same kind of age, I mean, you had a lot of people at different points going down coal mines at 12, 13, you know, 14, they didn't get educated beyond that period because the expectation was, you're going to go down the mine like everybody else in your family and that he didn't really have any other qualifications to, you know, basically find another job beyond something in manual labor. So he worked in a steel works that didn't work out a brickwork, that closed down and then he went to work in the local hospital, part of the National Health Service in the United Kingdom, as a porter and orderly. So basically somebody just pushing people around, there was no opportunity to retrain. So the big issue in my family was education, you've got to have one, you know, you've got to have some qualifications, the world is changing, It's changing really quickly and for you to kind of keep up with it, you're going to have to get educated and find a way out of this? I'm very early on, my father had basically said to me, there's nothing for you here, you're gonna have to if you want to get ahead. And he didn't have any kind of idea that as a girl, I wouldn't, I mean actually in many respects, I think I benefited from being a girl rather than a boy. There was no expectation that I would go into industry. There was, you know, some kind of idea that maybe I, you know, if I got qualifications, I could be a nurse, my mother was a midwife and so she had at age 16, left school and gone to train, you know, as a as a nurse and then as a midwife, I had other relatives have gone to teach, you know, in local schools and so there was an idea that, you know, women could get educated and there was a kind of a range of things that you could do, but the expectation then was go out there, do something with your life, but also a sense that you'd probably have to leave. So all of that was circling around me, particularly in my teenage years as I was trying to find my way through life and looking forward, </s><s>[INST] first of all, what does that even look like uh getting educated given the context of that place. You don't know, there's a whole world of mystery out there. So how do you figure out what to actually do out there. But was there moments formative moments, either challenging or just inspiring, where you wondered about what you want to be, where you want to go? [/INST] Yeah, there, I mean there are a number of things. I mean I think like a lot of kids, you know you talk to people and particularly from blue collar backgrounds said what did you want to do? I wanted to be a fireman, you know you got you know, kind of at one point was a little girl, I wanted to be a nurse and a little nurse's uniform like my mother, I didn't really know what that meant but you know I used to go around pretending to be a nurse. I even had a little magazine called Nurse Nancy and I used to read this and you know kind of that was one of the formative ideas. We also, it was a rural area, semi rural area and you know I'd be out in the fields all the time and I'd watch farmers, you know with their animals and I'd see vets coming along and you know watching people deal with the livestock and there's a kind of famous story at the time about a vet called James Herriot. It became here in the United States as well as a sort of a tv mini series had written a book and he was the vet for my, one of my great Aunt's dogs and people are always talking about him, I thought I could be a vet and then one day I saw one of the local vets with his hand up the back side of a cow in a field and he got his hand stuck in the cow was kicking him and I thought yeah maybe, maybe no, actually no I don't think I want to be a vet. So I cycled through all of these things about okay I could get an education but the whole sense was you had to apply your education, it wasn't an education for education's sake, it was an education to do something. And when I was about 14 or 15 my local member of Parliament came to the school and it was one of these you know pep talks for kids in these you know deprived areas. He had been quite prominent in local education and now he was a member of Parliament. He himself had come from a really hardscrabble background and had risen up through education, had even gone to Oxford and done philosophy, politics and economics and he basically told my class, even though it was highly unlikely any of us were really going to get ahead and go to elite institutions. Look you can get an education, you don't have to be held back by your circumstances but if you do get an education it's a privilege and you need to do something with it. So then I'm thinking, well, what could I do? Okay and education qualifications to do something, most people around me, I didn't, I knew didn't have careers. I mean, my dad didn't really have a career. He had jobs, my mom, you know, thought of her nursing as a career though and and it genuinely was and she was out there trying to help women uh survived childbirth. My mother had these horrific stories, you know, basically over the dining room table, I wish she'd stop, she'd leave out her nursing books. And I tell you if everyone had had my mom as a, as a mother, there'd be no, there'd be no reproduction on the planet. It was just this grim, horrific stories of breech births and fistulas and all kinds of horrors that my sister and I would just go, oh my God, you know what, please stop. So I thought, well, you know, I don't necessarily want to go in that </s><s>[INST] in that [/INST] direction. But it was the timing that really cinched things for me. I was very lucky that the region that I grew up county Durham despite the massive decline, deindustrialization and the complete collapse of the local government system around the still maintained money for education. And they also paid for exchanges and we have exchange programs with uh cities in Germany and France also in Russia, in Kostroma near Yaroslavl, for example, an old textile town similar, you know, down in its kind of region, but quite historic and the Russian context. In fact the original birthplace of the romanov dynasty. Um in customer, just as county Durham, it was quite a distinguished historic area in the, in the british context. And so it was an idea that I could go on exchanges, I could learn languages, I studied german, I studied french And then in 1983 there was the Oscar basically provoked by the euro missile crisis. So the station of new categories of strategic nuclear weapons and intermediate nuclear weapons in Western europe and in eastern europe during the height of the Cold War And the Syrian missile crisis over SS 20 and Pershing missiles went on from 1977. So when I was about 11 or 12, you know, all the way through into the later part of the 1980s. And in 1983 we came extraordinarily close to a nuclear conflict. It was very much another rerun of the Cuban missile crisis of 1962. So 20 years on the same kind of thing, the Soviets misread, Although I didn't know this at the time, I know a lot of this, you know, after the fact, but the tension was palpable. But what happened was the Soviets misread the intentions of a series of exercises operation able archer that the United States was conducting. And actually thought that the United States might be preparing for first nuclear strike and that then set up a whole set of literal chain reactions in the soviet union Eventually it was recognized that, you know, all of this was really based on misperceptions. And of course, you know, that later led to negotiations between Gorbachev and Reagan for the intermediate nuclear forces, the INF Treaty. But in 1983, that tension was just a cute. And for as a teenager, we were basically being prepped the whole time for um the inevitability of nuclear Armageddon. There were Tv series, films in the United States and the UK threads the day after we had all these public service announcements telling us to seek sanctuary or cover in the inevitability of a nuclear blast. And my house was so small, they said, look for a room without a window, there were no rooms without windows. My put on these really thick curtains over the window, you know, instead if there was a nuclear flash, you know, we'd have to, you know, get down on the floor, not look up, but the curtains would help like this is ridiculous, dad. And we would all try to see if we could squeeze in the space under the stairs are covered under the stairs like harry potter and it's all just, you know, totally nuts or go or you have to throw yourself in a ditch if you were outside. And I thought, well this this isn't gonna work. And one of my great uncles who had fought in World War Two said, well look, you're good at languages Fiona, why don't you go and study Russian trying to figure it out, figure out why the Russians are trying to blow us </s><s>[INST] up, because, [/INST] you know, during the exactly during World War Two, the United Kingdom, the United States and the soviet Union had all been wartime allies, and my uncle charlie thought well there's something gone wrong here, Maybe you can figure it out and as you said, go talk to them. So I thought, okay, I'll study Russian, so that's really how this came about. I thought well it's applying education, I'll just do my very best to understand everything I possibly can about the Russian language and the soviet union, and I'll see what I can do, and I thought well maybe I could become a translator. So I had visions of myself sitting around, you know, listening to things in a big headset and you know, basically translating perhaps at some future arms control summit. </s><s>[INST] So how did the journey continue with learning Russian, I mean, this early dream of being a translator and thinking how can I actually help understand and maybe help even deeper way with this conflict that threatens the existence of the human species. Um how did it actually continue? [/INST] Well, I mean, I read everything else actually possibly could about, you know nuclear weapons and nuclear war and you know, I started to try to teach myself, you know, Russian a little bit, it </s><s>[INST] was always in context of nuclear war. [/INST] It was very much in the context of nuclear war at this particular point, but also in historical context because I knew that the United States and the United Kingdom and the soviet union in wartime allies in World War Two. So we try to understand all of that. And also um you know, I like many other people I read, you know, Russian literature in translation, I'd read war and peace and you know, I love the book actually. I mean particularly the, you know, the story parts of it. I wasn't one really at that at that time when I was a teenager, I thought Tolstoy went on a bit, you know, in terms of his series of the gray man in history and you know, kind of social change though now I appreciate it more. But when I was about 14 I was like this man needed an editor, could have just got on with the story of an amazing story when incredible. You know, kind of book, this is, </s><s>[INST] I still think, [/INST] I think his wife tried, didn't she? But he got quite upset with. And then I kind of thought to myself, well how do I how do I study Russian? Because there were very few schools in my region, you know, given the impoverishment of the region where you could study Russian. So I would have to take Russian from scratch. And this is where things get really quite interesting because there were opportunities to study Russian at universities, but I would need to have first of all an intensive Russian language course in the summer and I didn't have the money for that. And the period is around the miners strike in the United Kingdom in 1984. Now the miners of County Durham had very interestingly had exchanges and ties with the miners of Donbass. Going back to the 19 twenties. And as I studied Russian history, I discovered there was lots of contacts between you know, bolshevik soviet union, the early period after the Russian revolution. But even before that, during the imperial period in Russia between the Northern England and the Russian empire in the old industrial areas, basically big industrial areas like the north east of England and players like Don Bass were built up at the same time, often by the same sets of industrialists and Donetsk in the Donbass region used to be called because it was established by a welsh industrialist who brought in miners from Wales to help you know, kind of develop the coal mines there and also the steelworks and others that, you know, we're hearing about all the time. So I got very fascinated in all these linkages and you know, famous writers from the early part of the soviet union, I give Guineas um Yassin worked in the shipyards and Newcastle upon Tyne and there was just this whole set of connections And in 1984 when the miners strike took place, the miners of Donbass along with other miners from famous coal regions like the Ruhr Valley for example in Germany or minors in Poland Sent money in solidarity to the miners of County Durham. And have been these exchanges have said going back and forth since the 1920s, formal exchanges between miners, you know, the region, the miners unions. And I heard again from the same great uncle who told me to study Russian that there were actually scholarships to the Children of miners and it could be former miners as well for their education and I should go along to the miners hall players called Red Hills where the miners of County Durham and actually pulled all of their resources and build up their own parliament and their own, you know, kind of players that they could talk among themselves to figure out how to enhance the welfare and well being of their communities and they put money aside for education for minors. There was all kinds of lecture series from the minors and all kinds of other activities supporting soccer teams and artistic circles and writing circles for example, people like George Orwell, you know, were involved in some of these writers circles in other parts of Britain and mine and communities for example. And so they told me I could, you know go along and basically apply for a grant to go to study Russian. so I show up and it was the easiest, you know, application I've ever come across. They just asked me to, my dad came along with me, they asked me to verify, you know, that my dad had been a miner and they looked up his employment record on little cards, you know, kind of a little a little tray somewhere and then they asked me how much I needed, you know, to basically pay for the travel and some of the basic expenses for the the study and they wrote me a check and so thanks to the miners of Donbass and this money that was deposited with the miners of County Durham, Durham miners association, I got the money to study Russian for the first time before I embarked on my studies at university </s><s>[INST] as you're speaking now, it's reminding me that there's a different way to look both at history and geography in different places is um you know, this is an industrial region. [/INST] That's right </s><s>[INST] and it echoes in the experience of living, there is more captured not by Moscow Kiev by at least historically, but by just being a mining talent industry. [/INST] That's right in the place itself. Yeah, I mean there are places in the United States, in Appalachia and west Virginia and in pennsylvania like the Lehigh Valley that have the same sense of place and the north east of England, you know, was the cradle of the Industrial revolution, it was the industrial version of the, of Silicon Valley, which has its own, I would say contours and frames and when you come to those industrial areas, your previous identities get submerged in that larger framework. I've always looked at the world through that lens of being, you know, someone from the working class, the blue collar communities from a very specific place with lots of historical and economic connotations And it's also a melting pot, which is the problems that the Donbass has experienced over the last 30 years, that people came from all over the place to work there. Of course, there was a population that one might say is indigenous, you know, might have gone back centuries there, but there would have been, you know, in the smaller rural farming communities, just like it was the same in the northeast of England. And people in the case of the north east of England came from Wales, they came from further in the south of England, the Midlands, they came from Scotland, they came from Ireland. Um I have all of that heritage in my own personal background and you've got a different identity and it's when somebody else tries to impose an identity like on you from the outside that things go awry. And I think that that's kind of what we've really seen in the case of Donbass, it's a place that's apart in many respects historically and in terms of its evolution and development over time and you know, particularly in the case of Russia, the Russians have tried to say well look, you know, because most people speak Russia, there is the lingua franca, I mean in the northeast of course everyone spoke english, but lots of people were irish speakers, you know, Gaelic irish speakers or you know some of them might have certainly been welsh speakers, there was lots of welsh miners who spoke welsh as their first language who came there, you know, but they but they created an identity, it's the same in Belfast in ulster, you know the northern province of of the, you know the whole of the irish island, you know the part of Ireland that is still part of the United Kingdom, that was also a heavily industrialized area, high manufacturing, mass manufacturing ship building for example, people came from all over there too, which is why when Ireland got its independence in United Kingdom ulster Belfast and that whole region, you know kind of clung on because it was again that melting pot, it was kind of inter intertwined with the larger industrial economy and had a very different identity and so that you know, for me growing up in such a specific place with such a special in many respects heritage gave me a different perspective on things when I first went to the soviet Union in 1987 to study there actually went to translators institute what was then called the modest series, which is now the Institute of Foreign Languages. I was immediately struck by how similar everything was to the north of England because it was just like one big working class culture that sort of broken out onto the national stage. Everything in Northern England was nationalized. We had british steel british called british rail british shipbuilding because after World War two, the private sector has been devastated and the state had to step in and of course the soviet union is one great big, giant nationalized economy when I get there and it's just the people's attitudes and outlooks of the same people didn't work for themselves. They always worked for somebody else and it had a quite a distortion on the way that people looked at the world. </s><s>[INST] Do you still speak? Question [/INST] I do, </s><s>[INST] and [/INST] it would be a big mystery for everybody and you have an advantage on me because your native language as well </s><s>[INST] for people wondering the english speakers in the audience, you're really missing a lot from the few sentences we sat there. Um yeah, it's, it's a fascinating language that stretches actually geographically across a very large part of this world. So there you are in 1987 exchange student in the soviet Union, what was that world world like? [/INST] Well, that was absolutely fascinating in that period because it's the period. Um that just around the time of the peak of perestroika Mikhail Gorbachev's role as president. Well, he wasn't quite present at that point. It's all Secretary general of the Communist Party of the soviet Union, trying to transform the whole place. So I arrived there in september of 1987 just as Gorbachev and Reagan sign the I. N. F. Treaty was just within, you know, kind of weeks of them about to sign that, which really ends that whole period that had shaped my entire teenage years of the end of the Euro missile crisis by finally having agreement on, you know, basically the reduction and constraints on intermediate nuclear forces. And also at this point, Gorbachev is opening the soviet union up. So we got all kinds of opportunities to travel in ways that we wouldn't have done before. Um not just, you know, in Moscow, which is where I was studying at the transit center to go to the caucuses to Central Asia went all the way to Khabarovsk, in the Russian far east, all the way around, you know, kind of Moscow. And there was at this point, it was also the christian euros, which has become very important. Now, this is the anniversary, the 1000th anniversary of the christianization of um of Russia, which of course has become a massive obsession of Vladimir Putin's, but, you know, 9 88 because I was there 87 to 88 at this point, the Russian Orthodox Church is undergoing a revival from being repressed during the soviet period, you certainly have the Church stepping out as a non governmental organization and engaging in discussions with people about the future of religion. So that was, you know, something that I wasn't expecting to to witness also, I mean being in Moscow, this is the cultural capital of a vast empire at this point, I've never lived in a major city before, it's the first big city I lived in, I've never been to the opera, you know, I the first time I got an opera at the bolshoi and I've never seen a ballet, I mean, I was not exactly steeped in high classical culture, kind of growing up in a, a mining region, you know, there's very limited opportunities for this kind of thing. I've been in a youth orchestra and the youth choir, my parents signed me up for everything, you know, they possibly could education wise, but it wasn't exactly any exposure to this. So, you know, I was kind of a standard by the sort of wealth of the cultural experience that one could have in Moscow. But the main thing was I was really struck by how the soviet union was on its last legs because this was Moscow, you know, I got this image about what it would look like. I was quite, to be honest terrified at first about what I would see that the big nuclear superpower. And since I got there, it was just this like as if a huge weight that I'd been carrying around for years and my teenage years just disappeared because it just ordinary people in ordinary place, not doing great, this is the period of, you know what they call deficit, you know, so the period of deficits, but there's no food in the shops, there was, you know, very little in terms of commodities, because the supply and demand, parts of the economic equation out of work, because it was a total central planning, you know, you'd go into, you know, a shop that was supposed to sell boots and there'd be just one pirate boots all in the same size and the same color. I actually looked out because one side was in this um Hungarian boot shop, that was right next to where my whole of residents was, and I was looking for a new pair of boots and every single pair of boots in the shop with my size and they're all women's boots and men's boots at all, you know, because there has been an oversupply of boots and that size production, but you could really kind of see here that there was something wrong. And you know, in the north of England, everything was closed down. The shops were shuttered because there was no demand because everybody lost their jobs was massive employment when I went off to university in 1984 90% youth unemployment In the UK, meaning that when kids left school they didn't have something else to go onto unless they got to university or vocational training or an apprenticeship and most people were still looking, you know, kind of months out of leaving school. And so shops were closed because people didn't have any money, you know, had 50% male unemployment in some of the towns as the steelworks closed down. And the wagon works for the railways, for example, in my area, but in Moscow, people, in theory did have money, but there was just, there was nothing to buy. Also, the place was falling apart, literally, I saw massive sinkholes open up in the street balconies fall off buildings, you know, one accident after another and then there was, you know, this real kind of sense, even though the vibrancy and excitement and hope of the Gorbachev period, a real sense of the soviet union had lost its way. And of course, it was only a year or so after I left from that exchange program and I already started with my degree program in soviet studies at Harvard, that the soviet Union basically unraveled and it really did unravel. It wasn't like it collapsed. It was basically that there was so many debates that Gorbachev had sparked off about how to reform the country, how to put it on a different path that, you know, no one was in agreement and especially all these fights, and, uh debates and disputes among the elites at the center as well as, you know, basically a loss of faith in the system in the periphery and among the general population that in fact pulled it apart and, and of course in 1991 you get Boris Yeltsin as the head of the Russian federation, then a constituent part of the soviet union, together with the presidents of Ukraine and Belarus, all of these being individual parts of the soviet union getting together and agreeing, essentially ending it and Gorbachev, you know, so basically, I'm there at the peak of this whole kind of period of experimentation and thinking about the future within a couple of years, it's all kind of gone and it's on a different track entirely. </s><s>[INST] Well, I wonder if we re ran the 20th century 1000 times if how many times the soviet union will collapse. [/INST] Yeah, I wonder about that too. And I also wonder about what would have happened if it didn't collapse. And Gorbachev had found a different direction. I </s><s>[INST] mean, you know, we see a very divisive time now in american history, the United States of America is very different cultures, very different beliefs, ideologies within those states, but those are, that's, that's kind of the strength of America's, there's these little laboratories of ideas [/INST] until though, that they don't keep together. I mean, I've had colleagues who have described what's happening to us right now is a kind of soft secession with states, you know, going off in their own direction. </s><s>[INST] The center. [/INST] Well, these kinds of conceptions that we have now divisions between red and blue states because of the fracturing of our politics. And I always thought that that wouldn't be possible in somewhere like the United States or um you know, many other countries as well because there wasn't that ethnic dimension, but in fact many of our, the way that people talk about politics has given it that kind of appearance in many respects because look, I mean, we know from the soviet union in the soviet period and from where you're from originally in Ukraine, that language is not the main signify of identity and that identity can take all kinds of other forms. </s><s>[INST] That's really interesting. I mean, but there has to be a deep grievance of some kind. If you took a poll in any of the States, in the United States, I think a very small minority of people would want to actually succeed. Uh even in texas where I spend a lot of my time, I just, I think that there is a common kind of pride of nation, you know, there's a lot of people complain about government and about how the country is going the way people complain about the weather when it's raining, they say, oh, this stupid weather, it's raining again, but really what they mean is we're in the smoke together. There's a together there that [/INST] I also feel that when I go around, I mean, I've spent a lot of time since I wrote my book in last october and this last year going around, I find I find the same feeling, but you know, when I traveled around the soviet Union back in the late 19 eighties, I didn't get any kind of sense that people wanted to see the end of the soviet union either it was an elite project. There's a a really good book called collapse by Vladislav who is a professor um at the London School of Economics and L. C. And Fox is pretty much my age and he's from the former soviet Union's Russian. And I mean he describes it very quite aptly about how it was kind of the elites, you know, that basically decided to pull the soviet union apart. And there is a risk of that, you know, here as well when you get parties and politics and people forgetting, you know, there are americans and they are all in this together, like a lot of the population thing, but they think that their own, you know, narrow partisan or ideological precepts, you know, camp for more and in the soviet case of course was also a power play, you know, in a way that actually can't quite play out in the United States because it was the equivalent of governors in many respects who got together three of them, you know, in the in the case of the heads of Russia Ukraine and Belarus who then, you know, got rid of, you know, basically the central the central figure of Mikhail Gorbachev, it would be a little difficult to do that. The dynamic is not the same, but it does worry me of having seen all of that close up in the late 19 eighties and the early nineties. I was I spent, you know, a lot of time in the uh in Russia as well as in Ukraine and caucasus, Central Asia and you know, other places after the collapse of the soviet union, but you kind of see the same elite divisions here in the United States pulling And, you know, in different in different directions and straining, you know, the overall body politics and the way that national politics gets imposed on local politics in ways that I it certainly wasn't when I first came to the US in 1989, I didn't honestly in 1989, when I first came here, I don't know anybody's political affiliation. I mean, I really knew that religious affiliation and and, you know, obviously race was a was a major phenomenon here. That was a shock to me when I when I first came. But many of the kind of the class, regional geographic, you know, kind of political dimensions that I've seen in other places. I didn't see them at play in the same way then as I do now. </s><s>[INST] And you take a lot of pride to this day of being nonpartisan that said, so you served uh for the George W. Bush Barack Obama and Donald trump administrations, always specializing in uh Eurasia and Russia. You were the top presidential adviser to president, former President Donald Trump on Russia and Europe. And famously testified in his first impeachment trial in 2019, saying I take great pride in the fact that I'm nonpartisan foreign policy expert. So given that context, what does nonpartisan mean to you? [/INST] Well, it means being very careful about not putting any kind of ideological lens on anything, you know, that I'm analyzing and looking out for saying about foreign policy for one thing, but also not taking, you know, kind of one stance of one party over another either. To be honest, I've always found american politics somewhat confounding because both the Democratic and the Republican Party are pretty big tent, some of their coalitions, you know, in europe, it's actually kind of in some respects, easier to navigate the parameters of political parties because, you, you know, have quite clear platforms. Um you know, there's also a longer history in many respects, obviously, I mean, there's a long history here in the United States of the development of the parties, you know, going back to the late 18th century, but in the United Kingdom, you know, for example, in the 20th century, the development of the mass parties. You know, it's quite easy to get a handle on, you know, at one point in the U. K. For example, the parties were real genuine Mass parties with people properly members and took part in regular meetings and pay jews and, you know, it was easy to kind of see what they stood for and the same in europe, you know, when you look at France and in Germany and Western Germany, of course Italy and and and elsewhere here in the United States, it's kind of pretty amorphous, you know, the fact that you could kind of register, you know, randomly, it seems to be a Democratic Republican like trump did at one point is democrat, next thing, he's a Republican and then you kind of usurp the party apparatus, but you don't have to be, you're not vetted in any way, you're not kind of, you know, they don't check you out to see if you have ideological coherence, you can have someone like Bernie Sanders on the other side on the left, you know, basically calling himself a Socialist and, you know, running for the Democratic presidential nomination. So, you know, kind of in many respects, parties in the United States are much more loose movements and I think you can, you know, it's almost like a kind of another cart menu of different things and that people can pick apart pick out and it's more over time, as I've noticed, become more like a kind of an affiliation even with a sporting team. I mean, I get very shocked by the way that people said I couldn't do this because you know, that's my side and I couldn't do anything and I couldn't support someone for the other side. I mean, I have a, a relative in my extended family here who um is a, is a dyed in the wool republican and on, you know, family holiday, it was a book on the table said 100 reasons for voting for a democrat. And I said, hey, are you thinking of shifting party affiliation? That I open the book and it's blank. It's pretty funny. I laugh. I thought, well, there you go. Then there's just, there's no way that, you know, people can pull themselves out of these frames. So for me it's very important to have that independence of thought. I think you can be politically engaged on the issues, but you know, basically without taking a stance that's defined by some ideological ideology or some sense of kind of parties and affiliation. </s><s>[INST] I think I tweeted about this maybe not eloquently in the statement, if I remember correctly with something, like if you honestly can't find a good thing that donald trump did or a good thing that joe biden did. You're not uh you're not thinking about ideas, you just picked the tribe. I mean, it was more eloquent than that, but it was, it was, it was basically, this is a really good test to see, are you actually thinking about like how to solve problems versus like your dread team or blue team, Like a sporting team, can you find a good idea of donald trump's that you like if you're somebody who is against donald trump and like acknowledge it to yourself privately. Oh that's a good idea. I'm glad he said that [/INST] or he's even asking the right kinds of questions which he often did actually. I mean obviously put them in a way that most of us wouldn't have done. But it was often kind of questions about why is this happening, why we're doing this? And you know, we have to challenge ourselves all the time. Said yeah actually why are we doing that? And then you have to really inspect it and say whether it's actually worth continuing that way or they should be doing something differently. Now he had a more kind of destructive quality to those kinds of questions, you know, but maybe it's the real estate developer any um that was you know taking a big wrecking ball to all of these kinds of, you know, sacred edifices and things like that. But often if you really paid attention, he was asking a valid set of questions about why do we continue to do things like this? Now we didn't often have answers about what he was going to do in response but those questions still had to be asked and we shouldn't be just rejecting them, you know out of turn </s><s>[INST] and you know the another strength the thing that people often criticized donald trump would say is a weakness is his uh lack of civility can be a strength because I feel like sometimes bureaucracy functions on excessive civility. Like actually I've seen this, it's not just this bureaucracy in all forms like um, in tech companies as they grow, everybody kind of, you know, you're getting pretty good salary, everyone's, everyone's comfortable and there's a meeting and you discuss how to move stuff forward and like you don't want to be the asshole in the room that says why this is why are we doing this this way? This is um, this could be unethical, this is hurting the world. This is totally a dumb idea. Like I mean I could give specific examples that I have on my mind. Currently there are technical, but the point is oftentimes the person that's needed in that room is an asshole. That's why steve jobs worked. So you know, a mosque works, you have to roll in. That's what first principles thinking looks like [/INST] the one bit when it doesn't work is when they start name calling, you know, kind of inciting violence against, you know, the people that disagree with. So that was kind of a problem because I mean often when, you know, when I was in the administration, I had all of europe in my portfolio as well as Russia and there were many times when, you know, we were dealing with