text
stringlengths
296
254k
<s>[INST] Thanks for listening to this conversation with Stephen Wolfram and thank you to our sponsors Express VPN and cash app. Please consider supporting the podcast by getting express VPN at Express VPN dot com slash lex pod and downloading cash up and using collects podcast. If you enjoy this podcast, subscribe on Youtube review of the five stars on apple podcast support on Patreon are simply connect with me on twitter at lex Friedman and now let me leave you with some words from Stephen Wolfram, it is perhaps a little humbling to discover that we as humans are in effect computational e no more capable than the cellular tomorrow with very simple rules. But the principle of computational equivalence also implies that the same is ultimately true of our whole universe. So while science has often made it seem that we as humans are somehow insignificant compared to the universe. The principle of computational equivalence now shows that in a certain sense where at the same level for the principle implies that what goes on inside us can ultimately achieve just the same level of computational sophistication as our whole universe. Thank you for listening and hope to see you next time. [/INST] </s>
<s>[INST] but also convince you and convince convinced each other in those early days when you're developing the science essentially what was missing an entire science and system of, of leg locks because it's not like you knew for sure that there's a lot here to be discovered in terms of control perhaps had just like you said, an initial intuition, but you know, you have to have enough, uh, there's perseverance required to take the johnny ive thing to take from the initial idea to the entire system is there is there a sense you have about how complicated and how big this world of control uh, in the uh, in leg locks is, how complicated is it, you have achieved a lot of success. You have a lot of powerful ideas in terms of inside outside, what's high percentage, what's not what's higher award, what's low risk, all those kinds of things. The, and then you also mentioned kind of transitions, not transitions, but how you move with your opponent to resist their escape through control. How much do you understand about this [/INST] world? This is a fascinating question. Um, as a general rule, the most, the most powerful developments are always at the onset of a project. Okay, let's give an example. Um, the jet engine was uh, I believe, first conceived in the late 1930s, just around the time of World War II, it was developed with great pace because of World War Two. Obviously military research was a huge thing back then and first fielded, I believe, by the Germans Uh, in around 1943. Um, jet aircraft didn't play a big role in World War Two. They were there at the end and they did play a significant role, but in terms of numbers, they just weren't there. So by around 1945, you had the onset of the jet age and the jet engine began to replace the piston engine and most aircraft, it was, it was the new way of doing things. If you look at the pace of development of Jet engine aircraft technology from 1945, 1960. It is unbelievable. There was a solid decade where they were gaining almost 100 miles an hour per year for a decade. That's a form of growth. That, I mean, in the world of engineering, that's, that's the only time you see growth like that is and things like Bitcoin and that's about it. Okay. Um uh, let's put things in perspective. Okay, and World War II, the standard US aircraft bomber was the B 17, which was a mid sized bomber with a fairly limited load capacity. And uh, I think top speed well below 300 mph. Just 10 years later, you had to be 52, Which could fly across continents and deliver nuclear weapons and carry bomb loads of up to £70,000 uh, in a decade that happened. I If you took a B-17 pilot in 1943 and put them inside a B- 52 a decade later, he would literally think he was on a ufo a ship from another planet. That was the speed of development, contrast that with the speed of modern development, if I took you in a time machine and I put you in a civil airliner, 1972 That's our Boeing 737, it's not that different from what you fly in today, flies at the same speed has the same range, flies at the same altitude, it's not that different. The amount of progress between 1973 and 2020 isn't very impressive, But the amount of progress from 1945, 1955 or even better in 1960 was staggering. And so the initial progress tends to be meteoric, but after that it tends to be incremental. That's with leg longs. </s><s>[INST] There's a guy named Elon musk. There's been almost no development in terms of uh, space, rocket propulsion and rocket launches and going out into orbit or going out into deep space. And one guy comes along one john Donahoe type character and says, well, it doesn't make sense why we don't use reusable rockets, why we don't make it much cheaper, why we don't launch every week as opposed to every few years. It doesn't make any sense why we don't go to the moon again over and over and over. It doesn't make any sense why we don't go to mars and colonize mars, it feels like it's not just a single Jump to a B- 52. It's a series of these kinds of jumps. So the question is, is there another leap within the leg locking system [/INST] time will tell. Um, I do believe that we're in a phase now where the really big jumps have already been made and we're in the incremental phase at this point. Um what I do believe is that you'll start to see new directions start to emerge where you start to see the interface between leg locking and wrestling, for example, the interface between leg locking and back attacks and that will provide new avenues of direction, which will provoke, create new spirits of growth. Um but in terms of breaking people's legs, this is the simple act of breaking legs. I believe we're in the incremental phase now rather than the meteoric phase. </s>
<s>[INST] that that notion is still somewhere deeply compelling to you. The notion that you can say you can drop thing on the table says this, You can expect this alcohol will give me some good results. I [/INST] hope there's I hope science will. I mean there's engineering and there's science. I think that they're not exactly the same. And I think right now we're making huge engineering like leaps and bounds. So the engineering is running away ahead of the science which is cool and often how it goes right? So we're making things and nobody knows how and why they work roughly. But we need to turn that into science. </s><s>[INST] There's some form it's uh there's some room for formalizing. [/INST] We need to know what the principles are. Why does this why why does that not work? I mean for a while people build bridges by trying but now we can often predict whether it's going to work or not without building it. Can we do that for learning systems or for robots? </s><s>[INST] Your hope is from a materialistic perspective that intelligence, artificial intelligence systems, robots. I was just more fancier bridges, belief space. What's the difference between belief space and state space? So you mentioned M. D. P. S. Found gps. You reasoning uh about you sense the world, there's a state. What's this belief space idea? [/INST] Yeah it sounds good. It sounds good to believe space. That is instead of thinking about what's the state of the world and trying to control that as a robot. I think about what is the space of beliefs that I could have about the world. What if I think of a belief as a probability distribution over ways. The world could be a belief state is a distribution. And then my control problem. If I'm reasoning about how to move through a world, I'm uncertain about my control problem is actually the problem controlling my beliefs. So I think about taking actions, not just what effect they'll have on the world outside, but what effect they'll have on my own understanding of the world outside. And so that might compel me to ask a question or look somewhere to gather information. Which may not really change the world state, but it changes my own belief about the world. </s><s>[INST] That's a powerful way to to empower the agent to reason about the world, to explore the world. Uh to what kind of problems does it allow you to solve to to uh consider belief space versus just state space? [/INST] Well, any problem that requires deliberate information gathering, Right? So if in some problems like chess there's no uncertainty or maybe there's uncertainty about the opponent. There's no uncertainty about the state. Ah And some problems there's uncertainty. But you gather information as you go, right? You might say, oh, I'm driving my autonomous car down the road and it doesn't know perfectly where it is. But the lion ours are all going all the time. So I don't have to think about whether to gather information. But if you're a human driving down the road, you sometimes look over your shoulder to see what's going on behind you in the lane and you have to decide whether you should do that now and you have to trade off the fact that you're not seeing in front of you and you're looking behind you and how valuable is that information and so on. And so to make choices about information gathering, you have to reasonably space Also. Also, I mean, also to just take into account your own uncertainty before trying to do things. So you might say if I understand where I'm standing relative to the door jamb, uh pretty accurately, then it's okay for me to go through the door, but if I'm really not sure where the door is, then it might be better to you not do that right now. </s><s>[INST] The degree of your uncertainty about about the world is actually part of the thing. You're trying to optimize informing the planet. Right? So this idea of a long horizon of planning for a PhD or just even how to get out of the house or how to make breakfast? You show this presentation of the WTF where's the fork of robot looking at the sink. Uh and uh can you describe how we plan in this world? Is this idea of hierarchical planning we've mentioned. So yeah. How can a robot hope to plan about something uh with such a long horizon where the goal is quite far away. [/INST] People since probably reasoning began to have thought about hierarchical reasoning. The temporal hierarchy in particular their spatial hierarchy. But let's talk about temporal hierarchy. So you might say, oh I have this long execution, I have to do but I can divide it into some segments abstractly, right? So maybe you have to get out of the house, I have to get in the car, I have to drive and so on. And so you can plan if you can build abstractions. So we started out by talking about abstractions and we're back to that. Now if you can build abstractions in your state space and abstractions sort of temporal abstractions, then you can make plans at a high level and you can say I'm going to go to town and then I'll have to get gas and then I can go here and I can do this other thing and you can reason about the dependencies and constraints among these actions. Again, without thinking about the complete details what we do in our hierarchical planning work is then say, all right, I make a plan at a high level of abstraction. I have to have some reason to think that it's feasible without working it out in complete detail. And that's actually the interesting step. I always like to talk about walking through an airport. Like you can plan to go to new york and arrive at the airport and then find yourself an office building later, you can't even tell me in advance what your plan is for walking through the airport, partly because you're too lazy to think about it maybe. But partly also because you just don't have the information, you don't know what get your landing in or what people are going to be in front of you or anything. So there's no point in planning in detail, but you have to have, you have to make a leap of faith that you can figure it out once you get there. And it's really interesting to me how you arrive at that. How do you, So you have learned over your lifetime to be able to make some kinds of predictions about how hard it is to achieve some kinds of sub goals. And that's critical. Like you would never plan to fly somewhere if you couldn't didn't have a model of how hard it was to do some of the intermediate steps. So, one of the things we're thinking about now is how do you do this kind of very aggressive generalization uh to situations that you haven't been in and so on to predict how long will it take to walk through the Kuala Lumpur airport? Like you give me an estimate and it wouldn't be crazy and you have to have an estimate of that in order to make plans that involve walking through the Kuala Lumpur airport, even if you don't need to know it in detail. So I'm really interested in these kinds of abstract models and how do we acquire them? But once we have them we can use them to do hierarchical reasoning which is I think it's very important. </s>
<s>[INST] let's take a brief to the philosophical, I just recently talked to Jim Keller who's uh sort of uh like the famed architect in the, in the, in the microprocessor world and he's been told for decades every year that the moore's law is going to die this year and he tries to argue that the moore's law is still alive and well and it'll be alive for quite a long time to come. [/INST] How long? Well </s><s>[INST] he's the main point is still alive, but he thinks uh there's still 1000 x improvement just on shrinking and transition as possible. Whatever the point is that the exponential growth you see is actually a huge number of these s curves, Just constant breakthroughs at the philosophical level. Why do you think we, as a descendants of apes were able to just keep coming up with these new breakthroughs on the CPU side, is this something unique to this particular endeavor or will it be possible to replicate in the quantum computer space? [/INST] Okay, Alright. That that there there was a lot there to the but but to to break off something, I mean, I think we are in an extremely special period of human history, right? I mean, it's it is uh you could say obviously special, you know, in in in many ways right there, you know, uh you know, way more people alive then there then there then there have been and and uh you know, the uh you know, the whole, you know, the future of the planet is in is in is in question in a way that it it hasn't been, you know, for for the rest of human history, but you know, in particular, you know, we are in the era where, you know, we finally figured out how to build, you know, universal uh, machines, you could say, you know, the things that we call computers, you know, machines that you program to uh simulate the behavior of of whatever machine you want. And um you know, and and and and and and and and and once you've sort of crossed this threshold of universality, you know, you've built, you could say, you know, touring, you've in stan she hated touring machines in the physical world. Well then the main questions are are ones of numbers. They're, you know, one's of how many how much memory uh can you access, how fast does it run? How many parallel processors, you know, at least until quantum computing. Quantum computing is the one thing that changes what I just said. But you know, as well as well as long as it's classical computing, then it's all questions of numbers and uh you know, the the you could say at a theoretical level the computers that we have today are are the same as the ones in the fifties. There just millions of times, you know faster and with millions of times more memory and you know, I mean, I think there's been an immense economic pressure to, you know, get more and more transistors, you know, get them smaller and smaller, get you add more and more cores and um you know, and and and and in some sense, like a huge fraction of sort of all of the technological progress that there is in all of civilization has gotten concentrated just more narrowly into just those problems. Right? And so, you know, it has been one of the biggest success stories in the history of technology, right? There's you know, I mean, it is I I am as amazed by it as as anyone else's right, But at the same time, you know, we also know that it, you know, and I I I really do mean we know that it cannot continue indefinitely, okay. Because you will reach, you know, fundamental limits on, you know, how small you can possibly make a processor and you know, if you want a real proof, you know, that would justify my use of the word, you know, we know that, you know, moore's law has to end. I mean, ultimately you will reach the limits imposed by quantum gravity. You know, you know, if if you were doing uh if you tried to build a computer that operated at 10 to the 43 hertz, who did 10 to the 43 operations per second, that computer would use so much energy that it would simply collapse to a black hole. Okay. So, you know that, you know, you know, in reality we're going to reach the limits long before that. But you know, that is a sufficient proof. Yes, Yes. </s><s>[INST] But it will be interesting to try to understand the mechanism, the economic pressure that you said, just like the Cold War was a pressure on getting us getting us get because I'm both my us is both the soviet Union and the United States getting us the two countries to get to hurry up to get the space to the moon. There seems to be that same kind of economic pressure that somehow created a chain of engineering breakthroughs that resulted in the moore's law. It would be nice to replicate. [/INST] Yeah, I mean, I mean, some people are sort of uh get depressed about the fact that technological progress, you know, may seem to have slowed down in in many, many realms outside of computing. Right? And there was this whole thing of, you know, we wanted flying cars and we only got twitter instead. Right. And good </s><s>[INST] old peter thiel. [/INST] Yeah. Yeah. Right. Right. </s><s>[INST] So then jumping to another really interesting topic that you mentioned, So Google announced were there working the paper in nature with Quantum supremacy. Can you describe again back to the basic what is perhaps not so basic? What is quantum supremacy? [/INST] Absolute. So quantum supremacy is a term that was coined by again by John Presque Isle in 2012. Uh Not not everyone likes the name, you know, but you know, it's it's sort of stuck uh you know, we don't uh sort of haven't found a better alternative. </s>
<s>[INST] on top of the code or the people in very nice places. Well I think I speak for millions of people yarn and saying thank you for creating this language that so many systems are built on top of them that make a better world. So thank you and thank you for talking today. [/INST] I really appreciate it will make it even better </s><s>[INST] Good. [/INST] </s>
<s>[INST] Uh, so his ability to play with his ideas mathematically, is what solidified the initial intuition that you could have was that the first time he was born, the idea that you have action at a distance, that you can have forces without contact, which is another revolutionary idea. [/INST] I would say that in the sense of dealing with the mechanics of force like effects considered to act at some distance. It is novel uh with both Hooke and Newton at the time. The notion that two things might interact at a distance with one another without direct contact that goes back to antiquity only there it would thought of more as a sympathetic reaction. You know, to a magnet and a piece of iron. They have a kind of mutual sympathy for one another. </s><s>[INST] I'm like uh like what love? What are we talking [/INST] about? Actually, they do sometimes talk like </s><s>[INST] that. That is love that. I you know, I talk like that all the time. I think love is somehow in consciousness or forces of physics that yet to be discovered. Okay, now, there's the the other side of things which is calculus. They began to talk about. The Newton brought a lot of things to this world. One of them is calculus. What is calculus? And uh what was role? What was Newton's role in bringing it to life? What was it like? What was the story of bringing calculus to this world? [/INST] Well, since the publication starting uh many decades ago by tom White side, who is now deceased of Newton's mathematical papers. We know a lot about how he was pushing things and how he was developing things. It's a complex question to say. What calculus is calculus is the set of mathematical techniques that enable you to investigate um what we now call functions. Mathematical functions which are continuous, that is that are not formed out of a discrete sets, Like the counting numbers for instance. Um uh Newton uh there were already um procedures for solving problems involving such things as finding areas, two under curves and tangents, two curves by using geometrical structures, but only for certain limited types of curbs, if you will, Newton as a young man, the we know this is what happened is looking at a formula which involves an expansion in separate terms, polynomial terms, as we say for certain functions. I know I don't want to get complicated here about this, but and he realizes it could be generalized and he tries the generalization and that leads him to a an expansion formula called the binomial theorem. That enables him to move ahead with the notion that if I take something that has a certain value and I had a little bit to it and I use this binomial theorem and expand things out. I can begin to do new things and the new things that he begins to do leads him to a recognition that the calculations of areas and the calculations of tangents to curves, Our reciprocal to one another. And the procedures that he develops is a particular form of the calculus in which he considers small increments and then continuous flows, uh and changes of curves. Uh and so on. And we have relics of it in physics today. The notation in which you put a dot over a variable indicating the rate of change of the variable. That's Newton's original type of notation </s><s>[INST] dot [/INST] Yeah, the dot notation possibly independently of Newton because he didn't publish this thing, although he became quite well known as quite a brilliant young man, in part because uh people heard about his work and so on. When another young man by the name of Gottfried Leibnitz visited London and he heard about these things. Uh It is said that he independently develops his form of the calculus, which is actually the form we use today, both in notation and perhaps in certain fundamental ways of thinking. It has remained a controversial point as to where exactly and how much independently Leibnitz did it, Leibnitz aficionados think, and continued to maintain he did it completely independently Newton when he became president of the Royal Society, put together a group to go on the attack saying, no, you must have taken everything we don't know. But I will tell you this About 25 or so years ago, a scholar who is a professor at indiana now named Domenico Mellie got his hands on a libyan it's manuscript called the 10 Taman, which was like Cabinet's attempt to produce an alternative to Newton's mechanics. And it comes to some conclusions that you have in the Newton's mechanics. Well, he published that, but Mellie got the manuscript and what Mellie found out was that Leibnitz reverse engineered the principia and cooked it backwards so that he could get the results he wanted </s><s>[INST] now was for the mechanics. So that means his mind allows for that kind of thing. Some people, you're breaking news today, you're starting. Some people, [/INST] some people think so, I think most historians of mathematics do not agree with that. Uh, a a friend of mine, rather well known physicist unfortunately died a couple years ago named Mike. Now Enberg at UC santa Cruz had some evidence along those lines. Didn't pass mustard with many of my friends who are historians of math. In fact, I edit with a historian of Math technical journal and we were unable to publish it in there because we couldn't get it through any of our colleagues. But I am, I remain suspicious. </s>
<s>[INST] So you mentioned Eric Schmidt in his book, they reached out to me that they want to do this podcast and I'm I know ERic Schmidt have spoken in before, I like him a lot obviously. Um so they said We could do a podcast for 40 minutes with Eric, 40 minutes with Eric and Henry together And 40 minutes with Henry. So there's a three different conversations and I had to like I had to do some soul searching because I said, fine, 40 minutes of ERic, we'll probably talk many times again, fine, let's talk about this ai book together for 40 minutes, But I said what I wrote to them is that I would hate myself if I only have 40 minutes to talk to Henry Kissinger. And so I had to hold my ground, went back and forth and then decided to part ways over this. And I sometimes think about this kind of difficult decision um in the podcasting space of when do you walk away? Because um there's a particular world leader that I've mentioned in the past where the conversation is very likely to happen and As as it happens, those conversations can often be, you know, unfortunately this person only has 30 minutes now. I know we agreed for three hours, but unfortunately, and you have to decide, do I stand my ground on this on this point? I suppose that's the thing that journalists have to think about, right? Like um do I hold on to my integrity and whatever form that takes? And do I stay in my ground? Even if I lose a fascinating opportunity Anyway, something I thought I thought about um something I think about and with Henry Kissinger, I mean he's had a million amazing conversations in your biography, so it's not like something is lost. But it was still, nevertheless to meet some soul searching that had to do as a as a kind of practice for what to me is a higher States conversation. I'll just mention as Vladimir Putin, um I can have a conversation with him unlike any conversation he's ever had, partially because I'm a fluent Russian speaker, partially because I messed up in the head in certain kind of ways that make for an interesting dynamic because we're both judo people, we both are certain kinds of human beings that can have a much deeper a political conversation. I have to ask to stay on the topic of leadership. You've in your book, Doom have talked about wars pandemics throughout human history and in some sense saying that all of these disasters are man made. So humans have a role in terms of the magnitude of the effect that they have on human civilization. Mhm. Without taking cheap political shots, can we talk about COVID-19? How will History remember the COVID-19 pandemic? What were the successes with? What were their failures of leadership of man of humans? [/INST] Doom was a book that I was planning to right before the pandemic struck as a history of the future based in large measure on science fiction. It had occurred to me in 2019 that I had spent too long not reading science fiction. And so I decided I would liven up my my intake by getting off history for a bit and reading science fiction because history is great at telling you about the perennial problems of power Putin is always interesting on history. He's become something of historian recently with his essays and lectures, but what history is bad at telling you is? Well, what will the effects of discontinuity of technology be. And so I thought I need some science fiction to think more about this because I'm I'm tending to miss the importance of technological discontinuity. If you read a lot of science fiction, you read a lot of plague books because science fiction writers are really quite fond of the plague scenario. So the world ends in many ways in science fiction. But one of the most popular is the lethal pandemic. So when, when the first email came to me, I think it was on january the third from my medical friend Justin stepping funny pneumonia in Wuhan. My antennae began to tingle because it was just like one of those science fiction books that begins in just that way in a pandemic as larry brilliant. The epidemiologists said many years ago. The key is early detection and early action. That's how you deal with a novel pathogen. And almost no Western country did that. We know it was doable because the time and he's in the south Koreans did it and they did it very well. But really no Western country got this right. Some were unlucky because super spreader events happened earlier than in other countries. Italy was hit very hard very early for other countries. The real disaster came quite late Russia, which has only relatively recently had a really bad experience. The lesson for me is quite different from the one that most journalists thought they were learning last year. Most journalists last year thought trump is a terrible president. He's seeing a lot of crazy things. It's his fault that we have high excess mortality in the United States. The same argument was being made by journalists in Britain Boris johnson dot dot dot brazil Jared bolsonaro dot dot dot even India Narendra modi the same argument and I think this argument is wrong in a few ways. It's true that the populist leaders said many crazy things and broadly speaking gave poor guidance to their their populations. But I don't think it's true to say that with different leaders these countries would have done significantly better if joe biden had magically been president a year earlier. I don't think the U. S. Would have done much better because the things that caused excess mortality last year weren't presidential decisions. They were utter failure of C. D. C. To provide testing. That definitely wasn't trump's fault. Scott Gottlieb's book makes that very clear. It's just been published recently. We utterly failed to use technology for contact tracing which the Koreans did very well. We didn't really quarantine anybody seriously. There was no enforcement of quarantine and we exposed the elderly to the virus as quickly as possible and elderly care homes and these things have very little to do with presidential incompetence. So I think leadership is of somewhat marginal importance in a crisis like this because what you really need is your public health bureaucracy to get right And very few Western public health bureaucracies got it right. Could the president have given better leadership? Yes. His correct strategy however was to learn from Barack Obama's playbook with the opioid epidemic. The opioid epidemic killed as many people on Obama's watch as covid did on trump's watch. And it was worse in the sense because it only happened in the US and each year it killed more people than the year before. Over eight years. Nobody to my knowledge has ever seriously blamed Obama for the opioid epidemic. Trump's mistake was to put himself front and center of the response to claim that he had some unique insight into the pandemic and to say with every passing week more and more foolish things. Until even A significant portion of people who voted for him in 2016 realized that he'd blown it, which was why he lost the election. The correct strategy was actually to make mike Pence the pandemics are and get the hell out of the way. That's what my advice to trump would have been. In fact it was in february of last year. So the mistake was to try to lead. Yeah, but actually leadership and a pandemic is almost a contradiction in terms what you really need is your public health bureaucracy not to funk it up and they really, really fucked it up. And that was then all blamed on trump. You know, Jim Fallows writes a piece in the atlantic that says well being the president's like flying a light aircraft it's pilot error. And I read that piece and I thought, does he really after all the years he spent writing, think that being president is like flying a light aircraft. I mean, It's really nothing like flying light aircraft. Being president is you sit on top of a vast bureaucracy with how many different agencies, 60, 70. We've all lost count and you're surrounded by advisers, at least a quarter of whom are saying this is a disaster. We have to close the borders and the others are saying, no, no, we have to keep the economy going. That's what you're running on in november. So being the president in a pandemic is a very unenviable position because you actually can't, you can't really determine whether your public health bureaucracy will get it right or not. </s>
<s>[INST] So they're simple equations, relatively simple that can describe things. You know, the fundamental functions. They didn't describe everything about our reality. That's not. Can you imagine universes where everything is a lot more complicated? Do you think there's something inherent about universes that Well, simple laws? [/INST] Well, first of all, let me this is a question that I encounter in a number of guides is a lot of people will raise the question about whether mathematics is the language of the universe. And my response is mathematics is the language that we humans are capable of using in describing universe. It may have little to do with the universe, but in terms of our capacity, it's the microscope, it's the telescope through which we it's the lens through which we are able to view the universe with the precision that no other human language allows. So could there be other universes? Well, I don't even know if this one looks like. I think it does. </s><s>[INST] But the beautiful surprising thing is that physics, there are laws of physics. Very few laws of physics. They can effectively compress down the functioning of the universe. [/INST] Yes, that's extraordinarily surprising. I like to use the analogy with computers and information technology. Uh If you worry about transmitting large bundles of data. One of the things that computer scientists do for us is they allow for processes that are called compression. Where you take big packets of data and you press them down into a much smaller packets and then you transmit those and then unpack them at the other end. And so it looks a little bit to me like the universe has kind of done us a favor. It's constructed our minds in such a way that we have this thing called mathematics which then as we look at the universe teaches us how to carry out the compression process. </s><s>[INST] A quick question about compression. Do you think uh the human mind can be compressed? The biology could be compressed. We talked about space travel to be able to compress the information that captures some large percent of what it means to be me or you, and then be able to send that at the speed of light. [/INST] Wow, that's a big question. And uh let me try to take it apart. Unpack it into several pieces. I don't believe that Wetware biology, such as we are, has an exclusive patent on an on intellectual consciousness. I suspect that other structures in the universe are perfectly capable of producing the data streams that we use to process. First of all, our observations of the universe and and an awareness of ourselves. I can imagine other structures can do that also. So that's part of what you were talking about, which I would um have some disagreement with </s><s>[INST] consciousness. What's the most interesting part of [/INST] consciousness </s><s>[INST] of us? Humans, Consciousness is the thing. [/INST] I think that's the most interesting thing about humans. And </s><s>[INST] then you're saying that there is other entities throughout the universe. [/INST] I could imagine. I can well imagine that the architecture that supports our consciousness again has no pattern on consciousness. </s><s>[INST] Just uh in case you have an interesting thought here, there's uh folks perhaps in philosophy called Panpsychism that believe consciousness underlies everything. It is one of the fundamental laws of the university. Do you have a sense that that could possibly [/INST] fit into? I don't know the answer that question. One part of that belief system is Ghia, which is that there's a kind of conscious life force about our planet And you know, I've encountered these things before, I don't quite know what to make of them, I my own life experience and I'll be 69, about two months and I have spent all my adulthood thinking about the way that mathematics interacts with nature and with us to try to understand nature and all I can tell you from all of my integrated experience is that there is something extraordinarily mysterious to me about our universe. This is something that Einstein said uh from his life experience as a scientist and this mysteriousness almost feels uh like the universes our parent. It's a very strange thing perhaps to hear science say, scientists say. But there's just so many strange coincidences that you just get a sense that something is going on. </s><s>[INST] Well, I interrupted you in terms of compressing what we're down to consent it at the speed of light. [/INST] So, so the first thing is, I would argue that it's probably very likely that artificial intelligence ultimately will develop something like consciousness, something that for us will probably be indistinguishable from consciousness. So that's what I meant by our biological uh processing equipment that we carry up here probably does not hold a patent on consciousness because it's really about the data streams. I mean, that's as far as I can tell. That's what we are. We are self actuated, self learning data streams. That to me is most accurate way. I can tell you what I've seen in my lifetime about what humans are at the level of consciousness. So if that's the case then you just need to have an architecture that supports that information processing. So let's assume that that's true. That uh that in fact what we call consciousness is really about a very peculiar kind of data stream. If that's the case, then if you can export that to a piece of hardware, something metal electronics, what have you, then uh you certainly will. Ultimately, that kind of consciousness could get to mars very quickly. It doesn't have our problems. You can engineer their body. As I said, it's a ship or a body. You engineer Winter both, um send it at the speed of light. Well, that one is a more difficult one because that now goes beyond just a matter of having a data stream. Is So now the preservation of the information in the data stream. And so unless you can build something that's like a super super super version of the way the internet works because most people aren't aware that the internet itself is actually a miracle. It's based on a technology called message packaging. So if you could exponentially eight message packaging in some way to preserve the information that's in the data stream, then maybe your dream becomes true. </s>
