Datasets:

ianiket23

/

podcast_llama_chat_format-5k

like 0

<s>[INST] Well, let me ask you another difficult topic. That's just like the other ones that we talked about. Uh that's going on in the news now, as we sit here today, the Supreme Court has voted to overturn abortion rights in a draft majority opinion striking down the landmark roe versus wade decision. What are your thoughts on this, first of all, the human institution of the Supreme Court, making these decisions throughout its history? And second of all, just the idea uh they're really powerful. Their controversial the difficult idea of abortion. [/INST] Yeah, I mean, I'm against abortion. I'm I'm pro life. The church recognizes from the moment of conception, we're dealing with a human life that's worthy of respect and protection, especially as you see the unfolding event of that person, you know, across a pregnancy, but at every stage we recognize the beauty and the dignity of that human being. And so we stand opposed to this, the outright killing of the innocent. So that's the church's view. Um, again, reaching out always in love and understanding and compassion to those who are dealing and believe me, every single pastor, every single priest understands that because we deal with people all the time, who are in these painful situations. But um, that's the moral side of it. The legal side, I think roe V wade was terribly decided. I think one of the worst expressions of, of american law since the dread scott decision. So I stand in favor of overturning roe V wade and Casey. I think they were terrible. The Casey decision is instructive to me. The it belongs to the nature of freedom that that decision says to determine the meaning of one's own life. And even, I don't get the language exactly right, But and of the universe like it gives this staggering scope to our freedom that we can determine the meaning, but that's repugnant to everything. We've just talked about that. I'm inventing the meaning of my life and of the universe. And so Casey that was instructive in a way because it it tips its hat toward the problem culturally is that I think in my freedom, I can determine everything, my choice is all that matters. And I would say no, your your choice should be correlated to the order of the good. It's not sovereign. It doesn't rain sovereignty over being and it makes its own decisions. So I think Casey was terrible law. And it was backing up roe v wade, which is terrible law. So I'm in favor of the overturning of those. I've spoken out that many times now. It will return it to the individual states. It's not going to, you know, solve the problem. The individual states will have to decide. I just heard yesterday, we were up in sacramento, the bishops having our annual meeting. And so we got the word, you know, from the governor and the legislators, um, that they're going to push for a constitutional amendment in California. So basically to make any attempt to limit abortion in any way, just illegal. You know, I think that's barbaric. You know, so I stand radically opposed to that. </s><s>[INST] It's such an interesting line because if if you believe that there's a it's a line that struggles with the question of what is does it mean to be a living being or to give life to something. Um, because if you believe that at the moment of conception, you're you're basically creating a human life, then abortion is murder. And then if you don't, then it's a sort of basic biological choice that's not taking away of a life. And the gap between those two beliefs is so vast. It's hard and yet so fundamental to the question of what it means to be alive. And the fundamental question about the respect for human life and human dignity. It's interesting to see um and also about freedom to, you know, all of those things are mixed in [/INST] there, it's a </s><s>[INST] beautiful struggle, [/INST] Maybe the freedom is the most important, you know, this is a freedom run amok or in classical philosophy and theology, freedom is not self determination. Freedom is the disciplining of desire. So as to make the achievement of the good first possible and then effortless what I'm saying. So modern freedom and the roots of that are people like William back. Um uh in the late Middle Ages, freedom means I hover above the yes and no yes or no, and I'm the sovereign subject of that choice and I will know basis, I will say yes or no, I'm like, louis the 14th, you know, I'm like Stalin or something, you know, but the queen's wouldn't have recognized that as freedom for him. It's I got this desire, you know, in me, I've got this will and it's pushing toward the good. But the trouble is I got so many attachments and and I'm so stupid and I'm so conditioned by my sin that I can't achieve it. So I need to be disciplined in my desire so as to make that achievement possible and then effortless. So right now I'm freely speaking, english to you and, you know, you have the experience and I've had a two of learning a foreign language and don't you feel unfree, you know, like when you're struggling with the language, when I was over in paris doing my doctoral work and you know, I was okay with french. But you know, my first time in a seminar and all these like, you know, intelligent francophones around the table and they're all just and I'm trying to say my little thing in my awkward french and I felt unfree because I, my desire wasn't wasn't directed, you know. But then over time I became freer and freer speaker of french. I was ordered more to the good. That's a better understanding of freedom than sort of sovereign self determination. But our country is now, I think really in the grip of that I decide. And that's why the Nietzschean thing comes to my mind, you know, the will to power. I'm beyond good and evil. It's just up to me to decide. God help us. No, it's the values that we intuit around us. Intellectual moral and aesthetic. The values think of the dog on the beach again, and that you get ordered to those, by your education, by your family, by your religion. And that's beautiful. That makes you free. You know, I can freely enter into this. So this sovereign self determination business, that's not my game. </s>

<s>[INST] Can you maybe elaborate a little bit deeper hollow microscope that can see 2 10 to the -100. How rotating black holes and presumably the that the detailed accurate detection of gravitational waves from black holes can reveal the discrete nous of space. [/INST] Okay, first thing is what is a black hole actually we need to go a little bit further in the in the story of what space time is because I explain a little bit about what spaces but it didn't talk about what time is and that's sort of important in understanding space time. So, </s><s>[INST] your senses, both space and time in this story are [/INST] discrete. Absolutely, Absolutely. But it's a complicated story and needless to say </s><s>[INST] it's simple at the [/INST] bottom. It's very simple at the bottom. It's very in the end, it's simple, but deeply abstract and and something that is simple in conception but kind of wrapping one's head around what's going on is pretty hard. Um But so so first of all we have this. So you have described these kind of atoms of space and their connections. You can think about these things as a hyper graph. You know, a graph is just you connect nodes, two nodes, but a hyper graph you can have, you know, you can have sort of not just friends, individual friends to friends, but you can have these triplets of Of friends or whatever else. It's it's um and so we're just saying and that that's just the relations between atoms of space are the hyper edges of the hyper graph. And so we've got some big collection of these atoms of space, maybe 10 to the 400 or something in our in our universe. And that's the structure of space. That's an every feature of what we experience in the world is a feature of that, that hyper graph. That spatial hyper graph. So then the question is, well, how does, what does that special typographic do? Well, the idea is that there are rules that update that spatial hyper graph. And you know, in a cellular automaton, you've just got this line of cells and you just say it every step at every time step. You got fixed time steps, fixed array of cells at every step. Every cell gets updated according to a certain rule. And that's that's kind of the that's the way it works now in this hyper graph, it's sort of vaguely the same kind of thing. We say every time you see a little piece of hyper graph that looks like this updated to one that looks like this. So it's just keep rewriting this hyper graph every time you see something looks like that anywhere in the universe, it gets rewritten. Now, one thing that's tricky about that which will come to is this multi computational idea which has to do with you're not saying in some kind of lock step way, do this one, then this one then this one. It's just whenever you see one you can do, you can go ahead and do it and that leads one not to have a single thread of time in the universe. Because if you knew which one to do, you just say, okay, we do this one, then we do this one, then we do this one. But if you say just do whichever one you feel like you end up with these multiple threads of time, these kind of multiple histories of the universe, depending on which order you happen to do the things you could do in. So it's </s><s>[INST] fundamentally asynchronous and parallel. [/INST] Yes. </s><s>[INST] Which is very uncomfortable for the human brain that seeks for things to be sequential and synchronous. [/INST] Right? Well, I think that this is this is part of the story of consciousness is I think the key aspect of consciousness that is important for sort of parsing the universe is this point that we have a single threat of experience. We have a memory of what happened in the past. We can say something and predict something about the future, but there's a single thread of experience and it's not obvious it should work that way. I mean, we've got 100 billion neurons in our brains and they're all firing all guns in different ways, but yet our experiences that there is the single thread of time that goes that goes along. And I think that one of the things I've kind of realized with a lot more clarity in the last year is the fact that our the fact that we conclude that the universe has the laws it has is a consequence of the fact that we have consciousness the way we have consciousness. And so the fact, so, so I mean, just to go on with kind of the basic setup, it's so we've got this special hyper graph, it's got all these atoms of space. They're getting they're getting these little clumps of atoms of space are getting turned into other clumps of atoms of space. And that's happening everywhere in the universe all the time. And so one thing is a little bit weird is there's nothing permanent in the universe. The universe is getting rewritten everywhere all the time. And if it wasn't getting rewritten, space wouldn't be knitted together, that is space would just fall apart. There wouldn't be any way in which we could say this part of space is next to this part of space. You know, one of the things that I was, people were confused about back in antiquity, you know, the ancient greek philosophers and so on is how does motion work? How can it be the case that you can take a thing that we can walk around and it's still us when we walked a foot forward, so to speak and in a sense, with our models. That's again a question, because it's a different set of atoms of space. When we when, you know, when I move my hand, it's moving into a different set of atoms of space. It's having to be recreated. It's not the thing itself is not there, it's it's being continuously re created all the time. Now, it's a little bit like waves in an ocean, you know, vortices and fluid, which again, the actual molecules that exist in those are not what defined the identity of the thing. And but it's a little bit uh you know, there's this idea that there can be pure motion that it can, that it is even possible for an object to just move around in the universe and not change is it's not self evident that such a thing should be possible. And that is part of our perception of the universe, is that we re parse those aspects of the universe. Where things like pure motion, impossible. Now, pure motion. Even in general relativity, the theory of gravity um pure motion is a little bit of a complicated thing. I mean if you imagine your average, you know teacup or something approaching a black hole, it is deformed and distorted by the structure of space time. And to say, you know, is it really pure motion? Is it that same teacup? That's the same shape? Well, it's a bit of a complicated story and this is a more extreme version of that. So so anyway, the thing that that's happening is we've got space, we've got this notion of time, sort of time is this kind of this rewriting of the hyper graph. And one of the things that's important about that time is this sort of computational irreducible process. There's something, you know, time is not something where it's kind of the mathematical view of of time tends to be time is just to coordinate. We can, you know, slider, slider turn a knob and we'll change the time that we've got in this equation. But in this picture of time, that's not how it works at all time, is this inexorable irreducible kind of set of computations that go on that go from where we are now to the future. But so so the thing and one of the things that is again something one has to break out of is your average trained physicists like me. He says, you know, space and time in the same kind of thing. They're related by you know the prank or a group and and Lawrence transformations and relativity and all these kinds of things. And you know, space and time uh you know there are all these kind of sort of folk stories you can tell about why space and time in the same kind of thing in this model. There fundamentally not the same kind of thing. Space is this kind of sort of connections between these atoms of space time, is this computational process? So the thing that the first sort of surprising thing is, well it turns out you get relativity anyway and the reason that happens that if you but some pieces here, which one has to understand but but the fundamental point is if you are an observer embedded in the system that are part of this whole story of things getting updated in this way and that there are there's sort of a limit to what you can tell about what's going on. And really in the end, the only thing you can tell is what are the causal relationships between events. So, an event in this sort of uh elementary event is a little piece of hyper graph got rewritten and that means a few hyper edges of the hyper graph were consumed by the event. And you produce some other hyper edges. And that's an elementary event. So then the question is what we can tell is kind of what the network of causal relationships between elementary events is that's the ultimate thing, the causal graph of the universe. And it turns out that, well, there's this property of causal invariants. That is true of a bunch of these models. And I think it's inevitably true for a variety of reasons. Um that makes it be the case that it doesn't matter. Kind of if you are sort of saying, well, I've got this hyper graph and I can rewrite this piece here and this piece here, and I do them all in different orders. When you construct the causal graph for each of those orders that you choose to do things in, you'll end up with the same causal graph. And so that's essentially why uh well, that's in the end, why relativity works. It's why our perception of space and time is is as as having this kind of connection that relativity says they should have. And that's that's kind of that's kind of how that works. </s>

<s>[INST] You're, amongst many things, age is just a black belt. one of the things that people are really curious about white belts and blue belts in jujitsu, but also people haven't tried the art is what does it take to be a jujitsu black belt? [/INST] I think that, you know, everyone's journey is a little bit different. But the one thing that the it was a Calvin Coolidge quote, you know, determination, persistence is the only thing that will win in the end. It will always win in the end, not brilliance, not toughness, not education, it's persistence. And I think that having the belief that no matter what happens to me, I will proceed forward and I will, I will figure out how to make this happen hell or high water I think is the one thing that ties together all of the people that I've ever met that made it through whatever it was that they were going through. Because you know, sometimes you can get lucky and you can have an easy time or and that luck could be, you had a good situation. It could be, I mean like in the obvious sense of like where you're living, where your training, what's going on, You had a good situation, you're unbelievably athletic, oh, you're going to be an astronaut, you're brilliant and, and an olympic athlete, you know, like, well that's a fantastic situation, you know, you won the genetic lottery and worked hard as well, but you also won the genetic lottery. It's a determination is the one thing though, because that person could have a very easy go of it initially and then tear their knee and then they're no longer the superhuman physical specimen that they were. The only thing that will keep them going is persistence. And I think that that um I would just say that persistence, I say, I'll just put one ft in front of the other and sometimes I can see the path ahead and sometimes it's beyond my vision, but I will not stop, I may even slow down, but I won't stop. And that's the only thing that I can say that I've seen tie everyone together because there's so many ways to the top of any mountain and there's so many different personalities and skills and backgrounds involved, but everyone, everyone carries </s><s>[INST] on at the core of the foundational advice is just don't quit, Just keep going, [/INST] that's the lesson of martial arts, I think, you know, we think it's like how to be strong or how to be, how to win, but in reality it's like how to persist, how to endure because it's all of us have been beaten so many times have gotten beaten up so many times and thought about quitting. Have I ever thought about quitting? Absolutely. Have I ever quit? Never. I will never, ever quit ever. I can see it. You might not be, I will be damned if I quit. </s><s>[INST] What's the darkest moment? Is it injury related? Like, is it? Uh so like to me like two possibilities, I've fortunately never been seriously injured, but I think that's a dark place to be like having to be out for many months for um, as generals saying, like with a head injury, especially like the uncertainty, that's one. And then the other side is if you have big ambitions as a competitor realizing that you're not as good like those, those doubts were like, I kind of suck, how am I supposed to be a world, the greatest fighter of all time? If I, if if like several people in the gym are kicking my ass, Those are the two things that paralyze you. [/INST] I think that everyone's darkest moment is maybe different looking from the outside for Ryan. I wouldn't say that he's had injuries and he said bad ones. I wouldn't say that was his darkest moment. I think for me, I would say some of my head injury was my darkest moment. Absolutely. And I've torn my a C L twice. I've torn my shoulders four times. I've had lots of surgeries. Um for me, the orthopedic injuries or not the most, how difficult it was the brain injury for others that might be the case for them. Maybe they've never experienced an injury and maybe for them that's their darkest moment from the outside. Obviously Ryan can speak to this more. But for Ryan I think it was the um inability to perform at certain points to the to the missing of opportunities that for him, from my perspective watching him go through and having seen various points of his growth from from early purple thought on. I think the hardest time for him looking and obviously was uh when he would hit moments where he wasn't able to perform for various reasons. He couldn't get fights. He he was having difficulties there. I think that that was the hardest point for him. </s><s>[INST] Did you did you think like with a head injury that you might not never be able to do so again? [/INST] Yeah. I mean I I mine was very um was really bad and it was just the one hit. But I had a looping memories for seven months. Didn't know it because when your brain's messed up you're not even aware that you're looping. Um And so uh I saw two different neurologists. I finally took a very long time. Um I didn't know if I was going to be able to have like linear thoughts or read a book. I didn't know at certain points if I could listen to music again. You know without making my head hurt. Um, and so, uh, it was almost two years before I woke up in the morning without a headache? Um, just waking up before I even start my day. And so </s>

<s>[INST] Yeah, I gotta say that's my view on life and love in general is scarcity is what makes it valuable. People talk about immortality, you know, I would like to be immortal, but it does, it does seem that when you let go of the fitness of life, I feel like that meals and the experiences you have get devalued significantly like the longer you live, the less value there are in an infinity if you live forever. I worry that all the meaning will dissipate and the same thing would love a quick criticism of sort of dating culture and all that kind of stuff. Like I haven't uh a shocking revelation that I've never been attended data or any of those things. I believe that scarcity and dating and interaction is like intensifies the value of when the interactions do happen, so when they like when love does happen. So in that sense there's something magical about scarcity in the more subjective psychological social world as well. And perhaps money is just another version of that, right? It's just, it's all about the stories and ideas we tell ourselves, [/INST] I think they're actually more interconnected than you're giving it credit for, right? Which is what is money, Money is time ultimately right? The the pursuit of the acquisition of money, right? Of whether it's a currency or true money is because that should give you more time. And so one of my favorite movies ever is uh it's funny because Justin timberlake is in it is this movie, I lose most people at that market in time in time. And basically the premise of the movie is that everyone has a clock that is embedded into their arms. And so uh if you go to work, you basically put your arm underneath when you leave and there's time that's deposited into your clock and if your clock ever hits all zeros, you're dead, you die on the spot. And so there's a number of scenes where people are basically running, you know, to get to you and I give you a little bit more time so that you can get to work on monday and then you work to acquire time. And so basically time becomes this currency. But what becomes very fascinating about it is there are sections in society where literally there's physical places, if you only have, let's say 72 hours or less, you're allowed to go to section one, Section five though because you have years and years and years on your clock. And in this movie, everyone at the age of 25 freezes from a biological aging standpoint, so everyone stays the same, but you may have lived for 1000 years. And so it becomes so fascinating about it is that rich people have time, poor people do not have time. And so in it Justin timberlake, the main character at one point essentially acquires a bunch of time and he's able to go to one of the higher levels. Um, and now he's attending all these Gallas and you know poker nights and all the stuff. And one of the first things that he learns is that in the lower end of society, everyone is running everywhere at all times in the movie because time is so finite and it is so scarce and so therefore why would I walk down the street? I must run down the street in the highest level of society. No one runs anywhere. And in fact if you run, you are seen as lower class because wealth is time. And so that movie is, you know, it's got a ton of kind of things that you can pull out of it. But to me is the perfect epitome of money is time. And so when you start to think about the acquisition of money right? It goes to this whole idea of time billionaire. And I know that um there's probably a lot of people have heard about this already, but If you think of a million seconds, it's about 11 days, A billion seconds is 31 years. And so if I said to somebody, you have to switch lives with Warren Buffett, would you do it? Some people would say, sure not be their initial reaction, but you have to be, you know, 92 years old is the money worth the lack of time, Most people would say no, there's this guy, Graham Duncan who really articulated this well, um and ultimately what ends up happening is you realize time is more valuable than the money, but you acquire the money to gain more time. </s><s>[INST] And the reason is valuable is because of the scarcity of time. We currently have the biology, the physics. It means that this is not just the narrative. We tell ourselves maybe just, I don't know, but it feels like pretty sure we're mortal in that sense. The scarcity there gives value to time. It's fascinating to think about all the thought experiments here of if that could actually be on the economy, if you can actually convert time in a frictionless way to money [/INST] Well, and if you start to pull on this little bit and say, Okay, a young person today, let's say somebody in their twenties has about two billion seconds left in their life, right? Kind of 60 years give or take based on life expectancy. They usually until they start to understand this concept, think of wealth in dollar terms, But dollars are being devalued and so, you know, $1 million dollars doesn't get you what it used to get right. It's kind of an old adage. And so what you're doing is you're pursuing something that ends up losing value. And so it's the constant rat race, it's how do I constantly try to get more, how do I get more dollars, how do I get more dollars? Because even if I say to myself, you know I'm going to retire when I get $100,000 When I get $200,000, $100,000.5 years from now it doesn't buy me what I thought it did. So now I need 500,000 or 200,000 or a million or whatever the number is. And so ultimately what ends up occurring is that the Bitcoin community and many people in kind of this idea of sound money is you want to be able to acquire an asset that not only will hold the value at the store of value over time, but it will actually appreciate over time. And so when you look at something like Bitcoin against the dollar against other types of assets, all of these assets are down compared to Bitcoin right now, some of that's just in the early days of kind of the pricing of an asset, you go from very small to something much larger. But now what you start to look at is well if you have a finite supply of something, what ends up happening is people begin to value it more. And so in a world where dollars are infinite and other fiat currencies are infinite. Bitcoin becomes very, very interesting, very special. Uh and something that is very aspirational. And so I think that's where you're starting to see people say wait a second, this is something where that finite secure store of value is essential to wealth generation and preservation over a long period of time. </s>

<s>[INST] much cameras means simulate how a real camera would see the real world, therefore you can explore the limitations of that. You can train perception algorithms on the in stimulation, all that kind of stuff. [/INST] Exactly. So, you know, it has been easier to simulate what we would call introspective sensors, like internal sensors. So for example, inertial sensing has been easy to simulate. It has also been easy to simulate dynamics like uh like physics that are governed by ordinary differential equations. I mean like how the car goes around, maybe how it draws on the road, how you interact with, interacts with the road or even an aircraft flying around like the dynamic of physics of that. What has been really hard has been to simulate extra cept of sensors, sensors that kind of like look out from the vehicle and that's a new thing that's coming like laser range finders are a little bit easier, cameras, radars are a little bit tougher. I think once we nail that down the next challenge, I think in simulation will be to simulate human behavior. That's also extremely hard. Even when you imagine like how a human driven car would act around. Even that is hard. But imagine trying to simulate, you know, a model of a human just doing a bunch of gestures and so on and you know, it's actually simulated. It's not captured like with motion capture but it is similar. That's that's very in fact, today I get involved a lot with like sort of this kind of very high end rendering projects and I have like this test that I've passed it to my friends or my mom, you know, I sound like two photos to kind of pictures and I say rendered which one is rendered, which one is real and it's pretty hard to distinguish except I realized except when you put humans in there. It's possible that our brains are trained in a way that we recognize humans extremely well. But we don't so much recognize the built environments because built environment came after per se. We evolved into being humans but humans were always there. Same thing happens. For example you look at like monkeys and you can't distinguish one from another but they sort of do and it's very possible that they look at humans. It's kind of pretty hard to distinguish one from another. But we do and so our eyes are pretty well trained to look at humans and understand if something is off, we will get it, we may not be able to pinpoint it. So in my typical friend test or mom test, what would happen is that we put like a human walking in a anything and they say you know this is not right, something is off in this video, I don't know what, but I can tell you it's the human eye can take the human and I can show you like inside of a building or like an apartment and it will look like if we had time to render it, it will look great. And this should be no surprise a lot of movies that people are watching. It's all computer generated. Even nowadays when you watch a drama movie and like there's nothing going on action wise. But it turns out it's kind of like cheaper I guess to render the background and so they would </s><s>[INST] but how do how do we get there? How do we get a human that's would pass the mom slash friend test a simulation of a human walking? Do you think that's something we can creep up to buy just doing kind of a comparison learning or you have humans annotate what's more realistic and not just by watching like what's the path as it seems totally mysterious how [/INST] to simulate human behavior. It's hard because a lot of the other things that I mentioned to including simulating cameras right? It is um the thing there is that you know we know the physics, we know how it works like in the real world and we can write some rules and we can do that. Like for example simulating cameras, there's this thing called ray tracing, I mean you literally just kind of imagine it's very similar to it's not exactly the same but it's very similar to tracing photon by photon, they're going around balancing on things and come into your eye by human behavior developing a dynamic like a model of that, that is mathematical so that you can put it into a processor that would go through that that's going to be hard and so so what else do you got, you can collect data right? And you can try to match the data or another thing that you can do is that you know, you can show the front test, you know, you can say this or that and this or that and that would be labeling anything that requires human labeling ultimately were limited by the number of humans that we have available at our disposal and the things that they can do, you know, they have to do a lot of other things that also labeling this data. So um so that modeling human behavior part is I think going we're going to realize it's very tough and I think that also affects, you know, our development of autonomous vehicles. I see them self driving as well, like you want to use so you're building self driving, you know, at the first time, right after urban challenge, I think everybody focused on localization mapping and localization slam algorithms came and google was just doing that. And so building these HD maps basically, that's about knowing where you are. And then five years later in 2012 2013 came the kind of coding code Ai revolution and that started telling us about everybody else's but we're still missing what everybody else is gonna do next. And so you want to know where you are, you want to know what everybody else is, Hopefully you know about what you're gonna do next and then you want to predict what other people are going to do in that last bit has has been a real real challenge. </s>

<s>[INST] rebellious and in certain kinds of ways [/INST] in some ways. Yeah, absolutely. I think most people didn't take too kindly to the bureaucracy and I'm sure the bureaucracy put up with an enormous amount that they didn't really want to, </s><s>[INST] so maybe to linger on it a little bit, you have a sense of what the philosophy that characterizes UNIX is the design, not just the initial, but just carry through the years? Just being there being around? What's the fundamental philosophy behind the system? [/INST] I think one aspect the fundamental philosophy was to provide an environment that made it easy to write or easier productive to write programs. So it was meant as a programmer environment, it wasn't meant specifically as something to do some other kind of job. For example, it was used extensively for word processing, but it wasn't designed as a word processing system, it was used extensively for lab control, but it wasn't designed for that. It was used extensively as a front end for big other systems, big dump systems, but it wasn't designed for that. It was meant to be an environment where it was really easy to write programs. That program which could be highly productive. And part of that was to be a community. And there's some observation from Dennis Ritchie, I think at the end of the book that says that that from his standpoint, the real goal was to create a community where people could work uh as programmers on the system. And I think in that sense, certainly for many, many years it succeeded quite well at that. And part of that is the technical aspects of, because it made it really easy to write programs, people did write interesting programs, those programs tended to be used by other programmers. And so it was kind of a virtuous circle of more and more stuff coming out. That was really good for programmers </s><s>[INST] and you are part of that community of programmers. So what was it like writing programs on that early UNIX? [/INST] It was a blast. It really was. You know, I like to program, I'm not a terribly good program but it was a lot of fun to write code. And in the early days there was an enormous amount of what you would today I suppose called low hanging fruit. People hadn't done things before and this was this new environment and the whole combination of nice tools and very responsive system and tremendous colleagues made it possible to write code. You could have an idea in the morning, you could do a, you know, an experiment with it, you could have something limping along that night or the next day and people would react to it and they would say, oh that's wonderful, but you're really screwed up here. And and the feedback loop was then very, very short and tight. And so a lot of things got developed fairly quickly that um in many cases still exist today and I think that was part of what made it fun because programming itself is fun. It's puzzle solving in a variety of ways. But I think it's even more fun when you do something that somebody else then uses, even if they wine about it not working, the fact that they used, it is part of the reward mechanism </s><s>[INST] and what was the method of an interaction? The communication when that feedback loop. I mean, this is before the internet, [/INST] certainly before the internet, it was mostly physical right there. You know, somebody who come into your office and say something. </s><s>[INST] So these places are all close by like offices are nearby, really lively interaction. Yeah, [/INST] no Bell Labs was fundamentally one giant building and most of the people were involved in this unique stuff. We're in two or three quarters and there was a room, oh, how big was it? Probably Call it 50 ft by 50 ft make up a number of that, which had some access to computers there as well as in offices and people hung out there and it had a coffee machine and so there was, it was mostly very physical. We did use email of course. Um, and but it was fundamentally for a long time, all on one machine, so there was no need for internet. </s><s>[INST] It's fascinating to think about what computing would be today without their labs, it seems so many the people being in the vicinity of each other, sort of getting that quick feedback working together. There's so many brilliant people. I don't know where else that could have existed in the world have been given how that came together. What, how does that make you feel that that's a little element of history? Well, [/INST] I think that's very nice, but in a sense, it's survivor bias and if it hadn't happened at Bell Labs, there were other places that were doing really interesting work as well. Xerox parc is perhaps the most obvious one. Xerox parc contribute enormous amount of good material. Um and many of things we take for granted today in the same way came from xerox parc experience. I don't think they capitalized in the long run as much their parent company was perhaps not as lucky in capitalizing on this. Who knows? But that would that's certainly another place where there was a tremendous amount of influence. There were a lot of good university activities. M. I. T. Was obviously no slouch in this kind of thing and and others as well. Um, </s><s>[INST] so UNIX turned out to be open source because of the various ways that a TNT operated and sort of had to uh it was the focus was on telephones. So [/INST] I think that's a mischaracterization in the sense, it absolutely was not open source, It was very definitely proprietary licensed, but it was licensed freely to universities in source code form for many years. And because of that generations of university students and their faculty people grew up knowing about uh UNIX and there was enough expertise in the community that then became possible for people to kind of go off in their own direction and build something that looked UNIX like. Um the Berkeley version of UNIX started with that licensed code and gradually picked up enough of its own uh, code contributions, notably from people like Bill Joy, that uh eventually it was able to become completely free of any T A T M T code and uh, there was an enormous amount of legal jockeying around this, that in the late, Early to late 80s, early 90's, something like that. Um and then uh Not something that I guess the open source movement might have started when Richard Stallman started to think about this in the late 80s, and by 1991 when Torvalds decided he was going to do a UNIX like operating system, there was enough expertise that uh, in the community that first he had a target, he could see what to do because the kind of the UNIX system called interface and the tools and so on, were there. Um, and so he was able to build an operating system that at this point when you say, you know, in many cases what you're really thinking is Lennox, </s>

<s>[INST] But the really cool thing is it has to do with the infinite fund that you're referring to, which is our brain seems to be very limited. And like you said, computation is [/INST] very plastic. Very plastic. And so it's a it's a interesting combination. </s><s>[INST] The the interesting open question is the limits of that in your plasticity. Like how how flexible is that thing? Because we don't we haven't really tested it. [/INST] We know about that experiments where they put like a pressure pad on somebody's head and had a visual transducer pressurize it. And somebody slowly learned to see. It's like it's </s><s>[INST] especially at a young age if you throw a lot at it. Like what what can it uh can it completely? So can you like arbitrarily expanded with computing power. So connected to the internet directly [/INST] somehow. Yes, probably. Yes. </s><s>[INST] So the problem with Biology and ethics is like there's a mess. They're like us. Humans are perhaps unwilling to take risks in uh, in two directions that are full of uncertainty. [/INST] So 90% of the population is unwilling to take risks. The other 10% is rushing into the risks unaided by any infrastructure whatsoever. And you know, that that's where all the fun happens in society has been huge transformations in the last, you know, a couple of 1000 years. </s><s>[INST] Yeah, it's funny. I mean, I got a chance to interact with this Matthew johnson from johns Hopkins, he's doing this large scale study of psychedelics. It's becoming more and more. I've gotten a chance to interact with that community of scientists working on psychedelics, but because of that, that opened the door to me to all these uh, what do they call psycho notes, the people who, like you said, the 10% who like, I don't care. I don't know if there's a science behind this. I'm taking this spaceship. Uh, if I'm being the first on mars, I'll be uh, you know, you know, psychedelics interesting in the sense that in another dimension, uh, like you said, it's a way to explore the limits of the human mind. Like what is this thing capable of doing? Because you kind of like when you dream, you detach it. I don't know exactly in your science of it, but you detach your like reality from what your mind, the images, your mind is able to conjure up in your mind goes into weird places. Like entities appear somehow Freudian type of like trauma is probably connected in there somehow. But you start to have like these weird vivid worlds that like, [/INST] so do you actively dream you? Why not? I have like 66 hours of dreams and I it's like a really useful time. </s><s>[INST] I know I I haven't, I don't for some reason I just knock out and uh I have sometimes like anxiety inducing kind of like very pragmatic like nightmare type of dreams but not nothing fun, nothing, nothing fun, nothing fun. I I try I unfortunately have mostly have fun in the waking world which is very limited in the amount of fun you can have. [/INST] It's not that limited either. Yeah, that's what we'll have to talk uh </s><s>[INST] new instructions. Uh [/INST] Yeah, there's like a manual for that. You might want to. </s><s>[INST] I looked it up, I'll ask you on what would you dream [/INST] you know, years ago and I read about, you know like you know a book about how to have, you know become aware of your dreams. I worked on it for a while. Like there's this trick about, you know, imagine you can see your hands and look out and and I got somewhat good at it like but my mostly when I'm thinking about things are working on problems I I prepped myself before I go to sleep. It's like I pull into my find all the things I want to work on or think about and then that let's say greatly improves the chances that I'll work on that while I'm sleeping. And then, and then I also, you know, basically asked to remember it and I often remember very detailed </s><s>[INST] within the dream or outside the [/INST] dream well to bring it up in my dreaming and then remember when I wake up, it's just, it's more of a meditative practice you say, you know, to prepare yourself to do that. Like if you go to the sleep, still gnashing your teeth about some random things that happened that you're not that really interested in, you'll dream about it. </s><s>[INST] That's really interesting maybe. [/INST] But you can direct your dreams somewhat by prepping, </s><s>[INST] you know, I'm gonna have to try that. It's really interesting. Like the most important, the interesting, not like uh what did this guy send an email kind of like stupid worry stuff but like fundamental problems. You're actually concerned [/INST] about interesting things you're worried about books you're reading or you know, some great conversation you had or some some adventure you want to have. Like there's there's a lot of space there and and it seems to work that, you know, my percentage of interesting dreams and memories went up. </s><s>[INST] Is there? Uh is that the source of uh if you were able to deconstruct like where some of your best ideas came from, Is there a process that's at the core of that? Like so some people you know walk and think some people like in the shower the best ideas hit him if you talk about like newton apple hitting him on the head [/INST] now I I found out a long time ago I'm I processing so much slowly. So like in college I had friends who could study at the last minute get in the next day, I can't do that at all. So I always front loaded all the work like I do all the problems early you know for finals like the last three days I wouldn't look at a book because I want you know because like a new fact day before finals may screw up my understanding of what I thought I knew. So my my my goal was to always get it in and give it time to silk and I used to you know I remember we were doing like three D. Calculus, I would have these amazing dreams of three D surfaces for normal, you know calculating the gradient and just like all come up so it was really fun like very visual and uh and if I got cycles of that that was useful. Um And the other is don't over filter your ideas like I like that process of brainstorming where lots of ideas going to happen. I like people who have lots of ideas but then then yeah I'll let them sit and let it breathe a little bit and then reduce it to practice. Like at some point you really have to does it really work like it was this real or not right? But but you have to do both. There's great attention. They're like how do you be both open and you know, precise. </s>

<s>[INST] of human girlfriends, um I'd love your advice in this direction, but you're you have an amazing relationship with Kaleil. Uh so you two are very different. So you host the Tiger Brother podcast together, but there's there's real love there. There's a there's a real connection. What what what do you um what do you love most about Kyla? Talk about love, bobby [/INST] lee. Yeah, I mean that's a really pretty deep, I've never really gone down this path. Um </s><s>[INST] We're gonna walk down that path together holding hands. [/INST] It's one of those things where the first time I met her, it was almost as if I had known her all my life. It was really weird. You know, I mean there was a a trust there. I mean that was just fundamentally there that I could trust her and that I could, you know when I look in the mirror and I see all my character defects and stuff, a lot of those things aren't necessarily things I want to share with people because I don't want to be judged or ridiculed. But with her I felt comfortable showing those things and I think she feels the same way about her and then secondly she's funny, you mean she made me laugh and and she's hot, it's all you know, I mean the perfect, it was like a perfect combination of things, you know I mean she one night we were in bed and I forgot what the joke was but she really made me laugh one night it was she was living in an apartment in Long Beach and I cackled, you know what I mean? And generally women don't make I mean not women, I'm dating comics do um don't make me cackle in that way. And then um Thirdly she has um she's partly asian. Mhm. So it's like you know one time I dated a white girl and I invited her to koreatown, are </s><s>[INST] you about to be a racist [/INST] a little bit? Yeah. And what I love about asian girls is they'll eat something first and ask what it is after. But white girls ask what it is before what is this, right? But Clyde would eat the eyeball eat everything go what did I just eat, I like that, you know what I mean? So it's like and it reminds me of my mom in that way in terms of like my mom growing up just Scare us and freak us out, we'd have a fish and she would eat the eyeball 1st to see a squirm and as a kid that you thought was gross and weird and this and that, but it's like, you know, when Khalil a does it, it just kind of like, I don't know, it just makes, makes me feel at home </s><s>[INST] in a weird way. It's a, it's a little act of fearlessness. I like [/INST] that. Yeah, </s><s>[INST] just put in your mouth and figure it out. [/INST] Yeah, that's what I like, and at the end of the day, she also out of all my girlfriends and this is gonna sound, not </s><s>[INST] strange, [/INST] but hard to admit, but my career when I met Camila was in the ship box, I could not get anything going. And um this is at the time where ken jeong who is a very good friend of mine and very talented was getting everything and I just remember going, I can't even get an audition, like I can't, I would go on the road lex and I would fill half the room, I just couldn't sell tickets and when I met her, I was just kind of like, maybe this is, I have to find love and open up my world in that way and she was the first girlfriend I ever had that looked at me and saw the potential and she said, no, this is not, it doesn't feel right, you're so funny and you're so relevant to me and this is what we're gonna do, and so she started tiger belly, you know, and then, um, obviously I had the skill set to do it. Um, but once tiger belly happened and then Andrew was like, let's do bad friends and then now things are great, you know, my career is, I'm too busy almost in a weird way, you know, and I feel like she had a lot to do with, like for instance, before I met her, even if I would get an audition, I wouldn't go because I just wouldn't get it in my head. I was like, I'm not gonna get this, I've gone on 1000 of these and they just never hire me, but she was so I just didn't go on on them for years. And then she was the first girlfriend that said, no, I don't care if you don't get it right, I just want you to be a pussy and I want you to walk through fear and so she would drag me to these things and I, for some reason would book them, you know, I mean? So </s><s>[INST] we saw the potential of what you could be, but she loves you for who you are already, [/INST] but </s><s>[INST] also loved you for the potential that you could become. [/INST] Yeah, and I'm lucky in that way, you know, </s><s>[INST] so on day one you could show her, you said you could show her your flaws to her, like you felt like you could be fragile with [/INST] her. Well I accidentally farted. </s><s>[INST] Yeah. Day one [/INST] On day one, you know, because I just had a fart machine and I have loose cheeks. Yeah. </s><s>[INST] Like how [/INST] you for the </s><s>[INST] listeners, He just winked at [/INST] me. I have loose cheeks and um, </s><s>[INST] but not in a gay way. Not [/INST] in a gay way. No. And I um I was on a couch and we're talking and I kind of adjusted my body. I ripped one by accident and she laughed. You know, I mean it wasn't embarrassing, you know? And um I also have a little penis, have a little penis and </s>

<s>[INST] the requirement to understand that is to be almost to a radical degree, be empathetic and to listen to the world. And I mean, you brought up sort of gender roles. It's not so simple. All of this is messy. For example, this is me talking. It's clear to me that, for example, the wolf culture has bullying built into it has some elements of the same kind of evil built into it. And when you're part of the wave of wokeness standing out for social rights? You also have to listen and think, are we going too far? Are we hurting people? Are we doing the same things that others that we're fighting against, that others were doing in the past. It's not simple. Uh, once you see that there's evil being done uh that it's easy to fix. No. And uh in our society it's there's something about our human nature that just to easily stops listening to the world to empathizing with the world. And we label things as evil, This is through human history, this is evil. You mentioned tribes, this religious belief is evil and so we have to fight it and we become certain and dogmatic about it. And then in so doing commit evil onto the world, it seems like a life that accepts and responsibility for the norms or in has to constantly be sort of questioning yourself and questioning like listening to the world fully and richly without being um weighed down by anyone sort of uh realization, you just always constantly have to be thinking about the world, am I wrong? Am I wrong? And seeing in the world this way, [/INST] I mean the very last thing you said, you've constantly got to be thinking about the world. You've constantly got to be listening, you've constantly got to be attending. And it's not simple. All that sounds exactly right to me. And the phrase that rings through my head is another one from the brothers Karamazov Dmitry is passionate sort of sometimes violent brother who um who is also sort of deep deeply cares. I mean he's because he's passionate, he's sort of got care through and through, but it's breaking him apart. He says at one point, um, God and the devil are fighting in the battlefield is the heart of man. And I just think, yeah, it's not simple and the idea that there might be a purely good way of doing things, it's just not our condition that we are, everything we do is going to be sort of undermined by some aspect of it. There's not going to be a kind of pure good in in human existence. And so it's sort of required that we're going to have to be um empathetic that we're gonna have to recognize that others are dealing with that just as we are. </s><s>[INST] So I apologize for distracting us. We were talking about Heidegger that uh, and the reason we were distracted is he happened to also be a Nazi, but he nevertheless has a lot of powerful ideas. What are the ideas he's brought to the world? [/INST] Okay, so that's a big, huge question. So let me see how much of it I can get on the tape. I mean the big picture is that Heidegger thinks and he's not really wrong to think this that the whole history of philosophy from plato forward, maybe even from the pre Socratic forward from like the sixth century BC to now has been motivated by a certain kind or has been grounded on a certain kind of assumption that it didn't have the right to make and that its lead us astray and that until we understand the way in which it's led us astray, we're not going to be able to get to grips with the condition we now find ourselves in. So let me start with what he thinks. The condition we now find ourselves in is lots of periods to hide occurs views. I'm not, I'm just going to sort of mush it all together for the purposes of today. Heidegger thinks that one of the crucial things that we need to contend with when we think about what it is to be us now, is that the right name for our age is a technological age. And what does it mean for our age to be a technological age? Well, it means that we have an understanding of what it is for anything at all to be at all. That we never really chose that sort of animating the way we live our lives. That's animating our understanding of ourselves and everything else that is quite limited. And it's organized around the idea that to be something is to be what sitting there as an infinitely flexible reserve to be optimized and made efficient. And Heidegger thinks that, uh, that's, that's not just the way we think of silicon circuits or you know, the river when we put a hydro electric power plant on it were optimizing the flow of the river so that it makes energy, which is infinitely flexible and we can use in any way at all. It's the way we understand ourselves. Two, we think of ourselves as this reserve of potential that needs to be made efficient and optimized. And when I when I talk with my students about it, I asked them, you know, like, what's your calendar look like? What's the goal of your day? Is it to get as many things into it as possible? Is it to feel like I've I've failed unless I've I've made my life so efficient that I'm doing this and this and this and this and this, that I can't let things go by the feeling that I think we all have, that there's some pressure to do that, to relate to ourselves that way is a clue to what Heidegger thinks, um, the technological age is about. And he thinks that's different from every other age in history. We used to think of ourselves in the 17th century, at the beginning of the of the enlightenment as subjects who represent objects. Take heart thought that a subject is something some mental sort of realm that represents the world in a certain way, and we are closed in on ourselves in the sense that um, we have a special relation to our representations. Uh, that's that's what the realm of the subject. But others, you know, in the Middle Ages we were created in the image and likeness of God and in the pre Socratic Age to be, was to be what washes up and lingers for a while and fades away. The paradigm of of what is we're thunderstorms and the anger of the gods, achilles, battle fury. And it overtakes everything and stays for a while and then leaves the flowers blooming in spring. And that's very different from the way we experience ourselves. And so the so the question is, um, what are we supposed to do in the face of that? And Heidegger thinks that the the priest opposition that's motivated everything from the pre Socratic forward is that there is some entity that's the ground of the way we understand everything to be for the Middle Ages. It was God that was the entity that made things be the things that they are for the enlightenment, it was us, maybe for start it's us and Heidegger thinks, um, whatever it is that stands at the ground of what we are, it's not another thing, it's not another entity and we're relating to it in the wrong way. If we think of it like that, there's some way and this is partly why I was interested in Meister Eckhart, he says what there is is there's giving going on in the world and we're the grateful recipient of it. And the giving is like, whatever it is, it's the social norms that were thrown into, we didn't choose them. They were given to us </s>

<s>[INST] Well, the basics of the cancer reveals, you know, it's like fundamental to the human experiences, trauma is tragedy. It's like money who gives a shit about money, education, all that is like weird new inventions. You know, life is short, You suffer with the various diseases and that is a reminder that life is short and reminder of the basic human connection and that's why you can bridge that gap all sparked by a handwritten letter which just makes for a helpless story. [/INST] And you know what? Like this is the commonality between us, A guy with three jobs to a billionaire. We both had that sense of a sledgehammer to the chest boom. You have cancer and you can't breathe For like 30 seconds. And then when your heart is just about to kick off and you you take a breath and you go, I'm sorry, what'd you say, doc? You have cancer. And it don't matter what kind one of my, one of my best buddy's body is going through right now prostate. And I got way too many of my buddies with cancer. Right? My buddy Hugh who became a vet since his first cancer. He was a fireman. He's now veterinarian, right? He diagnosed me actually over the phone by the way, um when they couldn't figure out what's wrong with me dr Hugh, He nailed it to the t. And we talk and the same thing that the dozen of my close friends that have cancer, the same thing we say is the fear. So mr coke and I, we shared that same sledgehammer to the chest and that same fear and it didn't matter how much money he had and how much I didn't and you know, it's just like the morning of the trade center, there was big time brokers Who went to their demise right? Working in these firms, God rest them. And there was dishwashers, excuse me, dishwashers up on the windows on the world restaurant 107th floor Making $5 an hour. And they died together. It didn't matter. It didn't matter if you had an armored car loaded with bills you were done that day and that's I think where people need to humanize each other just because you drive around in a nice car and you got your own jet and you got this and you got that don't mean nothing. When you're going when you're in that vulnerable spot, you could have you could have more money, you know than than than the U. S. Reserves, federal reserve or you could have a welfare check. You're going, I learned that in a cancer ward I had people in my ward that died on me. I was going around as a little bit of an ambassador because I was trying to, I was putting on a fake, I was putting on a fake like I got this, I got this, I was so scared. But when I got Past that, that seven days of torture and the days leading up to it, I go around and try to comfort the other cancer patients. I just want older african american gentleman. He couldn't talk because he had such advanced throat cancer. He was my roommate for a little while. But then he got worse that they had to put him by himself and you couldn't understand what he was saying because his throat was just so radiated from the radiation. But if you put your ear </s><s>[INST] down to him, you could make [/INST] out what he was saying. And I'm not faulting the nurses for maybe not wanting to do that. Right. It's, it's, they're busy. They've got a ton going on. They can't spend, you know. So if he was in need, I put my ear down and I find out and I go get it for him. So when they moved me down the hall, they asked me to come down with my ivy tower. He needed me. And uh, I knew it was bad because he just, his look was gone, I said, so what do you need? And he whispered, call my sister, I'm going, he had only one survivor in his whole life and she was in north Carolina and he wanted her to </s><s>[INST] know she couldn't get [/INST] up. She was elderly and I got the nurse and I got on the phone and I called his sister and I said ma'am I explained who I was and I said he can't really verbalize too well right now but he wants to say he loves you. Mhm. And I put the phone down and he told her he loved her and he said I'm going home and and that was it. And I hung the phone up and I I just said ma'am, I'm so sorry, I said you know they'll notify you and and I stayed with him for a while holding his hand and then you know they wanted him to rest and then I left and then I got the tap now or later and they said I was sorry he's gone. And then there was another girl and she was a young young girlfriend. One of the areas I work, young african american girl where I used to respond but I didn't know her but I knew her neighborhood and uh She had what I had but they weren't sure which one you know leukemia is there is there an elusive beast? There's 49 of them right and each one of them is like they got their own little nuances on specific treatment. So if they don't know what you have, they don't know what to do for you and she refused to let them drill into her hip to take the marrow because it's vicious. It hurts so much. It's like someone is born into your hip with a wood drill and it's no joke. And they asked me to try to convince her to let her let them do that or she was going to die because if they couldn't figure it out, it was advancing quickly. She was so I I talked to her and she said, I can't I can't I'm too scared. I said, what are you more scared to die? And she said, I am. I said okay, I'll stay with you, I'll hold your hand, you squeeze it as hard as you want. And I said if if you want they'll give you like a towel or something to bite on whatever I said, but you get that pain out, but you need to do this so you can get saved. And she said okay. And they came in and they had this huge thick needle like just bored into you and she's screaming for her life. And she's squeezing my fingers so hard and so hard. And I said that's okay, hon you keep going, you keep going, we got it, it's just 10 more seconds. 10 more seconds. They got it. They figured out her treatment and they got her onto her road to recovery. And then I spent a long time asking God, yeah, why why do I have cancer. But then I stopped and I went, wait a minute. I didn't die that day with my friends. She want me for asking why I have cancer. I had 10 years after 9 11 with such great years and I got to watch my little girl being born when john never got to see his son. So it was all gravy after that. And I said, but now I know I have my cancer because I can, I can empathize with people who haven't and I can try to be their voice when they can't talk, be their shield, try to take that pain because I can understand it can walk their walk and now I thank God for my cancer because it's made me a better human being. It's made me I'm not gonna lie. I brought a lot of anger for a while and and my family suffered it, but I really tried to go past that and he'll and and part of living out in the country, it's very, very healing for the mind and the soul. But I now thank God for the cancer because it humbled me. I didn't really need humbling. I wasn't, I wasn't a arrogant puffed up type of person at all. But You know, maybe I was running away myself a little bit and working on a TV show, I'm fine man, 30 at the time while I was 42 and got sick, you know, life was cruising man, it was great and then all of a sudden it was like a blow out on the highway in the middle of the night and you're just veering off towards the guard rail. </s>

<s>[INST] I mean, it's difficult to trust to trust humans in this day and age online, you know, because so we're working remotely, that's one thing, but just interacting with people on on the internet, it sounds sounds ridiculous, but you know, I've, because of this podcast, in part, I've gotten to meet some incredible people, but it, you know, it makes you nervous to trust folks and I don't know how to solve that problem. So, I'm uh talking with Mark Zuckerberg who dreams about creating the metaverse, What do you do about that world where more and more our lives is in the digital sphere, like, um one way to phrase it is most of our meaningful experiences at some point will be online, like falling in love getting a job or experiencing a moment of happiness with a friend with a new friend made online, all of those things, like more and more the fun, we do the things that make us love life will happen online, and if those things have an avatar that's digital, that's like a way to hack into people's minds whether it's with A I A I or kind of troll farms or something like that. I don't know if there's a way to protect against that, that that uh that might fundamentally rely on our faith in how good human nature is. So if most people are good, we're going to be okay. But if people will tend towards manipulation and um unlevel and behavior in search of power, then we're screwed. So I don't know if you can comment on how to keep the metaphor [/INST] secure. Yeah, I mean, I all I thought about when you were talking just now is my three year old son, you know, he asked me the other day, what's the internet mom? And I just almost wanted to cry, you know, I don't want that for him. I don't want all of his most meaningful experiences to be online, you know, by the time that happens. Um how do you know that person's human that avatar is human. You know, I believe in free speech. I don't believe in free speech for robots and bots and like look what just happened over the last six years. You know, we had bots pretending to be Black Lives Matter activists just to so some division or you know, texas secessionists or um you know organizing anti Hillary protests or just to sow more division to tie us up in our own politics. So that were so paralyzed, we can't get anything done. We can't make any progress and we definitely can't handle our adversaries and their long term thinking it really scares me. And here's where I just come back to just because we can create the metaverse, you know, just because it sounds like the next logical step in our digital revolution. Do I really want my, my child's most significant moments to be online? They weren't for me, you know, So maybe I'm just stuck in that old school thinking or maybe I've seen too much and um I'm really sick of being the guinea pig parent generation for these things. I mean it's hard enough with screen time, like thinking about how to manage the metaverse as a parent to a young boy. Like I can't even let my head go there. That's so terrifying for me. But we've never stopped any new technology just because it introduces risks. We've always said, okay, the promise of this technology means we should keep going, keep pressing ahead. We just need to figure out new ways to manage that risk. And you know, that is that's that's the Blockchain right now. Like when I was covering all of these ransomware attacks, I thought, okay, this is gonna be it for Cryptocurrency, you know governments are going to put the kibosh down, they're going to put the hammer down and say enough is enough. Like we have to put this genie back in the bottle because it's enabled ransomware, I mean five years ago they would hijack your PC and they'd say go to the local pharmacy, get an E gift card and tell us what the pin is and then we'll get your $200 now it's pay us, you know, five Bitcoin. Um and so there's no doubt cryptocurrencies enabled ransomware attacks. But after the colonial pipeline ransom was seized because if you remember the FBI was actually able to go in and claw some of it back from dark side, which was the ransomware group that hit it. And I spoke to these guys at TRM Labs. So they're one of these Blockchain intelligence companies and a lot of people that work there used to work at the treasury and what they said to me was, yeah, Cryptocurrency has enabled ransomware but to track down that ransom payment would have taken, you know, if we were dealing with fiat currency would have taken us years to get to that one bank account belonging to that one front company in the Seychelles. And now thanks to Blockchain, we can track the movement of those funds in real time. And you know what, you know, these payments are not as anonymous as people think like we still can use our old hacking ways and zero days and you know, old school intelligence methods to find out who owns that private wallet and how to get to it. So it's a, it's a curse in some ways and that it's an enabler but it's also a blessing. And they said that same thing to me that I just said to you. They said we've never shut down a promising new technology because it introduced risk. We just figured out how to manage that risk. </s>

<s>[INST] is it possible? I apologize. This is a really dumb question. But is it possible to that approved will come out that P equals NP but an algorithm that makes P equals NP is impossible to find. [/INST] Is </s><s>[INST] that like crazy? [/INST] Okay, well, well if P equals NP it would mean that there is such an algorithm that </s><s>[INST] it exists. [/INST] But um you know, it would it would it would mean that it exists now, you know in practice. Normally the way that we would prove anything like that would be by finding the album. But there is such a thing as a non constructive proof that an algorithm exists. You know, this is really only reared its head I think a few times in the history of our field right? But you know it is, it is theoretically possible that that such a thing could happen. But you know, there are so even here, there are some amusing observations that one could make. So there is this famous observation of Leonid Levin who is, you know, one of the original discoverers of nP completeness right? And he said, well consider the following algorithm that like I I guarantee will solve the Np problems efficiently just as provided that P equals Np Okay, here is what it does. It just runs, you know, it enumerates every possible algorithm in a gigantic infinite list, right? From like in like alphabetical order, right? You know, and many of them maybe won't even compile So we just ignore those. Okay. But now we just, you know, run the first algorithm, then we run the second algorithm, we run the first one a little bit more, then we run the first three algorithms for awhile within the first four for a while. This is called dovetailing by the way. This is a known trick and um theoretical computer science. Okay. But we do it in such a way that, you know, whatever is the algorithm out there in in uh in our list that solves np complete, you know, the np problems efficiently will eventually hit that one. Right. And now the key is that whenever we hit that one, you know, it was, you know, by assumption it has to solve the problem has to find a solution and once it claims to find a solution and we can check that ourselves. Right. Because they're these are problems then we can check it. Now, this is utterly impractical. All right. You know, you have to do this enormous exhaustive search among all the algorithms but from a certain theoretical standpoint, that is merely a constant pre factor. Right? That's merely merely a multiplier of your running time. So there are tricks like that one can do to say that in some sense, the algorithm would have to be constructive but you know in in in the in the human sense, you know it is possible that you know, it's conceivable that one could prove such a thing via non constructive method. Is that likely? I don't think so. Not not personally. </s><s>[INST] So that's P. And and P but the complexities is full of wonderful [/INST] creatures with </s><s>[INST] About 500 of them. 500. So how do you get uh Yeah well [/INST] how do you get more? Yeah. Well I mean I mean just for starters there is everything that we could do with a conventional computer with a polynomial amount of memory. Okay. But possibly an exponential amount of time because we get to reuse the same memory over and over again. Okay. That is called peace space. Okay. And that's actually a we think an even larger class than Np Okay, well P is contained in Np which is contained in peace space and we think that those containment are strict </s><s>[INST] and the constraint there is on the memory the memory has to grow with polynomial with the size of the That's [/INST] right. That's right. But in peace space we now have interesting things that were not in np like as a as a famous example, you know from a given position in chess, you know does white or black have the win? Let's say assuming provided that the game lasts only for a reasonable number of moves. Okay Or or likewise for go okay. And and you know, even for the generalizations of these games to arbitrary sized boards Because with an eight x 8 board, you could say that's just a constant sized problem. You just you know, in principle you just solve it and know of one time. But so we really mean the the generalizations of of, you know, games to a arbitrary sized boards here or another thing in peace space would be uh like I give you some really hard um constraint satisfaction problem like, you know, you know, traveling salesperson or uh you know, packing boxes into the trunk of your car or something like that. And I ask not just is there a solution which would be an np problem. But I ask how many solutions are there? Okay. That count the number of valid solutions that that that actually gives those problems lie in a complexity class called Sharpie. Or like it looks like hashtag like hashtag P. Okay, which sits between N. P and P. Space. Um There's all the problems that you can do in exponential time. Okay. That's called exp so um And by the way it was proven in the 60s that X is larger than pigs. Okay, so we know that much. We know that there are problems that are solvable in exponential time that are not solvable in polynomial time. Okay. In fact we even know we know that there are problems that are solvable and in cube time that are not solvable and and squared time </s><s>[INST] and that those don't help us with a controversy between P. [/INST] And unfortunately it seems not. Or certainly not yet. Right. The the the the techniques that we use to establish those things, they're very very related to help tour improve the unsolvable Itty of the halting problem. But they seem to break down when we're comparing two different resources like time versus space or like, you know, P versus np. Okay. But you know, I mean there's there's what you can do with a randomized algorithm, right? That can sometimes, you know with some has some probability of making a mistake that's called B pp bounded our probabilistic polynomial time. And then of course there's one that's very close to my own heart. What you can efficiently do do in polynomial time. Using a quantum computer. Okay. And that's called B QP. Right. And so you know what's understood </s>

<s>[INST] let me ask you a difficult question because [/INST] as opposed to the easy ones that you've been asking so far? </s><s>[INST] Well dostoyevsky is always just to warm up. Um so if death, if if if death every single day is the way to progress through life, you have become quite famous, [/INST] death and hell, </s><s>[INST] Death and hell, yeah. [/INST] Yeah, because you don't want to forget the hell part. </s><s>[INST] Uh Do you worry that your fame traps you into the person that you were [/INST] before </s><s>[INST] Elvis came? [/INST] An Elvis impersonator by the time he died? </s><s>[INST] Yeah. Do you fear that you have become a Jordan Peterson impersonator that do you fear of in some part becoming the famous suit wearing brilliant Jordan peter this the certainty in the pursuit of truth always right. [/INST] I think I worry about it more than anything else. I hope, I hope I do. I better </s><s>[INST] has fame to some degree when you look at yourself in the mirror, in the quiet of your mind, has it corrupted you? [/INST] No doubt in some regard. I mean it's a very difficult thing to avoid, you know, because things change around you. People are much more likely to do what you ask for example. Right? And so that's a danger because one of the things that keeps you dying properly is that people push back against you optimally. This is why so many celebrities spiral out of control, especially the tyrannical types that say run countries everyone around them stop saying, yeah you're you're you're deviating a little bit there. They laugh at all their jokes, they open all the doors, they always want something from them. The red carpets always roll rolled out. It's like well you think would not be lovely. It's well not if the red carpet is rolled out to you while you're on your way to perdition, that's not a good deal. You just get there more efficiently. And so one of the things that I've tried to learn to manages to get have people around me all the time who are critics who are saying, yeah I could have done that better and you're a little too harsh there and you're alienating people unnecessarily there and you should have done some more background work there. And, and I think the responsibility attendant upon that increases as your influence increases. And that's, that's a, as your influence increases, then that becomes a lot of responsibility. So, you know, and then maybe have an off day and well one, here's an example. I've been writing some columns lately about things that perturb me like the forthcoming famine for example. And it's hard to take those um, problems on, it's difficult to take those problems on in a serious matter. And it's frightening and it would be easier just to go up to the cottage with my wife and go out on the lake and watch the sunset. And so I'm tempted to draw on anger as a motivating energy to help me overcome the resistance to doing this. But then that makes me more harsh and judgmental in my tone. When I'm reading such things, for example, on Youtube then might be optimal. Now I've had debates about with people about that because I have friends who say no, if you're calling out the environmental, environmentalist, globalists who are harassing the dutch farmers, then a little anger is just the ticket. But then others say, well, you know, you don't want to be too harsh because you alienate people who would otherwise listen to you. It's like that's a hard balance to get right. </s><s>[INST] But also maybe anger hardens your mind to where you don't notice the subtle quiet beauty of the world, The quiet love that's always there, that permeates everything. Sometimes you can become deeply cynical about the world if it's the Nietzsche thing, battle not with monsters, unless you become a monster. And if you gaze into the abyss, the abyss gazes also into you. [/INST] But I would say bring it on, </s><s>[INST] right? [/INST] Because I also say knowing that he's absolutely right. But if you gaze into the abyss long enough, you see the light not the darkness. </s><s>[INST] Are you sure about [/INST] that? I'm betting my life on it. </s><s>[INST] That's a heck of a bet [/INST] because </s><s>[INST] it might distort your mind to where all you see [/INST] is a this </s><s>[INST] is a business, is the evil in this world [/INST] that I would say you haven't looked long enough, you know, that's back to the swords, the flaming swords. It's like so I said, the whole story of christ was prefigured in that image. It's like the story of christ psychologically is radical acceptance of the worst possible tragedy. That's what it means. That's what the crucifix means psychologically, it's like gaze upon that, which you are most afraid of. But that story doesn't end there because in in the in the story christ goes through death into hell. So death isn't enough. The abyss, the abyss of innocent death is not sufficient to produce redemption. It has to be a voluntary journey to hell and maybe that's true for everyone and that's like there is no more terrifying idea than that by definition. And so then well, do you gaze upon that? Well, yeah, who knows, who knows? </s><s>[INST] How often do you gaze upon death your own? How often do you remember remind yourself that this right ends [/INST] personally </s><s>[INST] personally [/INST] all the time? </s><s>[INST] Because you as a as a deep thinker and philosopher, it's easy to start philosophizing and forgetting that you're you might die to [/INST] the Angel of Death sits on every word. How's that? </s><s>[INST] How often do you actually consciously [/INST] all the time? </s><s>[INST] Uh notice the angel [/INST] all the time. I think it's one of the things that made me peculiar when I was in graduate school, you know, I I thought about I was I had the thought of death in my mind all the time. And I noticed that many of the people that I was with, these are people I admired. Fine, they that wasn't part of their character, but it was definitely part of mine. I'd wake up every morning, this happened for years, think time short, get at it time short, get at it. There's things to do. And so that was always there still there and still there with I would say and unbearable in some sense. Are </s>