our european colleagues where he was asking some pretty valid questions about, well why should we do this if you're doing that? You know, for example, the nord stream two pipeline, the United States has been opposed to europe's reliance on gas and oil exports from Russia, you know, the soviet union since the seventies and eighties and trump kept pushing this idea about so why are we, you know, spending so much money on NATO and NATO defense, and we're all talking about this, if you are then, you know, basically paying billions, you know, to Russia for gas, isn't this? You know, contradictory and of course it was, but it was the way that he did it. And I actually, you know, one instance had a discussion with a european defense Minister said to me, look, he's saying exactly the same things as people said before him, including former Defense Secretary Gates, it's just the way he says it, you know, so they took offense and then as a result of that, they wouldn't take action because they took offense at what he said. So it was a kind of then a way of could you find some other means of, you know, massaging this communication to make it effective, which we would always try to focus on because it's it's a kind of that was the delivery, but the but the actual message was was often spot on in those kinds of issues. I mean, he was actually highlighting, you know, these ridiculous discrepancies between what people said and what they actually did, </s><s>[INST] it's the delivery the charisma in the room to I'm also understanding the power of that of a leader, it's not just about what you do at a podium but it's in a room with advisers, how you talk about stuff, how you convince other leaders, [/INST] Yeah you don't do it through gratuitous insults and incitement of violence. That's one of the things you just you don't get anywhere with that. </s><s>[INST] It's possible [/INST] tough measures and maximum pressure. Often though it does work because there were you know, often times where you know that kind of relentless you know, nagging about something constantly raising. It actually did have results where it hadn't previously. So there's you know, the maximum pressure if it you know kind of kept on it in the right way. And you know, often when we were you know, coming in behind on pushing on issues, you know related to NATO or you know, other things in this same sphere, it would actually have an effect. </s><s>[INST] It [/INST] just doesn't get talked about because it gets overshadowed by you know, all of the other kind of stuff around this and the way that you know, he interacted with people and treated people </s><s>[INST] what was the heart, the key insights to your testimony and that impeachment. [/INST] Look I think there is a straight line between that whole series of episodes and the current war in Ukraine because Vladimir Putin and the people around him in the Kremlin concluded that the U. S. Did not care one little bit about Ukraine and it was just a game For Trump, it was personal game. He was basically trying to get uh Vladimir Zelensky to do him a personal favor related to his desire to stay on in um in power in the 2020 election. And generally they just thought that we were using Ukraine as some kind of proxy or some kind of instrument within our own domestic politics is, that's what it looked like. And I think that he knows the result of that Putin, you know, took the idea aware that he could, you know, do whatever he wanted. We were constantly being asked even prior to this by people around Putin, like Nikolai Patrushev, the head of the National Security Council equivalent in Russia, who we met with frequently, what's Ukraine t we don't get it, you know, why do you even care? So they they thought that we weren't serious that we weren't serious about Ukraine's territorial integrity and its independence or it is a national security player. And Putin also thought that he could just manipulate the political space in the United States. Actually could because what he was doing was seeding all this descent and fueling, you know already uh you know, debates inside of us politics, the kinds of you know, things that we see just kind of coming out now, this kind of idea that Ukraine was a burden, that Ukraine was, You know, basically just trying to extract things from the United States. The Ukraine had somehow played inside of us politics trump was convinced that the Ukrainians had done something against him, that they had intervened in the elections. And that was kind of, you know, a combination of people around him, trying to find excuses to, you know, kind of what had happened in the election, to kind of divert attention away from Russia's interference in 2016. And the Russians themselves poisoning the well against Ukraine. So you had a kind of a confluence of circumstances there. And what I was trying to get across in that testimony was the national security imperative of basically getting our act together here and separating out what was going on in our domestic politics from what was happening in our national security and foreign policy. I mean, I think we contributed in that whole mess around the impeachment, but it's the whole parallel policies around Ukraine to the war that we now have, </s><s>[INST] signaling the value we place in peace and stability in that part of the world, or the reverse, by saying, we don't care, [/INST] We seem to not care, it was just a game, </s><s>[INST] but the U. S. Role in that war is very complicated. One, that's 11 that's one of the variables um just on that testimony, did it in part break your heart that you had to testify essentially against the President of the United States, or is that not how you saw it? [/INST] I don't think I would describe it in that way. I think what I was was deeply disappointed by what I saw happening and the american political space, I didn't expect it. Look, I was a starry eyed immigrant. I came to the United States with all of these expectations of what the place would be. I'd already been disabused of, you know, some of the, um, let's just say, rosie perspectives on how the United States had been shocked by the depths of racial problems. It doesn't even sum up the problems we have in the United States. I mean, I I couldn't get my head around it when I first came. I mean, I I read about slavery in american history, but I hadn't fully fathomed, you know, really, the kind of the way that was ripping apart the United States when I read Alex talked Phil, and he commented on this and it obviously had, you know, kind of change to the expect the way that one would have expected all this time, you know, from the 18th century onwards. So that was kind of one thing that, you know, that I realized the civil rights movement and all of these, you know, acts of expansion of suffrage and everything else. We're imperfect at best. You know, I was born in 65 the same same time as the Civil Rights Act was heck of a long way still to go. So I wasn't, let's just say, you know, as starry eyed about everything that had been before, but I really saw an incredible competence and professionalism in, you know, the U. S. Government, it was gonna be in the election system and the integrity of it. And I mean, I really saw that I saw that the United States was the gold standard for, you know, kind of some of its institutions. And I worked in the National Intelligence Council, and I've seen the way that the United States had tried to address the problems that it had um had faced in its whole botched analysis of Iraq and this terrible strategic blunder of um honestly a crime in my view of invading Iraq. And but the way that people were trying to to deal with that in the aftermath, I mean, I went into the National Intelligence Council, the D. N. I. The Director of the Office of the Director of National Intelligence when they were coming to terms with what had gone wrong in the whole analysis about Iraq in 2003, you know, in the whole wake of people trying to pull together after 9 11 and to learn all of the lessons from all of this. And I saw, you know, just really genuine striving and and deliberation about what had gone wrong, What lessons can we learn from this? And then suddenly I found myself and this, I couldn't describe it just totally crazy looking glass thinking of Alice in wonderland Alice through the looking glass version of american politics. I mean, I'd seen everything starting to unravel over a kind of a period of time before I'd been asked to be in the administration, but I did not expect it to be that bad, honestly didn't. I mean, I had been warned, you know, by people that this was, you know, kind of really a very serious term that the United States had taken. But I really thought that national security would still be uppermost in people's minds. And it was a lot of the people that I work with. But what I found, you know, if you want to use that term of heartbreaking was the way in which all of these principles that I really bought into and try to uphold in the United States government. And then the things that we were trying to do with me and my colleagues have just been thrown out the window and that, you know, I would have to step up in defense of them and in defense of my colleagues who were being lambasted and, you know criticized and given death threats, were actually standing up and doing their own jobs </s><s>[INST] in particular on the topic of Ukraine, [/INST] not just on Ukraine international security overall. So, I mean, I've gone through this whole period even before we got to that point, I'm seeing non parties and government officials being attacked from all sides left and right, but especially the right and being basically accused of being parties and hacks in a deep state coup plotters, you know, you name it there, patriotism being questioned as well. And a lot of people I worked with in government like myself, naturalized americans or immigrants, many were refugees and many people had fought and and was on behalf of the United States in Iraq and Afghanistan being blown up and you know, they put their lives on the line, they put their family lives on the line, you know, because they believed in America and they were just there were reflections of americans from all kinds of works of walks of life is what really made you know, that cliche of America great, it wasn't, you know, whatever it was, it was being abandoned around in these crude, crass political terms. It was just the strength of an incredible set of people who have come together from all kinds of places and decided that they're going to make a go of it and that they're going to, you know, try to work towards the whole idea of the preamble of the constitution towards a more perfect union. And I, you know, I saw people doing that every single day despite all of the things that they could criticize about the United States still believing what they were doing and believing in the promise of the country, which is what I felt like. And then here we were, people were just treating it like a game and they were treating people like dirt and they were just playing games with people's lives. And we all had death threats, People's, you know, whole careers which were not just careers for their own self aggrandizement, but careers of public service trying to give something back were being shattered. And I find, you know, I just thought to myself, I'm not gonna let that happen because you know, I've come from, what are they going to send me back to Bishop Auckland in County Durham. Fine. I'm totally fine to go back because I could do something back there, but I'm not going to let this happen. I've made this choice to come to America. I'm all in and these guys are just behaving like a bunch of idiots and they're ruining it. You know, they're ruining it for everybody. </s><s>[INST] So the personal attacks on, on competent, hardworking, passionate people who have love for what they do in their heart, similar stuff I've seen for virologists and biologists. So colleagues, basically scientists in the time of covid when there's a bunch of cynicism and there was just personal attacks, including death threats on people that start, you know, work on viruses work. [/INST] They're going around, you know, basically, um, with protective gear on and somebody shoots them in the street that's just absurd. </s><s>[INST] But let me zoom out from the individual [/INST] people </s><s>[INST] and actually look at the situations that we saw in the in um the George W Bush Obama and Donald trump presidencies. And I'd like to sort of criticize each uh by the not the treatment of individual people but by the results. [/INST] Right? Yeah, I think that's fair. </s><s>[INST] So if you look at George W Bush and maybe you can give me insights. This is what's fascinating to me when you have extremely competent uh smart, hardworking, well intentioned people. How do we as a system make mistakes in foreign policy. So the big mistake, uh you can characterize in different ways, but in George W Bush is invading Iraq or maybe how it was invaded or maybe how the decision process was made to invade it again Afghanistan with maybe not the invasion, but details around like having a plan about you know, how to withdraw all that kind of stuff. Then Barack Obama to me similarly is a man who came to fame early on for being somebody who was against a rare voice against the invasion of Iraq, which was actually a brave thing to do at that time. And nevertheless, he, I mean, I don't know the numbers, but I think he was the president for years over, increased drone attacks increased. Like every everything from a foreign policy perspective, uh the military industrial complex that machine grew in power under him, not shrunk and did not withdraw from Afghanistan. and then, um, with donald trump the criticisms that you're presenting sort of the personal attacks, the chaos, the partisanship of people that are supposed to be nonpartisan. So that, you know, if you sort of, to steal man the chaos to to make the case for chaos, maybe we need to shake up the machine, throw a wrench into the engine into the gears and then every individual gear is gonna be very upset with that because it's the rent, it's not, it's not, it's an inefficient process, but maybe it leads uh, for government, it forces the system as a whole, not the individuals, but the system to reconsider how things are done. So obviously all of those things. Uh, the actual results are not that impressive. You [/INST] could have done that on the latter, you know, shaking things up because I'm all one for questioning and trying to shake things up and do things differently. But, you know, the questions if you bring the whole system down with nothing ideas of putting into place, like, I mean, like many people have studied the bolshevik revolution and, you know, many others as well and, you know, kind of, what's, you know, what's the pattern here, you know, that actually fits into what you're talking about here is a kind of rigidity of thought on the part of revolutionaries in many cases as well, and also narcissism, in fact, I think that takes a pretty strong sense of yourself, you know, kind of an only yourself to want to be President of the United States for example, we see that in, you know, many of our presidents of the Narcissist two different, you know, kind of degrees, you think about Lennon, you know for example and people can go back and read about Lenin, he formed his views about 18 and he never shook them off, he never evolved, he didn't have any kind of diversity of thought and when systems go awry, it's when they don't bring in different perspectives and so, you know, trump have you brought in different perspective? Actually listened to them and not just believe that he himself knew better than anyone else and then tried to divide everybody against each other, it would have been a different matter. It's a tragedy of a completely and utterly lost set of opportunities because of the flaws in his own nature because I mean again, there was called kinds of things that he could have done to shake things up and so many people around him remained completely disappointed. And of course he divided and pitted people against each other. You know, creating so much factionalism in american politics that, you know, people have forgotten their americans, they think that they're red or blue, you know, parts of teams and you know, if you go back over history that's kind of a recipe for war and you know, internal conflict, you go back to, you know, the Byzantine empire, for example, there's the famous episode of the Nika riots in constantinople where the whole city gets trashed because the greens, the reds, the blues, and these various sporting teams in the Hippodrome get whipped up by political forces and the pull the place apart. And that's, you know, kind of where we've been heading on some of these trajectories. But the other point is when you look back, you know, a Bush and Obama as well, there's a very narrow circle of decision making. You know, Bush period is the focus on the executive branch with Dick Cheney as the vice president being very fixated on it. And Obama, it's, you know, he and, you know, kind of the bright young things around him, you know, from himself is, you know, kind of intellectually, um, you know, one might say arrogant in many respects, you know, he was a very smart guy and, you know, he's convinced that he has and he ruminates over all things, but he's the person who makes, you know, a lot of decisions. And um, basically George W Bush used to call himself the decider as well. Right? I mean, the all the people who make the decisions, it's not always as consultative as you might think it is. And for trump, it's like I'm not listening to anybody at all. You know, it's just me and whatever it is that I'm walking up today and I've decided to do so I think, you know, the problem with all of our systems, why we don't get results because we don't draw upon, you know, the diversity of opinion and all the ideas. You know, people out there like you do that in science. I mean when, I mean, all my friends and relatives are in science. They got these incredible collaborations with people, you know, across the world. I mean, how did we get to these vaccines for the covid vice because of this incredible years of collaboration and of, you know, sharing results and sharing and ideas and our whole system has become ossified. You know, we think about the car congressional system for example, as well. And there's, you know, this kind of rapid turnover that you have in Congress every two years. You know, there's no incentive for people, you know, basically to work with others. They're constantly campaigning. They're constantly trying to appeal to whatever their bases and they don't really care about, you know, some do you know, that their constituents, but a lot of people don't. And the Senate, it's all kind of focused on the game of of legislation for so many people as well. Not focusing again on that kind of sense about what are we doing like scientists to kind of work together, you know, for the good of the country to push things along. And also our government also is siloed. There's not a lot of mechanisms for bringing people together, there ought to be and things like the National Security Council, the National Intelligence Council actually did that quite successfully at times for analysis that I saw, but we don't have, you know, we have it within the National Institutes of Health, but we saw the C. D. C. Breakdown on this, you know, kind of front, we we don't have sufficient of those institutions that bring people together from all kinds of different backgrounds. You know, one of the other problems that we've had with government with the federal government over, you know, state and local government is actually quite small, people think that the federal government is huge because because we have postal service in the military that are part of it, but your actual federal government employees is a very small number and you know, the Senior Executive service part of that is the older white guys, you know, kind of come up all the way over the last, you know, several decades, we have a really hard time bringing in younger people into that kind of government service unless they're political hacks, you know, and I want to, you know, kind of, they're kind of looking for power and you know, sort of influence. We have a hard time getting people like yourself and other, you know, younger people kind of coming in to make a career out of public service and also retaining them because, you know, people with incredible skills often get poached away into the private sector and you know, what are the people that I work with, the national security side and now what all kinds of, you know, high end political consultant sees or they've gone to Silicon Valley and they've they've gone to this place and that place, because after a time as a younger person, they're not rising up particularly quickly because there's a pretty rigid way of looking at the hierarchies and the promotion schemes and they're also getting lambasted by everybody. People like, you know, public servants, they're not really public servants. There's this whole lack and loss of a kind of a faith in public service and, you know, the last few years have really done a lot of damage. We need to revitalize our government system to get better results. We need to bring more people. And even if it's, you know, for a period of time, not just through expensive contracts for, you know, the big consulting companies and, you know, other entities that do government work out there, but getting into people in for a period of time, expending, expanding some of these management fellowships and the White House fellows and, you know, bringing in, you know, scientists, you know, from the outside giving, you know, that that kind of opportunity for collaboration that we see in other spheres. </s><s>[INST] I think that's actually one of the biggest roles for President, that for some reason, during the election that's never talked about is how good are you at [/INST] hiring and </s><s>[INST] creating a culture of like attracting the right, I mean, basically chief higher when you when you think of a ceo like the great C. E. O. S are maybe people don't talk about it that often, but they do more often for C. E. O. S than they do for presidents is like how good you are building a team. [/INST] But we make it really difficult because of the political process. I mean, and also because we have so many political appointments, we don't have less, to be honest. I mean, we look at other governments around the world, you know, that are smaller, it's much easier for them to hire people in. You know, some of the most successful are much smaller and it's not that I say that the, you know, the government is necessarily too big, but it's just thinking about each unit in a in a different way. We shouldn't be having so many political appointments, we should kind of find more professional appointments more non partisan appointments because, you know, every single administration that we've had over the last, you know, that's the span of presidencies. They have jobs that are unfulfilled because they can't get their candidates through Congress and the Senate because of all the kind of political games that are being played. I know loads of people have just been held up because it's just on the whim of, you know, some member of Congress, even though that the actual position that they want is really technical and doesn't really care about what, you know, what political preference they particularly have. So I think we have to try to look at the whole system of governments in the way that we would over, you know, other professional sectors and to try to think about this as just as you said there, that this is a government that's actually running our country, this is an operating system and you wouldn't operate it like that if you were, you know, looking at in any kind of rational way, it shouldn't be so ideologically or parties untainted every level anywhere. So I would actually just say make a bid for a more non partisan approach to a lot of the parts of government. You can still kind of bring in, you know, the political and premature, but also you have to explain to people at large in America as well that this is your government and that actually you could also be part of this, you know, things like the Small business administration, the Department of Agriculture, you know, all these kind of things that actually people interact with, but they don't even know it, the Personal service, you know, all of these things, I mean, people actually, when you ask them about different functions of government, they have a lot of support for the National Park Service, you know, for example, it's just when you talk about government and abstract where like, you know, too much bloated, you know, not efficient and effective, but if you kind of bring it down more to the kind of local and federal levels, that's kind of, you know, when people really see it, if people could see kind of themselves reflected in many of the people have gone into public service, I think that they would </s><s>[INST] have a [/INST] lot more support for it </s><s>[INST] more. Like superstars, like individuals, they're like big on social media, big in the public eye and having fun with it and showing cool stuff that is not right now. A lot of people see government as basically partisan warfare and then it just, it makes it unpleasant to do the job. It makes it uninspiring for people looking in from outside about what's going on inside government, all of it the whole thing. But you you are, you know, just with all due respect, you're pretty rare individual in terms of nonpartisanship, like it actually your whole life story, the humbling aspect of of your upbringing and everything like that. Uh do you think it's possible to have a lot of nonpartisan experts in government, like can you be a top presidential adviser on Russia For 10 years for 15 years and remain nonpartisan? [/INST] I think you can I don't think that's advisable though, by the way, because, I mean, I don't think anybody should be there. Your </s><s>[INST] first advice is to find yourself after. [/INST] You should definitely have term limits, just like you shouldn't everything right? I mean, it's just like 10 year in university kind of like </s><s>[INST] you [/INST] Kind of you know, we do we have natural term limits, but you know, you kind of you know, basically bottling it up for other people. I mean, you know what I'm trying to do now, I'm 57 now and I always try to work with, you know, people from different generations to me, just like, you know, I've I've really benefited from these, you know, kind of mentorship from people older, you can, you know, mentor up and well and mentor down. I mean, I would, you know, try to get you know, people from different backgrounds and different generations to work together in teams. Obviously I'd like to more team network kind of approach to things that the kind of things that you get again in science, right? I mean all these ideas are going to come from all kinds of different perspectives, age and experience does count for something, but you know, fresh ideas and coming in and looking at a problem from a different perspective and seeing something that somebody else hasn't seen before. I mean, I just, you know, kind of love working in a an environment with all kinds of different people and people who don't agree with you, you need people to take you on and said absolutely, that's crap kind of where did you come up with that from? You go, hang on, well, explain to me why you think so. And then, you know, you have this kind of iterative process back and forth. I mean, I would always encourage my colleagues to tell me when they thought it was wrong. I mean, sometimes I didn't agree because I didn't see the the, you know, the reasoning, but other times I'm like there, right, you know, that that was a complete mistake. I need to admit that and, you know, kind of we need to figure out a different way of doing things. But the one point I do want to get across is there were a lot of people who were non partisan that I worked with. I mean, honestly, and most of the jobs that I had up until more recently, I had no idea about people's political affiliation is just when you get into this kind of highly charged partisan environment that kind of force people, you know, to make decisions. And when you have, you know, one political party political factions trying to usurp power, it does make it quite difficult. I mean, that's the situation that we're in right now, and, you know, we're seeing some of the things happening that since I've seen and studied in other settings or seen for myself happening, you know, when you have a president who wants to cling onto power, you know, you've got to you've got to call that out, you know, is that the parties an act or is that a kind of, you know, defense of that larger political system that that that you're part of. So I think we've got to recognize that even if you're not partisan, you can be politically engaged and, you know, sometimes you just have to stand up there and speak out, which is, you know, what I did and what others did as well. None of those people who spoke out, you know, can initially saw that as a partisan act, even if some of them since then have decided to make political choices they hadn't made before, because in the situation actually forced people into, you know, taking site, it's very hard to still stay above the fray when you've got, you know, someone who's trying to perpetrate a coup. </s><s>[INST] Yeah, just to linger on that, I think it's hard and it's the courageous thing to do to criticize the president and not fall into partisanship after because the whole world will assume if you criticize donald trump that you're clearly a democrat. And so they will just everybody will criticize you for being a democrat. And then so you're now stuck in that, so you're going to just embrace that role, but to still walk the nonpartisan route after the criticism, that's the hard road. Uh, so not let the criticisms break you into, uh, you know, into a certain kind of ideological set of positions. [/INST] I mean, our political system needs revitalization. We need to be taking a long, hard look at ourselves here, and I think what people are calling out for, there's a fast way the population like me who are unaffiliated, you know, maybe some lean in one direction over another and unaffiliated doesn't mean you don't have views about things and political opinions and, you know, you make sound quite extreme on, you know, some of those, you know, by the from the left or right perspective, what people are looking for is kind of an articulation, you know, things in a kind of a clear way that they can get a handle on. And they're also looking for representation. Somebody is going to be there, you know, for you, you know, not part of a kind of a rigid team that you're excluded from. You know, the ins and the outs, what people are looking at now, they're looking at that in the workplace, because they're not finding that in politics. You're actually getting workers, you know, pushing the people talk about the rise of the work. People just saying, hang on a second, you know, the most important space that I'm in right now is my workplace, because that's where my benefits are from. They're not coming from the state. I mean, that's a peculiarity of United States system, you know, the Britain, you've got the National Health Service and you've got all the kind of national wide benefits. You know, you're not tethered to your employer like you are in the United States, but here now we're asking people, you know, people are pushing for more representation, they're asking to be represented in their workplace, be at Starbucks where barristers are, you know, another Starbucks employees are trying to unionize. We have unions among our research assistant at the brookings institution, where I am, you know, kind of teaching assistants and big universities are doing the same kind of thing as well, because they want to have their voice heard, they want to kind of play a larger role. They want to have change, and they're often pushing their companies or the institutions they work for to make that change, because they don't see it happening uh in the political sphere, it's not just enough to go out there and protest in the street, but if you want something to happen, that's why you're seeing big corporations playing a bigger role as well. </s><s>[INST] Yeah, and of course, there's, you know, there's a longer discussion, there's also criticisms of the mechanisms of unions to achieve the giving of a voice to people. [/INST] This goes back to my own experience growing up in Northern England, the Durham miners that I was part of for generations, you know, first person in my family, not in the minds on my dad's side. Um they created their own association, it wasn't a union person at the very beginning, later they became part of the National Miner's Union, they lost their autonomy and independence as a result of that, but what they did was they pooled their resources, they set up their own parliament so they could all get together literally, they built a parliament, you know, opened in like the same time as World War One and where they all got together cause they don't have the vote, they didn't have suffrage at the time because they have any money, you know, so they didn't couldn't pay the tax and they're, you know, they couldn't run for Parliament and this is, you know, the kind of the origins of the organized labor party's later, but they create this association so they could talk about how they could deal with things with their own communities and have a voice in the things that mattered, you know, education, you know, improving their work conditions. It wasn't like what you think about some kind of like big political trade union with, you know, left wing, you know, kind of ideas. In fact, they actually tried to root out later after the bolshevik revolution in the soviet union, even when they were still having ties with players like mines of Donbass in the 19 twenties, Trotskyites and you know, kind of leninists and you know, communists, they were more focused on how to improve their own well being, you know, what they call the welfare, they had some welfare societies where they were kind of trying to think and that's kind of what brewster's in Starbucks want, or workers in amazon they're talking about their own well being, it's not just about pay and work conditions, it's about what it means to be part of this larger entity, because you're not feeling that same kind of connection to politics, you know, at at the moment, because, you know, you're being told by a representative, sorry, I don't represent you because you didn't vote for me. You know, if you're not a democrat, you're not republican, you're not ready. You know, you're not blue, you're not mine. And so people are saying, well, I'm in this workplace, this is kind of my collective, you know, this is this is, you know, therefore this is what I'm gonna have to try to push to make change. So, I mean, this is kind of happening here and we have to, you know, realize that, you know, we've kind of gone away full circle back to that, you know, kind of period of the early emergence of sort of mass labor and, you know, the way that that's where the political parties that we know today and, you know, the kind of, early unions came out of as well, this sort of feeling of a mass society, but where people weren't really able to get together and implement or push for change. </s><s>[INST] You know, with unions on a small scale and a local scale, it's like every good idea on a small scale can become a bad idea and a large [/INST] scale. So </s><s>[INST] like marriage is a beautiful thing, but a large scale, it becomes the marriage industrial complex that tries to make money off of it, combined with the lawyers that try to make money off the divorce, it just becomes [/INST] this caricature </s><s>[INST] of a thing or like christmas and the holidays. It's like, [/INST] I don't disagree. But what I'm saying is that people are basically looking for something here and you know, kind of this is why I mean, I myself and start to think about much more local, you know, kind of solutions to a lot of these kind of problems. It's again, the team networked approach </s><s>[INST] on the impeachment. Looking back because you're part of it, you get to experience it. Do you think they strengthen their weakened this nation? [/INST] I think it weakened in many respects, just the way that it was conducted. I mean, there's a there's a new book coming out by a couple of journalists in the Washington post. I haven't actually seen it yet, but I really did, you know, kind of worry that myself that it became a spectacle. And although it actually, I think in many respects was important in terms of an exercise of civic responsibility and, you know, give people a big, massive lesson in civics, everyone's kind of running out and looking up the whole process of impeachment and what that meant kind of