<s>[INST] and what does control mean? So his action is the fundamental element. [/INST] It means making rational decisions now and rational decisions or decisions that maximize the measure of utility </s><s>[INST] and sequentially so many decisions. Time and time and time again now, like it's easy to see that kind of idea in the space of maybe games in the space of robotics. Do you see it bigger than that? Is it applicable? Like we're the limits of the applicability of reinforcement learning. [/INST] Yeah. So rational decision making is essentially the encapsulation of the ai problem viewed through a particular lens. So any problem that we would want a machine to do? Uh intelligent machine can likely be represented as a decision making problem. Classifying images is a decision making problem, although not a sequential one. Typically uh you know, controlling a chemical plant as a decision making problem, deciding what videos to recommend on youtube is a decision making problem. And one of the really appealing things about reinforcement learning is if it does encapsulate the range of all these decision making problems, perhaps working on reinforcement learning is uh you know, one of the ways to reach a very broad swath of ai problems. </s><s>[INST] But what what do you is the fundamental difference between reinforcement learning and maybe supervised machine learning. [/INST] So reinforcement learning can be viewed as a generalization of supervised machine learning. You can certainly cast supervised learning as a reinforcement learning problem. You can just say your loss function is the negative your reward. But you have stronger assumptions, you have the assumption that someone actually told you what the correct answer was uh that your data was idea and so on. So you could view reinforcement learning essentially relaxing some of those assumptions. Now, that's not always a very productive way to look at it because if you actually have a supervised learning problem, you'll probably solve it much more effectively by using supervised learning methods because it's easier. But you can view reinforced morning as a generalization of that. Know for sure, </s><s>[INST] but they're fundamentally different. That's a mathematical statement. That's absolutely correct, but it seems that reinforcement learning, the kind of tools will bring to the table today of today. So maybe down the line, everything will be a reinforcement learning problem just like you said, image classification should be mapped to a reinforcement learning problem. But today the tools and ideas, the way we think about them are are different sort of supervised learning has been used very effectively to solve basic narrow ai problems, reinforcement learning kind of represents the dream of a I it's very much so in the research space now into captivating the imagination of people of what we can do with intelligence systems, but it hasn't yet had as wide of an impact as a supervised learning approaches. So that sort of, my question comes to the more practical sense, like what do you see is the gap between the more general reinforcement learning and the very specific yes, it's a financial decision making with one sequence, one step in the sequence of the supervised learning. [/INST] So from a practical standpoint, I think that one one thing that is uh you know, potentially a little tough now and this is I think something that we'll see this is a gap that we might see closing over the next couple of years is the ability of reinforcement learning algorithms to effectively utilize large amounts of prior data. So one of the reasons why it's a bit difficult today to use reinforcement learning for all the things that we might want to use it for is that in most of the settings where we want to do rational decision making? Um It's a little bit tough to just deploy some policy that does crazy stuff and learns purely through trial and error. It's much easier to collect a lot of data, a lot of logs of some other policy that you've got and then maybe you you know if you can get a good policy out of that then you deploy it and let it kind of fine tune a little bit. But algorithmic li it's quite difficult to do that. So I think that once we figure out how to get reinforcement learning to bootstrap effectively from large data sets then we'll see a very very rapid growth in applications of these technologies. So this is what's referred to as off policy reinforcement learning or offline RL or batch RL. Um And I think we're seeing a lot of research right now that does bring us closer and closer to that. </s><s>[INST] Can you maybe paint the picture of the different methods she said? Uh Off policy, what's value based reinforcement learning, what's policy based, what's model based, what's off policy on policy, what are the different categories of [/INST] reinforcement? So one way we can think about reinforcement learning is that it's it's in some very fundamental way it's about learning models that can answer kind of what if questions So what would happen if I take this action that I hadn't taken before? Um and you do that of course from experience from data and often times you do it in a loop. So you build a model that answers these, what if questions uh use it to figure out the best action you can take and then go and try taking that and see if the outcome agrees with what you predicted. Um So uh the different kinds of techniques basically refer different ways of doing. And so a model based methods answer a question of uh what state you would get, basically what would happen to the world if you would take a certain action. Value based methods? Uh they answer the question of what value you would get, meaning, what utility you would get. Um but in a sense they're not really all that different because they're both really just answering these. What if questions now, Unfortunately for us with current machine learning methods answering what if questions can be really hard because they are really questions about things that didn't happen if you want to answer. What if questions about things that did happen, you wouldn't need to learn model, you would just like repeat the thing that worked before. Um and that's really a big part of why RL is a little bit tough. So if you have a purely on policy kind of online process then you ask these what if questions you make some mistakes, then you go and try doing those mistaken things and then you observe kind of the counter examples that will teach you not to do those things. Again if you have a bunch of off policy data and you just want to synthesize the best policy you can out of that data then you really have to deal with the challenges of making these these counterfactual. </s>
<s>[INST] In your new book titled Why we fight the roots of war and the paths for peace. You write, quote, let me be clear what I mean. When I say war, I don't just mean countries duking it out. I mean any kind of prolonged violent struggle between groups that includes villages, clans, gangs, ethnic groups, religious sects, political factions and nations wildly different as these may be. Their origins have much in common. We'll see that the northern irish zealots, Colombian cartels, european tyrants, Liberian rebels, greek, oligarchs, Chicago gangs, indian mobs. Rwandan Jenna side. There's a new word I learned. Thank you to you. Those are people who administer genocide, English soccer, hooligans and american invaders. So first let me ask, what is war in saying that war is a prolonged, violent struggle between groups. What do the words prolonged groups and violent means? [/INST] I sit at the intersection of economics and political science and I, I also do a little bit in psychology, but that's partly because I'm married to a psychologist sometimes do research with her. All these things are really different. So if you're a political scientist you spend a lot of time just classifying a really narrow kind of conflict and studying that. And that's that's an important way to make progress as a social scientist. But I'm not trying to make progress. I'm trying to sort of help everybody step back and say you know what? There's like some common things that we know from these disciplines that uh relate to a really wide range of phenomenon basically we we can talk about them in a very similar way and we can get really similar insights. So I wanted to actually bring them together but I still had to like say let's hold out individual violence which has a lot in common but but individuals choose to engage in violence for more and sometimes different reasons. So let's just put that aside so that we can focus a bit and let's really put aside short incidents of violence because those might have the same kind of things explaining them. But actually there's a lot of other things that can explain short violent sort violence can be really ah demonstrative like you can just I can use it to communicate information. The thing that all of it has in common is that it doesn't generally make sense. It's not your best option most of the time. And so I wanted to say let's take this thing that should be puzzling. We kind of think it's normal, We kind of think this is what all humans do. Uh, but let's point out that it's not normal and then figure out why and let's talk about why. And so that's so I was trying to throw out the short violence. I was trying to throw, throw out the individual violence. I was also trying to throw out all the competition that happens. It's not violent. That's, that's the normal, normal competition. I was trying to say, let's talk about violent competition because that's kind of the puzzle. </s><s>[INST] So that's really interesting. He said. Usually people try to find a narrow definition and you said progress. So you make progress by finding a narrow definition for example of military conflict in a particular context and progress means, Alright, well, how do we prevent this particular kind of military conflict or maybe if it's already happening, how do we deescalate it and how do we solve it sort of from a geopolitics perspective from an economics perspective. And you're looking for a definition of war that is as broad as possible, but not so broad, that you cannot achieve a deep level of understanding of why it happened and how it can be avoided. [/INST] Right? And a comment basically like recognize that common principles govern some kinds of behavior that looked pretty different like an indian ethnic riots. It's obviously pretty different than invading a neighboring country. Right? But uh, and that's pretty different than two villages or two gangs. A lot of what I work on is studying organized criminals and gangs to gang is going to where you think is really different. And, and of course it is, but, but there are some common principles, you can just think about conflict and the use of violence and um, not learn everything, but just get a lot, just get really, really far by sort of seeing the commonalities rather than just focusing on the differences. </s><s>[INST] So again, those words are prolonged groups and violent. Can you maybe linger in each of those words? What does prolonged mean? Where's the line between short and long? What does groups mean? And what does violent mean? [/INST] So let me, you know, I have a friend who, um, someone has become a friend through the process of my work and, and writing this book also, who was 2030 years ago was a, was a gang leader in Chicago. Um, so it's kind of Napoleon English or nap. And I remember one time he was saying, well, you know, when I was young, I used to, because he was 15, 16 and he'd go to the neighboring gang's territory. He said I'd go gang banging. And I said, well, I didn't know what that meant. I said, what does that mean? And he said, oh, that's just meant, I'd shoot him up like I should've buildings, I might shoot at people. I wasn't trying to kill that, he wasn't trying to kill them. He was just trying to sort of send a signal that he was a tough guy and he was fearless and he was someone who they should be careful with. And so I didn't want to call that war. Right? That was, that was, that's something different. That was short. It was kind of sporadic and he wasn't and he was, he was basically trying to send them information and this is what countries do all the time, right? We have military parades. Uh, and we uh, we might have border skirmishes. And uh and I wanted to sort of, so is it, what's short is a three month border skirmish a war? I mean, I don't, I don't try to get into those things. I don't want to, but I want to point out that like these long, grueling months and years of violence or like or the problem in the puzzle. And I just, I didn't want to spend a lot of time talking about, um than the international version of gangbanging. It's a different phenomenon. </s>
<s>[INST] That's fascinating. Of course you would say that because you're not even aware of your own. That's probably what kubrick would say to write is uh in describing why how nine thousands created the way how 9000 is created as you're just studying what's but the reality when when the specifics of the knowledge passes through your imagination, I would argue that you're incorrect in thinking that you're just disseminating knowledge that the very act of your imagination consuming, that's science. It creates something that creates the next step, potentially creates the next step. I I certainly think that's true with 2001 Space Odyssey I think at its best if it fails [/INST] that it's true that </s><s>[INST] it's best that it plans something. It's hard to describe. It inspires the next generation and it could be feel dependent. So your new series is more a connection to physics. Quantum physics quantum quantum mechanics, quantum computing and yet X Mark and has more artificial intelligence. I know more about ai my sense that Ai is much much earlier and it's in the depth of its understanding. I would argue nobody understands anything to the depth that physicists do about physics in Ai nobody understands ai that there is a lot of importance and role for imagination which I think you know, we're in that we're Freud imagine the subconscious we're in that stage of of Ai or there's a lot of imagination. You didn't thinking outside the box? [/INST] Yeah. It's interesting the the spread of discussions and the spread of anxieties that exist about Ai fascinate me. Um The way in which some people are, some people seem terrified about it What whilst also pursuing it. And I've never shared that fear about a I personally um uh but but the the way in which it agitates people um and also the people who it agitates. I find I find kind of fascinating. </s><s>[INST] Are you afraid? Are you excited? Are you sad by the possibility? Let's take the existential risk of artificial intelligence by the possibility and artificial intelligence system becomes our offspring and makes us obsolete. [/INST] I mean it's a huge it's a huge subject to talk about, I suppose. But one of the things I think is that humans are actually very experienced at creating new life forms because that's why you and I are both here and that's why everyone on the planet is here. And so something in the process of having a living thing that exists that didn't exist previously is very much encoded into the structures of our life and the structures of our societies. It doesn't mean we always get it right, but it doesn't mean we've learned quite a lot about that. Um, we've learned quite a lot about what the dangers are of uh, allowing things to be unchecked. And it's why we then create systems of checks and balances in our government. Um, and and so on and so forth. I mean, let's not say the other thing is, it seems like there's all sorts of things that you could put into a machine that you would not be so with us, we sort of roughly try to give some rules to live by and some of us then live by those rules and some don't. And with a machine it feels like you could enforce those things. So, so partly because of our previous experience and partly because of the different nature of a machine. I just don't feel anxious about it. I I more, I just see all the good that, you know, broadly speaking, the good that can come from it. But that that's just my that's just where I am on that anxiety spectrum, </s><s>[INST] you know, it's kind of there's a sadness. So we as humans give birth to other humans, right? But they're in their generations and there's often in the older generation of sadness about what the world has become now. I mean that's kind of [/INST] yeah, there is but there's a counterpoint as well which is the most parents would wish for a better life for their Children. So there may be a regret about some things about the past, but broadly speaking what people really want is that things will be better for the future generations, not worse. And so uh and then it's a question about what constitutes a future generation of future generation could involve people. It also could involve machines and it could involve a sort of cross pollinated version of the two. Or but but none of those things make me feel anxious. </s><s>[INST] It doesn't give you anxiety. It doesn't excite you like anything that's knows [/INST] not anything that's new. I don't think for example, I've got I my anxieties relate to things like social media that. So I've got plenty of anxieties about that, </s><s>[INST] which is also driven by artificial intelligence in the sense that there's too much information to be able to algorithm has to filter that information and present to you. So ultimately the algorithm a simple oftentimes simple algorithm is controlling the flow of information on social media. So that's another, [/INST] It is. But at least my sense of it, I might be wrong, but my sense of it is that the the algorithms have uh an either conscious or unconscious bias which is created by the people who are making the algorithms and and sort of delineating the areas to which those algorithms are going to lean. And so for example, the kind of thing I'd be worried about is that it hasn't been thought about enough, how dangerous it is to allow algorithms to create echo chambers say. Um But that doesn't seem to me to be about the ai or the algorithm. It's it's the naivety of the people who are constructing the algorithms to do that thing, if you see what I mean. </s>
<s>[INST] Is it religious in that the loss of religion? So is it a meaning crisis? Or is it out of a meeting? Crisis? Every discovery of, of religion in a, in a promethean type of, [/INST] I think it's the latter, I think there's a, there's this vacuum created </s><s>[INST] in that context. Is Hitler the central religious figure. And also did nazi Germany create Hitler or did Hitler create nazi Germany? So in this distributed cognition where everyone's having a dialogue, what's the role of the charismatic leader? Is it an emergent phenomena or do you need one of those two? Uh to kind of guide the populace, [/INST] I hope it's not a necessary requirement. I hope that the next buddha can be the rather than a specific individual? Um but I think in that situation, Hitler's charisma allowed him to take on a mythological, in the proper sense archetypal, he became deeply symbolic and he and he instituted all kinds of rituals, all kinds of rituals and all kinds of mythos, there's all this mythos about the master race and there's all these rituals, the swastika is of course self a religious symbol, there's all of this going on because he was tapping into the fact that when you put people into deeper and deeper meaning scarcity, they will fall back on more and more mythological ways of thinking in order to try and come up with a generative source to give them new meaning, making I should say, meaning participating behavior. </s><s>[INST] What is [/INST] evil? </s><s>[INST] Is this a word you [/INST] avoid? No, I don't because I think part of what we're wrestling with here is resisting the enlightenment. I mean the historical period in europe, the the idea that evil and sin can just be reduced to immorality, um individual human immorality. I think there's something deeper in the, the idea of sin than just immoral. I think sin is a much more comprehensive category. I think sin is a failure to love wisely, so that you ultimately engage in a kind of idolatry. You take something as ultimate, which is not. And that can tend to consulate these collective agents, I call them hyper agents within distributed cognition that have a capacity to wreck havoc on the world. That is not just due to a sort of a sum total of immoral decisions. You know, this goes to Hannah Arendt's thing, right? And the banality of Eichmann and she was really wrestling with it and I think she, she's close to something, but I think she's slightly off, you know Aikman is just making a whole bunch of immoral decisions, but it doesn't seem to capture the gravity of what the nazis did, the genocide and the warfare and and and she's right because you're not going to get just the summation of a lot of individual, rather banal, immoral choices adding up to what was going on. You're getting a comprehensive parasitic process within massive distributed cognition that is has the power to confront the world and confront aspects of the world that individuals can't. And I think when we're talking about evil, that's what we're trying to point to. This is a point of convergence between me and Jonathan Pageau, we've been talking about this. So </s><s>[INST] the word sin is interesting. Are you comfortable using the word sin [/INST] so </s><s>[INST] deeply rooted in [/INST] religion? It is and in part and I struggle around this um um because I was brought up as a fundamentalist christian and so that is still there within me, there's trauma associated with that </s><s>[INST] probably uh layers of self deception mechanisms, [/INST] no doubt, no doubt </s><s>[INST] to hear slowly escaping, [/INST] trying to and trying to come into </s><s>[INST] a proper [/INST] respectful relationship with Christianity via a detour through buddhism daoism and pagan neo paganism, </s><s>[INST] trying to find a way how to love wisely. [/INST] Yes, exactly, and so I want to, I think the term sin is good because somebody may not be doing something that we would prototypical call immoral, but if they're feeling to love wisely, they are disconnecting themselves in some important way from the structures of reality. And I think I think it was hume, I may be wrong. You said, you know, people don't do things because they think it's wrong. They do a lesser good in place of a greater good. And that's a different thing than being immoral, immoral. We're saying you're doing something that's wrong. It's like, well, no, no, you know, I'm loving my wife, That's a great thing, isn't it? Yeah. But if you love your wife at the expense of your kids, like maybe something's going awry here, Right, Well, I love my country, great. But should you love your country at the expense of your commitment to the religion you belong to, like, people should wrestle with these questions. And I think sin is a failure to wrestle with these questions properly. </s><s>[INST] Yeah. To be content with the choices you made without considering. Um is there a greater good that could be done? [/INST] Yeah. </s><s>[INST] Your lecture series on the meaning crisis uh puts us in dialogue in the same way as with the podcast with a bunch of fascinating thinkers throughout history. Heidegger Corbin, uh the man carl Young tillage Barfield is there. Can you describe this might be challenging, but one powerful idea from each that jumps to mind. Maybe Heidegger. [/INST] So for Heidegger, one real powerful idea that has had a huge influence on me. He's he's had a huge influence on me in many ways, he's a big influence on what's called for in cognitive science, and this whole idea about the non proposition all that was deeply uh you know, afforded by Heidegger and Marleau Ponty, but I guess maybe the one idea if I had to pick one is his critique of an to theology, his critique of the attempt to understand being in terms of a supreme being, something like that, and how that gets us fundamentally messed up and we get disconnected from being because we are over focused on particular beings. Were failing to love wisely, we're loving the individual things and we're not loving the ground from which they spring. Can </s>
<s>[INST] What fascinating properties of rule 30 have you discovered over the years, you've recently announced the rule 30 prizes for solving three key problems. Can you maybe talk about interesting properties that have been kind of Revealed, Rule 30 or other cellular tomorrow? And what problems are still before us, like the three problems you've [/INST] announced. Right? So, I mean, the most interesting thing about cellular automata is that it's hard to figure stuff out about them, and that's some uh in a sense, every time you try and sort of uh you trying to bash them with some other technique you say, can I crack them? The answer is they seem to be uncrackable. They seem to have the feature that they are um that they're sort of showing irreducible computation. They're not you're not able to say, oh I know exactly what this is going to do, it's going to do this or that. </s><s>[INST] But there's a specific formulations of that [/INST] fact. Yes. Right. So I mean for example, in in Rule 30 in the pattern you get just starting from a single black cell, you get this sort of very very sort of random looking pattern. And so one feature of that, just look at the center column and for example, we use that for a long time to generate randomness and Wolfram language. Just You know what rule 30 producers? Now the question is can you prove how random it is. So for example, one very simple question. Can you prove that and never repeat? No. We haven't been able to show </s><s>[INST] that will never repeat. [/INST] We know that if there are two adjacent columns, we know they can't both repeat. But just knowing whether that center column can never repeat, we still don't even know that. Another problem that I sort of put in my collection of, you know, it's like $30,000 for three, you know, for these three prizes for about Rule 30 I would say that this is not one of those is one of those cases where the money is not the main point, but it's just uh you know, help some motivate somehow the investigation. </s><s>[INST] So there's three problems you propose to get $30,000 if you solve all three or maybe [/INST] no, it's 10 </s><s>[INST] 1000 for each for each. Right? [/INST] My the </s><s>[INST] problems that's right. Money is not the thing. The problems themselves are just clean [/INST] Formulations, just you know, will it ever become periodic? 2nd problem is are there an equal number of black and white cells </s><s>[INST] down the middle column, [/INST] down the middle column? And the third problem a little bit harder to state, which is essentially is there a way of figuring out what the color of a cell at position T down the center column is in a with a less computational effort than about T steps. So in other words, is there a way to jump ahead and say, I know what this is gonna do. You know, it's just some mathematical function of t um </s><s>[INST] or proving that there is no [/INST] way or proven. There is no way yes, but both. I mean, you know, for any one of these one could prove That, you know, one could discover, you know, we know what rule 30 days for a billion steps. But maybe we'll know for a trillion steps before too very long, but maybe at a quadrillion steps, it suddenly becomes repetitive. You might say how could that possibly happen. But so when I was writing up these prizes, I thought, and this is typical of what happens in the computational universe. I thought, let me find an example where it looks like it's just going to be random forever. But actually it becomes repetitive and I found one and it's just you know, I did a search, I searched, I don't know, maybe a million different rules with some criterion. And this is what's sort of interesting about that is I kind of have this thing that I say kind of silly way about the computational universe, which is, you know, the animals are always smarter than you are. That is there's always some way one of these computational systems is going to figure out how to do something, even though I can't imagine how it's going to do it. And you know, I didn't think I would find one that, you know, you would think after all these years when I found sort of all possible things uh um funky things that that I would have uh that I would have gotten my intuition wrapped around the idea that, you know, these creatures are always in the computational universe are always smarter than I am going to be. But </s><s>[INST] you know, they're equivalently, you're [/INST] smart, right? That's correct. And that makes it that makes one feel very sort of, it's humbling every time. Because every time the thing is is, you know, you think it's going to do this, so it's not gonna be possible to do this. And it turns out it finds a way </s><s>[INST] of course the promising thing is there's a lot of other rules like Rule 30, It's just rule 30 is [/INST] oh it's my favorite because I found it first. </s><s>[INST] And that's right. But the problems are focusing on rule 30, it's possible that rule 30 is repetitive after trillion steps. And that doesn't prove anything about the other rules. It does not. But this is a good sort of experiment of how you go about trying to prove something about a particular [/INST] Rule. And it also, all these things helped build intuition that is if it turned out that this was repetitive two trillion steps that's not what I would expect. And so we learned something from that. </s><s>[INST] The method to do that though would reveal something interesting about the [/INST] no doubt, no doubt. I mean It's although it's sometimes challenging. Like the, you know, I put out a prize in 2007 for for a particular touring machine that I was the simplest candidate for being a universal turing machine. And the young chap in England named Alex Smith after a smallish number of months that I've got a proof and he did, you know, it took a little while to iterate but you had a proof. Unfortunately, proof is very it's a lot of micro details. It's it's not it's not like you look at and you say aha, there's a big new principal, the big new principal is the simplest turing machine that might have been universal actually is universal. And it's incredibly much simpler than the turing machines that people already knew were universal before that. And so that intuition aly is important because it says computation, universality is closer at hand than you might have thought. Um but the actual methods are not in that particular case, but not terribly illuminating would </s>
<s>[INST] And then there's the crappy open source version that tries to copy, which is Mussolini. Yeah. That just like, that does the same exact thing, but does it kind of shittier. [/INST] So anyway. So my main thing about this is basically like trying to fight your factory in the physical world is probably not going to work. People are, I think, overconfident on this stuff, right? With that said, I think we want to at all, you know, the future is not yet determined, right? At all odds, you know, we want to avoid a hot war between like, I mean, a hot war between the US and China </s><s>[INST] would be- [/INST] Do you think it's possible that we'll get a war? We're doing these things like Pelosi going to Taiwan and trying to cause something. Like, look, again, this is one of these things which is complicated because obviously, if you're, there's more than one perspective on this, right? Again, you've got the US establishment, the US conservative, the Taiwanese perspective, the Chinese perspective, all the bystanders over there, there's more than one perspective on this, okay? If you're, you know, one of China's many neighbors, you look at China with apprehension. Like Vietnam, for example, has sort of fallen into, or not fallen into, is partnering with India because they are mutually apprehensive of China. China is not making like great friends with its neighbors. It's kind of, you know, it's demonizing Japan. It's so ultra-nationalist nowadays. And so if you're Taiwanese, you're like, yeah, I do not want to be under the Chinese surveillance state, I completely understand it. Some people are pro reunification, others aren't, but there's more, you know, trend, you know, in some ways for independence. </s><s>[INST] Okay, fine. But there's also an increasing temperature across the entire world. As we sit here today, there's speeches by Vladimir Putin about the serious possibility of a nuclear war. And that escalates kind of the heat in the room of geopolitics. [/INST] It escalates the heat in the room, of course, right? And the thing is, people have this belief that because something hasn't happened, it won't happen, or it can't happen. But there were a lot of measures people took during the Cold War to make sure a nuclear exchange didn't happen, the whole mutually assured destruction thing and communicating that out, and the balance of terror. There were smart guys on both sides who thought through this, and there were near misses, right? There's that story about the Soviet colonel who didn't order a nuclear strike because he thought it was just like an error in the instruments, right? Okay, what's the point? Point is, you know, for example, Pelosi going to Taiwan, that didn't strengthen Taiwan. That didn't like, if you're gonna go and provoke China, I thought scholar stages, his Twitter account had a good point, which is you should, if you're actually gonna do it, then you strengthen Taiwan with like huge battalions of like arms and material and you make them a porcupine and so on and so forth. Instead, her kind of going and landing there and mooning China and then flying back in the middle of a hot war with Russia, that's absolutely, you know, in the middle of an economic crisis or what have you, it just, you know, can you pick battles or whatever, right? It's like, you don't have to fight Russia and China at the same time. It's like kind of insane to do that, okay? Plus even with Ukraine, some people were like, oh, this was like a victory for the US military policy or something. There was a guy who, I'm not trying to beat him up or anything, he was like, this is in March, thread on US security assistance to Ukraine, it's working. Ukraine might be one of the biggest successes of US security assistance. And the reason is, you know, US didn't focus on some high-end shiny objects, but on core military tasks, that focus should remain. And it's like, how is this a success? The West gave massive arms to Ukraine only after the invasion, but not enough before to deter. And now Ukraine is like this Syria-like battleground with, you know, a million refugees or whatever the number is, right? Their country is blown to smithereens, thousands of people dead. Whatever $1,000 gas in Europe with like 10X energy, radicalized Russians, the threat of World War III or even nuclear war, you know, shooting somebody isn't, that's not like the point of the military. The point is, you know, there's a million ways to smash Humpty Dumpty into pieces and, you know, unleash the blood-drenched tides, right? And have people shooting each other and killing each other. It's really hard to maintain stability. That's what competence is, is deterrence and stability, right? There's not like a success in any way. </s><s>[INST] It's like an absolute tragedy for everybody involved, right? Yeah, I mean, deterrence, of course, is the number one thing, but there, you know, there's a lot to be said there, but I'm a huge not fan of declaring victory as we've done many times when it's the wrong. [/INST] Yeah, I mean, look, I mean, the other thing about this is the whole mission accomplished thing during a- Mission accomplished is what I meant, yeah. Exactly, mission accomplished was obviously, you know, the thing is Russia lives next door to Ukraine. And so, I mean, just like Iraq lives next door to Iran and Afghanistan is next door to Pakistan and China. And so if the US eventually gets tired of it and leaves, those guys are next door, right? And so, you know, who knows what's gonna happen here, okay? But one of the problems is like, you know, the whole Afghanistan thing or the Iraq thing is the lesson for people was the uncertainty. They're like, is the US gonna fight? Don't know. Will the US win if it fights? Don't know. Therefore, roll the dice. That uncertainty is itself like tempting to folks, you know, like Putin or whatever, right? So point is, coming all the way back up, we were talking about how history, the futures are passed and FDR, like the business plot, FDR failed, but like the tech companies were able to deplatform Trump, right? And the left libertarian would say, do we want that much corporate power, okay? And so that's, so we gave the four case for Trump deplatforming, protecting democracy, the Trump supporter case against, which is on the secret history of the shadow campaign, the save the 2020 election, basically that article, the left libertarian or libertarian case against. And then to me, what is, you know, like I am more sympathetic to the libertarian slash left libertarian against. And then also maybe the fourth group, which is the non-American case, right? Which is to say, every, you know, Amlo, he was the, you know, head of state of Mexico, I think at that time, okay? Amlo, Macron, you know, other folks, everybody who's watching this around the world basically saw, let's say U.S. establishment or Democrat aligned folks just decapitate, you know, the head of state digitally, right? Like just, boom, gone, okay? And they're like, well, if they can do that in public to the U.S. president who's ostensibly the most powerful man in the world, what does the Mexican president stand against that? Nothing, right? Like these U.S. media corporations, these tech companies are so insanely powerful, everybody's on Twitter or what have you, other than China, leaving them aside, they've got their own root system. If somebody tried to de-platform Xi Jinping off of Sino Weibo, they'd probably just fall through a trap door, you know, their whole family, right? But for the rest of the world, it's on the, that is hosting their business, their politics on these U.S. tech companies. They're like, regardless of whether it was justified on this guy, that means they will do it to anybody. Now the seal is broken. Just like the bailouts, as exceptional as they were when at first everybody was shocked about them, then they became a policy instrument. And now there's bailouts happening, every single bill is printing another whatever, </s>