<s>[INST] Yeah. The we'll create conflicts of other sorts that lead to less human suffering than wars do like it we'll just start playing Diablo 456 and because you die in video games. So maybe we'll get some of the inkling of scarcity through the activities we partake in as opposed to our own body dying. I mean I feel shitty when I uh like you can remember in Diablo three you can play in hardcore mode where if you die in the game, your character is dead. Maybe you will get [/INST] the richness </s><s>[INST] of like that we currently get from life by having like little artificial versions of ourselves that die [/INST] interestingly enough as I have just like personally it spent more time in this world. I started realizing that you know there is a concept of like real fighting finite nous that still like exists and it might even still be a thing that provides meaning that doesn't require anyone to actually die. Like for example like how many people from middle school or even high school of yours? Like do you still talk to regularly? </s><s>[INST] I'm happy to be close friends with like four or 5 of them. [/INST] Okay. Like in my case the answer is zero for middle school into for high school, right? Exactly. You drop right? And so like there's a lot of these just like relationships that end up being very finite. Um a person changes There. I feel like a burst of changes enough of their worldview after 25 years. Was there even a study about this? Something like A person and themselves 25 years later about as different as like two different people or something like this. So yeah, I mean just like you can have conflict without bloodshed. I think you know you you can have a finite nous and even you know the necessary sort sorrows of a finite nous that give meaning without like literally any anyone having in their life. </s><s>[INST] And hopefully if we do extend our life will figure out ways to extend the period of time where there's newer neuro plasticity to or we could change our world views continually throughout that time. So you know these different phases of life. I thought it would be fun to hear you speak a little Russian cocktail russki corny agree tibia [/INST] the interior stuff up was </s><s>[INST] because [/INST] um because because uh yeah, cook them. Mm Of course that's what they're doing like them. You know the market reacted regularity of the Blockchain uh industry and like the cactus material. That was the toast to uh huh and McEwen like that choose to watch the time vortex. But uh no Fallujah category whiskey them. Yes. Uh um you know yeah. You think </s><s>[INST] there's uh so for people who don't speak Russian that metallic said that there's um that there is something to the spirit of the people that are Russian that are working in the Cryptocurrency world that is a little bit different and it's something that uh that connects to some kind of aspect of your own self, some kind of roots there. It's kind of interesting do you think that there's um does it make you sad that there's these two different worlds that are uh sort of in part disconnected by language? And I'm sure the same could be the case with china and other parts of the world or the language um slows the transmission of the beauty of the culture in a certain kind of way where you can't truly collaborate. Like you can all speak english, you're collaborating and maybe a technical level, but you're not collaborating on the level [/INST] of like some deep </s><s>[INST] human connection. Do you see that being able to speak both languages? [/INST] There's definitely benefits I think to be able to like speak multiple languages. And like once you can write like you you discover that given your mindset changes while you're in speaking in one language versus the other. Like people have told me this like when I speak Russian, I sound more like I guess like to the point and pragmatic when I speak chinese, I sound more cute when I speak english, I'm something else. Um Yes, uh there's definitely like a richness that you're missing if you're only like in one of these language bubbles. But you know, I guess the arguments on the other side would be that you know, if everyone spoke the same language then like there would just be one bubble. But this is the challenge, I think like uh there are actually benefits to having cultural diversity and you definitely don't want the entire world to be too conformist. Yeah. Well one of the interesting things about crypto is that it's just a culture that actually like manages to uh somehow, you know, have its uniqueness and present and even preserve its independence from all of all of these surrounding countries despite being embedded in all of them. </s><s>[INST] So it spans outside the geographic boundaries and language in some ways does as well. And in the way these cultures, these bubbles are created, I mean they overlap in interesting ways, It's almost like a hierarchy and the same is the case of the crypto world, there's uh there's communities associated with these cryptocurrencies, these communities within those communities and it's [/INST] yeah, I think like, you know, it's definitely sad whenever these groups are fighting each other um Yeah, like it's definitely good for them too, like if people can cooperate more. Um but you know, at the same time, like, just having, like groups of people that have, you know, different kinds of life experiences, like, you know, there's definitely something to benefit from that. </s>

<s>[INST] if we expand it out to meet them. So we're looking at a grab the aliens model 3D sim, right? What's this, that's the actual name of the video. What, by the time we get to 13.8 billion years, the fun begins. Okay, so this is, we're watching a three dimensional sphere rotating, I presume that's the universe, and then grab the aliens are expanding and filling that universe with all kinds of fun. Pretty soon, it's all full. It's full. So that's how the grab the aliens come in contact, first of all, with other aliens, and then with us humans. The following is a simulation of the grab the aliens model of alien civilizations. Civilizations are born that expand outwards at constant speed. A spherical region of space is shown. By the time we get to 13.8 billion years, this sphere will be about 3000 times as wide as the distance from the Milky Way to Andromeda. Okay, this is fun. It's huge. Okay, it's huge. All right, so why don't we see, we're one little tiny, tiny, tiny, tiny dot in that giant, giant sphere. [/INST] Why don't we see any of the grab the aliens? Depends on how fast they expand. So you could see that if they expanded at the speed of light, you wouldn't see them until they were here. So like out there, if somebody is destroying the universe with a vacuum decay, there's this doomsday scenario where somebody somewhere could change the vacuum of the universe and that would expand at the speed of light and basically destroy everything it hit. But you'd never see that until I got here cause it's expanding at the speed of light. If you're expanding really slow, then you see it from a long way off. So the fact we don't see anything in the sky tells us they're expanding fast, say over a third the speed of light. And that's really, really fast. But that's what you have to believe if we look out and you don't see anything. Now you might say, well, maybe I just don't want to believe this whole model. Why should I believe this whole model at all? And our best evidence why you should believe this model is our early date. We are right now and almost 14 million years into the universe on a planet around a star that's roughly 5 billion years old, but the average star out there will last roughly 5 trillion years, that is a thousand times longer. And remember that power law, it says that the chance of advanced life appearing on a planet goes as the power of sixth of the time. So if a planet lasts a thousand times longer, then the chance of it appearing on that planet, if everything would stay empty at least is a 1000 to the sixth power or 10 to the 18. So, enormous, overwhelming chance that if the universe would just stay set and empty and waiting for advanced life to appear, when it would appear would be way at the end of all these planet lifetimes. That is the long planets near the end of the lifetime, trillions of years into the future. But we're really early compared to that. And our explanation is, at the moment, as you saw in the video, the universe is filling up in roughly a billion years. It'll all be full. And at that point, it's too late for advanced life to show up. So, you had to show up now before that deadline. </s><s>[INST] Okay. Can we break that apart a little bit? Okay. Or linger on some of the things you said. So, with the power law, the things we've done on Earth, the model you have says that it's [/INST] very unlikely, like we're lucky SOBs. Is that mathematically correct to say? We're crazy early, that is. When early means like... </s><s>[INST] In the history of the universe. In the history of the... Okay. So, given this model, how do we make sense of that? If we're super... Can we just be the lucky ones? [/INST] Well, 10 to the 18 lucky, you know, how lucky do you feel? So, you know, that's pretty lucky, right? You know, 10 to the 18 is a billion billion. </s><s>[INST] So, then, if you were just being honest and humble, that that means... What does that mean? [/INST] It means one of the assumptions that calculated this crazy early must be wrong. That's what it means. So, the key assumption we suggest is that the universe would stay empty. So, most life would appear like a thousand times longer later than now if everything would stay empty waiting for it to appear. What is non-empty? So, the gravity aliens are filling the universe right now, roughly at the moment, they've filled half of the universe and they've changed it. And when they fill everything, it's too late for stuff like us to appear. But wait, hold on a second. </s><s>[INST] That's how... Did anyone help us get lucky? [/INST] If it's so difficult, what... How do... So, it's like cancer, right? There's all these cells, each of which randomly does or doesn't get cancer, and eventually some cell gets cancer and, you know, we were one of those. </s><s>[INST] But hold on a second. Okay. But we got it early. [/INST] Early compared to the prediction with an assumption that's wrong. That's... So, that's how we do a lot of, you know, theoretical analysis. </s><s>[INST] You have a model that makes a prediction that's wrong, then that helps you reject that model. Okay. Let's try to understand exactly where the wrong is, so the assumption is that the universe is empty. Stays empty. [/INST] Stays empty. And waits until this advanced life appears in trillions of years. That is, if the universe would just stay empty, if there was just, you know, nobody else out there, then when you should expect advanced life to appear, if you're the only one in the universe, when should you expect to appear? </s>

<s>[INST] you just briefly, because you used this term a lot and be nice to try to get a little more color to it, which is interception and extra reception. Uh what are we exactly talking about? So like what's included in each category? And how much overlap is there [/INST] into reception? Would be uh an awareness of anything that's within the confines or on the surface of my skin that I'm sensing </s><s>[INST] literally physiological, [/INST] physiological, like within the boundaries of my skin. And probably touch to the skin as well. Extra reception would be perception of anything that's X. Beyond the reach of my skin. So that that bottle of water um a sent um a sound although and this can change dramatically actually if you have headphones in you tend to hear things in your head if as opposed to a speaker in the room, there's actually the basis of ventriloquism. So there are beautiful experiments done by Greg reckon zone of at UC Davis looking at how auditory and visual cues are matched and we have an array of speakers and you can this will become obvious as I say it. But you know obviously the ventriloquist doesn't throw their voice, what they do is they direct your vision to a particular location and you think the sound is coming from that location. And there are beautiful experiments that Greg and his colleagues have done where they suddenly introduce an auditory visual mismatch. And it freaks people out because you can actually make it seem from a perception standpoint as if the sound arrived from the corner of the room and hit you like physically and people will recoil. And so sounds aren't getting thrown across the room, they're still coming from the defined location, an array of speakers. But this is the way the brain creates these internal representations. And again, not to I don't want to go down a rabbit hole, but um I think as much as I'm sure the listeners appreciate this but you know, everything in the brain is an abstraction, right? I mean they're they're the sensory apparatus, there are the eyes and ears and nose and skin and tasting all that are taking information and with interception. Taking information from sensors inside the body. The enteric nervous system for the gut. I've got sensory neurons that integrate my liver um etcetera. Taking all that. And the brain is abstracting that in the same way that if I took a picture of your face and I handed it to you and I'd say that's you you'd say yeah that's me. But if I were an abstract artist I'd be doing a little bit more of what the brain does. Where if I took a pad and paper, maybe I could do this because I'm a terrible artist and I could just mix it up. And let's say I would make your eyes like water bottles but I flip them upside down and I'd start assigning fruits and objects to the different features of your face. And I showed you I say lex that's you say well that's not me. And I'd say no but that's my abstraction of you. But that's what the brain does. The space time relationship of the neurons that fire that encode your face have no resemblance to your face. Right? And I think people don't really I don't know if people have fully internalized that but the day that I and I'm not sure I fully internalize that because it's weird to think about. But all neurons can do is fire in space and in time. Different neurons in different sequences perhaps with different intensities. It's not clear the action potential is all or none. Although people, neuroscientists don't like to talk about that, even though it's been published in nature a couple times, the action potential for a given neuron doesn't always have the exact same waveform people. It's in all the textbooks, but you can modify that way for </s><s>[INST] Well, I mean, there's a lot of fascinating stuff with with neuroscience about the fuzziness of all the uh of the transfer of information from neuron to neuron. I mean, we certainly touch upon it every time. We had all tried to think about the difference between artificial neural networks and biological neural networks. But can we maybe linger a little bit on this uh on the circuitry that you're getting at? So the brain is just a bunch of stuff firing and it forms abstractions that are fascinating and beautiful, like layers upon, layers upon layers of abstraction. And I think it just like when you're programming, I'm programming in python, it's uh it's all inspiring to think that underneath it all, it ends up being zeros and ones and the computer doesn't know about no stupid python or windows or Linux exit? It only knows about the zeros and ones in the same way with the brain. Is there something interesting to you are fundamental to you about the circuitry of the brain that allows for the magic that's in our mind to emerge? How much do we understand? I mean, maybe even focusing on the vision system. Is there something specific about the structure of the vision system, the circuitry of it that uh allows for the complexity of the vision system to emerge? Or is it all just a complete chaotic mess that we don't understand? [/INST] It's definitely not all a chaotic mess that we don't understand if we're talking about vision and that's not because I'm a vision scientist, ballistic division division. Well, because in the beauty of the visual system, the reason David Huebel and torn some weasel on the Nobel prize. It was because they were brilliant and forward thinking and adventurous and all that good stuff. But the reason that the visual system is such a great model for addressing these kinds of questions and other systems are hard is we can control the stimulate, we can adjust spatial frequency. How fine the grading czar, thick grading thin greetings, we can just temporal frequency, how fast things are moving. We can use cohen isolating stimuli we can use. There's so many things that you can do in a controlled way. Whereas if we're talking about cognitive encoding, like they, you know, encoding the space of concepts or something, you know, I you know, I like you if I may our am drawn to the big questions in neuroscience but I confess in part because of some good advice I got early in my career and in part because I'm not perhaps smart enough to go after the really high level stuff. I also like to address things that are tractable and I want, you know, we need to we need to address what we can stand to make some ground on at a given </s>

<s>[INST] something beautiful about martial arts. Like exactly as you said, is the coach like in wrestling and at least collegiate, like high level wrestling, it's like there's a dictatorship aspect to a coach that is very important to have like this, this ridiculous sometimes nature of like master and so on and bowing all these traditions. There's something, it seems ridiculous from the outside perhaps, but there's something really powerful to that because that process of you said, why not of letting go? The leap of faith requires you to believe that the coach has your best interest in mind and just give yourself over to there ideas of how, how you should grow and that's an interesting thing. I mean I've never been able to really see coaches I've had as human. They're always, you always, it's like a father figure or like you always put them in this position of power and I think that's I think at least for me it's been a very, it's been a very useful way to see the coach because it allows you to not think and like go and really allow yourself to grow and emotionally deal with all the beatings. [/INST] They'll push you were passed oftentimes where you would have stopped yourself, right. Which is great. And hopefully they know if they're paying attention and there's still a person they can make mistakes, they'll push you further than you would have gone but not so far that it's not facilitated. Right? That's something that I can say like for as a hobby. Um the head coach at Tristar, my head coach for mm a Kenny florian on my other head coaches from May have both been phenomenal influences paul Shriner who is the uh, one of the assistants, Marcello Garcia's Academy um coach me and you get to for a long time, brilliant instructor. They've all been able to do that. And I think what's interesting about all of those guys, they're very sharp but they are very intuitive as well. And I think that for us actually, uh, you know, told me about some of the john wooden said john wooden, the legendary U. C. L. A basketball coach. Just a simple philosophical idea. Just he said some people's life is Ebola shit. It needs some whipped cream in it. Some people's life is a bowl of whipped cream needs a little bit of shipping it just to balance it out and it's an interesting thing coaching everyone the same way doesn't work. You know, that's I think the difference being a coach and an instructor and a lot of times people think they want to coach, but they really want instructor, I'm like, hey, let's tell me what to do, not how to do it. And then other times people think they want, you know, an instructor and they really want to coach and I'm like, man, this guy is just giving me information, coaches so much more than an instructor and that's a huge leap and that's something that I think that people need to understand when they're going into martial arts and I understand, I can totally grasp why they don't, because how would they know? But I think about this a lot like me giving you $150 for a month, which is not nothing that's for sure that does not, that pays for instructor really coach is a relationship that gets developed because you can imagine like just the amount of emotional investment and time thinking away from, from like elections in here anymore, what can I do to help and what does he need? Like that's, that's serious and that's the difference between, that's, that's often times the difference that, that getting, getting over the hump in various situations. So it's a, it's an interesting, you know, bargain that's being made, like commitment by the, by the instructor who becomes a coach, commitment by the student, you know, like there's a financial transaction, there's a lot of things going on there, but I feel very fortunate to have had not just instructors in my time, but coaches and that means sometimes we butted heads and sometimes I look back and I think I was right and other times look back on my own now, they were definitely right. But there was always the trust, um, with the exception of, of one time that I feel that trust was greatly betrayed, um, that rightly or wrongly whether mistakes, mistakes will be made, but everyone is attempting to do, do the right thing under no circumstances what I intentionally do anything militias, you know, versus hey, I might have done, I'm gonna burn your house down, but you can be darn sure it wasn't on purpose. And I think that as long as there's that mutual understanding and mutual belief of goodwill, which again doesn't just magic up out of nowhere. I, I understand. I think that that's when then great things can happen. And I look at all the athletes that I know, you know, the guys and girls that I've watched become fantastic in various places? Almost invariably it never happened alone. </s>

<s>[INST] josh. Thanks for talking [/INST] today. My pleasure. Mhm. </s><s>[INST] Thanks for listening to this conversation with josh Barnett and thank you to our sponsors munk pack low carb, snacks, element, electrolyte, drink eight, sleep, self cooling mattress and rev transcription and capturing service, click the sponsor links to get a discount and to support this podcast And now let me leave you with some words from Sun Zoo in the art of war. The Supreme art of war is to subdue the enemy without fighting. Thank you for listening and hope to see you next time [/INST] </s>

<s>[INST] Do you have thoughts about the current war in Ukraine? Maybe from a military perspective, maybe from the Air force perspective. So I can just mention a few things, there's the Bayraktar drones that are being used, their unmanned, I think they have capability to be autonomous, but they're usually remotely controlled. They're used for reconnaissance, but they're also used by the Ukraine side for reconnaissance and I think um, also to destroy different technology tanks and so on different targets like this. So there's also on the, on the Russian side, the oil intent, there's the fighter jets MIG 29, the Ukraine side, Su 25 in the Russian side, is there anything kind of stands out to you about this particular aspects of what this war looks like that's unique to what you've experienced? [/INST] Maybe not unique, but it's just been absolutely incredible to see the footage, you know, I mean we're watching war on twitter, you know, essentially, and to see, you know, these aircraft flying down low spitting flares out, getting shot down, you know, it's incredible to to see this happening, you know, live for everyone to see. Um, so that's just kind of a quick meta comment. But as far as the actual, you know, I think these small form factor U A V s where they're just like strapping weapon to it and flying over and trying to drop it at the right time or any of these type of commercial applications of technology into this ad hoc warfare area is incredibly interesting because it shows, you know, how useful that technology can be outside of the military, right? Like these, like, especially like D G I right? Like there's obviously a lot of technology in there is being leveraged for other capabilities within, you know, PLC military or at least we would assume, um, what happens if that is more widespread, right? Like what if we were creating our own drones and they were being used against us, would we want to have some type of kill switch or something like that. Right? So what I think government is gonna have to consider like all these tools that are gonna be easily available to just any person could be turned into a tool of war. How do we stop that from being turned against us? You know, especially as we look at, you know, 10 years from now when we have a large number of autonomous U. A. V. S. Delivering packages and doing everything else over our country and any one of those could be potentially a weapon if we don't have the proper security. </s><s>[INST] Well, there's we're now in texas and texas values as guns and seize guns as among other things, a protector of individual freedom. You could see a future perhaps where and I certainly have experienced this in the empowering nature of this in Ukraine, where you can put the fight for independence into your own hands by literally strapping explosives to G. I drones that you purchase on your own salary. I mean that one of the interesting things about the voluntary army in Ukraine is that they're basically using their own salary to buy the ammunition to fight for their independence. That's a very kind of ideal, that sort of uh people speak about when they speak about the Second Amendment in this country, that it's interesting to see the advanced technology version of that, especially in Ukraine sort of using uh computer vision technology for uh surveillance and reconnaissance to try to um and and integrate that information to discover the targets and all that kind of stuff um to put that in the hands of civilians. It's fascinating to see, to sort of fight for their independence. You could say that to fight against authoritarian regime of your own government, all that kind of stuff. [/INST] It shows you how complicated the worst base in the future is going to be, you know, invading a land like that, where people have, you know, that many different types of resources absolutely changed warfare. </s><s>[INST] I mean, hopefully that creates a disincentive to start war, to go to war with a yeah, sort of it changes the nature of Guerilla warfare, [/INST] you know, I don't think Putin was expecting to be in that engagement quite as long as he has, of course. Um but it can show you how you can get caught up. You know, if if if land wars turn into an inescapable quagmire each time due to the complications around the the society's ability to access interesting tools, you know, it could be, you know, it could be a huge de motivator for aggression. Well, </s><s>[INST] let me ask you about this, do you think there will always be war in the world? Is this just a part of human nature? I think [/INST] so, I think I think it is until we, until we move past resource limitation, there's always going to be at least that one particular cause of conflict. And then we can also consider all our psychological lizard brain emotions that cause us to act out. Although, you know, hopefully we have enough things in place to stop that from rising to the level of war. But you know, we have our own biology or psychology and evolution to combat. Um, and then, but there are pragmatic reasons to exert violence sometimes unfortunately. And that one of those cases could be resource limitations. And so your question was, do I think there will be war in this world. My unfortunate answer is perhaps yes, but once there's more than one world and we're less resource constrained, then perhaps it will be a valve of source for that. </s>

<s>[INST] Yeah, it's kind of interesting the history of Cryptocurrency has this um tension of really good ideas that are hard to implement, so they take longer to implement and ideas they that are not as good but are faster to implement. This is like the story of like You have like Javascript, I basically took over the world because it was quick to implement within 10 days and then like later kept fixing itself. I don't know what to make of, that sort of from an engineering perspective, I'm more and more becoming comfortable and accepting the fact that our whole world will run a technology that's not as good as it could have been just because the crappy solution is faster to implement in the sticks, what do you make of that tension? [/INST] I think the compromise that we've been taking within ethereum is like when we have to take the crappy solution, we look for crappy solutions that are forward compatible with becoming good over time, right? Like when you build the quick and dirty thing, like you would still already have ideas in your head about you know what the more complete thing with all the security features at all and would look like right, even if it </s><s>[INST] requires a hard fork [/INST] um yes, like even so like for example we're starting right, like well yeah, I think it's likely that the first version of shortage that comes out like it's not going to have, you know, zK snarks India availability sampling for example, but we know what these technologies are, we can feel like we, you know have wrapped our heads around them and so we know how to build a system where we can put all the pieces in place so that it becomes very easy to bolt those components on in the future. Uh so like if you do things that way right then at the beginning you can have your system that has the functionality but say has less security or like less sustainability or less of something else. Um but then over time, like it's designed in such a way that it has this easy on on ramp to adding those things. Right? And if you don't think explicitly about like being future compatible, then you do often end up with the a quick and dirty solution that backs you into a corner and there are definitely cases where like I think the ethereum ecosystem has suffered from that and we have had to like expand pretty significant effort on, for example, removing features that we didn't realize that we actually can't sustain. Like one big example is just increasing the gas costs. So like making some operations more expensive when they because they should be expensive because they actually take a lot of time in the process. Yeah, so that's you know, making like think something's more expensive, kind of like taking some functionality away. So if you can like be cognizant of where you're likely going into the future and if you don't know, like even be cognizant of both, the most likely path that you'll take in the future and coming like thinking about your roadmap and coming up with the road map where you know that like if you want to do either of those things, then you have a queen path toward it. Like that's probably the best kind of practical way to get the best of worth worlds that we have. </s><s>[INST] Okay, let's talk about this uh wonderful process of [/INST] merging. </s><s>[INST] Okay, so there's the main net which is the theory in 1.0 chain or the chip, what should we say? The chain that uses proof of work as a consensus mechanism and then there is, what is it called? The beacon chain that uses the The proof of stake mechanism and I believe the beacon has been deployed successfully is working. So that was in December 2020. Uh there's a bunch of questions around that, that's fascinating as well, but I think the most fascinating question is um it's about merging those two, When do the two chains one that's put for work, one that's proof of stake merge and what are the most difficult parts of this process? [/INST] Right? So as you said, right, the way that we have set up this proof of state transition is that at first the proof of stake chain just launches on its own right, and this is the thing that happened in december and the proof of stake chain has been running for close to six months now. Um I mean by the time people watch this, it might actually be six months, um but it isn't actually coming to consensus on anything except for itself. Right? So the idea behind that is to just give the proof of stake chain time to mature time for people to build the ecosystem around that time to make sure that there aren't any bugs. Um and just like prove to the community that no proof of stake actually is real and it's uh and a full transition is realistic because, you know, the thing that you're transitioning to already exists and already works. And then at some point in the future you have this event called the merge, where you basically take the activity that's being done inside of the proof of work chain and you actually move it over into the proof of stake chain, so you get rid of the proof of work side completely. Uh so the way that the merge will work is um it's definitely gone through a few different iterations, like the earlier versions of this actually required more work for users and more work for clients. It was much more like, oh, there's this new chain, there's this old chain and then everyone has to migrate from the old change in the new chain. And then at some point we'll forget about the old Chin, the new version is designed to be much more seamless for users. Right? So basically what actually happens is that the old chain basically becomes embedded inside the new chain. Right? So starting from the merge transition block, every proof of stake chain block is going to contain a block of the what we consider now, what we consider to be the ethereum chain today, but we'll call it the execution chain and then at the same time to create one of these blocks, you're not going to need proof of work anymore, right? So basically at the same time you both get rid of the proof of work requirements for one of these blocks to be valid, but instead you require these blocks to be embedded inside of the proof of stake blocks. Right? So you basically have like a chain inside a chain. And this is from an architecture perspective, it's, you know, you might think it's a little bit suboptimal, but it actually has some nice properties and makes it easier to kind of think about the consensus and think about the what we call the execution layer, like transactions and contracts kind of separately and upgrade them separately. Um And it also just means that the upgrade process is extremely seamless, right? Because from the point of view of a client that's following the chain, you basically have to update nothing right? You're still following the same chain and follows the same rules. Except instead of checking proof of work, you'll switch to checking that these blocks are embedded inside of blocks of the proofs each other. So </s>

<s>[INST] The idea of symbolic discourse language. Can you try to define the scope of what of what it is? [/INST] So, we're having a conversation, it's a natural language. Can we have a representation of the sort of actionable parts of that conversation in a precise computable form, so that a computer could go do it </s><s>[INST] and not just contracts, but really sort of some of the things we think of as common sense essentially, even just like basic notions of human life. [/INST] Well, I mean things like, you know, I am, I'm getting hungry and want to eat something. Right? That that's something we don't have a representation, you know, in Wolfram language right now, If I was like, I'm eating blueberries and raspberries and things like that and I'm eating this amount of them. We know all about those kinds of fruits and plants and nutrition content and all that kind of thing. But the I want to eat them. Part of it is not covered yet. Um and you </s><s>[INST] know, you need to do that in order to have a complete symbolic discourse language to be able to have a natural language conversation [/INST] right, right to to be able to express the kinds of things that say, you know, if it's a legal contract, it's, you know, the party's desire to have this and that. Um and that's, you know, that's the thing, like I want to eat a raspberry or something that </s><s>[INST] it isn't that isn't this just like you said, it's centuries old, this dream, but it's also the more near term, the dream of Touring and four million a turing test. Yes. So wow, do you hope, do you think that's the ultimate test of creating something special because we [/INST] said, I tell you, I I think my special look if if the test is does it walk and talk like a human? Well that's just the talking like a human. But uh the answer is it's an okay test if you say is it a test of intelligence? You know, people have attached Wolfram Alpha, the Wolfram Alpha api to, you know, turing test bots and those bots just lose immediately because all you have to do is ask you five questions that you know, are about really obscure weird pieces of knowledge and it's just trot them right out and you say that's not a human, right? It's it's a it's a different thing, it's achieving a different uh </s><s>[INST] right now. But it's I would argue not, I would argue it's not a different thing. It's actually legitimately Wolfram Alpha is legitimately language. Wolfram language I think is legitimately trying to solve the touring the intent of the turing test. [/INST] Perhaps the intent, perhaps the intent. I mean it's actually kind of fun, you know, alan turing had, trying to work out, he thought about taking encyclopedia Britannica and you know, making it computational in some way and he estimated how much work it would be. Um And actually I have to say he was a bit more pessimistic than the reality we did it more efficiently </s><s>[INST] than but to him that represent. So [/INST] I mean he was he was on the monumental task. Yeah right? He was had the same idea. I mean it was, you know, we were able to do it more efficiently because we had a lot, We had layers of automation that he I think hadn't, you know, it's hard to imagine those layers of abstraction um that end up being being built up, </s><s>[INST] but to him it represented like an impossible task essentially. [/INST] Well, he thought it was difficult. He thought it was, you know, maybe if he'd lived another 50 years, he would have been able to do it. I don't know, </s><s>[INST] in the interest of time. Easy questions, don't you? What is intelligence [/INST] you talking? I love the way you say easy questions. </s><s>[INST] You talked about sort of Rule 30 and sell your time and humbling your sense of human beings having a monopoly and intelligence, but in your in retrospect, just looking broadly now with all the things you learn from computation, What is intelligence intelligence arise? [/INST] I don't think there's a bright line of what intelligence is. I think intelligence is at some level, just computation. But for us, intelligence is defined to be computation. That is doing things we care about. And you know, that's yeah, that's a very special definition. It's a very, you know, when you try and try and make it, you know, you try and say, well, intelligence to this is problem solving, it's doing general, this is doing that, this doesn't the other thing, it's it's operating within a human environment type thing. Okay, You know, that's fine. If you say, well, what's intelligence in general? You know, that's I think that question is totally slippery and doesn't really have an answer as soon as you say, what is it in general, it quickly segues into. Uh, this is what this is just computation, so to speak. </s><s>[INST] But in a sea of computation, how many things, if we were to pick randomly is your sense would have the kind of impressive to us humans levels of intelligence, meaning it could do a lot of general things that are useful to us [/INST] humans. Right? Well, according to the principle of computational equivalence, lots of them. I mean, and And, you know, if you ask me just in cellular automata or something, I don't know, it's maybe 1%, a few percent achieve. It varies actually. It's a little bit as you get to slightly more complicated rules, the chance that there'll be enough stuff there to uh, to sort of reach this kind of equivalence point. It makes it maybe 10, of all of them. So it's a it's very disappointing really. I mean, it's kind of like, you know, we think there's this whole long sort of biological evolution, uh, kind of intellectual evolution that our cultural evolution that our species has gone through. It's kind of disappointing to think that that hasn't achieved more, but it has achieved something very special to us. It just hasn't achieved something generally more so to speak. </s>

<s>[INST] what is it about those human decisions you have to make, Is that something you put in towards? Or is that just deep down some instinct that you develop as a pilot over time [/INST] when we, when you train, uh, you know, in aviation is a self cleaning oven. So if you make bad decisions, you're, and the list is long and distinguished of those who have died by making bad decisions. Um, so when you look at what he did or the way we train, because the commercial industry and the navy and the Air Force for all that, we have, what's called, we have emergency procedures that we have to know like the engine's on fire. The first three steps, you just have to know what they are, right. So they know the airline, uh, same type. You know, they go, hey, I know this is, they pulled the book out because the airplanes are designed, they're built to have some time. But there's a point where you have to make a decision and you can't second guess it. So when he decided, I'm putting this in the Hudson river, he couldn't all of a sudden halfway through it go, well, maybe I can get over to that airport. He, he looked, he made a quick assessment. This is that 80% solution where you go, these are not, you know, it's, it's like a multiple choice test when you go, oh my God, I don't really know the answer, but I know A and D. Are wrong. Gone. So the Jersey airport and going back to laguardia gone. So what's my next option? Well, the Hudson River's there. That's probably looking pretty good. Or what is my other one? Can I get a restart on the motors and then if I can get a restart now, can I take it someplace else? He had to make really, really fast decisions. And then once they as they go that 80% solution, you realize all right, I'm going into the Hudson. There's the 80% get the book out. Let's see if we can get in there. Start because if you listen to tapes are trying to get air started. The closer he gets to the water, the more he's going, I'm ditching the airplane. So the original decision to this is my best option right now. This is where I'm going. And you start eliminating anything that could possibly change the events which they tried to do. And then he gets to that last minute says we're going in the water. They changed the plan. They secure the airplane, They do exactly what they're doing. And he does that basically flawless landing on the on the Hudson. But you gotta remember every it's every six months for commercial. They go back and they do research in the airplane in the simulator where they trained to the airplane being broken. You just lost a motor. You just lost another motor. So they go through this extensive training, you know, and all these and it's, you know, you know, we refer to it in the navy is the pain cave where you're going to get in because you know that when you get in for your check, ride in a simulator that the airplane is going to break, you're gonna lose hydraulic and it's sometimes they're a problem like, oh, I just lost this hydraulic system. But I'm having an issue on the other motor. Well, if I shut down this motor and I've got a hydraulic, because there's two hydraulic systems, one on each motor, well, if I've got an issue with the left motor, hydraulic system and my right motor is starting to give me indications do I want to shut the right motor down because that's gonna kill my hydraulic system. That's good. And now I'm flying on a good motor with a bad hydraulic system and without hydraulics, airplane won't fly. So they, it's a really, they're challenging problems that you have to think through in real time. And of course the weather is never good. It's always dark. It's always crappy. You're gonna break out. And I mean, just all this stuff gets compiled on top of you and it's intended to increase the level of stress because when things happen like in sully's case we like to joke, it's going to stem power. You know, where the functional part of your brain shuts down and you are literally on instinct like an animal. Well, if you've trained so much that, that is the instinctive reaction that you're going to have when the main part of your cognitive abilities start to shut down. You're running. That instinct is ingrained so much into you that you know exactly what to do. And that's literally how it happens. </s><s>[INST] So there's no, how do I put it fear of death? Like in Sally's case, do you think he was at all ever thinking about the fact if his decision is wrong, a lot of people are going to die, [/INST] you know, I can't speak for him. But I would say there was so much going on in the cockpit in that time. His, his mindset was probably, I can do this. I'm trained. I'm going to do the procedures. I've practiced this before. I've done these things. And you know, I'm assuming that in his mind set because I never thought about when things were really bad. You know, if you're having problems with the airplane that you know, that I was gonna mort you know, and and planted into the ground, it was always maybe it's an ego thing where you think I can do this, you know what I mean? </s>

<s>[INST] You'll impact people. my little corner of the world, it was disappointing how rare that is. So one of the reasons I'm here in Austin, and one of the reasons my work gravitated towards Elon Musk is because he represents that person for me in the world of technology, in the world of CEO, in the world of business. It was very surprising to me, the more I've learned about the world of tech, how few people live unapologetically, fully, to their potential. I'm sure people, others do that, maybe music and art, I'm not sure. I don't know about those worlds. I do know about the technology world. And it was disappointing to me how many people compromise their integrity in subtle ways at first, but then it becomes a slippery slope and then you- [/INST] Can I say this, there's this great quote, and I always forget if it's Steinbeck or Hemingway, and this applies for money and applies for morality. The quote was, how did you go bankrupt? And he says, two ways, gradually and then suddenly. It's very hard to one day be like, I have no integrity. That doesn't happen. It's very easy if it's like, look, I stole this candy bar. What's the big deal if I steal this thing? Then you steal- People say they're no slippery slopes. They are, and they're big, and they're very slippery, and people slide- And this is the biggest one. And people violate their integrity even without stealing. Just little things about how they treat other people, how they treat themselves, the values they pursue. They don't go after the profession they really wanted to. They compromise with, in ways that they shouldn't with their spouse or with their mothers or whatever. And then they wake up one day with their 30. They look the other way when they seek justice, yep, yep. And this is why people go through a middle age, midlife crisis. Midlife crisis is a crisis where you suddenly realize, I didn't do it, I didn't live up to my standards. didn't live up to my youthful idealism. I compromised and I sold out. But I also would warn you about Silicon Valley. Yeah, I think at the top, people slide. This is the biggest one. They look the other way when they see justice. Very few of them stick to it. And partially it's the political pressure is unbearable. I mean, how would you? How can you? It would require to be a hero and very few of them are. But there are a lot of people who do really well at all kinds of levels in technology who little startups, people. And this is the point Michael was making. You don't have to be the best. You don't have to be a CEO to live to your max and to live with integrity and to live a great life. I know people who, because they joined Amazon or whatever, have just made a life for themselves, an amazing life for themselves, and have done great work at Amazon, let's say, and then have lived a great life because of the opportunity that created for them. So I think there are more good people out there, but yes, one of the saddest things of growing up is, even when you're a teenager and looking at adults and noticing how few of them actually live. I mean, really alive in a sense of living their values and enjoying their life. And you start with your parents and you look across the people. Everybody lives such mediocre lives. And the other thing is they don't have to. That's what people don't appreciate. They don't appreciate, particularly not in the world that we live in today. They're so wealthy </s><s>[INST] and we all have so many opportunities. So by way of advice, what advice would you give to young people to live their life fully? I mean, Michael and I have talked about this, but it bears repeating. So if you look at John Gault, if you look at the highest ideals of a life we could live, [/INST] what advice would you give to a 20-year-old today? 18-year-old, full 18-year-old. Can I say, I don't think, and I think Rand would agree. When Rand was writing John Gault, she says, when you have this character's human perfection, you don't want to get too close. So he's a little bit of a vague character because she was aware that when you're dealing with day to day, it kind of, the shine comes off. I think Roark is a lot better character for a young person. Oh, weird. Yeah, but Roark is all, the entirety of Fountainhead is Roark, so Adrian is the one of several. We barely know John Gault. Yeah, so, but Roark is someone where you could be like, okay. And what Roark also gives young people is- That's in The Fountainhead. The Fountainhead is the strength to persevere. Because when you're young, you're going to have down times. There's going to be times when you're lonely, there's going to be times when you don't have a girlfriend, there's going to be times when you're out of work, and you're thinking holy crap, I'm falling between the cracks, I'm going to accomplish that I'm going to be a failure and he gives them the courage. There's even a scene in the fountainhead, which is this amazing scene. I love that it's not talked about enough where basically Rourke is looking at one of his buildings and this little kid on a bicycle comes up to him and I wrote your own please correct me and he's like who built this and Rourke said I did and the line is you know Rourke didn't realize it but he just gave that kid the courage to face a lifetime and I think that is such a beautiful thing where you can find inspiration in this character don't become needlessly difficult don't start parroting his lines you're not Howard Rourke and he's not a real person but there's aspects of him that you can apply to your life and here's something else I'll give one example because this happened to me when I was working at Goldman Sachs I was doing tech support and my great-grandmother had passed away that year and I promised my grandmother I'd have thanks I've told the story several times I would have thanksgiving dinner with her I was working second shift fort to midnight and we were 24 seven help desk and I got the schedule for the next week and I sold my grandma gonna have lunch with her in Thanksgiving and they had put me down from fort to midnight the day before Wednesday which is my normal shift but then the day shipped the next day and I go to my boss I go I first I was second shift I'm like this Thanksgiving I promised my grandma and they're like well if you could find someone to fill this we'll do it and I I asked everyone, they're like, no. And I said, I'm not coming in. And I, 100%, not even a question, if I asked my grandmother, can we have dinner instead, she would have said yes. But this was one of those moments, maybe this is from my huge ego, where I felt like I was in a movie and I'm making a choice. Am I going to ask grandma? Or am I going to just bend the knee? And I go, I couldn't find anyone. And I go, I'm not coming in. And they go, if you're not coming in, you're fired. And I go, fire me. And they did fire me. And I have no regrets. And because if I compromised, I'd have money in my pocket. But since I didn't compromise, I could look at that story. Rand talks about how man is a being of self-made soul. I could look at that story. And next time, I have a time where it's a tough decision, where there's really pressure. I could be like, you know what? This is the kind of person you are. Stick to it. I'll give one more example. Sorry, Ron. I've given talks on networking and I tell people, I like to use humor because humor is a great way to shortcut the brain and get the truth to them directly. I say, if you know someone is in town, it's their birthday, and they're not doing anything, take them out. And I say, I do this for Rand reasons. I do it selfishly. And the audience laughs. And I go, you're laughing, but I go, the guy who takes people out for their birthday is awesome. That could be you. There's nothing stopping you. You're just not thinking of these terms. What's it going to cost you $30? But for the rest of their life or a few years, that person will remember you and be like, you know what? This person did right by me. And I'll give you a concrete example which changed my life profoundly. Ted Hope, who was the producer of the film, American Splendor, which started my mentor, Harvey Pekar, sent an email to his firm that said, Harvey's in town with nothing to do. If you want to hang out with him, here's your chance. They worked at a film company and I was the only one. I got the email. I wasn't working there from a friend who took him up on it. And as a consequence, Harvey wrote a graphic novel about me, Egon Hubris, which is $250 on eBay now and it moves at that, not too shabby. The point being- Yeah, we barely know Jungkook. You know what? Someone had a movie made about him. Someone is an interesting figure. Take the lunch and stay overtime for an hour. But so many people don't think in those terms and there's so many opportunities for them. So that's the advice I give. And I think it's also good to give advice via anecdote. So not only is the person getting the advice, they are learning why you got to that point. And maybe I'm wrong, but at least they've thought about it. Yeah, I mean, I agree with all of that. And I like the line, Iron Man's line about man as a self-made soul is a creature of self-made soul is huge and it's something most people don't realize. And it's something that modern intellectuals undermine. I mean, even somebody like Sam Harris, when you keep telling people they don't have free will, then you don't have a self-made soul because what is self-made? There is no self, according to Sam, right? He meditates and he sees that he doesn't have a self. So you're undermining the ability of people to take control of their own lives and make the kind of choices that are necessary to create the kind of moral character that is necessary for them to be successful. So I'd encourage people to go read Found Head and Out with Shrugged because put aside the politics, put aside even aspects of the philosophy, focus on these models. These are, How to Walk is a great model for all of us. It's a great story to have in your head, in your mind, when you encounter challenging choices that you might make. And then spend the time, and this is, I don't think I ever did this when I was young. I don't think people do this, but spend the time thinking about what your values really are. What do you love doing? What gets you going? What gets you excited? And, how can I make a living at this? How can I do this and live through this? And then think about what kind of life you want. What kind of, I don't know, what kind of people you want to hang out with. Don't let life just happen to you. Think it through, what kind of people, for example, if you want ambitious, excited, maybe you should move to Silicon Valley, to Austin, Texas, right? If you want to be around Aussie people, maybe you should go to Hollywood. Maybe you should go to New York. I don't know, but think about what kind of life you want to live, what kind of people you want to hang out with, what kind of woman you want to spend your life with, what kind of romantic relationship you want to have. Figure that out and go and do it. Don't sit around. Life is not- Or try and fail. It's okay. You're going to fail. Fake failures. You're going to fail. Oh, failure. Failures. Don't fail. And learn from that failure. And that's another thing. Think about what you're doing, why you're succeeding, why you're failing, and keep improving. working on it because it's not just going to happen like this. Nobody is Francisco to take a character out of Atlas Shrugged who succeeds at everything first try, right? We all need to fail a few times. We all need to, but what have you got to lose? Every second is never going to be back. I mean, these are all cliches, but they're all true cliches. So think, figure out what your values are and try to apply your reason, your rational thought on getting those values. And try to, we talked about early on in the interview. We talked about integrating your emotions with your cognition. I think that's crucial because you don't want to be fighting your emotions as you move towards these things. You don't want your emotions to be barriers to your own success. You want them to be cheerleaders, right, to cheer on when good things happen and to be negative emotions when it's justified that they're negative. So, work on integrating your soul. So, creating your soul, that's, that's the real challenge. And, I'll give one piece of meta advice. When you're young, you're going to be clueless, because you're going to be ignorant, you know the data. Don't ask your dopey friends for advice because they want to be helpful. But the friends want to be helpful. They're as dopey as you, they have uninformed as you. So, they're just going to give you platitudes and you're going to be worse off because now you're going to be confused. Especially with social media. social media. Reach out to people who are older than you, who are accomplished. You'd be surprised how often you've got to send them 20 bucks, buy them dinner, buy their book, whatever it takes. You are getting free, world-class advice for very cheap, and that is really a mechanism for success. And here's something very unpopular and not sexy. This is why people probably unfollow me. Read. Well, you'll tell me why after this. Read, read, read. Because you're not always going to have access to those experts. And I'm not talking about self-help books. I'm not even talking about self-help books. Read the world's literature. I mean, literature presents you with all the different characters. Read Dostoevsky. Read Who Go. Read all these authors that have taken time to really create characters and put them in situations that maybe you will never face those exact situations, but you'll face similar situations. And they play it out for you. You'll see what the consequences are. Great literature is a real tool for building your soul. Great art generally, with literature in particular, because it's more conceptual. </s>

<s>[INST] Right now. We're creating a lot of medical tools and diet tools and all that kind of stuff that's able to extend the capabilities of our body. But they need it needs to know about those signals. It needs to know about the signals the body sends. So it's obvious to me that this is the future of health and medicine and all that kind of stuff. Get special savings for a limited time when you go to Inside Tracker dot com slash lex this is Alex Friedman podcast To support it, please check out our sponsors in the description and now dear friends, here's Michael Levin embryo genesis is the process of building the human body from a single cell. I think it's one of the most incredible things that exists on earth from a single embryo. So how does this process work? Yeah. [/INST] It is it is an incredible process. I think it's maybe the most magical process there is and I think one of the most fundamentally interesting things about it is that it shows that each of us takes the journey from so called just physics to mind, right? Because we all start life as a single quiescent unfertilized oocyte and it's basically a bag of chemicals and you look at that and you say, okay this is chemistry and physics. And then nine months and some years later you have an organism with high level cognition and preferences and and in her life and so on. And what embryo genesis tells us is that that transformation from physics to mind is gradual. It's smooth there is no special place where you know a lightning bolt system now you've gone from from physics to true cognition that doesn't happen. And so we can see in this process that the whole mystery, you know the biggest mystery of the universe, basically how you get mind from matter </s><s>[INST] from just physics in quotes. Yeah. So where's the magic into the thing? How do we get from information coded in D. N. A. And make physical reality out of that information. So [/INST] one of the things that I think is really important if we're gonna bring in D. N. A. Into this picture is to think about the fact that what D. N. A. Encodes is the hardware of life DNA contains the instructions for the kind of micro level hardware that every cell gets to play with. So all the proteins, all the signaling factors, the ion channels. All the cool little pieces of hardware that sells half that's what's in the D. N. A. The rest of it is in so called generic laws and these are laws of mathematics. These are laws of computation. These are laws of of physics of all all all kinds of interesting things that are not directly in the D. N. A. And that that process. You know I think I think the reason that the reason I always put just physics in quotes is because I don't think there is such a thing as just physics. I think that thinking about these things and been categories like this is physics. This is true cognition. This is as if it's only faking. Although these kinds of things. I think that's what gets us in trouble. I think that we really have to understand that it's a continuum. We have to work up the scaling the laws of scaling and we can we can certainly talk about that. There's a lot of really interesting thoughts to be had there. </s><s>[INST] So the physics is deeply integrated with the information. So the D. N. A. Doesn't exist on its own. The D. N. A. Is integrated as in some sense in response to the laws of physics at every scale the laws of the environment exists in [/INST] yeah the environment and also the laws of the universe. I mean the thing about the thing about the D. N. A. Is that it's um once evolution discovers a certain kind of machine that if the if the physical implementation is appropriate, it's sort of uh and this is hard to talk about because we don't have a good vocabulary for this yet. But it's a very um kind of platonic notion that that if the machine is there, it pulls down interesting uh interesting things that you do not have to evolve from scratch because the laws of physics give it to you for free. So just as a as a really stupid example, if you're trying to evolve a particular triangle, you can evolve the first angle and you evolve this second angle. But you don't need to evolve the third, you know what it is already. Now, why do you know that's that's a gift for free from geometry in a particular space. You know what that angle has to be. And if you evolve an ion channel which is ion channels are basically transistors right? The voltage gated current conductance is if you evolve that ion channel you immediately get to use things like truth tables. You get logic functions. You don't have to evolve the logic function. You don't have to evolve. The truth table doesn't have to be in the D. N. A. It's you get it for free, right? And the fact that if you have nand gates you can build anything you want to get that for free. All you have to evolve is that that first step, the first little machine that that that enables you to couple to those laws and those laws of adhesion and and and many other things. And this is all um that interplay between the hardware that's set up by the genetics and the software. That's right. The physiological software that basically does all the computation and the cognition and everything else is a real interplay between the information and the D. N. A. And the laws of physics of computation and so </s>

<s>[INST] Well this is actually something I worry about in terms of long term effects or the cost in terms of longevity. It's very difficult to know how your choices affect your longevity because the impact is down the line, like just because something makes me feel good now, like eating only meat makes me feel good now. I wonder what are the costs on the line? [/INST] We'll think about what I was saying about the trade offs between growth and reproduction, which is what a mouse does and a whale that grows slowly reproduces slowly lives a long time. It's called the disposable Soma theory. Kirkwood just propose that in the 70's what meat probably does is put you in the mouse category, super fertile, grow fast, heal fast and then if you want to be a whale, you should restrict me and do things that promote the preservation of your body. </s><s>[INST] Is it difficult to eat a plant based diet that you perform well under? So uh mentally and physically just almost I'm asking uh almost like uh anecdotal question, unless you know the science [/INST] well the science is still being worked out but from the synthesis of everything I've read, I try to it's a date that's definitely full of leafy greens, particularly spinach is great because it's got the iron that we need plenty of vitamins. I also try to avoid too much fruit and berries, particularly for juice, definitely avoid that sugar high spike in your sugar is not healthy. In the long run. The other thing that's interesting is we discovered what are called what we call zero Hermetic molecules. Let me unpack that because it's a terrible name and I take full responsibility with my friend Conrad, howard's the Zeno means cross species and hore Missus is the term that what doesn't kill you makes you live longer and be healthier. And so we're getting cross species. Health improvements by molecules that plants make and plants make these molecules when they are also under adversity or perceived adversity for instance, are I I understand if you want really healthy are good oranges, you can drive nails into the bark of the tree before you harvest. Same with wine, you typically want them to be dry before you harvest or covered in fungus. And that's because these plants make these colorful and Zeno hermetic molecules that make themselves stress resistant, turn on their certain defenses. The sword jeans remember and when we eat them, we get those same benefits. That's the idea and we've evolved to do. So this isn't a coincidence. It's my theory, our theory that we want to know when our food supplies is under adversity because we need to get ready for a famine. And so we hunker down and preserve our body and by eating these colored food. So I practically speaking if it's full of color. If there's been some chewing by a caterpillar caterpillar organic grown locally in local farms, I'll eat that versus a watery insipid uh light colored um lettuce that's been grown in California. </s><s>[INST] So you want vegetables that have suffered. You want to David Goggins as vegetables. That's Xeno aromatic molecules. I love that. I'm going to take that one [/INST] with me. Thank you. Yeah, </s><s>[INST] I follow him on instagram is always screaming. You want the uh, that he's basically, uh, the Zeno hermetic version of a human. Um, I like it. So these are the molecules that are representative of stress. That has been um, that plant has been under. [/INST] The best example of that is resveratrol, which many people, including myself take as a supplement. Grapes, grape vines produce that in abundance when they're dried out or they have too much light or fungus. Uh, and that we've shown activates the sir to enzyme in our bodies, which remember is what extends lifespan in yeast and slows down aging in the brain? </s><s>[INST] That's beautiful. Yet I tend to avoid fruit as well. So green veggies, anything that's not very sweet. So I would just say you are relatively low, like you try to avoid sugary things as well. [/INST] Yeah, I'm fairly militant about that. Um, I rarely would add sugar to anything. Occasionally. I would um, a slice of cheesecake, but that would be maybe once or twice a year you have to give in occasionally. But yeah, anything that's sweet. I would rather substitute something like stevia if I need a sugar hit. </s><s>[INST] What about exercise? Your favorite topic? Is there? Uh, is there pot talking about it? Yeah. Okay, great. Is their benefits to longevity from exercise? [/INST] Well, no doubt that's proven just like fasting. It's pretty clear that that works. For example. There are studies of cyclists. It was something like People that cycle over 80 miles a week, Have a 40% reduction in a variety of diseases, certainly heart disease. So that, that's not even a question. But what's interesting is that we're learning that you don't need much to have a big benefit. It's an asymptotic curve. And in fact if you overdo it, you probably have reduced benefits, particularly you start to wear out joints, that kind of thing. But just 10 minutes on a treadmill a few times a week, getting you lose your breath, get hypoxic because it's called seems to be very beneficial for long term health. Um and that's the kind of exercise that I like to do aerobic though. I do enjoy lifting weights. So that is what I call my exercise, which has out of the benefits including maintaining hormone levels, male hormone levels, but also really why I do it is Um I want to be able to counteract the effects of sitting for most of the day and as you get older, you lose muscle mass, it's a percent or so a year and I don't want to be frail when I'm older and fall over and break my hip, which is, which happens every 20 seconds in this country. </s>

<s>[INST] concept. So [/INST] that's the kind of reason why it figures out the guitar thing, right? It will observe the same sound across multiple different videos and it figures out maybe this is the common factor that's actually doing it. </s><s>[INST] I wonder I used to have this argument with my dad a bunch for creating general intelligence. Whether smell is an important uh like if that's important sense of information, mostly we're talking about like falling in love with the Ai system and for for him, smell and touch are important and I was arguing that it's not at all, it's important, nice and everything, but like you can fall in love with just language really, but voice is very powerful and vision is next and smell is not that important. Can I ask you about this process of active learning? You mentioned interactivity. Alright. Is there some value within the self supervised learning context? To select parts of the data in intelligent ways, such that they would most benefit the learning process. [/INST] So I think so, I think, I mean I I know I'm talking to an active learning fan here of course. I think first </s><s>[INST] you were talking bananas and now you're talking about active learning. I love [/INST] it. I think </s><s>[INST] Yonah Cohen told me the active learning is not that interesting. I I think back back then, I didn't want to argue with him too much, but when we talk again that we're gonna spend three hours arguing about active learning, my sense was you can go extremely far with active learning, you know, perhaps farther than anything else. Like the to me there's this kind of intuition that similar to data augmentation, you can get a lot from the data, from intelligent optimized usage of the data. I'm trying to speak generally in such a way that includes data augmentation and active learning. That there's something about maybe interactive exploration of the data that um at least this part of the solution to intelligence, like an important part, I don't know what your thoughts are on active learning in general. [/INST] I actually really like active learning. So back in the day we did this largely ignored CpR paper called Learning by asking questions. So the idea was basically retain an agent that would ask a question about the image. It would get an answer and basically then it would update itself, it would see the next image, it would decide what's the next hardest question that I can ask to learn the most. And the idea was basically because it was being smart about the kinds of questions that was asking, it would learn in fewer samples, it would be more efficient at using data. And we did find to some extent that it was actually better than randomly asking questions. Kind of weird thing about active learning is it's also a chicken and egg problem because when you look at an image to ask a good question about the image, you need to understand something about the image. You can't ask a completely arbitrary random question. It may not even apply to that particular image. So there is some amount of understanding or knowledge that basically keeps getting built when you're doing active learning. So I think after learning and by itself is really good and the main thing we need to figure out is basically how do we come up with a technique to first model what the model nose and also model what the model does not know. I think that's the sort of beauty of it, right? Because when you know that there are certain things that you don't know anything about asking a question about those concepts actually going to bring you the most value. And I think that's the sort of key challenge. Self supervised learning by itself, like selecting data for it and so on. that's actually really useful. But I think that's a very narrow view of looking at active learning, right? If you look at it more broadly, it is basically about if the model has a knowledge about end concepts and it is weak basically about certain things. So it needs to ask questions either to discover new concepts or to basically like increase its knowledge about these end concepts. But that level, it's a very powerful technique. I actually do think it's going to be really useful even in like simple things such as like data labeling. It's super useful. So there is like one simple way that you can use active learning for example, you have yourself supervised model which is very good at predicting similarities and dissimilarities between things. And so if you label a picture as basically say a banana, uh now, you know that all the images that are very similar to this image are also likely to contain bananas. So probably when you want to understand what else is a banana, you're not going to use these other images. You're actually going to use an image that is not completely dissimilar but somewhere in between which is not super similar to this image but not super dissimilar either. And that's going to tell you a lot more about what this concept of a banana </s><s>[INST] is. So that that's kind of a heuristic. I wonder if it's possible to also learn learn ways to discover the most likely the most beneficial image? So like, so not just looking a thing that's um, somewhat similar to a banana, but not exactly similar, but have some kind of more complicated learning system, like learned discovery mechanism uh, that tells you what what images look for, like how I yeah, like actually in a self supervised way, learning strictly a function that says, is this image going to be very useful to me, given what I currently no, [/INST] I think there's a lot of synergy there. It's just, I think it's going to be explored. </s>