congressional prerogatives. I was as well. I was like, you know, like running off myself and, you know, trying to learn an enormous amount about it, because I was in the middle of a lot of this, that it didn't ultimately show responsibility and accountability. And that in itself was kind of, was weakened because on on both sides, there was a lot of parties and politics. I mean, I think that there was a dereliction of of duty in many respects. I mean, especially, I have to say on the part of Republican members of Congress who were, you know, kind of they should have been embracing, you know, Congress's prerogative. You could have, you know, kind of basically done this in a in something of a different way. But the whole thing is because it was this larger atmosphere of polarized, polarized, fractured, fractured politics, and I was deeply disappointed, I have to say in many of the members of Congress. On the Republican side, there's a lot of grandstanding that I really didn't like one bit on the Democratic side either, and not admitting to mistakes and, you know, not kind of addressing head on, you know, the fact that they, you know, kind of been pushing for trump to be impeached and, you know, talking about being an illegitimate president, you know, kind of right from the very beginning, and that, you know, as a result of a lot of people just saw this as kind of a continuation of political games, you know, coming out of the 2016 election. But on the republican side, it was just a game. That was people I knew who were, you know, basically, you know, 1.1 of them winked at me, you know, in the middle of this, you know, kind of impeachment is just like, don't take this personally. You know, this is </s><s>[INST] this is a [/INST] game. And I just thought this isn't a game. And that's why I think that, you know, kind of weakened because I mean, again, on the outside, it weakened as the whole process weakened in the eyes of the world because again, the United States was the gold standard. And I do think, I mean, again, in the, in the terms of the larger population, although a lot of people did actually see the system, you know, standing up trying to do something to help people account. But there still was that element of circus and a big political game and people being careless with the country. </s><s>[INST] But I do think that the democrats were the instigators of the circus. So as, uh, it's perhaps subtle, but there's a, there's a different way you talk about issues or concerns about accountability when you care about your country, when you love your country, when you love the ideals and when you versus when you just want to win [/INST] and stick it to the other side. </s><s>[INST] I [/INST] agree. I mean, there were people who, I actually thought manage that, that made it about the country rather than about themselves, </s><s>[INST] that [/INST] there were others who did a lot of grandstanding? </s><s>[INST] Yeah, [/INST] and and that's that's another problem of our political incentive structures. That the kind of sense of accountability and responsibility tends to be personal. You know, people, whether people decide to do it or not, it's not institutional, if that makes sense, We've had a kind of a breakdown of that kind of that sense. Now, I took an oath of office and I'm assuming that most of them did too, you know, I had to be sworn in, you know, when I took those positions, I took that seriously, but I already took an oath of citizenship. There's, you know, presumably you did too, you know, you kind of started to become an american citizen. It's not something you take on lightly. And, you know, that's why I felt this deep sense of responsibility all the time, which is why I went into the administration in the first place. I mean, I got a lot of flak for it because, you know, I thought, well, look, I've been asked And there's a real issue here after the Russian interference, and you know the whole influence operation in the 2016 elections and I knew what was going on and I should do something, you know, if not me, then, you know, okay, someone else will go and do it. But can I live with myself just sitting on the sidelines and criticizing what people are doing, you know, and kind of, you know, worrying about this, or am I actually gonna muck in there and, you know, just go and do something, It's like seeing your house on fire and you see that, you know, this is pretty awful and dangerous, but I could go in there and do something </s><s>[INST] to clarify the house on fire, meaning the cyber war that's going on, cyber attacks [/INST] in the 2016, you know, when the Russians had interfered in the election, you know, I mean, basically, this was a huge national security crisis and our politics, we've gone mad as a result of it, and in fact, we were making the situation worse and I felt that I could, you know, kind of at the time, but maybe I could do something here, I could try to clarify, I could, you know, work with others who I knew in the government from previous stints in the government to push back against this and try to make sure it didn't happen again. And look, and I also didn't have this, you know, mad, you know, kind of crazy ideological view of Russia either. I mean, I knew the place, I knew that people had been sitting a long time and quite calm about it. I don't take it personally, it's not kind of an extension of self it's, you know, something I've spent a long time trying to understand for myself going back to the very beginning of my with the Russians trying to blow us up. There must be an explanation. There was it was a very complicated and complex explanation. It wasn't as simple as how it sounded. And also there's a long tail to 2016, you know, Putin's perceptions, the kind of things that he thought were going on the, you know, the whole way that what they did was actually fairly straightforward. They've done this before in the soviet period during the Cold War classic influence operation. It just had gone beyond the bounds of anything they could have anticipated because of social media and just a confluence of circumstances, the United States as well. We were very fragile and vulnerable. And I remember at one point having a discussion with the Russian ambassador where, you know, we were complaining about the Russian intervention, he said, Are you telling me that the United States is a Banana Republic, that it's so vulnerable to these kinds of efforts? He actually looked genuinely mystified. Although he was probably part of a kind of political stick there. But he had a point, the United States had never been that vulnerable as it suddenly was in 2016. And in the time that I was in government and going back to what you asked about the whole impeachment and the whole exercise in in Congress. That vulnerability was as stark as it, you know, ever could be. Our domestic politics were as much a part of the problem as anything else. They were the kindling to all of the kind of the fires Putin, didn't start any of this other kind of problems domestically just took advantage of them. And you know, basically added a bit of an ex element here and there. </s><s>[INST] Yeah, the interference. I mean that's a much longer discussion because it's also for me, technically fascinating. Um, I've been playing with the idea of just launching like a million bots, but that are doing just positive stuff and just being kind Yeah, [/INST] it was kind of wondering if is it possible to do something on this skill that's positive? Because you know, a lot of people seem to be able to use all of this for pretty negative effect. You've got to kind of hope that you can do this. Use the same networks for positive effect. </s><s>[INST] I think that's actually where a lot of the war, I think from the original hackers to today, what gives people like me and I think a lot of people that in the hacking community pleasure is to do something difficult, break through the systems and uh, do the ethical thing. So do the, because if there's something broken about the system, you want to break through all the rules and do something that, you know, in your heart is the right thing to do. I mean, that's what Aaron Swartz did with releasing journals and publications that were behind pay walls to the public and got arrested for and then committed. Uh, but to me it's fascinating because I maybe you can actually educate me, but I felt that the Russian interference in terms of social engineering, in terms of bots, all that kind of stuff. I feel like there was more used for political bickering than to actually understand the national security problem, because uh, I would like to know the actual numbers involved in the influence. I would like to I mean, obviously, hopefully people now understand that better than are trying to defend the national security of this country. But it just, it felt like like for example, if I launched one bot and then and then just contact somebody at the new york times saying I launched this one bot, they'll just say uh, M I T scientist hacks, you [/INST] know, and </s><s>[INST] then that, but [/INST] that's exactly what happened. It was, you know, kind of, I think that, you know, Putin and some of the people around him understood because again, propaganda state, they spend an awful lot of time thinking about how you basically put out your own content and how you get maximum effect through performance. Putin himself is a you know, political performance artist. I mean, trump understood exactly the same thing, they were actually operating in parallel, not in collusion, but in parallel, you know, basically trump understood how to get lots of free air time, you know, how to get himself at the center of attention, Putin, you know, did that through a kind of, I think a less organic kind of way, you know, a lot of people working around him and that's the old bolshevik, agitprop and you know, kind of then the whole soviet propaganda machine and you know, Putin kind of growing up in that kind of environment and having, you know, the kind of the Kremlin press office and all the kind of people around him got kind of a massive machine, knew how that worked. I mean, they haven't done what the chinese did in Russia, like blocking everything and having a big firewall, it's kind of putting out lots of content getting into the, you know, the sort of center of attention trump's doing the same kind of thing. And the Russians understood that, you know, if you put a bit of things out there and then you call up the new york times and people are going to run with it and what they wanted was the perception that they had actually swayed the election. They loved it. This was the huge mistake of the democrats, everything. And I kept trying to push against this. No, they did not elect donald trump americans elected donald trump and you know, the Electoral college was a key part. Vladimir Putin didn't make that up, you know, and basically, I also remember, you know, one point, um Russian ambassador, you know, talking to me about when we were doing the standard, you know, here we are, we're lodging our complaint about the interference, you know, he didn't he basically said, well we didn't, you know, kind of invent Comey and you know, basically the, you know, the decision to reopen, you know, Hillary Clinton's emails or you know, kind of Anthony Weiner and you know, kind of his um you know, emails on his computer and I was like, yeah, he's right. I mean, you know, there were plenty of things in our own system that created chaos and tipped the election, not, you know, kind of what the Russians did, but you know, it's obviously easier to blame the Russians and blame yourself when, you know, things are kind of or those random forces and those random factors because people couldn't understand what had happened in 2016, there's no hanging chads like 2000 where there was, you know, kind of a technical problem that actually, you know, ended with the intervention, the Supreme Court, there was, you know, pure and simple the Electoral College at work And a candidate that nobody had expected, including the Republicans in the primaries, you know, to to end up getting kind of elected or put forward different 2016 suddenly becoming the president and they needed a meta explanation. It was much better to say Vladimir Putin Vladimir Putin, and the Kremlin guys were like, oh my God, yeah, fantastic Champagne corks popping this is great, our chaos agent, They knew they hadn't done it, but they'd love to take credit for it. And so, you know, the very fact that other people couldn't explain these complex dynamics to themselves basically dovetails beautifully with Vladimir Putin's attempts to be the kind of the Kremlin Gremlin in the system. And he's, you know, basically was taking advantage that forever more. And I wanted, you know, to basically try to work with us to cut through that. And the thing is then, you know, people lost faith in the integrity of the election system because people were out there, you know, suggesting that the Russians had actually distort the election books about that. They said, you know, that they hacked the system when, you know, they were trying to hack our minds. But again, we were the fertile sold for this. I mean, we know this from Russian history, the role of the bolsheviks, you know, the whole 19 twenties and 19 thirties with Stalin, the fellow travelers and the, you know, socialist, you know, international, I mean, the Russians and the Soviets have been, we're at this fears about kind of pulling, you know, kind of people along and into kind of a broader friend, but it didn't mean that they were influencing, you know, directly the politics of of of countries, you know, large, that plenty of interventions. It's just that we were somehow, it was, it was a confluence of events, a perfect storm. We were somehow exquisitely vulnerable because of things that we had done to ourselves. It was what americans were doing to themselves. That was the issue. </s><s>[INST] You think that's the bigger threat than large scale bought armies. [/INST] Those can be obviously they do have an impact, but it's, it's how people process information. It's kind of like the lack of critical thinking. I'm just not on the internet to that extent. I don't go looking for information, I'm not on social media, I'm in social media but not by myself, you know, I don't put myself out there. I'm not, I haven't got a twitter feed </s><s>[INST] the [/INST] cat and I have all kinds of strange things, which I kind of like, you know, occasionally people send things. But what I, what I what I try to do is just be really critical. I mean my, you know, my mom sends me stuff. What is this? It's just you know, your own mother can be as much of an agent of misinformation as you know, kind of Vladimir Putin, I mean we're all, you know, kind of, we all have to really think about what it is. We're reading. There's one thing from my childhood that was really important. I mean I always think every kid in school should have this my next door neighbor who was, he was actually very active in the, in the labor party and he was, you know, kind of really interested in the way that opinion, you know, shape people's political views. He was, well, she was a native welsh speaker. So you know, he was always trying to explore english and how you know, there was kind of the reach of you know, the english culture and you know, kind of how it was kind of shaping the way that people thought and he used to read every single newspaper, you know, from all the different spectrums, which was quite easy to do, you know, back in the seventies and eighties because there weren't that many in the UK context. And every sunday he would get all the different sunday papers from all the different kind of ideological vantage points. And then when I got to be a teenager, he'd invite me to look at them with him because he was my Godfather, he was just an incredible guy and he was just super interesting and you know, kind of culturally you know an outsider, always kind of looking in and he basically ran through, you know what The Guardian looked at the Observer, the Daily Mail, the Sun, you know, kind of all of these, you know, the Telegraph, all of these newspapers and how you could tell, you know, they're different advantage points. And of course it's complicated to do that now. I mean in this, you know, incredibly extensive media space, I look at what it is that they're saying. And then I tried to, you know, read around it and then you know, look at what other people are saying and why they're saying it and who are their, what's their context and that was kind of busy what I was taught to look at. And, and I think everybody should have that. </s><s>[INST] And certainly that's something that people in politics that are in charge of directing policy should, should be doing, They should be not getting lost in, uh, in the sort of the hysteria that can be created. Like it does seem that the american system somehow, not the political system, just humans love drama. Very good. Like the Hunter biden laptop story. We there's always like 123 stories somehow that we just pick that we're just gonna, this is the stuff we're gonna fight about for this election [/INST] and everyone's got an opinion on it. Everybody. Yeah. </s><s>[INST] And it's the most like Hillary Clinton's emails, Russians hacked the election. We [/INST] had john podesta's pastor recipes for a while. You know, that we were kind of all obsessing over. I don't know, people running out and trying them out or something like that. </s><s>[INST] And there's fun. I mean, there's all day the best conspiracy theories about Giuliani. I just love it. We just pick a random story sometimes. It's ridiculous. [/INST] And it detracts from what the larger question should be, which is about the family members of senior officials and whether they should be anywhere near any of the issues that they're, you know, there's ethics, there's government ethics and things, they're, you know, kind of across the board, but there's a bigger story in there, but that becomes a distraction. It's a look over there. You know, the oldest trick in the book, you know, kind of idea </s><s>[INST] politicians [/INST] are really good at that because it detracts from the larger question because every single member of congress and you know, government officials, their family should be nowhere near anything they're doing </s><s>[INST] well that I could push back and disagree on. I mean, it [/INST] depends on what they do if they're making money out of it, you know, and kind of basically being in business is what I mean. You know, kind of, this is a, this is an issue. So it's not, you know, Hunter biden on his own. It's, you know, kind of basically the kids of the trump family that, you know, you name it </s><s>[INST] in general like that. I just think it's funny like there's a lot of families that, you know, they work very closely together, do business together. It's very successful. I get very weird about that. It just feels like you're not, in fact, I don't even like hiring or working with friends initially you make friends with the people you work with. [/INST] That's right now. I have to, I have the same worries as well because it kind of clouds, you know, I would encourage, you know, my daughter to do something completely different, not going to the same field now, look, it's different if you're, you know in science or mathematics or something like this and you know, maybe, you know, kind of, you've got a family member, you're kind of building on some of the theories and ideas, you know, if Albert Einstein had a, you know, kind of an offspring, it was mathematics and you know, father's thinking, you know, further that would be very different. But if it's, you know, kind of, you're in business and other things and it's just, you know, it's the nepotism problem no one has that </s><s>[INST] says that [/INST] they do, if they're not, people aren't coming in and building on the ideas and constructive, </s><s>[INST] right? But even for son, daughter of Einstein, you want to think outside the box of the previous [/INST] meaning. But I mean, it's just but they shouldn't be sort of told no, sorry, you can't go and study math because, you know, whatever physics, you know, because of but </s><s>[INST] a lot of that, you can't actually make it into law. Well, you could, I suppose, but honestly, if you do that kind of thing, you should be transparent. There should be just an honesty about it [/INST] gets back to what I was talking about before we need diversity of views and diversity of thinking and you can't have other things, just like being parties on or, you know, rooting just for a team, you know, if something is gonna cloudy judgment or constrain the way you think about things and become, you know, kind of a barrier to moving on out. Look, that's what we see in the system around Putin, it's kind of kleptocratic and it's uh you know, it's filled with nepotism, although they kind of like the people who you kind of see out there in prominent positions of the sons or daughters of including Putin himself. I mean that's when a system has degenerated and that's gonna kind of, and I suppose in a way this is a symbol of the degeneration of the system, but again, it's just a diversion from, you know, kind of the bigger issues and bigger implications of things that we're discussing. </s><s>[INST] So, critics on the left often used a straw man of tds trump derangement syndrome, uh why does donald trump arouse so much emotion in people? [/INST] It's just the nature of the person. I mean, I don't feel particularly emotional about him, I mean he's kind of a he's a very flawed guy to be honest and this may seem bizarre. I felt sorry for him because this guy is so vulnerable, so wrapped up in himself that I mean he's just exquisitely open to manipulation and I saw people taking advantage of him all the time and he has zero self awareness. I mean, I kept thinking to myself, my God, if this guy didn't have this entourage around him, how would he function? I mean, I felt sorry for us as well, I mean that he ended up being our president because that should not have happened. I mean in terms of character and in terms of fit for fit for the </s><s>[INST] job, although I saw [/INST] this, you know, kind of over a period of time, but I didn't feel, you know, kind of any, you know, sense of derangement, you know, kind of around him, he didn't drive me nuts in that way. I just became I was just very worried about, you know, the kind of the impact that he was having on many issues. </s><s>[INST] Here's the important thing. So what I noticed that people that criticized donald trump is they get caught up in the momentum of it and they're unable to see. Um first of all, let's start with some ground truth, which is approximately half the country voted for the guy, right? [/INST] And more voted in 2020 than voted in 2016. </s><s>[INST] And I just I just feel like people don't load that in. [/INST] A lot of those people didn't vote for him and his personality and often could, because I know a lot of people who voted for him the first time and second time and they could disassociate, you know, kind of the, all of the kind of features of donald trump that drives other people nuts from, you know what they thought that an actual fact he could achieve in terms of and it wasn't just this kind of sense about what I couldn't possibly vote for democrats. Sometimes it's just like, well look, he shakes things up and we need things to shake to be shaken up and </s><s>[INST] some people might have voted him personality. [/INST] Some of them, some of them did as well, but I'm just saying that not all of them did either, </s><s>[INST] but [/INST] yeah, I can't say, I'm just saying anecdotally. I know people who voted him because he's him from the charisma and another devoted because he's shaking things up and you know, he's keeping people on their toes and you know, kind of we need that, you know the idea, </s><s>[INST] but the way to avoid trump derangement syndrome to, to me me as as a doctor, I'm sort of prescribing to the patients on this syndrome. This uh this issue is I feel like you have to empathize with the people, you have to imagine your mind all the different like um strengths that the people who have voted for donald trump see and really understand it. Really feel it like walk around with it and then criticize like I just feel like people get lost in this bubble of criticism in their own head. I don't forget like the tribe you're in or whatever in their own head, they're not able to see like half this country that were part of voted for the person. Same with biden, half the country voted for the guy, the people that are criticizing biden and they're doing this. The way biden is currently criticized is not based on policy uh is based on personal stuff similar to trump. [/INST] Yeah, I know it is. I mean that's what people do. Look, I think part of that is I mean look, first of all I want to say, I completely agree with you about understanding where people are coming from and I think it's very important for people to listen to other people and their views. I try to do that all the time. Trying to learn from that. You know, I mean, everybody's got a perspective and a context. We all live in a certain context. We're all living in history. Our own personal histories matter a lot. And also the larger context and environment in which we're living in and where we live and who we live with and you know the kinds of lives that we lead as well. Those are all extraordinary important. I mean I know that from you know myself, everything, you know that I've done in my life has been shaped by where I came from who I was, my family and the way that we looked at things you can't take yourself out of that. I mean you can do it in some, you know, like a science or something else. But you know, it's still your own views and maybe some of the ideas that you have in pursuing experiment might have been shipped by your larger context. You know, depending on what it is that you work on. But the other thing is the nature of the political system, the presidential election is like a personality contest, a beauty contest. It's like a kind of a referendum on, you know, one person or another. It's kind of like what we see in Russia honestly with, you know, Putin or not Putin or Putin and Putin before, you know, it's all about Putin and you know, what do you think about Putin? It's not about what the president should be doing and, you know, kind of what their policies are. That's kind of the bizarreness of the US political system that we've just seen this happening in the United Kingdom. You've got this core of a couple of 1000 a couple 100,000 rather, people in the Conservative Party have just voted for three leaders in a row. The rest of the country is and then they're just looking at, you know, whether they like that personality and you know, what they say to them rather than what they're necessarily going to do for the country. I mean, which is, you know, kind of pretty absurd. And then again, the presidency is a weird hybrid in the United States. You know, we were talking before about the person who should be running the country to the chief executive or the Prime Minister in another setting, but we don't think of it like that. You know, we often think about whether we like the guy or not or you know, we'd like to hang out with them all the, you know, one of my younger relatives and I said, so why did you vote for trump? Said, well he was great, it's funny, I went to his rallies, I got, you know, all kind of charged up and I said, could you see yourself voting for biden? No, he's too old and simple, you know, he's only just a little bit, you know, kind of older than trump or his, you know, the same agency grandma. Do you think your grandma's old? Oh no, not at all. But it's just this kind of perception is boring, you know, so that people are actually sometimes, you know, basically being, you know, kind of motivated by just a feeling, you know, kind of that, that kind of sense because that's the sort of nature of the, you know, the presidency. It's this kind of how you feel about yourself as an american or how you feel about the country really large, kind of the symbol of the state, you know, in Britain, you had Queen Elizabeth second and everybody, you know, seemed to for the most part, you know, everyone I guess, but most people respected her as a person as a personality, as a kind of symbol of the state, even if they actually didn't really like the institution of the monarchy. There was something, you know, kind of about that particular personality that you were able to, you know, kind of relate to in that context, but in the United States, we've got all that rolled into one, the head of state, the symbol of the state, the kind of the queen, the king, the kind of idea, the chief executive, the kind of prime ministerial role, and then the Commander in chief of the military, it's all things, you know, kind of at once, but ultimately, for a lot of people, it's just how you feel about that person. Oh, I couldn't cover for them because of this, or I couldn't vote for them because of that. And in 2016, you know, Hillary Clinton actually did win the election in terms of the popular vote. So it wasn't that, you know, kind of people wouldn't vote for a woman. I mean, more people voted for her on the popular level, not obviously, you know, through the Electoral College, in the Electoral College votes. So it wasn't just, you know, gender or something like that, but it was an awful lot of things for people found trump attractive because he was sticking up the big middle finger to the establishment, he's an anti establishment, changed character. There was a lot of people voted for Barack Obama for the same reason and voted for trump, We know that phenomenon. What was the 11 12% of people, you know, so they could vote for some completely, totally different, radically different people because that sort of sense of change and charisma, I mean I had people who voted for trump but would have voted for Obama again if he'd run again because they just like the way that he spoke like the way that you know because they said I mean this is all my own anecdotal things about one of my relatives that I could listen to Obama all day every day. I just love the way he sounded, I love the way he looked, you know, I was just like that the whole thing about him and then say about trump while he was exciting, it was interesting, you know he was kind of like you know whipping it up there, you know, so there's this just this kind of feeling, you know we always say about you know could you have a beer with this person and people people decided they couldn't have one with Hillary clinton and you know maybe they could go off and have one with Barack Obama and with donald trump, didn't want to have one with joe biden, you know for example and remember George W Bush didn't drink so he wouldn't have had to be with him, he'd have gone out and got a soda or something with him but you know there's this there's that kind of element of just that sort of personal connection in the way that the whole presidential election is set up, it's less about the parties, it's not about the platforms, it's more about the person. </s><s>[INST] Yeah. And picking one side and like sticking with your person, really like a sport team. What do you think about Vladimir Putin? The man and the leader? Let's actually look at the full, you've written a lot about him, the recent Vladimir Putin and the full context of his life. Um, let's zoom out and look at the last 20 plus years of his rule. In what ways has he been good for Russia? In what ways? Bad? [/INST] Well, if you looked at the first couple of terms of his presidency, I think, you know, on the uh overall ledger, he would have actually said that he made a lot of achievements from Russia. Now, there was of course the pretty black period of the war in Chechnya. But, you know, he didn't start that, that was Boris Yeltsin, that was obviously a pretty catastrophic event. But if you look at then other parts of the ledger of what Putin was doing, you know, from the two thousands, you know, onwards, he stabilized the Russian economy, uh, brought back, you know, kind of confidence and and and the Russian economy and financial system, he built up a pretty impressive team of technocrats for everything, the central bank and the economics and finance ministries who, you know, really got the country back into shape again and solvent paid off all of the debts and, you know, really started to build the country back up again domestically. And, you know, the first couple of terms again, putting Chechnya, you know, to, to one side, which is a little hard because, I mean, there was a lot of atrocities and I have to say that, you know, he was pretty involved in all of that because the FsB which he headed previously was in charge of wrapping up Chechnya and it created, you know, kind of a very strange sort of system of fealty, almost a feudal system in the kind of relationship between Putin at the top and in Chechnya, there was quite a lot of distortions, you know, kind of as a result of that in the way that the Russian federation was run, you know, a lot more of an emphasis on the security services for example. But there was a lot of pragmatism and opening up the country for business. Um, you know, basically extending relationships. I would say that, you know, by the end of those first couple of terms of Putin, Russians were living their best lives. Um, you know, there was a lot of opportunity for people, uh, people labor was being paid for, they weren't being taxed, the taxes were coming out of the extractive industries. Uh, there was, you know, kind of like, I guess a sense of much more political pluralism, but it wasn't the kind of the chaos of the Yeltsin period. I'll let you see a shift and it's pretty much when he comes back into power again In 2011, 2012, and that's when we see a kind of a different fares emerging And, you know, part of it is the larger international environment where Putin himself has become kind of convinced that the United States is out to get him and part of it goes back to the decision on the part of the United States to invade Iraq in 2003. There's also, you know, the recognition of Kosovo in 2008 and, you know, that the whole kind of machinations around all kinds of, you know, other issues of NATO expansion and elsewhere, but Iraq in 2003, and this kind of whole idea after that, that the United States is in the business of regime change and perhaps, you know, has him in his crosshairs as well. But there's also then kind of, I think, a sense of building crisis after the financial crisis and the great recession, 2008, 2009, because I think Putin up until then believed in, you know, the whole idea of the global financial system and that Russia was prospering and that Russia, you know, part of the G eight and actually could be genuinely one of the, you know, the major economic and financial powers and then suddenly he realizes that in the west is incompetent that, you know, we totally mismanaged the economy of our own the financial crash in the United States were kind of blowing up of the, of the housing bubble and that we were feckless and that that had global reverberations And he's prime minister of course, you know, in this kind of period, but then, you know, I think that that kind of compels him to kind of come back into the presidency and try to kind of take things under control again in 2007, And after that, he goes into kind of a much more sort of focused role where he sees the United States is a big, big problem. And he also, you know, starts to, you know, kind of focus on also the domestic environment because his return to the presidency is met by protests. And he genuinely seems to believe because again, this is very similar to believe here in the United States that donald trump couldn't possibly related by americans, that somehow was some kind of external inter interference because the Russians interfered and had an impact. Putin himself thinks at that time, it's one of the reasons why he interferes in our elections later, that the United States and others had interfere, because he knew that people weren't that thrilled about him coming back did kind of like the medvedev period and the protests in Moscow and ST Petersburg and other major cities. He starts to believe were instigated by the West by the outside because of, you know, funding for transparency in elections and you know, all of the Ngos and others, you know, they're operating State Department embassy funding, you know, the, you know, the whole attitude of God is back, you know, kind of thing. And so after that we see Putin going on a very different footing. It's also somewhere in that period 2011, we start to kind of obsess about Ukraine and he's always, you know, I think being kind of steeped in that whole view of Russian history. I mean, I heard at that time, I was in, I've written about this and many of the things that, you know, I've written about Putin, but in that same time for him, I'm going to all these conferences in Russia where Putin is, and Peskov, his press