<s>[INST] Yeah. Oh that's interesting. That's the case for, I was terrified of that, like a google, I thought I would become really comfortable in that air conditioned room and that I was afraid the quad situation is I mean what you present is really brilliant that it's exceptionally valuable. The lessons you learn because you get, you get, you get paid while you learn from others. If you see that if you see jobs in the space of your passion that way that is just an education, it's like the best kind of education. But of course you have from my perspective to be really careful not to get comfortable again in a relationship, then you buy a house or whatever the hell it is and then you get, you know, and then you convince yourself like, well I have to pay these fees for the car, for the cows, blah blah blah and then there's momentum and all of a sudden you're on your deathbed and there's grandchildren and uh you're drinking whiskey and complaining about kids these days. So I, you know that I'm afraid of that momentum, but you're right, like there's something special about education, you get working at these companies. [/INST] Yeah, I remember on my desk I had the like a bunch of papers on Quant Finance, a bunch of papers on optimization and then the paper on ethereum just on my desk as well and the white paper and it's like it's amazing how much how kind of and you can learn about, so that I also I think this like idea of like learning about intersections of things, I don't think there are too many people that know like as much about crypto and quant finance and machine learning as I do. And that's a really nice set of three things to know stuff about. And that was because I had like three time in my job. </s><s>[INST] Uh Okay. Let me ask the perfectly impractical but the most important question, What's the meaning of all the things you're trying to do? So many amazing things? Why what's the meaning of this? Life of yours [/INST] or ours? I don't know, humans. Yeah. So have you heard people say, asking what meaning of life is like asking the wrong question </s><s>[INST] or something? The question is wrong. No, that usually people get too nervous to be able to say that because it's like your question sucks. I don't think there's an answer. It's like the searching for it. It's like sometimes asking it, it's like sometimes sitting back and looking up at the stars and being like, uh huh I wonder if there's aliens up there. There's, there's a useful um like a palate cleanser aspect to it because it kind of wakes you up to like all the little busy hurried day to day activities. All the meetings, all the things you like a part of, we're just like ants, part of a system are part of another system. And and then when this asking this bigger question allows you to kind of zoom out and think about it, but there's ultimately, uh I think it's an impossible thing for a limited capacity, the cognitive capacity to capture, but it's fun to listen to somebody who is exceptionally successful, exceptionally busy now who's also young. Like you, they asked these kinds of questions about like uh death, you know, do you consider your own mortality kind of thing? And and life whether that enters your mind because it often doesn't get it kind of almost gets in the way. [/INST] Yeah. It's amazing how many things you can like that are trivial that could occupy a lot of your mind until something until something bad happens or something flips you. </s><s>[INST] And then you start thinking about the people, you love that in your life. Then you started thinking about like holy sh it this right ends. [/INST] Exactly. Yeah. I just had Covid. Um and I had it quite bad. It wasn't, it wasn't really bad. It was just like, I also got a simultaneous like lung infection, so I had like almost like bronchitis or whatever. I don't even, I don't understand that stuff, but it felt I I started and then you forced to be isolated, right? And so it's actually kind of nice because it's very, it's very depressing. Uh and then I've heard stories of, I think it's drawn parker, He had like all these diseases as a child and he had to like just stay in bed for years and then he like made napster, it's like pretty cool. Um so yeah, I had about 15 days of this recently, just last month and it feels like it did shock me into a new kind of energy and ambition. </s><s>[INST] Were there moments when you were just like terrified at the combination of loneliness and like, you know, the thing about Covid is like there's some degree of uncertainty uh like it feels like it's a new thing, a new monster that's arrived on this earth and so, you know, dealing with it alone, a lot of people are dying. It's like wondering like, [/INST] yeah, you do wonder, I mean for sure, and then these there are even um new strains in South Africa, which is where I was and maybe maybe the new strain had some interaction with my jeans and I'm just going to die. </s><s>[INST] But ultimately it was liberating. [/INST] So I loved it. Oh, I loved I love that I got out of it. Uh because it also affects your mind. You get you get confusion and kind of a lot of fatigue and you can't do your usual tricks of psyching yourself out of it. So, you know, sometimes it's like, oh man, I feel tired, okay, I'm just gonna go have coffee and then I'll be fine. It's like now it's like I feel tired, I don't even want to get out of bed to get coffee because I feel so tired and then you have to confront uh there's no like quick fix cure and you're trapped at home. But that, </s>
<s>[INST] It's the psychology question because there's something really pleasant about, you know, pointing out that the emperor has no clothes when everybody like uh you know, thinking outside the box and coming up with the true answer where everybody else is diluted, There's something, I mean, I have that for science, right. You want to prove the entire scientific community wrong. That's the whole, [/INST] that's right. And of course historically, lone geniuses have come out right sometimes. Yes. But often people who think they're alone genius and much more often turned out not to. Um, so you have to judge each case on its merits. The mere fact that you're a maverick, the mere fact that you you're going against the current tide doesn't make you right. You want to show you're right by looking at the evidence. </s><s>[INST] So because you focus so much on on religion and disassembled a lot of ideas there and I just, I was wondering if if you have ideas about conspiracy theory groups, because it's such a prevalent, even reaching into uh presidential politics and so on. It seems like it's a very large communities that believe different kinds of conspiracy theories. Is there some connection there to your thinking on religion? And I'm curious, [/INST] it's a matter, it's an obviously difficult thing. I don't understand why people believe things that are clearly nonsense like Well flat earth and also the conspiracy about not landing on the moon or um, that the United States engineered 9-11, that that kind of thing. Um, </s><s>[INST] so it's not clearly nonsense. It's extremely unlikely. [/INST] Okay, it's extremely unlikely that religion is a bit different because it's passed down from generation to generation. So many of the people who are religious got it from their parents who got it from their parents who got it from their parents and Childhood indoctrination is a very powerful force, but these things like the 9-11 conspiracy theory, the Kennedy assassination conspiracy theory, the man on the Moon conspiracy theory, these are not childhood indoctrination, these are um presumably dreamed up by somebody who then tells somebody else who then wants to believe it. And I don't know why people are so eager to fall in line with some to some person that they happen to read or meat who spin some yarn. I can kind of understand why they believe what their parents and teachers told them when they were very tiny and not capable of critical thinking for themselves. So I sort of get why the great religions of the world like Catholicism and Islam, go on persisting. It's because of childhood indoctrination, but that's not true of flat earth is um and sure enough, flat earth is um is a very minority cult </s><s>[INST] way larger than I ever realized. [/INST] Well, yes, I know, </s><s>[INST] but so that's a really clean idea, you've articulated in your new book and then, and I'll go and God and then got delusion is the early indoctrination. That's really interesting. You can get away with a lot of out there ideas in terms of religious texts if uh the age at which you convey those ideas at first as a young age. So indoctrination is sort of an essential element of propagation of religion. Uh so let me ask on the morality side in the books that I mentioned, God delusion and I'll go and God you describe that human beings don't need religion to be moral. So from an engineering perspective, we want to engineer morality into ai systems. So in general, where do you think morals come from in humans? [/INST] A very complicated and interesting question. It's clear to me that the moral standards, the moral values of our civilization changes as the decades go by, certainly as the centuries go by, even as the decades go by and We in the 21st century are quite clearly labeled 21st century people. In terms of our moral values, there's a spread. I mean, some of us are a little bit more ruthless, some of us more conservative, some of us more more liberal and so on. But we all subscribe to pretty much the same views when you compare us with, Say 18th century, 17th century people, even 19th century 20th century people. Um, so we are much less racist, were much less sexist and so on than we used to be. Some, some people are still racist and some are still sexist. But the spread has shifted that the Gaussian distribution has moved and moves steadily as the centuries go by. And that is the most powerful uh influence. I can see on our moral values and that doesn't have anything to do with religion. I mean, the the religion of the story of the morals of the old testament, uh, Bronze Age models, models are deplorable. Um, and um, they are to be understood in terms of the people in the desert who made them up at the time. And so, human sacrifice. Um, uh, an eye for an eye and a tooth for a tooth. Petty revenge killing people for breaking the sabbath, all that kind of thing. Um, inconceivable. </s><s>[INST] No. So at some point, religious texts may have in part reflected that Gaussian distribution at that [/INST] time. They did. I'm sure they always </s><s>[INST] reflect that and then now, but the sort of almost like the meme, as you describe it of ideas moves much faster than religious text to the new religion, [/INST] basing your morals on, on religious texts, which are written millennia ago, um, is not a great way to proceed. I think that's pretty clear. So, um, not only should we not get our morals from such text, but we don't, we quite clearly don't. Um, if we did, then we'd we'd be discriminating against women and we'd be, we'd be racist, we'd be killing homosexuals and so on. Um, so, so we, we we don't, and we shouldn't. Now, of course it's possible to By the, to use your 21st century standards of morality. And you can look at the Bible and you can cherry pick particular verses which conform to our modern morality. And you'll find that jesus says a pretty nice things, which is great. But you're using your 21st century morality to decide which versus to pick which versus to reject. And so why not cut out the middleman of the bible and go straight to the 21st century morality, which is where that comes from. It's a much more complicated question. Why is it that morality, moral values change as the centuries go by? The undoubtedly do. And it's a very interesting question to ask why It's a it's another example of cultural evolution, justice, technology progresses. So moral values progress for probably very different reasons. </s>
<s>[INST] think uh you you seriously concerned about this kind of thing where the ideas of sovereignty and that Bitcoin espouses would would actually one day be tested. Do you have like a legitimate concern because you said like one day very well might. Do you think it might [/INST] Yeah. Well, first of all, Bitcoin has been attacked again many times and we talk about the, you spoke about this with nick carter on your show, the sort of protocol wars or conflict or whatever. Right? And they almost died a whole bunch of times during that and ended up surviving. </s><s>[INST] Oh wow, I didn't, I didn't know how bad [/INST] it got it was, it was sort of a very existential threat and the queen survived and that's why I am so intrigued by it is that it basically survived an attack in an environment several years ago when Bitcoin was much more vulnerable than it is today. Um It survived an attack by a conglomeration of chinese billionaires, Silicon valley corporations and a ton of people who owned the majority of the hash rate and all this infrastructure, </s><s>[INST] They had 83 [/INST] percent of all the hash rate and they couldn't get what they wanted. And that was so intriguing to me. Like why didn't why didn't get killed? So as Nick said, I think you should read the block size war which is a book that you can get on amazon by Jonathan beer. Really good kind of like really important to understand the scaling conflict and the visions over the different visions of what the coin should be and you know, again, people like me believe it should be a freedom tool, not like a payments technology for retail and I'm just I'm glad it worked out the way it did because it almost didn't. </s><s>[INST] Do you think humans civilization will destroy itself? So if we think about all the threats facing human civilization, nuclear war, natural or engineer pandemics, You know, we talk about human rights violations, we talk about, uh, authoritarian governments, uh, taking control of the money supply. But do you have a great grander concerns for the future of human civilization? Do you have hope for us becoming multi planetary species? [/INST] Yeah, I mean, I guess long term we want to decentralize, right? We don't want a single point of failure in the earth is a single point of failure. Um, but no, I mean, you look at all this kind of like space fiction and I mean, who would want to live on mars man? It's like a freaking desert. I mean, the earth is so beautiful. I hope we can save it. You know, it's just so gorgeous when you look at the earth compared to any other like exoplanet or whatever you look at it. I mean, the earth is so spectacular and wondrous and singular. I think we've got to do everything we can to save it here. </s><s>[INST] That's funny. I mean, I uh, sure a lot of people would have said that about europe before the explorers ventured out columbus and the rest into the unknown. The thing about human nature is that we are explorers to some small fraction of us are insane enough to exploring the most dangerous grounds. And I'm pretty sure there's quite a few people that would love to take the first step on mars the first few steps on MArs in the harshest of environments, even when the odds of survival extremely low. And I'm thankful for those people because I sit back and drink my vodka back here on earth and enjoy [/INST] good friendships because </s><s>[INST] I think ultimately that step to MArs is going to be a first step into a multi into uh exploring and colonizing the rest of the galaxy. Mars might be a harsh environment, but maybe space is not uh, like uh other planets, other exoplanets, but also forget planets, just creating colonies that float about in space. Um, there's exciting technologies that are yet to be discovered yet to be engineered and built that I think require that first painful step. Like uh yeah, the journey of 1000 miles starts with one step. I think MArs is that first step. [/INST] Yeah, No, I was born the day before the challenger blew up. And it was always so tragic for me to look back on that because that really like altered our arc in terms of space exploration. Like that had not happened, we'd be in a very different arc and I do respect and admire people pushing for exploration, but at the same time, I just want to recognize like we just, you know, we know how unique earth is and I do think we got to do everything we can to to protect them. </s><s>[INST] But I think you have would answer the question if we're going to destroy ourselves, [/INST] I guess? Yeah. Yeah. I guess you do not Okay fine. If we do not decentralize properly out into different physical space is probably I guess. Yeah. </s><s>[INST] And I mean, do you have concerns that are immediately facing you? So um not in terms of the injustices on the world, but nuclear [/INST] war? Look, I'm a lot more concerned about what's happening right now. Like what is destroying ourselves? If you were to go and see what's happening in Xinjiang or North Korea right now or Eritrea that is destroying ourselves and it's already happened. So I guess the end, that's why I said yes, I mean if you don't decentralize and powers completely under one person, um life is destroyed as we know it. And you know, you don't have to go into science fiction to know what a totalitarian hellscape dystopia is. There's several that exists already. And you know, let's try to help those people at the same time as we're trying to like push out into space would be my leg counter I guess. </s>
<s>[INST] which sucks because life is finite and when you commit, you say, well, I'm never going to be good. Like when you choose one of these two passions, one of the two things you're interested in, you're basically saying, I'm letting go. I'm saying Macedonia to uh that's [/INST] true. That's true. Which is actually what does your means letting go? That's exactly right. I think that's exactly right. I think that's, I think you do have to make choices. You have to set priorities. I often laugh at students who tell me they want to have like three majors. If you have three majors who have no major, right? I mean, so I do think you have to make choices. I also think, um, it's important that whatever you do, even if it's a small thing you do, you always do the best you can, you always do excellent work. My kids are tired of hearing me say this at home, but I believe everything you do should be about excellence. The best you can do. If I'm going to wash the dishes, I'm gonna be the best person washing the dishes right? If I'm going to write a book review with the best possible book review I can. Why? Because you develop a culture among about yourself, which is about excellence? </s><s>[INST] Yeah, I was, I was telling you offline about all the kind of stuff, google fiber and cable installation, all that stuff. I've been always a believer washing dishes. People don't often believe me when I say this, I don't care what I do. I am with David Foster Wallace, I'm unbearable. There's so much joy for me I think for everyone. But okay, let me just speak for me to be discovered in getting really good at anything. In fact getting good at stuff that most people believe is boring or menial labor or uh, you know, impossible to be interesting. That's even more joyful to find the joy within that in the excellent. It's the Jiro dreams of sushi making the same fricking sushi over and over and becoming a master of that. That's, that can be truly joyful, [/INST] there's a sense of pride and on the pragmatic level, you never know when someone will spot that and uh intelligent people who perform at the level of high excellence, look for others </s><s>[INST] and it radiates some kind of signal. It's weird, it's weird what you're, it's weird what you attract to yourself when you just focus on mastery and and pursuing excellence and something like this is a cool thing uh about it. That's the joy of really truly experienced. I didn't have to do much work. It's just cool people kind of, I find myself in groups of cool people, like really people who are excited about life, we're passionate about life, there's a fire in their eyes. That's uh you know, at the end of the day, just makes life fun, you know, something and then also money wise, at least in this society we're fortunate to where if you do that kind of thing, money will find a way. Like I have the great I say this that don't care about money, you know, I have to think about what that means, because some people criticize that idea is like, yeah, that must be nice to say that uh because I have for much, many periods of my life had very little money, but I think or live in a society where not caring about money, but just focusing on your passions, if you're truly pursuing excellence, whatever that is, money will find you, that's I guess the ideal of the capitalist system [/INST] and I think that the entrepreneurs, I've studied and have the chance to get to know and I'm sure you'd agree with this, they, they do what they do because they're passionate about the product, they're not just in it to make money. In fact, that's when they get into trouble. We're just trying to make money. </s><s>[INST] Exactly. You said your grandmother Emily had a big impact on your life. She lived 202, What are some lessons she taught you [/INST] Emily who was the child of immigrants from, from Russia and Poland, who never went to college. Her proudest day I think was when, when I went to college, um, she um she treated everyone with respect and tried to get to know everyone, she knew every bus driver in the town, she'd remember their birthdays and one of the things she taught me is no matter how high you fly, the lowest person close to the ground matters to you and uh, you treat them the same way you treat the billionaire at the top of the podium. And she, she did that, she didn't just say that some people say then don't do it. She really did that. And I always remember that it comes up in my mind at least once a week because we're all busy doing a lot of things and you either see or you even feel in yourself the desire to just for, for the reasons of speed, to be short or not polite with someone who can't do anything to harm you right now. And I remember her saying to me, no, you you don't, you treat everyone with respect, you treat you know the person you're on the phone with, right customer service, you treat that person if you're talking to Jeff Bezos, so you're talking to Elon musk, right? Uh and and I think making that a culture of who you are so important and people notice that that's the other thing and they notice when it's authentic. Everyone's nice to the person at the bottom of the totem pole when you want to get ahead in the line for your driver's license. But are you nice to them when you don't need that? They notice that. </s>
<s>[INST] And I think basically, it's something where the reason it needs that would fix the FDA. Sorry to interrupt. Yes, we fix FDA by Yes, we fix FDA by exiting the FDA. Yeah, right. And then the FDA [/INST] would dry out and then it would hopefully, it might reform in my dry out, right. And this is, you know, why people are, for example, they're traveling across borders, you know, the gang orders from Canadian pharmacies, you know, a lot of this type of stuff, we can start to build alternatives, right? I mean, India's generic industry is really important, because it just doesn't enforce American IP there. So generic drugs are cheaper, right? And it's quite competent, it's been around for a while. So there's enough proof points there, where, again, I'm not seeing a panacea, it's going to be something which will require like American and Indian collaboration, I think there's going to be a lot of other countries and so on that are involved. You can start to see another poll getting set up, which is a confident enough civilization that is willing to take another regulatory path, right? And that is in some ways doing better on national software than the US's and it has enough of a bridge to the US that it can be that simulation, which you need, which is kind of something that outside poke, right? I want to talk about India, but let me just kind of wrap up on this big FDA, biomedical kind of thing, right? With the book, the network state, the purpose of the network state, you know, I want people to be able to build different kinds of network states, I want people to build the vegan village, I want people to be able to build a, you know, if they want to do the benthic option like a Christian network state, if people want to do different kinds of things, I'm open to many different things and I will fund lots of different things. For me, the motivation is just like you need to start a new currency, Bitcoin, it was easier to do that than to reform the Fed, I think it's easier to start new country than to form the FDA. And so I want to do it to, in particular, get to longevity, meaning longevity enhancement. And what does that mean? So in an interesting way, and this will sound like a trite statement, but I think it's actually a deep statement, or maybe hopefully try to convince you it is, crypto is to finance, or what longevity is to the current state of medicine. Why? It inverts certain fundamental assumptions. So at first, crypto looks like traditional finance, it's got the charts and the bands, and you're buying and selling, so on. But what Satoshi did is he took fundamental premises and flipped them. For example, in the traditional macroeconomic worldview, hyperinflation is bad, but deflation is also bad. So a little inflation is good, right? In the traditional macroeconomic worldview, it's good that there are custodians, banks that, you know, kind of intermediate the whole system, right? In the traditional, you know, worldview, every transaction needs to be reversible because somebody can make a mistake and so on and so forth, right? In the traditional worldview, you don't really have root access over your money. Satoshi inverted all of those things. Okay, obviously, you know, the big one is hyperinflation is bad, but he also thought mild inflation was bad, and deflation was good. That's just a fundamental shift. Okay. He gave you root access over your money. You're now a system administrator of you're own money. You can RUM-RF your entire fortune, or send millions with a keystroke. You are now the system administrator of your own money. That alone is why cryptocurrency is important. If you want system administration access at times to computers, you'll want it to currency, right? To be sovereign. You know, there's other assumptions where like the assumptions is every transaction is private in the existing system by default, or it's visible only to the state, whereas at least the initial, you know, the Bitcoin blockchain, everything is public, right? There are various kinds of things like this, where he just inverted fundamental premises. And, and then the whole crypto system is in the crypto economy is in many ways a teasing out of what that means. Just to give you one example, the US dollar, people have seen those graphs, where it's like inflating. And so it just like loses value over time. And you've seen that, okay? Whereas in most of the time, it's just sort of deny that it's losing any value. The, the, the most highbrow way of defending it is the US dollar trades off temporary short term price stability, for long term depreciation, and Bitcoin makes the opposite trade off, in theory, at least long term appreciation at the expense of short term price instability, because like, you know, there's the whole plunge protection team, and so on. Basically, there's there's various ways in which price stability is tried to be maintained in the medium term, at the expense of long term depreciation, you need to like a reserve assets to keep, you know, stabilizing the dollar against various things. So what does crypto medicine look like relative to fiat medicine to make the same analogy, right? The existing medical system, it assumes that a quick death is bad and early death is bad, but also that living forever is either unrealistic or impossible or undesirable, that you should die with dignity or something like that. Okay. So a little death is good. That's existing medical system. Whereas the concept of life extension, and, you know, David Sinclair, and you know, whether you call it health span, says rejects that fundamental premise. And it says, actually, the way to defeat cancer is to defeat aging, aging is actually a program biomedical, biological process. And we can, we have results that are showing stopping or even reversing aging in some ways. And so now just like, just like with the other thing, you say, a quick death is bad. And so is actually death itself. Right? So we actually want significant life extension. This is similar. It's very, it's very similar to what, you know, the rejection of the the fiat system, right? The fiat system says, a little inflation is good. Fiat medicine says a little death is good. Bitcoin says actually, no inflation, just get more valuable over time. And crypto medicine says, actually, let's, you know, extend life. This leads to all kinds of new things where you start actually thinking about, all right, how do I maintain my health with, you know, diagnostics? How do I, you know, take control of my own health with the decentralization of medicine? All the stuff that I've been describing sort of fits like longevity </s>
<s>[INST] that's probably studies on this now happening either have happened or are happening. The effect of seeing your own face on on camera because it's reminding you that you're supposed to be acting a certain way. And that's that is especially a stressful thing. [/INST] Yeah, you can't be in the moment as much. But I mean for you, you you make the decision to do all your podcast interviews in person, right? And so </s><s>[INST] and that's even when it's very costly if there's any kind of chemistry that contributes at all to the conversation, which I think most conversations have come to even the boring work meanings, there's something there because yes, you're trying to solve a particular problem at this particular time, but underneath it, there's a team building that's happening. And [/INST] honestly, </s><s>[INST] people also have told me about this, why they enjoyed the zoo meetings during the pandemic. It's like they're lonely, [/INST] like </s><s>[INST] they, you know, it's annoying to have to sit and listen to folks talk about nothing and so on, but they tune in anyway because it's kind of lonely to sit there by yourself and that I mean there's a deep connection there when you're with other people and that is especially true when they're they're in personal, which is a huge concern for me for like more and more offices from a capitalist perspective realizing, hey, why are we, why do we have these large office spaces? Why do we have to get people together? But I think in some, in some deep sense we do. But then you also talk about that once we do we want to protect the introverts, like you don't want the open space, which office space, which was a big fad for a while. I don't know where people stand on that point. [/INST] I think people are figuring it out in a post pandemic context, but I mean I know what you mean. So Before I became a writer, I was a corporate lawyer for like seven years and literally the only thing I miss from those years is hanging out with people at the office like I don't know just some of the funniest moments I've had in my life came from being at the office until midnight with the other people I was working with. So I know exactly what you're talking about. So I will say the offices there at that firm and at most firms in those days everybody had their own office. So it was like a dorm room. You know where it was like a long hallway with everybody in their own little dorm room. Um So you had tons of privacy but you would also come out and you can </s><s>[INST] roam whenever you want. [/INST] Yeah </s><s>[INST] and whenever you're Rome that means you're kind of open, you're looking for trouble, [/INST] your </s><s>[INST] interaction [/INST] and the extent to which you would keep your door open. You know. Is it wide open or was it half a jar or just a little bit? Those are all signals. </s><s>[INST] So is there because you said reenergized? Is there? Do you like to think? And again the human mind is complicated but do you like to think of it as like a bucket that gets refilled for introverts in terms of energy of um social interaction that that able to handle it is do you think of it like that as as a bucket that gets empty and needs to be refilled. [/INST] I think of it. Yeah more or less because I use the metaphor of a battery that gets recharged or not. It's basically the same thing. Different metaphor. But yeah, but just to add on that there is a layer of complexity to that because you could be somebody who doesn't want the kind of social life let's say where you have to be like on and presenting and interacting with tons of people all the time but you get really lonely if you were just by yourself, you know? So what you want is to maybe be in the company of a couple of people you know really well. Like for me the pandemic was not actually that hard for me personally. I mean I lost family but I mean from the point of view of what we're talking about it wasn't that hard because I live with my husband and my kids. So I knew it was hard on the kids and I felt badly for them. But for me I was like you know what, I kind of have a lot of social life right here in the house </s><s>[INST] and do [/INST] my work. Yeah. That's </s><s>[INST] the cool thing about the pandemic. I think it helped people figure out how much they love their family. [/INST] That's </s><s>[INST] true and and while you give you a chance to really reconnect with kids with your kids, like really spend time with them. It's just fascinating to watch. Like people actually it did strengthen the family unit and and often beautiful way, which just sucks to, to, to have to leave behind at this point. [/INST] Yeah. And I think that's part of what people are not gonna want to go back to that we need to solve for. Um to the extent that work becomes non remote. Again, I think people have just realized how precious those aspects of their lives are and you know, for somebody who's in a conventional office job where you're going home and seeing your kids for an hour before bedtime and that's your interaction with them. That's that's kind of a ridiculous way to set things up. </s>
<s>[INST] the eye and the AM and the I am is all kind of emerging through this whole process of evolution and so on. That's uh, let's just surface waves and there's a much deeper ocean that we're trying to figure out here. So how does you said they said that some of the stuff you're thinking about maps the spacetime, How does it map the space? [/INST] So, so just a very, very high level and I'll keep it brief. The structures that the physicists are finding Like the Apple two hedren. It turns out they're just static structure, their polyps but they remarkably, most of the information in them is contained in permutation matrices. So it's a matrix, like an N by N matrix that just has zeros and ones that contains almost all of the information. And you can they have these plastic graphs and so forth that they use to boot up the scattering, you can compute the scattering amplitudes almost entirely from these permutation matrices. So that's just now, from my point of view, I have this conscious agent dynamics. It turns out that the stationary dynamics that I was talking about were the entropy is increasing All the stationary dynamics are sketched out by permutation matrices. So, if you so called birkoff polito all the versaces of this public ip all the points, our permutation matrices and all the internal points are marco Vienne kernels um that have the uniform measure as a stationary measure. </s><s>[INST] I need to into it a little better. What what the heck you're talking about. But so basically there's some complicated thing going on with the network of conscience conscious agents and that's map a ble to this. You're saying it two dimensional matrix that uh scattering has to do with what the perception like, that's like photon stuff. I mean, I don't know if it's useful to sort of dig into detail. [/INST] I'll do just a high level thing. So the the high level is the long term behavior of the conscious agent dynamics. So that's the projection of just looking at the long term behavior I'm hoping will give rise to the Apple two hedren. The Upper two Hedren then gives rise to space time. So then I can just use their link to go all the way from consciousness through its asthma topics to through the application into space time and get the map all the way into our interface. </s><s>[INST] And that's why you mentioned the permutation matrix, because it gives you a nice thing to try to generate. It's the [/INST] connection with the amplitude, the permutation matrices are the core of the amplitude Hedren. And it turns out they're the core of the asthma topic, description of the conscious agents. </s><s>[INST] So not to sort of bring up the idea of a creator, but I like, first of all, I like video games and you mentioned this kind of simulation idea first of all, do you think of as an interesting idea, this thought experiment that we live in a simulation. And in general, do you think we live in a simulation? [/INST] So, the nick Bostrom idea about the simulation is typically couched in a physical ist framework. So there's the bottom level there's some programmer in a physical space time and they have a computer that they've programmed, brilliant cleverly where they've created conscious entities. So you have the hard problem of consciousness. Right. The standard heart problem. How could a computer simulation created, which isn't explained by that simulation theory. But then the idea is that the next level the the entities that are from the that are created in the first level simulation then can write their own simulations and you get this this nesting. So so the idea that this is a simulation is fine, but the idea that starts with a physical space, I think, yes, </s><s>[INST] there's there's different properties here. The partial rendering. And to me that's the interesting idea is not whether the entirety of the universe is simulated, but how efficiently can you um create interfaces that are convincing to all other entities that can appreciate such interfaces? How little does it take? Because you said like partial rendering or like temporal, a thermal rendering of stuff? Only render the tree falling in the forest when there's somebody there to see it. It's interesting think how can you do that super efficiently without having to render everything? And that to me is one perspective on the simulation, just like it is with video [/INST] games, where </s><s>[INST] video game doesn't have to render every single thing. It's just the thing that the observer is looking at [/INST] right there is actually that's a very nice question. And there's whole groups of researchers that are actually studying in virtual reality. What what is the sort of minimal requirements on the system. What how does it have to operate to give you an immersion experience to give you the feeling that you have a body to to get you to take it real and and there's actually a lot of really good work on that right now. And it turns out it doesn't take that much. You do need to get the perception action loop tight and you have to give them the perceptions that they're expecting if you want them to, but if you you can lead them along, if you give them perceptions that are close to what they're expecting, you can then maybe move their reality around a bit. </s><s>[INST] Yeah, it's a trick engineering problem, especially when you're trying to create a product that costs little, but that's it feels like an engineering problem, not a deeper scientific problem. Um or meaning obviously it's a scientific problem, but it's a scientific problem. It's not that difficult to trick us descendants of apes. But [/INST] here's here's a case for just us in our own, this is a virtual reality that we're experiencing right now. So here's something you can try for yourself if you just close your eyes and look at we're experience in front of you to be aware of your experience in front of you, which you experience is just like a model dark gray, but there's all sort of there's some dynamics to it, but it's just dark gray. But now I ask you, instead of having your attention forward, put your attention backward, what is it like behind you with your eyes closed? Mhm. And there? it's like nothing. </s>