<s>[INST] P. C. I'm excited to be working with cash app to support one of my favorite organizations called first, best known for their first robotics and lego competitions. They educate and inspire hundreds of thousands of students and over 110 countries and have a perfect rating. A 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 up 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 crystals. Gaudreau. [/INST] The Youtube </s><s>[INST] is the world's second most popular search engine behind google. Of course We watch more than one billion hours of YouTube videos a day, more than Netflix and Facebook video combined. YouTube creators upload over 500,000 hours of video every day, Average lifespan of a human being just for comparison's about 700,000 hours. So what's uploaded every single day is just enough for a human to watching a lifetime. So let me ask an absurd philosophical question if from birth when I was born and there's many people born today with the Internet, I watched Youtube videos nonstop. Do you think their trajectories through Youtube video space that can maximize my average happiness or maybe education or my growth as a human being. [/INST] I think there are some great trajectories through Youtube videos, but I wouldn't recommend that anyone spend all of their waking hours or all of their hours watching youtube. I mean I think about the fact that youtube has been really great for my kids. For instance. Uh, my oldest daughter, uh, you know, she's been watching youtube for several years. She watches Tyler Oakley and the vlog brothers and I know that it's had a very profound and positive impact on her character and my younger daughter, she's a ballerina and her teachers tell her that Youtube is a huge advantage for her because she can practice a routine and watch like professional dancers do that same routine and stop it and back it up and rewind and all that stuff. Right. So it's been really good for them. And then even my son is a sophomore in college, he um, he got through his linear algebra class because of a channel called Three Blue One Brown, which, you know, helps you understand linear algebra, but in a way that would be very hard for anyone to do on a whiteboard or a chalk board. And so I think that those experiences, from my point of view were very good. And so I can imagine really good trajectories through Youtube. </s><s>[INST] Have you looked at, do you think of broadly about that trajectory over a period because Youtube has grown up now? So over a period of years, you just kind of gave a few anecdotal examples. But you know, I used to watch certain shows on Youtube. I don't anymore. I've moved on to other shows. Ultimately. You want people to uh from Youtube's perspective to stay on Youtube to grow as human beings on Youtube. So you have to think, not just what makes them engage today or this month, but also over a period of years. [/INST] Absolutely, that's right. I mean if Youtube is going to continue to enrich people's lives, then, um, you know, that it has to grow with them and uh, and peoples interests change over time. And so I think we've, we've been working on this problem and I'll just say it broadly is like how to introduce diversity and introduce people who are watching one thing to something else they might like, we've been working on that problem all the eight years I've been at Youtube. Um, it's a hard problem because uh, I mean, of course it's trivial to introduce diversity. That doesn't </s><s>[INST] help. I got a random video. [/INST] I could just randomly select a video from the billions that we have. Uh, it's likely not to even be in your language. So the likelihood that you would watch it and develop a new interest is very, very low. And so, uh, what you want to do when you're trying to increase diversity is find something that is not too similar to the things that you've watched, but also something that you might be likely to watch and that balance finding that spot between those two things is quite challenging. </s><s>[INST] So, so diversity of content, diversity of ideas, It's uh, it's a really difficult. It's the thing like that's almost impossible to define, right? Like what's different? So how do you think about that? So two examples is uh, I'm a huge fan of three Blue one Brown say, and then one diversity, I wasn't even aware of a channel called Very Tasi, um which is a great science physics, whatever channel. So one version of diversity has shown me Derek's very potassium channel, which I was really excited to discover. Actually not watch a lot of his videos. [/INST] Okay, so you're a person who is watching some math channels and you might be interested in some other science or math channels. So like you mentioned, the first kind of diversity is just show you some some things from other channels that are related uh but not just, you know, not all the uh three blue one Brown channel throwing a couple others. So, so that's the, maybe the first kind of diversity that we started with many, many years ago, um taking a bigger leap is uh is about, I mean the mechanisms we do we use for that is is we basically cluster videos and channels together. Mostly videos. We do every almost everything at the video level. And so we'll we'll make some kind of a cluster via some embedding process. And then um and then measure, you know, what is the likelihood that that users who watch one cluster might also watch another cluster that's very distinct. So we may come to find that um that people who watch science videos also like um Jazz? Uh this is possible. Right? And so and so because of that relationship that we've identified, um through the measure through the embeddings. And then the measurement of the people who watch both. We might recommend a jazz video once in a while. </s><s>[INST] So there's this clustering the embedding space or jazz videos and science videos. And so you kind of try to look at aggregate statistics, where if a lot of people that jump from science cluster to the jazz cluster tend to remain as engaged to become more engaged than that's, that means those two are, they should hop back and forth and they'll they'll be happy, [/INST] right? There's a higher likelihood that a person from who's watching science would like jazz than the person watching science would like, I don't know, backyard railroads or or something else. Right? And so we can try to measure these likelihoods and use that to make the best recommendation we can. </s><s>[INST] So, okay, so we'll talk about the machine learning of that. But I have to linger on things that neither you or anyone have an answer to. There's gray areas of truth, which is, for example, no, I can't believe I'm going there. But politics, it happens so that certain people believe certain things and they're very certain about them. Let's move outside the red versus blue politics of today's world. But there's different ideologies, for example, in college. I read quite a lot of ayn rand I studied and that's a particular philosophical ideology I find I found it interesting to explore. Okay, so that was that kind of space. I've kind of moved on from that cluster intellectually, but it nevertheless is an interesting cluster. There's I was born in the soviet union socialism, communism is a certain kind of political ideology that's really interesting to explore again objectively. Just there's a set of beliefs about how the economy should work and so on. And so it's hard to know what's true or not in terms of people within those communities are often advocating that this is how we achieve Utopia in this world, and they're pretty certain about it. So how do you try to manage politics in this chaotic, divisive world policy or any kind of ideas in terms of filtering what people should watch next, in terms of also not letting certain things be on Youtube, this is exceptionally difficult responsibility, right? [/INST] Well, um, the responsibility to get this right is our top priority. And um and the first comes down to making sure that we have good clear rules of the road right? Like just because we have freedom of speech doesn't mean that you can literally say anything right, Like we as a society have accepted certain restrictions on our freedom of speech. There are things like libel laws and and things like that. And so um where we can draw a clear line, we do and we continue to evolve that line over time. Um however, as you pointed out wherever you draw the line, there's gonna be a borderline and in that borderline area we are going to maybe not remove videos, but we will try to reduce the recommendations of them or the proliferation of them by demoting them. And then alternatively in those situations try to raise what we would call authoritative or credible sources of information. So we're not trying to I mean, you mentioned Iran and um communism, uh you know, those are those are two like valid points of view that people are going to debate and discuss. And and of course people who believe in one or the other of those things are going to try to persuade other people to their point of view. And so, um we're not trying to settle that or choose a side or anything like that. What we're trying to do is make sure that the the people who are expressing those point of view and and offering those positions are authoritative. Incredible. </s><s>[INST] So let me ask a question about people I don't like personally you heard me, I don't care if you have comments on this. Uh uh and but sometimes they're brilliantly funny, which is trolls. So people who kind of mock, I mean the internet is full reddit of mock style comedy where people just kind of make fun of uh point out that the emperor has no clothes and there's brilliant comedy and that. But sometimes you can get cruel and mean so on that on the mean point and sorry to linger on these things that have no good answers, but actually I totally hear you that this is really important. You're trying to solve it? But how do you reduce the meanness of people on Youtube? [/INST] I understand that anyone who uploads Youtube videos has to become resilient to a certain amount of meanness. Like I've heard that from many creators and um, we would, we are trying in various ways comment ranking, um, allowing certain features to block people to, to reduce or or make that that meanness or that trolling behavior um, less effective on Youtube. And so, uh, I mean it's it's very important, um, but it's something that we're going to keep having to work on and and you know, as as we improve it, like maybe we'll get to a point where uh, where people don't have to suffer this sort of meanness when they upload Youtube videos. I hope we do, but uh, you know, but it just does seem to be something that you have to be able to deal with as a Youtube creator. </s><s>[INST] Now, do you have a hope that you mentioned two things that kind of agree with? So there's like a machine learning approach of ranking comments based on whatever based on how much they contribute to the healthy conversation, let's put it that way. And the other is almost an interface question of how do you, how does the creator filter so block or how does how do humans themselves, the users of youtube manage their own conversation. Do you have hope that these two tools will create a better society without limiting freedom of speech too much without sort of attacking even like saying that people, what do you mean limiting uh sort of curating speech? [/INST] I mean I think that that overall is our whole project here at Youtube. Like we fundamentally believe and I personally believe very much that Youtube can be great. It's been great for my kids. I think it can be great for society. Um, but it's absolutely critical that we get this responsibility part right, and that's why it's our top priority. Susan Wojcicki, who is the Ceo of Youtube um she says something that I personally find very inspiring, which is that We want to do our jobs today in a manner so that people 20 and 30 years from now, we'll look back and say, you know, YouTube, they really figured this out. They really found a way to strike the right balance between the openness and the value that the openness has and also making sure that we are meeting our responsibility to users in society. </s><s>[INST] So the burden on Youtube actually is quite incredible and the one thing that people don't don't give enough credit to the seriousness and the magnitude of the problem, I think so I I personally hope that you do solve it because a lot is in your hands a lot is riding on your success or failure? So it's besides of course running a successful company, you're also curating the content of the internet and the conversation on the internet. That's a that's a powerful thing. So one thing that people wonder about is how much of it can be solved with pure machine learning. So looking at the data, studying the data and creating algorithms that curate the comments, create the content and how much of it needs human intervention, meaning people here at Youtube in a room sitting and thinking about what is the nature of truth? What is what are the ideals that we should be promoting? That kind of thing? So algorithm versus human input. What's your sense? [/INST] I mean my own experience has demonstrated that you need both of those things um algorithms. I mean you're familiar with machine learning algorithm and the thing they need most is data and the data is generated by humans. And so for instance, um when we're building a system to try to figure out which are the videos that are misinformation or borderline policy violations. Well, the first thing we need to do is get human beings to make decisions about which which of those videos are in which category. And then we use that data and basically, you know, take that information that's that's determined and governed by humans and and extrapolated or apply it to the entire set of billions of Youtube videos and we couldn't, we we we couldn't get to all the videos on Youtube. Well without the humans. And we, we couldn't use the humans to get to all the videos of Youtube. So there's no world in which you have only one or the other of these things. Um, and just as you said, a lot of it comes down to um, people at Youtube spending a lot of time trying to figure out what are the right policies. Um, you know, what are the outcomes based on those policies? Are there the kinds of things we want to see? Uh, and then once we kind of get, get an agreement or build some consensus around around what the policies are, Well, then we've got to find a way to implement those policies across all of Youtube and that's where both the human beings, we call them evaluators or reviewers come into play to help us with that. And then, and then once we get a lot of training data from them, then we apply the machine learning techniques to take it even further. </s><s>[INST] Do you have a sense that these human beings have a bias in some kind of direction sort of? Uh, I mean that's an interesting question. We do sort of an autonomous vehicles and computer vision in general, a lot of annotation and we rarely ask what bias do the annotators have, You know, there even in the sense that they're better than their better and taking certain things than others, for example, people are much better at, for entertaining segmentation at segmenting cars in a scene versus segmenting bushes or trees. Uh you know, there's specific mechanical reasons for that, but also because the cement its semantic gray area and just for a lot of reasons people are just terrible at annotating trees. Okay, so in the same kind of sense do you think of in terms of people reviewing videos, are annotating the content of videos? Is there some kind of bias that you're aware of or seek out in that human input? [/INST] Well, we take steps to try to overcome these kinds of biases or biases that we think would be problematic. Um so for instance, like we ask people to have a bias towards scientific consensus that something that we we instruct them to do, um we asked them to have a bias towards uh demonstration of expertise or credibility or authoritative nous. Um but there are other biases that we that we want to make sure to try to remove and there's many techniques for doing this. One of them is you send the same thing to be reviewed to many people. And so um you know, that's one technique, another is that you make sure that the people that are doing these sorts of tasks are from different backgrounds and different areas of the United States or of the world, but then even with all of that it's possible for certain kinds of uh what we would call unfair biases to creep into machine learning systems primarily as you said, because maybe the training data itself comes in in a, in a biased way. And so we also have um worked very hard on, on improving the machine learning systems to remove and reduce unfair biases when it's um, when it goes against or or has has involved some protected class, for instance, </s><s>[INST] thank you for exploring with me some of the more challenging things. I'm sure there's a few more that we'll jump back to but let me jump into the fun part, which is um, maybe the basics of the quote unquote Youtube algorithm. What is the Youtube algorithm look at to make recommendations for what to watch next was from a machine learning perspective or when you search for a particular term. How does it know what to show you next? Because it seems to at least for me do an incredible job. Both. [/INST] Well, that's kind of you to say it didn't used to do a very good job, but it's gotten better over the years. Even even I observed that it's improved quite a bit. Um those are two different situations like when you search for something, uh, Youtube uses the best technology we can get from google um to make sure that that the youtube search system finds what someone's looking for. And of course the very first things that one thinks about is okay, well, does the word occur in the title for instance, um uh you know, but there but there are much more sophisticated things um where we're mostly trying to do some syntactic match or or maybe a semantic match based on uh words that we can add um to the document itself, for instance. Uh you know, maybe is this video I watched a lot after this query. Right. That's something that uh we can observe and then as a result, make sure that that that document would be retrieved for that query. Um Now, when you talk about what kind of videos would be recommended to watch next? Um that's something again we've been working on for many years and probably the first um the first real attempt to do that well, was to use collaborative filtering. </s><s>[INST] So you can describe what collaborative filtering is. [/INST] Sure, it's just um basically what we do is we observe which videos get watched close together by the same person. And if you observe that. And if you can imagine creating a graph where the videos that get watched close together by the most people are very close to one another in this graph. And videos that don't frequently watch close too close together by the same person or the same people are far apart. Then you end up with this um graph that we call the related graph that basically represents videos that are very similar or related in some way. And what's amazing about that is that it puts all the videos that are in the same language together for instance and we didn't even have to think about language. It just does it right. And it puts all the videos that are about sports together and it puts most of the music videos together and it puts all of these sorts of videos together. Um Just because that's sort of the way the people using Youtube behave. </s><s>[INST] So that already cleans up a lot of the problem. It takes care of the lowest hanging fruit. Which happens to be a huge one of just managing these millions of videos. [/INST] That's right. Um I remember a few years ago I was talking to someone who was um trying to propose that we do a research project concerning people who um who are bilingual. And this person was making this proposal based on the idea that Youtube could not possibly be good at recommending videos well to people who are bilingual. And so um she was telling me about this and I said well can you give me an example of what problem do you think we have on Youtube with the recommendations. And so she said well I'm a um a researcher in in the U. S. And when I'm looking for academic topics I want to look I want to see them in english. And so she search for one found a video and then looked at the watch next suggestions and they were all in any english. And so she said, oh I see Youtube must think that I speak only english. And so she said, now I'm actually originally from Turkey and sometimes when I'm cooking, let's say I want to make some baklava. I really liked to watch videos that are in Turkish. And so she searched for a video about making the baklava and then and then selected it was in Turkish and the watch next recommendations were in Turkish and she, I just couldn't believe how this was possible and how is it that, you know that I speak both these two languages and put all the videos together and it's just as a sort of an outcome of this related graph that's created through collaborative filtering. </s><s>[INST] So for me, one of my huge interest is just human psychology, right? And that's such a powerful platform on which to utilize human psychology to discover what people, individual people want to watch next. But it's also be just fascinating to me. You know, I've google search has ability to look at your own history and I've done that before. Just just what I've searched three years for many, many years and it's fascinating picture of who I am actually and um I don't think anyone's ever summarized. I personally would love that a summary of who I am as a person on the internet to me because I think it reveals. I think it puts a mirror to me or to others, you know, that's actually quite revealing and interesting. You know just uh maybe the number of it's a joke but not really the most number of cat videos I've watched videos of people falling. You know, stuff that's absurd. Uh That kind of stuff. It's really interesting and of course it's really good for the machine learning aspect to uh to show to figure out what the show next. But it's interesting have you just as a tangent played around with the idea of giving a map to people sort of as opposed to just using this information to show us next, showing them here are the clusters you've loved over the years kind of thing. [/INST] Well we do provide the history of all the videos that you've watched. So you can definitely search through that and and look through it and search through it to see what it is that you've been watching on Youtube. We have actually in various times um experimented with this sort of cluster idea finding ways to demonstrate or show people um what topics they've been interested in or what clusters they've watched from. It's interesting that you bring this up because um in some sense, the way the recommendation system of Youtube sees a user is exactly as the history of all the videos they've watched on Youtube and so you can think of um yourself or or or any user on youtube as kind of like a a D. N. A strand of all your videos, right. Um that sort of represents you. Uh you can also think of it as maybe a vector in the space of all the videos on Youtube. And so, you know, now, once you think of it as a vector in the space of all the videos on Youtube, then you can start to say, okay, well, you know which videos which which other vectors are close to me and uh to my vector. And and that's one of the ways that we generate some divers recommendations. Because you're like, okay, well, you know, these these people seem to be close with respect to the videos they watched on Youtube, but you know, here's a topic or a video that one of them has watched and enjoyed but the other one hasn't. That could be an opportunity uh to make a good </s><s>[INST] recommendation. I gotta tell you. I mean I know I'm going to ask for things that are impossible, but I would love to cluster than human beings. Like I would love to know who has similar trajectories as me because it probably would want to hang out right. There's a social aspect there. Like actually finding some of the most fascinating people I find on Youtube have like no followers and I started following them and they create incredible content. You know, and on that topic, I just love to ask. There's some videos and just blow my mind in terms of quality and depth and just in every regard, Our amazing videos and they have like 57 views. Okay, How do you get videos of quality to be seen by many eyes? So the measure of quality, is it just something? Yeah. How do you know that? Something is good? [/INST] Well, I mean, I think it depends initially on what sort of video we're talking about. So, um, in the realm of, let's say you mentioned politics and news in that realm, um, you know, quality news or quality journalism relies on having a journalism department, right? Like you have to have actual </s><s>[INST] journalists and fact [/INST] checkers and people like that. Um, and so in that situation, and in others, maybe science or in medicine, um, quality has a lot to do with the authoritative nous and the credibility and the expertise of the people who make the video. Now, if you think about the other end of the spectrum, uh, you know, what is the highest quality prank video for? What is the highest quality? Um, Minecraft video, right? Uh, that might be the one that people enjoy watching the most and watch to the end, or it might be, um, the one that, uh, when we ask people the next day after they watched it, were they satisfied with it? And so we, in, especially in the realm of entertainment, um, have been trying to get at better and better measures of quality or satisfaction or enrichment since I came to Youtube and we started with, well, you know, the first approximation is the one that gets more views, but um, but you know, we, we both know that things can get a lot of views and not really be that high quality, especially if people are clicking on something and then immediately realizing that it's not that great and abandoning it. Um and that's why we moved from views to thinking about the amount of time people spend watching it. What the premise that like, you know, in some sense, the time that someone spends watching a video is related to the value that they get from that video. It may not be perfectly related, but it has something to say about how much value they get. Um, but even that's not good enough, right? Because I myself have spent time clicking through channels on television late at night and ended up watching Under Siege two for some reason, I don't know. And if you were to ask me the next day, are you glad that you watched that show on TV last night? I'd say, yeah, I wish I would have gone to bed or read a book or almost anything else really. Um and so that's why uh, some people got the idea a few years ago to try to survey users afterwards. And so, um, so we get feedback data from those surveys and then use that in the machine learning system to try to not just predict what you're going to click on right now? What you might watch for a while. But what, when we ask you tomorrow, you'll give four or five stars to. </s><s>[INST] So just to summarize what are the signals from the machine learning perspective the user can provide. So you mentioned just clicking on the video, views the time watch maybe the relative time, watch the, uh, the clicking like and dislike on the video may be commenting on the video and those things, all of those things. And then the one I wasn't actually quite aware of even though I might have engaged in it is uh, a survey afterwards, which is a brilliant idea. Is there other signals? I mean that's already a really rich space of signals to learn from. Is there something else? [/INST] Well, you mentioned commenting also sharing the video. If you, if you think it's worthy to be shared with someone else, you </s><s>[INST] know, then Youtube or outside of Youtube as all either. [/INST] Let's see. You mentioned like, dislike </s><s>[INST] you like and dislike. How important is that? [/INST] Uh, it's very important, right? We want, it's predictive of satisfaction, but it's not, it's not perfectly predictive. Um, subscribe if you subscribe to the channel of the person who made the video, then that also is a piece of information and signals, um, satisfaction, although over the years we've learned that people have a wide range of attitudes about what it means to subscribe. We would ask some users who didn't subscribe very much why, but they watched a lot from a few channels would say, well why didn't you subscribe? And they would say, well, I I can't afford to pay for anything. You know, we tried to let them understand, like, actually doesn't cost anything, it's free, it just helps us know that you are very interested in this creator. Um but then we've asked other people who subscribe to many things and I don't really watch any of the videos from those channels, and we say, well, why did you subscribe to this if you weren't really interested in any more videos from that channel? And they might tell us, um why? Just, you know, I thought the person did a great job and I just want to kind of give him a high five. </s><s>[INST] Yeah. [/INST] And so </s><s>[INST] yeah, that's where I I said, I actually subscribe to channels where I just, this person is amazing. I like this person, but then uh I like this person, I really want to support them. Uh that's how I click subscribe, even though, I mean, never actually want to click on their videos when they're releasing it. I just love what they're doing and it's maybe outside of my interest area and so on, which is probably the wrong way to use the subscribe button, but I just want to say congrats, this is great work. Well, so you have to deal with all the space of people that see the subscriber and it's totally different. [/INST] That's right. And so, you know, we we can't just close our eyes and say sorry, you're using it wrong. You know, we're not gonna pay attention to what you've done. Um, we need to embrace all the ways in which all the different people in the world use the subscribe button or the like and the dislike button. </s><s>[INST] So in terms of signals of machine learning, uh, using for the search and for the recommendation, you mentioned titles like metadata, like text data that people provide description and title and maybe keywords. Maybe you can speak to the value of those things in search and also this incredible, fascinating area of the content itself. So the video content itself, trying to understand what's happening in the video. So Youtube released a data set that, you know, the, the machine learning computer vision world, This is just an exciting space. How much is that currently? How much are you playing with that currently? How much is your hope for the future of being able to analyze the content of the video itself? [/INST] Well, we have been working on that also since I came to Youtube </s><s>[INST] analyzing the content, [/INST] analyzing the content of the video. Right. Um, and uh, what I can tell you is that uh, our ability to do it well is still somewhat crude. We can, we can tell if it's a music video, we can tell if it's a sports video, we can probably tell you that people are playing soccer. Um We probably can't tell whether it's uh Manchester United or my daughter's soccer team. So these things are kind of difficult and and using them, we can use them in some ways. So for instance, we use that kind of information to understand and inform these clusters that I talked about. Uh and also maybe to add some words like soccer for instance, to the video if if it doesn't occur in the title or the description, which is remarkable that often it doesn't. Um I one of the things that I ask creators to do is is please help us out with the title and the description um for instance, we were a few years ago having a live stream of some competition for World of Warcraft on Youtube and it was a very important competition. But if you typed World of Warcraft in search, you wouldn't find it. </s><s>[INST] Well, the Warcraft wasn't in the title. [/INST] World of Warcraft wasn't in the title, it was Match for 78, you know, a team versus B team and World of Warcraft wasn't the title. Just like, come on, give me </s><s>[INST] being literal being literal on the internet is actually very un cool. Which is the problem is that right? Well, I mean uh in some sense. Well, some of the greatest videos, I mean there's a humor to just being indirect, being witty and so on and actually being uh you know, machine learning algorithms want you to be, you know, literal right? You just want to say what's in the thing, be very, very simple and in in some sense that gets away from wit and humor. So you have to play with both. Right? So but you're saying that for now sort of um the content of the title, the kind of the description in the actual text is one of the best ways to uh for the for the argument to find your video and put them in the right cluster. [/INST] That's right. And and I would go further and say that if you want people human beings to select your video in search, then it helps to have let's say World of Warcraft in the title. Because why would a person, you know, if they're looking at a bunch they type World of Warcraft and they have a bunch of videos, all of whom say World of Warcraft except the one that you uploaded? Well, even the person is going to think maybe this isn't somehow search made a mistake. This isn't really about World of Warcraft. So it's important not just for the machine learning systems, but also for the people who might be looking for this sort of thing. They get a a clue that it's what they're looking for by seeing that same thing prominently in the title of the video. </s><s>[INST] Okay, let me push back on that. So I think from the algorithm perspective, Yes. But if they typed in World of Warcraft and saw video that with the title simply winning and and and the thumbnail has like a sad um orc or something I don't know right? Like I think that's much it gets your curiosity up. And then if they could trust that the algorithm was smart enough to figure out somehow that this is indeed a World of Warcraft video that would have created the most beautiful experience. I I think in terms of just the wit and the humor and the curiosity that we human beings naturally have. But you're saying, I mean, realistically speaking, it's really hard for the algorithm to figure out that the content of that video will be well the Warcraft [/INST] and you have to accept that some people are going to skip it. Yeah. Right. I mean and so you're right, the people who don't skip it and select it are gonna be delighted. Um but other people might say, yeah, this is not what I was looking for </s><s>[INST] and making stuff discoverable, I think is what you're [/INST] really uh </s><s>[INST] working on and hoping so yeah. So from your perspective to put stuff in the title description [/INST] and remember the collaborative filtering part of the system. It starts by the same user watching videos together. Right? So the way that they're probably going to do that is by searching for them. </s><s>[INST] That's a fascinating aspect of its like ant colonies. That's how they find stuff is so, I mean, what degree for collaborative filtering in general is one curious ant, one curious user essential sort of just a person who is more willing to click on random videos and sort of explore these cluster spaces in your sense, how many people are just like watching the same thing over and over and over and over and how many are just like the explorers just kind of like click on stuff and then help help the other ant and the ant colony discover the cool stuff. You have a sense of that at all. [/INST] I really don't think I have a sense relative sizes of those groups, but I, but I would say that, you know, people come to youtube with some certain amount of intent and as long as they, um, to the extent to which they, they try to satisfy that intent. That certainly helps our systems right? Because our systems rely on on kind of a faithful amount of behavior the right like um and there are people who try to trick us right? There are people and machines that try to um, associate videos together that really don't belong together. But they're trying to get that association made because it's profitable for them. And so we have to always be resilient to that sort of uh, attempted gaming the system. </s><s>[INST] So speaking to that there's a lot of people that in a positive way perhaps, I don't know, I don't like it, but like to gain want to try to game the system to get more attention. Everybody creators in a positive sense want to get attention right. So how do you how do you work in this space when people create more and more sort of Clickbait, e titles and thumbnails sort of very tasking, Derek has made a video where basically describes that. It seems what works is to create a high quality video. Really good video where people would want to watch it wants to click on it but have Clickbait titles and thumbnails to get them to click on it in the first place. And he's saying I'm embracing this fact, I'm just going to keep doing it and I hope you forgive me for doing it and you will enjoy my videos once you click on them. So in what sense do you see this kind of Clickbait style attempt to manipulate to get people in the door to manipulate the algorithm or play with the algorithm. Game the algorithm. [/INST] I think that that you can look at it as an attempt to game the algorithm. But um even if you were to take the algorithm out of it and just say, okay, well all these videos happen to be lined up which the algorithm didn't make any decision about which one to put at the top of the bottom, but they're all lined up there, which one are the people going to choose? And and I'll tell you the same thing that I told Derek is um, you know, I have a bookshelf and they have two kinds of books on them. Uh, science books. Um, I have my math books from when I was a student and they all look identical except for the titles on the covers. They're all yellow. They're all from Springer and they're every single one of them. The cover is totally the same. Right? On the other hand, I have other more pop science type books and they all have very interesting covers, right? And they have provocative titles and things like that. I mean, I wouldn't say that they're Clickbait e because they are indeed good books. Um, and I don't think that they cross any line. But uh, but you know that that's just a decision you have to make, right? Like the people who, who write classical records in theory by purity Freddy. He was fine with the yellow title and the and nothing more. Whereas I think other people who, who wrote a more popular type book, uh, understand that they need to have a compelling cover and a compelling title. And uh, and you know, I don't think there's anything really wrong with that. We do, we do take steps to make sure that there is a line that you don't cross. And if you go too far, maybe your thumbnails especially racy or, or um, you know, it's all cats with too many exclamation points. We observe that um users are kind of uh, you know, sometimes offended by that. And so um so for the users who were offended by that we will then depress or suppress those videos </s><s>[INST] and which reminds me there's also another signal where users can say, I don't know if it was recently added, but I really enjoy it. Just saying I don't, I didn't something like I I don't want to see this video anymore or something like, like this is uh like there's certain videos to just cut me the wrong way. Like just just jump out at me is like I don't want to I don't want this and it feels really good to clean that up to be like I don't that's not that's not for me. I don't know. I think that might have been recently added, but that's also a really strong signal. [/INST] Yes, absolutely. Right. We don't want to make a recommendation that uh, people are unhappy with </s><s>[INST] and that makes me that particular one makes me feel good as a user in general and as a machine learning person because I feel like I'm helping the algorithm, my interaction on Youtube don't always feel like I'm helping the algorithm. Like I'm not reminded of that fact. Like for example, uh Tesla on autopilot and you know, I must create a feeling for their customers with people that own test is that they're helping the algorithm of testing. Like they're all like are really proud, they're helping complete learn. I think Youtube doesn't always remind people that you're helping the algorithm gets smarter. And for me, I love that idea. Like we're all collaboratively, like Wikipedia gives that sense. They're all together creating a beautiful thing. Youtubers uh doesn't always remind me of that, that's uh this conversation is reminding me of that but uh well that's a good tip. [/INST] We should keep that fact in mind when we designed these features. I'm not sure. I I really thought about it that way but that's a very interesting perspective. </s><s>[INST] It's an interesting question of personalization that I feel like when I click like on a video I'm just improving my experience, it would be great. It would make me personally, people are different but make me feel great if I was helping also the Youtube algorithm broadly say something, you know what I'm saying? Like there's a that I don't know if that's human nature, but you want the products you love and I certainly love Youtube like you want to help you get smarter smarter smarter because there's some kind of coupling between our lives together. Being better if youtube is better than my life will be better and that's that kind of reasoning, I'm not sure what that is and I'm not sure how many people share that feeling. It could be just a machine learning feeling but at that point how much personalization is there in terms of next video recommendations. So is it kind of all really boiling down to clustering like you find in years clusters to me and so on and that kind of thing or how much is personalized to meet the individual completely? [/INST] It's very, very personalized. So um your experience will be quite a bit different from anybody else's who's watching that same video at least when they're logged in. And um the reason is is that we we found that that users often want to different kinds of things when they're watching a video, sometimes they want to keep watching more on that topic or more in that genre. And other times they just are done and they're ready to move on to something else. And so the question is, well, what is this something else? And one of the first things one can imagine is, well maybe something else is um the latest video from some channel to which you've subscribed and that's going to be very different from for you than it is for me. Right. And and even if it's not something that you subscribe to, it's something that you watch a lot. And again, that will be very different on a person by person basis. And so um even the watch next as well as the home page of course is quite personalized. </s><s>[INST] So what we mentioned, some of the signals, but what does success look like? What does success look like in terms of the algorithm creating a great long term experience for a user or put another way, if you look at the videos I've watched this month, how do you know the algorithm succeeded for me? [/INST] I think first of all, if you come back and watch more youtube, then that's one indication that you found some value from </s><s>[INST] it. So just the number of hours is a powerful indicator. [/INST] Well, I mean, not the hours themselves, but um, uh, the fact that you return on another day, um, so that's probably the most simple indicator. People don't come back to things that they don't find value in, right? There's a lot of other things that they could do. Um, but like I said, I mean ideally we would like everybody to feel that Youtube enriches their lives and that every video they watched is the best one they've ever watched since they've started watching Youtube. And so that's why uh, we surveyed them and asked them like is this 1 - five stars. And so our version of Success is uh, every time someone takes that survey, they say it's five stars. And if we asked them, is this the best video you've ever seen on Youtube? They say yes every single time. So, um, it's hard to imagine that we would actually achieve that maybe ask them. Typically we would get there. But, but that would be what we think successes. </s><s>[INST] It's funny, I've recently said somewhere, I don't know, maybe tweeted, but that Ray Dalio has this video on the, the economic machine? I forget what it's called, but it's a 30 minute video. And I said it's the greatest video I've ever watched on Youtube. It's like I watched the whole thing and my mind was blown as a very crisp clean description of how the at least the american economic system works. It's a beautiful video. And I was just, I wanted to click on something to say, this is the best thing. This is the best thing ever. Please let me, I can't believe I discovered it. I mean the views and the likes reflect its quality. But I was almost upset that I haven't found it earlier and wanted to find other things like it. I don't think I've ever felt that this is the best video ever watched. And that was that. And uh, to me, the ultimate utopia. The best experiences where every single video, while I don't see any of the videos I regret. And every single video I watched is one that actually helps me grow, helps me enjoy life be happy and so on. Uh, well, so that's, that's, that's a heck of that's uh, that's one of the most beautiful and ambitious. I think machine learning tasks. So when you look at a society as opposed to an individual user, do you think of how youtube is changing society when you have these millions of people watching videos, growing, learning, changing having debates, Do you have a sense of Yeah, what the big impact on society is because I think it's huge, but you have a sense of what direction we're taking this world? [/INST] Well, I mean, I think, you know, openness has had an impact on society already. Uh there's a lot of um, </s><s>[INST] what do you mean by openness? [/INST] Well, the fact that unlike other mediums, there's not someone sitting at Youtube who decides before you can upload your video, whether it's worth having you upload it, um or worth anybody seeing it. Really, Right. Um and so, uh you know, there are some creators who say like, I wouldn't have this opportunity to, to reach an audience. Tyler Oakley often said that, you know, he wouldn't have had this opportunity to reach this audience if it weren't for Youtube. And uh, and so I think that's one way in which Youtube has change society. Um I know that there are people that I work with from outside the United States, especially from places where uh literacy is low and they think that youtube can help in those places because you don't need to be able to read and write in order to learn something important for your life, maybe, um you know, how to do some job or how to fix something. And so that's another way in which I think youtube is possibly changing society. So I've, I've worked at youtube for eight, almost nine years now and it's fun because I meet people and you know, you tell them where they, where you work, you say you work on Youtube and they immediately say, I love Youtube, right, which is great, makes me feel great. Uh, but then of course, when I asked them, well, what is it that you love about Youtube? Not one time ever, has anybody said that the search works outstanding or that the recommendations are great? Um, what they always say when I asked them, what do you love about Youtube is they immediately start talking about some channel or some creator or some topic or some community that they found on Youtube and that they just love. And so that has made me realize that Youtube is really about the video and connecting the people with the videos and then everything else kind of gets out of the way. </s><s>[INST] So beyond the video, it's an interesting because you kind of mentioned creator, what about the connection with just the individual creators as opposed to just individual video. So, like I gave the example of Ray Dalio video that the video itself is incredible. But there's some people are just creators that I love that they're one of the cool things about people who call themselves Youtubers or whatever is they have a journey. They usually almost all of them are they suck horribly in the beginning and then they kind of grow, you know, and then there's that genuineness in their growth. So, uh, you know, Youtube clearly wants to help creators connect with their audience in this kind of way. So how do you think about that process of helping creators grow, helping to connect with their audience develop, not just individual videos, but the entirety of the creator's life on Youtube. [/INST] Well, I mean, we're trying to help creators find the biggest audience that they can find and the reason why that's you brought up creator versus video. The reason why creator channel is so important is because um, if we have a hope of, of people coming back to Youtube, well, they have to have in their minds some sense of what they're going to find when they come back to Youtube. If Youtube were just the next viral video and I have no concept of what the next viral video could be. One time. It's a cat playing a piano and the next day it's uh, some Children interrupting a reporter and the next day it's, you know, uh, some other thing happening. Um, then then it's hard for me to, so when I'm not watching Youtube say, gosh, I, I really, you know, would like to see something from someone or about something. Right? And so that's why I think this connection between fans and creators so important um for </s><s>[INST] both because [/INST] it's, it's a way of uh, of sort of fostering a relationship that can play out into the future. </s><s>[INST] Like talk about kind of a dark and interesting question in general and again, a topic that you or nobody has an answer to, but social media has a sense of, you know, it gives us highs and gives us lows in the sense that creators often speak about having sort of burn burn out and having psychological ups and downs and challenges mentally in terms of continuing the creation process, there's a momentum, there's a huge excited audience that makes everybody feel that makes creators feel great. And I think it's more than just financial. I think it's literally just, they love that sense of community. It's part of the reason I upload to Youtube, I don't care about money, never will. What I care about is the community, but some people feel like this momentum and even when there's times in their life when they don't feel, you know, for some reason don't feel like creating So how do you think about burnout this mental exhaustion that some Youtube creators go through, is that something we have an answer for, is that something, how do we even think about [/INST] that? Well, the first thing is we want to make sure that the Youtube systems are not contributing to this sense, right? And so, um, we've done a fair amount of research to demonstrate that you can absolutely take a break if you are a creator and you've been uploading a lot. We have just as many examples of people who took a break and came back more popular than they were before, as we have examples of going the other way, </s><s>[INST] can we pause on that for a second? That the feeling that people have, I think is if I take a break, everybody, the party will leave, right? So if you can just linger on that, So, in your sense that taking a break is okay, [/INST] yes, taking a break is absolutely okay. And the reason I say that is because um we have, we can observe many examples of being, of creators, um coming back very strong and even stronger after they have taken some sort of break. And so I just want to dispel the myth that this somehow um necessarily uh means that your channel is going to go down or lose views, that is not the case. We know for sure that this is not a necessary outcome. Um and so we we want to encourage people to make sure that they take care of themselves, that is job one right? You have to look after yourself and your mental health. Um, and, you know, I think that it probably in some of these cases uh contributes to better videos once they come back, right, because a lot of people, I mean, I know myself if I'm burnt out on something that I'm probably not doing my best work, even though I can keep working until I pass out. And so, um I think that the taking a break uh may even improve the creative ideas that someone has? </s><s>[INST] Okay, I think that's a really important thing to sort of, to dispel. I think that applies to all of social media. Like literally I've taken a break for a day every once in a while. No, sorry, sorry if that sounds like a short time, but even like sort of email, just taking a break from email or only checking email once a day, especially when you're going through something psychologically in your personal life and so on or really not sleeping much because of work deadlines, it can refresh you in a way that's that's profound. And so the same [/INST] applies was there when you came back there. </s><s>[INST] So and and it looks different actually when you come back you're sort of brighter I'd with some coffee, everything the world looks better. So it's important to take a break when you need it. So you've mentioned kind of the the Youtube algorithm isn't, you know, E equals M C squared is not a single equation. It's it's potentially sort of more than a million lines of code sort of, Is it more akin to what autonomous successful autonomous vehicles today are? Which is they're just basically patches on top of patches of heuristics and human experts really tuning the algorithm and have some machine learning modules or is it becoming more and more a giant machine learning system with humans just doing a little bit of tweaking here and there. What's your sense first of all, do you even have a sense of what is the Youtube algorithm at this point and which however much you do have a sense, what does it look like? [/INST] Well, we don't usually think about it as the algorithm um because it's a bunch of systems that work on different services. Uh The other thing that I think people don't understand is that what you might refer to as the Youtube algorithm from outside of Youtube is actually a, you know, a bunch of code and machine learning systems and heuristics. But that's married with the behavior of all the people who come to Youtube every day. </s><s>[INST] So the people part of the code essentially. Exactly. Right. [/INST] Like if there were no people who came to Youtube tomorrow then they're, the algorithm wouldn't work anymore. Right. So that's a critical part of the algorithm. And so when people talk about, well the algorithm does this, the algorithm does that. It's sometimes hard to understand. Well, you know, it could be the viewers are doing that and the algorithm is mostly just keeping track of what the viewers do and then reacting to those things. Um in sort of more fine grain situations and I think that this is the way that the recommendation system and the search system and probably many machine learning systems evolve is, you know, you start trying to solve a problem and the first way to solve a problem is often with a simple heuristic. Right? And and you know, you want to say, what are the videos we're gonna recommend. Well, how about the most popular ones? Right. And that's where you start. Um and and over time you collect some data and you refine your situation so that you're making less heuristics and you are you're building a system that can actually learn what to do in different situations based on some observations of those situations in the past. And uh and you keep chipping away at these heuristics over time. And so I think that um just like with diversity, you know, I think the first diversity measure we took was okay, not more than three videos in a row from the same channel. Right? It's a pretty simple heuristic to encourage diversity, but it worked right. Who needs to see 456 videos in a row from the same channel? Um And over time we try to chip away at that and and make it more fine grain and and basically have it remove the heuristics in favor of something that can react to individuals and individual situations. </s><s>[INST] So how do you you mentioned, you know, we we know that something worked. How do you get a sense when decisions are the kind of a b testing that this idea was a good one. This was not so good. What's how do you measure that? And across which time scale? Across how many users, that kind of, that kind of thing? [/INST] Well, you mentioned that a B experiments. And so uh just about every single change we make to Youtube, uh we do it only after we've run a B experiment. And so in those experiments which run from one week, two months, um we measure hundreds, literally hundreds of different variables and measure changes with confidence intervals and all of them because we really are trying to get a sense for ultimately does this improve the experience for viewers? That's the question we're trying to answer and an experiment is one way, um because we can see certain things go up and down. So, for instance, um if we noticed in the experiment, people are dismissing videos less frequently or their um saying that they're more satisfied, they're giving more videos five stars after they watch them, then those would be indications of uh, that the experiment is successful, that it's improving the situation for viewers. Um but we can also look at other things like we might do user studies where we invite some people in and ask them, like, what do you think about this? What do you think about that? How do you feel about this? Um, and other various kinds of user research, but ultimately, before we launch something, we're gonna want to run an experiment. So we get a sense for what the impact is going to be, not just to the viewers, but also to the different channels and all of that </s><s>[INST] an absurd question, nobody knows what actually is interesting, Maybe there's an answer. But if I want to make a viral video, how do I do it? [/INST] I don't know how you make a viral video. I know that we have in the past tried to figure out if we could detect when a video was going to go viral, you know, and those were, you take the 1st and 2nd derivatives of the view count and maybe use that to um, do some prediction, but um, but I can't say we ever got very good at that. Oftentimes we look at where the traffic was coming from, you know, if it's, if it's, if a lot of the viewership is coming from something like twitter, uh, then then maybe it has a higher chance of becoming viral then maybe than than if it were coming from search or something. Um, but that was just trying to detect a video that might be viral. How to make one. Like I have no idea, you get your kids to interrupt you while you're on the, on the news? </s><s>[INST] Absolutely. Uh, but after the fact on one individual video ahead of time predicting is a really hard task, but after the video went viral in analysis, can you sometimes understand why went viral? From the perspective of youtube broadly first, I was even interesting for youtube, that particular video is viral or does that not matter for the individual for the experience of people? [/INST] Well, I think people expect that if a video video is going viral and it's something they would be interested in, then I would, I think they would expect Youtube to recommend it to </s><s>[INST] them. Um, so something's going viral. It's good to just let the wave people ride the wave of its violence. [/INST] Well, I mean we want to meet people's expectations in that way. Of course. </s><s>[INST] So like, like I mentioned, I hung out with Derek Mueller awhile ago a couple of months back. He's actually the person who suggested I talk to you on this podcast. All right, well thank [/INST] you Derek </s><s>[INST] At that time. He just recently posted an awesome science video titled Why are 96 million black balls on this reservoir. And In a matter of, I don't know how long, but like a few days you got 38 million views and still growing. Is this something you can analyze and understand why it happened this video? Any one particular video like it. [/INST] I mean we can surely see where it was recommended, where it was found, who watched it and those sorts of things. </s><s>[INST] So it's actually sorry to interrupt it. Is the video which helped me discover who Derek is. I didn't know who he is before. So I remember, you know, usually I just have all of these technical boring MIT stanford talks in my recommendation because that's how I watch and then all of sudden there's this black balls and Reservoir video with like an excited nerd and uh with like just why is this being recommended to me? So I clicked, I didn't watch the whole thing, it was awesome, but and then a lot of people have that experience like why was I recommended this, but they all of course watching and enjoyed it, which is what's your sense of this just wave of recommendation that comes with this viral video that ultimately people get enjoy after they click on it. [/INST] Well, I think it's the system, you know, basically doing what anybody who's recommending something would do, which is you show it to some people and if they like it, you say, okay, well can I find some more people who are a little bit like them? Okay, I'm gonna try it with them. Oh, they like it to let me expand the circle some more. Find some more people, Oh, it turns out they </s><s>[INST] like it too. And [/INST] you just keep going until you get some feedback that says that no, now you've gone too far, these people don't like it anymore. Um and so I think that's basically what happened now. Um you asked me about how to make a video go viral or make a viral video, I don't think that uh if you or I decided to make a video about 96 million balls that it would also go viral, it's possible that Derek made like the canonical video about those black balls in the lake and </s><s>[INST] so, Right. [/INST] And so I don't know whether or not uh, just following along is the secret. Right? </s><s>[INST] Yeah, but it's fascinating. I mean, just like you said, the algorithm sort of expanding that circle and then figuring out that more and more people did enjoy it and that sort of uh phase shift of just a huge number of people enjoying in the algorithm quickly automatically. I assume, figuring that out. That's a, I don't know the dynamics, the psychology. That is a beautiful thing. And so what do you think about the idea of, of clipping? Like, and uh, too many people annoyed me into doing it, which is they were requesting it. They said it would be very beneficial to add clips and like the coolest points and actually have explicit videos. Like I'm re uploading a video like a short clip, which is what the podcasts are doing. Do you see as opposed to like, I also add timestamps for the topics, you know, you want the clip, do you see Youtube somehow helping creators with that process or helping connect clips to the original videos? Was that just in a long list of amazing features to work towards? [/INST] Yeah, I mean, it's not something that I think we've, we've done yet, but I can tell you that. Um, I think clipping is great and I think it's actually great for you as a creator and here's the reason. Um if you think about, I mean, let's let's say the NBA is uploading uh videos of of its games. Well, people might search for Warriors versus Rockets, or they might search for Steph curry. And so highlight from the game in which Steph curry makes an amazing shot um is an opportunity for someone to find a portion of that video. And so I think that um you never know how people are gonna search for something that you've created and so you want to, I would say you want to make clips and and add titles and things like that so that they can find it um as easily as possible. </s><s>[INST] Do you have a dream of a future? Perhaps a distant future when the Youtube algorithm figures that out, sort of automatically detects the parts of the video? That are really interesting, exciting, potentially exciting for people and sort of clip them out in this incredibly rare space. Because if you talk about, if you don't even just this conversation, we've probably covered 30, 40 little topics and there's a huge space of users that would find, You know, 30% of those topics really interesting and that space is very different. It's something that's beyond my ability to clip out, right, but the algorithm might be able to figure all that out, sort of expand into clips. Do you have a do you think about this kind of thing? Do you have a hope a dream that one day they are going to be able to do that kind of deep content analysis. [/INST] What we've actually had projects that attempt to achieve this uh but it really does depend on understanding the video well and our understanding of the video right now is quite crude and so I think it would be especially hard to do it with a conversation like this one might be able to do it with um let's say a soccer match more easily, right? You could probably find out where the goals were scored and then of course you you need to figure out who it was that scored the goal and and that might require human to do some annotation, but I think that um trying to identify coherent topics in a transcript, like like the one of our conversation is um is not something that we're going to be very good at right away. </s><s>[INST] And I was speaking more to the general problem actually of being able to do both a soccer match and our conversation without explicit sort of almost my my hope was that there exists in algorithm that's able to find exciting things in video. [/INST] So google. Now on google search will help you find the segment of the video that you're interested in. So if you uh search for something like how to change the filter in my dishwasher, then if there's a long video about your dishwasher. And this is the part where the person shows you how to change the filter, then then it will highlight that area and provide a link directly to it </s><s>[INST] and you know it from your recollection. Do you know if the thumbnail reflects like what's the difference between showing the full video and the shorter clip? Do you know how it's presented in search results? You [/INST] don't remember how it's presented? And the other thing I would say is that right now it's based on creator annotations. </s><s>[INST] Got it. So it's not the thing we're talking about [/INST] but but folks are working on the more automatic version. It's interesting. People might not imagine this, but a lot of our systems start by using almost entirely the audience behavior. And then as they get better, uh the refinement comes from using the content </s><s>[INST] and I wish, I know there's privacy concerns but I wish uh Youtube explored the space which is sort of putting a camera on the users if they allowed it right to study their uh like I I did a lot of emotional recognition work and so on to study actual sort of richer signal. One of the cool things when you upload 3 60 like VR video to Youtube and I've done this a few times. So I've uploaded myself, horrible idea. Uh Some people enjoyed it. But whatever the video of me giving a lecture in in 36 12, 3 60 camera and it's cool because Youtube allows you to then watch where do people look at? There's a heat map of where you know of where the center of the VR experience was. And it's interesting because that reveals to you like what people looked at. It's [/INST] very not always what you </s><s>[INST] were. It's not in the case of the lecture is pretty boring, it is what we're expecting. But we did a few funny videos where there's a bunch of people doing things and they, everybody tracks those people, you know, in the beginning they all look at the main person and they start spreading around and looking at other people. It's fascinating. So that kind of, that's a really strong signal of what people found exciting in the video. I don't know how you get that from people just watching. Except they tuned out at this point. Like it's hard to measure. This moment was super exciting for people. I don't know how you get that signal may be common. Is there a way to get that signal where this was like, this is when their eyes opened up and they're like, like for me with the ray Dalio video, right? Like at first I was like, okay, this is another one of these like dumb it down for you videos and then you like start watching. It's like, okay, there's really crisp, clean, deep explanation of how the economy works. That's where I like set up and started watching, right? That moment. Is there a way to detect that moment? [/INST] The only way I can think of is by asking people to label it. Yeah, </s><s>[INST] you mentioned that were quite far away in terms of doing video analysis, deep video analysis of of course google youtube. You know, we're quite far away from solving the town was driving problem too. So it's, I [/INST] don't know, I think we're closer to </s><s>[INST] That. Well, the, you know, you never know and uh, the Wright brothers thought they're never, they're not gonna fly 50 years three years before they flew. So, uh, what are the biggest challenges would just say is that the broad challenge of understanding video understanding natural language, understand the challenge before the entire machine learning community of just being able to understand data. Is there something specific to video that's even more challenging than an understanding natural language, Understanding what's your sense of what the [/INST] biggest video is? Just so much information? And so precision becomes a real problem. It's like a, you know, you're, you're trying to classify something and you've got a million classes and you, the distinctions among them at least from a, from a machine learning perspective are often pretty small, right? Like, um, uh, you know, you need to see this person's number in order to know which player it is. And there's a lot of players, um, or you need to see uh, you know, the logo on their chest in order to know like which which team they play for and so, um, and that's just figuring out who's who, right? And then you go further and saying, okay, well, you know, was that a goal? Was it not a goal? Like is that an interesting moment as you said, or is that not an interesting moment? Um these things can be pretty hard, </s><s>[INST] so okay, so john looking, I'm not sure if you're familiar sort of with his current thinking and work. So he believes that self, what is referring to a self supervised learning will be the solution sort of to achieving this kind of greater level of intelligence. In fact, the thing he's focusing on is watching video and predicting the next frame. So predicting the future video. Right? Uh So for now we're very far from that. But his thought is because it's unsupervised or is he here first to his self supervised, you know, if you watch enough video essentially, if you watch Youtube, you'll be able to learn about the nature of reality, the physics, the common sense reasoning required by just teaching a system to predict the next frame. So he's confident this is the way to go. So for you, from the perspective of just working with this video, how do you think an algorithm that just watches all of Youtube stays up all day and night, watching youtube would be able to understand enough of the physics of the world about the way this world works, be able to do common sense reasoning and so [/INST] on. Um Well, I mean we have systems that already watched all the videos on Youtube, right, but they're just looking for very specific things right there. Um supervised learning systems that are trying to identify something or classify something. Um and I don't know if, I don't know if predicting the next frame is really going to get there because uh I don't I'm not an expert on compression algorithms, but I understand that that's kind of what compression video compression algorithms do is they basically try to predict the next frame and and um and then fix up the places where they got it wrong. Uh and that leads to higher compression than if you actually put all the bits for the next frame there. So, so I I don't know if I believe that just being able to predict the next frame is going to be enough because because there's so many frames and even a tiny bit of air on a per frame basis can lead to wildly different videos. </s><s>[INST] So, the thing is the idea of compression is one way to do compression is to describe through text what's containing the video, that's the ultimate level of compression. So the idea is traditionally when you think a video image compression, you're trying to maintain the same visual quality while reducing the size. But if you think of deep learning from a bigger perspective of what compression is is you're trying to summarize the video and the idea there is, if you have a big enough neural network just by watching the next, trying to predict the next frame, you'll be able to form a compression of actually understanding what's going on in the scene. If there's two people talking, you can just reduce that entire video into the fact that two people are talking and maybe the content of what they're saying and so on. That that's kind of the the open ended dream. So I just wanted to sort of express that is interesting, compelling notion. But uh it is nevertheless true that video our world is a lot more complicated than we get credit [/INST] for. I mean in terms of search and discovery, we have been working on trying to summarize videos in text or or with some kind of labels for eight years at least. And oh and we're kind of so, so, so </s><s>[INST] So if you were said, it's the problem is 100% solved And eight years ago was 0% solved. How where are we on that timeline would you say [/INST] to summarize a video? Well, uh maybe less than a quarter of the way. </s><s>[INST] So on that topic, what does YouTube look like 10 2030 years from now. [/INST] I mean I think that youtube is evolving to take the place of tv. Um you know, I grew up as a kid in the 70s and I watched a tremendous amount of television and uh, I feel sorry for my poor mom because people told her at the time that it was going to rot my brain and that she should kill her television. Um but anyway, I mean, I think that youtube is at least from my family, a better version of television, right? It's one that is on demand, it's uh more tailored to the things that my kids want to watch and also they can find things that um, they would never have found on television. And so I think that at least from just observing my own family, that's where we're headed is that people watch Youtube kind of in the same way that I watch television when I </s><s>[INST] was younger. So from a search and discovery perspective, what do you, what are you excited about and then 5, 10 2030 years, like what kind of things? It's already really good. I think it's achieved a lot of, of course we don't know what's possible. So it's uh, it's the task of search of typing in the text or discovering new videos by the next recommendation. I personally am really happy with the experience. I continuously, I rarely watch a video that's not awesome from my own perspective, but what's, what else is possible, What are you excited about? [/INST] Well, I think uh introducing people to more of what's available on youtube is um not only very important to Youtube and the creators, but I think it will help uh enrich people's lives because there's a lot that I'm still finding out is available on Youtube that I didn't even know. Um, I've been working Youtube eight years and it wasn't until last year that I learned that uh, that I could watch USC football games from the 19 seventies, like I didn't even know that was possible last year and I've been working here quite some time. So, you know, what was broken about, about that, that it took me seven years to learn that this stuff was already on Youtube, even when I got here. Um, so I think there's a big opportunity there and then, as I said before, uh, you know, we want to make sure that Youtube finds a way to ensure that it's acting responsibly with respect to society and enriching people's lives. So we want to take all of the great things that it does and make sure that we are eliminating the negative consequences that might happen. Um, and then lastly, if we could get to a point where all the videos people watch are the best ones they've ever watched that would be outstanding too. </s><s>[INST] Do you see in many senses becoming a window into the world for people, it's, especially with live video, you get to watch events. I mean, it's really, it's the way you experience a lot of the world that's out there is better than tv in many, many ways. So do you see becoming more than just video? Do you see creators creating visual experiences and virtual worlds? So if I'm talking crazy now, but sort of virtual reality and entering that space there is that at least for now, totally outside of what youtube is thinking about. [/INST] I mean I think google is thinking about virtual reality. Uh I don't think about virtual reality too much. Uh I know that we would want to make sure that youtube is there when virtual reality becomes something or if virtual reality becomes something that a lot of people are interested in. Um, but I haven't seen it really take off yet. </s><s>[INST] Take off. Well the future is wide open crystals. I've been really looking forward to. This conversation has been a huge honor. Thank you for answering some of the more difficult questions I've asked. I'm really excited about what uh Youtube has in store for us. It's one of the greatest products I've ever used and continues. So thank you so much for talking. [/INST] It's my pleasure. Thanks for asking me. </s><s>[INST] Thanks for listening to this conversation and thank you to our presenting sponsor cash app, download it, use code 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 become future leaders and innovators. If you enjoy this podcast, subscribe my youtube, give it five stars on Apple podcast, Follow on Spotify, support on Patreon or simply connect with me on twitter and now let me leave you with some words of wisdom from Marcel Proust. The real Voyage of Discovery consists not in seeking new landscapes but in having new eyes. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] let me ask, given that long arc of history, given that you do study the bible, what is the meaning of this whole thing? What's the meaning of life? [/INST] Wow, that's beautiful. I think that the meaning of life is is in part um what your own touches on when when he says that that the productive work, labor creativity is, is at the heart of what it is to be human. I just think that there there are some more arenas and maybe we even agree with a lot of them and I on a lot of them to be human, is to inherit a world which is imperfect, terribly imperfect, imperfect in many ways. And uh and and God created it that way. He created a world which is terribly lacking and he created us with the ability to stand up and to say, I can change the direction of this, I can do something to change the direction of this. I can take the time and the abilities that are given to me to be a partner with God in creating the world. It's not going to stay the way it was before me. It will be something different maybe a little bit, maybe a lot. But that's that is that is the heart, that is the key, that is the meaningful life is to be a partner with God in creating the world so that it is moving that much more in the right direction </s><s>[INST] the way we found. So nudge even if a little bit the direction of the world, well, uh you're you're on um you've actually been talking and your program about life quite a bit. Uh so let me ask the same question. I never tire you asking this question. What [/INST] do </s><s>[INST] you think is the is the meaning of this [/INST] whole? I mean, I don't believe in God. So God doesn't play a role in, in in my view of of the meaning of life. I think the meaning of life is to live, I like to say, to live with a capital l it's to embrace it and and I agree with your arm, in a sense you were born into a world and as human beings, one of the things that makes us very different than other animals is our capacity to change that world. We can actually go out there and change the world around us. We can change it materially through production and through that, we can change it spiritually through changing the ideas of, of people. We can we can change the direction to which humanity works. We can um, we can create a little universe. Part of that. I think part of the joy of creating a family is to create a little universe, right? We're creating a little world around us. That's part of the joy. And there is joy and family and make it all about difficulty and hard work. You know, part of the part of the idea of getting married is is to create a little world in which you and your spouse are are creating something that didn't exist before and and and and building something building a universe. But it's really to live. I mean, one of the things that I see and and it saddens me is wasted lives. There's people who just just cruise through life. They just, they just, they get bored and they get born in a particular place. They never challenge it. They never questioned, they just, you know, they live die and nothing really happened, Nothing really changed. They didn't produce, they didn't make anything of their life and produce here again, in the, in the largest sense, so to me, it's it's an every aspect of life, you know, as you know, because you've listened to my show, I love art, I love, I love aesthetics, I love the experience of great art, you know, I love relationships. I, you know, I I love producing them, you know, I like business, I like that, that aspect of it. Um and I think I think people, people are shallow in so many parts of their lives, which saddens me. I mean if if we if you had eight billion people on this planet, even if it never grew, even if we just stayed at eight billion, but the eight billion all lived fully, wow, I mean, what an amazing place. This would be, what an amazing experience we would have. So, so to me that is the meaning is just make the most that you have a short period of time on earth. And and that's it, this is it and and live it, experience it fully and and challenge yourself and push yourself. And and let me just say something about optimism, you know, one source of hope for me in the world in which we live right now is that there are people who do that, at least in certain realms of their lives, right? And and I'm inspired and I know a lot of people don't like me for this, but I'm inspired for example, by Silicon Valley, in spite of all the political disagreements I have with them and all of that. I'm inspired by people inventing new technologies and building I'm inspired by by the people you talk to about artificial intelligence and about about new ideas and about pushing the boundaries of science. Those things are exciting and it's it's terrific to see a world that I think generally is in decline yet. That these pockets in which people are still creating new new ventures and new ideas and new things that that inspires me and gives me hope that that is not dead. That in spite of the decay that's in our culture, there's still pockets where that spirit of being human is still is still alive and </s>

<s>[INST] it became a serious person, [/INST] I basically had, you know, I would I would always like go around in my rollerblades and my shorts and a t shirt and eventually it was a professional, like I bought all these khaki pants and you know, this nice like shirts with like, you know, what do they call it? The patterns? And I was like, you know, dressing with my nice belt every day showing up. And then a few months later I was like, I can't stand it and I just went back to my roller blades in my T shirts and my shirt and it was this struggle of sort of not feeling that I fit in. I was so intimidated by all of my colleagues, like just watching their incredible achievements, like persons next to me and the person, you know, the floor below me, I was like, oh my God, like they clearly made a mistake, what the heck am I doing here? How will I ever live up to these people's standards? And um eventually you grow up to realize that um the way that I grew up to realize that the way that other people perceive my work was very similar to the way that I perceived other people's work as flawless. I knew all of the flaws in my work, I knew the limitations, I knew what I hadn't managed to achieve and what I saw was maybe a third of the way of what I was trying to achieve and I saw everything is flawed, what they saw what what I had achieved, they didn't see what I hadn't achieved, they only saw the one third down, which was pretty good and they are is so they all respected me and I was feeling miserable about myself. I was like, I'm not worthy and I think that this is a cognitive problem that we have. We kind of um it's kind of like when we're talking about artificial general intelligence, ai of sort of we kind of have this definition that anything that machines can do is not intelligent and anything that they can't do is intelligent. Therefore we narrow, narrow, narrow, narrow the field of what intelligence really means and machines, do you think it's not intelligent? More I feel like it was doing the same thing with myself as soon as I could solve something, it was the kind of thing that a kid like me could solve and therefore it was kind of easy. But to the others it seemed hard. Yeah, but to me it seemed easy. So it was this kind of thing that everything that my colleagues were doing seemed impossible to me, but everything that I was doing seemed impossible to them. So it was that realization that sort of made me mature into sort of a lot more confident, but more comfortable human being. </s><s>[INST] Can you actually linger in that a little bit? You mentioned Minsky, remember he said something in an interview where he said the secret to his um like the way he approached life was to never be happy with anything he did. So there's something powerful as a motivator to do exactly what you're saying, which is everything you have achieved to see that as easy and unimpressive. What do you do with that? Because clearly that's a, I think useful [/INST] thing. I think I've kind of matured past that and I think the maturity past that is to sort of accept what it is and accept that it has helped others build onto it and therefore advance human knowledge. So it's very easy to fall into the trap of everything I've done is crap. What I told you last time is that I always tell my students that are best work is ahead of us. And I think that's more of my mindset </s><s>[INST] beautiful. Exactly what we've done [/INST] Is great. It's great for the time and it will become obsolete in 30 years. Not we can we are doing even better. Exactly. So basically our next work well, just strive and, and and again, you can't, you can't let the perfect be the enemy of the good at some point. You have to wrap I was having a student meeting with my student yesterday and it was like, listen, we know this is not perfect, but it's way better than anything that's ever been done before. You know how to improve it. But if you try to, your paper is never going to get published. So, so, you know, there's this balance of we're already at the top of the field, get it out and then you work on the next improvement and in my experience, this has never happened. We've never actually worked on the next improvement. And that's okay. It didn't make a difference because you're basically putting a new stepping stone that others will be able to step on and surpass you, my advisor in grad school. Well, basically tell me, and always let others write the second paper in that field. Just write the first one, move on, move on to the next field. You don't want to be writing the second and the third and the fourth and the fifth paper in the same field. Just, it's very shocking to a student to hear that because I was like, I was at the top of my game, I was owning that field and I published the first paper, I'm like, I'm ready for two and three and four. He's like, move on, just let it be. And I was like, whoa! And it's so liberating to sort of not have to surpass everyone, but just just put your little stepping stone out there and others will step on it and put their own stones further and eventually cross a bigger river. Then if you try to sort of make a giant leap all at once. So you need both </s>

<s>[INST] Yeah. [/INST] And so there's a lot of ingenuity and and it doesn't always work right. </s><s>[INST] Which actually from a perspective of the group threatening violence or actually doing violence is one way to make progress for your group. [/INST] We're talking about groups bargaining over stuff, right? We're talking about Russians versus Ukraine or Russians versus in the west or maybe it's managing games versus one another. Like there are a lot of their bargaining power comes from their ability to burn the house down, right? And so if I want to have more bargaining power, I can just arm a lot and I can threaten violence. And so the strategically wise thing to do, I mean, it's terrible, it's a terrible equilibrium for us to be forced into. But the strategically wise thing to do is to build up lots of arms to threaten to use them to credibly threaten to use them. But then trust or hope that your enemy is going to see reason and uh and and avoid this really terrible inefficient thing which is fighting. But the thing that's going on the whole time is both of you arming and spending like 20% of GDP or whatever on arms. That's pretty inefficient. That's the tragedy we don't have war and that's good, but we have really limited abilities to like incentivize our enemies not to arm and to keep ourselves from arming. We'd love to agree to just like both disarm but we can't And so the, the masses that we have to arm and then we have to threaten all the time. </s><s>[INST] Yeah. So the threat of violence is costing. Nevertheless, you've actually pulled up that now disappeared. The paper that said the big title called Civil War and your name is on it. What's that about? Well, [/INST] that was, I mean, when I finished graduate school and this is paper with my advisor at Ted Miguel at Berkeley. Um </s><s>[INST] Most nations, the paper opens have experienced an internal armed conflict since 1960 yet. While they were you still in grad school on this and [/INST] no, maybe last year or just just graduated. </s><s>[INST] Yeah. I wish I was in a discipline that road papers like this. This is pretty badass yet while civil wars central to many nations development, it has stood at the [/INST] periphery </s><s>[INST] of economic research and teaching so on and so forth. And this is looking at civil war broadly throughout history. Or is it just particular civil wars? We were [/INST] mostly looking at like the late 20th century. I mean, I was trained as a, what's called development economist, which is somebody who studies why some places are poor and why some countries are rich. Um, and I like a number of people around that time stumbled into violence. I mean, people have been studying, we're the wealth and poverty nations basically since the invention of economics, but there was a big blind spot for violence now there isn't anymore, it's like a flourishing area of study, but in economics, but at the time it wasn't. And so there were people like me and ted who we're sort of part political scientists because political scientists obviously been sitting this for a long time, who started bringing economic tools and expertise and like partnerships with political scientists and and adding to it. And so we wrote this. So after like people have been doing this for five or 10 years in our field, we wrote like a review article telling economists like what was going on. And so this was like a summary for economists. So the book in some ways is a lot in the same spirit of this article. This article, I mean, it's it's designed to be not written as like a boring laundry list of studies, which is what that's that's the purpose this article of service. It was for graduate students and professors who wanted to think about what to work on and what we knew. Um this book is like now trying to like not just say what economists are doing, but sort of say what economists? Political scientists, psychologists, sociologists, anthropologists like once what's how do we bring some sense to this big project and policy makers? Like what do we know and what do we know about building peace given? You know, because if you don't know what the reason for wars are, you're probably not going to design the right cure. Um, and so, so anyway, so that was the but, but I started off studying civil wars and I, because I stumbled into this place in northern Uganda basically by accident, it was never no intention of working in civil wars. I'd never thought about it. And and then, you know, basically basically I followed a woman there and </s><s>[INST] we'll talk about that. I asked [/INST] you first and for people </s><s>[INST] who are just watching where they have an amazing team of folks helping out pulling pulling pictures and articles and so on mostly. So I can put pull up pictures on instagram of animals fighting, which is what I do on my own time. And then we can discuss, analyze maybe with George ST Pierre. That's what all he sends me for people who are curious. But let me ask you one of the most difficult things going on in the world today, Israel Palestine, Will we ever see peace in this part of the world? And sort of your book title is The Roots of war in the past for peace or the subtitle, Why we fight? Um, what's the path for peace? Will we ever see peace [/INST] if we think about this ah uh conflict in the sense of like this dispute, this sort of contest this contest that's been going on between Israelis and Palestinians. It's going on for a century and they're really just 10 or 15 years of pretty serious violence in that The span of time, most of it from 2000 to 2009 and stretching up to 2014, they're like sporadic incidents which are really terrible. I'm not trying to diminish the human cost of these by the way, like I'm just trying to point out that whatever is happening as unpleasant and challenging and difficult as it is, it's actually not war. And so it is at peace. There's sort of an uneasy stalemate. The Israelis and Palestinians are actually pretty good at just sort of keeping this at a relatively low scale of violence. There's a whole bunch of like low scale sporadic violence that can be repression of civilians. It can be terror bombings and terror actions can be counter terror violence, it can be mass arrests, It can be repression, it can be denying people to vote, it can be rattling sabers, all these things that are happening, right? And it can be sporadic three week wars or sporadic, very brief episodes of intense violence before everybody sees sense and then settles down to this uneasy. That's not like you were right not to think of that as like a piece. And there's certainly no stable agreement, right? Um so a stable agreement and amity and any ability to move on from this extreme hostility. We're not there yet. And that's maybe very far away. But this is a good example of two rivals who most of the time have avoided really intense violence. </s>

<s>[INST] So that's a really powerful message, an embodiment uh sort of educating the world about sin that said day to day, there's like uh oscillations in terms of how much each human sins and there's a struggle against that. So, you know, that dog that loses himself on the beach may have had a lot of sex with other dogs leading up to that, that was uh may have been not the best dog, he could be leading up to that. So how, you know if it's a math equation, what is the final calculation look like in terms of ending up in heaven? What does it mean to live a good life in the end? Is it? Um, the average modest thing you do is is low. Can you, are you allowed to make mistakes? [/INST] Yeah. You know the the metric is love, right? And love is not a feeling. It's an act of the will to will the good of the other. That's acquaintance again to will the good of the other as other. You see that's the anti black hole principle when I I </s><s>[INST] will the good of the other [/INST] as others because if I'm willing you're good because it's good for me. So I guess it's good for you that I'm on this program. I guess I'm willing you're good, but that's because it's going to be down to my benefit. That's just an indirect egotism. That's why I see love is really rare and strange that I really want what's good for you as other. So not connected to the black hole tendency of my own prideful ego when I've broken that I've forgotten self and I've moved into the space of your own good, that's what love is now God wants us to be by this, they will know that you're my disciples that you love one another, jesus says, so that's it now. I mean life is ups and downs and back and forth and were better or worse at that. Oh the point of the churches to graft us on to christ that we might become more and more conformed to love. But you know the final calculus, I'll leave that to God, I mean, but but use love as the metric at the end of the day when you examine your conscience, did I will the good of the other today? How how effective was I at that And and be just like Ignatius Loyola, be brutally honest or was I just willing someone's good because it was good for me. Uh what where were those moments where I was like the dog on the beach see and play at the not so much God, the lawgiver surveying and you did you know three of those and four if God wants us to be fully alive, ST ironies is one of my great heroes, ancient Patrice stick figure and his famous line is Gloria dei homo of events, right? The glory of God is a human being fully alive and that gets us over this sort of obsession with the legalism. And did I do enough. And is that that's a big enough sin and God wants us fully alive. The key to that is willing the good of the other. He died that we might come to a richer appropriation of that. </s><s>[INST] So to be fully alive is to be in love with the world or to love the world deeply. And what love means is the other is get [/INST] out of yourself. </s><s>[INST] It's it's it's the humility getting out of yourself. [/INST] That somehow </s><s>[INST] is not that's not even selfless because the word selfless requires her to be a self. It's almost like just letting go. [/INST] You might talk about like a gift of self that you yourself aware, but you you give a gift of yourself yourself becomes not a magnet drawing things into itself, but it becomes a radiant source of life for others. Like mother Teresa would have had a keen sense of herself. It seems to me, but it was to light other people up so that they might be radiant. You know, that's the game. So I think you probably articulate it that way too. </s><s>[INST] Yeah, I love love. It's such an interesting thing, but [/INST] we have to be hard nosed about it. Like, you know, your friend dostoyevsky that love is a harsh and dreadful thing, right? It's not a feeling and our our culture is so sentimentalized love that it's having warm feelings or doing what people want. And that's not it at all. Love is always correlated to the order of the good because if I'm willing the good of the other. I have to know what that good is so apparent. Doesn't give the kid whatever she wants. But that's not love That's that's indulgence or that's sentimentality. But I have to know what the goods really are if I'm going to will them for you. </s><s>[INST] Yeah. In some sense, you're absolutely right. A component of love is the struggle to know the other. It's a struggle to understand. I mean that's um, that's what I mean by empathy. It's the it's not it's yeah, it's not valentine's day romantic gifts. It's it's a struggle. It's like trying to understand, trying to perturb your own mind and that of another human being to try to figure out who they are, what they want, what makes them happy, what are they afraid of, what are they hoping for? And it's like a dance dance of conversation and dance of just shared experiences and all that kind of stuff and all of that required for you to be, I guess. Um yeah, empathize, imagine yourself in their place and then love that person when you're living inside that person. Yeah, [/INST] several minutes ago about the pillars of Christianity. So we talked about God talk about incarnation, but you're getting now to a third key one namely the trinity because were monotheists, right? But we don't think God is monolithically one. We think God is a play of persons and the father from all eternity by a great mental act forms his interior word as acquaintance puts it. And that's the law goes, right. That's the very boom, that's the word by which the father knows himself and we call it the sun. So the imago it's the image of the father. But that's the great thing is that imago is not like just a dead image on a, on a mirror or a dead image of a pond or something. It's it's a full reflection of the father's being. He's one in being with the father. Therefore the sun has everything the father has except being the father. But that means that the two of them look at each other and they're just crazy in love with each other because the father is the fullness of being the son is the fullness of being and they're so crazy in love with each other that they, this is Fulton, she put it this way that there's this, they just, they love each other with this sigh and we call that the spirit of santos, that's the holy breath right? The holy sigh of love between the father and the son and that's one being one essence we say of God. But in these three persons but all your language of like dance and play and community. The greek fathers talked about perry choruses, which means God, the three persons kind of sit in a choir together. So they they they sing together, you know, and and that's why I see Christianity is unique in this claim that God is love. So every religion will say God loves, you know, in some way loves an attribute of God. God is love is a thing that God does sometimes but Christianity is unique in all the religions in saying that God is love </s>