secretary, they talk about him reading Russian history, I think, is this in this kind of period that he formulates this idea of the necessity of reconstituting the Russian world, the Russian empire. He's obviously been very interested in this. He's always said of course that the collapse of the soviet union was the great catastrophe 20th century, but also the collapse of the Russian empire before it. And he starts to be critical about Lenin, the bolsheviks and he starts to do all this, talking about Ukraine as the same country, Ukrainians and Russians being one and the same and this is where the ledger flips, because, I mean, the initial question you asked me is about has Russia as Putin been good for Russia or not. This is where we get into the focal point of or the point where he's not focusing on the prosperity and stability and future of Russia, but he starts to obsess about the past and start to take things in a very different direction. He starts to clamp down at home because of the rise of opposition. And the fact that he knows that his you know, brand is not the same as it was before. His popularity is not the same as it was before because he's already gone over that, you know, that period in anybody's you know, professional and you know, political life that you know, if you stay around long enough, people get a bit sick of you, you know, it should be talked about that before, should you stay, you know, kind of in any job for a long period of time, you need refreshing and you know, kind of Putin is, you know, starting to look like he's gonna be there forever and people are not happy about that and would like the chance as well to kind of move on and move up and you know with him and still in place, that's not going to be particularly possible and that, you know, it's around the time when he starts to make that decision of annexing Crimea and that's when the whole thing flips in my view, the annexation of Crimea in 2014 is the beginning of the end of Vladimir Putin being a positive force within Russia, because if you pay very close attention to his speech on the annexation of Crimea in March of 2014, you see all the foreshadowing of, you know, where we are now. It's already kind of his view of kind of his obsessions, his historical obsessions. His view of himself has been kind of fused with the state of kind of a modern czar and his idea that the West is out to get him and it becomes after that almost kind of like a Messianic mission, you know, to turn things in a different direction </s><s>[INST] and who are the key people to you in in this evolution of the human being of the leader. Is it Patrick Chef, is it shows you the Minister of Defense, is it like you mentioned Pest called the Press Secretary? Uh what role does some of the others like Lavrov play? [/INST] I think it's more rooted in the larger context. I mean, individuals matter in that context, but it's just kind of like this shared worldview. And if you go back to the early 1990s, immediately after the dissolution of the Soviet Union, when Yeltsin, you know, and the his counterpart from Ukraine Belarus pull it apart. There was an awful lot of people who wanted to maintain the soviet union, not just Putin, I mean, you remember after Gorbachev tried to have the new Union treaty um in 1991 and there was the Emergency committee set up the coup against Gorbachev, it was because they were worried he was going too far and unraveling, you know, the Union then as well, they were opposed to his reforms. There's always been a kind of a very strong nationalist contingent that become Russian nationalists over time rather than soviet, you know, hardliners who, you know, basically want to maintain the Empire, the Union in some form. And in the very early part of the 19 nineties, there was a lot of pressure put on Ukraine and all the other former survey Republics now, independent states by people around, you know, Mayor lucio, for example, in Moscow by, you know, other forces in the Russian duma, not just, you know, Vladimir Zhirinovsky and others, but really serious, you know, kind of what we would call him, like right wing nationalist forces, but it's, you know, pervasive in the system and it's especially pervasive in the KGB and in the security sector. And that's where Putin comes out of remember, Putin also was of the opinion that one of the biggest mistakes the bolsheviks made was getting rid of the Orthodox Church as an instrument of the state. And so there's this kind of restoration ist wing within the security services and the state apparatus that want to kind of bring back Russian orthodoxy is a state instrument, an instrument of state power And they were kind of, you know, looking all the time about strengthening the state, the executive, the presidency and, and so it's everybody who takes part in that And it's also there's more power honestly, and they see Putin as their vehicle for power. I think people like Sergei Kiriyenko, Kiriyenko back in the 90s, I mean, my God, that guy is all in or like Dmitry Medvedev You know, who was, you know, a warmer fuzzier version of Putin certainly had a totally different perspective, wasn't in the KGB fuzzier version. Yeah, I mean, he's kind of like, he was literally a warm personality. I don't know if you watched him during the September 30 annexation. The guy had all kinds of facial twitches and looks so rigid and stiff that he looks like he might implode. I mean, that wasn't, you know, how he was, you know, earlier in his career and he, you know, had a different view of paris striker. We always have to remember that Putin was not in Russia during paris strike, he was in Dresden watching the east german state fall apart and you know, dealing with the Stasi and in a kind of place where you weren't getting a lot of information about what was happening in West Germany or even what was happening back home in perestroika and he has that kind of group of people around him, the patron chefs and botany cuffs and others and so given off and others, you know, from, you know, the different configurations of his administration who have come out of that same kind of mindset and kind of, you know, wanting to put everything back together again. So there's a lot of enablers and a lot of, you know, power seekers and there are a lot of people who, you know, think the same as him as well. He is a man of his times, a man of his context, </s><s>[INST] you as a top adviser yourself and and a scholar of Putin. Do you think actually now in his inner circle, are there people he trusts [/INST] people he trusts for some things, but I don't think there's people he trusts for everything. I don't think the kind of person who tells anyone everything at all. I don't think he's got some, you know, he's he, I think he compartmentalizes things. He's often said that the only person who trusts himself, I think that's probably true, he's the kind of person who keeps his own counsel. I mean, people talk about Kovalchuk for example, or you know, kind of some of the other people who are, you know, friends with him that going to go back to his time in ST Petersburg, you know, at various points, he seem to, you know, spend a lot of time, you know, way back when talking to people who are, you know, people think of kind of more moderating forces like Aleksei Kudrin, but, you know, it doesn't seem to be interacting, you know, with them, you know, there are obviously aspects of his personal life, you know, does he speak to his daughters? Does he speak to you know, kind of lovers? You know, kind of in a way people speculate about, you know, kind of who might confide in. But I would greatly doubt that he would have deep political discussions with them. He's a very guarded, very careful person. </s><s>[INST] What about sources of information then? So trust a deep understanding about military strategies with um for certain conflicts like the war in Ukraine or even special uh subsets of the war in Ukraine or any kind of military operations. Getting clear information, [/INST] deeply suspicious, you know, of people and of of information. And I think part of the problems that, you know, we see with Putin now, I mean, I've come from isolation during Covid, I'm really convinced that, you know, like many of us, you know, a lot of Putin's views have hardened and the way that he looks at the world have been shadowed in very dark ways by the experience of this pandemic. You know, obviously he was in a bubble, different kind of bubble from most of us. I mean, most of us are not bubbles with multiple, you know, kind of palaces and you know, kind of the Kremlin, but you know, we've seen, you know, so much, it's obviously a lot of this stage that isolation, you know, they're kind of making it very clear that he's those are the guy who is in charge making all the decisions, you know, one end of the table and everybody else is at the other end. But, you know, it's very difficult and to bring, you know, information to him in that way. He used to have a lot of information bundled for him in the old days by the presidential administration. And I know that because it was a lot more open in the past and have a lot of meetings with people in the presidential administration who brought outside, you know, it's all source information, you know, for him and, you know, kind of funneled in information from different think tanks and, you know, different viewpoints and maybe a kind of more eclectic, diversified set of information. He would meet with people, you know, you've heard all the stories about where he had once called up, Masha Gessen, you know, and had a, you know, come in, you know, obviously a very different character as a as a journalist and a critic. You know, we've heard about Venediktov from Echo muscovy, the, you know, the radio program that the editor who Putin would, you know, talk to and consult with. He he'd reach out people, um, like little and Alex saver, for example, the head of Memorial, he had some respect for her and would, you know, sometimes just talk to her, you know, for example, all of that seems to have come to a halt and I think, I think a lot of us worry, I mean us who watch Putin about what kind of information is he getting, you know, is it is it just the information he's seeking and gathering himself that fits into his world view and his framework, we're all guilty of that, of looking for things gets while social media preferences. People just bring into him things that they think he wants to hear, like the algorithm, you know, kind of like the Kremlin working in that regard as he himself, you know, tapping into source of information that he absolutely wants. Remember, he is not a military guy, he's an operative and he was sort of trained in operations and contingency planning. The Defense Minister as a civil engineer, was the former Minister of emergencies. It wasn't a military planner. You know, somebody like Gary, the Head of the Chiefs of Staff, maybe a military guy, you know, in this, you know, case from the army, but he's also somebody who's in a different part the chain of command. He's not somebody who would spontaneously start, you know, telling Putin things and Putin, you know, comes out of the FSB out of the KGB, the soviet era and he knows the way that, you know, intelligence get filtered and works. He's probably somebody wants to consume raw intelligence. He doesn't probably want to hear anybody else's analysis and he's thrived in the past of, you know, picking things up from people, you know, I've taken part in all of these meetings with him, gone for hours because he's just collecting, he's collecting information. He's setting people out, he wants to know the questions they ask. He learned something about the questions that people ask, the way that they ask them. You know, so he's kind of soliciting information himself. And if he's cut off from that information, you know, because of circumstances, then, you know, how is he formulating things in his head? And again, getting into you can't get into his head, but you can understand the context in which he's operating and that's where you worry because he clearly made this decision to invade Ukraine behind the back of most of his security establishment. </s><s>[INST] You think so, [/INST] I think it's pretty apparent </s><s>[INST] what uh what what would the security establishment will be [/INST] that would be the larger, you know, thinking the funneling in information from the Presidential administration, from the National Security Council, it looks like, you know, he made that decision with a handful of people and then, you know, having worked in these kinds of environments and it's not that dissimilar, you filter information up. So think about, you know, you and I are talking for hours here. Um if you were my, you know, basically um, you know, senior official and I'm your briefer, I might only get 20 minutes with you and you might be just like, you know, looking at your watch the whole time and thinking, hang on a second, I've got to go and I've got this meeting, I've got that meeting and yeah, your point, you're not gonna wait there, so I give this long explanation, I've got to get to the point and then I've got to then choose for myself, what's the information I'm going to impart to you after the 20 things I think are important, You know, okay, I've got 20 minutes, maybe I only get two minutes, maybe, you know, you get called out and somebody, you know, kind of interrupts something happens, I'm going to get one minute, two minutes. I mean I wanted to remember, I had to give a presentation when I was in </s><s>[INST] government, you know, [/INST] to Henry Kissinger, you know, for that defense policy board and we planned bloody weeks on this thing. You know, power points were created, teams of people were brought together and you know, people were practicing this, we had all these, you know, different people there and I said, look, Henry Kissinger is an academic and former professor and you know, I you know, got to watch him in action. He's gonna like, you know, five seconds in if we're if we're lucky we get that far, ask us a question and just throw off our entire presentation, what is it that we want to convey and that's exactly what happened and then, you know, people aren't really prepared or they wanted to convey and that, you know, that prepared, you know, a nice sort of folsom power point like approach, we never even got there. And so God knows what, you know, he took away from it at the end of it, and that's, you know, think about Putin, he's going to be kind of impatient, he's we see the televised things where, you know, kind of sits at the table a bit like, you know, people won't necessarily see us here, and he puts his hands on the table, he looks across at the person, he says, so tell me, you know, what's the main things I need to know? And of course the person's mind probably goes blank. You know, the kind of the thought of like, oh God, what's the main thing? And then they start, well, Vladimir Vladimirovich and, you know, they start the kind of, you know, they're they're revving up, you know, to get to the point and then he cuts them off. So, you think about that, and then you think about what information has he got and then how does he process it? And is he suspicious of it? Does he not believe it? And what on what, inside of his own history then, you know, leads him to make one judgment over another. He clearly thought the Ukrainians would fall apart in five seconds. </s><s>[INST] We don't know if he clearly thought that, but that there was a high probability maybe. [/INST] I think, I think he pretty much thought it because I think he thought that, you know, kind of excellence. He wasn't very popular. There was an awful lot of, you know, pro Russian sentiment in whatever way he thinks that is because people have Russian speakers and that, you know, they're kind of, you know, in polling that, you know, they expressed affinity with Russia. I mean, certainly in Crimea that worked out because a majority of the population had, you know, higher sentiments or feelings of affinity with Russia and you know, obviously, you know, that that kind of they got traction there, but it's more complicated. We talked about Donbass before about being a kind of melting pot when, you know, they tried the same thing in Donbass Donetsk and Luhansk cause they tried in Crimea in 2014 didn't kind of pan out. In fact, you know, a whole war broke out. They tried, you know, to kind of in um, you know, many of the major cities are now under attack, including a desert to kind of ferment, you know, pro Russian movements and they're completely and utterly fell apart. So Putin was thinking and I'm pretty sure based on polling and the fsb having infiltrated, you know, an awful lot of the Ukrainian hierarchies, we're now seeing is quite apparent with some of the dismissals in Ukraine. It was pretty sure that, you know, kind of he would get traction and that it would be like 1956 in Hungary or 1968 in Czechoslovakia, remember he comes out of the and drop off levy as it's called, the kind of cohort of people who come and under into the KGB under Yuri Andropov and your Andropov has presided over a lot of these anti dissident, you know, kind of movements inside of Russia itself and how you suppress opposition, but also over, you know, how you deal with um, you know, kind of the uprisings in, you know, Czechoslovakia and Hungary. And there's all these lessons from this that, you know, you can put everything back in the box and yeah, there might be a bit of violence and a bit of fighting, but ultimately, you think you've got the political figures and you decapitate the opposition. So they thought you you Zielinski would runaway, Yanukovych run away. But, you know, that was kind of a bit, you know, sort of a different set of circumstances. And they thought that all of the local governments would, you know, kind of capitulate because they had enough Russians and inverted commas in there again, mistaking language and, you know, kind of positive affinity towards Russia for identity, or how people would react in the time and not understanding people's, you know, linkages and, you know, kind of importance of place, the the way that people feel about who they are in a certain set of circumstances, a place, </s><s>[INST] But the invasion of Ukraine in 2022 is unlike anything that he was ever involved with, but I [/INST] Don't think he thought it would be, you know, because it is kind of if he looks back into the past, you right though, he wasn't involved in 68 or 56 or what happened in the 1980s, in Poland, </s><s>[INST] but there's a very wide front and it's the capital and I mean, this isn't going, [/INST] this isn't Chechnya, this isn't, you know, kind of Syria, or for example, </s><s>[INST] this is a major, exactly like its large size, [/INST] It was more like Afghanistan, but they didn't realize that because again, Ukrainians are us, this is kind of inability to think that people might think differently and might want something different and that 30 years of independence actually has an impact on people and their psyches, and if I look back to the 19 nineties, I mean, I remember being in seminars in the Harvard at the time, and we were doing a lot of research on, you know, what was happening in, you know, the former soviet union at the time, because in the early 19 nineties, just after the, you know, the whole place fell apart and there was already under Yeltsin, this kind of idea of Russians abroad Russians in the near abroad Russian speakers and the need to bring them back in. And I remember we had seminars at the time when we talked about at some point, there'd be some people in Russia that would actually believe that those Russian speakers needed to be brought back into Russia, but that the people who spoke Russian might have moved on because they suddenly had other opportunities and other windows in the world, I mean, look what's happened in Scotland, you know, for example, most people in Scotland speak english, the Scottish language is not the standard bearer of Scottish identity. There's just, it's, it's almost of civic identity, different identity than not just national identity, just like you see in Ukraine and there's lots of english people have moved to Scotland and now think of themselves as Scottish Brazilians or Italians and you know, all kinds of people who've moved in there and it's a smaller population obviously and the scale of Ukraine, but you know, people feel differently and there's been a devolution of power and when Brexit happened, you know, Scotland didn't want to go along with that at all and wanted to kind of still be, you know, having a window on europe and that's kind of historic and lots of people in Ukraine have looked west, not east, it depends on where you are, not just in love if you know, or something like that, but also in Kiev and Kharkiv, you know, was kind of predominantly Russian speaking city, but he was also the center of Ukrainian culture and Ukrainian literature, you know, different points, people have different views. I grew up in the north of England, we don't feel like the south of England, there's been a massive divide between north and south and England for millennia, not just centuries. So, you know, people feel differently depending on where they live and you know, kind of where they grew up and Putin just, I didn't see that, you didn't see that. </s><s>[INST] Well, hold on a second, let me sort of push back at the fact that I don't think any of this is obvious. So first of all, Zelensky before the war was unpopular, [/INST] It was, what was it? 38%, something like that. But but best in the popularity. </s><s>[INST] Yeah, let me sort of make the case that the calculation here uh is very difficult if you were to pull every citizen of Ukraine and ask them, what do you think happens if Russia invades? Just like actually each put each individual Ukrainian in a one on one meeting with Putin and say, what do you think happens? I honestly think most of them will say that will that will agree with the prediction that the government will flee with collapse and the country won't unite around cause because of the factions, because of all the different parties involved? Because of the popularity [/INST] Of said the same thing about the Soviet Union when Hitler invaded in 1941. You see the Promise Putin always reads history from one perspective over another. I think most countries basically rise to their own defense. So this is actually one of the first times that Russia has been on the offensive rather than on the defensive, you know, So there's kind of a bit of a flip there. I mean, obviously Afghanistan, but you know, that was more complicated because it was it was also supposed to be an intervention, right? I mean, it wasn't supposed to be to annex Afghanistan, it was to try to prop up, you know, kind of or reinstall a you know, a leader there, Syria, you were in there to, you know, help your guy bashar al assad turn away the opposition Chechnya was a debacle. The Chechens fought back big time and it was only by dint of, you know, horrible violent persistence and ruthlessness and nasty dirty tricks that um you know, kind of Putin prevailed there. But and then, you know, you wonder did he prevail? Because what happened, you know, Chechnya sometimes describes the most independent part of the Russian federation. And Ramzan Kadyrov plays power games in Moscow, his predecessors, even his father and others wouldn't have done that. Akhmed Kadyrov and you know, before that Gdf and Maskhadov, I mean, they were willing to make a compromise, but you know, they wouldn't have had, you know, the same position that has had. So, you know, I think that again, it's it's your perspective and where you stand and what, which bit of history you start to read and that's why I said that, you know, can I think Putin, it's again, it's the information the way that he processes it. I think most Russians also can't believe that they've done something wrong in Ukraine. I mean maybe at this point things are changing a bit, but that's why there was, you know, so much kind of support for this in the right way. I mean, I have Russian friends again I said, but look what, you know, was happening and done yet, look what was, you know, the Ukrainians were doing to our guys, you know, look what was happening to Russian speakers. You know, we were defenders, we were not, you know, we're not invaders. I think, you know, again, the special military operation, you know, idea now, I think it's flipping obviously in the way that with the war going on there, but Putin wasn't, you know, kind of looking at what would happen, I mean, most of the kind of glory parts of Russian history when you kind of go in, you know, you chase napoleon back to paris or you chased the Germans back to Berlin, you put the flag above the Reichstag, that's a very different set of affairs when you've been fighting a defensive one, you've been invaded from a war where you invade someone else and even the most fractured populations like you had in the soviet union, the point rally round and World War One, the fell apart. I mean there's there's our didn't manage to rally everybody around the whole thing for the past and World War Two Stalin had to, you know, revive nationalism, including in the Republics in Central Asia and elsewhere to revive nationalism. And Ukraine's suddenly found nationalism, you know, that kind of sense. </s><s>[INST] That's really interesting because it's not it's not obvious especially what Ukrainians went through in the 1930s. It's not obvious that that, I mean, my grandfather was Ukrainian and he was proud to fight a Ukrainian, jew. He was proud to fight and willing to die for his country. It wasn't like his [/INST] country then was the soviet union </s><s>[INST] the soviet union. Right? Sorry to clarify [/INST] that he might fight now for his country. Ukraine. </s><s>[INST] Yes, but I'm just like lingering on the point you made it was not obvious that that united feeling would be there. [/INST] No. And again, it wouldn't have been obvious for the soviet union. </s><s>[INST] That's what, [/INST] that's what I'm saying. </s><s>[INST] Sorry. I was referring to my grandfather, the soviet union were both saying the exact same [/INST] thing </s><s>[INST] you're saying. That's a really powerful thing because I take it because you take history as it happened, you don't realize it could have happened differently. It's kind of, it's fast, [/INST] it's that whole counterfactual, right? Yeah. Because I mean, if you if you kind of, that's that's why we all need in the United States to really examine our own history because, you know, there's a lot of lessons from that that, you know, we we should treat very cautiously. It doesn't mean that, you know, history repeats or even rhymes, you know, the old axiom all the time, but there are a lot of things that you can take away differently from putting a different perspective and a different slant on the same set of events. I mean, I was used to wonder like how many books can be written on the french revolution, or even on the Russian revolution. You know, I studied with Richard pipes, remember, he was really offended after he'd written his great micro surplus on the Russian revolution, two volumes that other people would, you know, kind of right about the Russian revolution. So, I've written it all, and I thought, well, actually, maybe you haven't, it's like there might be some completely different angle there that you haven't really thought of, and that's Putin, you know, I remember Peskov saying, Putin reads history all the time in Russian history and I thought, well, maybe should read some world history, you know, maybe he should, you know, kind of read some european authors on Russian history, not just, you know, reading Lamanno PSA for, you know, Russian historians on Russian history, because you might see something from a very different perspective and look in the United States made a massive mistake in Vietnam right? I mean, they saw Vietnam is kind of weak manipulated by, you know, kind of external forces china soviet Union, but the Vietnamese fought for their own country, they suddenly became Vietnamese. And ho chi Minh became, you know, basically a kind of a war time fighter and leader, you know, in a way that, you know, perhaps people wouldn't have understood either. You </s><s>[INST] said, United States made a massive mistake uh, in Vietnam and that for some reason, sprung a thought in my head as the United States since World War Two. Had anything that's not a mistake in terms of military operations abroad, I suppose all the ones that are successes we don't even know about. Probably. So it's like very fast military operations [/INST] in Korea is divided. I mean, I don't know, it's successful, but, you know, kind of, I mean, there was a solution, found that, you know, some people promoting, you know, in this case as well, of a sort of division and a, you know, the D M. Z. And, you know, one side over the other and, you know, kind of perpetuating a division which I think is particularly successful. But if you think about World War One and World War Two, the United States came in, you know, and some very specific sets of circumstances in World War One, they did kind of come in to help, you know, kind of liberate parts of europe France and, you know, kind of the U. K. And, you know, everything else. Great Britain in the war towards the end of it, World War Two. You know there was that whole debate about whether the United States should even be part of the war. I mean we know it wasn't thought to overturn the holocaust and all of the kind of things you kind of wish it had been fought for that was because of Pearl Harbor and you know the japanese pulling in. But ultimately it was easy to explain why you were there, you know, particularly Poole Harbor and what had happened. It was harder to explain Vietnam and Korea and you know, maybe there wasn't that that's kind of gonna be a problem for Putin and that's why there is a problem for Putin all of his explanations of being questioned, you know, started off on NATO or this or that or the other and you know kind of liberating you know, Ukraine from nazis or you know kind of basically stopping the persecution of Russian speakers and all of this has now got lost in just this horrific destruction. And that's what happened in Vietnam as well. It became, you know, a great degradation of the Russian military with atrocities and people wondering why on earth the United States was in Vietnam. I mean even that kind of happened in Britain and the colonial you know kind of period as well, why was the United Kingdom doing you know committing atrocities and you know kind of basically fighting these colonial wars Northern Ireland why was the United Kingdom still, you know, kind of militarily occupying Ireland Cyprus, there's all kinds of, you know, instances where we look at these things because what Russia is doing now, Putin is trying to occupy another country irrespective of, you know, kind of the historical linkages and you know, the kind of the larger meta narratives that he's trying to put forward the </s><s>[INST] what role did the United States play in the lead up and the actual invasion of of Ukraine by Russia. A lot of people say that, I mean obviously Vladimir Putin says that part of the reason the invasion had to happen is because of security concerns over the expansion of NATO. And there is a lot of people that say that this was provoked by NATO. Do you think there's some legitimacy to that case? [/INST] Look, I think the whole situation here is very complicated and you have to take a much longer view than, you know, what happened in 2008 with the opened of Ukraine and Georgia, which actually, by the way I thought was a strategic blunder. Just to be very clear because it wasn't any kind of thinking through about what the implications of that would be. And you know, what would actually mean for Ukraine security. And also bearing in mind what Putin had already said about NATO expansion, they came on the wake of the recognition by the United States pretty unilaterally of Kosova and it also comes in the work of mentioned before the invasion of Iraq, which really, because very important for understanding Putin's psyche. So I think, you know, we have to go back, you know, much further than it's not just talking about kind of NATO and what that means. NATO is part of the whole package of Ukraine going in a different direction from Russia. Just as soon as the european Union, remember, the annexation of Crimea comes after, Ukraine has sought an association agreement with the european Union, not with NATO at that particular point, even though, you know, the EU on the security, common security defense policy, um basically has all kinds of connections with NATO, you know, various different levels of european security front, it was all about europe and going on a different economic and political and ultimately legal path, because if you have association agreement eventually get into the comedy tent and it just transforms the country completely in Ukraine is no longer the Ukraine of the soviet period of the Russian empire period. It becomes, you know, on a different trajectory like Czech Republic, Slovakia Poland, you know, another country, it becomes a different place, It moves into a different space and that's part of it. But if you go back again To the period at the very beginning of the 1990s, after the dissolution of the Soviet Union. Well, there's no discussion about NATO at that point and NATO enlargement. There is a lot of pressure again, as I've said before by nationalist elements on Ukraine trying to bring it back in the fold and wanting to make what was then, you know, this mechanism for divorce, more of a mechanism for re manage the commonwealth of independent states and in the early 1990s when Ukraine became an independent state, it inherited that nuclear arsenal from the soviet union, basically whatever was stationed opposition in Ukrainian territory at the time became Ukraine's strategic and you know kind of basically intermediate and tactical nuclear weapons. And you know in the United States at the time, you know, we had all this panic about what was gonna happen with all of that. I mean I think you know it was a scientist and kind of technically it would have been difficult for Ukraine to actually use this. I mean the targeting was you know done centrally, they were actually stationed there. But nonetheless, Ukraine like Belarus and Kazakhstan suddenly become nuclear powers. And you know Ash carter, the former U. S. Defense secretary has just died tragically. And Dave was talking about, you know, uh talking together today was part of the whole team of americans and others who you know try to work with Ukraine Belarus and Kazakhstan to get them to give up the nuclear weapons and back in the early period of that 93 94 go back and I mean I was writing about this at the time I wrote a report called back in the USSR, which is, you know, kind of on the website of the Kennedy school with some other colleagues, we're monitoring how there was all these accusations coming out of Moscow, the Defense Ministry and the Duma, the parliament and others that Ukraine was trying to find a way of making a dirty bomb, using its nuclear weapons, you know, becoming a menace. Um and, you know, kind of Ukraine might have to be brought to order. So a lot of the dynamics we're seeing now are happening then, irrespective of NATO, basically, the problem was always Ukraine getting away Yeltsin himself when he unraveled the soviet Union, didn't really wanted to unravel, but he didn't have the wherewithal to bring the country back again. Russia was weak after the collapse of the soviet Union, its economy imploded. Um it had to give sovereignty to all of these constituent parts of the Russian federation, in terms of the sort of devolution of authority. It had the war in Chechnya which Yeltsin stupidly sparked off in 1994 you had to to stand one of the region's oil rich regions, um you know, basically resting out a kind of a bilateral treaty with Moscow. You had the whole person was kind of seemed like it was falling apart so that, you know, you couldn't do anything on Ukraine, because you didn't have the wherewithal to do it. And then when, you know, kind of basically Russia starts to get its act back together again. All of these security nationalist types who would never wanted Ukraine belarus and Moldova or anywhere else to kind of move away. They didn't worry that much about Central Asia to be frank, but they know they did want you know the core states in their view to come back and Moldova was part of that even it's not Slavic but you know, they wanted belarus and northern Kazakhstan and probably Kazakhstan as well, which wasn't really thought about being part of Central Asia back in the fold as close as possible. So anything that gave those countries an alternative was seen as negative, you know, could have been an association with china, you know them joining, you know, kind of an association with latin America or africa or something else like that. But of course NATO has all of those larger connotations of it being in the