<s>[INST] on that one. So those two things are fascinating. So how do you have as a leader as that self awareness? So you just said it's really hard to be self aware. So for you personally, or maybe for other leaders you've seen or look up to, how do you know the both of the things you're doing are the wrong things to be doing, the way you speak to others, the way you behave and the things you're not doing, How do you how do you get that? There's [/INST] two aspects that one is like processing feedback that you're getting. So </s><s>[INST] how do you get feedback? [/INST] All right. So are you getting feedback? Right. So one way we do it, for example, discourse, we have three co founders and we periodically talk about decisions before we make them. So it's not like one person can make a mistake or like, wow, that's, you know, there can be misunderstanding things. So it's part of like, group consensus of leadership is like, it's good to have I think systems where there's one leader and that leader has the rule of absolute law are just really dangerous in my experience for communities, for example, like if you have communities run by one person, that one person makes all decisions, that person is gonna have a bad day, something could happen to that person. You know, something, you know, there's a lot of variables. So like at first when you think about leadership have multiple people doing leadership and have them talk amongst each other. So giving each other feedback about the decisions that they're making and then when you do get feedback, I think there's that little voice in your head, right? Like or your gut or wherever you want to put it in your body. I think that voice is really important. Like I think most people who have any kind of moral compass or like want to do, most people want to do the right thing, I do believe that. I mean there might be a handful of sociopaths out there that don't but most people, they want other people to think of them as a good person and why wouldn't you? Right? Like do you want people to despise you? I mean that's just weird, right? So you have that little voice that sort of the angel and devil on your shoulder sort of talking to you about like what you're doing, how you're doing, how does it make you feel to make these decisions right? And I think having some attunement to that voice is important, </s><s>[INST] but you said that voice also for I think there's a programmer situation to where sometimes the devil on the shoulder is a little a little too loud, so you're a little too self critical for a lot of developers, especially when you have introverted personality, how do you struggle with the self criticism of the criticism others. So one of the things of leadership is to do something that's potentially unpopular or where people doubt you and you still go through with the decision. So what's that balance? Like I [/INST] think you have to walk people through your decision making right? Like this is where blogging is really important. Communication is so important. Again, code language is just another kind of code is like here is the program by which I arrived at the conclusion that I'm gonna reach, right? It's one thing to say like this is a decision, it's final deal with it, right? That's not usually satisfying to people. But if you say, look, you know, we've been thinking this problem for awhile. Here's some stuff that's happened. Here's what we think is right? Here's our goals here is we want to achieve. And we've looked at these options and we think this available options is the best option. People be like, oh, ok, right. Maybe I don't totally agree with you, but I can kind of see where you're coming from. And like I say, it's not just arbitrary decision delivered from a cloud of flames in the sky, right? It's like a human trying to reach some kind of consensus about goals and their goals might be different than yours. That's completely legit, right? But if you're making that clear, it's like, oh well the reason we don't agree because we have totally different goals, right? Like how could we agree? It's not that you're a bad person is that we have radically different goals in mind when we started looking this problem </s><s>[INST] and the other one you said is passion, so or hard work. Sorry, uh [/INST] those are tied together to me in my mind, I mean that's a hard work compassion like for me like I just really love the problem discourse is sending out to solve because in a way it's like there's a there's a vision of the world where it all devolves into facebook basically owning everything and every aspect of human communication, right? And this has always been kind of a scary world for me. Um first because I don't think facebook is really good at execution, I gotta compliment them, they're very competent in terms of what they're doing. But facebook has not much of a moral compass in terms of facebook cares about facebook really, they don't really care about you and your problems, What they care about is how big they can make facebook right, </s><s>[INST] is that you're talking about the company or just a mechanism how facebook works kind [/INST] of both really right? Like and the idea with this course, the reason I'm so passionate about it because I believe every community should have the right to own themselves right? Like they should have their own software that they can run that belongs to them, that's their space where they can set the rules and if they don't like it, they can move to different hosting or you know, whatever they need, they need to happen can happen, but like this, this idea of a company town where all human communication is implicitly owned by WhatsApp instagram and facebook. And it's really disturbing to because facebook is really smart, like I said, they're great execution buying and what's happened buying instagram were incredibly smart decisions. Um and they also do this thing on, if you know, but they have this VPN software that they give away for free on smartphones and it indirectly feeds all the data about the traffic backed facebook so they can see what's actually getting popular through the VPN right? They have low level access to the network data because users have let them have that. So, </s>
<s>[INST] I'll tell you that. So this is the study of these constraints, [/INST] systems that are supposed to deal with physical objects. Systems that are supposed to deal with physical objects. So if you look at cognitive psychology, you can see there's multiple types of memory, which are to some extent represented by different subsystems in the human brain. So we have episodic memory, which shakes into account our life history and everything that's happened to us. We have declarative or semantic memory, which is like facts and beliefs abstracted from the particular situations that they occurred in. There's sensory memory, which to some extent is sense modality specific, and to some extent is unified across sense modalities. There's procedural memory, memory of how to do stuff, like how to swing the tennis racket, right? Which is, there's motor memory, but it's also a little more abstract than motor memory. It involves cerebellum and cortex working together. Then there's memory linkage with emotion which has to do with linkages of cortex and limbic system. There's specifics of spatial and temporal modeling connected with memory, which has to do with hippocampus and thalamus connecting to cortex. And the basal ganglia, which influences goals. So we have specific memory of what goals, sub-goals and sub-sub-goals we wanted to perceive in which context in the past. Human brain has substantially different subsystems for these different types of memory and substantially differently tuned learning, like differently tuned modes of long-term potentiation to do with the types of neurons and neurotransmitters in the different parts of the brain corresponding to these different types of knowledge. And these different types of memory and learning in the human brain, I mean, you can back these all into embodied communication for controlling agents in worlds of solid objects. Now, so if you look at building an AGI system, one way to do it, which starts more from cognitive science and neuroscience is to say, okay, what are the types of memory that are necessary for this kind of world? Yeah, yeah. Necessary for this sort of intelligence. What types of learning well with these different types of memory and then how do you connect all these things together? And of course the human brain did it incrementally through evolution because each of the sub-networks of the brain, I mean, it's not really the lobes of the brain. It's the sub-networks, each of which is widely distributed. which of each of the subnetworks of the brain co-evolved with the other subnetworks of the brain, both in terms of its patterns of organization and the particulars of the neurophysiology. So they all grew up communicating and adapting to each other. It's not like they were separate black boxes that were then glommed together, right? Whereas as engineers, we would tend to say, let's make the declarative memory box here and the procedural memory box here and the perception box here and wire them together. And when you can do that, it's interesting. I mean, that's how a car is built, right? But on the other hand, that's clearly not how biological systems are made. The parts co-evolved so as to adapt and work together. </s><s>[INST] So this- That's better necessary for this kind of world. By the way, how every human engineered system that flies, that was what we were using that analogy before is built as well. So do you find this at all appealing? Like there's been a lot of really exciting which I find strange that it's ignored work in cognitive architectures, for example, throughout the last few decades. [/INST] Do you find that more interesting? Yeah, I mean, I had a lot to do with that community. And Paul Rosenbloom, who was one of the, and John Laird who built the SOAR architecture are friends of mine. And I learned SOAR quite well in ACT-R and these different cognitive architectures. And how I was looking in the AI world about 10 years ago before this whole commercial deep learning explosion was, on the one hand, you had these cognitive architecture guys who were working closely with psychologists and cognitive scientists who had thought a lot about how the different parts of a human-like mind should work together. On the other hand, you had these learning theory guys who didn't care at all about the architecture but were just thinking about like, how do you recognize patterns and large amounts of data? And in some sense, what you needed to do was to get the learning that the learning theory guys were doing and put it together with the architecture, the cognitive architecture guys were doing. And then you would have what you needed. Now, you can't, unfortunately, when you look at the details, you can't just do that without totally rebuilding what what is happening on both the cognitive architectures and the learning side. So, I mean, they tried to do that in SOAR, but what they ultimately did like taking deep neural net or something for perception and you put it as one of the black boxes. </s><s>[INST] Yeah, it becomes one of the boxes. The learning mechanism becomes one of the boxes as opposed to fundamentally. [/INST] Yeah, that doesn't quite work. You could look at some of the stuff DeepMind has like the differential neural computer or something. That sort of has a neural net for deep learning perception, it has another neural net which which is like a memory matrix. It stores, say, the map of the London subway or something. So probably Demas Sosabas was thinking about this like part of cortex and part of hippocampus, because hippocampus has a spatial map. And when he was a neuroscientist, he was doing a bunch on cortex, hippocampus interconnection. So there, the DNC would be an example of folks from the deep neural net world trying to take a step in the cognitive architecture direction by having two neural modules that correspond roughly to two different parts of the human brain that deal with different kinds of memory and learning. But on the other hand, it's super, super, super crude from the cognitive architecture view. Just as what John Laird and SOAR did with neural nets was super, super crude from a learning point of view. Because the learning was like off to the side not affecting the core representations. I mean, you weren't learning the representation. You were learning the data that feeds into the TD. You were learning abstractions of perceptual data to feed into the representation that wasn't was not learned. So, yeah, this was clear to me a while ago, and one of my hopes with the AGI community was to sort of bring people from those two directions together. That didn't happen much in terms of... Not yet. And what I was gonna say is it didn't happen in terms of bringing like the lines of cognitive architecture together with the lines of deep learning. It did work in the sense that a bunch of younger researchers have had their heads filled with both of those ideas. This comes back to saying my dad, who was a university professor, often quoted to me, which was, science advances one funeral at a time. Which I'm trying to avoid, like I'm 53 years old, and I'm trying to invent amazing, weird-ass new things that nobody ever thought about, which we'll talk about in a few minutes. But there is that aspect, right? Like the people who've been at AI a long time and have made their career at developing one aspect, like a cognitive architecture or a deep learning approach, it can be hard once you're old and have made your career doing one thing. It can be hard to mentally shift gears. </s>
<s>[INST] I don't think you're overstating it. I I tend to be just from my limited knowledge of MIT but perhaps it applies broadly. I think the beauty of the university broadly speaking is the faculty [/INST] and the students. </s><s>[INST] And the problem arises from the overreach of a [/INST] over </s><s>[INST] growing administration [/INST] that </s><s>[INST] gives [/INST] again, thinks that it knows enough </s><s>[INST] to make [/INST] rules </s><s>[INST] and conclusions based on a set of beliefs and then based on that empowers a certain small selection [/INST] of students </s><s>[INST] to be the sort of voices of activism [/INST] of </s><s>[INST] a particular idea. And not, I think activism is beautiful but not just activism, but anybody that disagrees is shut down and that that I think the [/INST] blame </s><s>[INST] lies with the administration. So I think the [/INST] solution is in </s><s>[INST] lessening just like the solution with too big of a government too big of a bureaucracy is there needs to be ah redistribution of power to what makes universities beautiful, which is the [/INST] old students </s><s>[INST] and the young students, old students being professors. [/INST] So the </s><s>[INST] scholars and the curious minds, [/INST] the people that are </s><s>[INST] in this whole thing to explore the world to be curious about it on a salary that's probably way too low for the thing they're doing. That's that's the [/INST] that's the whole point. </s><s>[INST] And then the [/INST] administration? </s><s>[INST] It just gets in the way and, um, is the source [/INST] of this kind </s><s>[INST] of they I I would say [/INST] that in </s><s>[INST] your beautiful phrasing, I would say the [/INST] administration is the </s><s>[INST] barbarians at the gate. So, [/INST] um, </s><s>[INST] the solution is smaller bureaucracy, smaller administrations. I have two on this point. You had this conversation [/INST] you put on yourself stack, </s><s>[INST] uh, with [/INST] jordans, Jordan Peterson </s><s>[INST] about cognitive [/INST] inequality. </s><s>[INST] I think it's titled Wrestling [/INST] with cognitive inequality. This particular </s><s>[INST] topic of [/INST] just </s><s>[INST] differences between groups. Why is this? Why is it so dangerous to talk about why this particular [/INST] topic? Well, it's like you're calling black people </s><s>[INST] inferior. It's [/INST] like you're saying they're genetically </s><s>[INST] inferior. That's what [/INST] people say. It's like you're rationalizing the disparity of outcomes by reference to the </s><s>[INST] intrinsic [/INST] inferiority of black people. If you if you say cognitive ability </s><s>[INST] matters [/INST] for social outcomes, if you say cognitive </s><s>[INST] ability [/INST] exists, people </s><s>[INST] really are different in terms of their intellectual [/INST] functioning. And if you say cognitive ability differences are are are substantial between racially defined populations. The some of that there is cognitive ability, it matters. And the difference by race is the conclusion that outcome differences by race are in part due to natural differences between the populations. People find that to be completely offensive and </s><s>[INST] unacceptable. So [/INST] that's what I think is going </s><s>[INST] on. Can you steal me in that [/INST] case </s><s>[INST] that we should be careful [/INST] doing that kind of </s><s>[INST] research. So uh this has to do with research. It's like the nazis [/INST] used </s><s>[INST] Nietzsche [/INST] in their propaganda </s><s>[INST] right? You can [/INST] use white supremacists </s><s>[INST] could use [/INST] conclusions. </s><s>[INST] Um Cherry pick conclusions of studies to to push there to push their agenda. Can you steal a man in the case that we should be careful? Yeah [/INST] I could do it at three levels. 1 is </s><s>[INST] what do [/INST] we mean by cognitive ability? So there's many different </s><s>[INST] kinds of intelligence. A [/INST] person might say how good our I. Q. Tests </s><s>[INST] at measuring [/INST] other kinds of human capacities that are </s><s>[INST] pertinent to [/INST] success in life like temperament like emotional </s><s>[INST] intelligence and so on. [/INST] So intelligence is not a one dimensional thing measured </s><s>[INST] by G. [/INST] The cognitive psychologists talk </s><s>[INST] about G. The [/INST] general intelligence </s><s>[INST] factor which [/INST] is a statistical </s><s>[INST] construction. It's a [/INST] factor analytic resolution of the correlation </s><s>[INST] across [/INST] individuals in their performance on a battery of different kinds of tests. And they use that to </s><s>[INST] to [/INST] define a general factor of intelligence. And a person could say that is a very narrow view of what human mental </s><s>[INST] capacities [/INST] actually are. And that it was much better to think about multidimensional </s><s>[INST] measures of [/INST] human mental functioning rather than a single cognitive ability measure a so called I. Q. </s><s>[INST] Which is a narrow uh [/INST] construction that doesn't capture </s><s>[INST] all of [/INST] The subtle nuance of human difference in functioning functioning is not just the ability to uh recite backwards a sequence of numbers. I say 8795 </s><s>[INST] 32, you say [/INST] 235789. It's not just that intelligence is a complex uh management of many different dimensions of human performance, including uh things like being able to stick with </s><s>[INST] the task and [/INST] and not give up things like being able to discipline and control your impulses so as to remain focused and so forth. Um That could be one dimension. I could start by questioning the very foundation of the argument for racial differences in </s><s>[INST] uh cognitive [/INST] ability by saying that your measure of cognitive ability is </s><s>[INST] flawed. [/INST] I could go to a higher level. I could say what we're really interested in is social outcomes and the question of what factors influence social outcomes extends well beyond mental ability to many other things. So here's an example visual </s><s>[INST] acuity. [/INST] How well do you see you're not wearing glasses? I am. Visual acuity varies between human beings. Some people see </s><s>[INST] better than other people do. [/INST] Visual acuity can be measured. </s><s>[INST] I can put [/INST] you at the chart and you can can you identify and read that bottom line in small print or not. So we can measure visual acuity and it varies between human beings. Visual acuity is partly genetic. I think that's undoubtedly true. We inherit genes that influence whether or not we are nearsighted or farsighted or s stigmatic or whatever. So visual acuity difference between people and can be measured and is under genetic control. </s><s>[INST] On the other hand, [/INST] corrective lenses allow for us to level the playing field between people who are differently endowed in terms of visual acuity. Likewise, </s><s>[INST] social [/INST] outcomes and what we're really interested in employment earnings, uh, whether or not they're law abiding. How do they conduct themselves and their families and so forth amongst individuals? Yes. Social outcomes are influenced by so called cognitive ability, but they're influenced by many other things as well. If they can if there are interventions that can be undertaken in society that level the playing field between people who have different natural endowments of cognitive ability, the fact that people or groups different cognitive ability becomes less significant, just like it's less significant than people differ with respect to how well they see when corrective lenses allow for the leveling of the playing field. There are in fact interventions educational interventions, early childhood interventions that have been shown to level the playing field to create better life outcomes for people even if they happened to be in doubt with low intelligence. So, a second level of arguing against this whole program of research on human differences and intelligence is to observe that yes, human beings and perhaps racially defined groups may differ on the average and intellectual endowment, but they're well, maybe social interventions that level the playing field, whether it's in education or in other kinds of programmatic interventions, especially for the poor. A final level of argument is the one that you alluded to, which is that if you talk like this, you're going to encourage a kind of politics, which is very ugly. And it's best to frame the discussion in ways that don't put emphasis on racially defined natural differences between populations. Uh that's an argument that I am myself personally </s>
<s>[INST] somebody is just a mask or a persona that they kind of created for themselves. [/INST] And they might not even be aware of the persona. Like, is there some deep psychological stuff? Sometimes I've experienced a lot of failure in my life. You can see it in my nose, you know, you can see it in my lack of a digit, you know, the amount of, you know, the amount of failure you can see in somebody and how they wear them. Sometimes it's a pretty telling thing as far as them being able to be trusted or that you can trust their story or their experience. And when I say experience, I mean, I've met some criminals, like former criminals, or you know, some people have that background that I trust with my life, you know, because they're not reformed. But they figured out that that's not a life they can live long enough to continue on. And I've also met people that are in law enforcement that I wouldn't trust with my car keys, because whatever persona they have adopted over the years is a pretty good one, pretty good mask. Sometimes such a good mask, </s><s>[INST] they don't even know they're wearing it. And on top of that, it's not just the psychology, there's also neurobiology to it. I've been very fortunate and deliberate to surround myself with good people throughout my life. But I've recently gotten to observe, not close to me, but nearby, somebody that could be classified as a sociopath and a narcissist. I don't want to use those psychological terms, but it's like, oh, people come with different biology too. So it's not just like the trauma you might experience in your early life and all the deep complexity that leads to the psychology that you have as an adult, but it's also the biology you come with, the nature that you might not just have the machine that can empathize deeply with the experience of others. Or maybe a machine that gets off, gets a dopamine rush from the manipulation of other humans, [/INST] or the control of other humans. I mean, put an example of my own background. My mom didn't have a father. He left really early on in their childhood. My mom raised her two sisters and basically kept a household. She was a great mom. She was a badass. She was very independent. She showed me how to be independent. She showed me how to watch out for others and build me up in that way. And I had a great childhood as far as her and how she molded me. Later on, I figured out that when I had my own kid, I figured out that she was basically trying to make me into what she didn't have in a way. And if I can get to see somebody's parents, that's usually a sign of something, at least for me, as far as figuring out where people are. I think there's something to be said about nature and nurture and how some people come up. Some people are just born with that predatory instinct and you'll never know. I mean, they spend their whole life practicing how to hide it. But if you can figure out somebody's background, childhood, where they're from, you can kind of tell something about them. I'm from Tijuana. I'm a survivor. That's my background </s><s>[INST] as far as where I'm from. Culturally, genetically, psychologically, the full shebang. [/INST] Yeah. Yeah. I guess some people are born with certain predispositions and if they're in the right environment, some of the negative aspects might flourish more than others. For me, I mean, I grew up skateboarding in Tijuana. And I remember breaking into my first backyard pool. It was a house that a cartel guy owned and we used to skate the pool in the back of it. So I learned how to pop open padlocks with a small vehicle hydraulic lift. And I remember doing that. And later on in life, I got to train with people from other parts of Mexico and work with them. And I remember pulling that trick off and they were looking at me like, would you learn that? It's like some burglars in Tijuana. And they're like, wow, that's interesting. Are all people from Tijuana like that? And I said, no, we're not all like that. But I guess in some way we are because Tijuana produces kids like that. She produces the environment itself, produces a pretty specific person, I guess. Our normal or baseline normal is way different than most. </s><s>[INST] The trajectories that you can take in life are defined in a way that aren't available elsewhere in the world. Yeah. And so you develop, I mean, part of that psychological part of that is cultural and so on. Part of that is the cultural trauma. But then also the ethical lines based on the corruption, because I grew up in the Soviet Union and there's the same kind of understanding that [/INST] there's some great area of corruption. Yeah. Yeah. It's always there, like on the outskirts or even in the center, how you can grease things to make things easier. And how it's like a personal thing. I'll just pay off the Tijuana, we have a mordida, that's what we call it, when you pay a cop off. No, mordida means a bite, mordida as well. What's the bite aspect? So you get stopped for a traffic violation of some sort and the cop walks up to you. Obviously, you don't say the word bite, but it's like a slang term for it. And he asks for your paperwork and if you get fined or get a ticket, you say, can I pay the ticket here is what they say. And put their money inside the paperwork and hand it over to the cop, mordida. You think it's, I'm just going to do it and nobody knows, but it's a systemic thing. Everybody, like a lot of people do it. And then they don't trust </s>
<s>[INST] And this meta class is presumed in the documentation. Is it all negative? [/INST] No. What are you talking about? So, this is part of the problem in the madness of our age, right? Which is if you if you open up a drawer in your, in your cabinet, right? In your kitchen, and you see knives, spoons and forks, do you have a sense that the spoons are good utensils? And the knives or forks or bad utensils? Because they're mean, I mean, like, if you start thinking in these terms, that knife is there to do violence. That's violence you want done, right? When I cut a mango, I'm doing violence to the mango. The mango expects that I will do violence to it, because otherwise, I won't be able to get the meat and it won't get its seed, um, spread somewhere else. So, in part, violence is absolutely part of our story. </s><s>[INST] So, okay, so there's this meta violence class. Yeah. And [/INST] what's so the meta violence class is already, you know, it's a multiple inheritance pattern, whatever is going on right now, inherits from meta violence? </s><s>[INST] No, but there's there's certain sub classes that allow evil to emerge. So what what, what I'm specifically worried about is that what's on your mind lex, [/INST] what's what's really going on? Okay. </s><s>[INST] I worry that amidst the chaos of we have these protests or the chaos that could be created by the feeling that the election does not represent the voice of the people. Like saying that whoever gets quote unquote wins the election according to the some kind of reporting of the numbers that come out. That's not going to represent what people actually who people actually want to be the leader. Like something in that narrative will create so much division that people will resort to literal violence, like protests that really that the United States loses its United aspect. And because of that, because of that chaos and tension, evil people, evil forces. That my definition of evil is, you know, just cruel human beings use that moment to attain power. The kind of power that ultimately goes against the ideal of the United States. That could be donald trump that could be another human being. It doesn't really matter. My my worries that love doesn't win out in this. The unity doesn't went out on this and I feel like you and I have responsibility no small. [/INST] Yeah, I know. </s><s>[INST] And so how do we let love win in this moment of [/INST] we're gonna potential chaos, you're going to have to become a fighter, you have to, you're going to throw some serious punches if that's what you want. </s><s>[INST] You have to be Muhammad ali here because the moment you start criticizing anything, people, you have to be a masterful communicator, [/INST] because that's why you're here, look, lex in part, your decency is allowing you to do things that you couldn't otherwise. I saw that you had Michael malice on your podcast. Now, Michael malice is, I think of somebody who, at his best is extremely shrewd and insightful. Yes, he's also got this trolling game, which is quite open about and you talked to him about it, which I can't stand and that's this is the idea of grandpa doesn't get the internet. Well, I'm grandpa, I don't get the internet, I don't love the trolling. Yeah, there are trolls of the past who were incredibly good. I don't see any of the modern trolls as being that kind of genius level trolling, the people who deserve it in the way that they deserve it. You know, right now, what I see is that anything that stands up gets cut down, you know, it's like anything Ernest, you have to turn into cynicism and a meme, and it's this idea that the people who believe that the world is chaos and has no point are constantly trying to let you know, don't try to use the internet for meaning for decency for goodness, because we are going to find out that that's all sanctimonious hypocrisy and we will we will make you suffer. So I do think that there's a lot of sanctimonious hypocrisy in the world, some of it mine some of it yours. But we all have it and the trolls somewhat removed that, but it's not a judicious, kind, constructive, compassionate, caring version most of the time. And a lot of those trolls and I have this feeling about Michael malice. I don't know whether it's right that there's somebody who deeply cares and loves beneath it and that that's motivating some of the trolling behavior and you and I don't seem to be doing that. I don't see you as almost ever trolling </s><s>[INST] you and I are I'm very much against trolling. [/INST] I'm very much against trolling. It doesn't mean that it's selective. You know, I'm not even the same and true. Like everything we say, we say like I'm forward, I'm against it. This isn't my native language. I speak nuance. I don't speak this internet ship. Yeah. And the more I have to communicate through internet ship, right, I almost never take a tweet seriously if it contains the letters L. M. A. O. L. O. L. R. T. F L. U. F. O. L. </s><s>[INST] Mhm. There's an interesting affect where people say stuff and then finish with L. O. L. You're you put it beautifully that it indicates to me that this is a person we've talked about like why I wear the stupid suit is like this is anti this is to fight the L. L. O. L. At the end of sentences is take it's like stand up for the words you're saying. Yeah, don't finish stuff with L. O. L. Removing completely responsibility of the content of the sentence that preceded it. [/INST] Yeah. Also choosing the outfit that works both for men in black and the Blues brothers. Not a terrible choice. Okay, but getting back. Look, lex, we're not in a position to do this. You need to be seated in a different chair. Your chair is the wrong chair, You're in the wrong chair. It's been so long. All right. I want to talk about you. And joe biden, Joe Biden was a 29 year old guy with nothing particular going on so far as I can tell. Okay, I know people as impressive at age 29 is Joe Biden, You know, 12 rows back through three deep. Does't matter a huge number of people, none of them my age can get to where he got like we're all mora Yeah, anytime somebody takes out, like if you found Eddie Van Halen in a guitar shop, you'd be angry. What is this guy doing repairing guitars? Then? Somebody said maybe he loves to repair guitars. </s>