<s>[INST] Do you think that's a feature or a bug of our brain? The fact that we have this deep, difficult to dive into subconscious. [/INST] I think it's a feature because otherwise look we are we are like any other brain or nervous system or computer were severely band limited. If we if everything I do every emotion I feel every movement I make of, all of that had to be under the control of consciousness. I couldn't I couldn't I wouldn't be here. Right? So, so what you do early on your brain, you have to be conscious when you learn things like typing or like riding on a bike. But then what you do, you train up uh route. I think that involved basal ganglia and stride. Um you you train up different parts of your brain and then once you do it automatically, like typing, you can show you do it much faster without even thinking about it because you've got this highly specialized what transcript and I called zombie agents that I sort of, they're taking care of that while your consciousness can sort of worry about the abstract sense of the text you want to write. I think that's true for many, many things. </s><s>[INST] But for the things like uh all the fights you had with the ex girlfriend things that you would think are not useful to still linger somewhere in the subconscious. So that seems like a bug that it would stay there. [/INST] You think it would be better if you can analyze and then get it out of here, get </s><s>[INST] out or just forget it ever happened. You know, that that seems a very buggy kind of Well, [/INST] yeah, in general we don't have and that's probably functional. We don't have an ability unless it's extremely out cases. Clinical dissociation is right when people heavily abused when they completely repressed the memory. But that doesn't happen in in in you know in normal people, if we don't have an ability to remove traumatic memories and of course we suffer from that. On the other hand, probably if you have the ability to constantly wipe your memory, you probably do it to an extent that isn't useful to you. So </s><s>[INST] yeah, that's a good question with the balance. So um on the books, as Jack mentioned, correct me if I'm wrong, but broadly speaking, academia and different scientific disciplines. Certainly an engineering reading literature seems to be a rare pursuit. Perhaps I'm wrong on this, but that's in my experience, most people read much more technical text and do not [/INST] sort of </s><s>[INST] escape or seek truth in literature. Um it seems like you do. So what do you think is the value? What do you think literature as the pursuit of scientific truth? Do you think it's good, it's useful fire getting [/INST] access to much wider array of human experiences. </s><s>[INST] How valuable do you think it is? Well, [/INST] if you want to understand human nature and nature in general, then I think you have to better understand a wide </s><s>[INST] variety [/INST] of experiences, not just sitting in a lab staring at a screen and having a face flashed onto you for a millisecond and pushing a button. That's what that's what I used to do that. What most psychologists do there's nothing wrong with that. But you need to consider lots of other strange states you know </s><s>[INST] and literature is a shortcut for this. Well [/INST] Yeah because literature that's that's what literature is all about. All sorts of interesting experiences that people have. You know the contingency of it. The fact that you know women experience the world different, black people experience the world different and you know one way to expense that is reading all these different literature and try to find out you you see everything is so relative. When you read the books 15 years ago they thought about certain problems very very differently than that Then as today we today like any culture think we know it all that's comin to agriculture. Agriculture believes that it's a day they know it all. And then you realize well there's other ways of viewing the universe and some of them may have lots of things in their favor. </s><s>[INST] So this is a question I wanted to ask about time scale or scale in general. Uh when you with I. T. Or in general tried to think about consciousness. Try to think about these ideas kind of naturally thinking human time scales. Do you or and also uh entities that are sized close to humans. Do you think of things that are much larger? Much smaller as containing consciousness? And do you think things that take you know. Well you know ages. Eons to uh, to operate in their conscious cause effect cause effect. [/INST] That's a very good question. So I think a lot of small creatures because experimentally, you know, a lot of people work on flies and bees, right? So most people just think they are tormented. They're just bugs, for heaven's sake. Right? But if you look at their behavior like bees, they can recognize individual humans. They have this very complicated uh, way to communicate if you've ever been involved or, you know, your parents when they bought a house, what sort of agonizing decision that is? And bees have to do that once a year, Right, When they swarm in the spring. And then they have this very elaborate way. They have free enough scouts, they go to the individual sites, they come back, they have this power, this dance literally where they dance for several days. They tried to recruit other needs. It's very complicated decision way. When they finally want to make a decision, the entire swarm, They're scouts warm up the entire swarm and then go to one location, they don't go to 50. The question, they go to one location that the scouts have agreed upon by themselves. That's awesome. If you look at the circuit complexity, it's 10 times more denser than anything we have in our brain. Now, they only have a million neurons. But then, you know, it's amazing, complex, complex behavior, very complicated circuitry. So there's no question. They experienced something. Their life is very different. They're tiny. They only live you know for for where workers live maybe for two months. So I think and I E. T. Tells you this in principle. The substrate of consciousness is the substrate that maximizes the cause effect power over all possible spatial temple grains. So when I think about for example, do you know the science fiction story? The black cloud. Mhm. Okay. It's a classic holiday astronomer. He has this cloud intervening between the earth and the sun and leading to some sort of two global cooling. This is written in the 50s. It turns out you can using the the radio dish. They communicate with actually an entity. It's actually intelligent entity. And they sort of they convince it to move away. So here you have a radical different entity. And in principle I. T. Says well you can measure the integrated information in principle at least. And yes if that if the maximum of that occurs at the time scale of months rather than enough. It's sort of a fraction of a second. Yes. And they would experience life where each moment is a month rather than a microsecond, right? Rather than a fraction of a second in in the human case. And so there may be forms of conscience that we simply don't recognize for what they are because they are so radical different from anything you and I are used to again that's why it's good to read </s>

<s>[INST] be pretty specific, like [/INST] I'll think through the scenes, if I, if I know the locations and everything and I have this idea of what I'm going to create, right? </s><s>[INST] And [/INST] then I'm there filming right? And always without fail, reality is something altogether different than what I thought it would </s><s>[INST] be. But it's still good to have the original idea. Yeah, [/INST] yeah. But if I tried to hold to that original vision, right? And to create a film out of that idea, they'd be crap. All the films that would be so we have to adapt. I have to evolve my approach and then embrace what is actually occurring with the people who are actually doing it </s><s>[INST] and then re envision, so that re envisioning [/INST] is very active </s><s>[INST] during the entire [/INST] filming process. And so that's the second creation. That's the </s><s>[INST] rethinking and re visualizing based on what we're actually experiencing and seeing [/INST] what this film is going to be. And then I finished filming, right? And we're, </s><s>[INST] we bring the hard drives [/INST] back and we plug in the hard drives um, in the edit bay. </s><s>[INST] And [/INST] oftentimes, you know, because it's two of us filming most of the time. </s><s>[INST] I haven't seen [/INST] all the footage </s><s>[INST] because in the field it's all about just [/INST] filming, right? And then just </s><s>[INST] transferring the footage and [/INST] getting on safely, you know, cloned to multiple drives. I don't have a chance to review everything. I can't do </s><s>[INST] rushes like you do [/INST] in a large feature. So because I'm filming, half of it, I know what I've filmed, right? But I haven't </s><s>[INST] seen everything. The director [/INST] of photography is filmed, </s><s>[INST] right? [/INST] So the next stage for </s><s>[INST] me is reviewing [/INST] every single frame </s><s>[INST] of what's been [/INST] filmed. And that's where Discovery happens </s><s>[INST] the third time [/INST] or second time. Another is is, wow. Now </s><s>[INST] I thought we'd [/INST] film this, but actually um there's this over here and then I have to open up this second </s><s>[INST] vision and turn it and [/INST] Transform it into a 3rd vision for the film </s><s>[INST] based on [/INST] what's actually on the hard drive. So, so </s><s>[INST] you're is this like a daily [/INST] process? So what I do the fruit my processes that </s><s>[INST] once, if it's a really difficult [/INST] project, I'll take a break before I go through this. Just just for healing, you know, and and some space away and fresh </s><s>[INST] eyes and usually that's about [/INST] a month. And then once I reengage reengage whole hog, I </s><s>[INST] re engage fully [/INST] and and it and </s><s>[INST] I review every single [/INST] frame and as I do that, I create a spreadsheet. </s><s>[INST] Um [/INST] and for Hunger War, </s><s>[INST] that spreadsheet was, [/INST] I don't know, 15 </s><s>[INST] 100 lines long [/INST] or something where </s><s>[INST] it's basically [/INST] log notes and I and I watch every </s><s>[INST] scene and I take [/INST] notes and I </s><s>[INST] I know really [/INST] what we have and once I've gone through that process that takes about a month and I really know what we </s><s>[INST] came back with. [/INST] I create an outline for the film from that and that's the third visioning right? Um that's </s><s>[INST] usually completely [/INST] different than my original vision for the film to some extent right? But I have to stay open </s><s>[INST] to that entire [/INST] process. Um or or I'd be trying to create something that I can't really </s><s>[INST] create. [/INST] So I think those are the three creations for me. That's </s><s>[INST] so cool to know what we [/INST] have. Um </s><s>[INST] Just to lay it all out and to load it [/INST] in into your mind because like this is the </s><s>[INST] capture of reality. We have. [/INST] It's a very kind of scientific </s><s>[INST] process too because you know in [/INST] science you collect a bunch of data about the phenomena and now you have </s><s>[INST] to like analyze that data but now you're [/INST] phenomena is long gone. </s><s>[INST] Just the data and you have to uh write a paper about it. Like analyze the data. It's a similar things. You [/INST] have to like load it </s><s>[INST] all in. Where's the story? How how do you [/INST] that last? </s><s>[INST] Probably profound piece of doing the editing like in your mind Like what how to lay those [/INST] things out? Well it's </s><s>[INST] almost like the scientific [/INST] process right? I have a hypothesis, </s><s>[INST] a creative [/INST] hypothesis right? Not a scientific </s><s>[INST] one. And but then I'm testing the [/INST] hypothesis during the course of filming </s><s>[INST] right? And I have to [/INST] stay true to what the data tells </s><s>[INST] me in the end. [/INST] Creatively. So </s><s>[INST] it's very similar to the scientific [/INST] process is I don't know what we should, </s><s>[INST] you should probably [/INST] coin that. Yeah that's </s><s>[INST] pretty creative scientific process, something [/INST] like that. But </s><s>[INST] then you [/INST] actually do the edit and </s><s>[INST] you watch [/INST] that's also </s><s>[INST] uh iterative in the sense because maybe [/INST] when </s><s>[INST] You have a film that's 2030, 40 minutes or if its feature line, [/INST] uh </s><s>[INST] like it, [/INST] do you ever have it </s><s>[INST] where it sucks? [/INST] Like </s><s>[INST] it's not a stage where it looks like a stage where, Right? Right? [/INST] Like it's where he's like, no, </s><s>[INST] this is not. [/INST] This is not what I was about. Like when </s><s>[INST] it's all put together in this way, this [/INST] doesn't this </s><s>[INST] is not working right? This is not right? [/INST] Or do you, is it always like an incremental </s><s>[INST] step towards better and better? It's [/INST] incremental, incremental And there's always some moment </s><s>[INST] in the editing [/INST] process where there's a breakthrough, </s><s>[INST] whereas suddenly I understand how it fits together [/INST] more fully. </s><s>[INST] And you have to be like you said, resilient, you have to be patient that that moment will come. Are you ultra self critical [/INST] or are you generally </s><s>[INST] optimistic and [/INST] patient? </s><s>[INST] I don't think those [/INST] are mutually exclusive. </s><s>[INST] Right? So you just oscillate or you or they're like dance partners and [/INST] their dance partners? </s><s>[INST] Yeah, definitely. Dance, [/INST] you know, all the way through the </s><s>[INST] process by way [/INST] of advice. </s><s>[INST] You know, two young filmmakers how [/INST] to film something </s><s>[INST] that um [/INST] is </s><s>[INST] recognized by the world in some [/INST] way, I would say, you know, first off, </s><s>[INST] learn your craft, [/INST] right? Because </s>

<s>[INST] lost his sense of humor. [/INST] No, no, no, no. Well, yes. But from that day on he, he left on his own. He stopped taking cues for me. So I want to say that, you know, it was a good thing that I did, </s><s>[INST] but it was mostly means [/INST] yes, but it was mostly me. But it's true though. It's true, right? That the people, I think you're right. </s><s>[INST] But okay. So that's where does that get us? That gets us the idea that, I mean, certainly movie theaters are a thing, right? Where people like to be watching together, even though the people on the screen can aren't really co present with the people in the audience. The audience is present with themselves by the way. At that point, it's an open question is being raised by this. Whether movies will no longer be a thing because netflix is audience is growing. So that's, it's a, it's a very parallel question for education. Will movie theaters still be a thing right? In 2000 and I think, I think the argument is that there is a feeling of being in the crowd that isn't replicated by being at home watching it and that there's value in that. And then I think just, but it scales better online. [/INST] I feel like we're having a conversation about whether concerts will still exist after the invention of the record or the cd or wherever it is. Right? You're right, concerts are dead. Um, well, </s><s>[INST] okay. Before I think the joke is only funny if you say it before [/INST] now, </s><s>[INST] right? Yeah, three years ago. It's like, well no, obviously always to publish this until we have a [/INST] vaccine now, you know, we'll fix it in post. But I think the, the important thing is the virus, concerts changed </s><s>[INST] right? [/INST] First of all, movie theaters weren't this way right? In like the sixties and seventies, they weren't like this. Like blockbusters were basically what with jaws and star wars created blockbusters right? Before then there weren't like the whole summer shared summer experience didn't exist In our lifetimes. Right? Certainly you are well into adulthood by the time this country. So it's just a very different. It's very different. So what, what we're, we've been experienced in the last 10 years. It's not like the majority of human history, but more importantly concerts, right? Concerts means something. Most people don't go to concerts anymore. Like there's an age where you care about it, you sort of stop doing what you keep listening to music or whatever and not at all. So I think that's a painful way of saying that. Um, it will change. It's not the same thing as a going away replaces too strong of a word, but it will change. It </s><s>[INST] has to actually like to push back. I wonder because I think you're probably just throwing that your intuition out I want. Uh and it's possible concerts more people go to concerts now. But obviously much more people listening to this dumb when they then before there was records, uh, it's it's possible to argue that uh if you look at the data uh that it just expanded the pie of what music listening means. It's possible that like universities grow in the, in the parallel or the theaters grow. But also more people get to watch movies, more people get uh like be educated. So I hope that you, and to the extent that we can grow the pie and have education being not just something you do for four years when you're done with your other education. Um, but it would be a more lifelong thing that would have tremendous benefits, especially as the economy in the world changed rapidly. People need opportunities to stay abreast of these changes. And so I don't know, I could, I could, it's all part of the ecosystem. [/INST] It's all to the good. I mean, you know, I'm not gonna have an argument about whether we lost fidelity, we went from laser, just the DVds or record players to cds. I mean I'm willing to grant that that is true. But convenience matters And the ability to do something that you couldn't do otherwise because of the convenience matters. And you can tell me I'm only getting 90% of the experience, but I'm getting the experience, I wasn't getting it before or wasn't lasting as long or it wasn't as, I mean this just seems this just seems straightforward to me. It's gonna, it's going to change. It is for the good that more people get access and it is our job to do two separate things, One to educate them and make access available, that's our mission, but also for very simple selfish reasons, we need to figure out how to do it better so that we individually stay in business, we can do both of those things at the same time. They are not in um they maybe intention but they are not mutually exclusive. </s><s>[INST] So you've educated some scary number of people. So you've seen a lot of people succeed, find their path through life. Is there a device that you can give to a young person today about computer science, education about education in general, about life, about uh whatever the journey That one takes in there maybe in their teens in their early 20's sort of in those underground years as you try to go through the essential process of partying and not going to classes and yet somehow trying to get a degree [/INST] if you get to the point where you're far enough up in the, in the hierarchy of needs that you can actually make decisions like this, then find the thing that you're passionate about and pursue it and sometimes it's the thing that drives your life and sometimes it's secondary and you'll do other things because you've got to eat right, you got a family, you gotta feed, you've got people, you have to help or whatever and I understand that and it's not easy for everyone, but um always take a moment or two to pursue the things that you love, the things that bring passion and happiness to your life, and if you don't, I know that sounds corny, but I genuinely believe it, and if you don't have such a thing then you're lying to yourself, you have such a thing, you just have to find it and it's okay if it takes you a long time to get there. Rodney Dangerfield became a comedian in his fifties, I think it certainly was in his twenties, and lots of people failed for a very long time before getting to where they were going. Um you know, I try to have hope and it wasn't obvious. I mean, you know, you and I talked about the experience that I had a long time ago with with a particular police officer wasn't my first one, wasn't my last one, um but you know, in my view, I wasn't supposed to be here after that and I'm here. So it's all gravy, so you might as well go ahead and grab life as you can because of that. That's that's sort of how I see it, while recognizing, again, the delusion matters, right, allow yourself to be deluded, allow yourself to believe that it's all gonna work out just don't be so deluded that you you missed the obvious, uh and you're going to be fun, it's going to be there, it's going to be, they're gonna work out </s>

<s>[INST] 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 dan Carlin. Let's start with the highest philosophical question, do you think human beings are fundamentally good or are all of us capable of both good and evil and it's the environment that molds, how we, the trajectory that we take their life, [/INST] How do we define evil, evil seems to be a situational eye of the beholder kind of question. So if we define evil, maybe I can get a better idea of and, and and that could be a whole show couldn't defining evil. But when we say evil, what do we mean? </s><s>[INST] That's a slippery one. But I think there's some way in which your existence, your presence in the world leads to pain and suffering and destruction for many others in the rest of the world. So you you steal the resources and you use them to create more suffering than there was before in the world. So I suppose it's somehow deeply connected to this other slippery award was just suffering as you create suffering in the world. You bring suffering to the world. [/INST] But here's the problem. I think with it because I, I fully see where you're going with that and I understand it. The problem is, is the question of the reason for inflicting suffering. So sometimes one might inflict suffering upon one group of individuals in order to maximize a lack of suffering with another group of individual or one who might not be considered evil at all, might make the rational, seemingly rational choice of inflicting pain and suffering on a smaller group of people in order to maximize the opposite of that for a larger group of </s><s>[INST] people. Yeah, that's one of the dark things about, I've spoken and read the work of Stephen Kotkin, I'm not sure if you're familiar with the historian and he's basically a Stalin, uh joseph Stalin scholar. And one of the things I realized, I'm not sure where to put Hitler, but with Stalin, it really seems that he was sane and he thought he was doing good for the world. I really believe from everything I've read about Stalin that he believed that communism is good for the world. And if you have to kill a few people along the way, it's like you said, the small groups, if you have to sort of remove the people that stand in the way of this utopian system of communism, then that's actually good for the world. And it didn't seem to me that he could even consider the possibility that he was evil. He really thought he was doing good for the world. And that's stuck with me because he's one of the most is to our definition of evil. He seems to have brought more evil onto this world than almost any human in history and I don't know what to do with that. [/INST] Well, I'm fascinated with the concept, so fascinated by it that the very first hardcore history show we ever did, which was a full 15 or 16 minutes um was called alexander versus Hitler and the entire question about it was the motivations, right? So if you go to a court of law because you killed somebody, One of the things they're going to consider is why did you kill them, right? And if you killed somebody, for example, in self defense, you're going to be treated differently than if you maliciously killed somebody maliciously to take their wallet, right? And in the show, we we wondered because, you know, I don't really make pronouncements, but we wondered about, uh, if you believe Hitler's writings, for example, Minkoff, which, you know, is written by a guy who's a political figure who wants to get off. So, I mean, it's about as believable as any other political tract would be, but in his mind, the things that he said that he had to do were designed to for the betterment of the german people, right? Whereas alexander the Great, Once again, this is somebody from more than 2000 years ago. So with lots of propaganda in the intervening years. But one of the views of alexander the Great, is that the reason he did what he did was to, for lack of a better word, write his name in a more permanent graffiti on the pages of history, right? In other words, to glorify himself. And if that's the case, does that make alexander a worst person, that Hitler, because Hitler thought he was doing good. Whereas alexander, if you believe the interpretation was simply trying to exalt alexander. So, the motivations of the people doing these things, it seems to me matter, um I don't think you can just sit there and go, the only thing that matters is the end result because that might have been an unintentional byproduct, in which case that person had, you been able to show them the future might have changed what they were doing. So were the evil or misguided or wrong or made, you know, so, and I hate to do that because there's certain people like Hitler that I don't feel deserve the benefit of the doubt at the same time, if you're fascinated by the concept of evil and you delve into it deeply enough, you're going to want to understand why these evil people did what they did. And sometimes it can confuse the hell out of you, You know, who wants to sit there and try to see things from Hitler's point of view to get a better understanding and, and sort of commiserated with. So. Um, but I'm obviously first history show, I'm fascinated with the concept. </s>

<s>[INST] so I remember hearing about this, I think Dan Savage is a podcast. I think they're called furries. Furries. [/INST] Like furry parties. Yeah, exactly. I love people. Yeah, you know, that's like the thing. It's like whenever you hear these words, it's like humans, what would I think of next? So, but I do think that, and I write about this in Hacking Darwin, that as people come to believe that making children through the application of science is safer and more beneficial than having children through sex, we'll start to see a shift over time toward reproduction through science. We'll still have sex for all the same great reasons that we do it now. It's just reproduction less and less </s><s>[INST] through the act of sex. I love people. Yeah, I know. Man, it's such a fascinating future. Because as somebody, I value flaws. I think it's the good will hunting. That's the good stuff. The flaws, the weird quirks of humans, that's what makes us who we are, the weird. The weird is the beautiful, and there's a fear of optimization. [/INST] You should have it. I mean, it's very healthy. And I think that's the danger of all of this selection is that we make selections just based on social norms that are so deeply internal that they feel like they're eternal truths. And so we talked about selecting for IQ. What about selecting for a kind heart? Like there are lots of you. You talked about Hitler and Mein Kampf. Hitler has certainly had a high IQ, I guess is higher than average IQ. If we just select, I mean, that's why I was saying before, diversity is baked into our biology. But the key lesson, and I've said this many times before, the key lesson of this moment in our history is that after nearly 4 billion years of evolution, our one species suddenly has the unique and increasing ability to read, write, and hack the code of life. And so as we apply these God-like powers that we've now assumed for ourselves, we better be pretty careful because it's so easy to make mistakes, particularly mistakes that are guided by our best intentions. </s><s>[INST] To jump briefly back onto lab leak, and I swear there's a reason for that. What did you think about the John Stewart? This moment, I forget what it was, maybe a few months ago, in the summer, I think, of 2021, where he went on Colbert Report, or not the Colbert Report, sorry, Stephen Colbert's, whatever his show is. But again, John Stewart reminded us how valuable his wit and brilliance within the humor was for our culture. And so he did this whole bit that highlighted the common sense nature about what was the metaphor he used about the Hershey factory in Pennsylvania. [/INST] So what'd you think about that whole bit? I loved it. And so not to be overly self-referential, but it's hard not to be overly self-referential when you're doing a, however long we are, five-hour interview about yourself. Which reminds me, when you had Brett Weinstein on, and he said, I have no ego, but these 57 people have screwed me over, and I deserve credit. It's hard, it's hard to mock them. I am a person I will confess, it's enjoyable. Some people feel different. I kind of like talking about all this stuff and talking, period. So for me, in the earliest, I remember those early days when the pandemic started, I was just sitting down, it was late January or early February, 2020, and I just was laying out all of the evidence, just that I could collect, trying to say, make sense of where does this come from? And it was just logic. I mean, it was all of the things that John Stewart said, which in some overly wordy form, were all at that time on my website. Like, what are the odds of having this outbreak of a bad coronavirus more than a thousand miles away from where these bats have their natural habitat, where they have the largest collection of these bat coronaviruses in the world, and they're doing all these very aggressive research projects to make them more aggressive, and then you have the outbreak of a virus that's primed for human to human transmission. It was just, logic was my first step, and I kept gathering the information. But John Stewart distilled that in a way that just everybody got, and I think that, like, I loved it, and I just think that there's a way of reaching people. It's the reason why I write science fiction in addition to thinking and writing about the science, is that we kind of have to reach people where they are, and I just thought it was just, there was a lot of depth, I thought, and maybe that's too self-serving, but, like, in the analysis, but he captured that into those things about, it's like the, whatever, the outbreak of chewy goodness near the Hershey factory. </s>

<s>[INST] because then I'm not growing. Yeah, but then again, it could be like with chess. An AI, once it's significantly, obviously supersedes the performance of humans, it will live in its own world and provide maybe a flourishing civilizations for humans, but we humans will continue hiking mountains and playing our games, even though AI is so much smarter, so much stronger, so much superior in every single way, just like with chess. I mean, that's one possible hopeful trajectory here is that humans will continue to human and AI will just be a kind of a medium [/INST] that enables the human experience to flourish. Yeah, I would phrase that as rebranding ourselves from homo sapiens to homo sentiens. Right now, sapiens, the ability to be intelligent, we've even put it in our species name. We're branding ourselves as the smartest information processing entity on the planet. That's clearly gonna change if AI continues ahead. So maybe we should focus on the experience instead, the subjective experience that we have with homo sentiens and say that's what's really valuable, the love, the connection, the other things. Get off our high horses and get rid of this hubris </s><s>[INST] that only we can do integrals. So consciousness, the subjective experience is a fundamental value to what it means to be human. [/INST] Make that the priority. That feels like a hopeful direction to me, but that also requires more compassion, not just towards other humans because they happen to be the smartest on the planet, but also towards all our other fellow creatures on this planet. And I personally feel right now we're treating a lot of farm animals horribly, for example, and the excuse we're using is, oh, they're not as smart as us. But if we're not that smart in the grand scheme of things either in the post AI epoch, then surely we should value the subjective experience of a cow also. </s><s>[INST] Well, allow me to briefly look at the book, which at this point is becoming more and more visionary that you've written, I guess over five years ago, Life 3.0. So first of all, 3.0. What's 1.0? What's 2.0? What's 3.0? How's that vision sort of evolve, [/INST] the vision in the book evolved to today? Visionary to you. Life 1.0 is really dumb, like bacteria, in that it can't actually learn anything at all during the lifetime. The learning just comes from this genetic process from one generation to the next. Life 2.0 is us and other animals which have brains, which can learn during their lifetime a great deal. You were born without being able to speak English, and at some point you decided, hey, I wanna upgrade my software. Let's install an English speaking module. So you did? Life 3.0 does not exist yet, can replace not only its software the way we can, but also its hardware. And that's where we're heading towards at high speed. We're already maybe 2.1, because we can put in an artificial knee pacemaker, et cetera, et cetera. And if Neuralink and other companies succeed, we'll be Life 2.2, et cetera. But what the company's trying to build AGI or trying to make is of course full 3.0, and you can put that intelligence in something </s><s>[INST] that also has no biological basis whatsoever. So less constraints and more capabilities, just like the leap from 1.0 to 2.0. There is nevertheless, you speaking so harshly about bacteria, so disrespectfully about bacteria. There is still the same kind of magic there that permeates Life 2.0 and 3.0. It seems like maybe the thing that's truly powerful about life intelligence and cautiousness was already there in 1.0. [/INST] Is it possible? I think we should be humble and not be so quick to make everything binary and say either it's there or it's not. Clearly there's a great spectrum and there is even a controversy by whether some unicellular organisms like amoebas can maybe learn a little bit. After all, so apologies if I offended you. It wasn't my intent. It was more that I wanted to talk up how cool it is to actually have a brain where you can learn dramatically within your lifetime. Typical human. And the higher up you get from 1.0 to 2.0 to 3.0, the more you become the captain of your own ship, the master of your own destiny, and the less you become a slave to whatever evolution gave you, right? By upgrading your software, we can be so different from previous generations and even from our parents, much more so than even a bacterium. No offense to them. And if you can also swap out your hardware and take any physical form you want, of course, really the sky's the limit. </s><s>[INST] Yeah, typical human. Yeah, so it accelerates the rate at which you can perform the computation [/INST] that determines your destiny. Yeah, and I think it's worth commenting a bit on what you means in this context also if you swap things out a lot, right? This is controversial, but my current understanding is that life is best thought of not as a bag of meat or even a bag of elementary particles, but rather as a system which can process information and retain its own complexity, even though nature is always trying to mess it up. So it's all about information processing. And that makes it a lot like something like a wave in the ocean, which is not, it's water molecules, right? The water molecules bob up and down, but the wave moves forward, it's an information pattern. And the same way you, Lex, you're not the same atoms as during the first time you did with me. You've swapped out most of them, but it's still you. And the information pattern is still there. And if you could swap out your arms and whatever, you can still have this kind of continuity. It becomes much more sophisticated sort of wave forward in time where the information lives on. I lost both of my parents since our last podcast. And it actually gives me a lot of solace that this way of thinking about them, they haven't entirely died. A lot of mommy and daddy's, sorry, I'm getting a little emotional here, but a lot of their values and ideas and even jokes and so on, they haven't gone away, right? Some of them live on, I can carry on some of them. And we also live on a lot of other people. So in this sense, even with Life 2.0, we can to some extent already transcend our physical bodies and our death. And particularly if you can share your own information, your own ideas with many others, like you do in your podcast, then that's the closest immortality </s>

<s>[INST] I have to ask you about the wizard hat, you wrote a blog about neuralink? I I got a chance to visit and you only got a couple of times hanging out with those folks. Um you're, that was one of the pieces of writing you did that like changes culture and changes the way people think about a thing. The ridiculousness of your stick figure drawings are somehow, it's like, you know, it's like calling the Origin of the universe the Big Bang. It's a silly title but it somehow sticks to be the representative of of that in the same way the wizard had for the neural link is um somehow it was a really powerful way to, to explain that you actually proposed that the man of the year cover of Time should be one of your drawings? Yes, this is an outrage that it was Okay. So uh, what are your thoughts about like all those years later about neuralink? Do you find this idea? Like what excites you about is the big long term philosophical things? Is that the practical things do you think is super difficult to do on the neurosurgery side and the material engineering, the robotic side or do you think um, the machine learning side for the brain computer interfaces where they get to learn about each other, all that kind of stuff, I would just love to get your thoughts because you're one of the people that really considered this problem, really studied it, computer interfaces. [/INST] I mean, I'm super excited about it. It's a, I really think it's actually Elon's most ambitious thing more than colonizing mars, because that's just a bunch of people going somewhere, even though it's somewhere far neuralink is changing when a person is um eventually now, I I think that neuralink engineers and Elon himself would all be the first to admit that it is a maybe that whether they whether they can do their goals here, I mean, it is so crazy ambitious to try to their eventual goals are, you know, of course, in the in the interim they have a higher probability of accomplishing smaller things which are still huge, like basically solving paralysis. Uh you know, stroke Parkinson, things like that, I mean, it can be unbelievable and you know, anyone who doesn't have one of these things like we might, you know, we should everyone should be very happy about um this kind of helping with different disabilities. Um but the thing that is like, so the grand goal is this augmentation where it's, you take someone who's totally healthy and you put a cream machine interface in any way to give them superpowers. Um you know, it's the possibilities that they can do this if they can really, so, you know, they've already shown that they are for real, but you know, they've created this robot. Ellen talks about like it should be like LASIK where it's not it shouldn't be something that needs a surgeon. There shouldn't just be for rich people who have waited in line for six months. It should be for anyone who can afford LASIK and eventually hopefully something that isn't covered by insurance and you know, something that anyone can do um something this big a deal should be something that anyone can afford. Eventually and when we have this again, I'm talking about a very advanced phase down the road. So maybe a less advanced phase just just there may be right now if you think about when you listen to me, when you listen to a song, what's happening is do you actually hear the sound? Well, not really, it's that the sound is coming out of the speaker. The speaker is vibrating, it's vibrating. Air molecules, those air molecules, you know get vibrated all the way to your your head um uh pressure wave and then it vibrates your ear drum. Your ear drum is really the speaker now in your head that then vibrates bones and fluid. Which then but it stimulates neurons in your auditory cortex which give you the perception that you're hearing sounds now, if you think about that, do we really need to have a speaker to do that? You could just somehow if you had a little tiny thing that could vibrate ear drums, you could do it that way, that seems very hard, but really what you needed to go to the very end with the thing that really needs to happen is your auditory cortex neurons need to be stimulated in a certain way. If you have a ton of neuralink things in their neuralink electrodes and they get really good at stimulating things, you could play a song in your head that you hear that not is not playing anywhere, there's no sound in the room, but you here and no one else could and it's not like they can get close to your head and here, there's no sound, they could not hear anything but you hear sound, you can turn up, you open your phone, you have the neuralink app, you open the neuralink gap, you know, and and or just neural. So, so basically you can open your Spotify and you can play too, you know, you're you can play to your speaker, you can play to your computer, you can play right out of your phone, to your headphones or you can, you have now have a new one, you can play into your brain. And this is one of the earlier things, this is, you know, something that seems like really doable. Um, so, you know, no more headphones, I always think that's so annoying because I can leave the house with just my phone, you know, and nothing else or even just an Apple watch, but there's always this one thing like and headphones, you do need your headphones. Right? So I feel like you know that'll be the end of that. But there's so many things that you and you keep going, the ability to think together. You know, you can talk about like super brains. I mean one of the examples Ellen uses is that the low bandwidth of speech um if I go to a movie and I and I come out of a scary movie and you see how was I said it was terrifying. Well what did I just do? I just gave you, I just gave you, I had five buckets. I could have given you one was horrifying, terrifying, scary, eerie, creepy, whatever that's about it. And I had a much more nuanced experience than that. And I don't, all I have is you know these, these words right? And so instead I just hand you the bucket. I put the stuff in the in the bucket and give it to you. But all you have is the bucket. You just have to guess what I put into that bucket. All you can do is look at the label of the bucket and say I'll when I say terrifying, here's what I mean. So the point is it's very lossy. I have this all this new nuanced information of what I thought of the movie and I'm sending you a very low rez package that you're gonna now guess what the high res thing looked like. That's language in general. Our thoughts are much more nuanced and we can think to each other, we can do amazing things. We could have a brainstorm that doesn't feel like, oh we're not talking in each other's heads, not just that I hear your voice. No, no, no. We are just thinking, no, no words are being said internally or externally. The two brains are literally collaborating is something, it's a skill. I'm sure we'd have to get good at it. I'm sure young kids will be great at it and old people will be bad. But you think together and together you like, had they joined Epiphany and how how about eight people in a room doing it, right? So it gets, you know, there's other examples how about when you're a dress designer or a bridge designer and you want to show people what your dress looks like. Well right now, you got to sketch it for a long time here, just beam it onto the screen from your head. So you can picture it. If you know, if you can picture a tree in your head, well you can just suddenly whatever's in your head, you can be pictured. So we'll have to get very good at it right and take a skill, right? You know, you're gonna have to but the possibilities. My God talk about like I feel like if that works, if we really do have that as something. I think it will almost be like a new A D. B. C. Line. It's such a big change that the idea of like anyone living before everyone had brain machine interfaces is living in like before the common era. It's that level of like big change if it can work. </s>

<s>[INST] what about space of like healthcare? This is where you get into attention of like between capitalism and kind of more, I don't want to use socialism, but those kinds of policies that are less free market, [/INST] I think in this country, healthcare should be much more competitive. So you go to hospitals, doctors, they don't treat you like a customer. They treat you like an idiot or like a child or someone with third party payment and it's a pretty humiliating experience often. </s><s>[INST] Yeah. Do you think free market in general is possible? Like a pure free market? And is that a good goal to strive for? [/INST] I don't think the term pure free markets well defined because you need a legal order. Legal order has to make decisions on like what is intellectual property more important than ever? There's no benchmark that like represents the pure free market way of doing things. Uh, what will penalties be? How much do we put into law enforcement? No simple answers. But just saying free market doesn't pin down what you're going to do on those all important questions. So, </s><s>[INST] free market is a, is an economics, I guess, idea. So there's no, it's not possible for free markets generate the rules. They're like emergent like self governing. [/INST] It generates a lot of them right through private norms, through trade associations. International trade is mostly done, uh, privately and by norms. So it's certainly possible. But at the end of the day, I think you need governments to draw a very clear lines to prevent it from turning into mafia run systems. </s><s>[INST] You know, I've been hanging out with, with other group of Weirdos lately, Michael malice who's, uh, who exposes to be an anarchist anarchism, Which is like, I think intellectually just a fascinating set of ideas where the, you know, taking free market to the full extreme of basically saying there should be no, no government, what is it oversight, I guess? And then everything should be fully, like all the agreements, all the collective's you form should be, uh, voluntary, not based on the geographic land you're born on and so on. Do you think that's just a giant mess? Like, do you think it's possible for an anarchist society to work where it's, um, you know, in a, in a fully distributed way, people agree with each other, not just on financial transactions, but, you know, on, um, on their personal security and sort of military type of stuff, uh, healthcare and education, all those kinds of things. And where does it break down? [/INST] Well, I wouldn't press a button to say, get rid of our current constitution, which I view is pretty good and quite wise. But I think the deeper point is that all societies are in some regards anarchistic, and we should take the anarchist seriously. So globally, there's a kind of anarchy across borders, even within federalist IQ systems, they're typically complex. There's not a clear transitive itty necessarily of who has the final say over what? Just the state vis a vis its people, there's not per se a final arbitrator in that regard. So you want a good anarchy rather than a bad anarchy? If you want to squish your anarchy into the right corners. And I don't think there's a theoretical answer how to do it, but you start with the country, like, is it working well enough now, this country you'd say mostly you'd certainly want to make a lot of improvements, and that's why I don't want to press that, get rid of the constitution button. But to just dump on the anarchists is to miss the point. Always try to learn from any opinion, you know, and what in it is true. </s><s>[INST] I'm just like marveling at the, at the poetry of saying that we should squish our energy into the right corners. Love it. Okay, I gotta ask, I've been talking with uh, since we're doing a world Wind introduction to all of economics, I've been talking to a few objectivist recently and just, you know, I'm ran comes up as a as a person, as a philosopher. Throughout many conversations, a lot of people really despise her. A lot of people really love her. It's always weird to me when somebody arouses a philosophy or a human being arouses that much emotion in either direction. Does she make? Do you understand, first of all, that level of emotion? And what are your thoughts about Ayn rand and her philosophy objectivism? Is it useful at all, uh, to think about this kind of formulation of uh, rational self interest, if I could put it in those words, or I guess more negatively the selfishness or she would put I guess the virtue of selfishness [/INST] ein rand was a big influence on me growing up, the book that really mattered for me was capitalism, the unknown ideal. The notion that wealth creates opportunity and good lives and wealth is something we ought to value, rise and give very high status. It's one of her key ideas. I think it's completely correct. I think she has the most profound and articulate statement of that idea that said as a philosopher, I disagree with her on most things and I did, even, like as a boy when I was reading her, I read Plato before I ran and in a Socratic dialogue, there's all these different points of view being thrown around and whomever it is. You agree with. You understand the wisdom is in coming together at the different points of view, and she doesn't have that. So altruism can be wonderful. In my view, humans are not actually that rational self interest is often poorly defined to pound the table and say existence exists. I wouldn't say I disagree, but I'm not sure that it's a very meaningful statement. I think the secret to Ayn rand is that she was Russian, I'd love to have her on my podcast if she was still alive. I'd only ask her about Russia, which he mostly never talked about after writing We the living and she is much more Russian, then she seems at first even like purging people from the objectivist circles, it's like how Russians, especially female Russians so often purged their friends. It's weird all the parallels. </s>

<s>[INST] But it's a small change in I feel like people who are thinking about intelligence are not conceptualizing it that way. I actually haven't met too many people who believe that a neural network we'll be able to reason who seriously think that rigorously because I think it's actually interesting worldview and and we'll talk about it more. But it's been impressive what uh what neural networks have been able to accomplish. And I, to me, I don't know, you might disagree, but it's an open question whether like, like scaling size eventually might lead to incredible results to us, mere humans will appear as if it's general. [/INST] I mean, if you if you ask people who are seriously thinking about intelligence, they will definitely not say that all you need to do is is like the minus just in your network. However it's actually with you that's that's very popular. I think the deep learning community, that many people are kind of uh conceptually, you know, intellectually lazy about it, </s><s>[INST] right. But what I guess what I'm saying Exactly right is uh I haven't met many people and I think it would be interesting to meet a person who is not intellectually is about this particular topic and still believes that neural networks will go all the [/INST] way. I think, yeah, it's probably closest to that was provided to argue that uh currently planning techniques are already the way to general artificial intelligence and that's all you need to do is to scale it up to all the available train data. And that's if you look at the waves, that opening eyes, GPT stream model has made you see echoes of this idea. </s><s>[INST] So on that topic, GPT three, similar to GPT two actually have captivated some part of the imagination of the public. There's just a bunch of hype different kind. It's, I would say it's emergent. It's not artificially manufactured. It's just like people just get excited for some strange reason. And in the case of GPT three, which is funny that there is, I believe a couple of months delay from a release to hype, maybe I'm not historically correct on that, but it feels like there was a little bit of a uh lack of hype and then there's a phase shift into into hype. But nevertheless, there's a bunch of cool applications that seem to captivate the imagination of the public about what this language model that's trained in unsupervised way without any fine tuning is able to achieve. So what do you make of that? What are your thoughts about GPT three? [/INST] Yeah, So I think what's interesting about it is three is the idea that it may be able to learn new tasks in after just being shown a few examples? So I think it's actually capable of doing that that's novel and that's very interesting and that's something we should investigate. That. Said, I must say I'm not entirely convinced that we have shown it's capable of doing that. It's very likely given the amount of data that the model is trained on that what is actually doing is better matching a new task. You give it with the task that it's been exposed to any strain data. It's just recognizing the task instead of just developing a model of the task. Right? </s><s>[INST] But there's uh sorry to interrupt. There's a parallel to what you said before. Which is it's possible to see GPT three as like the prompt that's given as a kind of SQL Corey into this thing that has learned similar to what you said before, which is language is used to quarry the memory. So is it possible that neural network because the giant memorization thing? But then if it gets sufficiently giant will memorize sufficiently large amounts of things of the world, where it becomes more intelligence becomes aquarian [/INST] machine. I think it's possible that a significant chunk of intelligence is this giant associative memory. Uh I definitely don't believe that intelligence is just a giant associative memory but it may well be a big component. </s><s>[INST] So do you think GPT three? Four? Five? GPT 10 will eventually? Like what do you think? Where's the ceiling do you think you'll be able to reason? Um No that's a bad question. Uh like what is the ceiling is the better question? [/INST] How the world is gonna scare? How good is GPT N going to be? Yeah. So I believe GPT N is gonna be T. N. Is going to improve on the strength our GPT two and three which is it will be able to generate you know ever more plausible text in context, promise performance. Um Yes, if you train, if you're trying to begin model on more data than uh your text will be increasingly more context aware and increasingly more plausible in the same way that GPT three, it is much better generating plausible tax compared to GPT two. But that said, I don't think just getting up the model to more transformer layers and more training that is going to address the flaws GTT three which is that it can generate plausible text but the text is not constrained by anything else other than possibility. So in particular is not constrained by factual nous or even consistency, which is why it's very easy to get GPT Street to generate statements that are factually untrue or to general statements that I even self contradictory right? Because it's uh it's it's only goal is plausibility and it does no other constraints. It's not concerned to be self consistent for instance. Right. And so for this reason? One thing that I thought was very interesting which would be the string is that you can prove their mind the answer it will give you by asking the question especially square because it's very responsive to the way you ask the question. Since it adds no understanding of the content of the question. Right? Yeah. And if you if you are the same question in two different ways that are basically adversary engineered to produce certain answer, you will get two different answers to contract our answers. </s>

<s>[INST] and then it would be there. And then it would be there. Just to confess a small thing, don't ask me why, but I'm doing this physical challenge currently where I'm doing 680 pushups and pull ups a day. And my shoulder is currently as we sit here in a lot of pain. And I don't know, I would certainly right now, if you gave me a dial, I would turn that sucker to zero as quickly as possible. But I don't, I think the whole point of this journey is, [/INST] I don't know. Well, because you're a twisted human being. </s><s>[INST] I'm a twisted, so the question is, am I somehow twisted because I created some kind of narrative for myself so that I can deal with the injustice and the suffering in the world? Or is this actually going to be a source of happiness? [/INST] Well, this is a, to an extent is a research question that humanity will undertake, right? </s><s>[INST] So I mean, human beings, humanity, right? [/INST] So I mean, human do have a particular biological makeup, which sort of implies a certain probability distribution over motivational systems, right? So I mean, we, and that is there, that is there. Now the question is, how flexibly can that morph as society and technology change, right? So if we're given that dial and we're given a society in which say we don't have to work for a living and in which there's an ambient decentralized benevolent AI network that will warn us when we're about to hurt ourself. You know, if we're in a different context, can we consistently with being genuinely and fully human, can we consistently get into a state of consciousness where we just want to keep the pain dial turned all the way down and yet we're leading very rewarding and fulfilling lives, right? No, I suspect the answer is yes, we can do that, but I don't know that for certain. Yeah, no, I'm more confident </s><s>[INST] that we could create a non-human AGI system [/INST] and that is there, I don't know that, which just didn't need an analog of feeling pain. And I think that AGI system will be fundamentally healthier and more benevolent than human beings. So I think it might or might not be true that humans need a certain element of suffering to be satisfied humans, consistent with the human physiology. If it is true, that's one of the things that makes us fucked and disqualified to be the super AGI, right? I mean, this is the nature of the human motivational system is that we seem to gravitate towards situations where the best thing in the large scale is not the best thing in the small scale according to our subjective value system. So we gravitate towards subjective value judgements where to graph ourselves in the large, we have to un-graph ourselves in the small. And we do that in, you see that in music, there's a theory of music which says the key to musical aesthetics is the surprising fulfillment of expectations. Like you want something that will fulfill the expectations of listed in the prior part of the music, but in a way with a bit of a twist that surprises you. And I mean, that's true not only in outdoor music like my own or that of Zappa or Steve Vai or Buckethead or Christoph Pundericke or something. It's even there in Mozart or something. It's not there in elevator music too much, but that's why it's boring, right? But wrapped up in there is, we want to hurt a little bit so that we can feel the pain go away. Like we want to be a little confused by what's coming next. So then when the thing that comes next actually makes sense. </s><s>[INST] It's so satisfying, right? That's the surprising fulfillment of expectations. Is that what you said? Yeah, yeah, yeah. So beautifully put. Is there, we've been skirting around a little bit, but if I were to ask you the most ridiculous big question of what is the meaning of life, [/INST] what would your answer be? Yeah, yeah, yeah. It's so beautiful. Three values, joy, growth, and choice. I think you need joy. I mean, that's the basis of everything. If you want the number one value. On the other hand, I'm unsatisfied with a static joy that doesn't progress, perhaps because of some elemental element of human perversity, but the idea of something that grows and becomes more and more and better and better in some sense appeals to me. But I also sort of like the idea of individuality that as a distinct system, I have some agency. So there's some nexus of causality within this system rather than the causality being wholly evenly distributed over the joyous growing mass. So you start with joy, growth, and choice as three basic values. </s><s>[INST] Those three things could continue indefinitely. That's not, that's something that can last forever. Is there some aspect of something you called, which I like super longevity that you find exciting? That's what, is there in research wise, [/INST] is there ideas in that space that? I mean, I think, yeah, in terms of the meaning of life, this really ties into that because for us as humans, probably the way to get the most joy, growth, and choice is transhumanism and to go beyond the human form that we have right now, right? I mean, I think human body is great and by no means do any of us maximize the potential for joy, growth, and choice imminent in our human bodies. On the other hand, it's clear that other configurations of matter could manifest even greater amounts of joy, growth, and choice than humans do, maybe even finding ways to go beyond the realm of matter that as we understand it right now. So I think in a practical sense, much of the meaning I see in human life is to create something better than humans and go beyond human life, but certainly that's not all of it for me in a practical sense, right? Like I have four kids and a granddaughter and many friends and parents and family and just enjoying everyday human social existence. Well, we can do even better. Yeah, yeah, and I mean, I love, I've always, when I could live near nature, I spend a bunch of time out in nature in the forest and on the water every day and so forth. So, I mean, enjoying the pleasant moment is part of it, but the, you know, the growth and choice aspect are severely limited by our human biology. In particular, dying seems to inhibit your potential for personal growth considerably as far as we know. I mean, there's some element of life after death perhaps, but even if there is, why not also continue going in this biological realm, right? In super longevity, I mean, you know, we haven't yet cured aging. We haven't yet cured death. Certainly, there's very interesting progress all around. I mean, CRISPR and gene editing can be an incredible tool. And I mean, right now, stem cells could potentially prolong life a lot. Like if you got stem cell injections of just stem cells for every tissue, if your body injected into every tissue, and you can just have replacement of your old cells with new cells produced by those stem cells, I mean, that could be highly impactful at prolonging life. Now, we just need slightly better technology for having them grow, right? So using machine learning to guide procedures for stem cell differentiation and trans differentiation, it's kind of nitty gritty, but I mean, that's quite interesting. So I think there's a lot of different things being done to help with prolongation of human life, but we could do a lot better. So for example, the extracellular matrix, which is the bunch of proteins in between the cells in your body, they get stiffer and stiffer as you get older. And the extracellular matrix transmits information both electrically, mechanically, and to some extent, biophotonically. So there's all this transmission through the parts of the body, but the stiffer the extracellular matrix gets, the less the transmission happens, which makes your body get worse coordinated between the different organs as you get older. So my friend Christian Schaffmeister, at my alumnus organization, my alma mater, the Great Temple University, Christian Schaffmeister has a potential solution to this, where he has these novel molecules called spiral ligamers, which are like polymers that are not organic. They're specially designed polymers so that you can algorithmically predict exactly how they'll fold very simply. So he designed the molecular scissors that have spiral ligamers that you could eat and would then cut through all the glucosapine and other cross-linked proteins in your extracellular matrix, right? But to make that technology really work and be mature as several years of work, as far as I know, no one's funding it at the moment. So there's so many different ways that technology could be used to prolong longevity. What we really need, we need an integrated database of all biological knowledge about human beings and model organisms, like basically, hopefully, a massively distributed open-cock bioadm space, but it can exist in other forms too. We need that data to be opened up in a suitably privacy-protecting way. We need massive funding into machine learning, AGI, proto AGI, statistical research aimed at solving biology, both molecular biology and human biology based on this massive data set, right? And then we need regulators not to stop people from trying radical therapies on themselves if they so wish to, as well as better cloud-based platforms for automated experimentation on microorganisms, flies and mice and so forth. And we could do all this. You look, after the last financial crisis, Obama, who I generally like pretty well, but he gave $4 trillion to large banks and insurance companies. You know, now in this COVID crisis, trillions are being spent to help everyday people in small businesses. In the end, we'll probably will find many more trillions of being given to large banks and insurance companies anyway. Like, could the world put $10 trillion into making a massive holistic bio AI and bio simulation and experimental biology infrastructure? We could, we could put $10 trillion into that without even screwing us up too badly, just as in the end, COVID and the last financial crisis won't screw up the world economy so badly. We're not putting $10 trillion into that. Instead, all this research is siloed inside a few big companies and government agencies. And most of the data that comes from our individual bodies personally that could feed this AI to solve aging and death, most of that data is sitting </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] of making a seminal contribution to the body of human knowledge. There are certain problems like education that could be solved through this process of dematerialization. By the way, to give props to the 500K algebra teachers, when I look at YouTube, for example, one possible approach is each one of those 500,000 teachers probably had days and moments of brilliance. If they had the ability to contribute in the natural selection process, like the market of education, where the best ones rise up, that's a really interesting way. Which is the best day of your life, the best lesson you've ever taught could be found and sort of broadcast to billions of people. All of those kinds of ideas can be made real in the digital world. Now, traveling across planets, you still can't solve that problem with dematerialization. What you could solve potentially is dematerializing the human brain where you don't need to have astronauts on the ship. [/INST] You can have a floppy disk carrying a human brain. Touching on those points, you'd love for the 500,000 algebra teachers to become 500,000 math specialists and maybe they comp into 50,000 specialties as teams and they all pursue 50,000 new problems and they put their algebra teaching on autopilot. That's the same as when I give you 11 cents worth of electricity and you don't have to throw a boat eight hours a day before you can eat. It would be a lot better that you would pay for your food in the first eight seconds of your day and then you could start thinking about other things. With regard to technology, one thing that I learned studying technology when you look at S-curves is until you start the S-curve, you don't know whether you're a hundred years from viability, a thousand years from viability or a few months from viability. </s><s>[INST] Isn't that fun? That's so fun. [/INST] The early part of the S-curve is so fun because you don't know. In 1900, you could have got any number of learned academics to give you 10,000 reasons why humans will never fly and in 1903, the Wright brothers flew and by 1969, we're walking on the moon. The advance that we made in that field was extraordinary, but for the hundred years and 200 years before, they were just back and forth and nobody was close. That's the happy part. The happy part is we went from flying 20 miles an hour or whatever to flying 25,000 miles an hour in 66 years. The unhappy part is I studied aeronautical engineering at MIT in the 80s. In the 80s, we had Gulfstream aircraft, we had Boeing 737s, we had the space shuttle. You fast forward 40 years and we pretty much had the same exact aircraft. The efficiency of the engines was 20, 30% more. We slammed into a brick wall around 69 to 75. In fact, the Global Express, the Gulfstream, these were all engineered in the 70s, some in the 60s. The fuselage silhouette of a Gulfstream of a G5 was the same shape as a G4, is the same shape as a G3, is the same shape as a G2. That's because they were afraid to change the shape for 40 years because they worked it out in a wind tunnel. They knew it worked. When they finally decided to change the shape, it was like a $10 billion exercise with modern supercomputers and computational fluid dynamics. </s><s>[INST] Why was it so hard? [/INST] What is that wall made of that you slammed into? The right question is, why does a guy that went to MIT that got an aeronautical engineering degree spend his career in software? Why is it that I never a day in my life? With the exception of some Air Force Reserve work, I never got paid to be an aeronautical </s><s>[INST] engineer and I worked in software engineering my entire career. Maybe software engineering is the new aeronautical engineering in some way. Maybe you hit fundamental walls in certain until you have to return to it centuries later [/INST] or no. The National Gallery of Art was endowed by a very rich man, Andrew Mellon, and you know how he made his money? Aluminum. Okay, and you know what kind of airplanes you can create without aluminum? Nothing. It's a materials problem. So 1900, we made massive advances in metallurgy. I mean, that was US steel, that was iron to steel, aluminum, massive fortunes were created because this was a massive technical advance. And then we also had the internal combustion engine and the story of Ford and General Motors and Daimler, Chrysler, and the like is informed by that. So you have no jet engines, no rocket motors, no internal combustion engines. You have no aviation. But even if you had those engines, if you were trying to build those things with steel, no chance, you had to have aluminum. So there's like two pretty basic technologies. And once you have those two technologies, stuff happens very fast. So tell me the last big advance in like jet engines, there hasn't been one, like the last big advance in rocket engines, hasn't been one. The big advances in spaceship design from what I can see are in the control systems, the gyros and the ability to land. So it's a materials problem. Okay, right? </s><s>[INST] In a stable fashion, that's pretty amazing, landing a rocket. Also in the, at least according to Elon and so on, the manufacture of the more efficient and less expensive manufacturer of rockets. So like it's a production, whatever that you call that discipline of at scale manufacture, at scale production. So factory work. But it's not 10X. [/INST] I mean, maybe it's 10X over a period of a few decades. When we figure out how to operate a spaceship on the water in your water bottle for a year, right? Then you've got a breakthrough. So the bottom line is propulsion technology, propellants and the materials technology, they were critical to getting on that aviation S-curve. And then we slammed into a wall in the 70s in the Boeing 747, the Global Express, the Gulf Stream, these things were the space shuttle. They were all pretty much reflective of that. And then we kind of, then we stopped and at that point you have to switch to a new S-curve. So the next equivalent to the internal combustion engine was the CPU and the next aluminum equivalent was silicon. So when we actually started developing CPUs, transistor gave way to CPUs. And if you look at the power, the bandwidth that we had on computers and Moore's law, what if the efficiency of jet engines had doubled every three years? In the last 40 years, where would it be right now? So I think that if you're a business person, if you're looking for a commercially viable application of your mind, then you have to find that S-curve and ideally you have to find it in the first five, six, 10 years, but people always miss this. Let's take Google Glass, right? Google Glass was an idea 2013, the year is 2022 and people were quite sure this was going to be a big thing. And it could have been at the beginning of the S-curve. But fundamentally, we didn't really have an effective mechanism. People getting vertigo. </s>

<s>[INST] Have you read the Ernest Becker's denial of death, for example, is Ernest Becker's a philosopher uh that said that the death that the fear of death is really the primary driver of everything we do. So Freud had what I would agree with that. So to you, you've always thought about your even your own mortality? Yes, definitely. And uh can you elaborate on the reincarnation aspect of what you were talking about like that? We kinda, what's your sense that we had previous lives, [/INST] uh, in what have you thought </s><s>[INST] concretely? Or is it a lot of it kind of, as, you [/INST] know, I thought concretely about really. I mean, it's very clear when you see Children, young kids, or even dogs and cats that they come into the world with personalities, you know, and three kids and a family are gonna be completely different and completely their own person and, and and that person that they are doesn't change over life. And I, you know, there's one of the things that, um, I did in, uh, My book, the artist's journey, is that there were certain things where I tracked or just listed in order. Like all of Bruce Springsteen's albums are all of Philip Roth's books, you know, kind of a body of work throughout over, you know, a period of 30, 40, 50 years, you know, and you can see that there's a theme running through all of those things that it's completely unique to that person. Nobody else could have written Philip Roth's books or Bruce Springsteen songs. And you can even see sort of a Destiny there. So I ask myself, well, where did that come from, what it seems to be a continuation of something that was that happened before, and that will lead to something else, because it's not starting from scratch, it seems like there's a, uh, a calling a destiny in there already. This gets back to the muse and all that kind of thing. </s><s>[INST] So yeah, it's almost like the there's this, let's call it a God. Uh it's passing, it's almost like sampling parts of a previous human that has lived and putting that those into the new one, [/INST] sampling this is probably a pretty good word. </s><s>[INST] Taking some of the good Boy. You can't take all the good parts because the bad part is what makes the person, let's say you take it all together. Okay. Uh, this is humans only, it doesn't pass around from animals in your view. [/INST] Uh, I don't know. That's above my pay </s><s>[INST] grade. I don't know. So, okay, so you talk about the muse as um, the source of ideas maybe since you've gotten a few glimpses of her in your writing? Tell me uh let me, what is it possible for you to tell me about about her? Where does she reside? What does she look like? [/INST] I mean, you can look at in many different ways, right? The Greeks did it in an anthropomorphic way, right? They created gods that were like human beings. Um, but if you look at it from a cannibalistic, jewish perspective, jewish mysticism. You could say that it's the soul, the Nachama, right? That Seoul is above us on a higher plane, our own, your soul, my soul and is trying to reach down to us and and communicate with us and we're trying simultaneously to reach up to it through prayer or through if you're a writer or an artist and you know, when you sit down at the keyboard, you're entering into a kind of prayer, you're entering into a different state of of uh an altered consciousness to something. So you're opening yourself, opening the pipeline, turning on the radio to tune into the cosmic radio station. Another way of looking at it. This isn't a did you ever see um the movie City of Angels? The visual of the movie? It was um Meg Ryan. Oh </s><s>[INST] yeah, I've seen it, yeah. [/INST] And write the visual of the movie, sort of was Meg Ryan is a is a heart surgeon. And as she's operating on somebody suddenly Nicholas cage in this long duster coat, like Jesse James appears right next to her in the operating room and he's an angel and he's waiting to take out the soul of the patient on the, on the operating table. And she doesn't see him. She's totally unaware of him. And so is everybody else in the operating room, except maybe the guy who's about to die who suddenly sees him. But I kind of believe that there are beings like that or if you don't like that, it's a force, it's a consciousness. It's something that are right here right now and we, and they're trying to communicate to us and like through a membrane, like, tapping on that window over there. They're like right out there and they carry the future? They are everything that is in potential, all the works that you will do, lex your startup, whatever else you're doing, They they know that and it's not really you that's coming up with those ideas, in my opinion, those things are appearing, you know, it's like somebody knocks on the door and puts it in. I mean in the Iliad where gods and goddesses appear along with the human antagonists on the battlefield all the time, right? There'll be, you know, homer flashes to Olympus and then back to the real world. And there's a thing where one Aphrodite the let's say wants to help paris. And so she says, well, I will appear to him in a dream and I'll take the form of his brother and I'll say bump, bump, bump. So that's Creatures beings on one dimension as the Greeks art communicating with. And I believe that that's exactly what's going on. And one whatever analogy you want to use </s>