Cold War opposing entity. And Putin has always seen NATO as being the direct correlation of the Warsaw pact, which is one of the words just something dominated completely by the United States. Now that of course is why getting back to trump again trump was always going you know to the Europeans, if this is really supposed to be collective security in a mutual defense pact, Why are you guys not paying? You know, why does the U. S. States pay for everything. But you know, NATO was actually conceived as collective defense, you know mutual security and it was set up by you know the United States along with the U. K. And France and you know Germany and Turkey and you know other countries and we see that now with the entry of Finland and Sweden they didn't have to join NATO, they didn't want to join NATO for a long time, they wanted to partner with it just like Israel and other countries partner with NATO but once they thought that their security was really at risk, they wanted to be part of it. And so you know kind of your now really seeing you know that NATO is something other than just being um you know a creature or an instrument of the United States. But that's how Putin always saw it. So you know what this debate about NATO is all about Russia being provoked is wanting to kind of return to an old superpower bipolar relationship where everything is negotiated with the United States, it's to try to deny that Ukraine or belarus, well belarus has been absorbed by this point, you know by Russia or Moldova Kazakhstan or any of the other countries have any kind of agency or even Poland or Hungary or you know kind of France and Britain for years and years and years. Senior people like Putin and people around the Kremlin have demanded a return to the kind of what they call the concert of europe or the concept of Vienna where the big guys, which now means the United States and Russia just sit down and thrash everything out. And so, I mean, Putin by saying, look, it was provoked, the United States, it's NATO, it's a proxy war or it's it's this or it's that or this is going to be a nuclear confrontations like the Cuban missile crisis. The Euro missile crisis is basically just saying, you know, I want to go back to when the soviet union, the United States work things out. I want to go back to the whole, you know, period of the 19 eighties when Gorbachev and Reagan just kind of got together and figure things out or even better back to Yalta potsdam and Tehran. And the big, you know, meetings at the end of World War Two where we resolved the whole future security, we've had a war, we've had the Cold War now we've got another war, we've got a real war, Hot war, we've got a war in Ukraine, it should be the United States and Russia that sort this out. So this is where we see the United States waffling about as well, trying to figure out how to handle this because it has to be handled in a way that Ukraine has agency. Because if Ukraine doesn't have agency and nobody else has agency either, nobody else has any kind of decision making power and you know, we have an environment in which Putin thinks that there's only really three players, there's the United States and Russia and china and maybe occasionally might be India and perhaps brazil or some of the South Africa or some other country that maybe the bricks at some point, but you know, ultimately it's like the oldest big powers resolve everything. And so this war is also about Russia's right, Putin's right, you know, to determine things, you know, Strongman, a strongman, big country, too big country and you know, determine, you know, where things happen </s><s>[INST] next, That's why [/INST] he's talking about things being provoked, it's being the United States fault, </s><s>[INST] aren't there parts of the United States establishment that likes that kind of three party view of the world, [/INST] there's always gonna be people who like that part, that that approach of course there is, but then they don't necessarily dominate, that's the kind of thing that people kind of think about, I mean, you know, Putin can, you know, read, you know, all the various articles and here the kind of pronouncements of people, but you know, this gets back to, you know, the way that the United States operates, you know, Putin saw that, you know, trump, wanted to have a you know, top down, you know, vertical of power and other presidents have wanted to have that, but the United States is a pretty messy place and we have all kinds of different viewpoints now, of course, we know that in Russia everything, even criticism the Kremlin is usually fairly orchestrated usually to kind of flush out, you know what people think about things when we had these hardliners saying, you know, we needed more destruction of Ukraine, not less and that, you know, the army wasn't doing enough, it was in many respects, you know, kind of encouraged by the Kremlin and to see how people react to that, you know, to kind of actually create a constituency for, you know, being more ruthless than you had before because, you know, they wanted to clamp down in the United States, I mean, I can say whatever I want, it doesn't mean that I'm speaking on behalf of the White House and you know, even if I have been an advisor to this President that President and the other doesn't mean I'm you know, basically speaking on behalf of the U. S. Government, but there's kind of always an assumption from the Russians that, you know, when people, you know, say this and people do advocate one thing over another that they're, you know, it's operating, there's a lot of mirror imaging thinking that, you know, we're operating in the same kind of way. So yes, there are of course constituencies who think like that would love it to be back to that and there are many people out there with their own peace plans, all kinds of people out there to push this. </s><s>[INST] There does seem to be the engine of the military industrial complex seems to give some fuel to the hawks and they seem to create momentum in government. [/INST] Yeah, but other people do too. I mean there's always you know, kind of checks again, </s><s>[INST] you believe in the tension of ideas [/INST] because I think there's a lot of tension. I mean I've seen it, I've seen it inside of the government now, you know, and people can push back and that's why I speak out and I try to lay it out so that everybody can, you know, kind of figure out for themselves. I said the same to you as I say to everybody, this is how I see the situation and you know, this is you know, how we can analyze it here now look, do I think that we've handled you know, the whole Russia accounts, you know, fears. Well no we haven't. I mean we've we've we've taken our eyes off the ball many times. We fail to understand the way that people like Putin think, you know, you talked earlier about, you know, we need to have empathy for all the people who like trump like biden and somehow they think we've got to have strategic empathy about Putin as well. We've got to understand how the guy thinks and why he thinks like he does. You know, he he has got his own context and his own frame and his own rationale and he is rational, he is a rational actor in his own context. We've got to understand that we've got to understand that he would take offense at something and he would take action over something. It doesn't mean to say that, you know, we are necessarily to blame by taking actions, but we are to blame when we don't understand the consequences of things that we do and act accordingly or you know, take preventative action or recognize that something might happen as a result of something </s><s>[INST] you've been in the room with Putin. Um let me ask you for some advice and it's also just a good philosophical question for you or for me, if I have a conversation with Vladimir Putin right now, can you advise on what questions, topics, ideas to talk through to him as a leader, to him as a human? What would you like to understand about his mind? About his thinking? [/INST] Yeah, I remember what I said before. The Putin always tries to you know, reverse things. He wants to hear the questions that people have because remember he himself at different points has been a recruiter, which is, you know, the way that you're operating now as well, right? You're asking an awful lot of questions. Your questions also betray, you know, often at times where you're thinking about things, you know, the kind of context, you know, kind of any kind of dialogue like this reveals a lot about the you know, the other person and I've actually often, you know noticed in these settings that Putin likes to have a lot of give and take. So I think he would actually enjoy having a conversation, you know, with you. But again, he would always be trying to influence you inform and influence that's kind of, you know, part of the way that he always operates. So what you would have to, you know, be trying to think about. So what is it you would want to elicit information from him? You you're trying to understand the guy's worldview and what we're trying to also understand is if there's any room there where he might compromise on something, you know, So if your goal was to go in there, you know, to talk about Ukraine at this particular moment. I mean, one of the problems that I've often seen in the sort of the meetings we've had with Putin just ends up in sort of mutual recrimination, you know, kind of know what about what you've done or? No, you've done that about, you know, and there's always this what about ISM I mean, often say, well, you're saying that I've done this, but you've done that the United States invaded Iraq. What's the difference between, you know what I'm doing and all of the things that you've been doing here. I mean, what you would have to try to do is kind of elicit information about why or what he is thinking about this particular moment in time and why he thinks it. </s><s>[INST] Yeah. The what about ISm is a is a failure case. I think that shows from all the interviews. I've seen that with him that just shows that he doesn't trust the person on the other side. [/INST] He doesn't </s><s>[INST] right. But I I I'm not cynical like people's they they seem to think he's some kind of KGB agent that doesn't trust anybody. I disagree. I think everybody's human. And from my perspective, I'm worried about what I've seen is I think whether it's covid whether it's uh other aspects that I'm not aware of leading up to the invasion, he seems to be less willing to have a charismatic back and forth dialogue. [/INST] Yeah, an open discussion. You know, actually, you know, I said, you asked me before about, you know, that issue of trust and he often says he only trusts himself and I said, you know, he's often distrustful of people, but he does trust some people for certain things where he knows it's within their competence. Yeah. So he has people he trusts to do things because you know, he he knows they'll do them and he knows that will do them well. Which is why, you know, he has his, you know, old buddies from, you know, ST Petersburg, he's known for a very long time and he knows that they want, you know, try to pull a fast one over him, but he also knows their strengths and their weaknesses and what they can be trusted to do. I mean he's learning that, you know, some of the people in the military, but he, you know, thought were competent or people and other things are not right that they and it intends to actually have a lot of loyalty to people as well. Or he also kind of thinks it's best to keep him inside the tent and outside and he moves them around. You know, he kind of okay, you know, that he gives them multiple chances to redeem themselves if they don't. It's not like he hasn't done in, I mean there is a lot of that in the system, but the people that he's worked with for a long time and he moves them around to something else perhaps where they can do less harm. Although, you know, we often see that he has quite a small cadre of people that he's reliant on and you know, they're not up to the task, which is kind of what's happening here. But he also in the past has been more straightforward, just like you were saying here more pragmatic. And I think, you know, if you were engaged with him in Russian where you're actually literally speaking the same language because there's so much lost in translation. I used to jump out of my skin listening to some of the phone calls because you know, the way that they kind of relayed, you know, with an interpreter </s><s>[INST] because, you [/INST] know, I'm listening to the Russian and the translation, you know in real time and I haven't been at the translators institute is really difficult. Look, an interpreter is a trend in the moment to do something, you know, the syncronys, the sink, the synchronized or the real time translation, translation is an art as well as a skill. If you're doing simultaneous translation, that's the word in english and it's syncronys in in in Russia, you're you're kind of focused in the moment on the fragments of the discussion trying to render it as accurately as you possibly can. And when you come out of that, you you can't relay the entire conversation and often, you know, what translators do is they, you know, they take this little shot and not like journalists do and afterwards, you know, they they they've just been caught up in the moment and they haven't got the big picture consecutive translation is different, you know, kind of you're trying to convey the whole mood of like big chunks of dialogue that have already been there, but you know, sometimes you might not get that right either, and it breaks up the flow of the discussion, </s><s>[INST] that's terrible [/INST] and and often it's you know, the kind of the person who translates, it's different, you know, some of our best translators a woman, but you know, hearing a woman's voice, you know, translating a guy who has a particular guy's way of speaking and a much a way of speaking and a crude way of speaking, you know be that Putin or I've seen that happen with Erdogan, the president of Turkey, you know it gets translated by a much more refined, you know female speaker, you've just lost the whole thing and you know many of the translators on the Russian side are not competent in english in the way that you would hope they are, they're not, it's not just that they're not native speakers, they're just not trained to the same high standards. They used to be in the past and you just got you lose the nuance that you lose the feel, you know, you almost need you know kind of the interpretive actor, you know doing you know the kind of the the the interpretation for that, you need to match it as much as you can in the way that you do voice overs in film. The best way to talk to Putin is one on 1 in his own language. I mean I have a really great friend here who is one of the best interpreters of Putin is often asked by the you know the media to interpret for him. He was just, he was at the institute that I was I mean I know him from that that kind of period and he is just excellent, just like pavel Plushenko was absolutely phenomenal interpreting garbage off now he didn't always interpreted accurately because garbage off made lots of grammatical gaffes and sometimes was you know, Gorbachev himself would joke that pollution, you know, spoke better for garbage off than garbage off could himself. But Putin is actually quite precise and careful in the way that he speaks because a lot of menace. Sometimes the things deliberately, other times there's lots of humor and he's telling a joke for a particular reason. A lot of it is, I mean he actually uses the richness of the Russian language and the crudity of language that can't be conveyed in </s><s>[INST] expressions, [/INST] expressions, body language. The way that he sits back in the chair and slouch. Is that the kind of the way that he makes fun of people and you know kind of uses irony, just some of it is just lost and it needs to be conveyed </s><s>[INST] the depth of humor and wit. I met quite a few like political leaders like that and to speak only Russian when I was traveling in Ukraine, I don't know how you translate that. I think it's almost the other person that reminds me like that a little bit is Obama. There's Obama had a wit and intelligence but like he would smile and just set something that add a lot to it like uh like that he's trolling you or he's being sarcastic or like I don't, it's me converting it towards, it's obvious that all english speakers if they listen to Obama, but if you have to translate to a different language, I think you're gonna lose a lot of [/INST] Yeah, I mean when I watched the, I mean I watched many of Putin speeches, you know, just in Russian, not looking at any of the, you know, the subtitles or anything and it's just watching the word that his body language is at the time when he's saying things, whether you smoke, he'll sneer, he'll laugh, he'll he'll ad lib, you know, kind of something that obviously kind of, you know, wasn't there on the prepared speech and it's really critical and you know, kind of a lot some people speak, you know, like trump, it's just, it's kind of just words Putin, the words are very important, trumpets, the atmosphere, it's the kind of the way you feel about things, it's the buzz you get, you know, it's revving people up, it's the kind of slogans and Putin is, you know, he's conveying a lot in what he's saying </s><s>[INST] that I think, I mean of course, I don't know much because I only speak Russian in english, but I have in english or Russian have not met almost anyone ever as interesting in conversation as Putin the I think he shines, not in speeches, but in interactions with others [/INST] Yeah, when you watch those interviews and things with him and I've been at many of these sessions, it's been hours of him parrying questions and it's like watching a boxer sparring, you know, the kind of training about yeah, come on, give me another one, you know, and it's kind of like, and he prides himself and and he's made mistakes often. But the breadth of the issues that he's often covered has been interested has been fascinating. And I used to just take, you know, kind of, really detailed notes about this because you learn a term, but it's also about his worldview. Again, I mean, he does live in a certain box, like, we all do, and, you know, again, his world experience is not as extensive as, you know, you would hope it would be, but that's why you have to really pay attention. That's where we've messed </s><s>[INST] up. [/INST] That's where we haven't really paid a lot of attention to what he's been saying. He's been telegraphing this grievances, dissatisfaction, this, I'm gonna do something for years. </s><s>[INST] And the thing is during war time, the combined with propaganda and the narratives, resentment and grievance that you dig in on those, like, maybe you start out not believing it, but you're sure it's all going to believe it eventually. Well, [/INST] you convince yourself over time. Yeah, look, the longer you're in a position like Putin 22 years now, 23 years could be out there for 36 years. You become more and more rigid. I mean, this is, again, you know, something that you see in history, you know, you look at, you know, people through history of moved from, kind of, being kind of left wing and, you know, in the perspective too hard, right? They kind of have a kind of a sort of an ossification or rigidity emerges in their views. I mean, again, I used to have these arguments with Professor Price about Lenin because he would talk about and he said, but he didn't change his mind from being 18. Have you not thought about that? I mean, it's like we're not formed fully formed and individuals at 18, you know, we don't know anything, you know, something, but not everything. I mean, obviously the younger context, you know, the kind of the way that you kind of grew up the place, you grew up, the things that happened to the traumas you have, I mean, all of these have an impact, but if you don't grow beyond all of that, and Putin has been stuck in place since 2000 when he became President, he's not out and about, you know, kind of being a man of the people, you know, he, you know, he's not doing the kind of things that I used to do. Yeah, he gets out there and he goes to Kazakhstan and you know, got Tajikistan and he goes to china and he does this nothing. And a covid he didn't go anywhere. I mean very few places. And so he got he's got stuck and that worries me a lot because you could see before that he had a bit more flexibility of thought and that's why nobody should be in place forever. You should always kind of like get out there and go out there and learn a new skill. You know kind of you need some sort of you know he needed to get out more and do something different. </s><s>[INST] You had an interesting point. You've made that both Land Mizlansky and uh Putin are thinking about They're just politicians. They're thinking about the 2024 election which is coming up for both of them. [/INST] Have said that in some of the other interviews. Yeah that's true. </s><s>[INST] That's so interesting. I mean [/INST] because their election is going to be pretty much at the same time </s><s>[INST] as the U. S. Election. [/INST] That will be before. I mean because at some time in that you know only part of with the presidential election. </s><s>[INST] Yeah. And also I don't know if you know about us elections but they actually last way longer than [/INST] we already </s><s>[INST] already starting. So there's going to be a significant overlap. [/INST] You think </s><s>[INST] that actually comes into play in their calculus? I [/INST] think it was one of the reasons why Putin invaded in february 2022 because it's gonna be two years and it would be over by March of 2022 he got two years to prepare for, you know the election and you got a big boost, you know, not only he got a boost from Crimea. I mean I didn't mention that before. I mean one of the reasons for invading Crimea and annexing or invading Ukraine the first time, annexing Crimea was look what happened to his ratings, they went from kind of declining and it was still pretty good, you know, by anybody's standards to just rocketing off into the stratosphere. I mean, I didn't really meet anybody in Russia who thought that Alex in Crimea was you know, kind of a bad thing. I mean even, you know, kind of people who were post putting on so many other things. Crimea was, you know, Cream Nash, they kept saying, you know, this is kind of, you know, we got it back, you know, should never have gone away, it was ours, you know, and but you know, this is more complex and he wasn't, I don't think at the time planning on fixing all of Ukraine when he went in this special multi operation, he was going to try to turn it into what Belarus has become part of a, you know, bring back the commonwealth of independent states of the Union, then a new union with Belarus and Ukraine and Russia over time, but certainly, you know, remove Ukraine as a major factor, independent factor on the world stage and you know, consolidate Crimea and maybe, you know, kind of incorporate Donetsk and Luhansk, you know, kind of that was that was also a possibility, but it wasn't it wasn't in his intention in any case to have something on this kind of scale, he wanted to get on with then preparing for what was gonna be, he would think the cakewalk the shoe in of the next presidential election, I mean, last time around he had to invent a bit of competition with his person who is reputed to be his god daughter, senior subject, you know, for a bit of, you know, kind of entertainment for people, you know, the next time around, you know, maybe he wasn't really planning on running, you know, against any other, you know, serious opposition, he was just gonna have the acclaim of, you know, the kind of the great leader like President xi in china, you know, Putin was basically, I think, you know, he also hoped that he would be able to devolve some authority away, you know, kind of, so he's more like the, you know, the supreme leader kind of figure the czar like figure the monarch and then, you know, other people get on with the chief executive, prime ministerial running the country and he could kind of like step back and just enjoy this. You know, maybe there was gonna be again, a new union of Belarus Russia and um in Ukraine and some, you know, fashion and he would preside over that. So </s><s>[INST] speaking of opposition, you've criticized the famed Putin critic alexei Navalny, what's the nature of your criticism? [/INST] Well, it hasn't really been a kind of a criticism in the way that, you know, people have implied, but more just reminding people that Navalny isn't some stooge of the west as other people have, you know, kind of depicted him in the in the Russian firm, but, you know, saying that this is kind of, you know, his pro Western, he's he's a Russian nationalist and a Russian patriot, you know, in the past, he's articulated, you know, things are not so dissimilar from some of the people around Putin, and it's more just reminding people that, you know, just because you kind of see somebody, you know, is kind of in an opposition figure or somebody who might be more palatable from your perspective, looking from the West, they're not always going to be, you know, what you think they are Aleksei Navalny is a Russian, and, you know, in a particular Russian context is different from Putin, but he wouldn't necessarily, you know, kind of run, you know, the Russian system in ways that we would like. So that's kind of it's kind of a criticism, it's more of a critique of the way that we look at things, you know, I think it's a mistake to always, you know, so this is pro Western or this is a, you know, liberal. I mean, what the heck does that mean? Pro Western? I mean, he's a Russian is a Russian nationalist and the Russian patriot, and he's often, you know, been, you know, quite critical about immigration. Um, he's had some negative views about, you know, at one point, He said, don't feed the caucuses, you know, kind of played upon some of the, you know, the racial and ethnic tensions inside of, you know, Russia itself as well. Now he is a pluralist and, and he's, kind of, and he wants to have, you know, different, uh, set of political actors there, but he also isn't promoting revolution. He's not Lennon, he's not want to bring down the state, he wants to kind of, you know, change the people who are in charge. That's what he's being basically focused on. And, you know, he might have and have things to do things that, you know, we elsewhere might not like. </s><s>[INST] And I guess the bigger picture there is, it's not trivial to know that if you place another human empower, uh, to replace the current human empower, that things are going to be better. There could be a lot worse because there's a momentum to a system, a system is bigger than just this leader. Even when that leader has a huge amount of power, [/INST] that's absolutely right. And, you know, he grew up in that, you know, same system now, he's younger than Putin. So he's got a different generational perspective and he's not wedded to the soviet union or, you know, kind of, some concept of the Russian empire doesn't seem to spend a lot of time, I don't know what he's doing, you know, in jail, but he's probably not sitting around, you know, reading and, you know, the kind of the great kind of tracks of Russian history could be actually, but I mean, I think, you know, Navalny has a different world view and a different perspective, just like Medvedev was different, you know, in his time in the presidency and made some, you know, changes and some innovations there, but don't think that they're going to be radically different because Gorbachev, I mean, he was so different from Andropov and Chernenko, no, this is the person, but he was also constrained by the system and he wanted to have changed, but he wanted evolutionary change, he didn't know how to do it, but he didn't want to bring the whole system down, look at crush off when he came in, you know, after that whole period of, you know, everybody trying to figure out what to do after Stalin had died, and there was all this kind of back and forth and eventually Christoph emerges and, you know, he tries to make changes to the system, but he's also a creature of very specific context. He's grown up in the same system and, you know, kind of brings all kinds of elements of chaos there into the whole thing and, you know, gets into a standoff the United States, that we know, as the Cuban missile crisis and eventually, you know, gets removed, you know, we're looking at what's happening in the United Kingdom right now, they've just turned through three Prime Ministers and actually five prime ministers in, you know, kind of as many years, but all of those Prime ministers have come out of the context of the Conservative Party and the whole, you know, kind of just shades of, you know, the same thing, they've all come out of the same academic and, you know, kind of privileged backgrounds, even richie Cenac, the new Prime Minister is the first, you know, indian or anglo indian Prime Minister and british history. It was a kind of phenomenal, you know, kind of child of indian immigrants, but also a person of great privilege from the same academic and party background as the others, you know, so there are always differences with those human beings, but those contexts matter a lot. </s><s>[INST] What is the probability that Russia attacks Ukraine with a tactical nuclear weapon? [/INST] Well, Putin has definitely been thinking about it, right? I mean, he's the kind of person, if he's got an instrument, he wants to figure out how to use it. You know, we look at Polonium, we look at, you know, we look at all kinds of things, you know, that he's also presided over in Syria, he has put in charge of the war in Ukraine now General, so american is known as General Armageddon, you know, the kind of person who, you know, pretty much facilitated the use of chemical weapons in Syria, you know, for example, so, you know, don't think that Putin hasn't thought about how ruthless he can possibly be. The question is really the calculation, it says his estimation of the probability that will get the desired effect. We keep talking about this idea of escalate to deescalate, that's not what the Russians, you know, how they call it, but it's the whole idea that you do something really outrageous to get everybody else to back off. Now, when you talked about the precedent that the United States set of detonating the nuclear weapons in Hiroshima Nagasaki, what, you know, he obviously meant, the President of using nuclear weapons of course, which of course, we would then say, well, we showed then how the impermissible itty of ever doing that again. But what he's talking about is the President of escalating to such an extent that you stopped the war, because he reads that saying, well, you know, the, I dropped the bombs on Hiroshima Nagasaki, the war was brought to a quick conclusion. Of course, there's a huge debate in America about whether it was necessary to do that. Whether the war was ending anywhere did that really, you know, kind of change the minds of the Japanese high command and they're all kind of books and being written about that. And of course, you know, the revulsion that people felt in the work of that was just, you know, just the shock of, of what actually happened, and we've spent, you know, 70 years, you know, basically coming to terms of the fact that we did something like that, you know, the firebombing, you know, we've we've also looked at all the bombing, you know, in Vietnam and everywhere and you know, the all these massive bombing campaigns and realizing that actually often had the opposite effect on Nagasaki might have contributed. And there's a lot of scholarship suggesting it did to the end of the war, but all of the big bombing campaigns, the destruction actually prolonged was because they made people fight back as we're kind of seeing in the case of Ukraine. So Putin has to calculate the probability that if he uses some tactical nuclear weapon that it will get the desired effect, which is get us to capitulate and Ukraine to capitulate us to capitulate in the United States and Europeans not supporting Ukraine anymore, pushing towards the negotiating table negotiating Ukraine away and Ukraine saying, okay, we give up like happened in Hiroshima and Nagasaki in Japan. So it's it's his calculation, you know, as much as anything else, which is really important. So we have to show him that he won't get that </s><s>[INST] out of it. It's kind [/INST] of less our probability and, you know, kind of the odds of it, it's just how he calculates that probability, getting what he wants. </s><s>[INST] I mean, I guess that's how the game of poker works. It's your probability and your estimate of their probability and your estimate of their estimate of your probability. And I think he has two tools, right? So one is actually actually use of nuclear weapons. And then the threat of the [/INST] is very effective. </s><s>[INST] And the more real you make the That's right. So it's like the more you approach the actual use get very close to use [/INST] already using Chernobyl zap or Asia and then usual cranes the other nuclear reactor. So he's using civilian nuclear actors as a dirty bomb. So, you know, it's ironic that he has said Shoigu, his defense minister calling people are going to use a dirty bomb. They're already doing it. I mean, what what is, you know, kind of more destructive and stirring up all the radioactive dust and Chernobyl as you send your tubes through, you know, for example, are shelling, you know, the Chernobyl plant and the sarcophagus and putting at risk and operation you've got the International Atomic Energy Agency running out there in utter panic and you know, kind of also trying to intervene in the conflict. So you're putting, you know, civilian nuclear reactors at risk. I mean, that also has a great added effect of cutting off Ukraine's power supply because separation particularly was the third of Ukraine's power generation or some, you know, really high percentage. I have to go back and you know, take a look at that, but that's a twofer, you know, it's kind of a double effect there of undermining uh power generation also frightening Germans and others who have already been very worried about nuclear power and, you know, increasing leverage on the energy front, but also scaring people uh from the perspective of the use of nuclear weapon, Those reactors also become a nuclear weapon tactically deployed. And as you said that the discussion of using a nuclear weapon and engendering all those fears and he's already got an effect. Everyone's running around talking about the Cuban missile crisis and secret diplomacy and how we negotiated where Ukraine in return for Putin not blowing up a nuclear weapon. So he's got a lot of people already talking about that. </s><s>[INST] So sorry for the difficult and uh dark question. It could be for you directly or more like uh do you think we have a plan for this? What happens if he does drop a nuclear? What happened? Do you have a sense that the United States has a good plan? [/INST] I know we're talking about it. I think we probably have several plans because it depends on what, where, when, how </s><s>[INST] but that don't and also don't these things happen very quickly? [/INST] Well, there's also signaling and sign and signs of movement there. I mean, I want to be very, you know, kind of careful about this. But the thing is it's also very important that we do this with other nuclear powers. So the other thing that's different from how it might have been in the past. And particularly different from the Cuban missile crisis and the missile crisis. We're not the only nuclear players china has a major nuclear arsenal now, um less on the strategic side, but building it up, but very much on the intermediate range and tactical kim jong un is firing off weapons left, right and center at the moment in North Korea, we've got other rogue states, Putin's behaving like a rogue state just to be very clear. And this is what we've got with kim jong un in North Korea. We've also got India and Pakistan and we've got other states were not supposed to talk about that. We now have nuclear capacities and others that would like to have nuclear capacity. And the whole question here is about also proliferation. Getting back to that time when Ukraine had nuclear weapons at least they're on its territory and sort of belarus and Kazakhstan, you've got to wonder was it wise for them to give it up? We were worried about, you know, kind of loose nukes nuclear weapons, you know, kind of getting out of hand proliferation at the time. We wanted fewer nuclear powers. Russia wanted that to. Now we're going to have more, we've got more. And what Putin is saying is, well, that was stupid of Ukraine to give up the nuclear weapons. In fact, my colleagues and I back in our reporting back in the USSR kind of suggests they shouldn't give them up. And that's why we had the Budapest Memorandum, that's why the United