<s>[INST] So, okay, it's [/INST] like looking at, if you'll let me just give this one analogy, you know, you judge the distance of an oncoming car at night by looking at how bright it's headlights appear to be. And you've calibrated how bright the headlights are of a car that's two or three m away of known distance and you go, whoa, that's a a faint headlight. And so that's pretty far away. You also use the apparent angular separation between the two headlights as a consistency check in your brain, but that's what your brain is doing. So we can do that for cars. We can do that for </s><s>[INST] stars. Nice. I like that. But you know with cars the headlights are all there's some variation there but they're somewhat similar. So you can make those kinds of conclusions. What how much variation is there between supernova that you can you can you detect [/INST] them right? So first of all, there are several different ways that stars can explode and it depends on their mass and whether they're in a binary system and things like that. And the ones that we used for these cosmological purposes studying the expansion of the history history of the universe are the so called type roman numeral one, lower case A type one, a supernova. They come from a weird type of a star called a white dwarf. Our own sun will turn into a white dwarf in about seven billion years. It'll have about half its present mass compressed into a volume, just the size of earth. So that's an inordinate density. Okay, it's incredibly dense and the matter is what's called by quantum physicists degenerate matter. Not because it's morally reprehensible or anything like that, but this is just the name. Yeah, Quantum physicists give two electrons that are squeezed into a very tight space. The electrons take on a motion due to Heisenberg uncertainty Heisenberg's uncertainty principle and also due to the power of the exclusion principle, that electrons don't like to be in the same place, they like to avoid each other. So those two things mean that a lot of electrons are moving very rapidly, which gives the star an extra pressure far above the thermal pressure associated with just the random motions of particles inside the star. So it's a weird type of star, but normally it wouldn't explode and our son won't explode. Except that if such a white dwarf is in a pair with another, more or less normal star, it can steal material from that normal star until it gets to an unstable limit, roughly 1.5 times the mass of our sun, 1.4. So this is known as the china sea, trying to save our limit after Super Mannion Chandrasekhar, in indian astrophysicist, who figured this out when he was about 20 years old on a voyage from India to England, where he was to be educated and then he did this and then 50 years later he won the Nobel Prize in physics in 1984 largely for this work, Okay. That he did as a youngster who was on his way to be educated, you know, Oh, and his advisor, the Great Arthur Eddington in England, who had done a lot of great things and was a great astrophysicist. Nevertheless, he too was human and had his faults, he ridiculed chandra's scientific work at a conference in England and, you know, most of us, if we had been chandra would have just given up astrophysics at that time, You know, when the great Arthur Eddington, you know, ridicules our our work, but that's another inspirational story for the youngster, you know, just, just keep going, you know? But anyway, your advisors, no matter what your advisor says, right, so, or don't always pay attention to your advisor. Right? Don't don't be uh don't lose hope if you really think you're on to something that doesn't mean never listen to your advisor, they may have sage advice as well. But anyway, um you know, when a white dwarf grows to a certain mass, it becomes unstable. And one of the ways it can end its life is to go through a thermonuclear runaway. So basically the carbon nuclei inside the white dwarf starts start fusing together to form heavier nuclei. And the energy that those fusion reactions emit, and that's doesn't go into um you know, being dissipated out of the star or, you know, whatever, or expanding it. The way, you know, if you take a blowtorch to the middle of sun, you heat up its gasses, the gasses would expand and cool, but this degenerate star can't expand and cool. And so the energy pumped in through these fusion reactions goes into making the nuclei move faster and that gets more of them sufficiently close together that they can undergo nuclear fusion, thereby releasing more energy that goes into speeding up more nuclei. And thus you have a runaway a bomb, uh, an uncontrolled nuclear fusion reactor, right? Instead of the controlled fusion, which is what our son does. Okay, our son is a marvelous controlled fusion reactor. This is what we need here on earth fusion energy to solve our energy crisis. Right? But the sun holds the stuff in, you know, through gravity and you need a big mass to do that. So this uncontrolled fusion reaction blows up a star. That's pretty much the same in all cases. And you measure it to be almost the same in all cases, but the devil's in the details. And in fact we observe them to not be all the same. And theoretically they might not be all the same because the rate of the fusion reactions might depend on the amount of trace heavier elements in the white dwarf and that could depend on how old it is when it was. You know, whether it was born billions of years ago when there weren't many heavier elements or whether it's a relatively young white dwarf and all kinds of other things. And part of my work was to show that indeed not all the type one A's are the same. You have to be careful when you use them, you have to calibrate them. They're not standard candles the way it just, if all headlights are all candles were the same lumens or whatever you'd say their standard and then it would be candles </s>
<s>[INST] But for that step, then perhaps, hopefully, is a better example, because in this particular, like you said, land last, if I were to say, if I was an alien and arrived at Earth and, say, choice of land, maybe if you were interested in choosing a land that represents a network state where ideas that unites people based on ideas, maybe pick a land that doesn't lead to a generational conflict and war and destruction and suffering and all that kind of stuff. [/INST] That's right, yes. So, I'll get to that point, okay. So, now that I've said what are, you know, the positive things about Israel, and I think there's a lot to admire in Israel. As I said, I think there's also a lot to admire in the Palestinians and so on. I'm not taking any position on that. There's other inspirations for the network state. The second major inspiration is India, which managed to achieve independence non-violently. That's very important, right? So, can you fuse these things? A state started with a book that achieved independence non-violently and that managed to build this polyglot multicultural democracy that does, you know, India has its flaws, but it does manage to have human rights of lots of people respected and what have you, right? And has managed to, you know, there were times like emergency in the 1970s and they were gone, the declared emergency. There are times when seem touch and go, but overall with fits and starts, this flawed thing has kind of made its way through. And, you know, the third inspiration is Singapore with Lee Kuan Yew, who built a city-state from nothing. You know, I shouldn't say from nothing. Okay, there was something there, but let's say built one of the richest countries in the world without, like, huge amounts of natural resources in the middle of a zone where there was lots of communist revolution going on. And so he was the CEO, founder, essentially, of this amazing startup country, right? And, you know, finally, of course, America, which has too many influences to name, things we talked about the nation of immigrants, obviously the constitution and so on. And you think, okay, can we go, you think of, you know, these inspirations, what's interesting about these four countries, by the way, Israel, India, Singapore and the US, they have something in common. You know what that is? They're all forks of the UK code base. We think, obviously, you know, the UK was sort of the ancestor of America, but Israel was a former British colony, right? India </s><s>[INST] was a British colony, and so was Singapore, right? For people who don't know what fork and code base means, it's a language from versioning systems, particularly Git, represented online on a website called GitHub. And a fork means you copy the code, and all the changes you make to the code now live in their own little world. So America took the ideas that define the United Kingdom and then forked it by evolving those ideas in a way that didn't affect the original, the original country. [/INST] That's right. And what's interesting about this is, and of course, I'm saying that in a somewhat playful way, right? But I think it's a useful analogy, interesting analogy, right? So you have the Americans who forked, you know, the UK code base, and you have, you know, the Indians, Israelis, and the Singaporeans who also made their own modifications. And in some ways, each society has pieces that you can take from them and learn from them and try to combine them, right? So you have a state that is started by a book that non-violently assembles that crowdfunds territory around the world, that is led by a CEO, founder, and that is also governed by something that's like a constitution. But just like you went from, you know, I talked about the V1, V2, and V3 a lot, right? Like V1 is gold, and V2 is fiat, and V3 is Bitcoin, right? Or V1 is hunter-gatherer, and V2 is farmer-soldier, V3 is digital nomad, or sovereign collective, okay, which is not just an individual, but a group. Here, V1 is UK common law, they don't have a constitution. It's all precedent going for many years, right? V2 is the US constitution, and V3 is the smart contract, the social smart contract, which is a fusion obviously of Rousseau's concept of the social contract, and the smart contract. The social smart contract is like written in code, okay? So it's like even more rigorous in the constitution. And in many ways, you can think of going from the United Kingdom of England, Wales, you know, Scotland, Northern Ireland, the United States of America, the network states of the internet, okay? Where you go from the rights of Englishmen with the Magna Carta to Europeans, African Americans, all the immigrants to the, you know, the Americans or the, you know, North America, then you go to all the people of the world. And so you basically are more democratic, and you're more capitalist, because you're talking about internet capitalism, not just nation state law capitalism. In a sense, it's the V3, right? In other ways, it's the V3. Only about 2% of the world is over 35 native born American can qualify to be president of the United States. But 100% of the world, you can become the president of a network state. There might be a, you know, Palestinian Washington, or a, you know, Brazilian Hamilton, right? And now, rather than say, okay, maybe you're maybe you have a small percentage chance of immigrating to the US and a small percent chance of your descendant, you know, becoming like, you know, president. Now we can just say you can start online. And you know what, maybe this person is so exceptional day of Americans </s>
<s>[INST] And- I just have never unearthed maybe, but maybe I just, whenever I see life, it seems to flourish everywhere. The thing is, I don't- [/INST] The only thing I haven't seen is the start of it. Exactly. But, and how are we gonna understand that if we don't know the origin of life science? I mean, that's the- And the question here isn't exactly our ability to recapitulate everything that happened in the exact way that it happened, right? This is about what can happen rather than, </s><s>[INST] or maybe how it can happen. You think it's possible to study the origin of language using English. So, like there's a very particular chemistry here. There's a particular set of assumptions, understanding about what life is, what everything is. Our perception of reality is very specifically constructed through the evolutionary process. I wonder if it's possible to get to some first principles, deep understanding of how life originates in such a way that you can actually construct it on other planets. Ultimately, it feels like if you're doing it in a lab on Earth, you're always going to be using some aspect [/INST] of the life that's already here. So, that's what I sort of talked about in my talk as well. And- </s><s>[INST] Everyone should go watch the TED Talks, very good. The annoying thing to me about TED Talks, I guess it's by design, is they're too short. It's like, come on. [/INST] And did you know that? </s><s>[INST] There's no prompter involved? There's no, wait, there is or there isn't? Yeah, you have to memorize stuff, yeah. It's a, and thanks to my- [/INST] There must be a grueling process or there isn't. Yeah, it's a, and thanks to my amazing editor who probably is watching this too, David Bielow, it was very, very helpful. But I would say that- </s><s>[INST] Very professional, yeah. Very professional organization. I like this podcast, it's a very professional organization. I respect that medium. Yeah, anyway, in the TED Talk about life, [/INST] life creating life, yeah. So it's a likely scenario that once we understand how life as a chemical system is capable of formulating its own expression and generating a memory and manages its existence on a planetary body for billions of years, once we understand what conditions gave rise to that, we may be very likely to understand whether a different planet also be likely to instigate its own chemical revolution if it was provided through some missing ingredients. You can think of it as sending fertilizer to a different planet that is missing its own chemical composition or lacking or that it needs more of what it has. The difference between making that planet Earth-like, which this is not what that's about. We're not talking about terraforming or we're not talking about turning that planet into Earth-like system. We are talking about first understanding that planet, studying its chemistry, studying its properties well enough to understand whether it is close to its own chemical revolution and maybe giving it that extra nudge. So this is obviously a pretty big speculation and suggestion. And it's very interesting proposition because this is a yes or no question, right? This is the ultimate would you rather. It's the, and I think it says a lot about the perception of the person who's answering this question. That if the answer is no, no, no, absolutely not, that's not something we wanna do. </s><s>[INST] I wanna know why that is the case. So just to be clear, what we're talking about is looking at the chemical cocktail of a particular planet and having like tasting it and seeing what's missing. So having a very systematic, rigorous scientific process of understanding what is missing, not what is missing in terms of to make it earth-like but what is missing in order to be sufficiently have the spark or the capacity of the spark to launch the evolution revolution, the evolutionary process. Exactly. And then the question is, do we want to then complete the cocktail? [/INST] The proposition is to also make us think that we will likely have this capacity at some point, especially when we understand origin of life better and better. Right. So we will be asking ourselves this question. I guess I wanted to bring this to daylight a little bit because maybe in 10, 20 years, maybe more. </s><s>[INST] So you wanted to ask the ethical question, [/INST] should we basically start life elsewhere on another planet? Or enable the chemical, </s><s>[INST] the chemical capacity of that planet that it may one day itself get there. OK, so for me, the answer is yes. So if you were to try to argue against my yes, what would you say? Why not? What's the worst that can happen if we seed another planet with life? What are the things we should think about? Is your main concern a chemical biological one or is it an ethical one? [/INST] What do you think about the worst thing that can happen is that it wouldn't work. Right. So that it's not a likely it's not likely that an attempt like this would work. That's probably because how do you so you got to be very, you know, you have to have an understanding that I don't think we have just yet. </s><s>[INST] So I see. Because if it doesn't work, then we could try again, right? To me, the worst case, the thing I would be worried about is we create life. I mean, the same stuff I worry about, like with plants or is things that might have a conscious experience. And then the the dark aspect of life is life is increasingly complex life. [/INST] Maybe I meant to promote rising, but it seems to have the capacity to suffer. </s>
<s>[INST] in that place of safety and vulnerability, in that fascinating group of people, when their egos dissolved in this way, do they have similar experiences? Is there different places that their minds went? [/INST] Yeah, So, you know, once I had this kind of shattering experience, that Hitler is part of me, you know, no one else in the group had that probably a lot of them have maybe had that before, or they realized that they're not just, you know, the good, the white hat, good people and that they're all good and you know, we've got to fight against the bad people, you know, so, you know, people will go in different places and not only that if you do it again, you'll go into a different place than you went to the first time unless you have not resolved the issues. So I had a sequence of LSD trips that were very difficult, but it was like coming to the same sort of conundrum, the same challenge um that I was unable to overcome this idea of letting go and really fully dissolving, um letting the ego fully go and I would have this sequence of trips over a couple of months where I would reach this point where I was too scared to move forward and I would just be holding on. Um So there there are repeated themes sometimes. What stan growth has said which I find very beautiful is that the full expression of an emotion is the funeral pyre of that emotion. And what that means is if you can fully let in something then the essence of of life has changed is that it moves on that everything is in motion. Um And if you can fully experience it, even if it's a sense that you're going to be trapped in eternity in this hellish state if you surrender to that that's the way out. You know this full experience of something is this uh funeral pyre of that emotion. And so that runs against a lot of what modern psychiatry is doing to which is to suppress symptoms. And uh and instead of supporting people to kind of explore these insecurities so that then they can contain them and then they can move on. </s><s>[INST] So yeah resistance is not a way to make progress, [/INST] right. Right. Although in one of the reasons why we do the supplemental dose during the M. D. M. A. Or why there's advantages in a a 10 hour LSD experiences that you have a lot of opportunities to come up against this resistance. It may be too difficult to deal with and then you kind of push it aside and then a couple hours later you come back to it or you come back to impress news every once in a while. If you're not ready, it's hard to do that. I think with M. D. M. A. You can negotiate, that's I think a part of its safety in a sense. You're going to have this like, oh, I should be talking about this, but I were feeling this, but it's too much for me now. You can push it away. But with the classic psychedelics, this kind of membrane between the conscious and the unconscious that once you take the drug and it weakens this membrane and things are coming up. Um it's very difficult to negotiate with it. The the the key to successful uh classic psychedelic trips is surrender. Mhm. </s><s>[INST] You've talked about the first began to reconsider the negative health myths around psychedelics. When you learned that the book, one flew over the cuckoo's nest was written by Canc Easy when he was in part under the influence of LSD. So how do you think LSD helped him can keys in writing uh that incredible book. [/INST] Yeah. There's a process that is called semantic prime ng. And so what that means is that I say um night you say day. You know, there's kind of normal patterns of kind of, you say one word. What kind of words come to you next. And so they've done some research, they meaning scientists have done some research where you give people a psychedelic and then you do this semantic prime ng. And what you find is they have a wider range of associations than they normally would when they're not under psychedelics. So I think for kinky easy um he was able with psychedelics to get like uh a deeper kind of emotional connection to some of these states of mind that people were in the instant, this mental institution and that he could explore them more in depth and more eloquently. And and and also one of the things he talked about was the fog machine was you know how people's minds were sort of clouded by the people that ran the institution and the fog machine would be coming in. So I think the imagery and the metaphors that he used a lot in the book could come to him during LSD experiences and and then now he wasn't doing um you know very when you're writing you have to be literate, you have to be able to write, you know, so it would be more like beginning and ends of LSD trips instead of at the peak. But I think you would get a lot of these um the feeling tones are the images, the metaphors. I think he would get um these extent also LSD last so long. You can get these extended focus and you can really elaborate um um images and so much of psychedelic experiences are poetic and metaphorical. I mean you can take um you know, veterans who have never read a book of poetry in their lives, you know, and under the influence of M. D. M. A. Just what they described the imagery and the way they described their experiences metaphorical, poetic, It's incredible. Um and so I think that um ken Casey was able to channel these what LSD did to his mind in a way that most people couldn't do that he did because he was trying to write this novel and because he was so brilliant. </s>
<s>[INST] Well, the point of probing any subjective experience is impossible is that I'm not science. I'm lex so I can't probe another entities another. It's no more than bacteria [/INST] on my skin or lacks. I can ask you questions about your subjective experience and you can answer me. And that's how I know you're you're conscious. </s><s>[INST] Yes, But that's because we speak the same language. [/INST] You perhaps we have to speak the language of science. And honestly, I don't think consciousness just like emotions of pain and pleasure is not something that inevitably arises from any sort of sufficiently intelligent information processing. It is a feature of the mind. And if you have not implemented it explicitly, it is not there. </s><s>[INST] So you think it's a feat, it's an emergent feature of a particular architecture. So do you [/INST] think it's a feature in the same sense? So again, the subjective experience is all about guiding behavior. If you if the problems you're trying to solve don't really involve and died agent maybe in a social context, generating behavior and personal goals like this. And if you get science that's not actually what's happening, even though it is, it is a form of artificial, they are in the artificial intelligence in the sense that it is solving problems, it is a community knowledge committing a solutions and so on. So if you're not explicitly implementing a subjective experience implementing a certain emotions and implementing consciousness, it's not going to just spontaneously emerge. </s><s>[INST] Yeah. But so for a system like human like intelligence system that has consciousness, Do you think he needs to have a body? [/INST] Yes, definitely. I mean doesn't have to be a physical body. Right. And there's not that much difference between a realistic simulation of real world. So </s><s>[INST] there has to be something you have to preserve kind of thing. [/INST] Yes, but human like intelligence can only arise in a human life context, intelligence and other humans in </s><s>[INST] order for you to demonstrate that you have human like intelligence essentially. So what kind of test and demonstration would be sufficient for you to demonstrate human like intelligence? Just out of curiosity you you've talked about in terms of fear improving and program synthesis. I think you've written about that. There's no good benchmarks for this. That's one of the problems. So let's let's talk programs program synthesis. So what do you imagine is a good, I think it's related questions for human like intelligence. If a program synthesis, uh what's a good benchmark for either both. [/INST] Right. So I mean you're actually asking asking two questions which is one is about quantifying intelligence and comparing uh the intelligence of an artificial system to the intelligence for human and the other is about the degree to which this intelligence is human. Like it's actually two different questions. So if you look you mentioned earlier the turing test. Well I actually don't like the turing test because it's very lazy. It's all about completely bypassing the problem of defining and measuring intelligence and instead delegating to a human judge or panel of human judges. So it's it's a whole coop out right? If you want to measure ha human like imagine is I think you have to make it interact with other humans. Maybe it's not necessarily a good idea to have these other humans be the judges. Maybe you should just observe the view in comparison with the human would actually have done when it comes to measuring how smart or clever an agent is and comparing that today to the degree of humanitarian. So we're already talking about two things, right? The degree I kind of like the magnitude the magnitude of an intelligence and its direction, right? Like the normal vector but its direction and the direction is like human uh likeness and the magnitude the norm is uh intelligence. Uh you could call it intelligence right? So </s><s>[INST] the direction your your sense the space of directions that are human. Like it's very narrow. Yeah, [/INST] so the way you would measure the magnitude of intelligence in a system in a way that also enables you to compare it to that of a human. Well, if you look at different benchmarks for intelligence today, they're all uh too focused on skill at a given task. Let's kill it. Playing chess skill at playing goes skill at playing Dora. And I I think that's that's not the right way to go about it because you can always Be to human it at one specific task. The reason why our skill at playing go or juggling or anything is impressive is because we are expressing this skill within a certain set of constraints. If you remove the constraints, the constraints that we have one lifetime that we have this body and so on. If you remove the context, if you have unlimited train data, if you can have access to, you know, for instance, if you look at juggling at uh if you have no restriction on the hardware then achieving arbitrary levels of skill is not very interesting and says nothing about the amount of intelligence you've achieved. So if you want to measure intelligence, you need to rigorously define what intelligence is. Which in itself it's a very challenging problem. And do you think that's possible to define intentions? Yes, absolutely. I mean you can provide many people have provided some definition. I have my own definition. </s><s>[INST] Where does your definition to begin? If it doesn't end well, [/INST] I think intelligence is essentially the efficiency with which you turn experience into general Izabal programs. So what that means? It's the efficiency with which you turn a sampling of experience space into um um the ability to process a larger a chunk of experience space. So </s><s>[INST] measuring [/INST] skill can be one proxy because many, many different tasks can be one proxy for measure intelligence. But if you want to only measure skill, you should control for two things. You should control form the amount of experience that your system has and the prior years that your system has. But if you if you control if you look at two agents and you give them the same prior years and you give them the same amount of experience, there is one of the agents that is going to learn programs representation something, a model that will perform well on the large trunk of experience space than the other. And that is the smaller agent. Yeah. So if you </s>
<s>[INST] Like, [/INST] you know, it's not everything. It's cracked up to be, you know necessarily. </s><s>[INST] But no matter what, you know, a new place allows the possibility for new ideas. Even if they're somehow left leaning and all those kinds of things. I do think the only two things missing from Austin and texas are two dudes in a suit that sometimes have a podcast talking much nonsense and mike. So let's let's bring the best suit game to texas. I hope you do make it to texas at some point. Thanks so much for talking to me. Thanks for listening to this conversation with Sagarin Jetty and thank you to our sponsors Jordan's Harvard's show, Graham, early grammar assistant eight, sleep, self cooling bed and magic spoon, low carb cereal, click the sponsored links to get a discount and to support this podcast. And now let me leave you with some words from martin Luther king Jr about the idea that what is just and what is legal. I'm not always the same thing. He said, never forget that. What Hitler did in Germany was legal. Thank you for listening and hope to see you next time [/INST] </s>
<s>[INST] No, the the chest [/INST] upbringing. I make it come close to you, right? You see like whenever I do my exercises, the vector is always pulling straight towards me. Yeah. So just uh, you know, cupping close to you, the most dangerous thing that a person can do to me on an arm wrestling match is just pull me away from my body. That's that's a terrible thing for me. Yeah. So so that cupping, that's a massive part of the sport. So now when you think, what does the cup due to the other person, if I cup, they get turned over, right? So this has to get really strong this pro nation. So </s><s>[INST] so to fight the to fight that rolling. [/INST] Exactly, yeah. So that's that's through the thumb. </s><s>[INST] Yeah. Oh, so you put uh you got it, you put on the thumb and you put this motion. Yeah. Got it. [/INST] And those two things, those two things together, this cupping and rolling. This is what's going to make the person's hand bend back and once a person's hand is bent back there, just their whole game gets cut to pieces. They have very little good options. It's all like nasty stuff. Yeah. So those two things that's a that's a huge part of of your of your investment, uh rise always be climbing. Yeah, exactly. Yeah. Those three simple things, that's what I would tell anybody to spend most of their time on if you want to become an arm wrestler. </s><s>[INST] So, and to use bands would be good for this. [/INST] Bands are great because they're easy to transport. The only problem I have with bands is like, if you like to measure, you know, if you like to be precise, bands just aren't that precise </s><s>[INST] to have growth. Yeah, [/INST] just, I mean, it's just like, you know, you know exactly what you need. The prescription is kind of a band is kind of like and a lot of people myself included. I like to um I like to know exactly my outputs. So so weights, </s><s>[INST] so it would, it would be like cables, [/INST] cables are nice. Bands are great too. I I mixed the two bands are uh when I kind of don't need to they're more like easy for me. When I trained bands, bands are dangerous because the acceleration is so high on them. Like when you screw up with band training, the acceleration is way faster than gravity. Right? So if you do something bad, I can, I can make it go really much worse. </s><s>[INST] It's funny that you didn't mention bicep curls or it's a chain. It's changed. So you're I mean the idea if you focus on these three, the other stuff catches up, like it's all involved, this whole this whole thing is involved. [/INST] If you have an ax, right? The blade of the ax, that's that's these things, right? Like you need the pointy end of all your attacks to be awesome. </s><s>[INST] If you have a super sharp ax. Yeah, you can have a shitty hands. Yeah. Right. Yeah. So focus on that. The the point, the tip of the acts, yeah, the tip of the ax [/INST] is so important, right? Like if I have an awesome bicep and I can't quite use it. What's it good </s><s>[INST] for? Right? Yeah. I think a lot of emotions with the risk that you mentioned are just thinking about jujitsu, especially in the G. Um there's a lot of, I mean, there's so much importance to this and people don't often work it explicitly. So many of the chokes require ability to, it's almost like exactly like arm wrestling very close because you're weak here. What's that called, floppy wrist and you're strong with the cup. Yeah. And so you just getting the most of whatever that's involved, the muscle, the turning the pressure because that's where also the choke comes that little, the thing that makes you win an arm wrestling is also the thing that finishes the person when you have them grabbed the strength is very similar. Yeah, it's fascinating actually, of course, like you said, if you want to be very good, you should be doing the very specific exact emotion. [/INST] So if I was going to do jujitsu, I'd be like working out with the g </s><s>[INST] Yeah, the problem is, you know, it's difficult to construct the, the exact, so you have to actually go with people and then they don't like being choked right? So like, it's hard to, I'm actually a big, we have these kinds of debates all the time. Is um you know, I'm a big believer in drilling, I love doing something thousands of times like john donna hurt somebody. And I mentioned to you about the judi stick folks here, they're less believers in drilling. They, they see the value of almost like the mind of going live and exploring ideas. It's that play. You don't need to do the thing 1000 times. You just need to always be thinking about the little details that make you make you better and then in action practicing, like developing the strength, the power of the explosion of the agility in action. So actually rolling, I don't, you know, I, I agree with this, but I just believe in volume more so [/INST] you can accomplish it through volume. You can, you can play a lot. </s>
<s>[INST] And so the dendritic spikes that you were talking about, [/INST] well, we wouldn't model the spikes, but the idea that you have that today's neural networks have this company called a point in your arms is a very simple model of a neuron and uh by adding dendrites to them and just one more level of complexity that's in biological systems, you can solve problems in continuous learning um and rapid learning. So we're trying to take, we're trying to bring existing field, we'll see if we can do it. We're trying to bring the existing, feel the machine learning uh commercially along with us. You brought up this idea of keeping, you know, paying for it commercially along with us as we move towards the ultimate goal of the true AI system. </s><s>[INST] Even small innovations on neural networks are really, really exciting. It seems like such a trivial model of the brain and applying different insights, just even like you said, continuous learning or uh making it more a synchronous or maybe making more dynamic or like incentivizing [/INST] making it </s><s>[INST] uh and making it somehow much better incentivizing Spar City uh somehow. Yeah, well, [/INST] if you can make things 100 times faster than there's plenty of incentive that people, people are spending millions of dollars, you know, just training some of these networks. Now, these uh these transforming networks, </s><s>[INST] let me ask you the big question, how for young people listening to this today in high school and college, what advice would you give them in terms of which career path to take? And maybe just about life in general? [/INST] Well, in my case, um I didn't start life with any kind of goals. I was when I was going to college is like, what do I say? Well maybe we do, it's electrical engineering stuff, you know? Um it wasn't like, you know, today, you see some of these young kids are so motivated like change where I was like, you know, whatever. And um, but then I did fall in love with something besides my wife, but I fell in love with this, like, oh my God would be so cool to understand how the brain works. And then I said to myself, that's the most important thing I could work on. I can't imagine anything more important because if you understand the brains work, build tells machines and they could figure out all the other big questions in the world, right? So, and then I said, I want to understand how it works. So I fell in love with this idea and I became passionate about it, and this is a trope, people say this, but it was it's true because I was passionate about it, I was able to put up almost so much </s><s>[INST] crap, you [/INST] know, you know, I was I was in that, you know, I was like, person said, you can't do this, I was I was a graduate student at Berkeley when they said, you can't study this problem, you know, no one can solve this or you can't get funded for it, you know? Then I wanted to do, you know, mobile computing, and it's like people say you can't do that, you can't build a cell phone, you know, So, but all along I kept being motivated because I wanted to work on this problem, I said, I want to understand the brain works and I got myself me like one lifetime, I'm going to figure it out, do the best I can so by having that because, you know, it's really as you point out like, it's really hard to do these things, people, it's just, there's so many downers along the way, So many obstacles get in your way, I'm sitting here happy all the time, but trust me, it's not always like </s><s>[INST] that, that's I guess the happiness that the passion is a prerequisite for surviving the whole, the whole thing. [/INST] So I think that's right. Um, and so I, I, I don't want to get to some and say, you know, you need to find a passion and do it. No, maybe you don't, but if you do find something you're passionate about then then you can follow it as far as your passion will let you put up with </s><s>[INST] it. Do you remember how you found it? This is how the spark happened. [/INST] Why specifically for me? </s><s>[INST] Yeah, because you said it's such an interesting, it's like almost like later in life by later. I mean like not when you're five, you, you didn't really know and then all of a sudden you fell in love with that. [/INST] Yeah, there was, there was two separate events that compounded one. Another one When I was probably a teenager, might have been 17 or 18, I made a list of the most interesting problems I could think of. First was why does the universe exist? It seems like not existing is more likely. The second one was well given exist why they behave the way it does. You know the laws of physics, why is equal EMC squared, not empty cube, you know, attention question third one was like, what's the origin of life? Um, and the fourth one was what's intelligence and I stopped there, I said, well that's probably the most interesting one. And I put that aside As a teenager. But then when I was 22 and I was reading the No it was excuse me, I was 17, it was 1979. Excuse ME, I was reading. So I was at that time was 22. I was reading uh September issue of scientific American, which is all about the brain. And then the final essay was by Francis crick who of DNA fame. And he had taken his interest to study the brain now and he said you know there's something wrong here. He says we got all this data, Oh this fact this is 1979 all these facts about the brain, tons and tons of facts about the brain. Do we need more facts, but we just need to think about a way of rearranging the facts, we have. Maybe we're just not thinking about the problem correctly, you know, because he says this shouldn't be shouldn't be like this, you know? So I read that and I said wow, I said I don't have to become like an experimental neuroscientist, I could just look at all those facts and try to become a theoretician and try to figure it out. And I said that I felt like it was something I would be good at. I said I wouldn't be a good experimental that I don't have the patience for it. But I'm a good thinker. And I love puzzles and this is like the biggest puzzle in the world is the biggest puzzle all the time. And I got all the puzzle pieces in front of me. Damn, that was exciting. </s>