<s>[INST] out of fear, fear, [/INST] fear and like you know, I was kind of nervous because I, you know, there's a whole week and it was anticipating coming here and I watched the mark normand one, I watched the Yannis one to see you know how totally and last night my girlfriend just looked at me just goes, just show up. </s><s>[INST] Yeah, Carla knows who I am. [/INST] Do you think that first of all, let me ask you something? Yes. You think I have the day, you know how busy I'm to drive all the way over here to west Hollywood to do your thing, Why would I do that? Because we are well aware of who you are and we like you thank you God. And we want you on ours. I would love, I would love </s><s>[INST] that as a, I mean that's, that's, that's the reason I'm doing this is just to get in your pocket awesome. Uh yeah, it's funny because I just mentioned to you offline, I got a chance to talk to Oliver Stone and he asked me this thing, which is, you know, how many um listeners does this thing get all that kind of stuff And I don't even pay attention to that. So it's like, I just don't [/INST] a little bit. So you do don't, I </s><s>[INST] wrote extensions in my browser as well. I don't see the views, the number of views don't you [/INST] know that like some of your Youtube videos on interviews and stuff have over a million that </s><s>[INST] I know. I know, I know like loosely that like it bleeds through, but it's not part of my conscious like um thing I think about, I'm very, I've just seen it destroyed people's minds where they're no longer thinking creatively. They're not, they don't feel good if something they do doesn't get as much as attention as they thought it should. It just can destroy you even though it's good. It could be great stuff. You create that nobody everybody ignores. But it was still great. It is, it is still great and uh sort of letting that negatively affect your mind is, I don't know, I've seen it destroy people. So I'm very nervous about that. [/INST] It's like that old saying never live in the results. It's like if I, if I podcast to make, I'd like initially, honestly, when I did tiger belly, we made no money for the first couple of years, like, like not not enough to put a dent. I couldn't buy anything like, you know, nice or anything. Um, it was just side money, you know, I mean, I could buy some shoes once a month or whatever, right? And like I said before, um, I was, my career wasn't the shooter, right? So tiger belly wasn't like, this is gonna be the thing, you know, I mean, it was just something to do with my girlfriend creatively, you know, and it just so happens that it did do all these things for me, right? Um podcasting. But um, yeah, I never and still today, I don't do it for any of those things, you know, I do it because um, it's fun. </s><s>[INST] Yeah, [/INST] yeah, it is right. Yeah. </s><s>[INST] Let me ask you, since you say why you love Kalala, why do you love slash hey George George kimball, your producer, What's your favorite thing about him? Let's say that positive thing positive [/INST] this question because I, because, you know, it's like, you know, I don't wanna give them compliments, but you know, I'll try, </s><s>[INST] I'll [/INST] try. Um, </s><s>[INST] have you actually, I don't think you've publicly ever said anything. I don't [/INST] think I have either, so I'm gonna get I'm gonna give it a go, I'm gonna give it a go. You know, at the end of the day, when it comes to money, when it comes to responsibility, obviously this is a business now for you and me. It is, you know, it's it's a side business, but it's a business and um you want to be able to trust the people that are running it. And I have 100 trust in everything that he does in terms of financial things, in terms of technical things, in terms of all of it, you know, I mean merchandise and I have 100% belief in him, I and that's rare to find someone like that. Um Also at the end of the day, I know his heart and he really is a great guy. He, there's nothing about him, like for instance, you know, he was over the other day and I go, you know, I bought this keith wooden thing that some native man made and I don't know how to put it on the wall. So I just, you know, I go, hey can you, I figured this out and he goes, yeah, I got it, you know, I mean like he's just that guy, you know um he's also, but there is a part of me and this is probably wrong, but there's a part of me that feels like I kind of made him? </s><s>[INST] Yeah, he would be nothing without. [/INST] No, that's what I'm saying, I </s><s>[INST] heard it, that's [/INST] what I meant. </s><s>[INST] Okay, but that's not what you [/INST] said. It's probably wrong because he did all the things that he has in his life, he did on his own right, but still, for some reason </s><s>[INST] he'd be nothing without [/INST] you. But that's what I mean. So basically like, because when I met him, I was a part of this um Youtube studio called Maker Studios and he was just a producer there and that's how I met him and when he left Maker, he came to us and he wasn't a podcast producer and now he has this big company, he produces a bunch of podcasts, you know, and he has a bunch of employees and he has a nice business, you know, and I feel like I had a lot to do with it. </s>

<s>[INST] So that's something. So in summary. Eat ship early and eat ship often. Yes. Alright. Mark norman eat s. That's escalated quickly. Alright. I have a list of random questions for you. Um What activities make you lose track of time. Um Have that go into that zone. You have this happiness contentment about you that you just truly enjoy. [/INST] Yeah. I think a good conversation like I'll sit at the comedy cellar with friends, maybe a little whiskey is flowing and when you're really just vibing and in him, in him in what is it? </s><s>[INST] inhibited [/INST] and uninhibited when you're just vibing and you're uninhibited. You're saying crazy ship and you're laughing and you're not worried by seeming cool right now. And my seeming likable when you're just you 100% and it's all coming out of you and then they're saying stuff and you go back and forth and you feel that excitement when they're talking. But I want to say my thing and you know, you get all keyed up. I love that. And I look at my watch and like fun. It's three in the morning. This is we've been talking for five hours. So I love that. That makes the time fly by. Also, I bought a Speaking of self driving cars. I bought a 1973 BMW car and it's classic and it's stick shift and it's grizzly and gritty and rusty and it's a bucket of bolts, but I love driving it, </s><s>[INST] bucket of bolts tom waits for poets. Have you have you taken like a long trip anywhere like road trip in your life or with this BMW. [/INST] Not with it. It's pretty new, but I will. </s><s>[INST] It's a new 97. Yeah, [/INST] it's new to me and it just, it it goes in the face of everything we're doing now. Everything is digital. Everything is automated. Everything is hands off. Everything is delivered And this is the most hands on thing in the world. And I am dialed in, man, I got the tachometer, I keep an eye on that. Oh, I made I put the wrong gear and ship. Oh, it's about to stall, put some gas, put some clutch and it's all just brain power and and staying in focus and all that and it's the opposite of tweeting and texting and watching porn or whatever. So I almost needed that in my life. So I bought this car just to have this little exercise. </s><s>[INST] I hope you don't mind that. I'm just trying out random questions I wrote on you that are completely, they're like completely insane. [/INST] Bring it on baby. </s><s>[INST] This would be edited down to five minutes if everyone on earth disappeared and it was just you left. Well what would your days look like? What would you do? [/INST] That's tough because I'm already an introvert And I try to avoid people mostly like I like I one on one but crowds and all that is tough. </s><s>[INST] So basically unchanged. [/INST] Yeah, that's what I was gonna say. But then that's the irony is I would be so sad to not talk to anybody. So it's this weird bittersweet thing, but I don't know what I would do man. I guess it's kind of like when you're hung over, you just go into the primal survival mode. I gotta get food. I need water. I'm horny jerk off. You know, you just go, you know, you're not like playing the piano or or painting or at the gym. So I think I would just go into urges, man, primal urges, find food, store food, am I safe, make weapons, build a shelter that I can't get attacked in. I would go all survival mode and then once I may be realized if I was safe or not, there's no wild roaming dogs. I would start exploring and uh you know maybe somehow get a vehicle and I would try to expand and that would be it and maybe a journal </s><s>[INST] exploring to what to try to find new experiences, [/INST] new new life. If there's other, maybe there is another guy out </s><s>[INST] there. Also always there's a possibility. [/INST] Yeah, hope and then maybe there's a better place I could live, let's find that and then moving on then maybe there's more food over here. So yeah, the hope would drive me but it would be bleak and sad and horrible. Also </s><s>[INST] so what you're saying is you really want other people to be there so you can hide from [/INST] them as well said, </s><s>[INST] alright, what what's an item on your bucket list that you haven't done yet? Think about something, you'd be very upset if you died and you haven't done [/INST] well I'm terrified of having kids, you know, just because I'm a child myself and I'm selfish and lazy in a way. So kids are like this is your whole life now this is it you got to not let this thing die, you gotta love it, you gotta raise it. So kids scare the ship out of me. But I also feel like if I don't have them, I'll I'll regret it. </s><s>[INST] Well, you've seen so many people like you who are fundamentally changed by kids. Like it's a source, it's a source of like a deep source of happiness, even though you didn't anticipate it. Yeah, So you, like you penciled it into your bucket? Yes, Yes, you're it might be on there. [/INST] Ok. You want kids? </s><s>[INST] Yeah, well I want kids, I want to get married. Um I don't have kids. I kind of, I I don't like choice. So in the following way, like I I appreciate the value of scarcity and the power of scarcity. Like I don't like the modern dating culture, it's not some religious thing or whatever. I just like one girl for a long time or at least swinging for that always like swinging for the fences [/INST] and to be swinging right now. I mean </s>

<s>[INST] at every level of the bureaucracy of uh leadership. [/INST] People are well informed and they understand that the country is declining, that the human capital is declining, the infrastructure is declining. The economy is not really growing, it's not really diversifying. Russia's not investing in its future. The state officials understand all of that, and then they see that the Putin click is stealing everything in sight. So, between the failure to invest in the future and the corruption of a narrow group around the president, there's disillusionment in the state apparatus because they see this more clearly or more closely than the mass of the population. They can't necessarily yet oppose this in public because there are people, they have families, they have careers, they have Children who want to go to school or want a job. And so there are constraints on their ability to oppose the regime based upon what we might call cowardice or other people might call realism. I don't know how courageous people can be when their family, Children career on the line. So it's very interesting dynamic to see the disillusionment inside the government with the president, which is not yet fully public for the most part, but could become public and once again if there's an alternative. If an alternative appears, things could shift quickly and that alternative could come from inside the regime </s><s>[INST] from inside the regime. But the leadership, the party, the people that are now, as you're saying opposed to Putin, they're nevertheless, maybe you can correct me, but it feels like there's a structural is deeply corrupt. So each of each of the people were talking about our I don't feel like a George Washington. [/INST] Once again, the circumstances don't permit them to act that way necessarily right. George Washington did great things. But in certain circumstances a lot of the state officials in Russia for certain are corrupt. There's no question many of them, however, are patriotic and many of them feel badly about where the country has been going. They would prefer that the country was less corrupt. They would prefer that there were greater investment in all sorts of areas of Russia. They might even themselves steal less if they could be guaranteed that everybody else would steal less. There's a deep and abiding patriotism inside Russia as well as inside the Russian regime. So they understand that Putin in many ways rescued the Russian state from the chaos of the 1990s. They understand that Russia was in very bad shape as an incoherent failing state almost when Putin took over and that he did some important things for Russia's stability and consolidation. There's also some uh appreciation that Putin stood up to the west and stood up to more powerful countries and regained a sense of pride and maneuverability for Russia and the international system. People appreciate that and it's real, it's not imagined that Putin accomplished that. The problem is the methods that he accomplished it with. He used the kind of methods that is to say taking other people's property, putting other people in jail for political reasons. He used the kind of methods that are not conducive to long term growth and stability. So he fixed the problem. But he fixed the problem and then created even bigger long term problems, potentially. And moreover, all authoritarian regimes that use those methods, um, are tempted to keep using them and using them and using them until they're the only ones who are the beneficiaries and the group narrows and narrows, the elite gets smaller and narrower. The interest groups get excluded from power and their ability to continue enjoying the fruits of the system and the resentment grows. And so that's the situation we have in Russia is a place that is stuck. It was to a certain extent rescued. It was rescued with methods that were not conducive to long term success and stability. </s><s>[INST] The rescue referring to is the sort of the economic growth. When Putin first [/INST] Took took office, they had 10 years. They had a full decade of an average of 7% growth a year, which was phenomenal and is not attributable predominantly to oil prices during President Putin's first term as president, The average price of oil was $35 a barrel during his second term as president. The average price was $70 a barrel. So during those two terms when Russia was growing at about 7% a year, oil prices, We're averaging somewhere around $50 a barrel, which is fine, but it's not the reason Because later on when oil prices were over $100 a barrel, Russia stagnated. </s><s>[INST] So the initial growth, do you think Putin deserves some credit for that? [/INST] Yes, he does. Because he introduced some important liberalizing measures. He lowered taxes, he allowed land to be bought and sold. He deregulated many areas of the economy. And so there was a kind of entrepreneurial burst that were, that was partly attributable, partly attributable to government policy during his first term. But also he was consolidating political power and as I said, the methods he used overall for the long term, we're not able to continue sustain that success. In addition, we have to remember the china played a really big role in the success of Russia in the first two terms of Putin's presidency. Because china's phenomenal growth created insatiable demand for just about everything that the soviet union used to produce so fertilizers, cement fill in the blank chemicals, metals, china had insatiable demand for everything the soviet union once produced and so china's global raising of global demand overall brought soviet era industry back from the dead. And so there was something that happened, Soviet era industry fell off a cliff in the 1990s, there was a decline in manufacturing and industrial production greater than in the Great Depression in the US. But a lot of that came back online in the 2000s and that had to do with china's phenomenal growth. The trade between china and Russia was not always direct. So this was an indirect effect. But raising global prices for the commodities and the products, the kind of lower and lower value products in manufacturing, not high end stuff, but lower end stuff like steel or iron or cement or fertilizer Where the value added is not spectacular, but nonetheless, which had been destroyed by the 1990s and after the Soviet collapse, this was brought back to life. Now you can do that once, you can bring soviet era industry back to life once. And that happened during Putin's first two terms, In addition to the liberalizing policies, which spurred entrepreneurialism and some small and medium business. The crash of the ruble in 1998, which made Russian products much cheaper abroad and made imports much more expensive, also facilitated the resuscitation the revival of domestic manufacturing. So all of this came together for that spectacular 10 year 7% on average economic growth and moreover, people's wages after inflation, their disposable income grew more even than GDP group. So disposable income after inflation, that is real income Was growing greater than 7% in some cases 10% a year. So there was a boom and the Russian people felt it and it happened during Putin's first two terms and people were grateful rightly so for that. And those who don't want to give Putin credit, give oil prices, all the credits, but I don't think that oil prices can explain this. Having said that, that doesn't mean that this was sustainable over the long term. </s>

<s>[INST] And now here's my conversation with Ian Goodfellow. You open your popular deep learning book with Russian doll type diagram that shows deep learning is a subset of representation learning, which in turn is a subset of machine learning and finally a subset of Ai. So this kind of implies that there may be limits to deep learning in the context of A. I. So what do you think is the current limits of deep learning? And are those limits something that we can overcome with time. [/INST] Yeah, I think one of the biggest limitations of deep Learning is that right now it requires really a lot of data, especially labeled data. Um there's some unsupervised and semi supervised learning algorithms that can reduce the amount of labeled data you need, but they still require a lot of unlabeled data reinforcement learning algorithms, they don't need labels but they need really a lot of experiences. Um as human beings, we don't learn to play pong by failing at Pong two million times. So just getting the generalization ability better is one of the most important bottlenecks and the capability of the technology today. And then I guess I'd also say deep learning is like a component of a bigger system. Um So far nobody is really proposing to have uh only what you'd call deep learning as the entire ingredient of intelligence. You use deep learning as sub modules of other systems like Alphago has a deep learning model that estimates the value function. Um Most reinforcement learning algorithms have a deep learning module that estimates which action to take next but you might have other components, </s><s>[INST] so you're basically as building a function estimator. Do you think it's possible? He said nobody has kind of been thinking about this so far. But do you think neural networks can be made to reason in the way symbolic systems did in the 80s and 90s to do more create more like programs as opposed to functions. [/INST] Yeah, I think we already see that a little bit. I already kind of think of neural nets as a kind of of program, I think of deep learning as basically Learning programs that have more than one step. So if you draw a flow chart or or if you draw a tensorflow graph describing your machine learning model, I think of the depth of that graph is describing the number of steps that run in sequence and then the width of that graph is the number of steps that run in parallel. Now it's been long enough that we've had deep learning working that it's a little bit silly to even discuss shallow learning anymore. But back when I first got involved in ai when we used machine learning, we were usually learning things like support vector machines, you could have a lot of input features to the model and you could multiply each feature by a different weight. All those multiplication were done in parallel to each other, there wasn't a lot done in series I think we got with deep learning was really the ability to have ah steps of a program that run in sequence. And I think that we've actually started to see that what's important with deep learning is more the fact that we have a multi step program rather than the fact that we've learned a representation. If you look at things like resin nuts, for example, they take one particular kind of representation and they updated several times back when Deep Learning first really took off in the academic world in 2006 when Geoff Hinton showed that you could train deep belief networks, Everybody who was interested in the idea, thought of it as each layer learns a different level of abstraction that the first layer trained on images, learned something like edges and the second layer learns corners and eventually you get these kind of grandmother's cell units that recognize specific objects. Today. I think most people think of it more as a computer program. Where as you add more layers, you can do more updates before you output your final number. But I don't think anybody believes that Layer 150 of the resin yet Uh is a grand grandmother cell and you know, layer 100 is contours or something like that. </s><s>[INST] Okay, so you think you're not thinking of it as a singular representation that keeps building you think of it as a program sort of almost like a state representation is a state of understanding. [/INST] And Yeah, I think of it as a program that makes several updates and arrives it better and better understandings, but it's not replacing the representation at each step. It's refining it and in some sense that's a little bit like reasoning. It's not reasoning in the form of deduction, but its reasoning in the form of taking a thought and refining it and refining it carefully until it's good enough to use, do you think? </s><s>[INST] And I hope you don't mind. We'll jump philosophical every once in a while do you think of, you know cognition? Human cognition or even consciousness is simply a result of this kind of uh sequential sequential representation. Learning. Do you think that can emerge [/INST] cognition? Yes, I think so, consciousness it's really hard to even define what we mean by that. I guess there's consciousness is often defined as things like having self awareness and that's relatively easy to turn into something actionable for a computer scientist to reason about people also defined consciousness in terms of having qualitative states of experience, like quagliana, there's all these philosophical problems like could you imagine a zombie who does all the same information processing as a human but doesn't really have the qualitative experiences that we have, that sort of thing. I have no idea how to formalize or turn it into a scientific question. I don't know how you could run an experiment to tell whether a person is a zombie or not. And similarly, I don't know how you could run an experiment to tell whether an advanced ai system had become conscious in the sense of quality a or not, </s>

<s>[INST] you might have limits like I might not recognize him if he was upside down or something like that would be fascinating to to see what the limits of that joe Rogan concept is. [/INST] So nancy's lab has done that because early on she was challenged by people that said there aren't face neurons, there are neurons that they only respond to space and time, shapes and things like that, moving in particular directions and orientations and turns out nancy was right um they used the stimulate called gribble stimulate which any computer programmer would appreciate, which kind of more suffices to something gradually that eventually just looks like this like alien thing they call the gribble and the neurons don't respond to Gruebel's in most cases they only respond to faces and familiar faces. Anyway, I'm summarizing a lot of literature and forgive me nancy and for those of the gribble people, if there are something like you don't come after me with pitchforks, actually, you know what come out pitch for, you know what I'm trying to do. So the point is that in the visual system it's very concrete up until about visual area for which has color pinwheels and seems to respond to pinwheels of colors and um and so the stimulus become more and more elaborate, but at some point you depart that concrete representation and you start getting abstract representations that can't be explained by simple point to point wiring and to take a leap out of the visual system to the higher level concepts. When we talked about in the visual system, maps to the auditory system where you're encoding what frequency of tone sweeps. So this is gonna sound weird to do, but you know, like a Doppler, like hearing something car passing by for instance. But at some point you get into motifs of music that can't be mapped to just a what they call a tona topic map of frequency. You start abstracting and if you start thinking about concepts of creativity and love and memory, like what is the map of memory space? Well, your memories are very different than mine, but presumably there's enough structure at the early stages of memory processing or at the early stages of emotional processing or at the earlier stages of creative processing that you have the building blocks your zeros and ones if you will, but you depart from that eventually. Now, the exception to this, and I want to be really clear because I was just mainly talking about neocortex, the six layered structure on the outside of the brain. That explains a lot of human abilities, other animals have them too is that sub cortical structures are a lot more like machines. It's more plug and chug and what I'm talking about is the machinery that controls heart rate and breathing and receptive fields. Um You know, neurons that respond to things like temperature on the top of my left hand. And one of the, you know, I came into the neuroscience from more of a perspective initially of psychology, but one of the reasons I forced upon myself to learn some electrophysiology, not a ton, but enough and some molecular biology and about circuitry is that one of the most beautiful experiences you can have in life, I'm convinced, is to lower an electrode into the cortex and to show a person or an animal. You do this ethically of course, uh stimulus like an oriented line or a face. And you can convert the recordings coming off with the electrode into an audio signal and audio monitor. And you can hear what they call hash. It's not the hashish smoke, it's the hash you here and it's, it sounds like it just sounds like noise. And in the cortex eventually you find a stimulus that gets the neuron to spike and fire action potentials are converted into an auditory stimulus that are very concrete crack, crack, crack sounds like a bat cracking, you know, like home runs, you know, or or outfield balls when you drop electrodes deeper into the thalamus or into the hypothalamus or into the brain stem areas that control breathing. It's like a machine. You never hear hash, you drop the electrode down, This could be like a like a grungy old tungsten electrode not high fidelity electrode. As long as it's got a little bit of insulation on it, plug it into an audio monitor, it's picking up electricity. And if it's a visual neuron and it's in the thalamus of the retina and you walk in front of that animal or person that that neuron goes and then you walk away and it stops and you put your hand in front of the eye again and it goes and you could do that for two days and that neuron will just, every time there's a stimulus it fires. So whereas before it's a question of how much information is getting up to cortex and then these abstractions happening, where you're creating these ideas when you go sub cortical, everything is, </s><s>[INST] there's no abstraction, it's [/INST] two plus two equals four. There's no abstractions. And this is why I um you know, I know we have some common friends at neural link and I love the demonstration they did recently. I'm a huge fan of what they're doing and where they're headed. And no, I don't get paid to say that and I have no business relationship to them. I'm just a huge fan of the people in the mission. But my question was to some of them, you know when you're going to go sub cortical because if you want to control an animal. You don't do it in the cortex. The cortex is like the abstract painting. I made of your face moving, removing one piece or changing something may or may not matter for the abstraction but when you're in the sub cortical areas of the brain, a stimulating electrode can evoke an entire behavior or an entire state. And so the brain, if we can have a discussion about the brain and how the brain works, we need to really be clear which brain because everyone loves neocortex, it's like oh canonical circuits and cortex we're gonna get the cortical connect um and sure necessary but not sufficient not to be able to plug in patterns of electrical stimulation and get behavior eventually we'll get there. But if you're talking sub cortical circuits and that's where the action is. That's where you could potentially cure Parkinson's by stimulating the sub thalamic nucleus because we know that it gates motor activation patterns in very predictable ways. So I think for those that are interested in neuroscience it pays to pay attention to like is this a circuit that abstracts the sensory information or is it just one that builds up hierarchical models in a very predictable way and there's a huge chasm in neuroscience right now because there's no conceptual leadership, no one knows which way to go. And this is why I think neuralink has captured an amazing opportunity which was okay, well while all you academic research labs are figuring all this stuff out. We're going to pick a very specific goal and make the goal the endpoint and some academic laboratories do that. But I think that's a beautiful way to attack this whole thing about the brain because it's very concrete, Let's restore motion to the park and Sony inpatient academic labs do that want to do that too? Of course, let's restore um speech to the stroke patient, but there's nothing abstract about that, that's about figuring out the solution to a particular problem. So, anyway, those are my and I and I admit I've mixed in a lot of opinion there, But having spent some time like 25 years digging around in the brain and listening to neurons firing and looking at them anatomically, I think given its 2020 we need to ask the right, you know the way to get better answers, ask better questions and the really high level stuff is fun. It makes for good conversation and it has um brought enormous interest, but I think the questions about consciousness and dreaming and stuff, they're fascinating. But I don't know that we're there yet. So, </s>

<s>[INST] europe is far enough [/INST] far enough away. So that's why that would be, especially, it's </s><s>[INST] always the skeptics that ruined a good party. But [/INST] we need them. Of course </s><s>[INST] we need them at the party. We need some skeptics at the party. But boy, would that be so exciting to find life on one of the moons? [/INST] That would just be any kind of vegetation or life? Um, the question of the aliens of science fiction is a different matter, </s><s>[INST] intelligent aliens. Yeah, But if you have a good indication that there's life elsewhere in the solar system, that means life is everywhere. And that that's I don't know if that's terrifying or what that is, because if life is everywhere, why is intelligent life not everywhere? Why? I mean, you've talked about that most likely alien civilizations. If they are out there, they would likely be far ahead of us. The ones that would actually communicate with us and that, um, again, one of those things that is both exciting and terrifying, you've mentioned that they're likely not to be of biological nature. [/INST] Well, I think that's important. Of course. Again, it's speculation, but uh, in speculating about intelligent life. And I, I think the search seriously. In fact I chair the committee that the Russian american investor yuri milner supports looking for intelligent life is putting $10 million a year into better equipment and getting time on telescopes to do this. And so I think it's worthwhile. Even though I don't hold my breath for success, it's very exciting. But that does lead me to wonder what might be detected. And I think, well, we don't know, we've got to be open minded about anything. We have no idea what it would be. And so any anomalous objects or even some strange shiny objects in the solar system or anything we've got to keep our eyes open for. But I think if we ask what about a planet like the earth where evolution had taken more of the same track then, as you say, it wouldn't be synchronized. If it had lagged behind, then of course it would not have got to advanced life, but it may have had a head start. It may have formed on a planet around an older star. Okay, But then let's ask what would see? It's taken nearly four billion years from the first live to us. And we've now got this technological civilization which could make itself detectable to any alien live aliens out there. But I think most people would say that this civilization of flesh and blood creatures in the collective civilization may not last more than a few 100 years more. I think that the people may, some people would say that it will kill itself off. But I'm more optimistic and I would say that what we're going to have in </s><s>[INST] future [/INST] is no longer the slow Darwinian selection, but we're going to have what I call secular intelligent design, which will be humans designing their progeny to be better adapted to where they are. And if they go to mars or something somewhere, they're badly adapted and they want to adapt a lot and so they will adapt. But there may be some limits to what can be done with flesh and blood. And so they may become largely electronic, download their brains and have and be electronic. And if they're electronic then what's important is that they're near immortal and also they won't leslie want to be on the planet with an atmosphere or gravity. They may go off into the blue yonder and they if they're near immortal, they won't be daunted by interstellar travel taking a long time. And so if if we looked at what would happen on the earth in the next millions of years, then there may be these electronic entities which have been sent out and are now far away from the earth but still sort of burping away in some in some fashion to be detected. And so this this therefore leads me to think that if there was another planet, Richard evolved like the earth and was ahead of us, it wouldn't be synchronized so we wouldn't see a flesh and blood civilization, but we would see these electronic progeny as it were? And then this raises another question because there's a famous argument against there being lots of aliens out there, which is that they would come and invade us and eat us or something like that. You know, that's a common idea which family is attributed have been the first to say. Um and I think there's a escape clause to that because these entities would be say that they evolved by second intel to design designed by their predecessors and then designed by us. And uh Whereas Darwinian selection requires two things. It requires aggression and intelligence. This future intel design may favor intelligence because that's what they were designed for, but it may not favor aggression. And so these future entities, they may be um sitting deep thoughts, thinking deep thoughts, um and not being at all expansionist. So they could be out there and we can't refute their existence in the way the family paradoxes supposed to refute their existence because these would not be aggressive or expansionist? </s><s>[INST] Well, maybe evolution requires competition, not aggression. And I wonder if competition can take forms that are non expansionary. So you can still have fun competing in the space of ideas which may be primarily [/INST] will be philosophers perhaps. Yeah, </s><s>[INST] in a way. Right. It's uh it's an intellectual exercise versus a sort of violent exercise. So what is this civilization on mars look like? So do you think we would more and more, you know, maybe start with some genetic modification and then move to basically cyborgs, increasing integration of electronic systems, computational systems into our bodies and brains. [/INST] This is a theme of my other new book out this year, which is called The End of Astronauts And </s>

<s>[INST] audience this podcast [/INST] like this podcast. Exactly. So what we did in this work was basically trained to different neural networks one on the video signal, one on the audio signal. And what we wanted is basically the features that we get from both of these neural network should be similar. So it should basically be able to produce the same kinds of features from the video and the same kind of features from the audio. Why is this useful? Well, for a lot of these objects that we have, there is a characteristic sound, right? So trains when they go by, they make a particular kind of sound boats make a particular kind of sound people when they're jumping around with shout, whatever bananas don't make a sound. So where you can't find anything about bananas there </s><s>[INST] or when humans mentioned bananas? [/INST] Well, yes, when they say the word banana, then you </s><s>[INST] can't trust basically anything that comes out of a human's mouth as a source, that source of value is [/INST] used. The typical use case is basically like for example, someone playing a musical instruments, guitars have a particular kind of sound and so on. So because a lot of these things are correlated, the idea of multimodal learning is to take these two kinds of modalities, video and audio and learn a common embedding space, common feature space where both of these related modalities can basically be close together. Again, you use contrast learning for this. So in contrast of learning basically the video and the corresponding audio positives and you can take any other video or any other audio and that becomes a negative. And so basically that's it, it's just a simple application of contrast of learning. The main sort of finding from this work for us uh was basically that you can actually learn very, very powerful feature representations, very, very powerful video representations. So you can learn the sort of video network that we ended up learning can actually be used for downstream for, for example, recognizing human actions, recognizing different types of sounds, for example. Um so this was sort of the key finding. </s><s>[INST] Can you give a kind of example of a human action or like just so we can build up intuition of what kind of thing. [/INST] So there is this dataset called kinetics, for example, which is like 400 different types of human actions. So people jumping, people doing different kinds of sports or different types of swimming, so like different strokes and swimming goals and so on. So there are just different types of actions right there. And the point is this kind of video network that you learn in a self supervised way, can be used very easily to kind of recognize these different types of actions. Uh It can also be used for recognizing different types of objects. Uh and what period as we try to visualize whether the network can figure out where the sound is coming from. So basically give it a video and basically play of, say, a person just strumming a guitar, but of course there's no audio in this. And now you give it this sound of the guitar and you ask basically try to visualize where the network is, where the network thinks the sound is coming from. And that can kind of basically draw like when you visualize it, you can see that it's basically focusing on the </s><s>[INST] guitar [/INST] and the same thing. For example, for certain people's voices, like famous celebrities, voices. It can actually figure out where they're like where their mouth is. So it can actually distinguish different people's voices. For example, a little bit as well </s><s>[INST] without that ever being annotated in. Anyway, [/INST] so this is all what it had discovered. We never, like, we never pointed out that this is a guitar and this is the kind of sounded produces. It can actually naturally figure that out because it's seen so many correlations of this sound coming with this kind of like an object that it basically learns to associate this sound with this kind of an </s><s>[INST] object that's really fascinating, right? That's really interesting. So the idea with this kind of network is then you then fine tune it for a particular task. So this is forming like a really good knowledge base within a neural network based on which you could then train a little bit more to accomplish a specific task. Well, [/INST] so you don't need a lot of videos of humans doing actions animated, You can just use a few of them to basically get your, </s><s>[INST] how much insight do you draw from the fact that he can figure out where the sound is coming from? I'm trying to see. So that's kind of very, it's very CVP are beautiful, right? It's it's it's a cool insight. I wonder how profound that is. You know, does it speak to the idea that multiple modalities are somehow much bigger than the sum of their parts? Or is it really, really useful to have multiple modalities? Or is this just a cool thing that there's parts of our world that are uh can be revealed uh like uh effectively through multiple modalities, but most of it is really all about vision or about one of the modalities, [/INST] I would say a little uh tending more towards the second part. So most of it can be sort of figured out with one modality, but having an extra mortality always helps you. So in this case, for example, like one thing is when you're, if you observe someone cutting something and you don't have any sort of sound that whether it's an apple or whether it's an onion, it's very hard to figure that out. But if you hear someone cutting it, it's very easy to figure it out because apples and onions make a very different sort of different kind of characteristic sound when they're cut. So you really figure this out based on audio. It's much easier. So your life will become much easier when you have access to different kinds of Mortalities. And the other thing is so I like to relate it in this way. It may be completely wrong. But the distributional hypothesis and NLP right, where context basically gives kind of meaning to that word sound kind of does that too? Right? So, if you have the same sound, so that's the same context across different videos, you're very likely to be observing the same kind of </s>

<s>[INST] Yeah, that's what people tend to do. And they think about simulation. They think about our modern computers and somehow trivially crudely just scaled up in some sense. But do you think uh, the simulation, I mean, in order to actually simulate something as complicated as our universe that's made up of molecules and atoms and particles and quirks and maybe even strings. All that requires something just infinitely many orders of magnitude more of, of scale and complexity. Do you think we're even able to even conceptualize what it would take to simulate our universe? Or does it just uh, slip into this idea that you basically have to build a universe? Something so big to simulate it, is that it doesn't get this into this fuzzy area that's not useful at all. [/INST] Yeah, I mean, that's obvious. I mean, our universe is obviously incredibly complicated and for us within our universe to build a simulation of the universe as complicated allows is going to have obvious problems here. If the universe is finite, there's just no way that's gonna work. Maybe there's some cute way to make it work. If the universe is is uh is infinite. Maybe an infinite universe could somehow stimulate a copy of itself. But that's a that's going to be hard. Nonetheless. Just that we are in a simulation, I think there's no particular reason why we have to think the simulating universe has to be anything like ours. </s><s>[INST] You've said before that it might be so you can you can think of it and turtles all the way down, you can think of uh the simulating universe different than ours, but we ourselves could also create another simulating universe. So you said that there could be these kind of levels of universes and you've also mentioned this hilarious idea. Maybe talking cheek maybe not That there may be simulations within simulations. Arbitrarily stacked levels and that there may be that we may be in level 42 [/INST] along </s><s>[INST] those tax referencing Hitchhiker's guide to the universe. If we are indeed in a simulation within a simulation At level 42, What do you think? Level zero looks [/INST] like you would expect that level zero is truly enormous. I mean, not just uh if it's finite, it's some extraordinarily large, finite capacity. Much more likely. It's infinite. Maybe it's a maybe it's got some very high set through the cardinality that enables it to support just any number of any number of simulations so high degree of infinity at level zero, slightly slightly smaller degree of infinity at level one. So by the time you get down to us at level 42 maybe there's plenty of room for lots of simulations of finite capacity. Um if the top universe is only a small finite capacity, then obviously that's gonna put very, very serious limits on how many simulations are going to be able to be able to get running. So I think we can certainly confidently say that if we're at level 42, then the top level is pretty, pretty damn. </s><s>[INST] So it gets more and more constrained as we get down levels more and more simplified and constrained and limited resources. [/INST] And yeah, we still have plenty of capacity here. What was it? A fine man. 30. So there's plenty of room at the bottom. You know, we're still we're still a number of levels above the degree where there's room for fundamental computing, physical computing capacity, quantum computing capacity at the bottom level. So we got plenty of room to play with and make we probably have plenty of room for simulations of pretty sophisticated universes, perhaps none as complicated as our universe unless our universes is infinite, but still at the very least for pretty serious finite universes, but maybe universes somewhat simpler than ours unless of course we're prepared to take certain shortcuts in the simulation, which might then increase the capacity </s><s>[INST] significantly. Do you think the human mind ask people in terms of complexity, simulation is at the height of what the simulation might be able to achieve. Like if you look at incredible entities that could be created and this universe of ours, do you have an intuition about how incredible human beings are on that scale? [/INST] I think we're pretty impressive, but we're not that impressive. </s><s>[INST] Well above average. [/INST] I mean, I think human beings are a certain point in the scale of intelligence, which made many things possible. You know, you got through evolution through single cell organisms, through fish and mammals and primates and something happens once you get to human beings, we've just reached that level where we get to develop language and we get to develop certain kinds of culture and we get to develop certain kinds of collective thinking that has enabled all this amazing stuff to happen, Science and literature and engineering and, and culture and uh, and so on. So we had just at the beginning of that on the evolutionary threshold, it's kind of like we just got there, you know, who knows, a few 1000 or tens of thousands of years ago. So we're probably just at the very beginning for what's possible there. So I'm inclined to think among the scale of intelligent beings where somewhere very near the bottom, I would expect that, for example, if we're in a, if we're in a simulation, then the simulators who created Vassar Got the capacity to be far more sophisticated for a level 42, who knows what the ones at level zero, I like. </s>

<s>[INST] from a place of curiosity, You would try to figure [/INST] out what I want to understand who the person is and through questioning we can usually get there or through just spending time together, you find out who the person is. </s><s>[INST] What about finding out and figuring out how to then take the next steps of bringing out the best in them? Like uh is it just trial and error? Like, let's try this. [/INST] It's definitely trial and error. It's always trial and error. Are </s><s>[INST] you afraid of making a mistake? Like, let's let's add this instrument, Let's remove this instrument, let's add this line, let's remove this line. [/INST] Let's try and let's let's be open. It's one of the, one of the rule. We don't really have rules, but one of the agreements in the studio is any idea that anyone has will always demonstrate. It will always try it. Because I can describe to you an idea and you can think that's a terrible idea, let's not do that. And then I can play you the idea and then you can say, oh, that's really good. And it's completely different because we when we hear when we're told something, we have to imagine what that is and the way you see something and imagine it in the way I see something and imagine you are completely different. </s><s>[INST] So you say a thing and now there's two humans that play that thing in their mind differently in their imagination. And then there's a cool creative step and when you actually do it to see how it differs in the imagination and then the difference or the commonality will be like an exciting little discovery together. [/INST] Well, so many, so many groups of people making things together in a room, one personal suggests something and someone else's room saying that that doesn't sound like a good idea. Let's not do that. And then they move on. The testing of every idea is really important and that's how you get to see, Oh, that's not at all. What I thought it was gonna be happens to me all the time. I, I know because someone will suggest, why don't we do it like this? And I'll think That sounds bad and then I think, Okay, let's try it and then we hear it and then, you know, eight times out of 10. It's nothing like I imagined and great. </s><s>[INST] And you try not to have an ego about the fact that you thought it was not a good idea in your head. [/INST] There can't be any ego in this. It doesn't if if if everyone's there with the purpose of making the best thing we can, there's nothing else, you know, there are no, there can't be any boundaries to that. </s><s>[INST] So there's a moment I saw with, I know you don't love talking about previous things you've done, but it's cool to dive in there. [/INST] Everyone I'm finding </s><s>[INST] to sample it. Uh, anything once I have, I have this pain, I gotta talk now. [/INST] I'll </s><s>[INST] Think of something ridiculous that would, that would make you change your mind. Um you mentioned, uh I saw a video of you with with Jay Z or around 99 problems where you suggested acapella opening the song with ac apologists. No, no instruments, just voice that to me. I mean, that's one of the characteristics of the things, of the ways you've brought out the best an artist is doing less sort of the attending towards simplicity in some kind of way. So that that that choice of acapella is really interesting because, like, I could see a lot of people think that that's a bad idea, but it turned out to be a really powerful idea. Can you maybe talk about the simplicity how to find simplicity? Why you find simplicity is beautiful? It does appear to be beautiful. What is that? [/INST] Yeah, I I don't know where it comes from. It has been with me from the beginning of my work, the very first album I ever produced, The credit I took was reduced by me instead of produced by me. Um for that reason, like, I like the idea of getting to the essential and I have a better idea now that I've done it for a while, but at the time it was purely an instinctual thing and part of it is a sonic, there's a sonic benefit, which is the less elements you have, you can hear each of the ones that are there and they can sound better And the less there are, the more um the more space they could have around them and the more you can hear their personality. If you were to record 10 people playing the same guitar part and you listen to it, it would sound like guitar And if you play record one person playing a guitar part, it sounds like a person playing the guitar. It's different than just guitar. And the often in the studio the idea of building upon things and adding adding layers to thicken to make it sound bigger sometimes um The more things you add, the smaller it gets. So it's a it's a a lot of it is counterintuitive until you just didn't practice, see what try </s><s>[INST] it to try removing stuff until it's just right, it's the Einstein thing make it ah make it as simple as possible but not simpler. That's such a like finding a stopping place, just keep chopping away and chopping away. [/INST] Yeah there's something we we also like to do called the ruthless edit which is let's say you're at a point where it can work for anything. But I'll give you the example with an album. Um We've recorded 25 songs, We think the album is going to have 10 Instead of picking our favourite 10. We limited to what are the five or 6 that we can't live without. So going past even the goal to get to the real like heart of it and then say okay we have these five or six that we can't live without now, what would we add to that? That makes it better and not worse. And um it's just, it puts you in a different frame when you start with building instead of removing </s>

<s>[INST] Conaciously not contraction, but all that which I think it probably just means it's like it's artistic, it's interesting. It's edgy. [/INST] It's funny, so really, really well done, but it was really shocking to be that nobody else was doing anything creative with satire. Like for me, it was, it was like breathing. Like you're just doing sex and you're bored, and I'm like, what do you do? I don't know, let's try something funny. Like it's just the natural progression. And it felt to me like there was almost no competition. Like I would just be really creative and like immediately it was the top not safe for post on Reddit. Like, well, I didn't even try that hard. And so it's really shocking to me that other women who are doing this sort of thing. </s><s>[INST] Is that still a little bit of the case? Like that there's not as much like, because from my sort of outsider perspective that seems to be still the case. Like there's not, like, as you describe it, that's kind of cool. That's like almost like playing, like having fun with sexuality almost. [/INST] Yeah. </s><s>[INST] Yeah. And yeah, but that does require kind of thinking through... It's almost like a creative project, like a photography project or something like that almost like a little skit movie, [/INST] it's interesting, movie, it's interesting. Is this vibe of like how can you bring like vibrant novelty to whatever you're doing, anything you're doing. Yeah. And I really like doing this with surveys too. Like I've been doing a lot of standard surveys, but I'm also like experimenting with novel creative artistic surveys. I'm like, how do you ask a question in a way that's like beautiful and unusual and like a thing that's completely groundbreaking? </s><s>[INST] Like nobody's ever like trying to cross it with the word. You always make everything so poetic and romantic is disgusting, no. But yes, I think you have that engine in your head, I guess, of creativity. Like, yeah, the way you ask questions, which is not trivial to do. Like for, it's actually very difficult to do like good survey questions. And I mean, we're joking, but like, yeah, almost like poetic because you have to ask a question in a way that doesn't lead to the answer. Yes. Like you have to kind of inspire them to think and then indirectly get at the truth. [/INST] It's just very, it's an art form, honestly. Yes, yeah, and also in a way where they don't misinterpret the question because it's amazing how any question you think, oh, this is the clearest question possible. No, you're wrong. </s><s>[INST] It has to be even clearer. Right. Willingly or unwillingly. Cause like you also have to defend against that question being criticized later when you publish about it. All of that. [/INST] You have to think about it all. I think this might be my greatest strength. So I'm not very good at statistics. I'm not like great at presenting data, but I think probably my greatest strength is in fact survey design and like question phrasing. Cause I've tweeted so many thousands of polls and every single one, I get people telling me like the way that they misinterpreted the poll. So it's like, it's like gone through fire. And then again, I am testing the phrasings all the time. like, what happens if you slightly shift phrasings and eventually, I'll do the same question test over time to see how it changes and the way </s><s>[INST] the framing affects the results. So the good and the bad or the scamming, so you said good, the what was it, I forgot about your meaning you said? The freedom. The freedom. [/INST] The freedom to also be creative. Yeah, and the advantage to it, it was exhausting, the site that I was on the way that it structured is that you're ranking on the site and thus the amount of people that see you and thus the amount of money you earn is affected by the amount of money that you earn on average over the last 60 days. So if you're streaming and nobody's tipping you, this means that you're going to be dropping down in the rankings, which is gonna make it harder </s><s>[INST] in the future. [/INST] Okay, so the rich get richer in that site? Yeah, so it's very high pressure. Like if you're on, you need to be making money as fast as you can, if you wanna continue to make money. So that was really stressful. It was very mentally taxing. I would do it for a couple hours and just log off and be completely exhausted because you're just like on as hard as you can. And this is why I have a little PTSD on streaming. Like I've considered Twitch streaming and I try a little bit and I'm like, I haven't fully integrated the fact that you don't have to be like maximally entertaining every single second yet. You can actually just chill out and take it slow </s><s>[INST] and nothing bad happens. [/INST] Yeah, yeah, you can just enjoy silence. </s><s>[INST] Yeah. Did you feel lonely doing it? [/INST] I mean, even just streamers feel lonely. </s><s>[INST] I moved into a house of cam girls. [/INST] Did that make it better or worse? It better, they're great. </s><s>[INST] I'm still friends with them to this day. Also, it was like a team, [/INST] I was like, we're in this kind of together. Yeah, so we was like working together and stream together and swap our clothes and stuff. </s><s>[INST] It was great. [/INST] Swap ideas too. </s>

<s>[INST] been educated on, that just their whole life revolves around. Michael, you don't bring up Ayn Rand that much in conversation except as kind of references every once in a while as part of the humor of just the general flow and the music of the way you like to talk. Well, why do you think you don't integrate her into your philosophy when you're like explaining ideas and all those kinds of things? [/INST] Like why is she not, you know, a popular reference point for discussion of ideas? Because I don't know if everyone's going to agree with or can agree with me. I think for a certain percentage of the population, actually I talked to someone from the Ayn Rand institute, I forgot his name, Older Guy with Glasses, and he didn't disagree with me. He said, this is changing. I said, I think for a certain percentage of the population who are uninformed about her work, higher than 10%, less than 50%, you mentioned Ayn Rand, they have been trained to think this is identical to Scientology. So as soon as her name comes up, it's like, okay, I'm out the door. I'm not going to have anything to do with this. And everyone who follows her is a crazy person. That's one thing that has happened. Another thing is Rand in her personality was very aggressive and antagonistic. She was for a long time the lone voice in the wilderness being like, this isn't like one of her big adversaries in a certain sense is Milton Friedman. And she really hated how Milton Friedman was like, oh, you know, having rent control is inefficient. And she's like, inefficient. We're talking about mass homelessness and people dying. And you're talking about this, like what color tie goes with this color shirt? And in fact, it's hilarious. There was an organization called the Foundation for Economic Education Fee. Leonard Reed was the head of this. And there were a series of letters and she was helping him. She was much more philosophically grounded in a certain context than he was. And there was an essay, a pamphlet that he published called Roofs or Ceilings. It was co-written by Milton Friedman, later Nobel prize winner, and George Stigler, also later Nobel prize winner. And basically the argument was, well, if the government controls all housing, how's that going to work out? And she's sitting there and she's typing in all caps. So, you know, she's holding up this shift key and doing this on a typewriter and being like how, and you can imagine her app with her cigarette holder, apoplectic, being like, how is an organization ostensibly devoted to free enterprise discussing this Stalinist idea in the most casual of terms? She's like, have I taught you not? And what's amazing is so at fee, they only have her letters because she sent them to read the Ayn Rand Institute must have Leonard Reed's letters. I was able to, knowing Rand enough, predict exactly what the conversation would go like because he also did something she didn't approve of, which is he asked other people for feedback on her work. And she goes, I gave this to you to read. Who are you shopping around to some jerk that I don't, I need their approval. What are you doing? So it was a very interesting situation. But so that's one issue. I remember this is quite honest. I remember this is Ayn Rand when she's here. She was young. She wasn't that young. Well, I mean, it's before Ashleigh Shropp. It was before at left. So it's before she's super famous and before this is the fan heads being published. But she's trying to work with others and they're disappointing her left and right. She wasn't that young. She was in the 40s. And also when you are a, what she takes away from bad people is you have these kids, right? And you're going to sit down with them and they're going to be like, yeah, I'm going to take your guns. I'm going to lock you in your house. I'm going to take 60% of your income and all this other stuff. And they might up to reading Rand, they might sit down and have a discussion. And Rand goes, hey, you know what? You didn't have to give them an answer. You could say, go to hell. We're not having this conversation and you have no right to one second of my life. And this is not a legitimate opener. This is a declaration of war. This isn't like, it's not like if I sit down with you, I'm like, hey, Ron, here are my plans for your wife. Go to hell. This isn't a conversation we're having. Oh, I'm going to make you unsafe in your house. What? This is not a discussion. So what happens is these people who five minutes ago were able to have a debate with this kid because people read Rand when they're young often. And now that kid is like, yeah, I'm not even talking to you. It's her fault. Whereas in reality, it's that person's fault because that person had no right, although they've been trained to the contrary of our culture, to believe, yeah, I'm going to sit down and we're just going to equally have a discussion over your own life. And you have one vote and I have one vote and we're going to, oh, Lex has a vote and that's how it's going to be. And Rand's not having it. So I think those are two issues. And there's some other things which I don't need to get into, but one of the things that Rand said consisting of her life is that her philosophy is an integrated whole, right? So to be an objectivist isn't just like, I like Atlas Shrugged. It means I accept objectivism as a totality. Since I do not, I think it is proper to be respectful to her wishes and not constantly be, especially given that I have somewhat of a platform to be like, Ayn Rand, Ayn Rand, because I don't think Ayn Rand would have liked it if I was talking about Ayn Rand this much. </s>

<s>[INST] Do you think people at that time had the dream of what cloud computing is starting to become now. Which is computing is everywhere. That you can just plug in almost you know and you never know how the magic works. You just kind of plug in at your little computation they need to perform and it does. It was that the dream? I [/INST] don't know where that was the dream. I wasn't part of it at that point. Remember I was an intern first summer. But my sense is Given that it was over 50 years ago. Yeah. They had that idea that it was an information utility. That it was something where if you had a computing task to do you could just go and do it now. I'm betting that they didn't have the same view of computing for the masses. Let's call it the idea that you know, your grandmother would be shopping on amazon. I don't think that was part of it. But if your grandmother were a programmer it might be very easy for her to go and use this kind of utility. </s><s>[INST] What was your dream of computers at that time? What did you see as the future of computers? Because you have predicted what computers are today? Oh, [/INST] short answer. Absolutely not. I have no clue. I'm not sure I had a dream. It was a dream job in the sense that I really enjoyed what I was doing. I was surrounded by really, really nice people, Cambridge is very fine city to live in in the summer. Less so in the winter when it snows. But in the summer it was a delightful time. And so I really enjoyed all of that stuff and I learned things and I think the good fortune of being there for summer led me then to get a summer job at Bell Labs the following summer and that was going to be useful for the future. </s><s>[INST] So this Bell Labs is this magical legendary place. So first of all, where is by labs? And can you start talking about that journey towards UNIX at Bell Labs? [/INST] Yeah, So Bell Labs is physically um scattered around at the time, scattered around New Jersey. The primary location was in a town called Murray Hill or a location called Murray Hill is actually That across the boundary between two small towns in New Jersey called New Providence in Berkeley Heights. Think of it as about 15, 20 miles straight west of New york city and therefore about an hour north of here in Princeton. Um And at that time it had make up a number three or 4000 people there, many of whom had phds and mostly doing physical sciences, uh Chemistry, physics, materials kinds of things, but very strong math and it rapidly growing interest in computing as people realized you could do things with computers that you might not have been able to do before. You could replace labs with computers that had worked on models of what was going on. So that was, that was the essence of Bell labs and again, I wasn't a permanent play there. I was, that was another internship I got lucky and internships, </s><s>[INST] I mean if you could just lingering a little bit, what was the, what was in the air there? Because some of the, the number of Nobel prizes, the number of touring awards and just legendary computer scientists that come from their inventions, including developments including UNIX, it's just uh, it's unbelievable. So is was there something special about that place? [/INST] Oh, I think there was very definitely something special. Um I mentioned the number of people is a very large number of people, very highly skilled and working in an environment where there was always something interesting to work on because the goal of Bell labs, which was a small part of AT and T, which provided basically the country's phone service. The goal of a TNT was to provide service for everybody and the goal of Bell labs was to try and make that service, keep getting better. So improving service and that meant doing research on a lot of different things, physical devices like the transistor or fiber optical cables or microwave systems, All of these things, the lives worked on and it was kind of just the beginning of real boom times. And computing as well as when I was there. I went there first in 66. So computing was at that point fairly young and so people were discovering that you could do lots of things with computers. </s><s>[INST] So how's UNIX born? [/INST] So mall ticks in spite of having an enormous number of really good ideas, lots of good people working on it fundamentally didn't live up at least in the short run and I think ultimately really ever to its goal of being this information utility, it was too expensive and certainly what was promised was delivered much too late. Um and so in roughly the beginning of 1969, Bell Labs pulled out of the project. The project at that point had included M. IT. Bell labs and General Electric. General electric made computers. A general electric was the hardware operation. So Bell labs realizing this wasn't going anywhere on a time scale they cared about pulled out of the project. And this left several people with an acquired taste for really, really nice computing environments, but no computing environment. And so they started thinking about what could you do if you're going to design a new operating system that would provide the same kind of comfortable computing as C. T. S. S. Had, but also the facilities of something like Multex brought forward. Um And so they did a lot of paper design stuff and at the same time, Ken, Thompson found what is characterised as a little used PDP seven where he started to do experiments with file systems, just how do you store information on a computer and efficient way? And then this famous story that his wife went away to California for three weeks, taking their one year old son and three weeks and he sat down and wrote an operating system which ultimately became UNIX. So software productivity is good in those days. </s>

<s>[INST] and you accept being attacked from both sides and grow from it and learn from it. But the danger is that after being attacked assuming you don't get canceled a K A completely removed from your ability to tweet, uh, you might become jaded and not want to talk about autism anymore. [/INST] I don't and I didn't, I mean it's happened to me, </s><s>[INST] but that's what [/INST] I did was I listened to both sides and I chose, I tried to get information and then I decided that I was going to use autistic Children and now I'm moving forward with that. Like I don't </s><s>[INST] know for [/INST] now. Yeah. Until until I get updated information and I'm never going to get anything perfect. But I'm making choices and I'm moving forward because being a coward and like just retreating from that I think. But </s><s>[INST] here's the problem. You're a very smart person and an individual researcher thinker an intellectual, so that's the right thing for you to do. The hard thing is one as a company, imagine you had a PR team, he said kate like this. You [/INST] should. </s><s>[INST] Yeah, I mean, just well, if you were if you hired pr people, like obviously they would see that and they'd be like, well, maybe don't bring up autism, Maybe don't bring up these topics. You're you're getting attacked. It's bad for your brand. They'll say the brand word. They'll be uh you know, if you look at different demographics that are inspired by your work, I think it's insensitive to them. Let's not mention this anymore. Like there's this kind of pressure that all of a sudden you or or you do suboptimal decisions, you take a kind of poll. Um again, it's looking at the past versus the future, all those kinds of things. And it becomes difficult in the same way that it's difficult for social media companies to figure out like who's censor who recommend this [/INST] is ultimately a question about leadership. Honestly, like the way that I see leadership, because right now the thing that bothers me about institutions and a lot of people who run current institutions is that their main focus is protecting the institution of protecting themselves personally. That is bad leadership because it means you cannot have integrity, you cannot lead with integrity and it makes sense because like obviously if you're the type of leader who immediately blows up the institution, you're leading then that doesn't exist anymore. And maybe that's why we don't have any good leaders anymore because they had integrity and they didn't put, you know, the survival of the institution first. But I feel like you have to just to be a good leader, you have to be responsible and understand that with great power comes great responsibility, you have to be humble and you have to listen and you have to learn, you can't get defensive and you cannot put your own protection before other things </s><s>[INST] take risks where you might lose your job, you might lose your well being because of um because in the process of standing for the principles for the things you think are right to do. Yeah. Based on the things you like, based on learning from like listening to people and learning from what they what they feel and the same goes for the institution. Yeah. Yeah. But I ultimately actually believe that those kinds of companies and countries succeed that have leaders like that you should run for president. [/INST] No, thank </s><s>[INST] you. Yeah, [/INST] that's maybe the problem like the people who have good ideas about leadership, they're like, </s><s>[INST] yeah, this [/INST] is why I don't I'm not running a company. </s><s>[INST] It's been I think three years since the Jeffrey Epstein controversy at M. I. T. M I. T. Media Lab, joi ito the head of the Media lab resigned and I think at that time you wrote an opinion article about it. So just looking back a few years have passed, what what have you learned about human nature? Um from the fact that somebody like Jeffrey Epstein found his way inside M. I. T. [/INST] It's a really good question, what have I learned about human nature? I think, well there's there's how did this problem come about, and then there's what was the reaction to this problem and to it becoming public? And in the reaction, the things I learned about human nature were that sometimes cowards are worse than assholes, wow, I'm really </s><s>[INST] that's a really powerful statement, [/INST] I think because the assholes at least you know what you're dealing with, they have integrity in a way they're just living out their asshole values and the cowards are the ones that you have to watch out for and this comes back to people protecting themselves over doing the right thing. Um they'll throw others under the bus. </s><s>[INST] Is there some sense that not enough people took responsibility [/INST] for sure, and I mean, I don't want to sugarcoat at all what joe ito did, I mean, I think it's gross that he took money from Jeffrey Epstein, I believe him that he didn't know about the bad, bad stuff, but I've been in those circles with those like public intellectual dudes that he was hanging out with and any woman in those circles, like 10 zillion red flags, just the whole environment was so misogynist like and so personally because Joey like was a great boss and a great friend, I was really disappointed that he ignored that in favor of raising money um and I think that it was right for him to resign in the face of that, but one of the things that he did that I know many others didn't was he came forward about it and he took responsibility and all of the people who didn't, I think it's just interesting. The other thing I learned about human nature, okay, I'm going to go on a tangent, I'll come back I promise. So I once saw this tweet from someone or was a twitter thread from someone who worked at a homeless shelter and he said that when he started working there, he noticed that people would often come in and use the bathroom and they would just trash the entire bathroom, like rip things out of the walls, like toilet paper on the ground and he asked someone who had been there longer, like why did they do this? Why do the homeless people come in and trashed the bathroom and he was told it's because it's the only thing in their lives that they have control over. And I feel like sometimes when it comes to the response, the just the mobbing response that happens in the wake of some harm that was caused if you can't target the person who actually caused the harm who was Epstein, you will go as many circles out as you can until you find the person that you have power over and you have control over and then you will trash that. And it makes sense that people do this. It's again, it's a human nature thing. Of course you're gonna focus all your energy because you feel helpless and enraged and you and it's unfair and you have no other power, you're going to focus all of your energy on someone who's so far removed from the problem that that's not even an efficient solution. And </s>

<s>[INST] Any time, you know, networks, anytime you learn from data form representation from data an automated way, it's not very explainable as to or it's not introspective to us humans in terms of how this neural network sees the world. Where why does it succeed so brilliantly on so many in so many cases and fail so miserably in surprising ways and small. So what do you think this is uh the future. There can simply more data, better data, more organized day to solve that problem Or is there elements of symbolic systems that need to be brought in which are a little bit more explainable? [/INST] So I prefer to talk about trust and validation and verification rather than just about explain ability. And then I think explanations are one tool that you use towards those goals. And I think it is important issue that we don't want to use these systems unless we trust them and we want to understand where they work and where they don't work and in an explanation can be part of that. Right? So apply for a loan and I get denied. I want some explanation of why. And uh you have uh in europe we have the G. D. P. R. That says you're required to be able to get that. But on the other hand, an explanation alone is not enough, right? So you know, we were used to dealing with people and with organizations and corporations and so on and they can give you an explanation and you have no guarantee that that explanation relates to reality, right? So the bank can tell me why you didn't get the loan because you didn't have enough collateral and that may be true or it may be true that they just didn't like my religion or or something else. Uh I can't tell from the explanation. And that's, that's true, whether the decision was made by computer or by a person. So I want more, I do want to have the explanations and I want to be able to have a conversation to go back and forth and said, well, you gave this explanation, But what about this? And what would have happened if this had happened and what I need to change that? So, I think a conversation is a better way to think about it than just an explanation as a single output. Uh, and I think we need testing of various kinds. Right? So in order to know was the decision really based on my collateral or was it based on my religion or skin color or whatever. I can't tell if I'm only looking at my case, but if I look across all the cases, then I can detect the pattern. Right. Right. So you want to have that kind of capability? You want to have these adversarial testing? Right? So we thought we were doing pretty good at object recognition and images. They said, look, we're at sort of pretty close to human level performance on image in that and so on. Uh, and then you start seeing these adversarial images and you say, wait a minute. That part is nothing like human performance. </s><s>[INST] We can mess with it really easily. [/INST] You can mess with it really easily. Right? And yeah, you can do that to humans too. Right? So in </s><s>[INST] a different way, perhaps [/INST] humans don't know what color the dress was. And so they're vulnerable to certain attacks that are different than the attacks on the on the machines. But you know, the tax machines are so striking. Uh they really change the way you think about what we've done, right? And the way I think about it is I think part of the problem is we're seduced by our low dimensional metaphors, right? So, you know, you like that. You look in a textbook and you say, okay, now we've mapped out the space and you know, cat is here and dog is here and maybe there's a tiny little spot in the middle where you can't tell the difference. But mostly we've got it all covered. And if you believe that metaphor, uh then you say, well we're nearly there. And uh you know, there's only gonna be a couple of adversarial images, but I think that's the wrong metaphor. And what you should really say, it's it's not a two D flat space that we've got mostly covered, it's a million dimension space. And cat is this string that goes out in this crazy path. And if you step a little bit off the path in any direction, you're in nowhere land and you don't know what's going to happen. And so I think that's where we are. And now we've got to deal with that. So it wasn't so much an explanation, but it wasn't an understanding of what the models are and what they're doing. And now we can start exploring how do you fix that? </s><s>[INST] Yeah, validating their boston's of the system so on. But take you back to the this uh this word trust. Do you think we're a little too hard on our robots in terms of the standards we apply? So you know of uh there's a dance, there's a there's a there's a dance and nonverbal and verbal communication between humans. You know, if we apply the same kind of standard in terms of humans, you know, we trust each other pretty quickly. Uh you know, you and I haven't met before and there's some degree of trust, right that nothing's gonna go crazy wrong and yet to ai when we look at ai systems were we seem to approach whose skepticism always, always. And it's like they have to prove through a lot of hard work that they're even worthy of even inkling of our trust. What do you what do you think about that? How do we break that very close that gap? [/INST] I think that's right. I think that's a big issue. Uh Just listening, my friend uh Mark Moffett is a naturalist and he says uh the most amazing thing about humans is that you can walk into a coffee shop or a busy street in a city and there's lots of people around you that you've never met before and you don't kill each other? </s>

<s>[INST] one convenient thing in terms of turning ethics into computation and ask the question of what maximizes the likelihood of the survival of the species. [/INST] Yeah, that's a good existential issue. But then when you say survival of the species, right, you might say, um, you might, for example, for example, let's say, forget about technology, just, you know, hang out and, you know, be happy live our lives go into the next generation, you know, go for many, many generations where in a sense, nothing is happening that, okay, Is that not? Okay. Hard to know. In terms of, you know, the, the attempt to do elaborate things and the attempt to might be counterproductive for the survival of the species, like for instance, I mean, in, uh, you know, I think it's it's also a little bit hard to know. So, okay, let's take that as a, as a sort of thought experiment. Okay, You know, you can say, well, what are the threats that we might have to survive? You know, the super volcano, the asteroid impact the, you know, all these kinds of things. Okay, so now we inventory these possible threats and we say, let's make our species as robust as possible relative to all these threats. I think in the end it's a it's sort of an unknowable thing. What what it takes to uh, you know, so, so given that you've got this ai and you've told that maximize the long term, what does long term mean? Does long term mean until the sun burns out? That's that's not gonna work. You know, does long term mean next 1000 years? Okay. They're probably optimizations for the next 1000 years that uh, it's like, it's like if you're running a company, you can make a company would be very stable for a certain period of time. Like if, you know, if your company gets bought by some, you know, private investment group, then they'll, you know, you can, you can run a company just fine for five years by just taking what it does and you know, removing all R and D. And the company will burn out after a while, but it'll run just fine for a while. So if you tell the ai keep the humans okay for 1000 years, there's probably a certain set of things that one would do to optimize that many of which one might say, well that would be a pretty big shame for the future of history, so to speak for that to be what happens. But I think, I think in the end, you know, as you start thinking about that question, it is um what you realize is there's a whole sort of raft of underside ability, computational irreducible itty. In other words, it's I mean one of the good things about sort of the the the what our civilization has gone through and what sort of we humans go through is that there's a certain computational irreducible Itty to it in the sense that it isn't the case that you can look from the outside and just say the answer is going to be this at the end of the day, this is what's going to happen. You actually have to go through the process to find out. And I think that's that's both, that feels better in the sense, it's not a, you know, something is achieved by going through all of this uh all of all of this process. And it's uh but it also means that telling the ai go figure out, you know, what will be the best outcome. Well, unfortunately, it's going to come back and say it's kind of undecided ble what to do. We have to run all of those scenarios to see what happens. And if we want it for the infinite future were thrown immediately into sort of standard issues of of kind of infinite computation and so on. </s><s>[INST] So yeah. Even if you get that the answer to the universe and everything is 42 you still have to actually run the universe yes. To figure out like the question, I guess, or the the, you know, the journey is the point, [/INST] Right? Well, I think it's saying to summarize this is the result of the universe. Yeah, that's if that is possible, it tells us, I mean the whole sort of structure of thinking about computation and so on and thinking about how stuff works if it's possible to say and the answer is such and such. You're basically saying there's a way of going outside the universe and you're kind of, you're getting yourself into something of a paradox because you're saying if it's knowable what the answer is, then there's a way to know it, that is beyond what the universe provides. But if we can know it, then something that we're dealing with is beyond the universe. So then the universe isn't the universe, so to speak. </s><s>[INST] So. And in general, as we'll talk about at least far small human brains, it's hard to show that the result of a sufficiently complex computation. It's hard, I mean, it's probably impossible right on this side ability. So, and the universe appears by at least the poets to be sufficiently complex. They won't be able to predict what the heck it's all going to, [/INST] well, we better not be able to because if we can it kind of denies. I mean, it's, you know, we're part of the universe. So what does it mean for us to predict? It means that we that our little part of the universe is able to jump ahead of the whole universe and you know, this, this quickly winds up. I mean, it is conceivable, the only way we'll be able to predict is if we are so special in the universe, we are the one place where there is computation, more special, more sophisticated than anything else that exists in the universe. That's the only way we would have the ability to sort of the almost theological ability, so to speak, to predict what happens in the universe is to say somehow we're better than everything else in the universe, which I don't think is the case. </s>