States, the United Kingdom in particular have you know, basically some responsibility and obligation going back to 1994 when they promised Ukraine that gave up the nuclear weapons, that territorial integrity and sovereignty would remain intact. Some obligation to actually do something to step up. If we step back from that. This is the thing that people are not talking about. You know, what about nuclear proliferation? If you're South Korea or Japan, you know, you're any other country that's kind of worrying about your neighbors. Um and you know, what might happen to you, just like India and Pakistan are both like, you know, we've got to kind of keep our strategic nuclear balance here. Everything is up for question. Saudis will want a nuclear weapon. The Turks already want one that talked about one for years. You know, why should the Iranians be the only one with an Islamic nuclear weapon? You know, and if if we know that, you know, Iran has break up capacity now, the Saudis and all the other, you know, states that are in opposition to Iran will also want to have some nuclear capacity in the United States before, wanted to maintain everything under the nuclear umbrella. You know, one of the reasons why Sweden and Finland are joining NATO is because of suddenly all of these nuclear threats. Sweden was actually the last country on the planet to want to have nuclear weapons. They were actually pushing for a ban on nuclear weapons. The United Nations. Now that Putin is doing the nuclear saber rattling. You know, they're talking about joining and on the verge of joining a nuclear alliance, see what, what's happening here. So we have to make it more and more difficult for Putin to even contemplate that, that's why people are saying this is reckless, this is irresponsible. Putin is actually making the world less safe for himself down the line either. But he's thinking short term here, he's thinking, what can I do? What do I actually have? You can also destroy lots of infrastructure as he's doing. You can use subversion, you know, we're worried about all of the undersea cables, all these weird things happening, you know, off Orkney or in the mediterranean or you know, all these other things that are happening, not stream to pipelines and other infrastructure, there's all kinds of other things that you can do as well here. It's not just, you know, again, there's a civilian nuclear threat of blowing up, you know, one of the reactors. Now, it's gonna be sure about where the wind turns and the wind blows and there's all kinds of things to factor in here, but Putin is definitely sitting around calculating with other people, what can I do to turn this around. I mean, he still thinks that he can win this or in other words, he can or he can end it in on his terms Crimea Donetsk, Luhansk Hirshson and you know, capitulation recognized as being part of Russia. Oh, he can freeze it and then, you know, kind of figure out where it goes from there, what other pressure he can put on. I mean, I'm sure he's confident he can get rid of Zielinski and he can prevail over us. I mean, look, I'm in the UK is going through prime ministers, you know, faster than I'm changing my socks, you know, So it's like, you know, he can he can, you know, prevail on the, you know, basically he can he can have an impact on the political scene in europe and elsewhere. I mean, again, everyone's talking about winter coming and Putin's thinking, yeah, great. I've destroyed the infrastructure of </s><s>[INST] the winter. [/INST] Well, yeah, but I mean, look, the other thing is that we have to start preparing, I mean, we have to start thinking about this, we've got a wartime economy situation, That's where we are. We've got the home front to think about as well. Putin has declared war on us. He did that on September 30 and he's done it at other points as well. We've just not paid attention, but he pretty much pretty explicit in September 30, I mean go back and watch that speech and you know, he is gambling that, you know, people will go back, you know to basically taking Russian gas and oil, but it's not gonna be that simple as well. And do people and then, you know, the question has to be, do we really kind of think he's gonna play fair after that when he's kind of also shown that he can leverage that </s><s>[INST] it's such a complicated world [/INST] is complicated. It's very </s><s>[INST] competent. It's never I mean, this it feels like things are heating up, like and china is very quiet right now [/INST] because they're watching what happens. I mean, for President xi, he's trying to consolidate his power even further after the party congress, but he doesn't want to look like he made a mistake by backing Putin. I mean, he thought Putin was also going to be in our Ukraine would probably be open for massive chinese investment. China was the largest investor in Ukraine before the war. Largest single investor in the EU is bigger. Of course. How </s><s>[INST] do you hope the war ends in Ukraine? [/INST] Well, I mean, I do hope and you know, with a ceasefire negotiated solution, but it has to be with Russia compromising on something and that's not where we are right now. </s><s>[INST] Do you think both sides might be willing to compromise [/INST] most wars always end in that way? I mean, nobody is ever happy, </s><s>[INST] but they don't seem to either side, like legitimately doesn't want to compromise right [/INST] now? Because the thing is that for Ukraine right now, anything is a compromise at his expense. Right, vast devastation, unbelievable casualty rates biggest refugee crisis since World War Two, Russia's just said, sorry, this is our territory is not just Crimea, I think there could have been a negotiation over there, but you know, Donetsk and Luhansk, we've got all kinds of formulas, we've had all the way through history of, you know, putting things under a kind of guardianship Receivership of territory, the United Nations, all kinds of different ways of formulating that we could have easily been creative. But Russia is basically saying, sorry, we've taken this and any other negotiations, just you recognizing this for us not doing more destruction, that is not the basis for negotiation. And, you know, having, you know, kind of people come and just sort of laying those terms down is not a starting position. I think Russia is also, you know, in a dilemma of its own making now, because Putin has made it very difficult to compromise just by everything that he said. Now, if Ukraine, they've already won a great moral political and military victory, it's just hard to see it right at the particular moment. They've done what the Finns did in the winter war, which the Finns were devastated by the winter war as well, but they pushed them back. Now, the Finns lost a lot of territory, those cara leah and, you know, huge swathes of territory, but they've got to be Finland and now they're, you know, johnny NATO. But they've been part of the eu the question is how to get Ukraine to be Ukraine in a success. But you know, is and that's the challenge again, they've already won psychologically, politically militarily, because Putin doesn't succeeded in what he wanted to do, but he has succeeded in completely and utterly devastating them. And this is the kind of the old muscovite, old Russian imperial old servant mentality, you know, going all the way back to when the muscovites with a bagman for the, you know, the hold the for the Mongols, it was destruction. You know, you don't play with us will destroy you. People talk about it as mafia, but it's old. You know, all you have to go down and see Tarkovsky andre rieu. I mean, I remember, you know, seeing that film when I was first as a student in Moscow and just being whoa, this is so brutal. I mean, this is just unremittingly brutal. Because the whole point is that you show people who's the boss, the destruction is the point of things as well, because, you know, you are emphasizing your domination and that's what Putin is doing right now is saying, okay, you want to go in a different direction, so be it. But I'm gonna make you suffer. Remember when Khordokovsky got out of the penal colony, when Putin let him out eventually, he said he's suffered enough, But he suffered for 10, 11 years, I don't think Putin feels that Ukraine has suffered enough at this point, we have suffered. </s><s>[INST] There's a part of this invasion. That's punishment for something. [/INST] It's medieval, I mean, look, we're all capable of the same things, right? There was all that destruction and that's what assad was like in Syria, like his father, you destroy because you teach him a lesson. And look, Britain did that in the colonial era. I mean, all the history of british colonialism is exactly the same. I mean, all the mau mau, you know, in kenya, you know, up until recent times, brutality teaching people, you know, you're teaching them a lesson. You have to suffer the US today. I mean, we did it with the native americans, you know, we did it all over the place, you know, as well. This is kind of what big, you know, States do at different points in history. It's just that, you know, Russia has not moved on from that and we've learned some lessons later. I hope, you know, we're fully internalized them of things that we've done, you know, kind of the past. The United States ideally are trying to do better and most of europe is trying to do better as well. Think about France and Algeria, you know, again, you know, we can see this in many different settings, but I think, you know, for Putin right now, he hasn't taught all of us sufficient lesson. </s><s>[INST] I just, I talked to hundreds of people in Ukraine and the tough thing. They're inspiring thing is that there's a unity. The tough thing is a lot of them speak intensely of hate towards not just Russia, but Russians, Russians, [/INST] that's how Europeans felt about Germany and Germans at the end of World War Two. </s><s>[INST] And uh generational hate, like, well, I don't think that hate is gonna pass [/INST] while it might it might well take a generation. I mean, I weren't when I was a kid in the seventies, I went on exchanges to Germany And that was like, you know, 30 years, more than 30 years after the end of the war my grandfather had fought in World War I, wouldn't speak to my parents when they sent me on a um we haven't fought in World War Two, we fought World War One, he hated the Germans. And he and he did not want me going, you know, to Germany as an exchange student, he refused to meet, you know, kind of the german kid who, you know, came to stay at my house, you know, for example, I mean, it takes a long time to it takes a long time to get over that, But but you do, I mean, and we have we have in europe, and that was the whole point of, you know, all that kind of exercise of european unity after World War Two. Now, the big challenges, What do we do with Russia? There's a lot of people are talking about, we can't have european security without Russia, The people saying we can't have a europe, you know, kind of with Russia, you know, so how do we deal with this? We we've gotta basically, it's going to be like Japan and Germany after World War Two after this, just the level of the atrocities that have been carried out, as you said, the level of hatred, but we found a way of doing it Now, it's a lot of it will require a change on the part of Russia as well and Russians and really thinking about this, I mean Gorbachev before tried to deal in the late 1980s with the black spots in with glasnost with openness and talking about Russian history, just kind of never sort of withered on the vine as time went on, </s><s>[INST] what gives you hope about the future? [/INST] My hope comes into the fact that we've done things before, that we've got ourselves out of tough times and we've overcome stuff and in people because I meet amazing people, you just talked about hundreds of people that you've met with in Ukraine and you know, people all think differently contexts and circumstances change and people can evolve, some people get stuck, Putin's got stuck, but people can evolve and you know, I do think that if we all pull together and we've seen this in so many contexts, we can find solutions to things just like we get back again to our discussion about scientists and just the kind of amazing breakthroughs of, you know what we did on covid or done on you know kind of other diseases and things. And look there there is some similarities, there's a pathology around war and conflict. Years ago in the 1990s I worked on you know a lot of projects that were funded by the Carnegie Corporation of the United States under the presidency of David Hamburg was a scientist. And actually did see a lot of parallels between the sort of like the pathology of disease and you know kind of the pestilence you know conflict kind of idea and of course these you know parallels have to be very careful because you know they're not neat but there was kind of like an idea and then how do you sort of treat this? How do you deal with this? And we did come up with all kinds of of ideas and you know things that are still out there. We've created institutions that have helped to keep the peace. We just have neglected them, allowed them to degrade just like the United Nations and you know we've we've created problems inside them like the veto power of the permanent powers on the U. N. Security Council but we can change that. You're just gonna have a will and I do think out there there are sufficient people with a will and we've just got to get people mobilized I mean I'm always amazed by how people can mobilize themselves around a crisis. Remember Winston Churchill, I don't quote all the time because I can never remember half his quotes but I do remember the one about never let a good crisis go to waste. And I always think that that you know, yeah that we should we shouldn't let this crisis go to </s><s>[INST] waste [/INST] and something else can come out of this. Just like in Ukraine were worried before about corruption in Ukraine, the influence of the oligarchs, we've gotta run oligarchs here in the US we need to, you know, deal with as well. But this is a chance to do it differently. Yeah, it really is a chance to do things differently and </s><s>[INST] a part of that is young people I have to ask you and [/INST] These young people, I mean I'm feeling a bit on the older side now but I still feel I got a bit of you know, kind of youth within me at 57, I'm not that old but I'm not that young but we have to work together with younger and older people </s><s>[INST] together [/INST] in coalitions of, you know, across generations you </s><s>[INST] remind me of of kids who just graduated college and say and I I feel old yeah, no [/INST] I don't actually feel old but it is a number edge and you know when you know, you kind of think about when I </s><s>[INST] was that you don't like math. [/INST] Yeah, like things like that. Yeah. But I find it interesting, you know when I was, I remember when I was a little kid, I kept thinking about the year 2000 and I thought, Oh my God, I'll be dead, I'll be 35, years ago. </s><s>[INST] You've overcome a lot of struggle in your life based on different reasons. As you write about uh, class being one of them. You're funny sounding accent being another or just representation of class. Um, but in general, through all of that, to be at the White House, to be one of the most powerful voices in the world, what advice would you give from, grounded in your life story to somebody who's young, somebody who's in high school and college, thinking of how they can have a big positive impact on the world. [/INST] We all have a voice, right? We all have agency. We all actually have the ability to do something and you can, you know, start small in your local community or, you know, even in your own classroom, just helping you know, somebody else out or speaking up and advocating on behalf of things. You know, when I was about 11 years old, I got involved with the kids on save the whales. You know, we had all this, you know, kind of, we were hardly Greta Thunberg, but we, you know, we kind of got together in a kind of network writing to people and, you know, trying to raise money to, you know, help save the whales. Now, actually, the whales of the world doing somewhat better. I can't say that that was because of me and my network, but you know, it was kind of a way of organizing and you know, kind of joining in a larger movement. Everybody can be part of something bigger. The the thing is it's all about working together with others and giving other people a chance as well. I think, you know, one thing is that our voices have more impact when they're amplified. They don't have to be the voices of discord or the voices of hate. You know, you've been, you know, trying to do this with your podcast, you know, kind of give people abroad voice, give them a kind of platform and, you know, get them to join in with other people. And, you know, one of the things that I've been trying to do is, you know, kind of go and talk to just as many people as I possibly can and say, look, you know, we can all do something here. We can all, you know, lend our voices to a cause that we care deeply about. We can be kind to each other. We can give other people a chance, We can kind of speak out when we see that, you know, something is wrong and we can try to, you know explain things to people and what I'm trying to do at the moment, just sort of explain, you know, what I've learned about things and you know, hope that that helps people make informed judgments of their own and that, you know, kind of maybe take things further and learn something more. It's like kind of building upon, you know, the knowledge, you know, that that I have, you know, to try to import and everybody can do that different ways. You can kind of reach back if you're 14, help somebody who's seven for 21 help somebody who's 14, you know, kind of, you know, the kind of my age now, I'm always trying to, you know, reach back and you know, work with younger people, listen to younger people, help them out, make connections for them, listen to what they have to say about something, try to incorporate that and, you know, things that I'm saying as well, the main point is that we've all got a voice, we've all got agency and it always works better when we work together with other people, </s><s>[INST] but sometimes you can feel pretty hopeless, you can feel, I mean, there's low points, you seem to have a kind of restless energy, a drive to you where there are low points in the beginning when um in your early days when you're trying to get the education where it may have not been clear to you that you could be at all successful. [/INST] Yeah, they're always there always were. I mean, there were lots of points where I was just despondent, but then, you know, I'd meet somebody Who would just suddenly turn things around. I was this look was out there looking for it, you know, sometimes, you know, you just, if you're open and receptive to, you know, kind of hearing something from someone else. I mean, you know, often times when I felt so despondent, you know, in such a black mood, I didn't think I'd be able to go on and then I'd have a chance conversation with somebody. I mean, I don't remember, you know, sitting on the bench was probably 11 or 12 just crying my eyes out, just really upset and an old lady just came and sat next to me, put her arm around me said, Oh it's all right, what's the matter? You know, it can't be that bad can it? And it was just this human embrace, it's like somebody, you know, just basically reaching out to me that snapped me out of it and I thought, you know, here's somebody just you know, she didn't know who I was, she just felt really bad that I was, you know, sitting, you know, crying and I mean, I can't even remember, it was about anymore, </s><s>[INST] you know, now [/INST] it just seems inconsequential at the time, I probably thought my life was at an end, just, you know, sometimes people making out contact with you in the street and saying something to, you can kind of pull you out of something and you know, it's kind of a I think you just have to open yourself up to the prospect that not everyone is bad, just like you were saying before that there's you know, good in everybody, even during, you know, that really difficult period of impeachment, and I was trying to listen very carefully to people and I thought we always we still have something in common here, we need to remember that, you know, kind of when people are kind of forgetting who they are or you know, the context and their operating, there's always something that can, you know, can pull you back again, there's always that kind of thread, </s><s>[INST] so I'm sure you were probably attacked by a lot of people and you were still able to keep that optimism that well, [/INST] I kept it into kind of perspective, like when I was a kid, I mean things like I mentioned before, I got bullied, you know, kind of again, and I try to win some why are they doing this? one of the most amazing things that happened, you know, really? Almost my my dad was a pretty incredible person, and he would always open my eyes to something, I was getting bullied really nastily by a girl at school, and my dad start asking me questions about her and one day my dad, we're gonna go for a walk and my time is very small, remember it's very depressed, really, you know deprived area, and we go to this housing estate, public housing place that's not too far away from where I live and it's really, you know, kind of one of the most rundown places and already run down place. My dad like knocks on the door and I said what we're doing, dad, he says we're going off to, you know, we're going to visit somebody, an old family friend and I think even, you know, a distant relative knock on the door, This old man answers the door and Alfie, my dad's name is ALF Alfie, you know, kind of fancy seeing, you haven't seen you come on in, have a cup of tea, what you're doing said, I'm just walking past my daughter, we're going for a trip that we're going for, going for a walk, and then suddenly I see that girl and she's in the kitchen and I'm thinking, oh my God, bloody hell, you know, british expression, what's this? And it turns out that dad had figured out who she was and he knew her grandfather and she was living with her grandfather and she'd been abandoned by her parents and she was living in, you know, pretty dire circumstances and she'd been getting raised by her grandfather and she was just miserable and the reason she was bullying me was to make herself feel better and after that she never bullied me again, I mean we didn't even talk because there was a connection made and suddenly she realized that her grandfather was the only person she had. I knew my dad and there was some they were friends or they were even family, some, you know, kind of relationship there. I mean, I was related to half of North of England. I had no idea how we were related. You know, everybody was some relatives, people have lived there for generations again, this very small area. And that turned things around. So, just remember you might have and that's kind of suddenly talk to me. There's always a reason why somebody's doing something. A lot of times they're really unhappy with themselves. Sometimes something else going on their lives. Sometimes they just don't know any better. And I shouldn't take it personally because I don't have a personal connection with half these people who are out there saying that they want this and that to happen to me. </s><s>[INST] Well, thank you for the kindness and empathy still carrying your heart. I can see it through all the you must have gone through in the in the recent couple of years. It's really inspiring to see that. And thank you for everything you've done for the work you've written for, the work you continue to write and to do this seems like a really, really difficult time for human civilization on a topic that you are a world expert in. So don't mess it up. [/INST] I know I know everybody have that. Let's just let's just keep it together, right? </s><s>[INST] Exactly. [/INST] Keep it together. </s><s>[INST] Your words have a lot of power. So it's it's a it's a really, really tricky time. So thank you so much, given how valuable your time is to sit down with me today. It was an honor. [/INST] It's a privilege and a pleasure to talk to you as well. Thank you. </s><s>[INST] Thanks for listening to this conversation with Fiona Hill. To support this podcast. Please check out our sponsors in the description. And now let me leave you some words from john Steinbeck. Power does not corrupt. Fear corrupts. Perhaps the fear of the loss of power. Thank you for listening. I hope to see you next time. [/INST] </s>

<s>[INST] Right. So I started to view that really as what I mean, I've worked with the robots always broken [/INST] stoles. What in software engineering you call a walking skeleton, which is maybe the wrong metaphor to use for Sophia or maybe the right one. I mean, what a walking skeleton is in software development is if you're building a complex system, how do you get started? Well, one way is to first build part one well, then build part two well, then build part three well, and so on. Another way is you make like a simple version of the whole system and put something in the place of every part the whole system will need so that you have a whole system that does something. And then you work on improving each part in the context of that whole integrated system. So that's what we did on a software level in Sophia. We made like a walking skeleton software system where, so there's something that sees, there's something that hears, there's something that moves, there's something that there's something that remembers, there's something that learns you put a simple version of each thing in there and you connect them all together so that the system will do its thing. So there's a lot of AI in there. There's not any AGI in there. I mean, there's computer vision to recognize people's faces, recognize when someone comes in the room and leaves, try to recognize whether two people are together or not. I mean, the dialogue system, it's a mix of like hand-coded rules with deep neural nets that come up with their own responses. And there's some attempt to have a narrative structure and sort of try to pull the conversation into something with the beginning, middle, and end, and this </s><s>[INST] sort of story arc. I mean, if you look at the Lobner Prize and the systems that beat the towing test currently, they're heavily rule-based because, like you had said, narrative structure, to create compelling conversations, neural networks cannot do that well, even with Google Mina. When you actually look at full-scale conversations, it's just not... [/INST] Yeah, this is a thing. So I've actually been running an experiment the last couple of weeks taking Sophia's chatbot and then Facebook's Transformer chatbot, which they opened the model. We've had them chatting to each other for a number of weeks on the server just... That's funny. We're generating training data of what Sophia says in a wide variety of conversations, but we can see, compared to Sophia's current chatbot, the Facebook deep neural chatbot comes up with a wider variety of fluent sounding sentences. On the other hand, it rambles like mad. The Sophia chatbot, it's a little more repetitive in the sentence structures it uses. On the other hand, it's able to keep like a conversation arc over a much longer period, right? So there... Now, you can probably surmount that using Reformer and using various other deep neural architectures to improve the way these Transformer models are trained, but in the end, neither one of them really understands what's going on. And I mean, that's the challenge I had with Sophia, is if I were doing a robotics project aimed at AGI, I would want to make like a robo-toddler that was just learning about what it was seeing, because then the language is grounded in the experience of the robot. But what Sophia needs to do to be Sophia is talk about sports or the weather or robotics or the conference she's talking at. She needs to be fluent talking about any damn thing in the world, and she doesn't have grounding for all those things. So there's this just like, I mean, Google Mina and Facebook's chatbot don't have grounding for what they're talking about either. So in a way, the need to speak fluently about things where there's no non-linguistic grounding pushes what you can do for Sophia in the short </s><s>[INST] term a bit away from... It pushes you towards IBM Watson situation where you basically have to heuristic and hardcore stuff and rule-based stuff. I have to ask you about this. Okay, so because in part, Sophia is an art creation, because it's beautiful. She's beautiful because she inspires through our human nature of anthropomorphized things. We immediately see an intelligent being there. Because David is a great sculptor. He is a scary sculptor. That's right. So in fact, if Sophia just had nothing inside her head, said nothing, [/INST] if she just sat there, we already prescribed some intelligence to us. There's a long selfie </s><s>[INST] line in front of her after every talk. That's right. So it captivated the imagination of many [/INST] people. I was going to say the world, but yeah, I mean, a lot of people. Billions of people, </s><s>[INST] which is amazing. It's amazing, right. Now, of course, many people have prescribed much greater prescribed, essentially AGI type of capabilities to Sophia when they see her. And of course, friendly French folk like Jan LeCun immediately see that of the people from the AI community and get really frustrated because... It's understandable. And then they criticize people like you who sit back and don't say anything about, like basically allow the imagination of the world, allow the world to continue being captivated. So what's your sense of that kind of annoyance [/INST] that the AI community has? I think there's several parts to my reaction there. First of all, if I weren't involved with Hanson-Rabax and didn't know David Hanson personally, I probably would have been very annoyed initially at Sophia as well. I mean, I can understand the reaction. I would have been like, wait, all these stupid people out there think this is an AGI, but it's not an AGI, but they're tricking people that this very cool robot is an AGI. And now those of us trying to raise funding to build AGI, people will think it's already there and already works. On the other hand, I think even if I weren't directly involved with it, once I dug a little deeper into David and the robot and the intentions behind it, I think I would have stopped being pissed off, whereas folks like Yann LeCun have remained pissed off after their initial </s>

<s>[INST] Peterson [/INST] anaconda, right, we're still great friends, great friends, we talk all the time, I love him to death. There's a long story there about like why and how we can cover in some, some other podcasts, perhaps sort of more, maybe have more business focused one, but there's one area where I think Kanda should be more community driven, like he should be pushing more to get more community contributors to conda and let let let the, not the kind of constantly fighting this battle, right? It's actually, it's really a developers exact, you said like help the developers and then they'll actually move in the right direction, </s><s>[INST] that was the problem. I have as many of the cool kids I know don't use Kanda and that to me is confusing, [/INST] it is confusing and it's really a matter of kinda have some challenges first of all, kind of still needs to be improved, there's lots of improvements made and that is that aspect of weight, who's doing this and the fact that then the pipe a really stepped up, like they were not solving the problem at all and now they kind of got to where they're solving it for the most part and then effectively you could get like kinda solved a problem that was there and it still does and it's still, you know, there's still great things that can do, but um and we still use it all the time at one site and with other clients but with uh but you can kind of do similar things with pip and doctor. Right, So especially the web development community, that part of it again is this is the, there's a lot of different kind of developers in the python ecosystem and there's still a lack of, of some clear understanding, I go to the python conference all the time and there's only a few people in the people who get it and then others who are just massively trumpeting the power of pit but just do not understand the </s><s>[INST] problem. So one of the obvious things to me from a mom from a non program of perspective is the across operating system usability, that's much more natural. So they use windows and just it seems much easier to uh to recommend Kanda there, but then you should also recommend it across the board so I'll definitely sort of [/INST] what I recommend now is a hybrid. I do, I mean I'm is it possible to use it, is it, is what I like build the environment with pip with conduct, build an environment with conda and then pip, install on top of that, that's fine, be careful about pip, installing open c V or tensorflow or because if somebody is allowed that it's going to be most surely done in a way that can't be updated that easily, </s><s>[INST] so install like the big packages, the infrastructure, Kanda and then the weirdos [/INST] that like the weird like </s><s>[INST] implementation for some head um, there's a cool library. I used that based on your location and time of day and date tells you the exact position of the sun relative to the earth and it's just like a simple library but it was very precise and was like, all right. But that was that was in this pit is [/INST] the thing they did really well is python developers who want to get their stuff published. They, you have to have a pit recipe. Right? Even if it's, you know, the challenges and there's a key thing that needs to be added a pip. Just simply add to pit the ability to defer to a system package manager like because it's, you know, recognize you're not going to solve all the dependency problem. So let's give up and allow the allow system packager to to work that way and icon is installed. It has pip. It would default to conduct to install this stuff but red hat rpm would default rpm to install. That's all more things like that's the, that's a key not difficult but somewhat were some work feature needs to be added. That's an example of something like I've known we need to do it. I mean it's where I wish I had more money, I wish I was more successful in the business side trying to get there but I wish my you know my family, friends and full community that I know was larger was larger and had more money because I know tons of things to do effectively with more resources but you know I have not yet been successful channel tons of it some you know, I'm happy with what we've done. We've created again at one site what we created to get any kind of started we created humanity is going to kind of started done it again with Kwan site. Super excited by that by the way it took for years to do it. </s><s>[INST] What is Quan site? What is its mission? We've talked a few times about different fascinating aspects of it but it's like big picture what [/INST] quantity is uh it's vicious to connect data to an open economy. So it's basically consulting the pilot ecosystem. It's a consulting company and what I've said when I started it is we're trying to create products, people and technology. So it's divided into two groups and a third one as well. The two groups are a consulting services company that just helps people do data science and data engineering and data management. Uh better and more efficient. Full staff science, full thing. We'll help you build a infrastructure. If he was in jupiter we need we do staff augmentation need more pro programmers help used as more effectively. Help use Gpus more effectively. Just basically a lot of people need help. So we do training as well to help people, you know, both immediate help and then get get learned from somebody. Uh, we've added a bunch of stuff to, we kind of separate some of these other things in another company called open teams that, that we currently started. One of things I loved what we did. Anaconda was created a community innovation team. So I want to replicate that. This time we did a lot of innovation and anaconda. I wanted to do innovation but also contribute to the projects that existed, create a place where maintainers so that sci fi and numpy and number and all these projects we already started can pay people to work on them and keep them going. So that's labs. Concert Labs is a separate organization. It's a nonprofit mission. The profits of Quan said help fund it. And in fact every project that we have at quan site, a portion of the money goes directly to coincide. Labs to help keep it funded. So we've gotten several mechanism, we keep one site labs funded. Currently I'm really excited about labs because it's been a mission for a long time. </s>