<s>[INST] and just dynamically and just throwing, correct how many, uh, because uh, as I was mentioning to you, offline, Travis threw me a few times, a lot of times when he was listening in Austin and I just remembered, uh, so there's two things I, fortunately, or unfortunately in my life, having gotten a chance to train with folks of that level, just clean this throw and the power and it was very nice. Okay, I immediately actually enjoyed being thrown like that to throw a little shade at craig jones with his current matt situation. Um, is they're very, they were quite thin. Uh, and as Travis commented on and not just the thinness of the mats, but they were laid on like, concrete. So I felt, I felt it's like soft until it's not. Um, but uh, being thrown very cleanly, I just felt like there's, this is not going to lead to injury. It was great. It was an injury prone, but then, as I mentioned to you, when I, a day or two after my entire leg, one of them, I guess it's the left leg, um, was just just black bruise. It didn't, it didn't hurt too bad, but it was just, the body has gotten soft? So, I guess the question I have is, um, does the body get used to just that number of throws just over time being thrown thousands of times a month, [/INST] Unquestionably your body gets used to it. So it hardens, it gets really hard, which is why judo is, is hard to come back to after you've taken a long period of time off because your body is not used to that impact anymore. Um, I always found out that, you know, when I was training due to a lot, it's hard to, it's hard to shed weight and keep weight off because your body, like, you know, it develops like this layer of protection on itself that it doesn't want to give up, you know, when you're sucking a lot of weight, that means you're frail and, you know, so I always seem to retain weight more, you know, when you're doing hard judo training as opposed to, you know, losing weight. It's easy when you go out for runs and things like that to, to shed the water weight, but to actually keep the pounds off was </s><s>[INST] pretty hard. Yeah, the body kind of develops, like you said, a level of protection. What about the boundary, just out of curiosity. Again, I haven't ever had the opportunity to train with folks at a high level, um, is, you know, in jujitsu, the, there's different gyms have different styles, but I've noticed that at the highest levels, people, You can go pretty hard in a certain kind of way where it's more technical and you're not, you're moving at 100%, But the power is not 100%. It's, it's, it's a weird little dance. It's, it's like you're not really um, forcing stuff you're more focused on on the right timing, the right uh positioning of hands and feet and body and all those kinds of things. You're not like forcing stuff in the way you would in competition, like really the power that sounds similar to you for the way you try to defend or [/INST] so there's different styles of judo and they say the japanese style, the technical style of Judah is exactly what you just talked about. It's like, it's almost like two guys in pajamas, right? We're not going, we're not using, we're using minimal effort, maximum efficiency, We're moving around and we're trying to feel that movement and its timing and finesse and technique and fun and clean throws. And when, you know, when you train in japan, You can train 15 rounds of ran dori, five minute rounds, that's 75 minutes of straight, you know, sparring, you can do that straight in Japan without a problem. I mean you'll get tired, of course, you're going to fall a lot, you're gonna throw a lot. Um, but it's very like free feeling, um, and its technical as you explained, but then when you go to europe and you try to do rounds with the Europeans, they are very physical, they don't have that same finesse in their training that they do in japan and in europe you'd be hard pressed to do eight rounds of rand Oriana night. It's so physically exhausting because so much effort is going into just fighting and fending off the gripping system and the power of your opponent, you're physically drained after eight rounds around or So it's a much different feel </s><s>[INST] when you say europe, do you mean Germany France, Britain Russia? Is there a lot. So there's a kind of similarity to all of those kinds of approaches? [/INST] The only difference would be Russia that they do a lot more active drilling a lot more sequential movement, training. They don't focus as much on grand jury, you'll do much fewer rounds in Russia during training camps, then you wouldn't, In those other countries, we just talked about France, Germany, </s><s>[INST] etcetera. What about in this kind of american system where you have much less talent uh, to work with you, uh, just select whatever works for the particular athletes or do you have a something you prefer in your system? [/INST] So you need a combination of all of it. If you're going to win at the olympic level, you have to be able to deal with the finesse of the japanese, the physicality of the Europeans, you have to focus on, on the ground, no waza aspect because a lot of people are weak there in the world of the sport of judo has a chance to win. We've sort of developed our american system of judo at least for the last say probably the last 20 years would be the american system of judo which relies heavily on taking the individual and whatever techniques they do, perfecting those techniques and the combinations and other throws that go with those throws. But then implementing and overlaying an american system of gripping ne waza conditioning, mentality, training methodology, like in game planning, you know, to beat your opponents. And I think that's the that's the secret sauce to success for fair americans because there's no way if we don't have eight partners to train with him tonight that are going to give us good rounds, right? We might have to, you know, we're all the same guy, four times those two people for, you know, two times each now have four good rounds. The rest of the rounds, I'm not being pushed to the limit, so we trained differently. Um and a lot of times we do a lot of stuff like shark bait when our athletes are preparing for competition. For example, in kayla or Travis, we're preparing for competition, We might only have 20 people in the whole gym work to work out with those two Olympic medalist, right? And of those 20 people, maybe four of them are travis's size. You know, maybe there's only one girl in the room for Kayla, she's got to train with guys and then the other ones are teenagers that are too weak to train with either one of them. So what we would do is just put together four or five people that could you know give them a challenge and we line them up and they would do a minute, a minute, a minute minute and they do five minutes in a row, as hard as they can. That person can go hard for a minute with Travis or Kayla, they can't go five minutes hard but they can go one minute hard. So it made their training much much more intense, much more physically demanding and then rinse and repeat that six times or eight times in a night. You know, they just got 40 minutes of intense Mandiri, the person that was training with them that wasn't as good, only had to do six or eight minutes of training the whole night, you know? So </s>
<s>[INST] as a subset of the country. I was thinking about this, just reading articles by journalists, especially when you're not a famous journalist in yourself, but you're more like in your Times journalist. So the big famous thing is the institution you're a part of. Like you can just lie. Cause you're not going to get punished for it. You're going to be rewarded for the popularity of an article. So if you write 10 articles, it's, there's a huge incentive to just make stuff up. You gotta get clicks. To get clicks. That's the first and foremost. And like culturally, people will attack that article to say it's, it's not like one half the country will attack that article for saying it's dishonest, but they'll kind of forget the, you will not have a reputational hit. There won't be a memory like this person made up a lot of stuff in the past. No, they'll take one article at a time and they'll attach the reputation hits will be to New York Times, the institution. And so for the individual journalist, there's a huge incentive to make stuff up. [/INST] Totally. It's, it's, it's, and it's scary because it's almost like you can't survive if you're just an old school, honest journalist who really works hard and tries to get it right and does it with nuance. Like what you can be is you can be a big time sub-stacker or big time podcaster. A lot of people do have a reputation for accuracy and rigor and they have huge audiences. But if you're working in a big company right now, it's, I mean, especially, I mean, I, I, I, I, I think that many of the big media brands are very much controlled by the left and, but I will say that the ones that are controlled by the right are even more egregious. Not just in terms of accuracy, but also in terms of, you know, the New York Times, for all of its criticisms, it's, they have a handful of, they, they here and there, they put out a pretty, you know, saw an article that strays from the, you know, Barry Weiss wrote there for a long time, and then you've got, they wrote an article criticizing free speech on campus stuff recently, and they have, you know, they have a couple very, you know, left progressive friendly conservatives, but they have conservatives that are operating the op-eds. Fox News, you're not seeing thoughtful, Breitbart, you're not seeing thoughtful progressives writing there, right? </s><s>[INST] There's some degree to which the New York Times, I think, still incentivizes and values the vertical, the high effort. So you're allowed to have a conservative opinion if you do a really damn good job. [/INST] Like if it's a very thorough, in-depth art kind of. And if you kind of pander to the progressive senses in all the right ways. I always joke that Ted, they always have a couple token conservatives, but they get on stage and they're basically like, so totally, you're all, the progressivism's right about all of this, but maybe libertarianism isn't all about, you know, it's just, so there is an element, but you know what? It's something, it's better than being a total tribal. I think you can see the New York Times tug of war, the internal tug of war. You can see it, because then they also have these awful instances, you know, or like, you know, the firing of James Bennett, which is this whole other story. But like, they have, yeah, you can see it going both ways, but in the 60s, what did you have? You had ABC, NBC, CBS, you know, the 70s, you know, you had these three news channels and they weren't always right, and they definitely sometimes spun a narrative together, maybe, about the Vietnam or whatever, but if one of them was just lying, they'd be embarrassed for it. They would be penalized, they'd be dinged, and they'd be known as, this is the trash one. And that would be terrible for their ratings, because they weren't just catering to half the country, they're all catering to the whole country. So, both on the axis of accuracy and on the axis of neutrality, they had to, you know, try to stay somewhere </s><s>[INST] in the reasonable range, and that's just gone. One of the things I'm really curious about is I think your book is incredible. I'm very curious to see how it's written about by the press. Because I could see, I could myself write, with the help of Chad JPT, of course, [/INST] clickbait articles in either direction. </s><s>[INST] Yeah, it's easy to imagine. Your whole book is beautifully written for clickbait articles. If any journalist out there need help, I can help. Yeah. I can write the most atrocious criticisms. [/INST] Yeah, I'm, yeah, yeah, I'm ready, I'm braced. </s><s>[INST] Yeah, so, speaking of which, you write about social justice. You write about two kinds of social justice, liberal social justice and S.J.F., social justice fundamentalism. [/INST] What are those? Yeah, so, like, the term wokeness is so loaded with baggage, it's kind of like mocking and derogatory. And I was trying not to do that in this book. If it's the term loaded with baggage, you're already kind of, you're from the first minute, you're already behind. So, to me, also, when people say wokeness is bad, social justice is bad, they're throwing the baby out with the bathwater. Because the proudest tradition in the U.S. is liberal social justice. And what I mean by that, again, liberal meaning lowercase L. It is intertwined with liberalism. So, Martin Luther King, classic example, I have a dream speech, he says stuff like, this country has made a promise to all of its citizens and it has broken that promise to its black citizens, right? In other words, liberalism, the Constitution, the core ideals, those are great. We're not living up to them, we're failing on some of them. So, civil disobedience, the goal of it wasn't to hurt liberalism, it was to specifically break the laws that were already violating, the laws that were a violation of liberalism to expose that this is illiberal. That the Constitution should not have people of different skin color sitting in different parts of the bus. And so, it was really patriotic, the civil rights movement. It was saying, this is a beautiful, we have a liberalism is this beautiful thing and we need to do better at it. So, I call it liberal social justice and it used the tools of liberalism to try to improve the flaws that were going on. So, free speech, Mario Savio in the 60s was a, he's a leftist and what the leftist doing in the 60s on Berkeley campus, they were saying we need more free speech because that's what liberal social justice was fighting for. But you can also go back to the 20s, women's suffrage. I mean, the emancipation, the thing that America obviously has all of it, these are all ugly things that it had to get out of, but it got out of them, one by one and it's still getting out of them. That's what's cool about America. And liberal social justice basically is the practice of saying, where are we not being perfect liberals and now let's fix that. So, that's the idea of liberalism </s>
<s>[INST] When you describe it like that, it's obvious. But when you're first saying in this little circuit that there's going to be one candidate better than uh, than half. That's not obvious. [/INST] It's not </s><s>[INST] funny math. Nice. Okay, so you have this, but ultimately you want your trying to with the voting tree, I don't know if you're trying this, but to have a circuit that's, that's like complete, that's [/INST] small, that </s><s>[INST] achieves the achieves the the same kind of, I mean, the smaller is the four. Look, practically speaking, the lower the cost of running the election of running through of computing the circuit. [/INST] That is true. But actually at this point, the reason the question was interesting is because the there was no good guarantee that the winner of that circuit would have like have beaten a lot of people, Let me give an example, The best known circuit. When we started thinking about this was the circuit called Candidate, one plays against candidate to candidate, three plays against four. And then the winners played against each other. And then by the way, five plays against 67 against eight, the winners play against each other. You understand like a giant binary tree where the binary like a balanced binary tree, it's a balanced binary tree 1234 up, 2020 for everyone going up to find the winner. Beautiful. Well, you know what? There's a system in the world where It could just be that there's a candidate called # one That just beats like 10 other people, Just the 10 that they need to be on their way up and they lose to everyone else. But somehow they would get all the way up. My point is it is possible to outsmart that circuit in one weird way of the world, which makes that circuit a bad one because you want to say I will use this circuit for all elections And you might have a system of inputs that go in there where the winner only beat 10 other people, which is the people they had to beat on the way up. </s><s>[INST] So you want to have a circuit where there's as many like the final result is as strong as possible. Yes. And so what ideas do you have for [/INST] that? So we actually only managed to improve it to square root event. So if n is number of vortices and over two would be the ideal. We gotta we gotta describe the event versus longest. Yeah, exactly. Which is, well that is how it could be, a lot could be, it </s><s>[INST] could be a big improvement, so that's okay. Cool. Is there something you can say with words about what kind of circuit, what that looks like? [/INST] I can give an idea of one of the tools inside, but the actual execution ends up being more complicated. But one of the widgets inside this is building a system where you have like a candidate who plays like the one part of the whole huge huge tree. Is that that same candidate? Let's call them 77 plays against somebody. Let's make up some numbers, let's call the others like letters. So seven plays against a seven is also going to play against me separately. And the winners of each of those who play each other by the way. Seven is also going to play C seven is going to play D. And the winners are going to play each other and the winners are going to play each other. We call this seven against all. Well seven against, like everyone from a bunch of Got it. So there's some </s><s>[INST] nice overlap between the matchups. Yes somehow has a nice [/INST] feature to it. Yes. And I can tell you the nice feature because at the base of this giant tree, at the base of this giant circuit, like this is a widget, you rebuild the things that the widget. So I'm just describing one widget, but in in the base of this widget, you have lots of things which are seven against someone, Seven against someone. Seven against someone. In fact every matchup at the bottom is seven against someone. What that means is if seven actually beat everyone, they were matched up against, well, seven would rise to the top. So one possibility is, if you see a seven emerged from the top, you know, that seven actually beat everyone they were against. On the other hand, if anyone else is on top, let's call it f if f is on top, How did that get there? Well, FB seven on the way at the beginning. So the point is the outcome of this circuit has a certain property. If you see a seven, you know, that the seven actually be the Brazilian people, if you see anyone else at least, you know, they beat seven? </s><s>[INST] Yeah. Then you can prove that has a nice property. That's really interesting. Is there something you can say perhaps going completely outside of what we're talking about, is how we may uh have mathematical ideas of improving the electoral [/INST] Process. That wouldn't know, I can't give you that one. I mean, is </s><s>[INST] there like, do you ever see as um as is there be, do you see as there being a lot of opportunities for improving how we vote? Uh Like from your I don't know if you saw parallels, but you know, it seems like if this actually kind of maps to your sort of covid work, which is there's a network effect, right? It seems like we should be able to apply similar kind of effects of how we decide other things in our lives and and uh one of the big decisions will make is who represents us in government? Do you ever think about like mathematically about those kinds of systems? [/INST] I think a little bit about those because where I went to college, the way we voted for student government was based on this. Is it called ranked choice where you eliminating you eliminate the bottom and there's runoff elections? So that was the first time I ever saw that. And I thought that made sense. The only problem is it doesn't seem so easy to get something that makes sense adopted as the new voting system. That's a whole </s>
<s>[INST] I had speaking of getting attacked, I had a fun time getting attacked a few months ago for publishing a reading list, some reading at least a book a week, read 18 or 19 books from the [/INST] beginning of the year. You got attacked for the books you chose or for this? I don't know for what. I don't know for what, but it became quite viral. Attacked for reading? That's something. </s><s>[INST] So basically what happened is that people, I actually don't, it's not worth folks who know. Fair. Folks who don't even worry about it. What I really loved about being attacked for is it shows you can get attacked for anything, apparently. So it's not like I did something wrong. It was kind of a beautiful thing and it was just the most intensely beautiful display of absurdity of Twitter and the internet. There were articles written about me with a book list. There's no bad books on it. The thing I was being mocked for is reading Dostoyevsky, reading stuff that sounds like a high school reading list. Oh, I see. Or all these kinds of aspects of the reading list which doesn't stand up to any sort of legitimate kind of criticism. But the fact that people are just looking for single words or single aspects of a tweet and so on to criticize. It actually forced me to, because I released a video about summarizing my takeaways from one of the books and I've been meaning to do more and more, but every time I start to record it, I have this negative feeling. They kind of ruin the fun of sharing with others. [/INST] I know it's fair, apparently. Oh, I see. Yeah, I know exactly what you're talking about. My advice on that is don't do it. Just don't record it. And is that what you did basically? </s><s>[INST] Yeah, for now. But I think time cures it. But for now, I decided not to. Yes. [/INST] It's just until I feel joy when I do it. We are in such a privileged position to even be able to do this sort of thing, right? I have taken on projects and then it sort of sounds good or I end up doing it because there's some third party that brings the idea and I feel like I can't really say no or whatever. And then when I get in front of the camera or I have to write something for a while, I did a newspaper column that I hated doing. I realized that I'm ruining the exact thing that I have worked to build, which is that I can just do whatever I want. Why am I doing this? And sometimes it takes me a week to realize it. Sometimes it takes me a year, but just don't do it. That's the- </s><s>[INST] In this case in particular, it's also that there's a private thing I enjoy, which is reading. Right. And if sharing that private thing you enjoy is not fun, then just don't share it. Yeah, there's certain things, there's certain private things that should remain private, which is one of the first things ever. I'm the same person privately as I am publicly, but the books, it's like, man, I don't get to share, I guess through these conversations I can share some of the stuff I'm reading and enjoying it. Because it sucks. It sucks to get attacked for stuff. And it sucks to get attacked for stuff you love. [/INST] Yeah, especially reading. That's the bottom of the barrel. I have these ideas where I'll go, maybe for my next thing, I'll go from politics, which is so toxic. I'll go to travel blogging because there's so many travel bloggers I follow and there's so many interesting places. And then I go, wait a second. I like traveling and just hanging out. Now traveling is going to be my job and now I've got to bring two cameras with me and I've got to get shots and I've got to film my food. I'm not going to do that. I'm just going to do what I'm doing, but then I'll travel </s><s>[INST] when I want to take a vacation. And of course, some of it could be fun. I mean, I have to say, when I did one video on a book in 1984, I really enjoyed it. That whole process was fun. It was, um, um, I don't think I've ever thought as hard about a book when I had to make a video about it. Cause I had to like, you know, I read 1984. I don't know how many times, probably five, 10 times. I don't remember. Um, I read animal farm way more. Uh, but I don't think I was like, what do I think? What are the key takeaways for me? I didn't really know. Like if you asked me what I think about even animal farm, cause I haven't done that one and I've read that one. I don't know. Over 50 times is probably my favorite book is like, I would have to struggle and making a video about it. Basically a little mini lecture forced me to actually have an opinion about the details of it and to do enough research to think like, okay, what is the historical context of this book? I mean, it allowed me to say interesting and to think interesting stuff about the book. I, I, it was, I found it to be really rewarding to basically the old Feynman [/INST] thing. Uh, one of the best ways to learn is to teach video about it. Yeah. Yeah. I can't think of one thing I would say about animal farm and I read it again, not that long ago, but I don't know </s>
<s>[INST] why you, by the way? [/INST] I think because um I am kind of an agent of chaos, and Alex is in his own way, an agent of chaos and what is, provides an opportunity in this kind of news media space that you and I travel in, it's the kind of things where none of us three, you know, as we said on the show knew what it would be like if you, you know to certain within certain parameters what, you know, Megyn kelly or wolf Blitzer or any of these corporate figures are going to be like in a conversation to some extent, none of us had any idea, I knew they didn't know I was bringing knocking up jokes um so that was kind of what was so exciting, so I said at one point I'm kind of envious of the audience because this is there's so many exciting things that are happening and that the internet and podcasting provides people an opportunity to do that, it was great, </s><s>[INST] yeah, that was the greatest pairing with Alex jones that I've ever seen by far, so like, so I immediately knew, no, this isn't a knock on tim, but I don't even know if tim was prepared, [/INST] it was not prepared for this car could be prepared. </s><s>[INST] Well, so, I mean, I don't know if tim is used to that, I think Joe Rogan is more equipped prepared for the chaos, just the years he's been in it. Like I immediately thought this is the right pairing for joe Rogan because Alex jones has been on joe Rogan a few times, three times. My favorite so far was with tim Dillon, but tim was clearly tim. Dillon was also kind of uh a genius in his own right, but he was kind of a fan and he was back and he was stepping away, he was almost like in all of Alex jones where uh, you were both, you were in all of the experience that's being created and at the same time fearlessly just trolling the situation. I mean, to do a knock knock joke to stop me, that just shows that you're in control of the experience, You know, you're like writing the experience that immediately was like, this needs to be on Rogan, so I, I hope that happens as well, you're on your own of course on Rogan, but just you, that's an experience, that's the, whatever, this gotta be a good name for it, like Jimi Hendrix experience, there's no mic going out because it's taken, I don't know how many years you can, you can restart the experience [/INST] Because I feel so interrupt you. I feel a very big responsibility, especially in 2020 to provide fun and something cool and something unique that hasn't been done before for the audience. I think this has been a very rough year on our audiences psychologically and in other aspects of their lives. So I feel if I'm gonna be there, I'm going to put on a show and it's also going to be great because it also alienates the people you don't want, right? So there's a lot of people who sit there and be like, oh, he's telling people were too cool for school uh, where they're like, oh, he's telling knock knock jokes. This is stupid. I'm like, good if you have an issue with having eaten cotton candy or doing a puzzle with a kid with without, you know, by yourself, that's on you and it's something very, something I think is the enemy is cynicism and this idea that like, oh, this is too silly and it's like we need that kind of childlike aspect of our lives. I think it's something we could use more of, It's very much an aspect of our media culture that to kind of have condemnatory about that or to do it in a certain very corporate fake way. So it is something I encourage a lot, something I enjoy doing. Um, and again, I like the first time I was on tim, I had a propeller beanie on, you know, with the motorized and a lot of people were like, I can't take anyone seriously who dresses like this. I go good. If you judge someone's ideas by how they appear instead of the ideas themselves. You're not someone I want on my team. </s><s>[INST] Are we going to address? Yeah. The outfit you're wearing, We got dresses short for those who are colorblind. Michael is wearing the, or, or just listening to this Michaels. We're in the exact opposite the universe from, from another dimension outfit, which is a white suit and black shirt. Uh, so genius. Okay, so, uh, you [/INST] just see the next two looks I've planned. </s><s>[INST] Oh no. Yeah, they're great. [/INST] Well, obviously this relationship is going to enter. So we put them on in step. </s><s>[INST] Okay. Is there some deep philosophy of the humor is, uh, let's go through a trolling discussion. Is there some, is there like chapters to this genius or is this just, uh, what makes you smile in the morning? [/INST] I mean, I think you're honestly in this case using their genius a little loosely. I think this is particularly genius, but I do think it is fun. It is exuberant, it is joyous. Um, I think the bigger my audience has gotten and the more I actually communicate with fans, I do feel it kind of kicks in these paternal maternal instincts. It's, which is very, very odd. I did not expect to have that. I </s><s>[INST] mean, who's the dad? [/INST] I'm the dad and the mom, I remember. And it may have been similar for you. I'm curious to hear it for young, smart, like, um ambitious men, like 24-27 for me was a very rough period because that's the window where a lot of people get married and they kind of check out and if you're very much kind of finding your own road, um you don't know what's happening, no one's in a position to really guide you or help you. And it's, it's tough, it's a very tough window. And what I'm finding now is having these kids who are in that position, but now, instead of them stumbling along for some of them, I'm the one who could be like, no, no, no, no, it's not you, it's everybody else and to be able to give them that semblance of feeling, seen to use a cliche expression to feel normal and that no, no, you're the, you're the, you're the heroes here, they're the background noise. Um it's just really very uh flattering and humbling to be in that position. </s>
<s>[INST] Is there some aspect to it? That's it's like a muscle in terms of the all the combinations of letters and numbers that you just said. Is there some aspect that if uh I can improve the quarter lies the half life, decrease that number. If I just practice like I drink a lot of coffee is to sort of habit alters how your body is able to get rid of the caffeine, [/INST] not how the body is able to get rid of the caffeine but it does alter how sensitive the body is to the caffeine and it's not at the level of the enzyme degrading the caffeine. It's at the level of the receptors that caffeine will act upon. Now it turns out that those are called a denizen receptors and maybe we can speak about what a Dennis scene is and sleep pressure and all of that good stuff. But as you start to drink more and more coffee um the body tries to fight back and it happens with many different drugs by the way and it's called tolerance. And so one of the ways that your body becomes tolerant to a drug is that the receptors that the drug is binding to these sort of welcome sight these sort of you know, picture mitts as it were that received the drug those start to get taken away from the surface of the cell and it's what we call receptor internalization so the cell starts to think she wears you know there's there's a lot of stimulation going on, this is too much. So I'm just going to when normally I would you know coat my cell with let's just say five of these receptors for argument's sake things are going a little bit too ballistic right now I'm going to take away at least two of those receptors and downscale its just having three of those and now you need two cups of coffee to get the same effect that one cup of coffee got you before and that's why then when you go cold turkey on coffee all of a sudden the system has equilibrium rated itself to expecting X amount of stimulation and now all of that stimulation is gone so it's now got too few receptors and you have a caffeine withdrawal syndrome and that's why for example with you know drugs of abuse things like heroin when people go into abstinence you know as they're moving into their addiction they will build up a progressive tolerance to that drug so they need to take more of it to get the same high but then if they go cold turkey for some period of time the system goes back to being more sensitive again it starts to repopulate the surface of the cell with these receptors but now when they re use and they fall off the wagon if they go back to the same dose that they were using before, You know, 10 weeks ago or three months ago, that does can kill them. They can have an overdose even though they were using the same amount at those two different times. The difference is that it's not the dose of the drug, it's the sensitivity of the system and that's the same thing that we see with caffeine in terms of training the muscle as it were. Is the system becomes less sensitive. Can calibrate </s><s>[INST] is there a time the number of hours before bed? That's a safe bet to most people to recommend you should drink caffeine this many hours. Like is there an average half life that should be aiming at? Or is this advice kind of impossible because there's so much variability, [/INST] there is huge variability and I think everyone themselves, you know to a degree knows it, although I'll put a caveat on that too because it's slightly dangerous point. So the recommendation for the average adult and who where is the average adult in society? There is no such thing, but for the average adult it would be probably cutting yourself off maybe 10 hours, you know before. So assuming a normative time in society, I would say try to stop drinking caffeine, you know before two PM and just keep an eye out, you know and if you're struggling with sleep, dial down the caffeine and see if it makes a difference. </s><s>[INST] Can I ask you about sleep and uh learning so how to sleep effect learning sleep before learning sleep after learning, which are both fascinating kind of dynamics of the minds, interaction with this extra conscious state. [/INST] Yeah, sleep is profoundly and very intimately related to your memory systems and your informational systems. Um the first as you just mentioned is that sleep before learning will essentially prepare your brain almost like a dry sponge, ready to sort of, you know, initially soak up new information. In other words, you need sleep before learning to effectively imprint information into the brain to lay down fresh memory traces and without sleep, the memory circuits of the brain and we know we've studied these memory circuits will you know, essentially become waterlogged as it were for the sponge analogy and you can't absorb the information as effectively. So you need sleep before learning, but you also need sleep. Unfortunately after learning to to then take those freshly minted memories and effectively hit the save button on them. But it's nowhere near as quick as a digital system. It takes hours because it's a physical biological change that happens at the level of brain cells. But sleep after learning will cement and solidify that new memory into the neural architecture of the brain, therefore making it less likely to be forgotten. So, you know, I often think of sleep in that way as it's almost sort of future proofing information in in what way? Well, it means that it gives it a higher degree of assurance to be remembered in the future rather than go through the sort of degradation that we think of as forgetting. So the brain has in some ways by default, you know, there is forget and actually I would love to, I was going to say sleep is relevant for memory in three different ways, but I'm going to amend that and say there's four different ways which is learning, maintaining, memorizing abstraction, assimilation association and then forgetting which the last one sounds oxymoronic based on the form of three, but I'll see if I can explain. So sleep after learning then sort of, you know, sets the that information like Amber um, in, you know, in in solidification. The third benefit, however, is that sleep we've learned more recently is much more intelligent than we ever gave it. Credit for. Sleep doesn't simply just take individual memories and strengthen them sleep well, then intelligently integrate and cross link and associate that information together. And it's almost like informational alchemy. So that you wake up the next morning with a revised mind wide web of associations. And that's probably the reason that, you know, you've never been told to stay awake on a problem, you know? And in every language that I've been quite about that phrase or very something very similar seems to exist, which means to me that this creative associative benefit of sleep transcends cultural boundaries. It is a common experience across humanity. Um Now I should note that I think the french translation of that is much closer to you. Um I think you sleep with a problem, whereas the british just sleep on a problem. The french you sleep with a problem. I think it's so much about the romantic difference between the british and the french, but let's let's not go that um </s>