<s>[INST] Yeah, I agree with you in my mind that sort of destruction and suffering our next door neighbors. So we don't need to destroy all of human civilization if much a large fraction that lives in conditions that we would equate the suffering that's uh that's not a good world, Is there advice that you would give to a young people today about life, about career, about how they can help a world or 53% are living uh are living under authoritarian governments. But in general world that's full of injustice but also full of opportunity. [/INST] Just thinking about my own upbringing, I went to a public school here and we never learned about money. It was never part of our curriculum. Um Even personal finances was not part of our curriculum. You can take like an optional course to learn about business or something. Um And I think that that would be really valuable as a young person or as a teenager um to start incorporating into your Children's lives is like a curiosity about what is money I think would be very healthy regardless of what path that takes them down. Because we don't think about it enough either from an administrative sort of personal finance thing about like responsibility or more fundamentally like what is it? And who creates it? Where did it come from? Both of those things are very important. So my advice to a young person would be to get to the point where you feel like you can answer the question, what is money? So </s><s>[INST] you ultimately see money as as kind of power and freedom and a mechanism is suffering. [/INST] So court to everything. The United States, whether you want to call it the tax Americana, the empire, the hyper power or whatever you want to call this moment in time where the U. S. Is dominant around the world. It is because of the fact that we have this petrodollar system where we are able to force the Saudis and other oil producing nations to sell their oil in dollars. That is really inescapable, inseparable from our power. And that's very rarely talked about and it's very important to understand. So young people started thinking about that stuff. Be good. </s><s>[INST] I remember being sounds silly to say but I remember being really uncomfortable that I was dependent on my parents at a young age for for like financial [/INST] You need to be 18 to a bank account or whatever. One of the people that we supported today traffic through our we do software development funding for people in Bitcoin open source projects. And he's one of the guys we funded is this very young smart sort of prodigy. He's like 17. But one of the reasons he got into Bitcoin was because he wanted to have control of his money when he was like 14. If you think in history people who invented uh all kinds of incredible contributions to science or math. I mean a lot of them did it before they were 15. So think about that maturity that is capable and possible in many people like I've participated in some of the years ago some of the sort of selection processes for like the thiel fellowship which is really amazing. Like these people who are 14, 15, 16, who don't need to go to college, they're already like, so smart, they can figure it out, but they wouldn't be allowed to have a bank account, right? So, hey, that's kind of cool. Like now you have a permission less money, you can you can open up yourself without permission from your parents. It's kind of cool. </s><s>[INST] Yeah, That's fascinating to me. I I feel like I would have loved my parents more [/INST] if you had a little more separation if </s><s>[INST] I had freedom to to fully realize myself, because I felt like I was a little bit trapped, but I don't know, it's uh it's not explicit, right? It's a little bit, it's like a subtle push that you're somehow dependent on them. I mean, part of that is like, I think it actually very much has to do not talking about money, like, what does it take to operate as an individual entity in this world? Like, knowing that when you're 10 years old, knowing that when you're very young so that you've uh then you see the how amazing it is To uh have the support of your parents until you're 18, like have that freedom uh have the freedom to appreciate the value parents bring, and at the same time the freedom to leave uh in some capacity to carve your own path. I mean, just, just all of that, I think for for weirdos, like me, especially because I was a very non traditional path that I think it would be very empowering and certainly will be empowering in the third [/INST] world, not just Weirdos like you. Yeah I was going to mention one of the people I got who taught me about Bitcoin, her name's Roya Mahboob, she's an afghan technology ceo and in 2013 she started paying her employees in Bitcoin because uh they were not allowed to open bank accounts. The women that worked for her, she started the country's first female like all female software company and if they brought cash home they're like husbands or uncles or brothers would steal it from them. There's a power patriarchal dominance thing going on but they had phones and she was able to pay them in Bitcoin and no one knew and it gave them that power and that that's always stuck in my mind is a very interesting effect of this kind of thing of permission this money like that. It could be an empowerment tool. So absolutely. </s><s>[INST] So in your own personal life where did the deep concern for the suffering in the world come from? Where was that born? [/INST] I was going to be an engineer actually. And then in 2003 we invaded Iraq and I got very interested in why we did that as a nation and I switched to my focus of study to international relations and that's how I kind of went down the kind of political science democracy rabbit hole and ended up getting a job at the Human rights Foundation so that I'm a very much a child of like 9 11 and the Iraq war. Those are the two really formative events for me personally, can you break that </s>

<s>[INST] It's just forever. Yeah, it is. I'm gonna apply that to my dating life once again. [/INST] Metaphors just keep on coming. Metaphors just keep on coming. Well, if you think about it, like my tastes has changed throughout the years. When I first saw a Model 3 Tesla, I thought it was the most hideous car I've ever, without the Gorilla, I was like, this is so stupid. It took me all but two months to think that it was one of the coolest looking cars. Same with Cybertruck. I mourned Cybertruck. When I first saw that thing, I was at that thing with, and I went with, we used to do a podcast called Our Ludicrous Future. So we talked a lot about cars and EVs and stuff. We went to that unveiling and literally, we had almost a non-alcohol-induced hangover the next morning of mourning the hideousness of Cybertruck. Come six months later, a year later, </s><s>[INST] and I'm like, damn it, that thing's actually kinda cool. That also teaches you something about, again, it's the thing you said earlier, sort of going against the current of the experts or the beliefs or whatever and making a decision from first principles. Some of that also applies to design and styling and fashion and culture and all that. Big time. Some of that, fashion especially, it's so interesting. So subjective. Being rebellious against the current fads [/INST] actually is the way to pave the new fads. Big time, so subjective. When it didn't take long for others to follow, you look at currently what Hyundai's doing with their, I forget which one, the Ionic or something like that. It's square. It's boxy. It's a throwback. It's 80s. It's got these beautiful retro tail lights. It's got these square headlights. It's very inspired by Cybertruck, in my opinion. It might not be. It might be coincidental that we're all kind of getting </s><s>[INST] this retro future vibe, but retro future vibe. I personally like the boxy, so I never, I still haven't understood Porsches, Porsches. I still can't quite understand the small size, [/INST] the curves, I don't quite get it. Like I said, I don't love the look of the RX-7. I don't love it, but I love it because of the engineering, </s><s>[INST] I guess, that it represents, you know what I mean? Yeah, it's not the surface stuff. It's the deep down stuff. It's that 50-50 weight distribution that matters. All right, let's talk about Starship a little bit. We've been sneaking up to it from a bunch of different directions. Can you just say, what is Starship and what is the most impressive thing to you about it? I mean, you've talked about the engines involved. Maybe you haven't really, kind of like dancing around it, but because this is such a crucial thing in terms of the next few years, in terms of your own life personally, and also just human civilization reaching out to the stars, it seems like Starship is a really important vehicle to making that happen. So what is this thing that we're talking about? [/INST] Yeah, so Starship is currently in development, the world's largest, most powerful rocket ever built, fully reusable rocket, a two-stage rocket. So the booster is landed and, all this is currently aspirational until it's working. So I'll say what it's aspirationally going to be. And obviously I have faith that that will happen, but just factually. So the booster will be reused, landed and refueled and reused. The upper stage will be landed, refueled and reused. And ideally, rapidly, in the sense, not talking about months or weeks of refurbishment, but literally talking about like mild inspections, and ideally like under 24 hour reuse, where you literally land it and fly it like an airplane. So it utilizes liquid methane and liquid oxygen as its propellants. It utilizes the current iterations of it are 33 Raptor engines on the booster engine, or on the booster, and six Raptors on the second stage. So they'll be three that are vacuum-optimized and three that are sea level-optimized on the upper stage. That are primarily, they'll be used I think stage separation anyway in space, but their main reason that they use them is so they can use them for landing too, the three sea level engines to be able to propulsively land the upper stage as well. </s><s>[INST] So the three Raptor engines are the ones that generate the thrust that makes it the most powerful rocket ever built? By almost double. Compared to Saturn 5, really? [/INST] The N1 had 45 meganewtons of thrust, the Saturn 5 had, I think, 35 or 40 meganewtons of thrust, and this has 75 meganewtons. So we're talking almost double. It's a lot of power. </s><s>[INST] That could be the sexiest thing I've ever heard. Okay, so what are the different testing that's happening? So like, what's the static fire with some of these Raptors look like? And where do we stand? You were just talking about offline, like the thing that happened yesterday. [/INST] Yeah. That was impressive. You know, everything in this is kind of iterations. And so, you know, the milestones that we're seeing... We actually have on everydayastronaut.com, we have a milestone checklist of like all the things we're hoping to see that we kind of need to see before the first orbital flight of this rocket. So a big milestone that got checked off yesterday was a wet dress rehearsal. So it's literally like fueling the rocket up, getting ready to do everything, but lighting the engines basically. So we're talking about loading it with propellant all the way. This is the first time. Yeah, right. Where's the milestone? Right there at the top, click that big picture. Yep, just anywhere, that big picture. </s><s>[INST] Yep, yeah, right there. It's the milestones. So there's the what dress rehearsal? So what, what dress rehearsal? [/INST] Yep. So, that's where they, for the first time, they filled it completely to the brim with both liquid oxygen and liquid methane. Now, they had done component-level testing where they filled with liquid nitrogen, which is, you know, it's an inert gas, so it's could like say it leaks out, it's not gonna explode. You could just have a big giant pool of liquid nitrogen flooding the area. But it's not going to be an explosion. So they've done that for cryo testing to make sure all the components and stuff can handle being at cryogenic temperatures. It's kind of a good analog before you start putting your fuel and your oxidizer in there. But now, as of yesterday, they fully fueled the rocket with propellant. Both stages, the first stage and the second stage, were all fully stacked on the pad. I mean, it was the first sense we really got of like, this is what it's going to look like right before it takes off. </s>

<s>[INST] what you ask about Dick dan is gonna love hearing this, I'm going to uh do you have, do you have a period of history, whether it's dan or in general that you draw for your own life? Like kind of thinking about the world about human nature that you go to is a World war two, Is it uh Wrath of the Cons, the genghis khan, is that some other more ancient history? Is that World War One? Is there something that kind of echoes with you in the voice of dan or or anyone else that you connect to? [/INST] I feel like the 19 thirties and forties are fascinating because they force you to like really grapple with the question of like, you know, where does evil come from? Right? Like the sort of mental puzzle that I've always had in my head is like on the one hand, you know, things like the holocaust happened, but on the other hand, if you just go in like have a coffee with with people, then like 100 times out of 100 everyone just seems so nice. But so yeah, I like how do you kind of reconcile the macro and the micro there? Right? And that's the sort of thing. That's very difficult if you don't have um a lot of, I guess the right kind of personal experience, like, especially if your personal experience starts off being sheltered, like it was for me, right? Like, you know, I know the stereotype is that the nerves get bullied in school, but like, actually for me in my school experience was just being treated with kindness by everyone. And uh, so that definitely made it harder to understand things. I remember actually being pretty blindsided when I started ethereum and then within six months there started being fights over like who would get more shares if if ethereum turned out to be a company and then I suggest that we should just make it be a nonprofit and somehow that ended up upsetting people. Um so, so the, so the fascinating thing for me is that the guy I've been, you know, obviously reading and listening to the history and then at the same time just like observing things happening in the crypto space. And so one of my interesting, um like mental intuitions that I've gotten is that I think like most evil doesn't come out of greed, it comes out of fear. And like one example of this in ethereum lands right? Is like I think the part of ethereum history where I thought that the ethereum community was at its lowest, and even when I personally was at my lowest now if you go back to the DAO fork in 2016 right? So you know the DAO hack happens and then we made this controversial decision to change the ethereum protocol. Uh And uh we um you know then there was that ethereum classic split and as soon as that ethereum classic split happened, you know there was like a lot of anger everywhere and they're starting their started especially being anger when the price of E. T. C. Started like taking up right? So this was the time when it Ether started off being $13 in an ethereum classic started at zero, but then Suddenly there was this one day when like Keith dropped to 12.5 BTC went up to 0.5 and then they dropped more and people were saying things like um you know oh this whole thing ethereum classic is just a like a sigh up by you know the Bitcoin community and just a wealthy Bitcoin is trying to destroy ethereum and like in the back of my mind I knew that that wasn't entirely true, like there were definitely were Bitcoin is but at the same time like I think blaming political like internal disorder or blaming disagreements on foreign interference right? Like this is the sort of thing that you know, like countries governments do all the time, like it's a very convenient excuse, right? Because it allows you to just like blame these things that are happening on the foreigners and avoid actually grappling with the fact that like, well no, actually you have people in your very own community who just disagree with you and have a different belief. And I think, you know, I feel like the ethereum community, like during that time did not do a very good job of grappling with that. And I feel like like I during that time did not do a very good job of grappling with that. And so there was a lot of like blaming the Bitcoin ear's, there were also even a lot of people calling for us to use trademark wind, like basically Sue exchanges and try to prevent them from a listing ethereum classic. And like to me that was very unethical, right? Like this uh like using like basically using the government as a weapon to try to attack the other Cryptocurrency and destroy it as like goes completely against them. You know, the ideals of freedom and you know, like things that at least in theory we're supposed to stand for. Um but you know, like in that particular time, like basically what was happening was that, you know the Dc price was rising and at the same time the th price was dropping in lockstep and it really and there are a lot of Bitcoin people basically saying and this is the end of a theory. I mean I think a lot of people really were afraid that ethereum would be just like completely destroyed as a result of this. And so like Exactly that's yeah exactly. It came from the fear and like that's what I like allowed people to rationalize like an abandonment of principles that I think they would not have accepted in other circumstances. And I I definitely like to some extent played along with this myself and I definitely regret that to some extent well and I I definitely regret like the excesses completely. But so that and then obviously you know, Bitcoin block sized war similar sort of stuff happens. So like that that insight was interesting because like it does mentally make a lot of sense, right? Like when you're actually afraid that you know unless you act in some way that you know your entire world is going to collapse, like it's much easier to just rationalize you know forgetting your principles and doing whatever you have to to just save the specific thing that you care about. </s>

<s>[INST] Can I ask you a difficult question. So there's this famous um photograph of a falling man, so many people had to decide when they're above the fire in the fire whether to jump out of the building or to burn to death. What do you make of that decision? What do you make of that situation. [/INST] Those people who jumped those were acts of sheer desperation. I've been in fires and just minor burns but minor, you know, in situation, but I've been trapped or caught somewhat ended up in the burn center for some nothing, nothing serious at all. But like, but I I for those brief seconds, half a minute was, thank God if I didn't have my fire gear on, I would have been burned to very, very horrible level. Those people we're burning alive and they had the choice of either to stay there and burn alive or two launch themselves. And some of them, I don't fault them, but they had a few folks, they won't show it anymore because they say, I don't know why I defend some people, but they had a couple of folks that took umbrellas and they took garbage bags because they thought that it would slow down there except the acceleration rate to the ground and maybe just maybe they wouldn't be killed. And that's to me, a true sense of desperation for humanity to say I'm going to die either way. But let me take my chance and I don't know the exact number of those folks who did that, but our first Member of the Fire Department killed firefighter Daniel sir from 8 to 16 was struck by a jumper and one of my dear friends was ordered to help take him and they knew he was passed away because he was hit by a Flying Missile. I mean 120 mph body lands on you. Those those two bodies are now crushed And they were ordered to take that firefighter and bring him across the street to engine 10 Ladder 10. It was literally a firehouse less than 100 yards from the facade of the trade center from the trade center complex, they literally right there and there was plane parts that went into that firehouse landed into the front doors onto the roof. But the building itself was not destroyed. So it was used as a mini command center for quite a while. So my friend was ordered to take Daniel's body in respect and bring it over to this firehouse and give it some semblance of dignity and lay it out on one of the the bunk room, the bunks we have in the bunkhouse and just cover it with a sheet and put a sign please firefighter kill do not disturb and then we'll get to him later because obviously this operation is going to go on for days and my friend who is such a great, great, wonderful guy is so still to this day filled with guilt because if they weren't taking his body out with the respect and dignity that they did, it took a while because you know it's just it's a tough situation, his ladder company, it's coming over the bridge, there's a famous picture Vlad in 118, you see this tractor trailer fire truck is the one with the guy in the back also drives and it's a zoomed out shot and you see the Brooklyn bridge and you see only the fire truck in the middle and you see the two burning towers in the distance. Well his engine company was just ahead of them on the bridge and the only reason that engine company lived is their initial duty assignment was to take that firefighter and bring his body over. It's like the military, we don't leave anyone behind. These are our guys as we, some guys say it's all about the guy right next to you and nothing else really matters when that guy right next to you goes down, it stops, you get that guy to safety or if he's dead, you get him out. So in that time frame that saved his life. But that's a heavy burden to carry now for the rest of your life because you say if I wasn't helping my dead friend, I'm dead. Yeah. </s><s>[INST] What did it look like a ground zero? What did it feel like? What did it smell like? What you said it? There is a sense that it was almost like a war zone. But can you paint the picture of um how much dust is in the air? How hot is it? How many people are there? And again, how did it feel like [/INST] it was just um, it was a scene of controlled chaos control because there was a semblance of command and we were just trying to do our jobs, but it was such a frantic pace because we're now digging frantically knowing that there's life underneath this pile </s><s>[INST] and this is throughout the afternoon of [/INST] that. Yeah, I mean this was nonstop, you know, uh just nonstop really for for days. But from my particular crew, we literally kept going. We initially were dispatched over towards number seven, had </s><s>[INST] just gone down, [/INST] We were searching the post office that was there, there was reports of people trapped and we painstakingly searched every single inch of that building to make sure no one was left in there. And then we were deployed to the pile and the piles sort of ambiguous because it was just such a vast, vast pile. I mean, it went for city blocks and we were we were assisting in the retrieval of two port Authority police officers were lucky enough to survive, but they were trapped, they were deep down into a crevasse and they had to be physically dugout and extricated. So there was a couple of 100 few 100 guys involved in that process of bringing in equipment, jaws of life airbags to lift steel, you just to cut pieces of steel. It was just a huge operation and we were back toward the logistics end of it. Shuttling in gear and and bring it, bring in stretchers, bringing in oxygen, you know, whatever whatever was needed. And you were trying to climb over this, this jagged pile of debris. It wasn't like you just walked 100 ft on a on a street with something, you were trying to climb over this I beam and then down into this hole and then I'll back up that whole. I mean, just to run one piece of equipment, took a half an hour to get 100 ft, 200 ft mind you, some of these pieces of equipment, £100 you know, generator for her stools, this massive motor on a frame, </s>

<s>[INST] dream. What was the what was it like to be at? M. I. T. What was that culture shock you mean America in general but also I mean Cambridge is its own culture. So what was M. I. T. Like what was America like? [/INST] I think I wonder if that's similar to your experience at M. I. T. I was just at the media lab in particular, I was just really impressed is not the right word. I didn't expect the openness to like innovation and the acceptance of taking a risk and failing. Like failure isn't really accepted back in Egypt right? You don't want to fail like there's a fear of failure which I think has been hardwired in my brain. Um but you get to M. I. T. And it's okay to start things and if they don't work out like it's okay you pivot to another idea. And that kind of thinking was just very new to me. </s><s>[INST] It was liberating what media lab for people who don't know. M. I. T. Media lab is its own beautiful thing because they I think more than other places I might reach for big ideas and like they try. I mean I think I mean depending of course on who but certainly with Rosalind is you try wild stuff, you try big things and crazy things and and also try to take things to completion so you can demo them. So always always always have a demo. Like if you go one of the sad things to me about robotics lab at M. I. T. And there's like over 30 I think uh is like usually when you show up to robotics lab there's not a single working robot. They're all broken. All the robots are broken. Which is like the normal state of things because you're working on them. But it would be nice if we lived in a world where robotics labs had uh some robots functioning. One of my like favorite moments that just sticks with me. I visited boston dynamics and there was a first of all seeing so many spots, so many legged robots in one place. I'm like I'm home. [/INST] But </s><s>[INST] the uh this is where I was built. The cool thing was just to see there was a random robot spot was walking down the hall was probably doing mapping but it looked like he wasn't doing anything and he was wearing he or she. I don't know. But it well I like I [/INST] like in my mind </s><s>[INST] there are people, they have a back story but this one in particular definitely has a back story because he was wearing a cowboy hat. So I just saw a spot robot with a cowboy hat walking down the hall. And there was just this feeling like there's a life like he has a life. He probably has to commute back to his family at night. Like there's a there's a feeling like there's life instilled in this robot and it's magical. I don't know there was it's kind of inspiring to see. [/INST] Didn't say hello to did he say hello to you? Very </s><s>[INST] there's a focused nature to the robot. No listen I love competence and folk great like it was not going to get distracted by the shallowness of small talk. There's a job to be done and he was doing it. So anyway the fact that it was working is a beautiful thing. And I think media lab really prides itself on trying to always have a thing that's working. They could show off. [/INST] Yes. We used to call it demo or die. You you could not you could not like show up with like power point or something. You actually have to have a working, you know what my son who is now 13. I don't know if this is still his life long goal or not. But when he was a little younger his dream is to build an island that's just inhabited by robots like no humans. He just wants all these robots to be connecting and having fun and there you </s><s>[INST] go. You have human. Um Does he have an idea of which robots he loves most. Is it is it rumble like robots? Is it humanoid robots? Robot dogs or? It's not clear yet. [/INST] Um We used to have a which was one of the M. I. T. Media lab spinouts and he used to love </s><s>[INST] with a giant head. [/INST] Yes. It </s><s>[INST] spins. Right. Exactly. And it's an I like not glowing like. Right. [/INST] Right. Right. Right. Exactly </s><s>[INST] How 9000 but the friendly [/INST] version. He loved that. And then he just loves uh yeah he just I think he loves all forms of robots actually. </s><s>[INST] So embodied intelligence. [/INST] Yes. I </s><s>[INST] like I personally like legged robots especially uh anything that can wiggle its but no that's not the definition of what I love but that's just technically what I've been working on recently. So I have a bunch of legged robots now in Austin and I've [/INST] been doing </s><s>[INST] I was I've been trying to have them communicate affection with their body in different ways just for [/INST] art for </s><s>[INST] art really because I love the idea of walking around with the robots like as you would with the dog. I think it's inspiring to a lot of people. Especially young people like kids love [/INST] kids love </s><s>[INST] it. Parents like adults are scared of robots but kids don't have this kind of weird construction of the world that's full of evil. They love cool things. [/INST] Yeah I remember when Adam was in first grade so he must have been like seven or so I went in his class with a whole bunch of robots and like the emotion ai demo and and I asked the kids I was like do you would you kids want to have a robot you know robot friend or robot companion? Everybody said yes and they wanted it for all sorts of things like to help them with their math homework and to like be a friend. So there's, it just struck me how there was no fear of robots was a lot of adults have that like us versus them. </s>

<s>[INST] 11 million. Argue for the natural origin. And there's a few recent papers that come out arguing this. It's kind of fascinating to watch this whole thing. But I think what they're arguing is that there's this Hunan market that's one of the major markets, the wet markets in Wuhan that there's a bunch of cases that were reported from there. So if I look at, for example, the Michael Warby perspective that he wrote in Science, he argues, he wrote this a few days ago, the predominance of early COVID cases linked to Hunan market and this can't be dismissed as a certaintment bias, which I think is what people argue that you're just kind of focusing on this region because a lot of cases came but there could be a huge number of other cases. So people who argue against this say that this is a later stage already. So he says no. He says this is the epicenter and this is a clear evidence, that circumstantial evidence, but evidence nevertheless that this is where the jump happened to humans, the big explosion. Maybe not K-0, I don't know if he argues that, but with the early cases. So what do you make of this whole idea? [/INST] Can you steel man it before we talk about the outside? Before we talk about the outside. And my goal here isn't to attack people on the other side. And my feeling is if there is evidence that's presented that should change my view, I hope that I'll be open-minded enough to change my view. And certainly Michael Warby is a thoughtful person, a respected scientist and I think this work is contributive work, but I just don't think that it's as significant as has been reported in the press. And so what his argument is, is that there's an early cluster in December of 2019 around the Huanan Seafood Market. And even though he himself argues that the original breakthrough case, the original case, the index case where the first person infected happened earlier, happened in October or November. So not in December. His argument is, well, what are the odds that you would have this cluster of cases in the Huanan Seafood Market? And if the origin had happened someplace else, wouldn't you expect other clusters? And it's not an entirely implausible argument, but there are reasons why I think that this is not nearly as determinative as has been reported. And I certainly had a lot of, I and others had tweeted a lot about this. And that is first, the people who were infected in this cluster, it's not the earliest known virus of the SARS-CoV-2, it began mutating. So this is, it's not the original SARS-CoV-2 there. So it had to have happened someplace else. Two, the people who were infected in the market weren't infected in the part of the market where they had these kinds of animals that are considered to be candidates as an intermediary species. And third, there was a bias, actually, I'll have four things. Third, there was a bias in the early assessment in China of what they were looking for. They were asked, did you have exposure to the market? Because I think in the early days when people were figuring things out, that was one of the questions that was asked. And fourth, and probably most significantly, we have so little information about those early cases in China. And that's really unfortunate. I know we'll talk about this later because the Chinese government is preventing access to all of that information, which they have, which could easily help us get to the bottom, at least know a ton more about how this pandemic started. And so this is, it's like grasping at straws </s><s>[INST] in the dark with gloves on. That's right. But to steel man the argument, we have this evidence from this market. And yes, the Chinese government has turned off the lights essentially. So we have very little data to work with, but this is the data we have. So who's to say that this data doesn't represent a much bigger data set that a lot of people got infected at this market where it's even at the parts or especially at the parts where the meat, [/INST] the infected meat was being sold. So that could be true. And it probably is true. The question is, is this the source? Is this the place where this began? Or was this just a place where it was amplified? And I certainly think that it's extremely likely that the Huanan Seafood Market was a point of amplification. </s><s>[INST] And it's just answering a different question. Basically what you're saying is it's very difficult to use the market as evidence for anything because it's probably not even the starting point. [/INST] So it's just a good place for it to continue spreading. That's certainly my view. What Michael Waraby's argument is, is that, well, what are the odds of that? That we're seeing this amplification in the market. And let me put it this way. If we had all of the information, if the Chinese government hadn't blocked access to all of this, because there's blood bank information, there's all sorts of information. And based on a full and complete understanding, we came to believe that all of the early cases were at this market. I think that would be a stronger argument than what this is so far. But everything leads to the fact that, why is it that the Chinese government, which was frankly after a slow start, the gold standard of doing viral tracking for SARS-1, why have they apparently done so little and shared so little? </s>

<s>[INST] So, uh, so who's in the sidecar in that picture of the future? Exactly. The [/INST] baby version of our immortal selves. </s><s>[INST] Okay, so once the baby grows up, is there any use for humans? [/INST] I think so. I think that out of out of epistemological bility, we need to keep humans around for a long time and I would hope that anyone making those systems would believe that to be true. </s><s>[INST] Out of epistemological humility. What's the nature of the humility that that [/INST] we don't know what we don't know? </s><s>[INST] So we don't Right. [/INST] First, I mean, first we have to build systems that that help us do the things that we do know about that can then probe the unknowns that we know about. But the unknown unknowns, we don't know. We could always know nature is the one thing that is infinitely able to surprise us. So we should keep biological humans around for a very, very, very long time. Even after our immortal selves have transcended and have gone off to explore other worlds, gone to go communicate with the life forms living in the sun or whatever else. So, um, you know, I think that's that's for me, these are these seem like things that are going to happen. Like I don't really question that that they're gonna happen, assuming we don't completely, you know, destroy ourselves. </s><s>[INST] Is it possible to create an ai system that you fall in love with and it falls in love with you and you have a romantic relationship with it or a deep friendship let's say, [/INST] I would hope that that is the design criteria for any of these systems. If we cannot have a meaningful relationship with it, then it's still just a chunk of silicon. So </s><s>[INST] then what is meaningful because back to sugar? [/INST] Well sugar doesn't love you back, Right, so the computer has to love you back and what does love mean? Well in this context for me love, I'm going to take a page from lng bhutan. Love means that it wants to help us become the best version of ourselves. Yes. Um that's </s><s>[INST] that's beautiful. That's a beautiful definition of love. So what what role does love play in the human condition at the individual level and at the group level. Because you're kind of saying that humans, we should really consider humans both at the individual and the group and the societal level. What's the role of love in this whole thing? We talked about sex, we talked about death thanks to the bacteria, they invented it at which point did we invent love by the way? I mean is that is that also [/INST] No, I think I think love is the start of it all and the feelings of and this gets is sort of beyond just you know, romantic, sensual, whatever kind of things. But actually genuine love as we have for another person, love as it would be used in a religious text, right? I think that capacity feel love more than consciousness, that is the universal thing are feeling of love is actually a sense of that generative itty when we can look at another person and see that they can be something more than than they are and more than just what we, you know, a pigeon hole, we might stick them in. We see, I mean, I think there's in any religious text you'll find um voiced some concept of this that you should see the grace of God and the other person, right? That they're they're made in the spirit of of what you know that the love that God feels for his creation or her creation. And so I think this thing is actually the root of it. So I would say before, I don't think, I don't think molecules of water feel consciousness have consciousness, but there is some proto micro quantum thing of love, that's the generative itty um when there's more energy than what they need to maintain equilibrium and that when you sum it all up is something that leads to, I mean I had my mind blown one day as an undergrad at the physics computer lab, I logged in and you know when you log in a bash for a long time, there was a little fortune that would come out and it said man was created by water to carry itself uphill and I was logging in to work on some you know problems that and I logged in and I saw that and I just said son of a bit, you know, I just I logged out and went to the coffee shop and I got a coffee and I sat there on the quad and like you know, it's not wrong and yet wtf right. Um so when you look at it that way it's like yeah, okay, non equilibrium physics is a thing. Um And so when we think about love and we think about these kinds of things, I would say that in the modern day human condition there's a lot of talk about freedom and individual liberty and rights and all these things, but that's and that's very Hegelian, that's very kind of following from the western philosophy of of the the individual as sacrosanct, but it's not really couched, I think the right way because it should be how do we maximize people's ability to love each other, to love themselves first, to love each other, their responsibilities to the previous generation, to the future generations and those are the kinds of things. That should be our design criteria right. Those should be what we start with to then come up with the philosophies of self and of rights and responsibilities. Um but that that love being at the center of it, I think when we design systems for cognition um it should absolutely be built that way. I think if we simply focus on efficiency and productivity, these kind of very industrial era um you know, all the things that Marx had issues with right? Those that's that's a way to go and and really I think go off the deep end in the wrong way. </s>

<s>[INST] So what do you think about another touchy subject? But what do you think about the politicization of science on topics like global warming, embryonic stem cell research and other topics like it? What's your sense? Why, [/INST] what do you mean by the politicization of global warming </s><s>[INST] meaning that if you say, I think what you just said, which is global warming as a serious concerns human cause there may be some detrimental effects. Currently there is a large percent of the population of the United States that would as opposed to listening to that statement, would immediately think, oh, that's just a liberal talking point, that's what I mean. [/INST] That's not so true anymore. I don't think our problem is a population that's skeptical about climate change because I think that the extreme weather, fire events that we are experiencing with such frequency, it's really gotten to people, I think they're, I think that there are people in leadership positions who choose to ignore it and to pretend it's not there. But ultimately, I think they will be rejected. The question is, will it be fast enough? Uh, but you know this, I don't, I think actually that most people have really finally taken the reality of global climate change to heart and they look at their Children and grandchildren and they don't feel good because they come from a world which was in many ways in terms of climate fairly familiar and benign and they know that we're headed in another direction and it's not just that, it's what we do to the oceans, the rivers, the air, you know, I mean, you asked me like, what is, what is the message of cosmos? Is that is that we have to think in longer terms, you know, I think of the soviet union, the United States and the Cold War and they're ready to kill each other over these two different views of the distribution of resources. But neither of them has a form of human social organization that thinks in terms of 100 years, let alone 1000 years, which are the time scales that science speaks in. And that's part of the problem is that we have to get a grip on reality and where we're headed. Yeah, and it's, I'm not fatalistic at all, but I do feel like, you know, and in setting out to To do this series, each season we were talking about climate change in the original cosmos in episode four And warning about inadvertent climate modification in 1980, you know. And of course, Carl did his PhD thesis on the greenhouse effect on Venus. And he was painfully cognizant of what a runaway greenhouse effect would do to our planet. And not only that, but the climatic history of the planet, which we go into in great detail in the series. So yeah, I mean, how are we going to get a grip on this, if not through some kind of understanding of science. Um, can I just say one more thing about science is that its powers of prophecy, Our astonishing, you Launches spacecraft in 1977 and you know where each and every planet in the solar system is going to be in every moon and you run with that flawlessly and you exceed the design specifications of the greatest dreams of the engineers and then you go on to explore the Milky Way Galaxy and you do it. I mean, you know, the climate scientists, some of the people that we whose stories we tell in cosmos, they their predictions were and they were working with very early computer modeling capabilities. They have proven to be so robust nuclear winter, all of these things, This is a prophetic power. And yet, how crazy that, you know, it's like, it's like the romans with their lead cooking pots and their lead pipes or the Aztecs ripping out their own people's hearts. This is us, We know better. And yet we are acting as if it's business as usual. </s><s>[INST] Yeah, the beautiful complexity of human nature is uh speaking of which, let me ask uh tough question I guess because there's so many possible answers. But what aspect of life here on earth do you find most fascinating from the origin of life? The evolutionary process itself, the origin of the human mind. So intelligence. The some of the technological developments going on now or us venturing out into space or space exploration. What just inspires [/INST] you, You inspire me, everyone does inspire me. But I have to say that to me at the origin of as I've gotten older to me, the origin of life has become less interesting </s><s>[INST] because [/INST] I feel, well not because it's more I think I understand I have a better grasp of how it might have </s><s>[INST] happened. Do you think it was a huge leap? So, I think [/INST] it was we are a byproduct of geophysics and I think it's not I my suspicion of course, which is take it with a grain of song. But my suspicion is that it happens more often in more places than we like to think. Because, you know, after all the history of our thinking about ourselves, it's been a constant series of demotions in which we've had to realize. No, no. So to me </s><s>[INST] that's the origin [/INST] of consciousness is to me also not so amazing if you think of it as, you know, going back to these one celled organisms of a billion years ago, who had had to know, well, if I go higher up, I'll get too much sun and if I go lower down, I'll be protected from, you know, UV rays, things like that. They had to know that or you I eat me, I don't I mean, even that I can see if you know that then knowing what we know now, it's just it's not so hard to fathom. It seems like, you know, there's I never believed there was a duality between our minds and our bodies and I think </s>

<s>[INST] So that's really interesting. So, you've, you've talked about agency, I think maybe calling it a convenient fiction at all these different levels. So even at the human individual level, it's kind of a fiction. We all believe because we are like you said, made of cells and cells are made of atoms. So that's a useful fiction. And then there's nations that seems to be a useful fiction, but it seems like some fictions are better than others. You know, there's a lot of people that argue the fiction of of nation is a bad idea. One of them lives two doors down from me michael malice. He's an anarchist. You know, I'm sure there's a lot of people who are into meditation that believe the idea this useful fiction of agency of an individual is troublesome as well. We need to let go of that in order to truly like to transcend. I don't know, I don't know what, what words you want to use, but suffering or to, uh, to elevate the experience of life. So you're kind of arguing that, okay, so we have some of these useful fictions of agency. We should add a stronger fiction that we tell ourselves about. The agency of groups in the hundreds of the half of Dunbar's number five X. Dunbar's number [/INST] Yes. Something on that order. And we call them fictions. But really the rules of the game, right? Rules that we we, we feel are fair, our rules that we consent to. </s><s>[INST] I always question the rules when I lose like a monopoly. That's when I usually question when I'm winning. I don't question the rules. [/INST] We should play a game monopoly someday. There's a trippy version of it that we could do </s><s>[INST] what, what kind of [/INST] contract monopoly is introduced by a friend of mine. To me where you can write contracts on future earnings or landing on various things and you can hand out like, you know, you can land the first three times you land on park, place is free or whatever just, and then you can start trading those contracts for money </s><s>[INST] and then you create human civilization. Uh, and somehow, Bitcoin comes into it. Okay. Uh, but some of these [/INST] actually, I bet if me and you, and ERIC sat down to play a game of monopoly and we were to make N. F. T. S Out of the contracts we wrote we could make a lot of money. Now it's a terrible idea. I would never do it. But I bet we could actually sell the N. F. T. S around. </s><s>[INST] I have other ideas to make money that I could tell you. And they're all terrible ideas um including cat videos on the internet. Okay. But some of these rules of the game, some of these fictions are it seems like there better than others. [/INST] They have worked this far to cohere human to organize human collective action. </s><s>[INST] But you're saying something about especially this technological age requires modified fictions. Stories of agency. Why the Dunbar number. And also, you know, how do you select the group of people? You know, Dunbar numbers. I think I have the sense that it's overused as a kind of law that somehow we can have deep human connection at this scale. Like some of it it feels like an interface problem too. It feels like if I have the right tools, I can deeply connect with a large number of larger number of people. It just feels like there's a huge value to interacting just in person getting to share traumatic experiences together. Beautiful experiences together. But there's other experiences like um that in the digital space that you can share. It just feels like Dunbar's number can be expanded significantly. Perhaps not to to the level of millions and billions but it feels like it could be expended. So how do we find the right interface you think? Um for having a little bit of a collective here that has agency, [/INST] you're right that there's many different ways that we can build trust with each other. Um my friend joe Edelman talks about a few different ways that um you know, mutual appreciation, trustful conflict, um just experiencing something like, you know, there's a variety of different things that we can do, but all those things take time and you have to be present, the less present you are. I mean there's just again a no free lunch principle here, the less present you are, the more than you can do, but then the less the last connection you built. So I think there is sort of a human capacity issue around some of these things now that being said yes, we can use certain technologies. So for instance if I write a little monograph on my view of the world, you read it a synchronously at some point and you're like wow, peter, this is great. Here's mine. I read it, I'm like wow lex, this is awesome. We can be friends without having to spend 10 years, you know figuring this stuff out together. We just read each other's thing and be like, oh yeah, this guy is exactly in my wheelhouse and vice versa and we can then um you know, connect just a few times a year and maintain a high trust relationship. It can expand a little bit but it also requires these things are not all technological nature requires the individual themselves to have a certain level of capacity To have a certain lack of neuroticism, right? If you want to use like the the ocean big five sort of model people have been pretty centered, the less centered you are the fewer authentic connections you can really build for a particular unit of time. It just takes more time. Other people have to put up with your crap. Like there's a lot of the stuff that you have to deal with if you are not so well balanced. Right? So yes we can help people get better to where they can develop more relationships faster and then you can maybe expand Dunbar number by quite a bit but you're not going to do it. I think it's really hard to get it beyond 10 X. Kind of the rough swag of what it is, you know. </s>

<s>[INST] So what does it take to uh simulate contact? I mean it just seems uh I mean there's something just beautiful the way you were like explaining contact and you were like tapping your fingers on the on the table while you're while you're doing it. Just um [/INST] easily, </s><s>[INST] easily just like just not even like it was like helping you think I guess um what I um do you have this like awesome demo of um loading or unloading a dishwasher? Just picking up a plate, grasping it like for the first time? Um That's just seems like so difficult. What how do you simulate any of that? [/INST] So so it was really interesting that what happened was that um we started getting more professional about our software development during the DARPA robotics challenge. I I learned the value of software engineering and how these how to bridle complexity I guess that's that's what I want to somehow fight against and bring some of the clear thinking of controls into these complex systems we're building for robots. Um, shortly after the DARPA robotics challenge, Toyota opened a research institute, T. TR I. Toyota Research Institute. Um they put one of their, there's there's three locations. One of them is just down the street from M. I. T. And uh and I helped ramp that up, right. As a part of my the end of my sabbatical I guess. Um So T. R. I. Is uh has given me the TR I robotics effort has made this investment in simulation and drake. And Michael Sherman leads a team there of just absolutely top notch dynamics experts that are trying to write those simulators that can pick up the dishes. And there's also a team working on manipulation there that is taking problems like loading the dishwasher and we're using that to study these really hard corner cases kind of problems in manipulation. So for me this um simulating the dishes and we could actually write a controller if we just cared about picking up dishes in the sink, once we could write a controller without any stimulation whatsoever. And we could call it done, but we want to understand like what is the path you take to actually get to a robot that could perform that for any dish in anybody's kitchen with with enough confidence that it could be a commercial product, right? And it has deep learning perception in the loop. It has complex dynamics in the loop. it has controller, it has a planner. And how do you take all of that complexity and put it through this engineering discipline and verification and validation process to actually get enough confidence to deploy. I mean the DARPA challenge made me realize that that's not something you throw over the fence and hope that somebody will harden it for you. That they're really fundamental challenges in uh enclosing that last gap </s><s>[INST] there during the validation and the testing. [/INST] I think it might even change the way we have to think about the way we write systems. Um what happens if you, if you have the robot running lots of tests, it screws up, it breaks a dish. Right? How do you capture that? I said you can't run the same simulation are the same experiment twice in in a real on a real robot. Do we have to be able to bring that one off failure back into simulation in order to change our controllers, study it, make sure it won't happen again, do we? Is it enough to just try to add that to our distribution and understand that? On average, we're going to cover that situation. Again, there's like really subtle questions at the corner cases that I think we don't yet have satisfying answers for </s><s>[INST] like how do you find the corner cases? That's one kind of is there? Do you think it's possible to create a systematized way of discovering corner cases efficiently. Yeah. And whatever the problem is. [/INST] Yes. I mean, I think we have to get better at that. I mean, control theory has um for for decades talked about active experiment design uh so people call it curiosity these days, it's roughly this idea of trying to exploration or exploitation, but but in the active experiment design is even, is more specific. You could try to um understand the uncertainty in your system design. The experiment that will provide the maximum information to reduce that uncertainty. If there's a parameter you want to learn about what is the optimal trajectory I could execute to learn about that parameter for instance, um scaling that up to something that has a deep network in the loop and planning in the loop, it's tough. We've done some work on, you know, with model kelly and Mancina, we've worked on some falsification algorithms that are trying to do rare event simulation that try to just hammer on your simulator. And if your simulator is good enough, you can um, you can spend a lot of time, you can write good algorithms that try to spend most of their time in the corner cases. So you basically imagine you're, you're building uh autonomous car and you want to put it in downtown new Delhi all the time. Right? An accelerated testing. If you can write sampling strategies which figure out where your controller is performing badly in simulation and start generating lots of examples around that, you know, it's just the space of possible places where that can be where things can go wrong is very big. So it's hard to write those algorithms. </s><s>[INST] Rare event simulation is just a really compelling notion. Uh, If it's possible, [/INST] we joke and we call it, we call it the black swan generator black swan because you don't just want the rare events, you want the ones that are highly impactful. </s>

<s>[INST] So put some flesh on the, yeah. Basically, there's a good book I'm reading because I think a lot of documents became public recently. And so- [/INST] There's a window when it opened up. </s><s>[INST] Now it's probably closing back down again, but- But you know, great biographies because of that were written like I'm currently reading Mao's Great Famine [/INST] by Frank de Carter, which is a hoo boy. Yeah, it's crazy, okay? Here's the thing is, capitalism was punishable by death in living memory in China. Just to explain what that meant, okay? I mean, that's what communism was, right? It was literally the same China that has like the CC, you know, the entrepreneurs and Jack Ma and so on and so forth. 40 something years ago, capitalism was punishable by death. But to put, to give you a concrete example, this is a famous story in China, maybe apocryphal, but it's what, you know, the folks have talked about. There's a village in Xiaogang and basically all the grain that you were produced was supposed to go to the collective. And even one straw belonged to the group. At one meeting with communist party officials, a farmer asked, what about the teeth in my head? Do I own those? Answer, no, your teeth belong to the collective, okay? Now, the thing is that when you're taking 100% of everything, okay, work hard, don't work hard, everyone gets the same so people don't want to work, right? So what happened? These farmers gathered in secret and they did something that was like, would have gotten them executed. They were a contract amongst themselves and said, we all agree that we will be able to keep some of our own grain. We will give some of them to the regime so when it comes to collect grain, they've got something. We'll be able to keep some of it. And if any of us are killed for doing this, then the contract said that the others would take care of their children, okay? To keep some of what you earned, </s><s>[INST] I mean, just think about how it's- They formed a mini capitalism society [/INST] within a secret capitalism society amongst five people. Right, so now that they could keep some of what they earned, right, schemes were earned, they had a bumper harvest. And you know what happened with that bumper harvest? That made the local officials really suspicious and mad. They weren't happy that there was a bumper harvest. They're like, what are you doing? You're doing capitalism, right? And in a few years earlier, they might've just been executed. And in fact, many were. That's what it means when you see millions dead. Millions dead means guys were shot for keeping some grain for themselves, okay? It means like guys came and kicked in the door of your collective farm and raped your wife and took you off to a prison camp and so on and so forth. That's what communism actually was, okay? It hasn't been depicted in movies. There's a great post by Ken Billingsley in the year 2000 called, if I get this right, Hollywood's Missing Movies, okay? This is basically here, I'll paste this link so you can put it in the show notes, all right? This is worth reading. It's still applicable today, but now that we have stable diffusion, now we have all these people online, now that Russia and China are America's national bad guys, as they were before, they are again, perhaps we'll get some movies on what communism actually was during the 20th century and how bad it was, right? And vaccinate people against that as well as against Nazism, which they should be, okay? </s><s>[INST] The point of this, go ahead. No, because I'm congratulating myself on the nice because you're sending me excellent links on WhatsApp and I just saw that there's an export chat feature. Yes, great. Because we also have disappearing messages on, so I was like, all right, this is great. Great. I'll be able to get it. Your ability to reference sources is incredible, so thank you for this. [/INST] Anyway. Yes. Otherwise, if I say something, it sounds too surprising, so that's why I want to make sure I have it on this topic. Yeah, so like, yeah, I mean, people would be like shot for holding some grain, so what happened though was Deng Xiaoping said, okay, we're not going to kill you. In fact, we're going to actually set up the first special economic zone in Shenzhen. He didn't try to flip the whole country from communist to capitalist in one go. Instead, he's like, we can reform in one place. And in fact, he fenced it off from the rest of China and it did trade with Hong Kong and he spent his political capital on this one exception. It grew so fast, they gave him more political capital. You know, some people think actually that the Sino-Vietnamese war was Deng's way of just distracting the generals while he was turning China around to get it back on the capitalist road. And what he did was the opposite of a rebranding. He did a reinterpretation. Like a rebranding is where the substance is the same, but the logo is changed, okay? You know, you were Facebook, you're now meta. That's a rebranding, right? Reinterpretation is where the logo and the branding is the same. They're still the CCP, they're still the Chinese Communist Party, but they're capitalist now, the engine under the hood. It's deniable, okay? And this is a very common, once you realize those are different things, </s>

<s>[INST] So, the thing is the idea of compression is one way to do compression is to describe through text what's containing the video, that's the ultimate level of compression. So the idea is traditionally when you think a video image compression, you're trying to maintain the same visual quality while reducing the size. But if you think of deep learning from a bigger perspective of what compression is is you're trying to summarize the video and the idea there is, if you have a big enough neural network just by watching the next, trying to predict the next frame, you'll be able to form a compression of actually understanding what's going on in the scene. If there's two people talking, you can just reduce that entire video into the fact that two people are talking and maybe the content of what they're saying and so on. That that's kind of the the open ended dream. So I just wanted to sort of express that is interesting, compelling notion. But uh it is nevertheless true that video our world is a lot more complicated than we get credit [/INST] for. I mean in terms of search and discovery, we have been working on trying to summarize videos in text or or with some kind of labels for eight years at least. And oh and we're kind of so, so, so </s><s>[INST] So if you were said, it's the problem is 100% solved And eight years ago was 0% solved. How where are we on that timeline would you say [/INST] to summarize a video? Well, uh maybe less than a quarter of the way. </s><s>[INST] So on that topic, what does YouTube look like 10 2030 years from now. [/INST] I mean I think that youtube is evolving to take the place of tv. Um you know, I grew up as a kid in the 70s and I watched a tremendous amount of television and uh, I feel sorry for my poor mom because people told her at the time that it was going to rot my brain and that she should kill her television. Um but anyway, I mean, I think that youtube is at least from my family, a better version of television, right? It's one that is on demand, it's uh more tailored to the things that my kids want to watch and also they can find things that um, they would never have found on television. And so I think that at least from just observing my own family, that's where we're headed is that people watch Youtube kind of in the same way that I watch television when I </s><s>[INST] was younger. So from a search and discovery perspective, what do you, what are you excited about and then 5, 10 2030 years, like what kind of things? It's already really good. I think it's achieved a lot of, of course we don't know what's possible. So it's uh, it's the task of search of typing in the text or discovering new videos by the next recommendation. I personally am really happy with the experience. I continuously, I rarely watch a video that's not awesome from my own perspective, but what's, what else is possible, What are you excited about? [/INST] Well, I think uh introducing people to more of what's available on youtube is um not only very important to Youtube and the creators, but I think it will help uh enrich people's lives because there's a lot that I'm still finding out is available on Youtube that I didn't even know. Um, I've been working Youtube eight years and it wasn't until last year that I learned that uh, that I could watch USC football games from the 19 seventies, like I didn't even know that was possible last year and I've been working here quite some time. So, you know, what was broken about, about that, that it took me seven years to learn that this stuff was already on Youtube, even when I got here. Um, so I think there's a big opportunity there and then, as I said before, uh, you know, we want to make sure that Youtube finds a way to ensure that it's acting responsibly with respect to society and enriching people's lives. So we want to take all of the great things that it does and make sure that we are eliminating the negative consequences that might happen. Um, and then lastly, if we could get to a point where all the videos people watch are the best ones they've ever watched that would be outstanding too. </s><s>[INST] Do you see in many senses becoming a window into the world for people, it's, especially with live video, you get to watch events. I mean, it's really, it's the way you experience a lot of the world that's out there is better than tv in many, many ways. So do you see becoming more than just video? Do you see creators creating visual experiences and virtual worlds? So if I'm talking crazy now, but sort of virtual reality and entering that space there is that at least for now, totally outside of what youtube is thinking about. [/INST] I mean I think google is thinking about virtual reality. Uh I don't think about virtual reality too much. Uh I know that we would want to make sure that youtube is there when virtual reality becomes something or if virtual reality becomes something that a lot of people are interested in. Um, but I haven't seen it really take off yet. </s><s>[INST] Take off. Well the future is wide open crystals. I've been really looking forward to. This conversation has been a huge honor. Thank you for answering some of the more difficult questions I've asked. I'm really excited about what uh Youtube has in store for us. It's one of the greatest products I've ever used and continues. So thank you so much for talking. [/INST] It's my pleasure. Thanks for asking me. </s>

<s>[INST] yeah, the picture, it doesn't quite make sense. You uh, you've done a study on cocaine and sexual decision making. Uh, can you explain, can you explain the findings? I mean, uh, in a broad sense, how do you do a study that involves cocaine and uh, the other, how do you do a study involving the sexual decision making and then how do you do a study that combines both. [/INST] Yes. Sex and drugs to, I'm just missing the rock and roll to controversial rock n roll isn't very controversially. Yeah. So the cocaine, you know, lots of hoops to jump through. You gotta have a lot of medical support. You got to be at a basically an institution, a research unit like I'm at that has a long history. Um and the ability to do that, um, uh and get ethics approval, Get FDA approval. But it's possible. And whenever you're dealing with something like cocaine, you would never want to give that to uh not someone who hasn't already used cocaine and you want to make sure you're not giving it to someone who is an active user who wants to quit. So the idea is like, okay if you're, if you're using this type of drug anyway and you're, we're really sure you're not looking to quit. Hey, you use a couple of times in the lab with us so we can at least learn something. Um And part of what we learn is maybe to help people not use and will reduce the harms of cocaine. So there's hoops to jump through with the sexual um decision making. I looked at, the main thing I looked at was this model of, I applied delayed discounting to what we talked about earlier than now versus later. That kind of decision making. That goes along with addiction. I applied that economies decisions. Um and I've done probably published about 20 or so papers with this in different drugs and and uh </s><s>[INST] so the primary metric is whether you do or don't use economy. That's [/INST] right hypothetic. And so this is using hypothetical decision making. But I've published some studies looking at um showing a tight correspondence to self reported um in correlation als studies to self reported behavior. </s><s>[INST] So this is like so like how do you did you do a questionnaire kind of thing? [/INST] Right. So it's a it's not quite a questionnaire but but it's a it's a it's a behavioral task requiring them to respond to. So you show pictures of a bunch of individuals and it's it's kind of like one of these fun behavior. Like a lot of them you get like the numbers of boring but it's like Okay hot or not like which of these 60 people would you have a one night stand with men women. So pick whatever you like a little bit of this, a little bit of that whatever you're into. It's all variety there out of that group. You pick some subsets of people who do you think is the you know one you most want to have sex with the least. He thinks most likely to have an S. T. I. Or at least likely a sexually transmitted disease by S. T. I. And then you could do certain decision making questions of what I've done is asked say this percy read a vignette, this person was have sex with you. Now you met them to get along um casual sex scenario like a one night stand, would it condoms available? Just raise your likelihood from 1 to 100 on this kind of scale. Would you use it? But then you can change your your scenario to say, okay now imagine you have to wait five minutes to use a condom. So the choice is now instead of using common versus not. In terms of your likelihood scale it now it ranges from um have sex without a condom versus on the other end of the scale is wait five minutes to have sex with a condom. So you rate your likelihood of where your behavior would be along that continuum. And then you can say, okay well what about an hour? What about three hours? What about what about 24 </s><s>[INST] misunderstanding? Uh Now without a condom or five minutes later with a condom isn't? Uh So what what's supposed to be the preference for the person? Like is like what there's a lot of factors coming into play right? There's a uh like there's like pleasure, personal preference. And then there's also the safety, those are too like are those competing objectives, [/INST] right? And so we do get at that through some individual measures. And and this task is more of a face valid task where there's a lot underneath the hood so for most people sex with the condom is the better reward but underneath the hood of that is just that the purely physical level they'd rather have sex with without the condom, it's going to feel. What do </s><s>[INST] you mean by a reward? Like when they calculate their trajectory through life and try to optimize it than sex with a condom is a good idea? [/INST] Well it's it's really based on I mean yeah yeah, presumably that's the case that that that that there's but it's measured by like what would really that first question where there is no delay, most people say they would be at the higher net scale a lot of times 100% they said they would definitely use </s><s>[INST] use a condom [/INST] condom, Not everybody and there we know that's the case, it's like that that some people don't like calm some people say yeah I want to use a condom but you know a quarter of the time ended up not because I just get lost in the passion of the moment. So for the people, I mean the only reason that people so behaviorally speaking at least for a large number of people in many circumstances condom use is a reinforce er just because people do it like you know why are they doing it? They're not because it makes the sex feel better but because it makes that it allows for at least the same general reward even actually even if it feels a little bit not as good you know with the condom nonetheless they get most of the benefit without the concurrent oh my gosh is this risk of either unwanted pregnancy or getting HIV or way more likely than HIV, you know herpes you know in general awards etcetera, all the all the lovely ones. Um And we've actually done research saying like where we gauge the probability of these individual different S. D. I. S. It's like what's the heavy hitter in terms of what people are using to judge in to evaluate what they're going to use a condom. </s>

<s>[INST] Why projections, is it? Uh I mean there's a meal instead of putting words into your mouth because I can imagine a lot, I mean to me. No, I will start putting words in your mouth despite what I just said. Uh So I mean to me, projections, working on your networks, for example, from artificial neural networks for machine learning perspective, it's often that's exactly what you're doing. You have an incredibly complex thing and you're trying to uh find simple representations in order for you to make sense of it. So, I was kind of thinking about in that way, which is like um this incredibly complex in your own own network that is kind of projecting itself onto the world through this low bandwidth expression of emotion and speech and all that kind of stuff. And the way it's we only have that window into your soul, the eyes and the speech and so on. And so that in that way where um when there's any kind of disorder, we get to only see that disorder through that narrow window as opposed to the full complexity of its origins. [/INST] The word projections definitely serves that purpose here, but it's it's got a few other really appropriate other connotations as well. So the first thing is a projection in terms of neuroscience is this long range connection that goes from one part of the brain to another. And so it's what binds to parts of our brain together. There are projections long range connections of axons. These are the outgoing threads that connect one part of the brain to another part. There's a there's a projection that links for example, auditory cortex where we hear things to reward centers where we can feel where feelings of pleasure and reward are initiated. And it's been shown that if you have reduced connectivity along that dimension, you are less able to enjoy music. And so these connections, these projections matter. They define how effectively two parts of the brain can engage with each other and join together to form a a joint representation of something. So that's one meaning, it's pure neuroscience. The word projection is used all the time and it happens to be something that optogenetics, a technique that we maybe we'll talk about a little later it works particularly well with we can use light to turn on or off the activity along these projections from one spot of the brain to another. </s><s>[INST] And this is particularly referring to the long range connections. [/INST] It's particularly straightforward along these long range projections that connect different parts of the brain but it works over shorter range too. But then there's this other meaning of projections which you were bringing up which is very relevant which is at some point you you can reduce something from one level of dimensionality to another and you can project down into a lower dimensional space for example. And then finally there's a psychiatric uh term projections which comes up all the time which is uh we very often will look at our internal states and to understand somebody else will project them onto somebody else will try to understand someone else's behavior and make sense of it by projecting our own inner feelings, our own uh sort of narrative onto them. And use that as a way to help us understand them better. And we'll do the reverse to, we'll take things we see in the outside world and we'll bring them into ourselves and see how well they map. How will they align that's called introduction. So projections as it turns out to be a really rich word. And finally, of course there's the very common sense of it as a projector that illuminates by conveying information across space with light. So for english for english language. Perfect word to use </s><s>[INST] for this book. But [/INST] it was funny is not every, there are a lot of international translations now and all those rich connotations aren't captured in other languages. And so for some translations, connections is used instead of projections. In fact, even in England, the british version has connections instead of projections because apparently projections doesn't have the full connotation. I was told </s><s>[INST] you have to sacrifice some of the rich um ambiguity of meaning with connections. That's interesting. I mean, can I and words are so interesting. They have so many me. I love language and how much is lost in translation. I'm very fortunate enough to be able to speak. I'm not good at languages. I was just, I guess forced to buy life circumstance to learn two languages Russian and english. And it's just so interesting to watch how much of culture, how much of people, how much of history is lost in translation, the poetry, the music, the history of the pain and the way the scientists actually express themselves, which is funny, I mean, just it's so sad. Um to see how much brilliant work that was written in Russian, there's a whole culture of science in the soviet union is not lost. It makes me wonder in the modern day how much incredible science is going on in china that is lost in translation. And I will never, I mean that makes me very sad because I'll never learn chinese in the same way that I've learned english and Russian, maybe whenever I say stuff like that, people are like, well there's still time, but uh you know, uh yeah, that's that's that's actually fair, that uh I think the 21st century, both china and us will have very important roles in the scientific development. Uh and we should actually bridge the gap through language. And that, that doesn't just mean convincing chinese to speak english, that means also learning chinese. [/INST] Well, we need these bridge people who can do both. You know, the um you know, Nabokov for example, writing in english beautifully. Uh you know, one of my favorite poets Borges who, you know, mentioned earlier, he wrote both in english and in spanish, I think, you know beautifully in both. We need those people who can serve as bridges across cultures who really can do both. </s>

<s>[INST] So the, the challenge of course is all kinds of, you said institutional cover. There's all kinds of institutions that cover for people that don't, that do evil onto the world to do sinful things in the world. But there's something about the Church which is, um, the as an organism is supposed to be an embodiment of good in this world of love in this world. And it breaks people's hearts to see this kind of, even a small amount, uh, this kind of thing happen within the church. It wakes you up to the cruelty of the absurdity of the world sometimes. Like it's it's it's back to the the question of why do bad things happen to good people, why does God allow this kind of thing to happen? And sort of maybe an unanswerable question, do you have an answer to that question? [/INST] I can gesture toward it using rather of strike language, which is true enough, it's completely emotionally unsatisfying, but its naming it truthfully enough. And it goes back to Augustine, which is God permits evil to bring about a greater good. Now again, I know how unsatisfying, that sort of spare, austere language can sound, but it gets us off the horn of the horns of a dilemma, you know, acquaint is, you know, when he lays out a question, he always has the objections first. So is there a God? Well, objection one objection two objection three. And he's really talking about steel manning and argument acquaintances. Great at that. Um, one of the really steel manned arguments is that the right grammatical form </s><s>[INST] of one [/INST] of the, what's the past participle about the steel man? Um, but one of the best arguments, he formulates it this way. Um, if one of two contrary is be infinite, the other would be altogether destroyed. And his example from his medieval physics, he goes, if there were an infinite heat, there'd be no cold, right? But God has described as infinitely good, therefore God exists, there should be no evil, but there is evil, therefore God does not exist. That's a darn good argument. That's a really persuasive argument. And I think I've done this for a long time and apologetics and then sort of higher philosophy, that's the best argument against God. Um, but here's something before I press ahead with it, something I find really interesting. I think the three best arguments against God all come from within the religious tradition, namely the book of Job. So Job, he's great. I mean, he's a great guy, he does everything right. He's he's God's great servant and he and he's punished in every possible way, You know, he has every possible suffering. Aquinas argument from the suma. And then to your friend and mine dostoyevsky, I think in the brothers Karamazov, Yvonne's argument when he's trying to wreck the faith of Alyosha. And it's um these examples drawn they think from from the headlines of his own time, of the most abject cruelty to Children, like an innocent child being made to suffer. How in God's name could that happen if God exists? And he's all good. So I get it. But see the book of job thomas, the coin is dusty. These are all profoundly believing people. Like when I hear um Stephen fry, you know, the famously atheist writer, he he will bring out this argument with great authority. He does of, you know, Children with bone cancer and worms that go into the eyes of Children and blind them before they kill them. And but he's been preceded by the author of job thomas Aquinas and dostoyevsky, who who stood right think of job in, in the whirlwind, he stands there in the, in the whirlwind, you know, so you can't blame the christian tradition for not dealing with this problem, you know, for like brushing under the carpet. I mean, it is, it has stood in the whirlwind of this problem. </s><s>[INST] It's still a difficult problem to deal with, that. There's all this cruelty of the world. It's there's a lot of examples through history, just in my own family history with the soviet union with Stalin, Yes, The atrocities that Stalin has brought onto its the people of the Soviet Union throughout the 20th centuries and nearly measurable and yet When you look at the entirety of human history, you will see progress, not just the Soviet Union, but the entirety of the civilization throughout the 20th century. And Stalin has a role to play. There's a there's a dark aspect to somehow evil helps us make progress. And I don't know how to put that in the calculation, it's, I don't, you know, on a local scale, I want to alleviate suffering. I'm probably lean heavily, lean pacifist, not out of weakness, but out of strength, but man, it does seem that history Sprinkle with evil and that evil does somehow not just towards good. [/INST] Yes, sometimes we can see it and that's where the that's where the idea comes from, that evil is permitted to bring about some greater good and we can sometimes really see it. Um can we always see it? No. In fact, typically we don't see it, but now you bring another factor into this, which is the difference between our minds and God's mind. So our minds, I mean, look, even they're remarkably capacious, but they take in a tiny, tiny tiny swath of of space and time and even like our eyes kind of taken so much of the light spectrum and these little, these little ape sensory um that we have that can just take in a little tiny bit of reality, really? How are we ever in a position to say, oh no, there's no possible good that would ever come from that, even the greatest evil that, you know, every dostoyevsky and and can conjure up and Stephen fry still, how could we have the arrogance to say? I know there's no good that could ever come from that? I know there's no morally justifiable reason why God would ever permit that, because I think that's hubris to the ends degree for us to say that. And that's the the assumption behind this claim that God can permit evil to bring about a greater good. Now God understands it. But we're like, we're like little kids, you know, like a four year old and their parents make a decision. And we said, what, why in the world would you do this to me? Um this is my pastoral experience. Years ago there was a young father and his son was like three or something and he was in the hospital for something, I forgot what it was, but he had to undergo surgery, right? So after the surgery, he's in great pain, this poor kid, this three year old kid and the dad was there with him, you know, holding his hand and you know, and the sun, this is what the father told me, he said, he's looking at me like, what gives here, I mean, why would you, you love me? I've always assumed that and yet you're presiding over this somehow, you're approving of this and doing nothing to get me out of it, right? And he said, a kid couldn't articulate that, but his eyes did and his I and the father said it was just killing me because I knew I couldn't explain it to him. And it's true, I mean, you could vaguely gesture toward, but the kids don't understand surgery and cutting his body and taking things out of it and that this was going to, you know, make him much better in the long run. But I remember thinking that's a great metaphor for us, vis a vis God is, here's God infinitely loving God who is with us all the time. And we say, what are you doing? Why aren't you taking this away from me? And the answer ultimately is, trust, trust me, trust me, surrender to me </s>