<s>[INST] the protocol for shooting at a thing? Was was was there a concern that it's a direct threat, not just surveillance but a thing that could be a threat [/INST] at least from my perspective like that never really crossed into my mind. I thought it was potentially a intelligence um you know, failure that we could be being watched and information gathered, but I didn't think that it was something that would Proactively engage me in a hostile manner. It wouldn't really make sense either to it would be shocking to like have one of these objects take out an F18 but there's no real tactical advantage other than fear. Perhaps </s><s>[INST] psychological [/INST] yeah </s><s>[INST] I've learned a lot about the psychological warfare in Ukraine. This is a big part of the war in terms of when you talk about siege warfare about warfare wars that last for many years, for many months and then perhaps could extend two years. But yes um it didn't seem it didn't fit your conception of a threatening [/INST] entity. So </s><s>[INST] looking back now from the all the pieces of data you've integrated, you've personally at it what what do you think it could be? [/INST] I don't know. I don't know what it could be. I think we've been able to categorize it successfully into a few buckets. We've been able to say that you know, this could be us technology that someone put in the wrong piece of sky or you know, perhaps was developed and tested an inappropriate spot by someone that wasn't being best practices. </s><s>[INST] Is there sorry to interrupt. Is there a sort of modularity to the way the military operates the way it's possible for one branch not to know about the tests of another. [/INST] Yeah I think it's perfectly reasonable to think that that could occur right. And so if we just make that assumption we can integrate that into our analysis here and just say okay but at the point we're at now, you know, we have to assume that that's not the case right with everything that's been going on in the statements have been made and the hearings, I think that if it was a a non communication issue, um we're in big trouble at this point. What </s><s>[INST] about it being an object from another nation? From china from Russia [/INST] or even one of our allies? Perhaps Right. Maybe that's you know, I don't think it's um controversial to say that our allies could be gathering information about us or anything of that nature, but that would be an extreme case. But I think it's just important to say right to not just say Russia or china and just call them the bad guys and assume that if they don't have it, no one can do it. Um, and so from my perspective, you know, anyone else, anyone else and it doesn't necessarily need to be a foreign power could be a non government entity perhaps, although I think that's very unlikely. But again, these are these are things you must consider if you kind of throw everything everything other than the U. S. Under under scrutiny. But you know, from what has been reported and the behaviors that have been seen, it would be, I would expect to see remnants of that technology elsewhere in the economy, there seems to be too many things that require advanced technology that would be beneficial commercially as well as another military applications for it to be completely locked away by one of our competitors Now, I could see us perhaps locking something away if we're already in the lead and having it to pull out as needed. But for someone that's perhaps in a power struggle and they're in second place, they might be more aggressive with the development of different types of technology willing to accept bigger risks. </s><s>[INST] Do you think it could be natural phenomena that we don't yet understand? [/INST] I think that there are a number of things that this is going to be right. I don't think there's one thing at the end of the day, but I certainly think that that is part of what some of this could be. I don't think it's what we were seeing on the east coast. Uh, and I don't think it is related to the Roosevelt incident or I'll even go out and say the Nimitz incident. But </s><s>[INST] what's the Roosevelt [/INST] incident? The Roosevelt incident typically referred to as a gimbal and or the go fast video. </s><s>[INST] And then the Nimitz is from uh, what the David favor has witnessed directly and spoken about who will talk about that as well. I just love to get your, your sort of interpretation of those incidents. But yeah, so in this particular case natural phenomena could be a part of the picture, but you're saying not the whole picture. [/INST] Yes, yes. And we can't discount it. </s><s>[INST] Oh, the other thing is what about the failure of pilot eyesight, like sort of some deep mixture of actual direct vision, human vision system failure and like psychology like um seeing something weird and then filling in the gaps [/INST] because </s><s>[INST] in order to make sense of the weird, [/INST] I've tried to expose myself to a scenarios like that that I don't naturally think are right, but I've explored them to see if they could have some truth. And one example is let's imagine a scenario where if we're seeing these objects every day off the east Coast, I can imagine a technology or an operation where you had some type of traditional propulsion system, operating drones in order to gather data like we had discussed and I could I could envision a clever enough adversary that could perhaps destroy or somehow remove these objects and replace them with new objects essentially when we're not looking right. And that accounts for the large airborne time. And so I I explore options like that and I try to see, you know, what what evidence and assumptions need to be made in order to prove or disprove that. And you know, you would need so much infrastructure, you know, you need some, you need so many assets and so I try to explore some of those policies and some of those concerns and as aviators were trained into many uh like actual physical like eyesight and kind of illusion training. So like at nighttime flying there's so many things that can happen flying with false horizons and so we received hours of training on that type of stuff. But this just falls outside the category from my perspective, </s>

<s>[INST] This is a beautiful picture. Are incredibly mysterious existence. So is that humbling to you, exciting the idea of multiverses. I don't even know how to even begin. [/INST] Well, you're exciting for me because what I do for a living is string theory. That's my day job. I get paid by the city of new york to work on string theory. And you see string theory is a multiverse theory. So people say, first of all, what is string theory? String theory simply says that all the particles we see in nature, the electron, the proton corks, what have you are nothing but vibrations on a musical string, on a tiny tiny little string. You know, J robert. Oppenheimer, the creator of the atomic bomb was so frustrated in the 19 fifties, with all these subatomic particles being created in our atom smashers. That he announced. He announced one day that the Nobel Prize in Physics should go to the physicist who does not discover a new particle that year. Well, today we think there's nothing but musical notes on these tiny little vibrating strings. So what is physics? Physics is the harmonies you can write on vibrating strings? What is Chemistry? Chemistry is the melodies you can play on these strings? What is the universe? The universe is a symphony of strings. And then what is the mind of God? That Albert Einstein so eloquently wrote about for the last 30 years of his life, the mind of God Would be cosmic music resonating through 11 dimensional hyperspace. </s><s>[INST] So beautifully put, what do you think is the mind of Einstein's God? Do you think there's a Why that we could untangled from this from this universe of strings? Why are we here? What is the meaning of it all? [/INST] Well, steven Weinberg, winner of the Nobel Prize once said that the more we learn about the universe, the more we learned that it's pointless. Well, I don't know, I don't profess to understand the great secrets of the universe. However, let me say two things about what the giants of physics have said about this question. Einstein believed in two types of God. One was the God of the bible. The personal God the God that answers prayers walks on water, performs miracles. Smite the Philistines, that's the personal god that he didn't believe in. He believed in the God of Spinoza, the God of order, simplicity. Harmony, Beauty. The universe could have been ugly. The universe could have been messy. Random, but it's gorgeous. You relies on a single sheet of paper, we can write down all the known laws of the universe. It's amazing. On one sheet of paper, Einstein's equation is one inch long. String theory is a lot longer and towards the standard Model. But you could put all these equations on one sheet of paper, it didn't have to be that way. It could have been messy. And so Einstein thought of himself as a young boy entering this huge library for the first time, being overwhelmed by the simplicity, elegance and beauty of this library. But all he could do was read the first page Of the 1st vol well, that library is the universe, with all sorts of mysterious magical things that we have yet to find. And then Galileo was asked about this Galileo said that the purpose of science, the purpose of science is to determine how the heavens go the purpose of religion is to determine how to go to heaven. So in other words sciences about natural law and religion is about ethics, how to be a good person, how to go to heaven. As long as we keep these two things apart, we're in great shape, the problem occurs when people from the natural sciences begin to pontificate about ethics and people from religion begin to pontificate about natural law. That's where we get into big trouble. </s><s>[INST] You think they're fundamentally distinct morality and ethics and our our idea of what is right and what is wrong. That's something that's outside the reach of string theory in physics, [/INST] That's right. If you talk to a squirrel about what is right and what is wrong, there's no reference frame for a squirrel and realize that aliens from outer space, if they ever come visit us, they'll try to talk to us like we talk to squirrels in the forest. But eventually we get bored talking to the squirrels because they don't talk back to us. Same thing with aliens from outer space and they come down to Earth. They'll be curious about us to a degree, but after a while they just get bored because we have nothing to offer them. So our sense of right and wrong, What does that mean? Compared to a squirrels sense of right and wrong. Now, we of course do have an ethics that keeps civilizations in line enriches our life and makes civilization possible. And I think that's a good thing, but it's not mandated by a law of physics. </s><s>[INST] So if aliens do alien species were to make contact, forgive me for staying on aliens for a bit longer. Do you think they're more likely to be friendly to befriend us or to destroy us? [/INST] Well, I think for the most part they will pretty much ignore us if you're deer in the forest, who do you fear the most? Do fear the hunter with his gigantic 16 gauge shotgun? Or do you fear the guy with the briefcase and glasses? Well, the guy with the briefcase could be a developer about to basically flatten the entire forest, destroying your livelihood. So instinctively you may be afraid of the hunter. But actually the problem with Deers in the forest is that they should fear developers because developers look at deer as simply getting in the way. I mean in war of the worlds by H. G. Wells, the aliens did not hate us. If you read the book, the aliens did not have evil intentions toward him. Homo sapiens No, we were in the way. So I think we have to realize that alien civilizations may view as quite differently than in science fiction novels. However, I personally believe and I cannot prove any of this. I personally believe that they're probably going to be peaceful because there's nothing that they want from our world. I mean, what are they going to take it? What are they going to take us for? Gold? No, gold is a useless metal. For the most part it's silver. I mean it's gold, golden color, but that only affects Homo sapiens, squirrels don't care about gold. And so gold is rather useless element. Rare earths may be platinum based elements. Rare earth for the electronics. Yeah, maybe. But other than that we have nothing to offer them. I mean think about it for a moment. People love Shakespeare and they love the arts and poetry. But outside of the earth they mean nothing, absolutely nothing. I mean when I write down an equation in string theory, I would hope that on the other side of the galaxy there's an alien writing down that very same equation in different notation. But that alien on the other side of the galaxy Shakespeare poetry Hemingway it would mean nothing to him or her or it </s>

<s>[INST] is there on this particular instructional, if you can convert it to words? Uh you talk about finishing submission, is there some interesting insights, the fine, beautiful or profound about finishing the rear naked choke or just finishing submissions for the back control. Is there something like, you know, you talk about the squeeze in the crash and all these kinds of principles? Is there something about control about the process of finishing that? Uh you find especially profound about this [/INST] position. Absolutely the opposite of one profound truth can be another profound truth. So like uh I do jesus say that no I don't, I actually was a guy on tumbler. Um but uh it was really really cool. There's like a like a tree in the background. But anyway uh so let's say like I'll use I'll use examples like first off um I I saw someone finishing a 50 50 here, look in the UFC one promo, it was like some chubby dude knew karate like inside here looking another dude and you go uh huh. Well I didn't know they were doing that back then at least and whether they were doing it all, how many times does someone do something and then that works and then we go okay cool versus hey maybe we should do it all the time. So anyway how long did where we all talk to the seat all the way we all do the seatbelt introduced to like a long time. Why works? In fact it works so well and it was so it was then the people who used it were so prolific that we went well solve that one. Good to go alright no more thinking and then you go imagine you were like the Merkle of Merkle flip all those positions that were showing in the in the DVD which is pretty much or whatever the heck it is. And the digital V. D. Um No not V. D. You don't want that digital digital video something but basically uh recognizing that doing it on the wrong side is at least as effective. Doesn't mean that the other side wasn't good. There could be something that's the literal borderline opposite of that and you go uh huh. Well that's something like imagine like I would say almost all of these things all the tactics and all the strategies. So I guess that was something that we came to like training in the gym like year ago maybe and then playing with since and it's just it's huge. I'm like always. So let me get this straight first if I can use my strong side seatbelt, my my right arm over the shoulder and all the time. Well that's that's really helpful because that's a lot better than I left, do both sides of my left. But if I had to bet my life on on being able to finish it, I would want my right arm over uh everything that's a tactic or a strategy evolved from an idea like capitalism is an idea, you know, anarchy is an idea and then it becomes, what does that all mean? What what are the consequences? What's the fallout of all this? Right. So what if we start with ju jitsu? The idea of the guard, right? And we go, well, I mean Wendy, why do use the guard? No other martial art really has developed the guard in the same way the jujitsu has. Well what is the guards? Guards and a defensive idea where you're kind of on your back to some extent or another and you're using your legs as a wall between you and the other person and the other guy represents danger and you're like, yeah, that's a great idea is it? I mean it clearly works at least to a certain extent. But what where do I want to put my legs when I want to get up? Not on the other dude, I'm trying to put them on things on the floor. If I want to generate a ton of power, what's the first thing I do with my feet? I anchor them to the floor. Drive for a punch. You name it, move away, jump dark, you name it. So does it mean that that's a terrible idea to be on your back? No, clearly it works and clearly it liberates has function. But what if the function that we're giving it and where and the how much, how much focus were assigning to it is disproportionate to its effectiveness? Maybe what if it's not a good idea? I'm not saying it's not a good idea, but what if it wasn't that's a foundational idea of judicial and then how much, because no one questions that foundation, how much innovation is built on top of the idea? Well, of course I want to be being on my back is an okay position. So now they're innovating, but they're innovating within a closed system that they don't, they think they're innovating in like in this open space of, oh my God, it could be anything when really it could be anything within this little set, but you don't realize that you're gonna set, you don't realize that you're in a box, there would be answers that would become so immediately apparent to you. If you were willing to look outside of that, but you'll literally never even look over to your left because you don't even realize the left exists. </s><s>[INST] Do you think there's a lot of places and you get so whether it's back control or generally guards and all the different positions where there's a lot of space, like a lot a lot to be discovered by questioning the basic assumptions. Maybe if you give examples of like back control, like is there something you've [/INST] discovered this? Like Merkel versus seatbelt? Was Merkel with seatbelt, seatbelt is right arm over the shoulder? Left arm under the arm on, I'm on the I'm on the same side as my choking arm. Merkel is just, I do the same thing. I don't even just my hands. I walked myself over to the left side, I'm on the opposite side. It's actually more powerful </s>

<s>[INST] you know what's interesting is you know MIT that's computer science but in general but let's just even say computer science curriculum how does the computer science curriculum change now you mentioned you mentioned programming like why would you be when I was coming up programming as a prestigious position why would you be dedicating crazy amounts of time to become an excellent programmer like the nature of programming is fundamentally changing [/INST] the nature of our entire education system </s><s>[INST] is completely turned on its head has anyone been able to like load that in and like think about because it's really turning [/INST] I mean some English professors some English teachers are beginning to really freak out now they give an essay assignment and they get back all this fantastic prose like this is the style of Hemingway and then they realize they have to completely rethink and even you know just like we stopped teaching writing scripts is that what you say in English? Yeah handwritten yeah yeah when when everybody started typing you know like so much of what </s><s>[INST] we teach our kids today yeah I mean that's everything is changing and it's changing very it's changing very quickly and so much of us understanding how to deal with the big problems of the world is through the education system and if the education system is being turned on its head then what what's next it feels like having these kinds of conversations is essential to try to figure it out and everything's happening so rapidly I don't think there's even you're speaking of safety what broad the AI safety define I don't think most universities have courses on AI safety it's like a philosophy seminar [/INST] it's a philosophy seminar and like I'm an educator myself so it pains me to see this say this but I feel our education right now is completely obsoleted by what's happening you know you put a kid into first grade and then envisioning and then they're going to come out of high school 12 years later and you've already pre-planned now what they're going to learn when you're not even sure if there's going to be any world left to come out to clearly you need to have a much more opportunistic education system that keeps adapting itself very rapidly as society re-adapts the skills that were really useful when the curriculum was written I mean how many of those skills are going to get you a job in 12 years I mean seriously </s><s>[INST] if we just linger on the GPT-4 system a little bit you kind of hinted at it especially talking about the importance of consciousness in the human mind with homosentience do you think GPT-4 is conscious? [/INST] I love this question so let's define consciousness first because in my experience like 90% of all arguments about consciousness boil down to the two people arguing having totally different definitions of what it is and they're just shouting past each other I define consciousness as subjective experience right now I'm experiencing colors and sounds and emotions but does a self-driving car experience anything? That's the question about whether it's conscious or not right? Other people think you should define consciousness differently defined by me but then maybe use a different word for it or they can I'm going to use consciousness for this at least so but if people hate the yeah so is GPT-4 conscious? Does GPT-4 have subjective experience? Short answer I don't know because we still don't know what it is that gives this wonderful subjective experience that is kind of the meaning of our life right because meaning itself feeling your meaning is a subjective experience joy is a subjective experience love is a subjective experience we don't know what it is I've written some papers about this a lot of people have Giulio Tononi Professor has stuck his neck out the farthest and written down actually very bold mathematical conjecture for what's the essence of conscious information processing he might be wrong he might be right or we should test it he postulates that if consciousness has to do with loops in the information processing our brain has loops information can go round and round in computer sciencenurdspeak you call it a recurrent neural network where some of the output gets fed back in again with his mathematical formalism if it's a feed-forward neural network where information only goes in one direction like from your eye retina into the back of your brain for example that's not conscious so he would predict that your retina itself isn't conscious of anything or a video camera now the interesting thing about GPT-4 is it's also just one way flow of information so if Tononi is right and GPT-4 is a very intelligent zombie that can do all this smart stuff but isn't experiencing anything and this is both a relief in that you don't have if it's true in that you don't have to feel guilty about turning off GPT-4 and wiping its memory whenever a new user comes along I wouldn't like if someone did that to me neutralized me like in Men in Black but it's also creepy that you can have very high intelligence perhaps then it's not conscious because if we get replaced by machines otherwise it's sad enough that humanity isn't here anymore because I kind of like humanity but at least if the machines were conscious it could be like well but they are descendants and maybe we they have our values and they're our children but if if Tononi is right and it's all these are all transformers that are not in the sense of the of Hollywood but in the sense of these one-way direction neural networks so they're all the zombies that's the ultimate zombie apocalypse now we have this universe that goes on with great construction projects and stuff but there's no one experiencing anything that would be like ultimate depressing future so I actually think as we move forward to the building more advanced AI we should do more research on figuring out what kind of information processing actually has experience because I think that's what it's all about and I completely don't buy the dismissal that some people some people will say well this is all bullshit because consciousness equals intelligence it's obviously not true you can have a lot of conscious experience when you're not really accomplishing any goals or you're just reflecting on something and you can sometimes have things doing things that are quite intelligent probably without being conscious </s>

<s>[INST] Is there uh memories big or small, weird, surprising just any kind of beautiful anecdote um from your chest career, like stuff that pops out that people might not know about this stuff when you look back and just makes you smile. [/INST] No, so I'll tell you about the most satisfying tournament, victory of my career. Um so that was the Norwegian championship under 11 in 2000 before that tournament. I was super anxious </s><s>[INST] because [/INST] I started like kind of late at chess, I I played my first tournament when I was 8.5 and a lot of my competitors had already played for for a couple of years or even 34 years at that point And the first time, so I played under 11 championship in 99 and I was like a little over the middle of the pack, I'd never played against any of them before, so I didn't know what to expect at all. And then over the next year I was like edging a little bit closer in each tournament. I felt like I was getting a little bit better and when we had the championship, I knew that I was ready that I was now at the same level of the best players, I was so anxious to, to show it. I remember I was just the feeling of excitement and nervousness before the tournament was incredible. The tournament was weird because I started out, I gave away a draw to a weaker player whom I shouldn't have drawn to, and then I drew against the other guy Who was clearly like the best story 2nd best. And at that point I thought it was over because I thought he wouldn't, he wouldn't give away points to others. And then the very next day he lost to somebody. So the rest of the tournament, it was just like, I was always like playing my game and watching his and we both won the rest of our games, but it meant that I was half a point, I had like, the feeling when I realized that I was gonna win um That was just so amazing. It was like the first time that I was the best at my age and at that point </s><s>[INST] you're hooked? [/INST] Yeah at that point I realized you know this I could actually be very good at this. So </s><s>[INST] you you you kind of saw, what did you think your ceiling would be? Did you see that? Did you see that one day? You could be the number one. [/INST] No, I didn't, I didn't think that </s><s>[INST] was possible at all. [/INST] Um But </s><s>[INST] when you first I [/INST] thought that could be the best in Norway at that point </s><s>[INST] because [/INST] like I started relatively late, </s><s>[INST] right? And [/INST] also like I knew that I studied a lot more than the others. I knew that I had a passion that they didn't have. They saw chess as something </s><s>[INST] like [/INST] it was, you know, it was a hobby, it was like an activity. It was like um it was like going to to football practice or any other sports. Like you go you practice like once or twice a week and then you play a tournament at the weekend. That's that's what you did for me. It wasn't like that. Like I would go with my books and my board every day after school. Uh And I wouldn't I would just constantly be trying to learn new things. I had like two hours of internet time on the computer each </s><s>[INST] week [/INST] and I would always spend them on on chess. Like I think before I was 13 or 14 I'd never opened a browser for any other reason than to play chess. </s><s>[INST] Would you describe that as love or as obsession or something in between? It's everything, [/INST] everything. But so I mean it wasn't hard for me to tell at that point that I had something that the other other kids then because I was never the one to grasp something very, very quickly. But once I started I always got hooked and then I never stopped learning. </s><s>[INST] What would you say? You've talked about the middle game as a as a place where you can play pure chess. What do you think is beautiful to you about chess? Like the thing when you were 11, what [/INST] is beautiful to me is when your opponent can predict every single one of your moves and they still lose. How </s><s>[INST] does that happen? [/INST] No. Like it means that at some point early you're planning your evaluation has been better so that you play just very simply, very clearly, it looks like you did nothing special and your opponent lost without a chance. So </s><s>[INST] your how do you think about that by the way, are you basically narrowed down this gigantic tree of options to where your opponent has less and less and less options to win to escape? And then they're trapped? That's [/INST] essentially </s><s>[INST] is there some aspect to the patterns themselves, to the positions, to the elegance of like the dynamics of the game that you just find beautiful. That that that doesn't that where you forget about the opponent [/INST] general, I try and create harmony on the board, like what I would usually find harmonious is that the pieces work together that they protect each other uh and that there are no pieces that are sub optimally placed or if they are sub optimally placed, they can be improved pretty easily. Like I hate when I have one piece that I know is badly placed and I kind of improve it </s><s>[INST] when when yeah, when you're thinking about the harmony of the pieces, when you're looking at the position, you're evaluating it, are you looking at the whole board or is it like a bunch of groupings of pieces overlapping? [/INST] I like </s><s>[INST] dancing together kind of thing. [/INST] I would say it's more of the ladder that would be more precise that you look, I mean </s>

<s>[INST] So for an individual learn a trade, become a craftsman, a sort and uh find somebody to love and who loves you. [/INST] That's right and I have a family in and stick with it. They should be surely you're gonna get angry, you're gonna get disappointed, you're gonna get all kind of stuff with but come back and make up before before you go to sleep </s><s>[INST] well. Uh I did half of those things. I got the first one and working on the 2nd 1. So I appreciate the advice. Well mari, thank you so much for joining us. Can you tell me the story of how you two met? [/INST] Well um, my parents every summer would go to the lake in in Canada and the place was called Turkey Point, which is on lake Erie and uh just have a nice summer holiday there, water skiing, swimming, you know, sunbathing. This is back in the sixties and I was sitting on the pier with a few girlfriends and telling them my story, you know? And then all of a sudden I looked up and I saw this figure in the distance coming onto the pier. Now we're all dressed in bathing suits and swimwear or swimming and this that and the other and here he comes. Dark trousers in fact they were black white shirt and a tie and a straw kind of a Panama hat and you know, so he was very, he stood out and so I invited him to come and sit down and so he continued to talk and we just talked and talked and talked and then later moved to the beach And um I think the next time I saw him he was talking to another girl and I thought, yeah, you know, I know I was okay, Okay next well, but six months later I received a letter and it's a letter from Roger and then we start this lovely correspondence and we just start writing, you know, in those days, you just wrote everything. And uh and then the next summer he was coming up again, he was on his way to Alaska and um he says I would like to come by and see you and I said, well I'll be in the same place that I met you last year. And so when we, when he came up this time For some reason Roger reached for my hand and I reached for his and man, that was it. It was like love at four. 1st </s><s>[INST] touch was love. [/INST] It was just like a silence, you know, and oh my gosh, and we didn't even look at each other, it was just oh my goodness what happened here? And I was the type of person I never wanted to get married, not way, way, way down the road, never have any Children and I wanted to see the world first and then do all that, you know? And um </s><s>[INST] but that was it, that was love and you've been together ever since. Yeah, Well the thing is about the love, the the two of you have for each other is it had to persevere through quite a heck of a journey. So how did Rodgers drug smuggling change the nature of your love and your relationship? [/INST] Well let's that remains steadfast. It it endured and um since Roger's been home, I think we've rekindled the love that we had when we first met, </s><s>[INST] but [/INST] I think my faith, um you know my faith, my steadfast faith and also the fact that Roger and I communicated, we wrote letters, you know, he he never complained. I know there were the Children there, he never had mistreated me, I love this guy and we had a lot of experiences. It was just </s><s>[INST] even the good looking charismatic, he's pretty, [/INST] Yeah, and he said he was adventurous, you know? And would you say that again? But yes, it was just I know I, you know, I missed him physically, but he was just we were just so strong in spirit, you know? And um we could talk to one another. </s><s>[INST] Yeah. Well what was it like Roger and you're a free man seeing Murray for the first time in person again, [/INST] I cried for three days. Everything. I look at a picture of her, I came home and uh she prepared a meal for me and uh it was the old oak table that I'd redone and the chairs the same one and the green place mats and the same china that we had in the same silverware? And it just just all of it just brought back the same paintings on the wall. It was just like unbelievable. After 35 years She had all my clothes cleaned and my shoes shining and I put the shoes on and I walked out on the strings on the soles came off with the shirts and all fit perfect everything. So it's just wonderful. And just just to see her and then just to think about see her picture of her 50th birthday of her 60th birthday, her 70th birthday. I wasn't there in the picture of her and with the Children. It just it was heartbreaking. And about the third day I thought man up fellow. I mean you've got to so uh I got over and quit, quit with the uh quit the tears. It was it was it was everything was just pulsating with life. It was just unbelievable to get out of that place. It really was. </s><s>[INST] Is there uh do you regret the drug smuggling that took you away from the woman you love? [/INST] Oh yes. 100% just no, I wouldn't have done it again if you don't think you're going to get caught And uh it's just no it's just I did it for money and I had everything in the world I wanted before I did that. </s>