<s>[INST] You can lose yourself. You can forget yourself. [/INST] You forget you're on a treadmill and you just start like walking and you're sweating and you're, and you're having wine and then certain points you're like, Like, uh, you, like, you, you start jogging, especially like we were watching, uh, not all quiet on the rest in front. What's the one where they've got to, they've got to get the message to the front line. I would run like I was in World War two. I would run when they would run and it was fucking awesome. And I would be like, cause they were doing drinks. They'd be like, take a drink. You got to run up there and be like, okay. Yeah. I'm really into, I'm really into history podcasts right now. Like I've been in them for a while. 20th century or everything? Everything. Everything. I listened to, uh, uh, was it Marcus Aurelius and Cleopatra today? Uh, in the middle of the podcast, they're like, you know, just, you know, Cleopatra wasn't as hot as everyone says. I was like, why are you saying that? Yeah. Tell me she's a six. She looked like Snooki. Yeah. Like, let me, let me dream that she looked like Kim Kardashian. Yeah. And then I listened to that one today. </s><s>[INST] I listened to World War II a lot. Oh. A lot of books on World War II, a lot of podcasts about it. [/INST] What's your favorite theater, the Pacific or European? </s><s>[INST] No, European. Pacific, well, because my family's so much of it has died in that theater. Dude, so much of it. I hate to sound cliche, like I'm Arnold Schwarzenegger in an 80s movie, but it's personal. [/INST] Well, you know what I find funny about that? Yeah. Is Lenin, It was Lennon, right? John Lennon? No, no, no. Lennon was World War II, right? Or was it Stalin? Stalin. Stalin thought him and Hitler would be friends. Yeah. I think that's so cute that he was like, we're going to be buddies. Yeah. Like we're boys. Yeah. And then Hitler's like, oh, fuck you. I'm Hitler, bro. This is what I do. </s><s>[INST] Well, at first he was like, fuck yeah. Yeah. Yeah, yeah, yeah. We'll be friends. [/INST] Yeah, yeah, sure, sure. And then call me, call me. Better yet, I'll show up and win her. How's that sound? Yeah. That, uh, that, uh, I find that I find all of that so fascinating. When I was a kid, I had a hard time understanding how, cause we were always at war with Russia when I was a kid and I had a hard time understanding how we could be on the same team as Russia in World War two. And I was like, wait, how did that turn south? And then you, this is a podcast. Yeah. I'm, I'm that all of that, all of that, like, All of the World War II, I got really into the Pacific shit for a while, but I'm really deep in the, in the whole, we went to Normandy from the Cliffs of Dover and to think, so that's the fucking beach. That's the fucking beach. Oh shit, this is cold as fuck. These dudes jumped in ice cold water. And this isn't like a cool beach, like this is, And it's just so insane to, and then to see like the, it's pretty intense. I don't know why I got into history late in life. I wasn't, I was kind of into it, but I'm really into it now. And I love just learning a little something about, you know, today was, I listened to like the Noiser has a great history stuff. It's like history for dummies, I think. Like I get, I can't listen to the really smart stuff. It starts losing me. Too many names that I'm gone. </s><s>[INST] Yeah. Well, Dan Carlin is always the best. [/INST] Your podcast with Dan Carlin was so fucking good. He is. He is. I mean, I only know about Martin Luther because of Dan Carlin. I only know. Like I would have, I made a joke about some Lutheran the other day. And everyone laughed and I was like, did you guys listen to the same podcast? I did because I just am quoting Dan Carlin. I that his podcast, I mean, we all quoted the same shit about Genghis Khan about how he could shoot a dove off a horseback. But we knew that all four hoofs had to be off the ground at the same time they shot. They would sometimes take their meat and stick it under their saddles. And that, I mean, Dan Carlin is He is the motherfucker. Yeah. God, those were ma'am discovering podcasts was the coolest time of my life. </s><s>[INST] And the interesting thing about him is, is audio. And so it's the voice. So for me, I mean, everybody has a story with a prostitute in a motel. Dan Carlin was my prostitute in the motel. I invited him to a motel. I don't even remember in the middle of nowhere. He shows up with that voice and the rest, the rest is history. Things they will never know what happened. Oh boy, did he like, no, I'm just kidding. I'm really running with it. Yes, we did we got along with it. I mean, he's an incredibly kind and thoughtful person constantly self-critical thinking he's not good enough He just works on those episodes forever forever and he just thinks that there's these just like with Goggins. There's these other historians That I think like way on him like they're going to judge him or something like this in his mind I talked about I talked to it with them, but Daniel Patelli and I guess [/INST] His thing is, I guess his hang-up is, Carlin's is, he's not like this, he doesn't feel like he's a real historian, but he is. I mean, it's the way he shares the story. Look, we had a history teacher in seventh grade who was a con artist, and he came and taught her seventh grade, and it was a total con artist. All he taught us about was barnstorming, barnstorming and the JFK assassination. I walked away having such an appreciation for barnstorming, a very small blip on Americana. But I know a lot about barnstorming because of this guy and he, because he was passionate about barnstorming. It was the funniest seventh grade history class I've ever taken my entire life. </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] Well, there's also, like how many design discussions do there have to be about particular details, like implementation of particular small features? Because the features that seem small, I bet some of them might be like really require really big design decisions. [/INST] Yeah, yeah. Well, so I mean, let me give you another example of this. Python has a feature called async await. So it's, it's a new feature. I mean, in the long arc of history, it's a relatively new feature, right? That allows way more expressive asynchronous programming. Okay. Again, this is, this is a, Python is a beautiful thing, and they did things that are great for mojo for completely different reasons. The reason the async await got added to Python, as far as I know, is because Python doesn't support threads. Okay. And so Python doesn't support threads, but you want to work with networking and other things like that that can block. I mean, Python does support threads, it's just not its strength. And so, and so they added this feature called async await. It's also seen in other languages like Swift and JavaScript and many other places as well. async await and mojo is amazing, because we have a high performance header, gs, compute, runtime underneath the covers, that then allows non-blocking IO so you get full use of your accelerator. That's huge. Turns out, it's actually really an important part of fully utilizing the machine. You talk about design discussions. That took a lot of discussions, right? And it probably will require more iteration. And so my philosophy with mojo is that, you know, we have a small team of really good people that are pushing forward, and they're very good at the extremely deep knowing how the compiler and runtime and like all the low level stuff works together. But they're not perfect. Same thing as the Swift team, right? And this is where one of the reasons we released mojo much earlier is so we can get feedback. And we've already like renamed a keyword, did a community feedback and we use an ampersand and now it's named in out. We're not we're not renaming existing Python keywords because that breaks compatibility, right? We're naming things we're adding and making sure that they are designed well, we get usage experience, we iterate and work with the community because, again, if you scale something really fast and everybody writes all their code and they start using it in production, then it's impossible to change. And so you want to learn from people, you want to iterate and work on that early on. And this is where design discussions, it's actually quite </s><s>[INST] important. Could you incorporate an emoji like into the language, into the main [/INST] language? Like a good, like a good, like a, like a, do you have a, do you have a </s><s>[INST] favorite one? Well, I really like in terms of humor, like raw, full, whatever, rolling on the floor, laughing. So that could be like, what would that be the use case for that? Like an exception, throw an exception of some sort? I don't know. You should totally file feature requests. Or maybe a hard one. It has to [/INST] be a hard one. People have told me that I'm insane. So this is, this is, I'm </s><s>[INST] liking this. I'm going to, I'm going to use the viral nature of the internet to [/INST] actually get this, to get this past. I mean, it's funny, you come back to the flame emoji file extension, right? The, you know, we have the option to use the flame emoji, which just even that concept cause, for example, the people that get </s><s>[INST] up to say, now I've seen everything. Yeah. There's something, uh, it kind of, it's reinvigorating. It's like, uh, it's like, Oh, that's possible. That's really cool. [/INST] That for some reason that makes everything else like, I think the world is ready for this stuff. And so, you know, when we have a package manager, we'll clearly have to innovate by having the compiled package thing be the little box </s><s>[INST] with the bow on it. Right. I mean, it has to be done. It has to be done. It has to be done. Is there some stuff on the roadmap that you particularly stressed [/INST] about or excited about that you're thinking about a lot? I mean, as a today snapshot, which will be absolutely tomorrow, uh, the lifetime stuff is really exciting. And so lifetimes give you safe references to memory without dangling pointers. And so this has been done in languages like Rust before. And so we have a new approach, which is really cool. I'm very excited about that. That'll be out to the community very soon. Um, the traits feature is really a big deal. And so that's blocking a lot of API design. And so there's that. I think that's really exciting. Um, a lot of it is these kind of table stakes features. Um, one of the things that is, uh, again, also lessons learned with Swift, uh, is that, uh, programmers in general like to add syntactic sugar. And so it's like, Oh, well this annoying thing, like, like in Python, you have to spell unbar, unbar add. Why can't I just use plus deaf plus? Come on. Why can't I just do that? Right. And so trigger a bit of syntactic sugar. It makes sense. It's beautiful. It's obvious. We're trying not to do that. And so, um, for two different reasons, one of which is that again, lesson learned with Swift. Swift has a lot of syntactic sugar, um, which may or may be a good thing. Maybe not. I don't know. But, um, but because it's such an easy and addictive thing to do sugar, like make sure blood get crazy, right? Um, like the community will really dig into that and want to do a lot of that. And I think it's very distracting from building the core abstractions. The second is we want to be a good member of the Python community, right? And so we want to work with the broader Python community and yeah, we're pushing forward a bunch of systems programming features and we need to build them out to understand them. But once we get a long ways forward, I want to make sure that we go back to the Python community and say, okay, let's do some design reviews. Let's actually talk about this stuff. Let's figure out how we want this stuff all to work together. And syntactic sugar just makes all that more complicated. So, </s>
<s>[INST] him. Like he was great. This craftsman. I mean, that's the craftsmanship to that. [/INST] Yeah, But also the mental agility to understand the whole thing, put the pieces in contacts, you know, real view of the balance of the design worked because if you don't understand it properly, when you start to draw it, you'll, you'll fill up half the white board with like a little piece of it and you know, like your ability to lay it out and understandable way. It takes a lot of understanding. So </s><s>[INST] and be able to zoom into the detail and then Zuma [/INST] to make really fast. </s><s>[INST] What about the impossible things that your dad believe that you can do anything. That's a weird feature for a craftsman. Yeah, it seems that that uh echoes in your own behavior. Like that's that's the, [/INST] well, it's not that anybody can do anything right now, right? It's that if you work at it, you can get better at it and there might not be a limit. And they did funny things like, like he always wanted to play piano. So, at the end of his life, he started playing the piano when he had Parkinson's. He was terrible. But he thought if he really worked out in this life may be the next life, you'd be better at it, </s><s>[INST] He might be onto something. Yeah. [/INST] People enjoy doing it. Yeah. It's pretty funny. </s><s>[INST] Do you think the Perfect is the enemy of the good and hardware and software engineering? It's like we were talking about Javascript a little bit and the messiness of the 10 day building process. [/INST] Yes. Let's, you know, creative tension, right? Mhm. So, creative tension is you have two different ideas that you can't do both, right? And and but the fact that you want to do both causes you to go try to solve that problem. That's the creative part. So, we're building computers. Like some people say we have the schedule and anything that doesn't fit in the schedule we can't do, right? So, they throw out the perfect Because they have a schedule. I hate that. All right. Then there's other people who say we need to get this perfectly right? And no matter what? More people more money, right? And there's a really clear idea about what you want and some people really articulating it. So, let's call that the Perfect. Yeah. All right. But that's also terrible because they never ship anything. You never had any goals. So now you have now you have your framework, you can't throw out stuff because you can't get it done today because maybe you get it done tomorrow or the next project, right? You can't. So you have to, I work with a guy that really like working with, but he over filtered his ideas </s><s>[INST] over filters. [/INST] He started thinking about something as soon as he figured out was wrong with it, he'd throw it out and then I start thinking about it and you know, you come up with an idea and then you find out what's wrong with it and then you give it a little time to set because sometimes, you know, you figure out how to tweak it or maybe that idea help some other idea. So idea generation is really funny. So you have to give your idea space like spaciousness of mind is key, but you also have to execute programs and get shift done. And then it turns out computer engineering is fun because it takes, you know, 100 people to build a computer, 200 or 300 whatever the number is and people are so variable about, you know, temperament and you know, skill sets and stuff that in a, in a big organization you find the people who love the perfect ideas and the people that want to get stuffed on yesterday and people like that come up with ideas and people like the let's say shoot down ideas and it takes the whole it takes a large group of </s><s>[INST] people, some are good at generating ideas, some are good at filtering ideas and then all in that giant mess you somehow, I guess the goal is for that giant mess of people to uh find the perfect path through the tension, the creative tension. But like how do you know when you said there's some people good at articulating what perfect looks like what a good design is. Like if you're sitting in a room and you have a set of ideas about like how to design a better processor, how do you know this is this is something special here, this is a good idea, let's try this. [/INST] Have you ever brainstormed idea with a couple of people that were really smart and you kind of go into it and you don't quite understand it and you're working on it and then you start, you know, talking about it, put it on the whiteboard, maybe it takes days or weeks and then your brain starts to kind of synchronize, it's really weird, like you start to see what each other's thinking and it starts to work like you can see it work like my talent and computer design is I can I can see how computers work in my head like really well and I know other people can do that too and when you're working with people that can do that, like it is kind of amazing experience. And then, and every once a while you get to that place and then you find the flaw, it was just kind of funny because you can, you can fool yourself, but the two of you kind of drifted along the direction that was useless. That happens to like you have to because you know, the nice thing about computers and there's always reduction practice. Like you come up with your good ideas and I've noticed some architects who really love ideas and then they work on them and they put it on the shelf, then go work on the next idea and put on the shelf, they never reduced to practice. So they find out what's good and bad because mom was every time I've done something really new by the time it's done, like, the good parts are good, but I know all the flaws, like </s>
<s>[INST] there is an aspect in which that question is quite dumb, especially because it's being used to almost very generically by these different networks to say, well we're trying to work this out, but you know, basically, uh how much do you see the value of seeing things you don't like? Not you disagree with because it's very difficult to know exactly what you articulated, which is the stuff that's important for you to consider that you disagree with. That's really hard to figure out. The bottom line is the stuff you don't like if you're a Hillary clinton supporter, you may not want to, it might not make you feel good to see anything about donald trump. That's the only thing algorithms can really optimize for currently [/INST] everything, you know, they can do better. This is weird. I think so. Now we're engaged in some moronic back and forth, where I have no idea why people who are capable of building google facebook twitter are having us in these incredibly low level discussions. Do they not know any smart people do they not have the phone numbers of people who can elevate these discussions? </s><s>[INST] They do. But this optimized for a different thing and they're pushing those people out of those rooms there. [/INST] They're optimizing for things we can't see and yes profit is there? Nobody, nobody's questioning that. But they're also optimizing for things like political control or the fact that they're doing business in Pakistan and so they don't want to talk about all the things that they're going to be bending to in Pakistan. So they were involved in a fake discussion. </s><s>[INST] You think so? You think these conversations at that depth are happening inside google. You don't think they have some basic metrics under user engagements. You're [/INST] having a fake conversation with us guys. We know you're having a fake conversation. I do not wish to be part of your fake conversation. You know how to cool. You know, these units, you know, high availability, like nobody's business. My gmail never goes down almost. See you think </s><s>[INST] just because they can do incredible work on the software side with infrastructure, they can also deal with some of these difficult questions about human behavior. Human understanding. You're not, I've [/INST] seen that I've seen the developers screens that people take shots of inside of google and I've heard stories inside of facebook and Apple, we're not, we're engaged. They're engaging us in the wrong conversations were not at this low level? Here's one of my favorite questions why is every piece of hardware that I purchased in in text base equipped as a listening device? Where where is my physical shutter to cover my lens? We had this in the 1970s Cameras that had lens caps. You know, how much would it cost to have a security model? Pay five extra bucks? Why is my indicator like software controlled? Why when my camera is on? Do I not see that the light is on? By putting it is uh something that cannot be bypassed. Why have you set up all my devices? It's some difficulty to yourselves as listening devices and we don't even talk about this. This this this this thing is total fucking bullshit. </s><s>[INST] Well, I hope these discussions are happening about privacy. This is there more difficult than you're giving? It's not just privacy. Yeah, [/INST] it's about social control. We're talking about social control. Why do I not have controls over my own lovers? Just have a really cute ui where I can switch, I can dial things or I can at least see what the algorithms are. </s><s>[INST] You think that there is some deliberate choices being made? [/INST] There's emergence and there is uh intention. There are two dimensions. The vector does not collapse onto either access. But the idea that anybody who suggests that intention is completely absent is a child </s><s>[INST] that's really beautifully put. And uh like many things you've said is gonna make me, can [/INST] I turn this around slightly like? Yeah. I sit down with you and you say that you're obsessed with my feet. Mhm I don't even know what my feet is, what are you seeing that? I'm not </s><s>[INST] I was obsessively looking through your feed on twitter because it was really enjoyable because it was the tom Lehrer element is the humor in it. [/INST] By the way that feed is eric are weinstein on twitter? Eric are weinstein? </s><s>[INST] Yeah, [/INST] why </s><s>[INST] why did I find it enjoyable or what it was I seeing? [/INST] What are you looking for? What are we doing this? What is this podcast about? I know you've got all these interesting people, I'm just some guy who's sort of a podcast guest </s><s>[INST] sort of podcast, you're not even wearing a tie, I mean not even not even a serious interview. Uh I'm searching for meaning for happiness, for a dopamine rush, So short term and long term. [/INST] And how are you finding your way to me? What what what what is I I don't honestly know what I'm doing to reach you. </s><s>[INST] The representing ideas which feel common sense to me and not many people are speaking. So it's kind of like the dog, the intellectual dark web folks right. Uh they these folks from Sam Harris and Jordan Peterson to yourself are saying things where it's like you're like saying, look there's an elephant is not wearing any clothes and I say yeah, yeah let's have more of that conversation, that's how I'm finding you, [/INST] I'm desperate to try to change the conversation we're having? I'm very worried. We've got an election in 2020. I don't think we can afford four more years of a misinterpreted message, um which is what donald trump was, and I don't want the destruction of our institutions. They all seem hell bent on destroying themselves. So I'm trying to save theoretical physics, trying to save the new york times, trying to save are various processes. And I think it feels delusional to me that uh this is falling to a tiny group of people who are willing to speak out without getting so freaked out that everything they say will be misinterpreted and that their lives will be ruined through the process. I mean, I think we're in an absolutely bananas period of time and I don't believe it should fall to such a tiny number of, of shoulders to shoulder this way. </s>
<s>[INST] I think you'll love it to go to simply save.com slash likes to customize your system and claim your free indoor security camera plus 20% off with interactive monitoring. This is a lex Friedman podcast. To support it, please check out our sponsors in the description and now dear friends, here's Christopher Capa Zola. Let's start with a big and difficult question, how did World War One start on [/INST] The one hand, World War I started because of a series of events in the summer of 1914 that brought sort of the major powers of Europe into conflict with one another. But I actually think it's more useful to say that World War I started at least a generation earlier when rising powers particularly Germany Started devoting more and more of their resources towards military affairs and naval affairs. This sets off an arms race in Europe, it sets off a rivalry over the colonial world and who will control the resources in Africa and Asia. And so by the time you get to the summer of 1914. </s><s>[INST] And so in a [/INST] lot of ways I say the war has already begun and this is just the match that lights the flame. </s><s>[INST] So the capacity for war was brewing within like the leaders and within the populace, they started accepting sort of slowly through the culture propagated this idea that we can go to war. It's a good idea to go to war. It's a good idea to expand and dominate others, that kind of thing. Maybe not put in those clear terms, but just a sense that military action is the way that nations operate at the global scale. [/INST] Yes, Yes. And right. So yes, there's a sense that the military can be the solution to political conflict in europe itself and the end is that war and military conflicts are already happening, right, that there's war, particularly in Africa in North Africa in the Middle East, you know, Balkans conflict is already underway. Um, and the european powers haven't faced off against each other. They usually faced off against in asymmetrical conflict against much less powerful states. Um, but you know, in some ways that, that war is already underway. So </s><s>[INST] do you think it was inevitable because World War One is brought up as a case study where it seems like um, a few accidental leaders and a few accidental events or one accidental event led to the war. And if you change that one little thing, it could have avoided the war. Your senses, the drums of war have been beating for quite a while and it would have happened almost no matter what, or very likely to have happened. [/INST] Yes, historians never like to say things are inevitable. Um and certainly, you know, there were people who could have chosen a different path, both in the short term and the long term, but fundamentally there were irreconcilable conflicts in the system of empires in the world. In 1914. I can't see uh you know, it didn't have to be this war, but it had, it probably had to be a war. </s><s>[INST] So there was a german empire, the Austro Hungarian Empire, There's France and great Britain us US p called the empire at that moment. [/INST] Yet, when </s><s>[INST] do you graduate to empire status? [/INST] Well, certainly after, after 1898 with the acquisition of the former territories of the Spanish Empire. You know, the United States has formal colonial possessions. Um and it has sort of mindsets of of rule and military acquisition that would define an empire in a kind of more informal sense. </s><s>[INST] So you would say you would put the blame or the responsibility of starting World War One into the hands of the german empire and Kaiser Wilhelm the second, [/INST] You know, That's a really tough call to make. Um and you know, that deciding that is going to keep historians in business for the next 200 years. And uh I think there are people who would lay all of the blame on the Germans, right? And you know, who would point toward a generation of arms build up, you know, alliances that that Germany made and promises that they made to uh to their allies in the Balkans, to the Austro Hungarians. Um And so yes, there's an awful lot of responsibility there. Um there has been a trend lately to say, um no, it's no one's fault, right, That, you know, that all of the various powers literally we're sleepwalking into the war, right? They backed into it inadvertently. I think that lets everyone a little too much off the hook. Right. And so I think in between is uh you know, I would put the blame on the system of empires itself on the system, but in that system, the actor that sort of carries the most responsibility is definitely imperial Germany. </s><s>[INST] So the leader of Austro Hungarian Empire franz joseph the first, his nephews, Archduke franz Ferdinand, he was assassinated. And so that didn't have to lead to war. And then the leader of the German empire, Kaiser, Wilhelm the second pressured sort of uh started talking trash um and boiling the water that ultimately resulted in the explosion. Um Plus all the other players. So what can you describe the dynamics of how that unrolled what us, what's the role of us? What's the role of France was the role of great Britain Germany and Austro Hungarian Empire. Yeah. [/INST] Over the course of about four weeks, right following the assassination of the archduke in Sarajevo. Um it sort of triggers a series of political conflicts and ultimately ultimatums um sort of demanding um sort of that that one or other power sort of stand down in response to the demands of either um you know, Britain France or or or in turn Germany or Russia at the same time that those alliances kind of trigger automatic responses from the other side. And so it escalates. Um and once that escalation is combined with the call up of military troops, then none of those powers wants to be sort of the last one to kind of get ready for conflict. So even throughout it, they they think they are getting ready in a defensive maneuver. Um and they, if they think if there is conflict, well, it might be a skirmish, it might be, you know, sort of a standoff. Uh it could be solved with diplomacy later because diplomacy is failing now. Um that turns out not to be the case. Diplomacy fails. It's not a skirmish, it becomes a massive war. And the americans are watching all of this from the sidelines, They have very little influence over what happens that summer. </s><s>[INST] How does it go from a skirmish between a few nations to a global war, is there a place where there's a phase transition? Yeah, [/INST] I think the phase transition is in, over the course of the fall of 1914, when the Germans make an initial sort of bold move into France in many ways they're fighting the last war, the Franco Prussian war of 18 of 1870. Um and they really do sort of, you know, kind of want to have a quick sort of lightning strike in some ways against France to kind of bring the war to a speedy conclusion, France turns out to be able to fight back more effectively than the Germans expected. Um and then uh the battle lines sort of harden and then behind that the french and the Germans as well as the british on the side of the french, start digging in literally. Right. Um and digging trenches, trenches that at first are, you know, three ft deep to, you know, to avoid shelling from artillery, then become six ft 10 ft deep, you know, two miles wide, that include telegraph wires, that include whole hospitals in the back. And then at that point, you know, the the front is locked in place and the only way to break that is sort of basically dialing the war up to 11 right sort of massive numbers of troops, massive efforts, none of which work. Right. And so the war is stuck in this, but that's the, that's the phase transition right there. </s><s>[INST] What were the machines of war in that case you mentioned trenches, What were the guns used? What was the size of guns? What are we talking about? What, what what did Germany start accumulating that led up to this war? [/INST] One of the things that we see immediately is the industrial revolution of the previous 30 or 40 years brought to bear on warfare. Right. And so you see sort of machine guns, you see artillery, uh you know, these are the kind of the key weapons of war on both sides, right. The vast majority of battlefield casualties are from artillery shelling from one side to another. Um not you know, sort of rifle or or even sort of, you know, machine gun kind of attacks in some ways the weapons of war are are human beings, right? Um you know, tens of thousands of them poured over the top in these sort of waves to kind of try to break through the enemy lines and it would work for a little while. Um you know, but but holding the territory that had been gained often proved to be even more demanding than than gaining it and so often um you know, each side would retreat back into the trenches and and wait for another day. </s><s>[INST] And how did Russia, how did Britain, How did France get pulled into the war? I suppose that France one is the easy one. But what, what is the order of events here becomes a global war? [/INST] Yeah, so Britain France and Russia are at this time and in that are in alliance. Um and so the conflicts, you know, in the summer of 1914, that lead sort of to the declarations of war happened sort of one after another. Right. Um in August in late August of 1914. Um and all three powers essentially come in at the same time because they have promised to do so through a series of alliances um conducted secretly in the years before 1914, that committed them to defend one another. Uh Germany, Austria, Hungary and the Ottoman Empire have their own sort of set of secret agreements that also commit them to defend one another. Um And what this does is it sort of brings them all into into conflict at the exact same moment. They're also for many of these countries bringing not just their their national armies, but also their empires into the conflict. Right, so Britain and France of course have, you know, enormous sort of global empires, They begin mobilizing soldiers as well as raw materials, Germany has, you know, less of an overseas empire, Russia. And the Ottoman Empire of course have their own sort of hinterland. Um you know, within the empire and very soon, you know, sort of all of the warring powers are are bringing the entire world into into the conflict. </s><s>[INST] Did they have a sense of how deadly the war is? I mean, this is another scale of death and destruction at [/INST] the beginning? No, but very quickly um the scale of the devastation of these sort of massive over the top attacks on trenches is apparent to the military officers. And it very quickly becomes apparent even at home. Uh, you know, there is of course censorship of the battlefields and, and you know, specific details don't reach people, but you know, for civilians and in any of the warring powers, they know fairly soon how destructive the war is. Uh, and to me, that's always been a real sort of, um, puzzle. Right? So that by the time the United States comes to decide whether to join the war in 1917, they know what exactly what they're getting into, right? They're not backing into the war in the ways that the European powers did. Um, you know, they've seen the devastation, they've seen photographs, they've seen injured soldiers and they make that choice anyway. </s><s>[INST] When you say they doing the leaders of the people did, uh, the, the death and destruction reach the minds of the american people by that time. [/INST] Yes, absolutely. You know that we don't in 1917 have the mass media that we have now. But um, but you know, there are images in newspapers, there are newsreels that play at the movie theaters. Um, and of course some of it is sanitized, but, but that combined with press accounts often really quite descriptive press accounts. Um, glory accounts </s><s>[INST] reached, [/INST] you know, anyone who cared to read them. You know, certainly plenty people didn't follow the news felt it was far away. But, but most americans who cared about the news knew how devastating this war was? </s><s>[INST] Yeah, there's something that happens that I recently visited Ukraine for a few weeks. There's something that happens with the human mind as you get away from the actual front where the bullets are flying like literally one kilometer away, you start to not feel the war that you'll hear an explosion, you'll see an explosion. You start to like get assimilated to it or you start to get used to it. And then when you get as far away from like currently what is Kiev, you start to, you know, the war is going on, Everybody around you is fighting in that war, but it's still somehow distant and I think with the United States, with the ocean between, even if you have the stories everywhere, it still is somehow distant. Like the way a movie is maybe, Yeah, like a movie or a video game, it's somewhere else. Even if your loved ones are going or you are going to fight. [/INST] Yeah, that is absolutely the case. And in some ways that's true. Even for the home fronts in in europe, you know, except for the areas where, you know in Belgium and France where the war is, you know, right there in your backyard for other people. Yeah, there's a, there's a distance and soldiers of course feel this very strongly when they european soldiers, when they're able to go home on leave often, you know, deeply resent the, you know, the, what they see is that the luxury that that civilians are living in during the war. </s><s>[INST] So how did us enter the war? Who was the president? What was the dynamics involved? And could it have stayed out [/INST] to answer your last question first? Yes. Right. Uh that the United States could have could have stayed out of the First World war uh as a military power. Um the United States could not have ignored the war completely, right? It shaped everything right? It shaped It shaped trade, it shaped goods and services. Agriculture. You know, whether, you know, there was a crop coming, whether there were