<s>[INST] two different perspectives and the same physical reality. [/INST] Exactly. And it's just as you say, um you know, I knew that six times eight was the same as eight times six, right? I knew my times tables. Like I knew that that was a fact, but did I really know it until that moment. That's the question, right? I knew that I sort of knew that the times table was symmetric, but I didn't know why that was the case until that moment. And in that moment I could see like, oh, I didn't have to have somebody tell me that that's information that you can just directly access. That's a really amazing moment and as math teachers, that's something that we're really trying to bring to our students. And I was one of those who did not love the kind of Euclidean geometry, ninth grade class of like prove that isosceles triangle has equal angles at the base, like this kind of thing. It didn't vibe with me the way that algebra numbers did. Um but if you go back to that moment from my adult perspective, looking back at what happened with that rectangle, I think that is a very geometric moment. In fact, that moment exactly encapsulates the intertwining of algebra and geometry. This algebraic fact that, well, in the instance eight times six is equal to six times eight. But in general that whatever two numbers you have, you multiply them one way and it's the same as if you multiply them in the other order. Um it attaches it to this geometric fact about a rectangle, which in some sense makes it true. So, you know, who knows? Maybe I was always fated to be an algebraic geometry, which is what I am as a as a researcher. </s><s>[INST] So that's a kind of transformation. And you talk about symmetry in your book. What the heck is symmetry? What the heck is these kinds of transformation on the objects that once you transform them, they seem to be similar. What do you make of it? What's its use in mathematics or maybe broadly and understanding our world. [/INST] Well, it's an absolutely fundamental concept and it starts with the words symmetry in the way that we usually use it when we're just like talking english and not talking mathematics, right, sort of something is when we say something is symmetrical, we usually means it has what's called an axis of symmetry. Maybe like the left half of it looks the same as the right half. That would be like a left, right axis of symmetry. Or maybe the top half looks like the bottom half or both. Right. Maybe there's sort of a fourfold symmetry where the top looks like the bottom of the left looks like the right um or more and that can take you in a lot of different directions. The abstract study of what the possible combinations of symmetries. There are a subject which is called group theory was actually um one of my first loves mathematics when I thought about a lot when I was in college. But the notion of symmetry is actually much more general than the things that we would call symmetry. If we were looking at like a classical building or a painting or or something like that. Um you know, nowadays in math, um we could use a symmetry to refer to any kind of transformation of an image or a space or an object. Um you know, so when I talk about in the book is um take a figure and stretch it vertically, make it twice as make it twice as big vertically and make it half as wide. Um that I would call a symmetry. It's not a symmetry in the classical sense, but it's a well defined transformation that has an input and an output. I give you some shape. Um and it gets kind of I call this in the book of scrunch, I just had to make up some sort of funny sounding name for it. It doesn't really have um a name. Um And just as you can sort of study which kinds of objects are symmetrical under the operations of switching left and right or switching top and bottom or rotating 40° or what have you. Um You could study what kinds of things are preserved by this kind of scrunch symmetry and this kind of mhm. More general idea of what a symmetry can be. Um Let me put it this way. Um a fundamental mathematical idea in some sense, I might even say the idea that dominates contemporary mathematics or by contemporary, by the way, I mean like the last like 150 years, we're in a very long time scale in math. I don't mean like yesterday, I mean like a century or so up till now is this idea that the fundamental question of when do we consider two things to be the same? That might seem like a complete triviality. It's not, for instance if I have a triangle and I have a triangle of the exact same dimensions, but it's over here um are those the same or different? Well you might say like well look there's two different things. This one over here, this is over there. On the other hand, if you prove a theorem about this one, it's probably still true about this one. If it has like all the same side lines and angles and looks exactly the same the term of art if you want it, you would say they're congruent. But one way of saying it is there's a symmetry called translation which just means move everything three inches to the left. And we want all of our theories to be translation and variant. What that means is that if you prove a theory about a thing that's over here and then you move it three inches to the left. It would be kind of weird if all of your theorems like didn't still work. So this question of like what are the symmetries and which things that you want to study urine variant under those symmetries is absolutely fundamental. Boy, this is getting a little abstract, </s>

<s>[INST] Once again get it at Express VPN dot com slash likes pod to get a discount and to support this podcast. And now here's my conversation with Stephen Schwarzman. Let's start with a tough question, what idea do you believe? Whether grounded and data or an intuition that many people you respect, disagree with you on. [/INST] Well there isn't all that much anymore since the world so transparent, but uh one of the things I I believe in uh put it in the, the book, what it takes is is if you're gonna do something, do something very consequential, do something that's quite large. Uh if you can, that's unique because if you operate in that kind of space when you're successful, it's it's a huge impact. The prospect of success enables you to recruit people who want to be part of that. And those type of large opportunities are pretty easily described. Uh and and so not everybody likes to operate at scale. Some people like to do small things because it is meaningful for them emotionally. And so occasionally you get a disagreement on that, but those are life choices uh rather than commercial choices. </s><s>[INST] That's interesting. What good and bad comes with going big. So we often, in America think big is good, what's the benefit? What's the cost in terms of just bigger than business, but life happiness, the pursuit of happiness? [/INST] Well, you do things that make you happy. It's, it's not mandated. Uh and everybody is different. Uh and um, some people, um you know, if they have talent, like playing pro football, uh you know, other people just like throwing the ball around, uh, you know, not even being on a team, what's better, depends what your objectives are, depends what your talent is. Uh you know, it depends, um, you know, what, what gives you joy. </s><s>[INST] So in terms of going big is it both for impact on the world and because you personally gives you joy? [/INST] Well, it makes it easier to succeed actually, because if you catch something for example, that's cyclical, That's huge opportunity, then then you usually can find someplace within that huge opportunity where you can make it work if you're prosecuting really small thing and you're wrong, you don't have many places to go. Uh So, you know, I've always found that the easy place to be. Uh and you know, um the ability where you can concentrate uh human resources, get people excited about doing like really impactful big things. Uh and you can afford to pay them actually because the bigger thing can generate much more in the way of of financial resources. So that brings people out of talent to help you. Uh and and so all together it's a virtuous circle, I think. </s><s>[INST] How do you know an opportunity when you see one in terms of the one you want to go big on? Is that intuition, is it facts? Is it uh back and forth, deliberation with people you trust? What's the process? Is it art? Is it science? [/INST] Well, it's pattern recognition. And how do you get to pattern recognition first? You need to understand the patterns and and the changes that are happening. And and that's uh that's either uh it's observational on some level. You can call it data or you can just call it listening to unusual things that people are saying that they haven't said before. And you know, I've always um tried to describe this. It's like seeing a piece of white linen on a, on a black dress, but most people disregard that piece of lint, they just see the dress, I always see the lint. Uh, and and I'm fascinated by how did something get someplace, it's not supposed to be. So it doesn't even need to be a big discrepancy, but if something shouldn't be someplace in a constellation of facts that, that, you know, sort of made sense in a traditional way, I've learned that if you focus on why someone discordant note is there, that's usually a key to something important. And if you can find two of those discordant notes, that's usually a straight line to someplace and that some places not where you've been, and usually when you figure out that things are changing or have changed and you describe them, which you have to be able to do because it's not uh some odd intuition, it's just focusing on facts. It's almost like a scientific discovery. If you will, when you describe it to other people in the real world, they tend to do absolutely nothing about it. And that's because humans are comfortable in their own reality. And if there's no particular reason at that moment to shake them out of their reality, they'll stay in a even if they're ultimately completely wrong. And I've always been stunned that when I explain where we're going what we're doing and why almost everyone just says that's interesting and they continue doing what they're doing And and so uh you know, I think it's pretty easy to do that uh you know, but what you need is a huge data set. So, you know, before ai and people's focus on data, you know, I've sort of been doing this mostly my whole life. I'm not a scientist, I'm not let alone a computer scientist. And you know, you can just hear what people are saying when somebody says something or you observe something that simply doesn't make sense. That's when you really go to work, the rest of it's just processing, </s>

<s>[INST] that most people interact with. I mean, to push back a little bit of consequential in a physical sense, but if we return to the power of the psychological sense of contempt, I would say store clerks and stuff like that [/INST] can also be a source of contempt. They're not agents of the state. </s><s>[INST] Right. But if we look at the landscape of contempt, which throughout the 20th century, or the bus, right, you can experience the same kind of contempt in other aspects of society. [/INST] But yes, the cops have consequences. In other, but yes, the cops have consequences. I would still put the police. The policeman or the police person is the person walking down the street with a gun. Gun, yeah. And if you think about the way in which the law, the extent to which the police are authorized to use their force, the police have extraordinary, extraordinary authority. Look, you're driving your car and you're speeding. The police can arrest you right then and there and take you to jail. </s><s>[INST] That's an extraordinary path. But have they also have, because of that, the leverage, just one human to another, they have more leverage to be an asshole and to show contempt to you. They certainly do. To be the lesser, to lean into the lesser aspects of their nature as all humans can just to be an asshole to show contempt. You had a bad day. [/INST] They have the more freedom to do that. They certainly do, yes, and that's why, that's why police officers are very important. I recognize, I know police officers. They have a very difficult job, a very important job. Very important, again, remember what I just talked about, under protection. I want the police to protect me. I want the police to protect me from the rapist, the robber. So I, you know, the police, I'm with the police. We need good policing. But we need good policing and for good policing, we need accountability. And one of the scandals, one of the just absolute scandals of American law is the extent to which the police are not held accountable. It's absolutely remarkable the degree to which American law fails to properly hold police accountable. They have an important job, a difficult job. I want them to be very well paid. And as far as I'm concerned, you know, we should be, police should make more money. They should be given the importance of what they do. They should have more respect, more prestige, more money. With all of that, they should be held accountable. And the way things are now, they're not held accountable. And every day, we see the consequences in our newspapers or just, you know, </s><s>[INST] talking with people. So what do you make of the different perspective on this? From to bring up a person that I'll probably speak with Heather McDonald, who wrote a book called War on Cops and will often bring up the stuff that does show up in the data to show the disproportionate amount of homicides committed by African Americans. And we'll also justify racial profiling on that basis in stop and frisk programs. And we'll also bring up things like the Ferguson effect saying that because of this pushback and all the stuff we've been saying about police in those areas, the police will step back [/INST] and crime will increase. I was in one debate with her. And one of the things that I said is it was a debate that was sponsored by the Federalist Society, conservative legal group, conservative law students at Harvard Law School. We had a, she made a presentation and they asked me to respond. And one of the things that I said was when we're talking about the police, I'm disappointed with the reaction of some of my conservative colleagues. And I would consider her to be one of my conservative colleagues. Because what are the sort of the, what are some of the important precepts of conservatives? One very important precept of conservatives, limited government, limited government. conservatives talk about the tendency of government to overreach itself and governmental agents to overreach themselves. And I say, you're right. You're right. I just, you know, right on. Why is it that you somehow forget that when you're talking about the police? When you're talking about the police, you seem to be unaware of this tendency that is so much in your consciousness and other places. But now when you're talking about the police, you make it seem as though I'm, you know, other people are being paranoid when they talk about the danger of overreach. We need to be very careful about the danger of overreach. Another thing with respect to the police, what to conservatives, transparency in government, right? You're absolutely right. We need transparency in government. So why is it that so often when we're talking about policing, why is it that conservatives actually embrace police unions and are the enemies of transparency? Why is it that you want to prevent the citizenry from knowing that officer so-and-so has, you know, there have been 10 incidents in the last year in which citizens have complained about officer so-and-so. Don't you think that the citizenry ought to know that? Why is it that you want to keep that under wraps? So overreach, transparency, the tendency or the, you know, the problem of governmental agent corruption. Why is it that those sorts of things are forgotten about when some conservatives, by the way, not all conservatives, not all conservatives, there's some conservatives who have stuck and appropriately so to their guns and have said, hey, we need to make sure that the police stay in their lane. We need to make sure that the police do not overstep constitutional bounds. We need to be, we need to insist on transparency. There are some conservatives who have taken that line and I salute them. But there are a lot of conservatives, and I would say Heather McDonald was one of them, who all of a sudden become just, you know, totally uncritical status </s>

<s>[INST] Exactly. Just out of curiosity what it seems like one possible solution. I'd like to see what you think of it based on what you just said based on wanting to know answers for when you're yourself in that situation. Is it possible for patients to own their data as opposed to hospitals owning their data? Of course theoretically I guess patients own their data but can you walk out there with the USB stick containing everything or uploaded to the cloud where a company you know I remember Microsoft had a service like I tried I was really excited about and google health was there. I tried to give I was excited about it basically companies helping you upload your data to the cloud so that you can move from hospital to hospital from doctor to doctor. Do you see a promise of that kind of possibility. [/INST] I absolutely think this is you know the right way to exchange the data. I don't know now who is the biggest player in this field but I can clearly see the different you know for even for totally selfish health reasons when you are going to a new facility and many of us are sent to a specialized treatment, they don't easily have access to your data. And today you know we might want to send this mammogram need to go to the hospital find some small office which gives them the C. D. And the ship as a city. So you can imagine we're looking at the kind of decades old mechanism of data exchange. So I definitely think this is an area where hopefully all the right regulatory and technical forces will align and we will see it actually implemented. </s><s>[INST] It's sad because unfortunately I have, I need to research why that happened, but I'm pretty sure google health and Microsoft health vault or whatever it's called, both closed down, which means that there was either regulatory pressure or there's not a business case or there's challenges from hospitals, which is very disappointing. So when you say, you don't know what the biggest players are, the two biggest that I was aware of closed their doors, some hoping uh I'd love to see why and I'd love to see who else can come up. And it seems like a one of those uh Elon musk style problems that are obvious needs to be solved and somebody needs to step up and actually do this large scale data, you know, data collection. [/INST] So I know there is an initiative in massachusetts, I think I should lead by the governor to try to create this kind of health exchange system where at least to help people who kind of when you show up in emergency room and there is no information about what archaeologists and other things. Uh so I don't know how far it will go. But another thing that you said and I find it very interesting is actually who are the successful players in this space and the whole implementation. How does it go to me? It is from the anthropological perspective, it's more fascinating that ai that today goes in healthcare, you know, we've seen so many, you know, attempts and so very little successes and it's interesting to understand that every by no means uh you know, have knowledge to assess it, why we are in the position where we are. </s><s>[INST] Yeah, it's interesting because um data is really fuel for a lot of successful applications and when that data requires regulatory approval, like the FDA or any kind of approval, it it seems that the computer scientists are not quite there yet in being able to play the regulars were a game, understanding the fundamentals of it. [/INST] I think that in many cases when even people do have data, we still don't know what exactly do you need to demonstrate to change the standard of </s><s>[INST] care? [/INST] Like let me give you example, related to my breast cancer research. So, traditional in traditional breast cancer risk assessment, there is something called density which determines the likelihood of a woman to get cancer. And this is pretty much says, how much white do you see on the mammogram? The white, It is the more likely the tissue is dance. And um The idea behind then, it's not a bad idea, 1967, a radiologist called Wolf. I decided to look back at women who are diagnosed and I see what is special in their images. Can we look back and say that they are likely to develop. So he come up with some patterns and it was the best that his human I can uh can identify that it was kind of formalized and coded into four categories. And that's what we're using today and uh today this density assessment is actually a federal law from 2019 approved by president trump and for the previous FDA commissioner where women are supposed to be advised by their providers if they have high density putting them into higher risk category. And in some states, you can actually get supplementary screening paid by your insurance because you and this category. Now you can say, how much science do we have behind whatever biological science or epidemiological evidence. So it turns out that between 40 and 50% of women have dense breast. So about 40% of patients are coming out of their screening and somebody tell them you are in high risk. Now, what exactly does it mean if you as half of the population in high risk? It's from say maybe I'm not, you know, what do I really need to do with it? Because the system doesn't provide me a lot of the solutions because there are so many people like me, we cannot really provide very expensive solutions for them. And the reason this whole density became this big deal. It's actually advocated by the patients who felt very unprotected because many women when did the mammograms which were normal. And then it turns out that they already had cancer quite developed cancer. So they didn't have a way to know who is really at risk. And what is the likelihood that when the doctor tells you you okay, you're not Okay. So at the time and it was, you know, 15 years ago, this maybe it was the best piece of science That we had and uh, you know, quite 15, 16 years to make it federal law. But now that this is this is a standard. Now with a deep learning model, we can so much more accurately predict who is going to develop breast cancer just because you're trained on a logical thing. And instead of describing how much white and what kind of white machine can systematically identify the patterns? Which was the original idea behind the sort of the tri geologist machinists can do it much more systematically and predict the risk when you're trained The machine to look at the image and to say the risk in 1 to 5 years. Now, you can ask me how long it will take to substitute this density, which is broadly used across the country. And I really is not helping to bring this new models. And I would say it's not a matter of the algorithm algorithms already orders of magnitude better that what is currently in practice, I think it's really the question, who do you need to convince, how many hospitals do you need to run the experiment? What all this mechanism of adoption? And how do you explain to patients and to women across the country that this is really a better measure? And again, I don't think it's an ai question. We can walk more and make the algorithm even better, but I don't think that this is the current, you know, the barrier. The barrier is really this other piece that for some reason it's not really explored. It's like anthropological peace. And coming back to your question about books, there is a book that I'm reading. It's called American sickness by Elizabeth Rose in town and I got this book from my clinical collaborator, dr Connie Lehman. And I said I know everything that I need to know about american health system, but every page doesn't fail to surprise me. And I think there is a lot of interesting and really deep lessons for people like us from computer science who are coming into this field to really understand how complex is the system of incentives in the system to understand how you really need to play to drive an option </s>

<s>[INST] It's not going to work. So you said the Mars planet was there in the beginning. What about the reusability of rockets? [/INST] Was that there in the beginning? I think reusability definitely, you know, it's a necessary part of making any kind of interplanetary mission, you know, in order to actually do that just financially, </s><s>[INST] you have to start reusing these things. In terms of the development of the Falcon 1 and Falcon 9, how early on did the goal of reusing the rocket, having the rocket actually land, how early [/INST] did that goal creep in? I can't speak for Elon and SpaceX, but it was pretty immediate that they wanted to try to recover. And as a matter of fact, I think the very first two Falcon 9 rockets and Falcon 1, I think, they even wanted to try to recover using parachutes to recover the first stage. And now, fast forward almost 20 years later, and Rocket Lab is actually doing a concept like that, where they're pulling a parachute after the first stage is re-entering, and they actually are trying to recover it with the helicopter. It's going to try to snatch it out of the air. They've actually done it. They've actually done it successfully once. </s><s>[INST] How does the helicopter grab the rocket? [/INST] With this giant like drag line and a hook. Oh, wow. And then literally just like grab snags onto the parachute. Wow. And it's pretty amazing. But this is a small rocket. Their rocket's only about a metric ton. </s><s>[INST] The booster is empty and it's pretty amazing. So the rocket releases parachutes. Yep. Like really high up. I'd love to see this. Yeah. It's an interesting idea. There's so many interesting ideas and possibilities. Like SpaceX basically just innovated a lot of different weird ideas just in the pursuit of making things more efficient, reusable, all of that. So basically thinking from first principles how to solve this problem. And so what you find is like [/INST] you'll get all these kind of crazy kind of solutions. And with SpaceX, they weren't even getting to the point of the booster surviving reentry long enough to be able to pull the parachutes. Yeah. You know, their mass fractions, you know, and that varies every single rocket's different. You know, all the, you know, for instance, rocket lab uses carbon composite fuselage and tanks or, you know, same thing. And that's very, very lightweight, has really good mass fractions and therefore their drag coefficients and things like that. They were able to survive reentry of the first stage which is something that SpaceX wasn't able to do at the time. What's kind of the big, I think, breakthrough for SpaceX with reusing the booster is they realized we have to basically slow down before we hit the atmosphere. And so they actually do what they used to call a reentry burn which I still think is the correct term cause it is reentering the atmosphere, but now they call it the entry burn and they light up three of the nine Merlin engines not only to slow it down, but actually even while those engines are firing it creates like a literal force field as it's falling through the atmosphere. Interesting. And, but it also decreases the velocity by almost half or around half. And then that therefore decreases the amount of, you know, the biggest thing with the atmosphere is that as it gets compressed against the front of anything flying through the atmosphere, the compressed atoms just get hot and they can get so hot they turn into a plasma and they get so hot they can just absolutely destroy anything. So they slow down enough that the air molecules don't end up destroying the vehicle on reentry. Then they realized, I think, at some point it's probably a similar crossover. They're like, well, if we're letting the engines already to slow down in the atmosphere we can just that same engine to land and so what if we just stuck landing legs on it and just landed the thing vertically and next thing you know is December 21st, 2015, they did exactly that for the first time. </s><s>[INST] The first time. So you were there before that then, right? [/INST] Yeah. In 2014? Yeah. In 2014. Yep. Early 2014. And for me, that was so fun watching. That was like the peak of me just becoming obsessed with this idea. I'm watching and back in the day, it was like months between launches, so a launch was like a big idea. I'd wake up at 3am to watch this landing attempt or whatever, you know, and every, you know, there is CRS4 almost landed, CRS5 almost landed, CRS6, CRS7 blew up. I was watching that on, I think it was like a Saturday morning or maybe a Sunday morning and I remember watching that and watch it blow up and I was like, oh, now what? You know, and it blew up on a scent. It was their first failure. So it was their 18th flight, I believe. And on Sierra 7 the upper stage had one of the bottles, there's bottles inside the tanks that are filled with helium and one of those bottles broke off on a scent and actually just completely over pressured the upper staging. The upper stage blew up and the whole rocket went kaboom in an uncontrolled manner. So then they came back with vengeance, when they came back, the first mission back is the first time that they landed a rocket, which was awesome. So they returned to flight after the anomaly was landing a rocket. And then stuck the landing. </s><s>[INST] Yup. Fuck the landing. Yup. Well, actually the first time, so the first time you were there, what was that like? [/INST] What do you remember from that day? I was surprised at how much bigger the rocket was than I imagined. I originally, when I was going down to Kennedy Space Center, I was disappointed that I wasn't seeing like a, you know, I didn't know a ton about rockets. I knew enough to like know what a space shuttle was, what like the Saturn V was, you know, but that was probably about the end of my knowledge. I just remember being disappointed that I wasn't seeing a big, quote unquote NASA rocket flying. You know, I was thinking to my head like, oh, I'm gonna see this launch. It's probably gonna be like, you know, three stories tall or something, you know. Yeah. Just some little skinny little stick and some little firecracker and yay. You know. I think I'd almost been pitched that too. I think the people that I was working for at the time I think they kind of were down playing. And it's like, well, it's not a big rocket here. It's not gonna be that exciting, you know. But we get out there to the pad and I'm like, this thing's huge, this is not a small rocket. Like this is, you know, it's 70 meters tall, 220 feet tall. It's huge. And I think people forget like the scale of that, you know? It might look skinny and tall and all this stuff, but it's still a very, very large piece of machinery. It's physically about as large as you can ship, the booster's about as big as you can ship across the country period without like completely shutting down highways. You know, it is made within those exact specifications of like having, you know, lane privileges and bridges and everything. It's, you know, 12 feet wide, 3.7 meters wide, and it's 45 meters long. So it's like exactly what you can fit with a pretty standard, you know, like before you start getting into crazy amounts of problems shipping the rocket. And it's huge. It's huge. And people just don't understand that. And so when I saw with my own eyes, I remember just being like, </s>

<s>[INST] the troublemaker he is [/INST] but causality is important but causality is not is not like a single silver bullet. It's not like one single principle. There are many different aspects here. And one of the ways in which uh one of our most reliable ways of establishing causal links and this is the way, for example, the medical community does this is randomized control trials. So you have a you pick some situation and now in some situation you perform an action and for certain others you don't Right? So you have a control experiment. Well, the child is in fact performing controlled experiments all the time. Right, okay. Small scale and in a small scale and but but that is a way that the child gets to build and refine its causal models of the world. And my colleague Alison Gopnik has together with a couple of authors. Co authors has this book called the scientists in the crib referring to the Children. So, I like the part that I like about that is the scientist wants to do wants to build causal models and the scientist does control experiments and I think the child is doing that. So to enable that we will need to have these these active experiments. And I think this could be done some in the real world and some of </s><s>[INST] you have hope for simulation. I [/INST] hope that's </s><s>[INST] an exciting possibility if we can get to not just photo realistic, but what's that called life realistic simulation. So you don't see any fundamental blocks to why we can't eventually simulate the principles of what it means to exist in the world as a [/INST] Physical. I don't see any fundamental problems that I mean. And look the computer graphics community has come a long way. So the in the early days back going back to the 80s and 90s they were they were focusing on visual realism right? And then they could do the easy stuff but they couldn't do stuff like hair or fur and so on. Okay, well they managed to do that then they couldn't do physical actions right? Like there's a bowl of glass and it falls down and it shatters. But then they could start to do pretty realistic models of that and so on and so forth. So the graphics people have shown that they can do this forward direction not just for optical interactions but also for physical interactions. So I think of course some of that is very computer intensive but I think by and by we will find ways of making models that were more realistic. </s><s>[INST] You break vision apart into in one of your presentations early vision, static scene, understanding dynamics and understanding and raise a few interesting questions. I thought I could just throw some some at you just to see if you want to talk about them. So early vision. So it's what is it that you said um sensation, perception and cognition. So is this a sensation? Uh huh. What can we learn from image statistics that we don't already know. So at the lowest level, what what can we make from just this? The statistics basic. So there were the variations in the rock pixels, the textures and so on. [/INST] Yeah. So what we seem to have learned is uh is that there's a lot of redundancy in these images. And as a result we're able to do a lot of compression. And this compression is very important in biological settings. Right? So you might have 10 to the eight photo receptors and only 10 to the six fibers in the optic nerve. So you have to do this compression by a factor of hundreds to one. And so there are analog of that which are happening in in our neural artificial neural network earlier </s><s>[INST] there. So there's a lot of compression. They can be done in the beginning just just the statistics. Um How much how much? Well [/INST] so I mean the way to think about it is just how successful this image compression. Right? And we and there are and that's been done with older technologies but it can be done with there are several companies which are trying to use sort of these more advanced neural network type techniques for compression, both for static images as well as for for a video. One of my former students has a company which is trying to do stuff like this. Uh I think I think that they are showing quite interesting results. And I think that that's all the success of that's really about image statistics and video statistics, </s><s>[INST] but that's still not doing compression of the kind when I see a picture of a cat. All I have to say is it's a cat. Another semantic kind of competition. [/INST] Yeah. So this is this is the lower level. Right? So we are we are as I said, yeah, that's focusing on level status. </s><s>[INST] To linger on that for a little bit. You mentioned, how far can bottom up image segmentation go? And in general, what you mentioned that the central question for scene understanding is the interplay of bottom up and top down information. Maybe this is a good time to elaborate on that. Maybe define what is what is bottom up, what is top down in the context of computer [/INST] vision. Right. That's uh so today, what we have are a very interesting systems because they were completely bottom up. How are that bottom? So, bottom up means in this case means a feed forward neural network. So they start from the raw pixels and they end up with some something like cat or not a cat. Right? So our our systems are running totally feed forward. They are trained in a very top down way. So they're trained by saying, okay, there's a cat, there's a cat. There's a dog. There's a zebra, etcetera. And I'm not happy with either of these choices fully we have gone into because we have completely separated these processes right? So there's a so I would like the process uh so what do we know compared to biology? So in biology what we know is that the processes in at test time at runtime those processes are not purely feed forward but they involve feedback. So and they involve much shallower neural networks. So the kinds of neural networks we are using in computer vision say a resnet 50 has 50 layers well in in the brain in the visual cortex going from the retina to I. T. Maybe we have like seven. Right so they're far shallower but we have the possibility of feedback. So there are backward connections and this might enable us to uh to deal with the more ambiguous stimuli for example. So the the biological solution seems to involve feedback. The solution in in artificial vision seems to be just feed forward but with a much deeper network and the two are functionally equivalent because if you have a feedback network which just has like three rounds of feedback you can just unroll it and make it three times the depth and created in a totally feed forward way. So this is something which we have written some papers on this theme but I really feel that this should this team should be pursued further have </s>

<s>[INST] spent quite a long time with Pearl. That was another letting go let go of this kind of data processing system. [/INST] The reasons why python became the lingua franca of scientific code and machine learning in particular. And data science, it really had a lot to do with anything was better than C or C plus. Plus recently a guy who worked at Lawrence livermore National Laboratories in the the sort of computing division wrote me his his his memoirs and and he had his his own view of how he helped something he called computational steering into existence. And this was the idea that you you take libraries that in in his days were written in FORTRAN that that solves universal mathematical problems. Uh And those libraries still work but the scientists that use the libraries use them to solve continuously different specific applications and answer different questions. And so those poor scientists were, were required to to use, say for trend, because FORTRAN was the library, the language that the library was written in and then the scientists would have to write an application that sort of uses the library to solve a particular equation or set off of answer a set of questions and the same same for C plus plus because there's there's interoperability. So the dusty decks are written either in C plus plus or FORTRAN. Uh and so paul Dubois was one of the people who I think in the mid 90's saw that that you needed a higher level language for the scientists to to sort of tie together the fundamental mathematical </s><s>[INST] algorithms of linear [/INST] algebra and and other stuff. And so gradually some library started appearing that did very fundamental stuff with arrays of numbers in python. I mean when I first created python, I was not expecting it to be used for arrays of numbers. Much, I thought that was like an outdated data type and everything was like objects and strings. And like python was good and fast at string manipulation and objects obviously, but the race of numbers were not very efficient and the multidimensional race didn't even exist in the language at all. Uh but there were people who realized that python had extensive bility That was flexible enough that they could write 3rd party packages that did support large arrays of numbers and operations on them very efficiently. And somehow they got a foothold through sort of different parts of the scientific community. I remember that the Hubble space telescope people in Baltimore were somehow big python fans in the late nineties and at various points, small improvements were made. And more people got in touch with using python to derive these libraries of interesting uh, algorithms. And like once, once you have a bunch of scientists who are working on similar problems, say they're all working on stuff that that data that comes in from the Hubble space telescope. But they're looking at different things. Some some are looking at stars in this galaxy, others are looking at Galaxies, the math is completely different, but the underlying libraries are still the same. And so they exchange code. They say, well, I wrote this python program or I wrote a python library to solve this class of problems. And the other guys either say, oh, I can use that library to or if you make a few changes, I can use that library to why, why? Why start from scratch in PERL or javascript where there's not that infrastructure for arrays of numbers yet, whereas in python you have it. And so more and more scientists at different places doing different, different work discovered python. And then then people who had an idea for an important new fundamental library decided, oh, python is actually already known to our users. So let's use python as the user interface. I think that's how tensor, I imagine at least that's how tensorflow ended up with python as the user interface interface, </s><s>[INST] right? But with tensorflow there's a deeper history of what the community, so it's not just like what packages needs, it's like what the community leans on for programming language because tensorflow had a prior library that was internal to google, but there was also competing machine learning frameworks like Theano cafe that were in python, there was some scholar, um some other languages, but python was really dominating it and it's interesting because there's other languages from the engineering space like matt lab that a lot of people used, but different design choices by the company, by the core developers led to it not spreading. And one of the choices of matt lab by Math works is to not make it open source, right or not. You know, having people pay, [/INST] it was very expensive product and so universities especially disliked it because it was a price per seat. I remember hearing. </s><s>[INST] Yeah, but I think that's not why it failed or failed to spread. I think the universities didn't like it, but they would still pay for it. The thing is it didn't feed into that Git hub, open source uh, packages culture. So like and that's somehow a precondition for for viral spreading the hacker culture, like the tinkerer culture uh with, with python, it feels like you can build a package from scratch or solve a particular problem and get excited about sharing that package with others and that creates an excitement about a language. I [/INST] tend to like python's approach to open source in particular because it's sort of, it's almost egalitarian. Um uh there's there's little hierarchy, there's there's obviously some because like you all need to decide whether you drive on the left or the right side of the road sometimes, but there is a lot of access for people with little power. You don't have to work for a big tech company to make a difference. In the python world. We have affordable events that really care about community and support people and sort of the community is is is like a big deal at our conferences and in in the PSF when the PSF funds events, it's always about growing the community, the PSF funds very little development. They that they do some, but most of the developed, most of the money that the PSF forks out uh is to community fostering things. </s>

<s>[INST] one way to put it if it's okay. Let me because it is, it is a poem. I um go go too often actually. Um you mentioned reciting some lyrics and I'm actually gonna go back to that at some point to get get a few songs that touch you. But this is one of the things I I go to often I I'll read it to remind myself it's um advice from, from father to son and it's a kind of mantra that it's just nice to live by. So if it's killing me just use this opportunity to one more time read if, by Rudyard kipling if you can keep your head when all about you are losing theirs and blaming it on you. If you can trust yourself when all men doubt you, but make allowance for their doubting too. If you can wait to not be tired by waiting are being lied about. Don't deal in lies or being hated. Don't give way to hating. And yet don't look too good, nor talk too wise. If you can dream and not make dreams your master, if you can think and not make thoughts, your aim, if you can meet with triumph and disaster and treat those two impostors just the same. If you can bear to hear the truth, you've spoken twisted by knaves to make a trap for fools, or watch the things you gave your life to broken and stoop and build them up with worn out tools. If you can make one heap of all your winnings and risk it all on one turn of pitch, and toss and lose, and start again at your beginnings, and never breathe a word about your loss. If you can force your heart to nerve and send you to serve your turn long after they're gone. And so hold on when there's nothing in you except the will which says to them. Hold on, if you can talk with crowds and keep your virtue. I like this one, and walk with kings, nor lose the common touch! If neither foes and their loving friends can hurt you. If all men count with you, but none too much. If you can fill the unforgiving minute With 60 seconds worth of distance. Run, Yours is the earth and everything that's in it and which is more you'll be a man, my son, thank you Andrew. Thank you. Thank you. Mike for the knife. [/INST] I don't know. It's a it's an and engraved in it. Yeah, it's yours, </s><s>[INST] yours is the earth and everything that's in it. [/INST] We toiled over what to engrave. And then finally I just said, mike, just pick something that speaks to you. You're the craftsman. And so he selected that </s><s>[INST] there's certain ways to pull yourself in that book actually. Uh carl dies are all gonna die. Sarath. He wrote the book projections. One of my favorite, first of all, just as you said, incredible writer. Just amazing. Just, I mean, if you wrote fiction, if you wrote those kinds of things, I'm curious to see where he goes with his writing. It's very interesting. I [/INST] think that book took him 10 years to write, which is vindication for me and for you because we're both supposed to write books and we haven't done it. </s><s>[INST] Yeah, I mean, you know, in some sense, you're um, first book will have, you know, decades in it, right? Even if you just take half a year to write it. It's like the first book, like the first album for a musician. I mean, it's a light, it's a journey. It's a, it's a it's a but he uses uh poems and quotes and they're really well, it's [/INST] a beautiful book. It's a dreaming book. I think when people hear that it's a book about neuroscience, they think they're going to get a textbook or a protocols book or something. It's nothing like that. But it really is a deep dive into the mind of the psychiatrist and the researcher and so much feeling and compassion. I love that you love poetry. I mean, I didn't know that until I saw you on Rogan read if um, and I'm not a very rabid consumer of poetry, but I, I'm a big Wendell berry fan. Um uh, and I try and read a poem once every few </s><s>[INST] days [/INST] also. I think if it's a tough act to follow, I mean, that's the richness and the I mean, you said every 3rd line in there is something that you would, you know, you consider your life well lived. If you if you said that right, </s><s>[INST] what about the preparation for the solo podcast, you said you listen to certain songs, you know, you sing or recite the lyrics of certain songs is they're ones that kind of come to mind that are interesting. [/INST] Um yeah, I've always been very lyrics driven and I don't understand music. I've talked to rick about this. I think I've talked to you about this little, but I don't really understand. Yeah, I mean, I can hear music and like it, but I don't really understand the structure of it, but lyrics make a lot of sense </s><s>[INST] touch your soul, [/INST] it's the lyrics, it's not the instrumentals. So I'm a huge joe strummer fan and I'm gonna lose punk points for saying this, but I'm not a clash fan. So he obviously is best known for the clash most clash song start off great and then after about 30 seconds and at least in my mind just kind of disintegrated into a bunch of mush. Whereas um joe strummer and the Mescaleros, which is what he did as an adult, as a you know later. And some of his solo work, he actually rick produced some work that he did with johnny cash, you know rick pulled johnny cash out of essentially out of retirement and had him do his albums before he died. And so anything that strummer did, there's a there's a favorite song of mine by strummer. It's called Burning Lights. Um you can find it, there is an album now where you can find it or Tennessee Rain or some of these things that he did, which are a little bit more folky, so not really punk. So I love that song um a bunch of songs by rancid that I love, </s>

<s>[INST] through public policy, but definitely exists today as well. So you mentioned living wage. Is there a tension between a living wage, maybe you could speak to what a living wage means, and the workers owning all of the profit of the company, sort of this kind of spectrum? No, I guess the spectrum is from like no minimum wage, the lowest possible thing you could pay to a worker, then somewhere in that spectrum is a living wage. And then at the top is like all of the profit from the company is owned by the workers. [/INST] Split to the workers. I mean, I think that any society is going to have to make distributional choices. You could have imagined a variety of capitalism in which workers are paid quite little, but there's extremely high taxation and there's redistribution after the fact. You could imagine a system in which there's less taxation after the fact, but there's more guarantees and regulations on how much people are paid before the fact. In my vision of a socialist society, there would be similar way that unions work and in my example, the centralized bargaining unions would work that bargain at the sectoral level and not just at the enterprise level like our unions do today. There could be benchmarks set for different occupations or wages. And the reason why you would want a benchmark at a worker controlled firm is that you don't want workers self-exploiting themselves in order to gobble up market share because you don't want them collectively deciding, okay, we're going to invest in this longer term time horizon and out-compete other people that way. So you might say, okay, if you do this sort of clerical work, you have to be paid the equivalent of $15 an hour. That's a minimum, but on top of that, you get dividends from excess profits. And I think it would also have to be combined with public financing for expansions and for development, which could be done in quite a competitive way. So you could have a variety of banks, my vision, state-owned banks, but how would they decide who to invest in and who to not invest in, who to give a loan for expansion to and who not to? Because you don't want it to be like, oh, I'm going to invest in my nephew's firm and not this other firm or I'm going to invest in this guy's firm because he's an Italian, but not this guy's firm because he's Albanian or whatever else. Just make it rational to level up. Their goal is just like any other investment person at a bank today to maintain a certain risk profile and to have an interest yield and decide to invest on that basis. So if there's a huge automotive firm that has been on business for 50 years that needs a little operating cash, yeah, they could get their $50 million or 3% loan. If you have some crazy blue sky idea and you managed to get it to that point, maybe you and your friends would get it at 12% or something close to what a VC would offer today. So I only go into these details not because to say that a system doesn't have to in advance map out all the different possibilities, but I think it does have to be willing to accept a lot of things that we know today. I can't give you a version of socialism that everything's going to be fine, we're going to live harmoniously and we won't have these sort of tensions and you could hunt in the evening and fish in the afternoon and write criticism, whatever else. I do hope that there's horizons beyond this that we could aspire to. I do have those visions, but for now I think our task as socialists is to imagine a five minutes after midnight, </s><s>[INST] like what can we do right away within our lifetime vision? So that means through some level of central planning, [/INST] reallocating resources to the workers. So I think the primary mechanism in this private sector under socialism would be a market mechanism, firms competing against each other to expand, connected to a system of public financing. But even at that level, the individual bankers and public banks and so on would be operating based on their own rationality and the state would certainly shape investment decisions, but maybe no more than they do in a lot of capitalist systems. So the state might already today in a lot of countries decide, we want to invest in green technology, so it's gonna be favorable rates for people or tax credits for people investing in green technology. So the state already shapes investment. I think what should be centrally planned, and this is where I'm proud to sound like an old school socialist, is things like healthcare, things like transit, things like our natural monopolies of lots of types, I think can be done very well through planning and we already have plenty of examples, but a lot of this society, I think would be the private sphere of worker controlled cooperatives, competing against each other, </s><s>[INST] weak firms failing, successful firms expanded. And the banks, you're saying publicly or privately owned? Publicly owned. Let's just put it all on the table that it's almost guaranteed that every system has corruption. So I guess the bigger question is, which system has more corruption? This one was central planning and worker cooperatives versus unfettered capitalism [/INST] or any flavor of capitalism. I think any system has potential for corruption. I think it depends on like how good your civil services, how much oversight do you have to resolve a problem once it arises? </s>

<s>[INST] so one of the I guess uh toxicity on my part was a really bad word to use. But if we talk about what makes a good leader and just look at an example in particular uh looking at Elon musk, he's known to put push people to the limits in a way that I think really challenges people in a way they've never been challenged before to do the impossible. But it can really break people. And [/INST] jobs was hard and amazon is hard and you know, but the thing that's important is none of them lie about it. You know that you know, people ask me about amazon all the time. Like Jeff Bezos never lied about it. You know, Even the ones who like amazon don't last more than a couple of years before they burn out. Um But when we're honest about the culture then it gives people the opportunity who like to work in that kind of culture to choose to work in that kind of culture as opposed to pretending and saying, oh no this is all, you know, it's all lovey lovey here and then you show up and it's it's the furthest thing from it. So I </s><s>[INST] mean [/INST] it, you know, I think the reputations are putting a lot of pressure on people to, you know, jobs, jobs was not a an easy man to work for. Um he he pushed people, but everyone who worked there was given the space to create and do things that they would not have been able to do anywhere else and work at the level that they didn't work anywhere else. And jobs didn't have all the answers. I mean, he pushed his people to uh to come up with answers. He he wasn't just looking for people to execute his ideas. Um uh and people did people accomplished more than they thought they were capable of, which is wonderful. </s><s>[INST] How do you, you're talking about the infinite game and not thinking about too short term and yet you see some of the most brilliant people in the world being pushed by LAMAs to accomplish some of the most incredible things when we're talking about autopilot, we're talking about some of the hardware engineering and they do some of the best work of their life and then leave. How do you balance that in terms of what it takes to be a good leader, what it takes to accomplish great things in your life. So I [/INST] think there's a difference between uh someone who can get a lot about to get a lot out of people in the short term and building an organization that can sustain beyond any individual. There's a difference </s><s>[INST] when you say beyond any individual, you mean beyond beyond. If the leader dies, correct, [/INST] could Tesla continue to do what it's doing without Elon musk, </s><s>[INST] You know, you're, you're perhaps implying, which is a very interesting question that it cannot, [/INST] I don't know, you know, the argument you're making of this, this, this person who pushes everyone, arguably it's not a, not a repeatable model, right? You know, is Apple the same without steve jobs or is it slowly moving in a different direction? Um, or has he established something that could be resurrected with the right leader </s><s>[INST] that was his dream I think is to, to have to build an organization that lives on beyond them? At least I remember reading that, I think that's [/INST] what a lot of leaders desire, which is to create something that was bigger than them. You know, most businesses, most entrepreneurial ventures could not past the school bus test, which is, if the founder was hit by a school bus, would everyone continue the business without them or would they all just go find jobs and the vast majority of companies would fail that test? Um, you know, in, in especially in the entrepreneurial world that if you take the inspired visionary leader away the whole thing collapses. So is that a business or is that just a force of personality and a lot of entrepreneurs, you know, face that reality, which is they have to be in every meeting, make every decision, you know, come up with every idea because if they don't, who will, and the question is, well, what have you done to build your bench? Um, is it, it's not, sometimes it's ego, the belief that only I can, sometimes it's um just things got did so well for so long that I just forgot and sometimes it's a failure uh, to build the training programs or or hire the right people that could replace you who are maybe smarter and better. Um, and browbeating people is only one strategy. I don't think it's necessarily the only strategy, nor is it always the best strategy. I think people, people get to choose the cultures they want to work in. So this is why I think, I think companies should be honest about the kind of culture that they've created. You know, I heard a story about Apple where some, somebody came in from a big company, you know, he had accomplished a lot and his ego was very large and he was going on about how he did this and he did that and he did this and he did that. And somebody from Apple said, we don't care what you've done. The question is what are you going to do? And that's that's, you know, for somebody who wants to be pushed, that's the place you go because you choose to be pushed. Um now we all want to be pushed to some degree, you know, anybody who wants to, you know, accomplish anything in this world, wants to be pushed to some degree, whether it's through self pressure or external pressure or in a public pressure, whatever it is. Um but I think this, this whole idea of one size fits all is a false narrative of how leadership works, but what all leadership requires is creating environment in which people can work at their natural best. </s>

<s>[INST] I'm asking you. It's almost possible to really forget the external world. Really, really immerse [/INST] yourself what to forget completely. Why would we forget? You know, we've got pretty good memories. Maybe you can stop paying attention to the external world, but you know that this already happens a lot. I go to work and maybe I'm not paying attention to my home life. I go to us. I go to a movie and I'm immersed in that. So that degree of immersion. Absolutely, but we still have the capacity to remember it to completely forget the external world. I'm thinking that would probably take some I don't know, some pretty serious drugs or something to make your butt to make your brain is </s><s>[INST] impossible. So, I mean, I guess I'm getting at is consciousness uh truly a property that's tied to the physical brain. Or can it can you create sort of different offspring copies of consciousness is based on the world that you enter. [/INST] Well, the way we're doing it now, at least with a standard VR, there's just one brain interact with the physical world. Plays a video game, puts on a video headset, interact with this virtual world. And I think we typically say there's one consciousness here that nonetheless undergoes different environments, takes on different characters, you know, in different environment. This is already something that happens in the non virtual world. I might interact one way in my home life, work life, social life, um and so on. So at the very least that will happen in a virtual world very naturally. People might, people have people sometimes adopt the character of advertise very different from themselves. Maybe even a different gender, different race, different social background. So that much is certainly possible. I would see that as a single consciousness is taking on different personas. If you want literal splitting of consciousness into multiple copies. I think it's going to take something more radical than that. Like, maybe you can run different simulations of your brain in different realities and then expose them to different histories and then, you know, You split yourself into 10 different simulated copies, which then undergo different environments and then ultimately do become 10 very different consciousnesses. Maybe that could happen. But now we're not talking about something that's possible in the near term, we're going to have to have brain simulations and a G. I. For that to happen. </s><s>[INST] God, it's so before any of that happens, it's fundamentally you see it as a singular consciousness, even though it's experiencing different environments, virtual or not, it's still connected to the same set of memories, same set of experiences and therefore one sort of joint a conscious system. [/INST] Yeah. Or at least no more multiple than the kind of multiple consciousness that we get from inhabiting different environments in a non virtual world. </s><s>[INST] So you said as a child, you're a music color center, [/INST] center State </s><s>[INST] Senate State. So we're songs that colors for you. So what songs had what colors, [/INST] you know, this is funny. I didn't paint much attention to this at the time, but I listen to a piece of music and I'd get some kind of imagery of a of a kind of uh kind of color. The weird thing is mostly they were kind of murky dark greens and olive browns and the colors when all that interesting. I don't know what the reason is my theory is that maybe it's like different chords and tones provided different colors and they all tended to get mixed together into these somewhat uninteresting browns and greens. But every now and then there will be something that had a really pure Carlos. This is a few that I remember. There was a here there and everywhere by the Beatles with bright red and has this very distinctive tonality and it's called structure at the, at the beginning. So that was bright red. There's a song by the Alan Parsons project called Ammonia Avenue. That was, it was kind of a pure, a pure blue. Anyway, I've got no idea How did this happen. Didn't even pay that much attention until it went away when I was about 20 synesthesia often goes away. </s><s>[INST] So it's purely just the perception of a particular color or was there a positive or negative experience with? Like was blue associate with a positive and red with the negative or is it simply the perception of color? Associate with some characteristic of the song? [/INST] For me, I don't remember a lot of association with the motion or with value was just this kind of weird and interesting fact. I mean at the beginning I thought this was something that happened to everyone songs of colors. Maybe I mentioned it once or twice and people said, uh no, uh, it was like, it was kind of cool when there was one that had one of these, especially pure colors, but only much later once I became a grad student thinking about the mind that I read about this phenomenon called synesthesia and was like, hey, that's what I had and now I occasionally talk about it in my classes, an intro class and still happens sometimes a student comes up and says, hey, I have that. I never knew about that. I never knew it had a name. </s><s>[INST] You said they Wanna went away at age 20 or so and uh, that you have a journal entry from around and saying songs don't have colors anymore. [/INST] What happened? What happened? Yeah, It's definitely sad that it was gone in retrospect. It's like, hey, that's cool. The colors have gone. </s>

<s>[INST] The following is a conversation with David Patterson touring award winner and professor of computer science at Berkeley. He's known for pioneering contributions to rISC processor architecture used by 99% of new chips today and for co creating raid storage. The impact that these two lines of research and development have had in our world is immeasurable. He's also one of the great educators of computer science in the world. His book with john Hennessy is how I first learned about it was humbled by the inner workings of machines at the lowest level quick summary of the ads to [/INST] sponsors </s><s>[INST] the Jordan Harbinger show and cash up. Please consider supporting the podcast by going to Jordan's harbinger dot com slash lex and downloading cash app and using code. Lex podcast, click on the links, buy the stuff. It's the best way to support this podcast and in general the journey I'm on in my research and startups. This is the artificial intelligence podcast. If you enjoy, subscribe on youtube, review five stars on apple podcast. Support on Patreon or connect with me on twitter and lex Friedman spelled without the e just F r I D M A M. As usual, I'll do a few minutes of as now and never any ads in the middle that could break the flow of the conversation. [/INST] This episode is supported by the jordans Harbinger show. </s><s>[INST] Go to Jordan harbinger dot com slash lex. It's how he knows I sent you on that page. There's links to subscribe to it on apple podcast, Spotify and everywhere else. I've been binging on this podcast. It's amazing, Jordan's a great human being, he gets the best out of his guest dives deep, calls them out when it's needed. It makes the whole thing fun to listen to. He's interviewed Kobe Bryant, Mark Cuban, Degrasse, Tyson, Garry Kasparov and many more. I recently listened to his conversation with frank a big nail author of Catch Me if you can and one of the world's most famous comment, perfect podcast, length and topic for a recent long distance run that I did again go to Jordan harbinger dot com slash lex to give him my love and to support this podcast. Subscribe also on apple podcast Spotify and everywhere else. This show is presented by cash app, The greatest sponsor of this podcast ever, and the # one finance app in the app store. When you get a used code lex podcast cash app lets you send money to friends buy Bitcoin, invest in the stock market with as little as $1 since cash app allows you to buy Bitcoin. Let me mention that Cryptocurrency in the context of the history of money is fascinating. I recommend the scent of money is a great book on this history. Also, the audio book is amazing [/INST] debits and credits on </s><s>[INST] Ledgers started around 30,000 years ago, Us, dollar created over 200 years ago and the first decentralized. Cryptocurrency released just over 10 years ago. So given that history, Cryptocurrency is still very much in its early days of development, but it's still aiming to and just might redefine the nature of money. 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 system education for young people around the world. And now here's my conversation with David Patterson. Let's start with the big historical question, How have computers changed in the past 50 years at both the fundamental architectural level and in general in your eyes? [/INST] Well, the biggest thing that happened was the invention of the microprocessor. So computers that used to fill up several rooms could fit inside your cell phone. And uh not only and not only they get smaller, they got a lot faster so there Million times faster than they were 50 years ago and they're much cheaper and they're ubiquitous. Uh you know, there's 7.8 billion people on this planet, probably half of them have cellphones spent now. Just remarkable </s><s>[INST] it's probably more microprocessors than there are people. Sure, [/INST] I don't know what the ratio is, but I'm sure it's above one. uh maybe it's 10-1 or some number like that, what is </s><s>[INST] a microprocessor? [/INST] So a way to stay with a microprocessor is to tell you what's inside a computer. So computer forever has classically had five pieces, there's input and output, which kind of naturally as you'd expect is input is like speech or typing. An output is displays um there's a memory and like the name sounds, it remembers things. So it's integrated circuits whose job is you put information in. Then when you ask for it it comes back out that's memory. And the third part is the processor where the team microprocessor comes from and that has two pieces as well. And that is the control which is kind of the brain of the processor. And the what's called the arithmetic unit is kind of the brawn of the computer. So if you think of the as a human body, the arithmetic unit. The thing that does the number crunching is the is the body and the control is the brain. So those five pieces input, output, memory Uh arithmetic unit and control are have been computers since the very dawn and the last two are considered the processor. So a microprocessor simply means a processor that fits on a microchip. And that was invented about, you know, 40 years ago was the first microprocessor. </s>

<s>[INST] done in the longer term [/INST] though, the </s><s>[INST] balancing, [/INST] I'll say, I hope so, but to come to some dead in the end though, that is true. Time will get us all. Yeah, but well that was so that was the first one and that was when I realized I'm terrible at EMA. But I like it. I should just stop this until I one day learn how to actually grapple much, let's learn how to fight. But I remember this guy named Dave Kaplan was the reason my ears are all messed up who was on the ultimate fighter and got punched in the face and knocked out by Tom Lawler, who I'll always appreciate for doing that. Um, but uh, anyway, tom uh, I appreciate time appreciate Dave to David. Davis, great day was just a huge bully and used to like, really not completely unmercifully, but relatively unmercifully beat the crap out of me. And uh, anyway, the years look good. So I appreciate that. I tell people it's a tumor that I got and I'm gonna, if they want in on a class action lawsuit with a TNT, they should, you know, I sent them an email. But anyway, you're very </s><s>[INST] financially savvy, [/INST] Good. No, I just give the impression. Dave basically said, Hey, don't worry man, you're never going to be good at Emma and you're never gonna be the grappling either. But even if you are good at grappling, which in my opinion, you will never be, you will never be good at fighting. And I said, Dave, if I do nothing else in my life, I'm gonna keep training until I can make you pay for that and now that I can make him pay for that really easily, he doesn't train anymore. But I love Dave. Dave's awesome. He actually won the singing bee. What an interesting dude. Super interesting guy. But anyway, uh, none of the Virginia like speaks a couple languages. Super interesting guy. Like shockingly good at jeopardy to, uh, not that I'm any good, but still shockingly good at jeopardy. So anyway, years later met for as a hobby. Actually, john Danaher, um, I met john Danaher and he put me in touch with for, as a hobby. I started training at tristar, you know, immediately loved working with for us and learning under for us, started training at Tristar and I did, my first real professional and um a fight um as someone that actually does had practiced a little bit prior. Uh and I think august 2000 and 12 and uh that was against the guy, he was four and five at the time, so I had some experience, good kind of like first go for me honestly and I won that fight by T. K. O. And then it was a little bit of time off and then I did another fight against a tough guy named magic Hamilton. Um He was five and two at the time and he was three and I was an atmosphere a little bit of fighting experience. Um one that one in the first round of via rear naked choke and then uh started to experience difficulty getting getting fights at that point. Um you know, where you </s><s>[INST] continuously introduced as like the master grappling, the submission [/INST] at least that was that was my thing. I don't know if I was, </s><s>[INST] that was the source of the fear for [/INST] People. I think so because I mean that definitely wasn't much at striking at that point, you know, I definitely a lot, I'd like to think I'm pretty hard to hurt, although I try not to lean on that and I played baseball for like 16 years so I can hit things pretty hard, I just wasn't able to, I recognized pretty early on that I had no idea how to actually hit things hard without becoming hittable myself. So I think that's kind of, the big thing is a lot of times, like, almost you were mentioning before, if you try to go and get people to early, you can hit them if they're not that good, but you're going to get hit yourself. So you're making, you're basically making a wager, you're making a trade of your own life for the ability to hit them. When you watch guys like Israel Adesanya Floyd, Mayweather, Stephen Thompson, uh Connor McGregor when he's fighting really well, it's not a trade, they're not, you're hitting them and they're hitting you. It's, they're hitting you, but it takes years and years and years and years to be able to learn how to do that. Tom lee is another great example of that. You know, my closest trading partner, one of my best friends, and currently now one champion, uh one championship in uh in Asia, the champion of the featherweight or lightweight, featherweight, um 1 55 over there now, and he recently defeated martin win in a really great fight and Tom knocked him out, long time champion and tom doesn't let you hit him, he doesn't let you touch him. I feel so fortunate to have met guys like Stephen and john to go early on in career and go holy moly, I can't even, it's not even like all you let me walk over and find you, it's like fighting a ghost that periodically shows up with a hammer and smoke she and the melon and then disappears </s><s>[INST] into the ether again. So the way they approach the fighting game is thinking, how can I attack without being hit Every, every strategy. Every idea you have about what you're going to do has to do with uh, like that, minimizing the [/INST] Return. Absolute. I mean, that's what all good fighting is done all poor fighting. If you know, throughout the course of history, most generals, whatever they saw read or you know, they did battles by attrition. You know, it's like, yeah, man, I've got 150 guys, you've got 50, you're like, yeah, 60 of my guys die killing your 50. Like that's great for me. But it's not so great for the 60 guys that died. You know, I hope it's worth it. So when you realize that not only you're not just Kobe Bryant and you're Phil Jackson to, you got to do everything. You know, if you got to run across the beach in Normandy, so be it. But that better be, you should have to make sure we thought this through and they're like, hey, there's no way we can like, you know, walk around the side, huh? Because oftentimes there there is and I think a lot of times there's a lot of incentives in professional fighting too for people who want to do that? And we come up with all sorts of, well, I'm trying to be exciting are you? Is that really what you came here to do is I came here to win and I think that anyone that, that's really successful came here to win and if it ends up being exciting, well, that's fantastic. I hope that people enjoy watching something and that's great. But that's a qualitative assessment anyway. You know, you want to also be able to, you know, live the rest of your life. I think it's easy, you know, all of these Meldrick taylor, I'm a big boxing fan, Meldrick taylor, excellent fighter, um came this close, uh, to a world title and was stopped with, like he was in a fight that he was winning with seconds remaining, literally seconds remaining and they probably could have just let it go and he would have been world champion and it was brutal if you ever watched legendary nights like HBO Boxing show, it's great, but uh it's heartbreaking, it's absolutely heartbreaking and also like the beating that he absorbed in that fight, change them for the rest of his life. And also, you know, don't think he'd never been hit before, but it was one of those, we go, it's all fun and games until you can't remember your name at age 44 years old and I didn't come here, what did patent saying? Nobody, nobody wins a war by dying for his country and make the other poor bastard die for his. And I think that that's kind of what we're shooting for and you know, the lionization of absorbing damage and that not being a big deal. Like you hear that all the time. So and so can take shots that would put a lesser fighter down. What does that even mean? You know, like, so let me get this straight. Your ability to absorb damage is a part of you. I mean, I guess that don't get me wrong, that is an attribute that's nice to have if you if you need it. But there's plenty of people that actually have really porous defense that are just very, very difficult to hurt for whatever </s>

<s>[INST] in real time with him. I have noticed that you have an allergic reaction [/INST] to confabularization. Confabulation. </s><s>[INST] Confabulation, confabulation. That if somebody says something a little micro-untruth [/INST] it really stops your brain. Here I'm not talking about micro-untruths, I'm just talking about making up things out of whole cloth. So it's like, if someone says something, well, what about, and then the thing they put at the end of that sentence, it's just a set of pseudo facts that you can't possibly authenticate or not in the span of that conversation. Whether it's about UFOs or anything else, they will seem to make you look like an ignoramus when in fact, everything they're saying is specious, whether they know it or not. I mean, there's some people who are just crazy, there's some people who are just bullshitting and they're not even tracking whether it's true, it just feels good, </s><s>[INST] and then some people are consciously lying about things. But don't you think there's just a kind of jazz masterpiece of untruth that you should be able to just wave off by saying like, well, none of that is backed up by any evidence and just almost like take it [/INST] to the humor place and then. But the thing is, the place I'm familiar with doing this and not doing this is on specific conspiracies like 9-11-truth. So because of what 9-11 did to my intellectual life, I mean, it's really just, it sent me down a path for the better part of a decade. Like I became a critic of religion. I don't know if I was ever gonna be a critic of religion, right? But it happened to be in my wheelhouse because I spent so much time studying religion on my own and I was also very interested in the underlying spiritual concerns of every religion. And so I was, I devoted more than a full decade of my life to just, what is real here? What is possible? What is the nature of subjective reality and how does it relate to reality at large? And is there anything to just, who was someone like Jesus or Buddha? And are these people frauds? Are these just myths? Or is there really a continuum of insight to be had here that is interesting? So I spent a lot of time on that question </s><s>[INST] through the full decade of my 20s. And that was launched in part by 9-11-truth or? [/INST] No, but then when 9-11 happened, I had spent all this time reading religious books, understanding, empathically understanding the motivations of religious people, right? Knowing just how fully certain people believe what they say they believe, right? So I took religious convictions very seriously and then people started flying planes into our buildings. And so I knew that there was something to be said about that. Allegedly. The core doctrines of Islam, exactly. So I went down, so that became my wheelhouse for a time, terrorism and jihadism and related topics. And so the 9-11-truth conspiracy thing kept getting aimed at me and the question was, well, do I want to debate these people, right? Like? Alex Jones, perhaps. Yeah, so Alex Jones I think was an early purveyor of it, although I don't think I knew </s><s>[INST] who he was at that point. [/INST] Allegedly. </s><s>[INST] Yeah, like Alex Jones, perhaps. [/INST] Yeah, and privately I had some very long debates with people who, one person in my family went way down that rabbit hole. And I just, every six months or so, I'd literally write the two hour email that would try to deprogram him, however ineffectually. And so I went back and forth for years on that topic with, in private with people. But I could see the structure of the conspiracy. I could see the nature of how impossible it was to play whack-a-mole sufficiently well so as to convince anyone of anything who was not seeing the problematic structure of that way of thinking. I mean, it's not actually a thesis. It's a proliferation of anomalies that don't, you can't actually connect all the dots that are being pointed to. They don't connect in a coherent way. They're incompatible theses that are not, and their incompatibility is not being acknowledged. But they're running this algorithm of things, things are never what they seem. There's always malicious conspirators doing things perfectly. We see evidence of human incompetence everywhere else. No one can tie their shoes expertly anywhere else. But over here, people are perfectly competent. They're perfectly concealing things, like thousands of people are collaborating inexplicably. I mean, incentivized by what, who knows? They're collaborating to murder thousands of their neighbors, and no one is breathing a peep about it. No one's getting caught on camera. No one's, no one's breathed a word of it to a journalist. And so I've dealt with that style of thinking, and I know what it's like to be in the weeds of a conversation like that. And the person will say, okay, well, but what do you make of the fact that all those F-16s were flown 800 miles out to sea on the morning of 9-11 to do an exercise that hadn't even been scheduled for that day, but it was, and now all of these, I dimly recall some thesis of that kind, but I'm just making these things up now, right? So like that detail hadn't even been scheduled for that day, it was inexplicably run that day. So how long would it take to track that down, right? The idea that this is anomalous, like there was a F-16 exercise run on it, and it wasn't even supposed to be run that day, right? Someone like Alex Jones, their speech pattern is to pack as much of that stuff in as possible at the highest velocity that the person can speak. And unless you're knocking down each one of those things, to that audience, you appear to just be uninformed. You appear to just not be, wait a minute, he didn't know about the F-16s. Yeah, sure. He doesn't know about Project Mockingbird, you haven't heard about Project Mockingbird? I just made up Project Mockingbird, I don't know what it is, but that's the kind of thing that comes tumbling out in a conversation like that. That's the kind of thing, frankly I was worried about in the Covid conversation, because not that someone like Brett would do it consciously, but someone like Brett is swimming a sea of misinformation on social, living on Twitter, getting people sending the blog post and the study from, you know, the Philippines that showed that in this cohort Ivermectin did X, right? And like to actually run anything to ground, right? You have to actually do the work journalistically and scientifically and run it to ground, right? So for some of these questions, you actually have to be a statistician to say, okay, they use the wrong statistics in this experiment, right? Now, yes, we could take all the time to do that, or we could at every stage along the way in a context where we have experts we can trust go with what 97% of the experts are saying about X, about the safety of mRNA, about the transmissibility of COVID, about whether to wear a mask or not wear masks. And I completely agree that that broke down unacceptably over the last few years. But I think that's largely a social media and blogs and the efforts of podcasters and sub-stack writers were not just a response to that, I think it was a symptom of that and a cause of that, right? And I think we're living in an environment where we've basically, we have trained ourselves not to be able to agree about facts on any topic, no matter how urgent, right? What's flying in our sky? What's happening in Ukraine? Is Putin just de-nossifying Ukraine? There are people who we respect who are spending time down that particular rabbit hole. Like this is, maybe there are a lot of Nazis in Ukraine and that's the real problem, right? Maybe Putin's not the bad actor here, right? How much time do I have to spend empathizing with Putin to the point of thinking, well, maybe Putin's got a point and it's like, what about the polonium and the nerve agents and the killing of journalists and the Navalny and like, does that count? Well, no, listen, I'm not paying so much attention to that because I'm following all these interesting people on Twitter and they're giving me some pro-Putin material here and there are some Nazis in Ukraine. It's not like there are no Nazis in Ukraine. How am I going to weight these things? </s>