<s>[INST] also, what it made me realize, I know I didn't really think through this, but it made me realize if there is alien civilizations out there. The thing we're most likely to see first would be space junk. My uh stupid understanding of it and the second would be really dumb. Kind of you can think of maybe like relay nodes or something objects that you need to have a whole lot of for particular purposes of like space travel and so on like speed limit signs or something. I don't know whatever we have on earth. A lot of that's dumb. It's not alien aliens and themselves, it's like artifacts that are useful to the engineering in the systems that are engineered by alien civilizations. So like it would, we would see a lot of stuff in terms of setting in terms of looking for alien life and trying to communicate with it. Maybe we should be looking not for like smart creatures or systems to communicate with. Maybe we should be looking for artifacts or even as dumb as like space junk. It just kind of refrain my perspective of like what are we looking for signs because there there there there could be a lot of stuff that doesn't have intelligence but gives us really strong signs that they're somewhere is life or intelligent life and uh yeah, that may be kind of and I know it might be dumped to say but reframe the kind of thing that we should be looking for. [/INST] Yeah, so the benefit of looking for intelligent life is that we perhaps have a better chance of recognizing it. Um, we couldn't necessarily recognize what an alien stop sign looked like. Um, and maybe, you know, the theorists are people who sort of model and try to understand solar system objects are, are pretty good at coming up with models for anything. I mean maybe a momo was a stop sign, but we're clever enough that we could come up with some physical explanations for it. And then, you know, we all want to go with the simplest possible, we all want to believe the most skeptical possible explanation. And so we missed it because we're too good at coming up with alternate explanations for things. </s><s>[INST] And it's such an outlier is such a rare phenomenon that we can't, we can't study 100 or 1000 of these objects. We have, we have just one. And so the science almost destroys the possibility of something special being there. It's like a johnny Ive's design of Apple. I don't know if you know who that is. He's the lead designer. He's the person who designed the iphone and all the major things. He talked about. His brilliant, one of my favorite humans on earth and one of the best designers in the history of earth. He talked about like when he had this origins of an idea like in his baby stages, he would not tell steve jobs because steve would usually like trample all over it. He would say this is a dumb idea. So I sometimes think of the scientific community in that sense because the the weapon of the scientific method is so strong at its best that it sometimes crushes the out of the box outlier evidence. You know, we don't get a lot of that evidence because we don't have um we're not lucky enough to have a lot of evidence so we have to deal with just special cases and special cases could present an inkling of something much bigger. But the scientific method user tramples all over and it's hard to know what to do with that because The scientific method works, but at the same time, every once in a while it's like a balance, you have to do 99% of the time, you have to do like scientific rigor. But every once in a while this is not you saying me saying smoke some weed and sit back and think, I wonder, you know it's the joe Rogan thing, it's entirely possible that it's alien space junk anyway. [/INST] Yeah, I think so. I completely agree. And I think that most scientists do speculate about these things, it's just at what point do you act on those things? Um So you're right that the scientific method has inherent skepticism and for the most part that's a good thing because it means that we're not just believing crazy things all the time. Um, but it's an interesting point that requiring that high level of rigor occasionally means that you will miss something. That is truly interesting because you needed to verify it three times and it wasn't verifiable. </s>

<s>[INST] Yeah, I had when I was giving lectures at m I t. There was one that was scary shitless and uh I mean, everybody, you know how students are and all that kind of stuff, They're kind of bored and they don't they don't understand that you're human too there. Yeah. Or this could be just me. [/INST] They don't understand you're trying to fastest human. Uh, </s><s>[INST] But there's 1 1 gentleman in the audience and he went to all the lectures. Older gentleman, he was a faculty at MIT and he just without very kind of nonchalant. I just said after the lectures, he kind of nodded me and say you did great. And uh before like one time he said in a non creepy way, I know this is going to come off as creepy. He said, uh, you look great today. Like he said that in a um, I don't in the way, so he's like 60, 70, whatever. Like he in this, I don't know if it's in a wise sage way because I was wearing a suit and tie. Like I looked like, you know when you dress up like a young kid, you Yeah. [/INST] So he </s><s>[INST] was just like, alright, you're, you're all dressed up, you look great, you got this. I don't know that has a lasting impact. That kind of pat on the back. But I agree with you. Um, cruelty towards other adults is somehow understandable because it's ah a world full of conflict. But cruelty towards Children. It doesn't, it doesn't quite that I can't, I can't understand it. I can't understand how you could act in a way that directly causes suffering to a child in front of you. Yeah, that is like the, I don't think I've ever talked to me, this might be a good time to ask you about this. What do you make, what lessons do you draw about human civilization from Jeffrey Epstein from Just Lane. Everybody thinks about different things. When you talk to eric Weinstein, he thinks about intelligence and like who, like Jeffrey Epstein is a front for something else. That's what he thinks about. I think about the weakness of grown man in the face of charismatic evil, which is like for me, directly as M I T I didn't know I actually was, I guess I was at M I T. When Jeff Epstein was just at the very end, he must have been there. Um I didn't know any of this, but it really bothers me that nobody was able to see through this man, because he's obviously what is also obvious to me is that he was very charismatic. Like, I mean, I I try to think about human nature from this perspective is um directly, like we said, help one life would I know Jeffrey Epstein? If he was in my life, I would I would I know evil when I saw evil, even [/INST] if it's sitting across from you </s><s>[INST] even I mean, you so Exactly, the evil laugh, thank you. The thing. [/INST] Well, </s><s>[INST] well, the thing I I'm sure we'll talk about it, maybe not, it doesn't really matter, We see things you and I Michael very differently about a lot of things politically and so on. The reason why I like you a lot. The reason, like, the people I do in my life is there's a there's a warmth, there's a kindness, there's a humanity underneath it all. I don't really care what you believe. I don't care, like I don't care what your twitter says. You know, it's easy to mistake your twitter to indicate that there's not a deeply human love for humanity in there and that's what I'm detecting, that [/INST] I think I would </s><s>[INST] be able to detect Jeffrey Epstein, [/INST] I'm just imagining the T 1000 detected. </s><s>[INST] Yes. Uh I imagine, I hope I would be able to not um detect that Epstein lacks that completely, even if he's charismatic in the, in the humor he has, even if he is charismatic in the expression of curiosity for science, which he did. He was curious about like, uh, not just like, boring minutia of science. He was interested about the big questions in science, which I could see that become exciting to scientists. Like, oh, wow, here's a person who's thinking big. That's always exciting when somebody goes into a room and thinks about like, how do we solve intelligence? How do we travel faster than the speed of light? That's exciting to people, especially people with money, because it's like, all right, So, we might be able to actually do big things here, but you could see through the bullshit that the dead, the deadness in the eyes, I don't know. Uh so I think about that because I feel like I have the responsibility for me as an individual to detect evil. [/INST] So I, do you know who Michael Alig is? Okay, this is gonna be a whole long, this is gonna be on lex clips, but there's a whole long story. So there was a scene in New York in the 90s called the club kids and they would go out to different nightclubs at night, they would all dress and really kind of crazy um costumes and but the costumes are all like, like goofy and like, just like, like an angel. This was dressed like a nurse. It was, there's a juvenile aspect to it. They're all taking, you know, ketamine and ecstasy to all hours. This is kind of rape culture was coming up in there and the head of it, and in fact, there's a, a clip on Youtube, I think it was the jane Whitney show of the club kids. And G G L. And G. G. Allin is uh you know, kind of punk rock performer, hard rock performer who passed away and the audience. And G. G. Allin was very aggressive and like a crazy person. My friend once saw him in a concert and he took a dump onstage, smeared it all over his face grabbed the girl from the audience and gave her a big kiss and as she walked by him, she just went like this like, excuse me, like went to the bathroom, So the audience is screaming at G G allin because he's very visibly over the top. Whereas you got a bunch of these kids dressed in these silly costumes, you guys just having fun. Well the head of the club kids, Michael Alig ended up killing someone. There was a kid called Angel Menendez who hung around with them. He would always have angel wings and boots. Uh one time there at Michael's condo with another with a drug dealer named freeze, they got into a fight. So Angel got hit in the head with a hammer, they killed him. What are we gonna do with the body? Uh they put it on ice in the bathtub. They had a party. So everyone is going to bathroom while angels bodies there, Michael got there like all right, we got to take care of this. Michael got extremely high on heroin had like silk cutlery from Macy's saw the body and pieces put in a box. They took him in a cab, the cab driver helped him throw the body into the river and then Michael starts walking around Manhattan wearing Angel's boots and would tell people I killed Angel now because he was a super effeminate over the top. Like he would pee in people's beer kind of guy. Everyone's like, oh God, Michael like, like you and your stupid pranks, but it was true and he got caught um and he got sent to jail. So I was in a store in Manhattan in Soho and it was one of those stores, we have like, all sorts of things for sale, and I saw a painting and it said malice and I was like, wait what? And it was Malik, it was Michael Alig painting he had painted while in jail. So my mom bought it for me for my birthday, I remember a birthday, it was and I started writing him in prison, he was going to write a memoir called caligula, which is clever, and then I actually went to visit him, like, I want to see what this person is like, because on the, on one hand, he's king of new york nightlife, this goofy person. And it's also kind of ironic that G G allin is like, maybe he's gross, he's not killing anybody is probably accountant off the stage and Michael Alig killed someone and then bragged about it, tongue in cheek, so, but meeting him And he passed away last December um, on Christmas actually just Christmas, 2020, um he was clearly a sociopath, and I've never met a sociopath before. Now, a lot of times you'll read these, like, you take a buzzfeed quiz, like, are you a sociopath, and it's like, oh my feelings weren't hurt when I was mean to someone, it's not a thin line between like me and you and him, it's a thick thick line because when you're talking to someone like that, at least in this specific case he was being very friendly, he wasn't, and it's not like he was gonna kill anyone or as a threat to me, um but there's that sense, like something's really off here and he was talking to me about how after he had killed Angel, he would just talk about it because he felt so much guilt, he just wanted to get caught, it's like, no, no, no, you know what he was describing wasn't guilt, he was describing just, he didn't like the knife over his head, like waiting to get caught, I'm like, you don't even know what guilt is, so it was kind of like, oh wow, so as for Jeffrey Epstein, but the thing is Michael Alig is, it was in a very low social position and the thing is when someone is powerful, very high status and they do something, we are as kind of hierarchal animals, we kind of defer to their norms, so if you're at a party with, let's suppose either of us and it's like a Jeffrey Epstein party and everyone at the party is doing some sort of weird drug we've never heard of, we wouldn't really feel comfortable judging them because like their norms kind of become the norm for that space. Um the lesson for me about Jeffrey Epstein, uh there's a, there's a lot of them because I think this the to me, the biggest moment was the Amy Rohrbach situation, Amy Rohrbach was caught on a hot mic saying that they had all the goods on him, They had all the names and that Buckingham Palace called them. They killed the story because they weren't going to get a Meghan Markle interview out of it. So that the willingness of those in power to do the wrong thing for the flimsiest pretext, which I think was a big important lesson. Also, the fact that no one at Abc had any consequences for this. In fact, the only person who got in trouble for all this was someone who used to work at Abc went to, I believe CBS and they got fired from CBS because apparently they had access to footage at one point, even though they weren't the ones who had leaked it. Um so whistleblowers are like the only, like for example, the case in um uh eric Garner, the guy who was selling loose cigarettes in new york city who was arrested, he had a heart attack or whatever it was on the way to jail, he died. The only person, so the cops had a situation where the only person who had got in trouble because of that was the guy filming it. Like he went to jail. So I think there is if there's a lesson in terms of, we look at Julian assange right there's a huge amount of power exercised by elites to make sure that what is done on the cover of Darkness remains on the cover of Darkness and also Kevin McCarthy who was currently the House Minority Leader Leader of the republicans, He wrote a letter to abc news like you had this guy, maybe you couldn't call in the authorities, but you could have leaked it to somebody. Why hasn't anything come forward? Nothing happened as a result of this. We also have to keep in mind that the longest serving Republican speaker of the House and history, Dennis Hastert went to jail because of things related to pedophilia and things like that. So as Russians and this is something I think you and I have mentioned before. Americans are very naive, often decreasing lee so about the nature of evil. They think an evil person is someone who is like getting kickbacks. Um, or you know, like the cuomos are colluding something like that. I would hardly even call that evil. Um, no, no, this is the sort of things that are so depraved that you would never think about it in a million years in your own home. You don't think in these terms. And and I think they get off on doing things that if the average person heard about it, the average person would be shocked because that gives them the sense of we're above them were different from them. The rules don't apply to us there's a lot to say </s>

<s>[INST] So the interesting aspect of dosh coin is it? So in contrast to like Bitcoin and ethereum which are these serious implementations that Cryptocurrency that seek to solve some of the problems that we're talking about with smart contracts and and uh resist the banks and all those kinds of things. Dutch coin operates more in the space of memes and humor while still doing some of the similar things. And it presents to the world sort of a question of whether memes whether humor, whether narrative will go a long way in the future, like much farther than some kind of boring old grounded technologies, whether we'll be playing in the space of fun, like once we built a base of comfort and stability and like a robust system where everyone has shelter, everyone has uh food and the basic needs covered, I will go into then operate in the space of fund. Mhm. That's that's what I think about dogs going because it seems like fun spreads faster than anything else. Fun of different kinds. And that could be bad fun and that could be good fun. And so this is a battle [/INST] of good fun spiral very, very quickly when you when you if you if you post something that people find funding. Yeah. </s><s>[INST] And that's what does corn represents. So there's like, it's a big corn represents like financial uh like serious financial instruments. And then door scores represents fun. And it's interesting to watch the battle go on on the internet to see which wins. This is also like open question to me of what is the internet because fund seems to prevail on the internet. And is that a fundamental property of the internet moving forward when you look 100 years out? Or is this a temporary thing? That was true at the birth of the internet? And it's just true for a couple of decades until it fades away and the adults take over and become serious again. [/INST] Well, I think the adults took over initially and then it was later on that people started using it for fun, frivolous things like memes. Um And that's I think that's pretty much unstoppable, you know. Yeah, because even people who are very serious uh you know enjoy um sending around a funny picture or uh something that amuses them. </s><s>[INST] Yeah. I I personally think we spoke about World War Two. I think memes will save the world and prevent all future wars. You've been handwriting your work for the past 20 years since writing the baroque cycle. What are the pros and cons of handwriting or typing [/INST] for me? I started it as an experiment when I started the rural cycle because I had noticed that if I sometimes if I was stuck having a hard time getting started, if I just picked up a pen and started writing it was easy to to go. So I just decided to keep with that. If it got in my way I didn't like it I could always just go back to the word processor will be fine. So but I never that never happened. So there's a certain security that comes from knowing that it's ink on paper and there's no operating system crash or software failure that can obliterate it. Um There's um um I it's a slower output technique and so um a sentence or a paragraph spends a longer time in the buffer up here before it gets committed two paper. Whereas I can type really fast and so I can slam things out before I really thought them through. So I think the first draft quality ends up being higher. Um And then editing first draft of editing is just faster because um instead of like trying to move the cursor around or whatever or you know hitting the backspace key, I can just draw a line through a word or a sentence or just around the whole paragraph and exit out. Um And in doing so I very quickly created an edit. But I've also left behind a record of what the text was prior to the edit. </s><s>[INST] Of course. You know all the digital versions have those quote unquote features but their experience is different. Is there a romance to just the physical, you know the touch of the pen to the paper doing what has been done for centuries? [/INST] I think there is I think there is a just the simplicity of it and not having any intermediary technology beyond the the pen and the paper uh is just very simple and clean. Um And um um so I've got a bunch of fountain pans and I started buying fancy paper from Italy a few years ago because I I thought I would be more conservative with it, you know? But it still doesn't it's still a trivial expenditure so it doesn't really alter my my habits very much. Uh </s><s>[INST] huh. So all that said you once you do type stuff up, you use Imex I use Imex obviously the superior editor of course You uh let me just ask the ridiculous futuristic question because Max has been around forever. Do you think in 100 years we will still have imax in them or like Pick up pick up let's say 1500 [/INST] years. Yeah. Yeah. No I mean whenever you're doing anything in Lenox you you're spending a lot of time editing little config files and scripts and stuff and you need to be able to pop in and out of of editing those things and it needs to work like even if the windowing gooey is dead and all you've got is like a command line you to get out of that problem, you might need to enter an editor and uh and ultra file. So I think on that level there always have to be sort of uh very simple. Well imax isn't very simple but you know what I mean? There have to be basic editors that you can use um from either the command line or a gooey um Just for administering systems now how widespread they will be. Um You know there's a certain amount of what's the story of the the there's the american folk tale of the the guy who the hammer guy who drives the railroad spikes, john Henry trying to keep up with the steam hammer and eventually the steam hammer winds because he can't drive the spikes fast enough. So there's a sense in which you know Microsoft like yeah who knows how much they've invested in code visual studio to to you know or or Apple with X. Code. So they've put huge amounts of money into enhancing their IDs and imax in theory can duplicate all of those features um by you know if you just have enough Lennox hackers writing imax lisp macros. Um but you know, at some point um it's gonna be hard to to maintain that level of of to keep up feature for feature. </s>

<s>[INST] It's possible something like plants is actually a set of living organisms on ecosystem of living organisms. They're just operating a different time scale and a far superior intelligence and human beings and then human beings will die out and plants will still be there and they will be they're yeah, [/INST] they're also there's an evolutionary adaptation playing a role at all of these levels. For instance, if mice don't get enough food and get stressed, the next generation of mice will be more sparse and more scrawny. And the reason for this is because they in natural environment, they might have probably hidden a drought or something else. And if they're over grace, then all the things that sustain them might go extinct and there will be no mice few generations from now. So to make sure that there will be mice and five generations from now basically the might scale back and a similar thing happens with the predators of mice, they should make sure that the mice don't completely go extinct. So in some sense, if the predators are smart enough, they will be tasked with shepherding their food supply. Maybe the reason why alliance have much larger brains and antelopes is not so much because it's so hard to catch the antelope as opposed to run away from the lion. But the lion's need to make complex models of the environment more complex than the antelopes. </s><s>[INST] So first of all, just describing that there's a bunch of complex systems and human beings may not even be the most special or intelligent of those complex systems even on earth. Makes me feel a little better about the extinction of human species that we're talking [/INST] about. Maybe you're just gonna exploit to put the carbon back into the atmosphere. </s><s>[INST] This is just a nice uh [/INST] you know, the big stain on evolution is not as it was trees evolved trees before they could be digested again. Right? There were no insects that could break all of them apart. Uh cellulose is so robust that you cannot get all of it with microorganisms. So many of these trees fell into swamps and all this carbon became inert and could no longer be recycled into organisms and we are the species that is destined to take care of that. So this </s><s>[INST] is kind of [/INST] take it out of the ground, put it back into the atmosphere and the earth is already greening. So within a million years or so when the ecosystems have recovered from the rapid changes that they're not compatible right now, there's going to be awesome again. </s><s>[INST] And there won't be even a memory of us of us. Little apes. [/INST] I think there will be memories of us. I suspect we are the first generally intelligent species in the sense we are the first species with an industrial society because we will leave more phones than bones in the stratosphere. </s><s>[INST] Or ci phones them bones. I like it. But then let me push back. You kind of suggested that we have a very narrow definition of, of intel. I mean, why aren't trees more general uh higher level of general intelligence. [/INST] Trees were intelligent and there would be at different time scales, which means within 100 years the tree is probably not going to make models that are as complex as the ones that we make in 10 years. </s><s>[INST] But maybe the trees are the ones that made the phones right? [/INST] Like </s><s>[INST] you [/INST] could say the entirety of life, did it? You know? Uh The first cell never died. The first cell only split, right? And every divided and every cell in our body is still an instance of the first cell that split off from that very first cell. There was only one cell on this planet as part as we know. And so the cell is not just a building block of life. It's a hyper organism, right? And we are part of this hyper organism. So nevertheless, </s><s>[INST] this hyper organism know the this little particular branch of it, which is as humans because of the industrial revolution. And maybe the exponential growth of technology might somehow destroy ourselves. So what what do you think is the most likely way we might destroy ourselves? So, some people worry about genetic manipulation. Some people, as we've talked about, worry about either dumb artificial intelligence or super intelligent artificial intelligence destroying us. Some people worry all nuclear weapons and weapons of war in general. What do you think if you had to if you're a betting man, What would you better on in terms of self destruction? And it would be higher than 50 would be higher than 50%. [/INST] So it's very likely that nothing that you bet on matters after we've been our bets. So I don't think that bets are literally the right way to go about Once </s><s>[INST] you're dead, it doesn't you won't be there to collect. [/INST] So it's also not clear if the species go extinct, but I think that our present civilization is not sustainable. So the thing that will change is there will be probably fewer people on the planet than are today. And even if not then still most of people that are alive today will not have offspring 100 years from now because of the geographic changes and so on and the changes in the food supply. It's quite likely that many areas of the planet will only be livable with a close cooling chain in 100 years from now. So many of the areas around the equator and in uh uh subtropical climates that are now quite pleasant to live in will stop to be inhabitable without conditions. </s><s>[INST] So, you honestly, wow, cooling chain, close knit cooling chain communities. So, you think you have a strong worry about the the effects of global warming [/INST] itself. It's not the big issue. If you live in Arizona right now, you have basically three months in the summer in which you cannot be outside. And so you have a close cooling chain, you have air conditioning in your car and your home and you're fine. And if they are conditioning would stop for a few days that in many areas you would not be able to survive. Can we just pause for a second, Like you say, so many brilliant poetic things like, what is the clothes that do people use </s>

<s>[INST] here. I was talking to jimmy jimmy Pedro. He was surprised by this to most matches. You can't see even you talk about like a uh come back gable steals and you can't see the full match like a crappy highlight. [/INST] So the two the two biggest things in it and really the three the N. C. Championships on ESPN the olympic trials on NBC. In the olympics. For NBC. And these these these companies are so big. They don't have a department dedicated to selling the rights to that footage. Right? So the rights to wrestling footage which knowing that cares all that much about accepting a niche are the exact same as track and field or our basketball in the olympics. So yes all of this stuff is completely inaccessible to us. The the N. C. A. S. The olympic trials in the olympics. You can't go watch old film on. It </s><s>[INST] sucks older current film. Yeah. So you can't even watch the gable match the gable students know they did uh You know they do something that I know is the funk out of me. Okay. They they they do like a three or two minute highlight [/INST] so it's like they </s><s>[INST] capture the most important thing. But like it's all about the build [/INST] up. It's </s><s>[INST] like it's that very beginning when you step on the mat and the nerves and you walk out and like that. I mean I don't know. Uh you miss then then when the triumph happens where the heartbreak happens it has that much more power. [/INST] Yeah. If you want to go to war with NBC or ESPN I'm happy to join. This </s><s>[INST] is bullshit. IOC [/INST] well, I mean I've seen all night I </s><s>[INST] IOC is selling that for the olympics is the one that's [/INST] making well so NBC broadcast. So they obviously have the live rights you would think they would have recorded if they're I mean they're the ones recording and you think they keep the rights when you </s><s>[INST] think, no no there are like getting a license of it. They're getting exclusive like license but like the you know for example, uh, I've had this talk to Travis stevens the judo player and There's a really sort of famous matches, the heartbreak in his career from 2012 Olympics where he goes against the German Ole Bischof, whatever. It's a 20 minute match to go to war and that's not available anywhere, but it's uploaded on Youtube and set to private. The reason I know this is on the IOC channel. So they've uploaded all of these matches. [/INST] They haven't been put up. So actually, so my Olympic match, the 1x1 got put public and I don't know if it's private. It's got put up on Youtube as alluded to it. The week of my jake paul fight. It was so dumb and like why is every 13 years later this bullshit like this should have been up. So, I mean, okay, so what about olympic trials footage That has to be the USO CNN or NBC. So I know like, okay, so I don't Flow writes that work for them. I know if Flow buys your event or whatever right? They buy the rights generally in the contract. They'll have rights to both live stream it and then use that footage at any point moving forward. So those matches live on flows website. That's why I would be surprised if NBC didn't have something similar. </s><s>[INST] Flow does a pretty good job of providing like a a place where you can watch all these matches. NBC does not. Yeah and and and also there's an argument with flow as well. But certainly with the olympics there's a difference between what flow does and what the olympics represent. Like it feels like the olympics which is what the charter says should be as accessible as possible. Like like you should really lower the barrier for entry for the olympics. [/INST] And you know that's what the charter says. But those people in the house see those this isn't the worst people ever. They're very bad </s><s>[INST] but they're not they're not bad. They're just lost touch of the dream they once had when they joined the house. [/INST] Well I would argue I would argue all the way back. These are rich fat cat too. Like I get so mad about the N. C. A. Which finally now got rid of this term bullshit term amateurism. It's like well there's some holy grail where you can't make money to be an amateur athlete. But the people who own the IOC or the people who own the institutions, college institutions are making boatloads of money off of you. That's crowd. </s><s>[INST] So you competed like you said at the 2008 Olympics. Did you believe you can win gold? Yeah. Absolutely. So the your mental game at some point. Yeah I was ready. So what what went wrong? This wasn't good enough. [/INST] That's what I said. Yeah I mean so at that point in time um It was my first year international competition. So when I came out in 2007 is my first time making 74 kg, which is pretty small for me. Um I had some failures, but then quickly I turned that around and I was having success uh in America is being everyone, I don't wanna be easy, but yeah, you know, I was doing really well. Um I went international one time and I, there's one match I got cheated on the Russians, they're cheaters, she was Ukraine, not Russia. Um I lost one real match we're actually lost. Um and it was to Dennis argues who would go on to win three world title. He was behind the t of that year and it was competitive, you know, so I knew, okay, I'm like, I'm going with the best guys in the world. I beat a bunch of other guys who, you know, were we're good, it had passed decent results. So I knew I was like right there, unfortunately, I ran this guy, Ivan Fundora and and I had someone who's scouting reports from my high school coach, coaches for our academy john mason rick and funder was the worst stylistic matchup. I got him. Um and I lost him second round, so I wasn't good enough. I had, I decided to keep wrestling, I probably would have gotten better, but at that point, Davis wasn't in </s>

<s>[INST] So you need to see look at that grass fed and finished or grass fed 100 [/INST] That ratio of Omega 3-6 is it changes in like a week on grain. So it's radically different. Unfortunately it's the same thing for you and me could eat clean for a month, you know junk for three days, your garbage, right? It's not like you can just like coast on that, right? We know that's like the same thing for animals or physiology changes foods. The number one way we interact with our environment and our body changes really rapidly and dramatically. </s><s>[INST] So we know belcampo and just the way sort of this regenerative farming approach of belcampo and the sort of humane is good for the land is good for the animal. Can you comment on ways it's good for the human that eats the meat? Is this me better for you? [/INST] Yes, it's and this is where you know the kind of focus on the joy and animals doing yoga and all this sort of like cynical stuff about, about this type of agriculture. Say just like set that aside. You know it really is better for your health. It's got a better fat ratio, it's less inflammatory, it's got higher protein. Um it's just better product in the case of beef, it's lower and fat and that fat is a better quality. It's higher in poultry and pork is also higher in protein. So all the nutritionals are better. It's got higher density of vitamins, got higher density of minerals and none of this stuff is radically different than, you know, it's not like it's the product is black and white, but they're every metric meaningfully is better in the right direction across the board. So why wouldn't you </s><s>[INST] I hesitate to take anecdotal evidence as like final scientific conclusions, but it does seem I've eaten quite a bit of belcampo meat for example. And it's just my body seems to respond like is less bothered by it meaning like uh less inflamed. I just feel better because I mostly eat a meat diet and it it does seem to be a little bit of a difference what kind of meat I eat where it comes from. I don't know if that's my own psychology also. I mean there is an aspect to like when you know that the meat came from a good place and all the ways we've we've defined good, you feel better about it and that has an effect, decreased stress. So I'm a huge believer in that, like, outside of just nutrition, how you feel about the whole experience is a huge impact, but it does feel like the meat itself is actually just leading to less inflammation for me, or like less like the blo blo bloated feeling and all those negative effects that could come with me versus like certain other ground beef that I eat, like store bought um chicken breast or steak, all those kinds of things. My body is a little bit more, works a little bit harder to process that food. It feels like, I don't know if there's science to that, but anecdotally that seems to be the case. [/INST] Omega sixes are a big part of that in the case of the, you eat a lot of beef, you love beef. And so in a conventional beef product, it's a 1 to 30 ratio of omega three sixes and can sometimes 1 21 to 30 but that's the wrong direction in our beef, it's, you know, as low as 1 to 1. So that in the mega sixties are what's part of inflammation right now, You know, the the magic and animals is that they are incredibly efficient processors, right? And in the same way that, you know, the the the body can protect uh from, you know, can process and take out tons of things that are toxic to the environment, animals bodies can do that too. So the beauty of meat is that it can be pretty clean, you know, things like round up and stuff don't end up in the meat when we have antibiotics in our meat, we're not worried about getting like Tetris cycling from the chicken breast. What we're worried about is the workers getting touch recycling the chicken growing faster than it should the meat being chewy er and not as high quality. So they but the actual antibiotics don't the animals great at filtering that they get that out. So you have to think about meat, not as like contamination of like oh there's gonna be some of that garbage they used in the farming in my meat. Um But it's the more subtle things, it's the fat ratio, it's the protein density and there's also uh just I think in my experience um there's just more complex flavor and things that taste more complex. This is you know, science backs this up there. They fill you up faster. So if you're looking to limit, you know, to to eat for fullness and but not eat as many calories. More complex foods are the way to do that. And that hit, you know, you hit your society, help you hit that society. So things like I mean all the key um you know, I mean acids that help you feel full mostly from meat, right? Um So those are that's part of it like it but all meats have those then there's other kind of micronutrients and things about that complex flavor that help you feel full faster. </s>