<s>[INST] essential, very, very crucial to human existence. I mean, I'd love to hear what you think, but you don't see religion and philosophy and mythology as just a continuous spectrum. [/INST] Yeah, so religion is a primitive form of philosophy. It's pre-philosophical. Where I thought Rand was going to go, and he didn't go, was that I think, I agree with what he was going to say, Rand was a mythologizer. In certain specific contexts, Atlas Shrugged is a myth. It's one thing to sit down and say, these are the people who move us forward. These are the values that are important. When you experience it through a story, through a movie, through a TV show, a poem or a painting, it affects you in a very visceral, very different way. Talk about American history. You have the founding fathers, then you have the myth of the founding fathers. Now, unfortunately, the term myth often means lie. But it could mean, in a useful sense, an abstraction to help you systematize and concretize ideas. So you have the myth of Reagan, you have the myth of Thatcher. The reality often falls very short. But when you look at how these different figures are mythologized, not only is it very inspirational on a personal level, very motivating on a personal level, it's also a great way to concretize ideas. Because just how humans think, it's one thing think about ideas. But when you see someone who embodies these ideas, Miss America, you know, I was saying earlier, I hadn't asked her on my show. These people might be jerks. But when you look at them, one specific aspect of their life and you extrapolate it, that can be to anyone very motivating. And it's very important for people to have the belief that happiness and achievement is possible. Because it's very hard to keep that in mind, especially if you're depressed, if you're anxious, you're unemployed, you don't have a girlfriend, you think it's gonna be like this forever. And then you look at someone's story. And they're like, you know what that astronaut interview Clayton Anderson, he applied 13 times, didn't get a callback, applied the 14th time, got a callback, didn't get the job 15 times you get the job, he talks to kids. And he goes, Listen, apply 13 times. Even if you don't get the callback, you'll still feel I'm doing something. And having heard him and the myth of Clayton Anderson, this is going to tell people, yeah, you know what, that could be me. You don't think you don't think absolutely. And it's not just happiness. It's, it's, it's the fact that virtue works. Yeah, that the integrity. I mean, what's what's the power of the fountain? I know you love the fountain. Yeah, part of the power of the fountainhead is how it works, absolute commitment to integrity. He is committed to integrity, and he gets any and he's happy, right. And it's very rare in life to see that, to actually see a concrete of that. And it's very hard to hold it in your mind. Yes, I'm gonna be stuck in the quarry, or I'm gonna be stuck doing this horrible job. But if I stick to my principles, I'm going to be how it works. Now I've got that concrete. I know I can, I can immediately relate to that success. So I think art is essential. And I think in a sense, what we do to Thatcher and Reagan is art. You have to be careful in true stories, not to diverge too far from reality because then when you discover the reality, you don't want to whitewash it. And particularly when it has political implications, and then it's really bad. So particularly with Reagan and Thatcher, you have to be careful, because they want anyone near as good as people try to make them out to be. But these are powerful, powerful, powerful stories. And people are moved by it. And the integration of emotion with reason is crucial, right? One of the one of the goals to be happy is to bring your emotions in line with your thinking. And I think that stories and arts more broadly. And I, you know, when I go and see Michelangelo's David, it does the same thing to me. You know, I can stand up to anybody, because he did. And look, he succeeded. And, and it makes sense that he could, right? I don't discover the reality. </s><s>[INST] So this is a really interesting idea of bringing your emotion in line with your thinking with your reasoning. So Ben Shapiro famously has this saying, how do you like that transition, Michael? You gave me props. I know you do. [/INST] He's not Ben, it's Ben Shapiro. Yeah. Someone is not taking your calls. Beni. I guess it's the daily don't take the caller. </s><s>[INST] Back to the island with the murder. I think we know. Murder Island. We would know who would be committing the murder. I have the suit for it. So he has the saying of facts don't care about your feelings. And that always, I've always felt badly about that statement somehow, like it was incomplete. So it's interesting too, that you mentioned, bringing your emotions in line with your thinking. Like, what do you think about that statement? [/INST] Murder Island. I got this one. What Ben is doing. Ben. Ben, what he's doing in a loose way is attacking Kantianism. Because Kant, it's almost impossible for Westerners who aren't schooled in this to understand the idea of philosophical idealism, because it sounds so crazy that you're like, these great minds of all time can't really be saying this. I must be missing something. So the idea of when we hear idealism, we think John F. Kennedy is an example, you aspire things, you think life can be better than it is. That's not what it means in a philosophical sense. In philosophical idealism, it means ideas are more real than reality. That I have this idea, then this comes along, it's the reality that isn't correct. My idea is still correct. A good example of this that you see all the time on the internet is when they refer to Mitt Romney and John McCain as rhinos, Republicans in name only. And it's like, who is more a real Republican? The nominee of the party, the senator, the governor of the party, or some person in your mind who has never existed and there's no evidence for them existing. So what Kant did is he bifurcated reality into what we see around us, the phenomenal world, but then it's inferior. The real world, the nominal world, we can't access it. Because we have eyes, we only see the thing as it appears, not as it is in itself. And because of this, everything we know is a shadow and is secondary. And that's Plato, straight out of Plato. Right. And the real reality is this realm of ideas. So when Ben is saying facts don't care about your feelings, what he is really saying is, reality comes first, your feelings have to be a response or a reaction to it. You can't say this is how I feel. This table doesn't care. You can yell at it all day long, it will still be indifferent to your emotional state, because it comes first. That's Plato. Yeah. So it's a great statement. I think he's cribbing it from Ayn Rand, in a sense. I love it, yeah. There's a sense in which he is. I mean, who popularized that kind of idea? And Ben has read Ayn Rand quite extensively. Not enough. Not enough, well. Not enough to reference her. That's with Yarmulke. So yeah, obviously. He may be read enough, but didn't understand enough. But it's absolutely reality. Reality is unaffected by your emotional state and your feelings about it. And this is a great claim against the idealism, the philosophical idealism of much of the world out there, both left and right. I think politically, culturally, the left and right are detached from reality. They live in a different dimension, in a different space that they are creating in their own minds that has nothing to do with the real world. And when they fail, they make stuff up to justify their failure. Not enough to reference her. So, so. Jack fired. Right, so this is, you know, all of really the ideas that are promulgated today on both sides are this kind of detached from reality. We're putting emotions or ideas before reality itself. But I believe that, you know, emotions are responses. They're responses to reality conditioned by our existing concepts. You're going to have to talk slowly to talk emotions to Lex because he doesn't really understand. I don't understand. </s>

<s>[INST] is no one could be in my level. You're the you're the smartest person since Abraham Lincoln that I've that I've ever seen [/INST] unlike him. I actually am honest. So so he is someone who very much swims in heretical ideas, Aristotle. Here's another thing like if you bring up that Aristotle said that some people are born to be slaves. He wasn't speaking about race. He just meant people's souls. H. L. Mencken who was a great heretic in the early 20th century figure. Uh, one of his quotes that I say all the time, which people have seen a lot in this past year, that the average man does not want to be free, he merely wants to be safe. That I think, I don't know what I am not familiar with, what mull bugs saying about slavery because his writing is ponderous. But that certainly is something I think that it's undeniable that I think more people are realizing there's a large percent of the population that is actively disinterested in freedom and the more responsibilities that entails. </s><s>[INST] Well, I mean really just the word slavery, if you want to make some kind of point or even think about the topic outside the context of this is a horrible thing that happened in the United States history and other countries history. And let's be clear, this is be very important in their slavery going on today. And then a lot of people argue that uh, sex trafficking and all those kinds of things. I mean, there's there's atrocities going on today that, you know, uh, talking about it in a way that's not immediately saying this is the most horrible thing that happened ever. You know, it's something I think about a lot is like if I want to say something controversial, I should do so with skill with care and only about things I care about. [/INST] Well, here's where I would disagree, not when I say things, I often say things that are controversial or I will say on controversial things in a controversial way, because it's a useful mechanism to alienate people you don't want around you, because if there are people who are going to be shocked by certain topics, like we should have ended World War Two, Like even as a hypothesis, they just clutched their pearls, they're like, oh, you want the holocaust to happen, I can't discuss most things with you because you're not interested in having a conversation, you're interested in your emotional response. </s><s>[INST] Yeah, I think I see things differently. Maybe it's a bit of a devil's advocate, but what in at least the modern discourse of like twitter and social media and so on, I find that if you do that, you're not actually removing the people that are not thoughtful and kind and so on, You're actually attracting loud people, like a small number of them, they come over and start yelling at you, start yelling, they're basically ruined the party by showing up and just screaming and so all the thoughtful people leave. [/INST] Well that's why you have to be a very heavy blogger. You have to block people on twitter because you have to cultivate your audience and have them. Like a lot of times people come at me, I don't care, then they'll start attacking members of my audience and then I'm like dang, I gotta block them because they've won this one because I can't have that. </s><s>[INST] Yeah, I don't know, I unnecessarily provoking people, it feels uh [/INST] it's, you see this is beta testing, you try to break the system and see what works, you put as much pressure as possible. This is very much computer stuff that you should be able to appreciate. The point being when you have a program, you're trying to intentionally sit there and do as many mistakes, see what go wrong, right. Is that not common? Yeah. Yeah, </s><s>[INST] so you're saying that that's a way to see communication with the world, as you say something un controversial and controversial way and that blocks people [/INST] or does it trigger them? Do they roll their eyes, you know what it's gonna be their emotional response or they start yelling? </s><s>[INST] The problem is the reason I can't think like this, or I can't because I'm not sure about the point I'm trying to make always like, I'm not always 100% sure that I'm right about things like, so I'm in being thoughtful, I'm afraid that I'll turn off with with an an eloquently phrased or even incorrect statement, I will do damage that can't be undone in terms of having a good conversation by the topic, so I want to be very careful about like I'm not saying, afraid, fear is not what I'm talking about. I think fear is, is uh, like not saying something out of fear is at the core of the many of the problems of the world today. But I'm just saying be say stuff with care if I'm going to touch race is a topic. It feels like you really should be deeply first have a point to make. Like you really care about a point you want to make and second think deeply about how to say that point in a way that communicates it the best and and touching. I would say, uh, listen, I've on your show, which is, which is great. I mean, I'd like to say thank you for having mentioned small Bugs are welcome. That's the uh, that's the name of the show. Thank you for having a couple of times. It's it's great to sort of get him to in this loose way to talk about different kinds of stuff. I [/INST] don't think we talk about race at all. So no, no, no, no. I'm just bringing it back to what you were asking, which is if you read the Wikipedia, the perspective is going to be, this guy talks about slavery constantly where it's completely </s>

<s>[INST] Yeah, yeah, disappear into the distance. And then you get to actually stand on mars and see and just to look you're standing on the ground and you're looking out and you see the planet from whence you came and where you might not be coming back but there's a challenge to the whole thing. Whereas the risk is tremendous and I don't know, I find that risk really compelling for some reason, but that could be just the exploration, I guess that's a genetic thing too. How much do you want to explore? There's a sense though, in which even in the best case scenario where they did get the technology to whisk you to MArs and in a fairly short period of time, it's kind of an inauthentic sense of exploration because your participation in it is no more exciting than your participation in an airline flight to a foreign country. You're basically, you didn't have anything to do with the creation of the, of the vessel. You're not in command of the vessel. You're not in any way, shape or form important to the mission. You're just a person sitting in the passenger seat and you get off in a destination the same way you would, if you flew to Singapore or London or someplace like that. Well, there's a hierarchy of, there's a leadership and then there's a bunch of people and they all have roles. You don't get to go to MArs without having a, because you made it sound like space tourism where you just pay a ticket. I, I don't, I think it's a long time before you have space tourism to MArs where you have nothing to contribute. Okay. Like you will have to go, What do you do? You go through? Like a training program? Training program and then there's, there's technical things you'll be contributing. So they would bring people, you know, in terms of agriculture. I don't know. Okay, so this is, this is better. This sounds like they're actually, they're more like explorers. Like if you, you talked before about explorers and in human history where Magellan sets off on his boat and every person on the boat had a specific function. They were, they were all into the mission in a very authentic fashion. If they weren't on the boat, the performance of the crew would somehow suffer. So this sounds much better. And just like with Magellan and I think most of the crew died. A significant number. Yeah. From yeah, from bacteria. I mean from things that are unexpected and so on. And if we discover life on MArs, I mean, who knows what that entails? Because that's like a manned mission to MArs would likely be very driven by the research to do all the kind of um exploration required to find life. Now from uh mr musk uh point of view as a developer, presumably there has to be some kind of financial incentive here too. Is there some kind of financial benefit to MARS missions? Is presumably um there wouldn't be that many people on earth that could afford a ticket to pay for the kind of research and development that would require this, is there some kind of mining on mars of minerals that would be used? I think there's a lot of answers to this, but the only honest answer is the one that looks back into human history where we did a lot of things just because we could a lot of hard things just because we could and that led to a lot of innovation that ultimately made our life better. So this is more, this is why you have Nasa, this is why you have government organizations like what's the purpose of Nasa? Nasa would answer that by saying, okay, well we're helping launch satellites up there, all that. They'll have a bunch of answers, but the reality is the programs worth funded in large part by our desire to explore the unknown and there's some aspect to which we have to all invest into that because historically speaking that has produced a lot of cool things along the way. They were totally unexpected. Like, but Nasa is funded by public funding the taxpayer. How is mr musk going to fund this? Well, currently, most of the funding was SpaceX is Nasa giving money to so they're making a competition who can, who can get our satellites, we need to go to um you know, it was for the space station to resupply the space station or we need to launch satellites up who's going to carry those quote unquote payloads. They just need. So, Nasa is paying whoever the heck wants to get kilograms of thing up into space, Why did this is Nasa's specialty? Why did they just give up on that? What they did, They realized we're mr musk came along and then Brazos and others that said we can do it for 1/10 the price. So why did the, why should the taxpayers pay for the, why don't you Nasa do what you do well, which is like test out cutting edge stuff, make sure they're safe and now that we've developed um a car, let us let us ups and Fedex, take care of doing this at scale, doing it cheaper, doing it better. I mean that's the argument and Nasa took what they realized is is it took way, way too long to do stuff when you're investing millions of dollars, billions of dollars into a project. The the bureaucracy builds up and the conservatism builds up to where your I mean you really have to test everything out. So projects take years and then you have somebody like Elon musk coming along and says, well let's do launches every every week as opposed to just throw away the rocket, will reuse the rocket. That was one of the sort of cutting edge inventions. It's a dumb obvious idea. Like Elon says, why do you throw away the place the equivalent is if you flew a plane every time you throw it away, why are we every time throwing away the plane? But Nasa tried that kind of thing with the space shuttle since the 19 seventies. And yes, well they did that with the space shuttle, but not not at the scale here, that uh there was the space shuttle was seen as this like majestic, amazing thing that requires a huge amount of investment with the Elon musk is like no, every basic rocket, it should be reusable cut, cut costs, cut costs. [/INST] Do you do you think like the more technology we have, the more advanced we become, the more specialized we need to be like, is that for that reason that now they, there's different branch, like you just explained now that they're specialized in this, but they left, you know, other </s>

<s>[INST] And that it's a natural derivation of action and speech. Okay, that's fascinating to think about sovereignty from the evolutionary perspective. And then ultimately money is the technology layer that enables sovereignty. So, you know, it's really fascinating to think about our modern human society as deeply rooted in these like evolutionary roots from the very origins of life on earth. So what, you know, some of the ideas you just mentioned, what do you see are some interesting characteristics of just life on earth that propagated to us humans? Like what ideas propagated to have roots in the evolution? [/INST] Yeah, I think one of the deepest empulsions in life is the territorial imperative. So all life is seeking to expand its dominion over space and time. And we think about, you know, again, physically with space, it's advantageous to an animal or an organism to have more territory under its control to raise offspring. So it's all about reproductive fitness at the end of the day. And then we'd also think of reproduction itself as the genetic impulse to have more, to replicate oneself across time. So it's territoriality across time in a way. And this is very common in most animals. Not all animals are territorial, but many are. And you see very interesting behaviors resulting from territoriality. This is like animal combat, you know, the reason birds sing is territoriality, a number of other things. And it's my hypothesis, and others have shared this hypothesis as well, that mankind is clearly, I think, would argue a territorial species, and that he expresses this territoriality in property rights. So property, when that word, we hear that word, we typically think of an asset. We think of, oh, this house or this stock or whatever. But property is actually the socially acknowledged relationship between a human and an asset, such that you have exclusive rights and responsibilities to a particular asset. It is not the asset itself. </s><s>[INST] So property, it's information, it's a relationship. By the way, my mind was just blown. property is information, it's not the actual asset. That's really important. Very important. That's really interesting. [/INST] Yeah, very important. That's really interesting. Yeah, and then it comes down to how do we organize ourselves such that property, that the contributions people are making are commensurate with the consideration they're receiving? if you're adding value to a piece of property, you're developing a piece of land for use, in theory, to be fair, you should have the rights to that fruit if you go out and plant a garden or whatever it may be. And this is rooted in natural law where we have rights to life, liberty, and property. Those are just the base, the fundamental layer of morality and capitalism, frankly. And you could think of, to get really primordial with it, the first capitalist in the world, just to kind of get some definitions out here, I'll say capitalism versus communism or socialism as the spectrum I'll speak on. The first capitalist in the world would be the guy, the caveman, that maybe dug a little hole for himself to shield himself from the elements, right? Maybe there was a rainstorm or a snowstorm and he dug a little enclave and he protected </s><s>[INST] himself. I thought you were going to go, because you said primordial, I thought you were going to [/INST] go back to earlier biological systems. I guess primordial for humans. For humans, yeah. And then the first communist or socialist would be someone that decided the fruits of his labor belong to him. So he would have violently encroached on that individual and taken his plot for himself, for his own use. For humans, yeah. And that's the spectrum across which capitalism in the pure sense and communism in the pure sense operate in that capitalism, each individual has the exclusive rights to the fruits of their labor. So anything they spend their time, effort, energy, creating in the world, they own the rights to that and they can trade those rights with others, other cell phone people that have done similar things. Communism or socialism would imply that other people, typically the state have the rights, at least some rights </s><s>[INST] to the value you've created. So there's this interesting moment when that first caveman, that first capitalist drew a line, a circle in this cave and said, this is mine. You could say it was free to be claimed at the time he claimed it, but it's an interesting moment when an asset becomes an asset, when space-time, as you're referring to, becomes something that now can be possessed by a human being. Is there something special about this moment? Because it feels like, first of all, in terms of space and time, it feels like there's a lot of available space-time yet to be claimed. So if we just look at the universe, right? We're talking about, there's a funny thing with Elon Musk and Mars. I think they sneaked in there for SpaceX, that nobody on Earth has any authority on Mars or any. This is a very interesting question. It seems almost like humorous at this time, but perhaps not. Perhaps there'll be sections of space, not just on planets, that are going to be even fought over. So is there something special about this moment? Because in discussing violence and respect for property, it feels like this is a special moment. Because ultimately, conflict arises when you make claims on a particular territory. It's not always in conflict where people say, when you look at Hitler or something, for example, his claim would be in many of the lands that he attacked and invaded, that this has always belonged to Germany. So is there something you could say as to what it means to own an asset or a property? [/INST] Yeah. So in the ancient days of hunters and gatherers, we could say that property was mostly a loydial title, which meant it's just whatever you can defend. So if you've got knives and daggers and satchels and maybe some pelts you've hunted, whatever you can hold and defend is yours. And there's not like there's a government to appeal to. You're just sort of a free agent operating in the wild, defending the assets you can protect on you, more or less. And what really changed the nature of property is when we get into the agricultural age. So there's a big flip where we went from just foraging and hunting all the time, constantly moving, trying to stay alive, to deciding we're going to settle here. We figured out how to cultivate crops. We can increase the population because we can harvest more energy from the sun and we can establish a longer term civilization. What happens in that transition is that we begin creating economic surplus. So for the first time in history, we have stock houses of grain to defend or maybe meat or cattle or whatever it is we're creating, we now have savings. And it's at that time when government emerges as well, because once you have savings or you have an economic surplus, you have something that other people want to steal. This one thing we'll touch on a lot today is people always want something for nothing. People are always seeking the path to get something for nothing. And I think that drives a lot of our decision making. And it actually encourages us to be innovative in a lot of ways. You could say it's our laziness that's helping us be inventive in a way. We're trying to accomplish greater results with less efforts over time, but we can cross that line in seeking something for nothing where we start to violate the life, liberty, and property of others. And that's where we shift from capitalistic society to something more communistic. And so that's what government is. It's a protection producing enterprise for the economic surplus generated by a trading society. So when people begin to trade, they create what's called the division of labor, which is a very common economic term. Basically means you're better at making hats, I'm better at making boots. If you specialize in hats, I specialize in boots and we trade, we've created a positive sum game where you and I both benefit. So we become collectively more than the sum of our parts through trade. And that's why human beings do trade because we become more energy efficient. As a result, we create more outputs per unit of input. And you can think of government in that respect. If we're looking at it, maybe in a tech sense that the economy is the trade network that generates wealth, generates innovation, generates all this whole lap of luxury we live in today that we've inherited from our forebears is from the market. It's not from a government. The government is the network security, if you will. So we're paying expenses to a vendor to protect peace, to preserve life, liberty, and property in that network so that we can have, when there's inevitably disputes over private property, we can have nonviolent dispute resolution in the rule of law. And we can have a reasonable expectation of being able to conduct commerce without violence. The problem has been that the protector tends to, they're in a monopolistic position, we would say. They tend to start abusing that position to obtain property for themselves. Again, trying to get that something for nothing. When you control, you are the security guard for the economy. The first thing they tend to monopolize is money. Because if you can control the money, you're effectively controlling people, their energy, their perceptions. And that becomes a, particularly through inflation, becomes an avenue to get something for nothing. And that you can just print more money that everyone else is forced to sacrifice their </s>

<s>[INST] So you already, you were sitting on, on a track record of successes and failures in your own mind where you had sort of already a confidence, a calm a calmness. Uh, but still was there a doubt that you can get this done, [/INST] like how </s><s>[INST] hard is it to achieve a sort of a confidence to a level where you could present it to steve and actually believe that this is doable? Like what what do you remember when [/INST] that moment I think it was after I triple checked. But I couldn't I couldn't bring anyone in right? I couldn't let anyone in on this. So it was just me. </s><s>[INST] No [/INST] no no no because I couldn't bring anybody when I mean bring anyone in on this one. It was a highly confidential program inside Apple there was like four people who knew about it, right? And so I couldn't bring anyone from Apple because I was a contractor. I couldn't bring anyone else from the outside world. I'm working for Apple and I'm under this crazy N. D. A. Right in this contract. So it was just It was so I'm I'm doing this oh and at the same time I'm also buying every competitive product MP three player and tearing them all apart, right, tore them all apart and looking at them and trying to learn from those as well. So it was all of this stuff in six weeks. So I didn't sleep right? But I was like because I was trying to make this from I was I was envisioning using this since the Nino right? And I was like oh my God right? But there was another doubt that I had and it wasn't just could you make the product but could Apple actually have the, the balls to make it because Apple was not the same company That you know it today in 2001 </s><s>[INST] really? It was cautious, conservative [/INST] careful. It was barely break even. It was $4 or $5 billion dollar company. </s><s>[INST] So the guts required, there's not necessarily in the innovation, it's like, this is going to cost a lot of money and we're going to potentially lose all of it because it'll be a flop. [/INST] Well, there's not just that, but there was only the Mac and the Mac wasn't doing very well. Yeah, There was less, it was about a 1% only in the us market share for the Mac, right? The company was in debt. Bill Gates had to give him a loan, </s><s>[INST] right, [/INST] Michael Dell at the time was saying, shut down the company and give the money back to the shareholders. So this is not the company that you know that people, oh my God, the iphone came out. It's a very different level of confidence and financial situation that the company was in versus the ipod. </s><s>[INST] So given that what was the conversation when you finally presented to steve, what was that conversation like? [/INST] The conversation was, well, we went through, we went through it, the presentation and all that stuff happened and he, he was just like, and you know, he never, he would flip through it real quick, throw the presentation aside and said, okay, let's talk about this. Right? And so we went through it all and one was a big conversation about Sony and Sony was the number one in all audio categories, home portable, what in the world? Okay. I had been already gone through 10 years of failure and I was like, wait a second. How are we going to compete with Sony? And I was always worried that Sony was gonna come out with whatever it was, they were going to come out with their MP three player and that was it game over. Right. And so I was like steve. And and this is why it took me </s><s>[INST] four [/INST] weeks to finally sign on to join Apple after he greenlighted the ipod program in that meeting was because I had built other things in the past at phillips the nino and below. But they didn't know how to sell it or market it, they didn't know how to retail it. Right. So I was like, we could build this and I was like steve, I'm pretty sure I can build this. I've done this before. But how are we going to sell it? You have all your marketing dollars on the Mac. And he looked at me and he goes, you build this with a team and our team and Apple over me, right? And I dedicate that we will make sure that at least two quarters of all marketing dollars will only go to this product and nothing else, </s><s>[INST] wow. [/INST] Right. that was Mac was the lifeblood of all revenue of the company. So </s><s>[INST] steve saw something special here. [/INST] Exactly. And he said I'm going to commit all the marketing dollars if you can deliver the experience that we're all talking about, if we can do that. And that was Jeff Robin as well because Ipod would have never happened without itunes. You know, people don't understand that was a bundle, you couldn't do one without the other and vice versa. So Jeff and I were, you know, if Jeff and you can present and bring that um bring that experience to life, I will put all the marketing dollars behind it. </s><s>[INST] When did the marriage of ipod and Itunes sort of, what was that birth of ideas that made up itunes? [/INST] Itunes existed before the ipod. Okay, And so Jeff Robin had his company. Oh man, I can't remember the name but it was bought, he was making a MP three player app for the Mac. Mhm. Steve saw it because there was MP three player apps like winamp and other things that were on the PC real player and steve saw that going on and saw that Jeff and his small team had this, this, I can't remember sound something anyways, he bought that and that became the basis of itunes and then Jeff ran all of Itunes And so what happened specifically there was they were starting to hook up to all these 3rd party MP three players because there's a lot of korean, the mp man, like Walkman, but mp man, all these and they were trying to hook them up and they were like, these are horrible experiences and through that and they said Itunes was something that was gonna help grow the Mac base because we were trying to get more people on the Mac. So this program would be a great new thing you could add to the Mac and there was also internet connectivity at the time for the imac And so they did that and then they're trying to do these, these hookups. They weren't going well. And that's when they said we need to build our own or steve said we need to build our own since these are such horrible experiences, people don't want to just burn cds from itunes, we need to get that music on the go. But in an apple fashion, that's when I was called to come in to do that. The ipod thing after the six weeks then he already envisioned, I'm sure he had it envisioned because they were trying to do this thing Okay, now that's it Itunes, what, you know, it wasn't called Ipod yet. You know, what would become the ipod that is going to be the thing that then propels apple into this new thing because you've been bringing all these music lovers in that are going to need their their next generation or Sony, Walkman Version 2.0 </s>

<s>[INST] Yeah, me too. Yeah. It's it's a cool it's a it's a virtual hug. [/INST] I think it's like I was just listening to something about </s><s>[INST] the [/INST] different Russian writers. I was mentioning him to you this academic, his name is Gary saul Morson and he studies Russian literature and he was talking about, I don't know if I'll be able to get this right, but basically that people misunderstand a work like anna Karenina, him </s><s>[INST] and that [/INST] we think of it as telling us that you're supposed to live, you know, you're supposed to have like these grand, tempestuous romances that might end in death or despair or whatever it is, but you know, you should be in it for the intensity of the emotion. And he's saying actually that's not that's exactly not what Tolstoy was saying, that actually it was the opposite that he was really making, he was really advocating for everyday life. He was saying, it seems from every day, like he was juxtaposing anna Karenina with all these other couples who are just living happily and quietly day by day. And that was what he believed was the ideal. So as as opposed to the grand rush and as opposed to the intensity, </s><s>[INST] is there a uh, a depth is there a romance? It's just the day to day. [/INST] Don't get don't </s><s>[INST] get distracted by the dopamine roller coaster ride of the Grant romantic notions [/INST] and enjoy it while it's happening because those are life experiences also, but not to mistake those for being everything. </s><s>[INST] Where is he from? [/INST] He's a professor at Northwestern </s><s>[INST] Northwestern [/INST] and apparently his lectures are like the most popular on campus </s><s>[INST] people love him. Gary saul Morrison is an american literary critic and Slob Ist. He's particularly in over his scholarly work on the great Russian novel lists Leo Tolstoy and Fyodor dostoevsky Morrison is Lawrence the professor in the arts and Humanities at Northwestern University. Wow. And there's a lot of incredible work and then I'm sure looking through the lens of Russian literature and the romance of all of that, he's looking at modern at the modern world. [/INST] Yeah, I think you should have him on your podcast </s><s>[INST] and quiet flows the vodka or when Pushkin comes to shove the curmudgeons guide to Russian literature and culture. This is one of the silly books he has on the list. Okay, cool. Oh [/INST] no, I was just saying, yeah, like I find that when I take photos on my phone, I hardly ever take photos at the moment, you're supposed to like everybody's gathered for some event. I'll forget to take the photo, but I take a lot of like scenes from everyday life because that's what I actually want to remember in the end. </s><s>[INST] Yeah, yeah, I'm the same the same. It's actually concerning because it's bad for productivity because I love everyday life so much. Then why why do any ambitious big thing. [/INST] Your productivity is pretty good. I don't know that you have to worry about </s><s>[INST] it. I do. So I want to launch a business, You know, I have, I have a dream outside, this is like a fun side thing that, you know, I wanna, there's been a lifelong passion anyway, that's a, I like building, I like building stuff and I haven't been doing that as much as I would like. That's because largely because I like sitting in silence and enjoying the beauty that is just nature and life and when there's people, there's people, I love people, I love everything. And so when you love everything, why go through hell to build a company? [/INST] Yeah, it's a valid question. I mean, I think you have to have a really good reason for wanting to do </s><s>[INST] it, but then your heart calls you for the certain, sometimes you look out into the mountains and you say for some reason I long to go there even if it means leaving the tribe and putting yourself in danger and doing stupid shit, that's a human, um, imperative for exploration. [/INST] Yeah, absolutely. Like when we were talking about, um, you know, this idea of longing being like the source code of humanity, I think that's also the source code of our creativity. It's a, it's the same logging for Eden. It's like you're always reaching for something that you want to get to you or that you want to build. It's the best of us. </s><s>[INST] What do you think? Uh, you've read about creativity and sadness, You practically speaking, how should we leverage sadness for creativity is that sort of in the artist domain, in the writer's domain, in the engineering domains and so on. [/INST] It's definitely in those domains, but it's in all domains. Um, you know, we're all going to face pain in this life at some point and we all have the ability to weather it and withstand, withstand it and live with it for a bit and then try to transform it into something that we find beautiful. Um, you know, and it's very easy to, to notice the grandeur of like the, you know, the painting hanging on the gallery wall or the new company that's just been created. But it takes 1000 different forms, right? You know, you could bake a cake or like </s><s>[INST] in [/INST] the wake of the pandemic, we've had more people applying to medical school and nursing school And after 9-11, you had people applying for jobs as firefighters and teachers. So there's something in the human spirit that takes pain and turns it into meaning when we're at our best and when we're not at our best, we deny the pain and then take it out on ourselves and on other people. So there's a kind of fork in the road what to do with it. But we know, I mean there's all these studies that I go through in the book. Like there was one, um, where the researchers had people watch different movies, like happy movies, sad movies, bittersweet movies and they found when people watched Father of the Bride, which is like the ultimate bittersweet. You know, you're walking your daughter down the aisle kind of feeling that was they would give them creativity tasks after watching these different movies. And the people who had been primed for bittersweetness were the most </s>

<s>[INST] yeah, I've seen a few things written about you. The things I've seen a pretty good writing. Um you know, most ai related things make my eyes roll. Like when the press like question What kind of sound is that actually okay. It sounds like it sounds like a truck. Okay. Sounds like an elephant. At first I got excited. You never know. This is 2020. I mean it was such a human story. It was well written. Uh, well researched. I forget what, where I read them. But so I'm glad somehow somebody found you to be the good writers were able to connect to the story. There must be a hunger for this story. [/INST] It definitely was. And I don't know what happened. But I think, I think the idea that he could bring back someone who's dead and it's very much wishful, magical thinking. But the fact that you could still get to know him and you know, seeing the parents for the first time talk to the chat bought and some of the friends. And it was funny because we have this big office in Moscow where my team is, you know, our Russian artists working out off. And I was there when I wrote, I just wrote a post on facebook like hey guys, like I built this if you were just, if this all important, if you want to talk to roman. And I saw a couple of his friends are common friends, like you know, reading a facebook, downloading, trying and a couple of them cried and it was just very not because it was something, some incredible technology or anything. It made so many mistakes. It was so simple. But it was all about, that's the way to remember a person in a way. And you know, we don't have, we don't have the culture anymore. We don't have you know no one's sitting Shiva, no one's taking weeks to actually think about this person and away from me that was it. So that was just they day in day out thinking about him and putting this together. Um So that was that just felt really important that somehow resonated with a bunch of people and you know I think some movie producers bought the rights for the story and just everyone was so has anyone made a movie? I don't think so. Um There were a lot of T. V. Episodes about that but not really </s><s>[INST] is that still on the table? [/INST] Which is really that's cool. </s><s>[INST] You're like a young uh you know like that because you see like like a steve jobs type, let's see what happens there sitting on it. [/INST] But for me it was so important as roman was really wanted to be famous. He really badly want to be famous. He was all about like make it like fake it to make it, I want to you know want to make it here in America's wall and he couldn't and I felt you know that was sort of paying my dues to him as well because all of a sudden he was everywhere and I remember case Newton who was writing the story for the verge, he was uh he told me hey by the way I was just going through my inbox inbox and I saw I search for roman for the story and I saw an email from him where he sent me his startup and he said, I really like, I really want to be featured in the verge, can you please write about it or something? Like pitching the story? And he said, I'm sorry, like that's not good enough for us or something and he passed and he said, and there were just so many of these little details were like, he would find his like, you know, and we're finally writing, I know how much uh roman wanted to be on the verge and how much he wanted the story to be written by Casey and I'm like, well that's maybe he will be, we're always joking that he was like, I can't wait for someone to make a movie about us and I hope Ryan Gosling can play me </s><s>[INST] like, you [/INST] know, I still have some things that romans still but um </s><s>[INST] that would be uh I got, this has to meet Alex Garland who wrote ex machina [/INST] and movie. </s><s>[INST] I yeah, the movie is good but the guys um better than like he's a special person actually, I don't think he's made his best work yet. Like for my interaction with him, he's a really, really good and brilliant and the good human being and a brilliant director and writer. So um yeah, so I, I hope like he made me also realize that not enough movies have been made of this kind, so you had to be made, they're probably sitting waiting for you to get famous, like even more famous [/INST] should get there. But it felt really special though, but at the same time our company wasn't going anywhere, so that was just kind of bizarre that we were getting all this press for something that didn't have anything to do with our company and but then a lot of people started talking to romans, some shared their conversations and what we saw there was that um also our friends in common, but also just strangers were really using it as a confession booth or a therapist or something. They were just really telling room and everything which was by the way pretty strange because it was a chad bought of a dead friend of mine who was you know barely making any sense, but people were opening up um and we thought we just built a prototype of replica which would be an ai friend that everyone can talk to um because we saw that there is demand um And then also was 2016. So I thought for the first time I saw um finally some technology that was applied to that, that was very interesting. Uh some papers started coming out, deep learning applied to conversations and finally it wasn't just about these, you know, hobbyist making uh You know writing 500,000 </s>

<s>[INST] Meaning like intensity of conflict, that's well put. There is competition. Doesn't it have that extra level of animosity? It's a little bit more conflict than it is. [/INST] It can. Sometimes there's personality differences. For example, like Gordon Ryan and Felipe Panner, they admire each other a lot. They respect each other's skills, but they certainly don't love each other. That's for sure. There can be certain match-up where there's more intensity. But then there's other match-ups where the two athletes come out and it's no more intense than a hard </s><s>[INST] sparring session. First of all, because I would love to look at a couple of matches with you. And before that, let me say a big thank you to Flow Grappling. First of all, helping the sport of grappling and jiu-jitsu in general by having organized footage and tournaments that show this sport in its best light to the world. And they do an incredible job with that. So if you're interested in supporting grappling as a sport, helping it grow, you should definitely support Flow Grappling. Go to their website, sign up. Also, Flow Wrestling. I'm a huge fan of wrestling. Maybe there'll be a Flow Judo at some point. Currently, I don't think they'll do any major Judo stuff. So anyway, I'm a big supporter of theirs. And I do have criticism that they know about, which is I hope they continue to improve on the aspect of making the footage discoverable and accessible, making it easy for you to do search through Google and on their website to find matches to get excited. Like if me and Joe Rogan are getting excited about a particular match, we want to be able to pull it up super quickly. We want to be able to pull up Gordon Ryan's matches super quickly from ADCC, make it super easy to show and share if we have to pay for it fine, but make it easy. And when you sign in order to sign up for Flow, it should be one click, click, not five clicks. It should be one click. It should be easy. I think it's inexpensive. If you care about grappling, it's definitely worth it. You should sign up. Anyway, my love goes out to Flow Grappling. And also my love goes out to Mo Jasm, as we said. He's the organizer of ADCC. The next one is in 2024. It should be 2024. Well, you should follow ADCC underscore official on Instagram and just send as much love towards Mo and ADCC in general. Like I said, the most prestigious, it's like where the best grapples in the world show up. And the magic happens. It's like some of the most historic matches in grappling in Jiu-Jitsu ever happened on that stage. Anyway, if I could talk about some of the interesting performances for the athletes you coached, you post on Instagram. Let's start with Gordon Ryan. Gordon Ryan, ADCC 2022. The greatest event in grappling history is over. New stars emerged, established stars shown bright again, but one man stood above all like a colossus. Gordon Ryan. You have a way with words, John Donner. I have seen many incredible feats of grappling, but I've never saw a performance like this. For many, Mr. Ryan is a polarizing figure in the sport. For many others, an inspiration to look up to. But after this weekend, there was no disagreement amongst haters and fans about his merit. He is the best ever. It was a long and difficult journey to ADCC 2022. Just one year ago, and so on as you told the story, it was a virtuoso performance of unmatched technique, preparation, and confidence. No one else can claim credit for this achievement. This was his and his alone. No one else today brings together technical depth, tactical insight, and confidence to use them on stage as he does. I had many students, but I only won Gordon Ryan. And I think Gordon responded, all this is true besides the credit that sits with you. Thank you. And a heart emoji. Very nice. So anyway, that's as a way of introduction to Gordon Ryan. Can you take me through his set of performances and maybe any matches that stand out? So he competed in his division, which is the plus 99 kilos, [/INST] and in the super fight against Andre Gova. That's correct. This was in fact the first time in history that this was allowed. For your listeners who don't follow grappling, we may have been very rude and just throwing a lot of stuff at you without explaining ourselves. First of all, ADCC is like the Olympics of grappling. It occurs every two years. You can either qualify for the event through winning matches in a qualification process, or you can be invited. The only people who get invited are either former winners or people in the sport who are just widely recognized superstars who bring some kind of brand value, who have proven in the past that they have what it takes to compete at that level. In this format, there are two kinds of matches. There are weight division matches in which you compete against people, roughly your own size and weight. There is an open weight where anyone of any size can enter. So you can have very small people fighting very large people. And there is a second category called a super fight where established champions who have won previous open weight tournaments fight each other in one-off battles, one athlete against another. So in most of the matches, you will fight repetitively over time towards a gold medal. But in one category, you fight one fight, the so-called super fight, which is usually the headline fight of the event. Traditionally, if you were in the super fight, you could not compete in the weight categories. It was seen as too risky because you might get injured during the weight category, or you might have to fight for very tough fights in a row and get exhausted so that you're ineffective during the main event of the show, the super fight. So throughout its history, ADCC has always resisted the idea of an athlete being allowed to do both weight category and a super fight. It's never happened before. Gordon Ryan requested to be able to do this because of his extraordinary stature in the sport. The ADCC organization granted his request. That was the first time ever. In addition, Gordon Ryan would be fighting to be the first person to win three gold medals in three different weight categories. This has never been done before. So it was a huge event on Gordon's part. Bear in mind also that prior to this event, he had fought just a month and a half earlier against a former ADCC open weight champion, Felipe Pena, who had defeated him in the past in a completely different rule set and then previously that against the current world champion. So there'd been a buildup to this. So he had been very active coming up to the event and then he went in to fight arguably the greatest ADCC champion of all time, Andre Galván, which would occur late on Sunday and would have to fight the toughest people, including the possibility of fighting his nemesis, Felipe Pena, in the weight division prior to getting to the super fight. So there was genuine concern here that he may have completely overstepped himself. The biggest concern I had as a coach, and I'm sure the organizers, Mo Jasim, must have had the same concern is that he would get injured or exhausted fighting in his weight division. There were two athletes in particular, Felipe Pena, who had given Gordon a very tough 40-minute match in a no-rules setting shortly before ADCC, and his former training partner, Nick Rodriguez, who were expected to give Gordon very, very tough matches if they came up against each other. So there was a genuine concern that Gordon may burn himself out before he even got to fight the guy who most people believe is the greatest ADCC champion of all time. So our concern was how do we manage this? So what we looked for is extremely efficient methods of reducing the time of the matches, making the matches as short as possible. Our favorite way to fight bigger, stronger athletes, and I think Gordon was the lightest athlete in his weight division. Everyone goes, oh, Gordon's so big and strong, it's actually quite light. I think he was outweighed </s>

<s>[INST] But to find that out, that [/INST] means we'd have to literally sacrifice </s><s>[INST] embryos. [/INST] Probably so and which itself has of course, uh </s><s>[INST] you know, a lot of complications, [/INST] ethical considerations, some people just wouldn't it's a nonstarter </s><s>[INST] for lots of people. [/INST] So but we do know that </s><s>[INST] the sperm [/INST] survives earlier said nobody cares about sperm apparently. </s><s>[INST] Now [/INST] we're doing several studies on autism risk for fathers and sperm and you know it's really easy to get sperm. I'll just tell you its </s><s>[INST] people say you're [/INST] helping us, what we're </s><s>[INST] asking for a friend. [/INST] Um </s><s>[INST] Okay cool. Are you [/INST] involved in action one </s><s>[INST] asking to experiments [/INST] like what what </s><s>[INST] does is [/INST] your lab directly </s><s>[INST] or indirectly involved with in terms of experiment [/INST] design. What are you excited </s><s>[INST] about different [/INST] experiments that </s><s>[INST] are happening out there? Some of them [/INST] were doing a lot of the direct training for the cruise is really saying how do you </s><s>[INST] how do you do a [/INST] modern genetics experiments for the </s><s>[INST] Axiom? One inspiration [/INST] for an axiom one. We're also collaborating with Trish which is the </s><s>[INST] translational research [/INST] arm for Nasa that's in </s><s>[INST] Houston. And there [/INST] it's a lot of sharing of samples and data </s><s>[INST] for all these missions [/INST] basically for all </s><s>[INST] the commercial spaceflight [/INST] missions there'll be a repository where you can look at the data from the astronauts. You can look at some of the genetic information, some of the molecular changes. So that's being built up with Trish which has been fabulous collaboration between Cornell </s><s>[INST] and Trish. [/INST] But the other thing we're doing is for </s><s>[INST] access to is training [/INST] them. How do you for example if you want to look at a </s><s>[INST] virus you can take a swab [/INST] of something extracted sequence it and say do I have omicron or do I have a different virus And we're </s><s>[INST] doing the exact same [/INST] work in flight? But we're having the astronauts do the extraction, the sequencing and the analysis </s><s>[INST] of all the [/INST] molecules. And so one of the common occurrences herpes is reactivated often into spaceflight </s><s>[INST] oral herpes. So [/INST] you can see that viral reactivation is one of the biggest kind of mysteries in </s><s>[INST] space flight, where [/INST] the immune system seems to be responding a </s><s>[INST] lot as active. The body's [/INST] really perturbed, but </s><s>[INST] viruses start shedding again [/INST] and it's really and this </s><s>[INST] happens clinically again. We see this for [/INST] like for example, hepatitis C or </s><s>[INST] hepatitis B. You [/INST] can get infected with it and it can stay </s><s>[INST] in your body for decades and [/INST] still kind of be hiding in the </s><s>[INST] body. And in this case we see it in [/INST] spaceflight. Herpes comes back. So we want to figure out is it </s><s>[INST] there first of all and then when [/INST] is it happening </s><s>[INST] and characterize it better? But have [/INST] the astronauts do it themselves </s><s>[INST] rather than collecting it and bring [/INST] it back to Earth and figuring out later, we could see in real </s><s>[INST] time how it's happening [/INST] and then also look at their blood. We'll see what what is changing in their blood in </s><s>[INST] real time with these these new [/INST] sequences. So I'm excited about the genomics and space if you will. So clearly somebody that </s><s>[INST] loves robots. [/INST] Um How many robots are up there in </s><s>[INST] space that helped with the experiments? [/INST] Like what? How </s><s>[INST] much technology [/INST] is there would you </s><s>[INST] say? Is it [/INST] is it really a manual </s><s>[INST] activity or is there a lot [/INST] of robots helping out </s><s>[INST] good questions so [/INST] far. It's almost all manual because the robots have to all undergo the destructive fire and vibrational </s><s>[INST] testing. So if you have a million [/INST] so excited. So if </s><s>[INST] you can get [/INST] that thing is a lot less than a million. But </s><s>[INST] we're definitely gonna [/INST] test it out for the </s><s>[INST] and I guess [/INST] in which order and they have </s><s>[INST] to just separate for each [/INST] one vibration fire uh note </s><s>[INST] note to self [/INST] do fire testing </s><s>[INST] for the legged robots [/INST] and the destructive testing. </s><s>[INST] That would be fascinating. [/INST] I wonder if </s><s>[INST] any of the focus on working with did that kind of testing on the materials like what breaks first with the robots question [/INST] And also the big question. So </s><s>[INST] what's interesting about this for axiom and [/INST] Phillies, commercial spaceflight areas. </s><s>[INST] If you can fund [/INST] it, you could fly it. Right? So if you have to say like I want to fly these series </s><s>[INST] of robots up [/INST] because I think they could help build something or they could help </s><s>[INST] measure or repair the spacecraft or [/INST] you have to come up with a good reason. Yeah. Well for Nasa you have to be good. But I think for private space </s><s>[INST] flight you could have the reason is [/INST] I'm curious and that could </s><s>[INST] just exactly like and [/INST] I've got a private fund or you've got your own money </s><s>[INST] and then you pay [/INST] uh per kilogram essentially. And I mean there are some things you </s><s>[INST] can't say I want to send [/INST] a nuclear bomb up there. I'm </s><s>[INST] curious. I don't think that would [/INST] fly, but there's probably rules in terms of free floating </s><s>[INST] robots, right? They probably [/INST] have to be attached. I have to like it's an orchestra that plays together </s><s>[INST] all the experiments that are [/INST] up there. There's probably it's not silos, it's not separate, separate kind of things. But you're saying </s><s>[INST] it's all mostly manual, [/INST] how much electronics is there in terms of data collection in terms of all that kind of stuff, a lot of electronics. So a lot of its tablets, there's laptops up there. There are, you know, the whole space station is running and tumbling on electronics. Actually. One of the biggest </s><s>[INST] complaints astronauts [/INST] have is is </s><s>[INST] sleeping up there. It's hard, not only because you're in zero gravity, [/INST] but there's a consistent loud </s><s>[INST] hum of the space station. [/INST] There's so many things active and humming </s><s>[INST] and moving [/INST] That are keeping this station alive. The co two scrubbers, all </s><s>[INST] the instrumentation, [/INST] it's it's loud. So I think it is a </s>

<s>[INST] So how does uh evolutionary competition apply to the world of neural networks? Because I've seen quite a bit of work from you and others on the in the world of your evolution. So maybe first, can you say, what is this field? [/INST] Yeah, your evolution is a combination of of uh neural networks and evolution computation in many different forms. But the early versions were simply using evolution the way um as a way to construct the neural network instead of say uh stochastic gradient descent or back propagation, because evolution can evolve these parameters, weight values in a neural network just like any other string of numbers. You can you can do that. Uh and that's useful because some cases you don't have those targets that you need to back propagate from, and it might be an agent that's running a maze or a robot playing a game or something. Uh you don't, again, you don't know what the right answer says, you don't have back, but this way you can still evolve in your own head and neural networks are really good at this task because they recognize patterns and they generalize interplay between known situation. So you want to have a neural network in such a task, even if you don't have a supervised targets. So that's the reason and that's a solution. Uh and also more recently now, when we have all these deep learning literature, it turns out that we can use evolution to optimize many aspects of those designs. The deep learning architectures have become so complex that there's little hope for as little humans to understand their complexity and what actually makes a good design. Uh and now we can use evolution to give that design for you and it might be mean, um optimizing hyper parameters like the depth of layers and so on, or the topology of the network, um how many layers, how they're connected, but also other aspects like what activation functions you use where in the network during the learning process or what loss function you use. You can generalize that generate that even data augmentation all the different aspects of the design of deep learning experiments could be optimized that way. Um So that's an inter interaction between two mechanisms. But there's also um when we get more into congress science and the topics that we've been talking about, you could have learning mechanisms to level time scales. So you do have an evolution that gives you baby neural networks that then learn during their lifetime. And you have this interaction of two time scales. And I think that can potentially be really powerful. Um Now in biology we are not born with all our faculties, we have to learn, we have a developmental period and humans it's really long. Uh And most animals have something and and probably the reason is that evolution of D. N. A. Is not detailed enough plentiful enough to describe them. We can't describe how to set the brain up. Um But we can evolution can decide on a starting point and then have a learning algorithm that will construct the final product. And this interaction of you know intelligent uh Well uh evolution that has produced a good starting point for the specific purpose of learning from it. Uh with the interaction of with the environment that can be a really powerful mechanism for constructing brains and constructive behaviors. </s><s>[INST] I like how you walk back from intelligence. So optimized starting point maybe. Uh, okay, there's a lot of fascinating things to ask here. And this is basically this dance between neural networks and evolutionary competition. Could go into the category of automated machine learning to where you're optimizing whether it's hyper parameters of the topology or hyper parameters taken broadly, but the topology thing is really interesting. I mean, that's not really done that effectively or throughout the history of machine learning has not been done. Usually there's a fixed architecture, maybe there's a few components you're playing with, but to grow a neural network essentially the way you grow in that organism is really fascinating space. How, how hard it is. It do you think to grow a neural network and maybe what kind of neural networks are more amenable to this kind of idea than others seem quite a bit of work on recurrent neural networks? Is there some architectures that are friendlier than others? And is is this just a fun, small scale set of experiments or do you have hope that we can be able to grow um, powerful neural networks? [/INST] I think we can and most of the work up to now is taking architecture that already exists that humans have designed And tried to optimize them further and you can totally do that a few years ago we did an experiment. We took a winner of the uh, image captioning competition. Um, and um, the architecture and just broken into pieces and took the pieces and and that was our search back, see if you can do better and we indeed good 15% better performance by just searching around the network design that humans had come up with a really nails and others. Uh so but that's starting from a point of point that humans have produced but we could do something more general. It doesn't have to be that kind of network. The hard part is just a couple of challenges. One of them is to define the third space, what are your elements? Uh and how you put them together? Uh and the space is just really, really big. So you have to somehow constrained and have some hunts what will work because otherwise everything is possible. Um And another challenge is that in order to evaluate how good your designers, um you have to train it. I mean you have to actually try it out and that's currently very expensive. Right? I mean, deep learning networks may they taste taste the train Well, imagine you having a population of 100 have to run it for 100 generations. It's not yet quite feasible, computational e um it will be but but also there's a large carbon footprint and all that. I mean, we're using a lot of computation for doing it. So intelligent methods. Uh an intelligent I mean, um we have to do some science in order to figure out what the right representations are and right operators are. And how do we evaluate them without having to fully train them? And that is where the current researches and we're making progress on all those fronts. Um so, so yes, there are certain architecture demo m unable to that approach. But also I think we can create our own architecture and all representations that are even better. </s>

<s>[INST] that is interesting levels of humor and uh, insight there on both of those, [/INST] the difference between human move and engine and like what an engine move is is I think two things, number one, a computer move is outlandish in its in its concept and its um and and it's idea so the best example that I can give of that is if you gave 100 grand masters of position and told them, you know what do you think the best move here is for black? Not in this position right here, we have nothing. But an overwhelming amount of them would look at the position, evaluate everything they know about the game of chess which is relatively similar but obviously slightly imbalanced based on their skill level and they would come up with a sample size of two or three moves and in comes the computer with a fucking haymaker and suddenly everybody goes, oh everything we know about chess has gone out the window. So they all start looking at that move and they know it's the best move. So now they start adding the evidence behind the verdict as opposed to getting to the verdict while first looking at the evidence. So the concept of it and the idea of it is so outlandish based on a certain type of position that you can't fully grasp it, you have to continue to beg the engine to tell you what the variation is. A move is only good if its extension is good, that's the way chest works. So it's like a move is good is because the computer has seen that the various branches of things going forward are also good. So you bring all that back and no human could have even conceptualized that initial thing. But the second thing about computer moves is they look counterintuitive. So that's a, if you might be in a position where it looks like the demands of the position are A B C. And then the computer is like, nope, it's not because I've seen the future way more than you possibly could have and I don't have emotions. </s><s>[INST] So [/INST] like dumb </s><s>[INST] moves and brilliant moves can look similar. [/INST] Yes and oftentimes do and this is actually back to the hans thing. A lot of people now dissecting these games they're playing and there are, they're basically saying like even Fabiano Caruana, one of the best players in the world was on some on his podcast yesterday basically saying, okay, this is beyond my level saying out of my league, what's that, what's out of your league, you played for the World Championship kind of, we get what we can read between the lines, right? It's, it's </s><s>[INST] possible that is that level of genius, is there like different, different kinds of genius? Like where one, you could be out of each other's league kind of thing. [/INST] Maybe in the case of magnus, it's understanding of Endgames, it's just somehow he understands the, that last phase of the game and the complexities and the problems he can pose better than anybody else. </s><s>[INST] So you can see magnus do uh poor looking moves in the end game [/INST] or </s><s>[INST] like moves that don't fit what seems your gut says is would be the optimal [/INST] Yes. But also, So it's not that you even think that you just might not even consider them because of over reliance on your own information or even the computer. That was what was going on in game six. He kept doing things and kept playing and kept finding play and posing those questions that humans and computers could not understand. So he beat the engine basically he could, so that contributed computer would have defended. </s><s>[INST] So by the, by the time this podcast comes out, which I don't know will be in a week or something like that. I feel like more will happen. [/INST] Let's </s><s>[INST] see your predicting and how does this hans drama end saga. [/INST] Let's </s><s>[INST] look in [/INST] um, in </s><s>[INST] three months. By the time we get to the next world championship, let's say what uh what are the options? What are the possible let's imagine, let's not say like what the probability is that, what are the options uh chess dot com is forced to or agrees to or whatever to come up with a huge amount of evidence of cheating in the past or hans comes out what, what, what can hans do with this. So I'm uncomfortable with the general, make sure you can maybe update me on this but there was a little bit of an attack on him a lot of an [/INST] attack that </s><s>[INST] he's a cheater right? Without evidence without clear conclusive evidence, [/INST] physical evidence, physical </s><s>[INST] evidence. So all of those right? That's [/INST] the tricky thing. </s><s>[INST] Yeah so like that stuff we're talking about is beyond my level that starts being um kind of intuitive circumstantial evidence. [/INST] There's the statistical evidence behind the over the board games that he's played in 2020 2021 where the games match what's called engine correlation more than magnus and many other top grandmasters combined but that can be argued is because he was very strong in playing weaker opposition. So there's always kind of this argument against statistics right? There is the fact that the guy who magnus name dropped maxim bloody lucky is a chess grandmaster. And he's even been I think president of the U. S. Chess federation. I've played him in some blitz games. It turns out I wasn't even fully aware of the extent of this. He has been banned from dot com </s><s>[INST] for cheating [/INST] for cheating. Have </s><s>[INST] they actually has him and hans actually [/INST] worked? Yes so that was why he name dropped that right. That's also not good. You see where this is getting you still don't have the physical proof but you have </s><s>[INST] smoke. [/INST] So I don't know how this ends. I don't know if this if if he denies it to the death and he ends up filing some sort of legal action, some sort of ethics complaint or he admits everything. I don't know. </s>

<s>[INST] Like a temporary one that just cleans up some of the elements. [/INST] Well, sort of, right? Because if you think of the, we haven't talked about this yet, but if you know what a star looks like, a massive star looks like in its interior before it explodes, you have hydrogen and helium still on the outskirts, and then you have your layers of heavy and heavy elements all the way up to iron. So you have an iron core in the center. And because you can't get any energy out of iron when you want to fuse to iron atoms anymore, right? That's when the supernova explodes, or occurs, really. It's actually an implosion first, and then you have a bounce of the sort of neutron star phase that occurs in the process. And then, you know, the star just gets disrupted. Yeah. It's like this giant, you know, basketball. And then, whoa, it all goes up. An implosion first, an explosion after. Yeah. And so in the process, right, if you make your black hole basically big enough, it will suck away some of the iron, because that's the closest in terms of the layers. You hold on to it. You don't let it escape. And carbon is much further out. You let it all go. Nice. </s><s>[INST] And so that is so awesome. It all goes up. An implosion first, an explosion after. And so that explains why you can have a big oomf and not much iron yield. Yes, yes. So is this explained the HE 1327? Correct. [/INST] And others like it. Yes, yes, correct, yes. So there's a well-established now that the lower the iron abundance of the stars are, the higher the carbon sort of gets. </s><s>[INST] And carbon is such an interesting element in that regard. [/INST] If we come back to the formation of the first low mass stars, right, so we had the hotter gas, just hydrogen and helium that made the first stars. There were 100 solar masses or so because the gas couldn't cool enough. So they were big and puffy. Carbon then, coming from the first stars, probably led to enough cooling in these gas clouds </s><s>[INST] that enabled the formation of the first low mass stars. [/INST] So think about what happened if there wouldn't have been any carbon or the properties of the carbon atom would be different. It would not have cooled the gas in such significant ways perhaps. There wouldn't be any low mass stars. We wouldn't be here today, right? And we're carbon-based. And so I think carbon is really the most important element in the universe for a variety of reasons because it just enabled this whole evolution that we're now observing and literally seeing in the sky. And it's really fascinating. </s><s>[INST] So combined with the fact that you have the iron deficient, so all of that is probably important to creating humans. [/INST] Yeah, yeah, we need all the elements. But if you don't have stars, you know, like the sun, small stars that can actually host planets, that have long lifetimes, you need long, long lifetimes if you want to have a stable planet and develop humans. </s><s>[INST] So carbon is kind of important in many ways. [/INST] Yeah, yes, yes. </s><s>[INST] This is perhaps an interesting tangent. If I could just mention that you interviewed military Dresselhaus, carbon queen, the remarkable life of the nanoscience pioneer. Is there something you could say about the magic of carbon and the magic of Milly? [/INST] Well, Milly was certainly magic. She was a professor at MIT for many decades. I met her a number of times. Her photograph, actually a young and an older, Milly is still on the wall every time I step out of the elevator in one of the buildings, I see it. She pioneered all sorts of carbon nanowork. So she was a material scientist, very far removed from what I do on a daily basis. But yes, carbon has amazing properties when you study it. And again, that's indeed another aspect of why carbon is so fascinating, not just in the cosmos, but also for us, making us, creating us in the way that we can use it. It's wonderful. </s><s>[INST] Just sometimes think about this chemical evolution in this big philosophical way that we're the results of that chemical evolution. We're made of this stuff. We're made of carbon. [/INST] Yes, we're made of store stuff. Yeah, and it came- Class taking him right. </s><s>[INST] Yeah, and it came- Class taking him right. I mean, it's almost like a cliche statement, but it's also a materials, a chemical, a physics statement, that we came from hydrogen and helium. And that's somehow this formation has created this interesting complexity of soup that made us. What are we supposed to make of that? Like what? Did we just get really lucky? Why did we get all this cool stuff? [/INST] Yeah, that's a good question. </s><s>[INST] I don't think it's a question that has an answer. I keep just asking why. But it's just this incredible mystery. So much cool stuff had to happen. So much, sorry, hot stuff had to happen to create us. [/INST] And so much could have gone wrong, and there would have been another outcome. And it's actually amazing how many things kind of fell in place. I mean, maybe that's all sort of soft deterministic in some ways, right? We are who we are because that was the path. Maybe we would have ended up being robots. I don't know. But it's certainly wonderful to, you know, a scientist for us to help contribute unraveling our cosmic history, right? I always say the biological evolution on Earth was absolutely facilitated by the chemical evolution of the universe, right? And one doesn't go without the other. And that evolution- From a human perspective. </s>