immigrants coming across the Atlantic to work in American factories, right? The US can't ignore the war, but the us makes a choice in 1917 to enter the war by declaring war right on on Germany and Austria. Uh and in that sense, um this is a war of choice, but it's it's kicked off by a series of events. Right? So President Woodrow Wilson has been president through the this entire period of time. Uh he has just run uh in the 1916 presidential election on a campaign to keep the United States out of war. But then in early 1917, the Germans in some ways um sort of twist the americans arms right that the Germans sort of high command comes to understand that, you know that they're stuck, right? That they, you know, they're stuck in this trench warfare, they need a big breakthrough. There one big chance is to kind of is to sort of break the blockade to push through that, that the british have imposed on them to break the break through against against France. And so they do. And along with this, they start sinking ships on the atlantic, including american ships. The Germans know full well this will draw the United States into war. But the Germans look at the United States at this moment, a relatively small army, a relatively small navy, a country that at least on paper is deeply divided about whether to join the war. And so they say, let's do it, but they're not going to get any american soldiers there in time. Right? Uh you know, it was a gamble, but I think probably the their best chance they took that gamble they lost right in part because french resistance was strong in part because americans mobilized much faster and in much greater numbers than the Germans thought they would. So </s><s>[INST] the american people were divided. The [/INST] american people were absolutely divided about whether to enter this war. Right. From 1914 to 1917, there is a searing debate across the political spectrum, it doesn't break down easily on party lines about whether it was in the U. S. Interest to do this, Whether American troops should be sent abroad. Um whether you know, Americans would end up just being cannon fodder for the European empires eventually as American ships are sunk um first in the Lusitania in 1915 than in much greater numbers in 1917. You know that the tide starts to turn and Americans feel that you know, our response is necessary and the actual declaration of war in Congress is pretty lopsided, but it's not unanimous by any means. </s><s>[INST] Lopsided was entering the war. [/INST] Yeah, </s><s>[INST] Well that's really interesting because there's echoes of that in later wars or Congress seems to nobody wants to be the guy that says no to war for some reason. Once you sense that in terms of, sorry, in terms of the politicians because then you appear weak. But I will, I wonder if that was always the case. So you make the case that World War One is largely responsible for defining what it means to be an american citizen. So in which way does it define the american citizen? When [/INST] you think about citizenship, What it means is two things. First of all, what are your rights and obligations? What is sort of the legal citizenship that that you have as a citizen of the United States or any other state? Uh And the second is a more amorphous definition of like what does it mean to belong right to be part of America, right to feel american to uh, you know, to love it or hate it or be willing to die for it. Right. Um, and both of those things really are crystal clear, um, in terms of their importance during the war. Right? So both of those things are on the table being a citizen who is a citizen who isn't matters. So, people would never carry passports or or you know, any anything before suddenly have to. Um, but also what it means to be an american right to feel like it to be part of this project is also kind of being defined and enforced during </s><s>[INST] One project, you know, is a funny way to put a global war. Right? So, can you tell the story? Perhaps that's a good example of it, of the James Montgomery Flagg's 1916 poster That reads, I want you, a lot of people know this poster, I think in its original form, it's meme ified from, I don't know, but we know this poster and we don't know where it came from, or most Americans, I think me included didn't know where it came from, and it actually comes from 1916. Does this post represent the birth of something new in America, which is a commodification or I don't know that propaganda machine that says what it means to be an american. It's somebody that fights for their country. [/INST] Yeah, So the image and it's in fact, I think one of the most recognizable images, not only in the United States, but in the entire world, right? Um, and you can you can bring it almost anywhere on earth in 2022 people will know what it refers to, right? And so this is an image that circulated first as a magazine cover later as a recruitment poster where the figure is Uncle Sam sort of pointing at the viewer with his fingers pointing and saying, I want you Right? And the I want you as a recruitment tool to join the us army. And this image, you know, really kind of starts as a kind of like I said, a magazine cover in 1916 by the artist James Montgomery Flagg. It initially appears under the heading, what are you doing for preparedness meaning to prepare in case war comes to the United States, right? At that point in 1916 were still neutral. Um in 1917. Uh, it's turned into a U. S. Army recruiting poster. Um, and then it reappears in World War Two reappears generations after, you know, like you said, it's now gets remixed, meme ified, it's all over the place, </s><s>[INST] I think [/INST] for me it's a it's a turning point. It's a sort of window into american culture at a crucial moment in our history where the federal government is now embarking on a war overseas, that's going to make enormous demands on its citizens and at the same time where sort of technologies of mass production and mass media and what we would probably call propaganda are being sort of mobilized for the for the first time in in this new kind of way. </s><s>[INST] Well in some sense, is it fair to say that the empire is born, the expanding empire is born from the Noam chomsky perspective kind of empire [/INST] that </s><s>[INST] seeks to have military influence elsewhere in the world. [/INST] Yes, but I think as historians, we need to be at least as interested in what happens to the people who are getting pointed to by Uncle Sam right? Rather than just the one, you know, whether he's pointing at us. Um and you know, so so yes, he's asking us to do that, but but how do we respond? </s><s>[INST] And the people responded? So the people are ultimately the the machines of history, the mechanisms of history, it's not the Uncle Sam. Uncle Sam can only do so much if the people aren't willing to step up. [/INST] Absolutely they and, you know, the american people responded for sure, but they didn't build what Uncle Sam asked them to do um, in that poster, right? Um and I think that's you know, kind of a crucial aspect that, you know, there never would have been sort of global US power without the response that begins in World War One. </s><s>[INST] What was the Selective Service Act of 1917. [/INST] So, one of the very first things that uncle Sam wants you to do right is to register for selective service for the draft, right? Um and the laws passed very soon after the US enters the war. Um it's sort of, you know demanding that all men first between 21 and 30, then between 18 and 45 register for the draft. Um and they will be selected by a government agency, by a volunteer organization. </s><s>[INST] It [/INST] is a legal requirement to register. Not of course not everyone who registers is selected. Uh, but over the course of the war, 24 million men register almost four million serve in some fashion. What </s><s>[INST] was the response? What was the feeling amongst the american people to have to sign up to the selective service act? [/INST] Well, I have </s><s>[INST] to register. This [/INST] is uh this is a bigger turning point than than we might think right in some ways this is a tougher demand of the american public than entering the war. It's one thing to declare war on Germany, right? It's another thing to go down to your local post office and fill out the forums that allow your own government to send you there to fight. Um, and this is especially important at a time when the federal government doesn't really have any other way to find you unless you actually go and register yourself. Right? Um, and so, you know, ordinary people are participating in the building of this war machine. But at least a half a million of them don't write and simply never fill out the forums moved from one town to another. </s><s>[INST] But you said 20 million, 20 something [/INST] About 24 million register at least 500,000. </s><s>[INST] Is it surprising to you that that many registered? It [/INST] is, and that's what I I, you know, sort of tried to dig in to figure out how did, how did you get 24 million people to register for the draft? And, uh, it's certainly not coming from the top down, right? Um, you know, there may be 100 sort of agents and what's now called the FBI. Um, you know, it's certainly not being enforced from Washington. It's being enforced in, you know, through the, the eyes of everyday neighbors, you know, through community surveillance, all kinds of ways. </s><s>[INST] Oh, so there was like a pressure, [/INST] There's a lot of pressure, </s><s>[INST] interesting. So there's not a significant like the anti war movement, as you would see, maybe later with Vietnam and things like this. [/INST] There was a significant movement before 1917, but, but it becomes very hard to keep up an organized anti war movement after that, particularly when the government starts shutting down protests. </s><s>[INST] So as the Selective Service Act of 1917 runs up against some of the freedoms, some of the rights that are uh defined in our founding documents. What was that clash, like what was sacrificed? What freedoms and rights were sacrificed in this process? [/INST] I mean, I think on some of the fundamental right right is liberty right? That conscription sort of demands. Um, you know, uh, sacrifice on the behalf of some for the for notionally for the protection of all </s><s>[INST] if you're against the war, you're forced to fight? [/INST] Yes. You know, and there were small provision for conscientious objectors, solely those who had religious objections to all war right, not political objections to this war. Um and um you know, several 1000 were able to take those provisions, but even then, um they faced social sanction they faced ridicule, some of them faced intimidation. You know, so those liberty interests, both individual freedom, religious freedom. You know, those are some of the first things to go. </s><s>[INST] So what about freedom of speech? Was the silencing of the press of the voices of the different people that were object? [/INST] Yes, absolutely. Right. And so very soon after the selective service act is passed, then you get the Espionage Act, which of course is back in the news in 2022. </s><s>[INST] What's the espionage act? [/INST] The Espionage Act is a sort of Omnibus bill. It contains about 10 or different provisions, very few of which have to do with espionage. But one key provision basically makes it illegal to say or do anything that would interfere with military recruitment. Right? Um and that that provision is used to shut down radical publications to shut down german language publications. Um and, you know, this really has a chilling impact on speech during the war. </s><s>[INST] Could you put into words what it means to be an american citizen that is in part sparked by World War One. So what is what is that, what does that mean? Somebody that's should be willing to sacrifice certain freedoms to fight for their country. Um Somebody that's willing to fight the spread freedom elsewhere in the world, spread the american ideals. Like what what what um does that begin to tell the story of what it means to be an american? [/INST] I think what we see is a change, right? So citizenship during World War One now includes uh the obligation to defend the country right to serve right and two if asked to die for it, right? And we certainly see that and I think we see the close linkage of military service and U. S. Citizenship coming out of this time period. Um but you know when you start making lots of demands on people to fulfill obligations in turn they're gonna start demanding rights. Um and we start to see not necessarily during the war but after more demands for free speech protections, more demands for for equality for marginalized groups. Um and so you know, obligations and rights are sort of developing in a dynamic relationship. </s><s>[INST] Oh it's almost like an overreach of power sparked a sense like oh crap we can't trust centralized power to abuse like to drag us into a war. We need we need to be able to, so there's a the birth of that tension between the government and the people. It's [/INST] a rebirth of it, you know, of course that, you know, that tension is always there. But but in its modern form, I think it comes from this </s><s>[INST] re intensification of it. So what about the, you said that World War One gave birth to the surveillance state in the U. S. Can you explain? [/INST] Yeah. So the espionage act, you know, sort of empowers federal organizations to watch other americans. Um they are particularly interested in anyone who is obstructing the draft. Um, anyone who is trying to kind of organize labor or strikes or radical movements. Um, and anyone who might have sympathy for, for Germany, which basically means, you know, all german americans come under surveillance initially. Um you know, this is very small scale, but but soon every government agency gets involved from the Treasury Department's Secret Service to the Post Office, which is sort of reading mail to the Justice Department which mobilizes 200,000 volunteers. You know, it's a it's a really significant enterprise. Much of it goes away after the war. But of all the things that go away, this core of the surveillance state is the thing that persists most most fully. </s><s>[INST] Is this also a place where government, the size of government starts to grow in these different organizations or maybe creates the momentum for growth of government. [/INST] Oh, it's it's X. Exponential growth, right? That you know that over the course of the war by almost any metric you use, right? The size of the federal budget, the number of federal employees, the number of soldiers in the standing army, all of those things skyrocket during the war. They go down after the war, but they never go down to what they were before </s><s>[INST] and probably gave a momentum for growth. Did World War One give birth to the military industrial complex in the United States? So war profiteering expanding of the war machine in order to financially benefit a lot of parties involved. [/INST] So I guess I would maybe break that into two parts. Right? That on the one hand, yes. Um, the there is war profiteering. Um, there are investigations of it. Um, in the years after the war, there is a widespread concern that the profit motive had played, uh, you know, too much of a part in the war. And that's definitely the case. Um, but I think when you try to think of this term military industrial complex, um, it's best, you know, to think of it as, you know, at what point does the one side lock in the other, right, that military choices are shaped by industry, uh, you know, objectives and, and vice versa. And I don't think that that was fully locked into place during World War One. I think that's really a Cold War phenomenon, when the United States is on this intense kind of footing for for two generations in a row. </s><s>[INST] So industrial is really important there. That is companies. So before then, weapons of war were created, were funded directly by the government were like um like who was manufacturing the weapons of war, They [/INST] Were generally manufactured by private industry. Um uh there were of course our arsenal sort of 19th century iterations where the government would produce its own weapons partly to make sure that they got what they wanted. But, but most of the weapons of war, for all of the European powers and the United States are produced by private industry. </s><s>[INST] So why do you say that the military industrial complex didn't start then? What was the, what was the important thing that happened in the Cold War? [/INST] I think, um one way to think about it is that it's the Cold War is a point at which it switches from being a dial to a ratchet, right? So during World War One, um, you know, the relationship between the military and industry dials up, you know fast and high and stays, you know, stays that way and it dials back down. Whereas during the Cold War sort of, the relationship between the two often looks more like a ratchet. It goes up again </s><s>[INST] in the way that you start, I think the way the military industrial complex is often involved um discussed is as a system that is unstoppable. [/INST] Like </s><s>[INST] it expands it almost, I mean, if you take a very cynical view, it creates war so that it can make money. It doesn't just find places where it can help through military conflict, it creates tensions that [/INST] directly or indirectly </s><s>[INST] lead to military conflict that can then fuel and make money from. [/INST] That is certainly one of the concerns of both people, um you know, who are critical of the First World War and then also of Dwight Eisenhower right, when he's president and and sort of in his farewell address where he sort of introduces the term military industrial complex and some of it is about the profit motive, but some of it is a fear that Eisenhower had, that no one had an interest in stopping this, right, and that no one had a voice in stopping it and that the ordinary american could could really do nothing to sort of, you know, to kind of to dial to dial things down. </s><s>[INST] Is it strange to you that we don't often hear that kind of speech today with like Eisenhower speaking about the military industrial complex. So, for example, we'll have people criticizing the spending on the on war efforts, but they're not discussing the yeah, the machinery of the military industrial complex, like the the basic way that human nature works, that we get ourselves trapped in this thing, they're saying like there's better things to spend money on versus describing a very seemingly natural process of when you build weapons of war, that's going to lead to more war, Like it pulls you in somehow [/INST] Yeah, I would say throughout the Cold War. Um and even after the end of it, there has not been a sustained conversation um in the United States about about our defense establishment, right? What we, you know, what we really need um and you know, what what serves our interest. Um and and to what extent sort of other things like market forces, profit motives, um you know, belong in that in that conversation. Uh what's interesting is that in the generation after the First World War, that was that conversation was on the table right through a series of investigations in the US the night committee Um in Britain, a Royal Commission journalistic exposes, you know, this would have been just talked about constantly in the years between about 1930 and 1936, as people were starting to worry, right, that storm clouds were gathering in Europe again. </s><s>[INST] Yeah, but it almost seems like those folks get pushed to the fringes, you made an activist [/INST] versus </s><s>[INST] uh into like versus a thinking leader. Those [/INST] discussions are often marginalized, framed as conspiracy theory um etcetera. Um And um you know, I think it's important to realize that, you know, uh in the generation after World War One, this was a serious civic conversation. It led to, you know, sort of investigations of defense, uh sort of finance. It led to experiments Um in Britain and France in public finance of war material. And I think those conversations need to be reconvened um now in the 21st century, </s><s>[INST] is there any parallels between World War One and the war in Ukraine? The reason I bring it up is because you mentioned, sort of there was a hunger for war, the capacity for war that was already established and the different parties were just boiling the uh, the tensions. So there's a case made that America had a role to play, NATO had a role to play in the current war in Ukraine. Is there some truth to that? Um, when you think about it in the context of World War One, or is it purely about the specific parties involved, which is Russia and Ukraine? [/INST] I think it's very easy to draw parallels between World War One, uh, and the war in Ukraine, but I don't think they really work um, that, you know, the First World War uh, in some ways is generated by a, You know, fundamental conflict in the European system of empires, right? In the global system of empires. Um, so in many ways, if there's a parallel, the war in Ukraine is the parallel to some of the conflicts in, you know, in the Mediterranean and the Balkans in 1911-1913, um, that, um, you know, that then later there was a much greater conflict. Right? And so I think if there's any lessons to be learned for how not to, you know, let World War Three look like World War One, um, it would be to make sure that, you know, that systems aren't locked into place. Um, that escalate wars out of out of people's expectations. </s><s>[INST] That I suppose what I was implying that this is the early stages of World World War Three, that in the same way that several wolves are licking their chops or whatever the expression is, they're they're creating tension. They're creating military conflict with the kind of unstoppable imperative for global war. That's, I mean, many kind of people that are looking at this are really worried about that now. The the stopping the forcing function to stop this war is that there's several nuclear powers involved, which has at least for now, worked to stop full on global war. But I'm not sure that's going to be the case. In fact, it's one of the surprising things to me In Ukraine, is that still in the 21st century we can go to something that involves nuclear powers, not directly yet, but awfully close to directly go to a hot war. And so do you worry about that, that there's a kind of descent into a World War One type of scenario? [/INST] Yes, I mean, that that keeps me up at night and I think it should keep, you know, the citizens of both the United States and Russia up at night. Um, and I think uh Again, it gets back to what I was saying in that in the summer of 1914, even then things that looked um like a march toward war could have been different, right? Um and so I think it's important for leaders to um of both countries and of all of the sort of related country, you know, of Ukraine of the various NATO powers to really sort of imagine off ramps and to imagine alternatives um and to make them possible. Um you know, whether it's through diplomacy, whether it's through other formats, um you know, I think that, you know, that that's the only way to prevent sort of greater escalation. </s><s>[INST] What's the difference between World War One and the Civil War in terms of how they defined what it means to be an american, but also uh the american citizens relationship with the war. Um what what the leaders were doing is they're interesting differences in similarities [/INST] besides </s><s>[INST] the fact that everybody seems to have forgot about World War One in the United States and everyone still remembers Civil War. [/INST] I mean, it's true and you know, the the american civil war defines american identity. Um uh in some ways, along with the Revolution in the Second World War, more so than any other conflict. Um and you know, it's it's a fundamentally different war, right? It's one because it is a civil war, right? Because um because of secession because of the confederacy. Um you know, this is a conflict happening on the territory of the United States between americans and so the dynamics are, are, are really quite different, right? So, you know, the leaders particularly Lincoln have a different relationship to the home front, to civilians um than than they then say Wilson or Roosevelt have in the in World War One and two. Also </s><s>[INST] the way you would tell the story of the civil war, perhaps similar to the way we tell the story of World War Two, there's like a reason to actually fight the war. The way we tell the stories we're fighting for this idea that all men are created [/INST] equal, </s><s>[INST] that the war is over slavery in part, perhaps that's a [/INST] radical, </s><s>[INST] drastic oversimplification of what the war was actually about in the moment. Like how do you get pulled into an actual war versus a a hot discussion? And the same with World War Two people kind of frame the narrative that it was against evil, Hitler being evil. I think the key part of that is probably the holocaust is how you can formulate Hitler's being evil if there's no holocaust, perhaps there's a case to be made that we wouldn't see World War Two as such. Quote unquote good war, that there's an atrocity that had to happen to make it really uh to be able to tell a clear narrative of why we get into this war. Perhaps such a narrative doesn't exist for World War One. And so that doesn't stay in the American mind who tried to sweep it under the rug given though overall 16 million people died. So, so to you, the differences in the fact that you're fighting for us for ideas and fighting on on on the homeland. But in terms of people's participation, you know, um, fighting for your country, Was there similarities there? [/INST] Yeah, I mean, I think uh, I mean the civil war in, in both the north and the south troops are raised overwhelmingly through volunteer recruitment. There is a draft and in both the north and the south. But uh, you know, it's, it's not significant. Only 8% of uh, of confederate soldiers came in through conscription. Um, and so in fact, you know, the, the mobilization for volunteers often organized locally around individual communities or states create sort of multiple identities and and levels of loyalty where people both in the north and the south have loyalty both to their state regiments, um, to their, their sort of community militias and as well to to the country, they are fighting over the country, right over the United States. And, and so the and the Union and the confederacy have conflicting and ultimately irreconcilable visions of that. But but you know, that sort of nationalism that comes out of out of the Union after the victory in the war is a kind of crucial force shaping America ever since. </s><s>[INST] So what was the neutrality period? Why did us stay out of the war for solo? Like what was going on in that interesting? Like what made Woodrow Wilson change his mind? What, what, what was the interesting dynamic there? [/INST] I always say that the United States entered the war in April of 1917, but Americans entered it right away. Right. They entered it. Um, you know, some of them actually went and volunteered and fought almost exclusively on the side of Britain and France. Um, at least 50,000 joined the Canadian Army or the British Army and serve millions volunteer. They sent humanitarian aid. I think in many ways, modern war creates modern humanitarianism. Um, and we can see that in the neutrality period. Um, and even if they wanted the United States to stay out of the war, a lot of Americans get involved in it by thinking about it, caring about it, you know, arguing about it. And, and you know, at the same time, they're worried that british propaganda is shaping their news system. They are worried uh, that german espionage is undermining them. They're worried that both Britain and Germany are trying to interfere in american elections in american news cycles, you know, there and at the same time, a revolution is breaking out in Mexico. Right? So they're sort of, you know, concerns about what's happening in the Western hemisphere as well as what's happening in europe. </s><s>[INST] So World War One was supposed to be the war to end all wars and it didn't, How did, how did World War One pave the way to World War Two, every nation probably has their own story in this trajectory towards World War Two. How do europe allow World War Two to happen? How did the soviet Union Russia allow World War Two to happen? And how did America allow World War Two to happen in Japan? [/INST] Yeah, you're right. The answer is different for each country, right? Uh, that in some ways in Germany and the culture of defeat and the experience of defeat at the end of World War One leads to a culture of resentment, recrimination, finger pointing blame. That makes german politics very ugly as one person puts, it brutalizes german politics um </s><s>[INST] places resentment at the core of the populace and its politics. [/INST] Yeah. And you know, so in some ways that lays the groundwork for the kind of politics of, of resentment and hate that comes from the, from the nazis. Um, you know, for the United States in some ways the failure to win the peace um, uh, you know, uh, sets up the possibility for for the next war, right? That that the United States, uh, you know, through Wilson is sort of crafting a new international order in order that this will be the war to end all wars. But because the United States failed to join the League of Nations, you see the United States really sort of on the hook for another generation in ASia. The story is more complicated, right? Um, and I think it's worth bearing that in mind that that World War Two is a two front war. It starts in ASIA for its own reasons. Um, World War One is transformative for Japan, right? It is a time of massive economic expansion. Um, a lot of that sort of economic wealth is poured into sort of greater industrialization and militarization. And so when the military wing um in Japanese politics takes over in the 1930s, there in some ways, flexing muscles that come out of the First World War. </s><s>[INST] Can you talk about the end of World War One, the treaty of Versailles um house what's interesting about that dynamics there, of the parties involved, of how it could have been done differently to avoid the resentment is there or again, is it inevitable? [/INST] So the war ends and very soon, even before the war is over, um the, the United States in particular is trying to shape the peace, right? And the United States is the central actor at the Paris Peace Conference in 1919. Woodrow Wilson is there, he's presiding um and he knows that he calls the shots, so </s><s>[INST] he was respected, [/INST] he was respected, but uh, but resentfully in some ways by, by the european powers Britain and France and italy to a lesser extent, who, you know, felt that they had sacrificed more, um they had two goals, right? They wanted to shape the, the imperial system in order to make sure that they're, you know, kind of fundamental economic structures wouldn't change, and they also wanted to sort of weakened Germany as much as possible, right? So that Germany couldn't rise again. What this leads to is a peace treaty that um, you know, maintains some of the fundamental conflicts of the imperial system and makes bankrupt Germany starves Germany and kind of feeds this politics of resentment that make it impossible for Germany to kind of participate in european order. </s><s>[INST] So people like historian Niall Ferguson, for example, make the case that if Britain stayed out of World War One, we would have avoided this whole mess and we would potentially even avoid World War Two. This kind of counterfactual history, do you think it's possible to make the case for that? That there was a moment, especially in that case staying out of the war for Britain, that the escalation to a global war could have been avoided and one that ultimately ends in a deep global resentment. So where Germany is resentful not just of France or particular nations, but is resentful of the entire, I don't know how you define it, the West or something like this in the entire global world, [/INST] I wish it were that easy and, you know, I think, um, it's useful to think in counterfactual, um, you know, what if, um, and if you believe as historians do in causation, um, then if that one thing causes another, then you also have to believe in counterfactual, right, that if something hadn't happened, then maybe that wouldn't, you know, that would have worked differently. Um but I think all the things that led to World War One are multi causal and nuance, and this is what historians do, we make things more complicated. Um and so, you know, there was no one thing that could have, you know, that that could have turned the tide of history, you know, and you know, oh, if only Hitler had gotten into art school, or if only Fidel Castro had gotten into the major leagues, you know, uh those are interesting thought experiments, but few few events in history, I think are that contingent. </s><s>[INST] Well, Hitler is an example of somebody who's a charismatic leader that seems to have a really disproportionate amount of influence on the tide of history. So, you know, if you look at Stalin, you could imagine that many other people could have stepped into that role and the same goes for many other, the other presidents through, or even mao it seems that there's a singular nature to Hitler that you could play the counterfactual that if there was no Hitler, you may have not had World War Two, he better than many leaders in history was able to channel the resentment of the populace into a very aggressive expansion of the military and um, I would say skillful deceit of the entire world in terms of his plans and was able to effectively start the war. So, is it possible that, I mean, could Hitler have been stopped, could we have avoided if he just got into art school [/INST] or </s><s>[INST] again, do you feel like there's a current of events that was unstoppable? [/INST] I mean, part of what you're talking about is is Hitler the individual as a sort of charismatic leader who's able to mobilize, you know, the the nation. Um and part of it is Hitlerism write his own sort of individual ability to play, for example, play off his subordinates against one another to set up a system and, you know, of that, of that nature that that in some ways escalates violence, including um you know, the violence that leads to the holocaust. Um and some of it is also Hitlerism as a, as a leader cult. And we see this in many other sort of, you know, things where, where a political movement surrounds one particular individual who may or may not be replaceable. Um so, so yes, um the World War II, we got would have been completely different um if a different sort of faction had risen to power in Germany, but but Europe, you know, depression era, Europe was so unstable. Um, and democracies collapsed throughout Western Europe over the course of the 1930s, you know, whether they had charismatic uh, totalitarian leaders or </s><s>[INST] not? Have you actually read one book I just recently, um finished, I'd love to get your opinion from a historian perspective, there's a book called Blitzed Drugs in the third Reich by norman Ohler, it makes a case that Drugs played a very large um Meth essentially played a very large role in World War Two. There's a lot of criticism of this book saying that it's um kind of to what you're saying, it takes this one little variable, it makes it like this explains everything, So everything about Hitler, everything about the blitzkrieg, everything about the military, the way the strategy the decisions could be explained through drugs or at least implies that kind of thing. Um and the interesting thing about this book, because Hitler and Nazi Germany is one of the most sort of, written about periods of human history and this was not drugs were almost entirely not written about in this context. So here comes along this semi historian, because I don't think he's even a historian, he's a a lot of his work is fiction. Hopefully I'm saying that correctly. So he tells a really, that's one of the criticisms, he tells a very compelling story that drugs were at the center of um of this period, and also of the man of Hitler, What are your sort of feelings and thoughts about um if you've got a chance to read this book, but I'm sure there's books like it that tell an interesting perspective, singular perspective on a war. [/INST] Yeah, I mean, I I have read it and I also had this sort of eye opening experience that a lot of historians did and they're like, why didn't why didn't we think about this? Right. Um and you know, I think whether he's, you know, the the author older is you know, sort of not a trained academic historians, but the joy of history is like, you don't have to be one to write good history. Um and I don't think anyone, you know, sort of criticizes him for for that. I like the book as a as a window into the third Reich and of course drugs don't explain all of it, but it helps us see um you know, it c helps us see the people who supported Hitler um the ways in which um you know, it was that mind altering and performance altering drugs were used to kind of keep soldiers on the battlefield. The ways in which um you know, I think that we we don't fully understand the extent to which the third Reich is held together with like duct tape from um you know, from a pretty early phase by like 1940 or 41 even, you know, it's all smoke and mirrors. And I think that wartime propaganda, both Germans trying to say, you know, we're winning everything and America trying to mobilize and the other allies, you know, to mobilize against Germany Described a more formidable enemy than it really was by 1941 and 42. </s><s>[INST] Yeah, I mean, I could see both cases. One is that duct tape doesn't make the man, but also as an engineer. I'm a huge fan of duct [/INST] tape because </s><s>[INST] it does seem to solve a lot of problems. And I do worry that this perspective that the book presents about drugs is somehow to the mind really compelling because it's almost like the mind or at least my mind searches for an answer how could this have happened? And it's nice to have a clean explanation. And drugs is one popular one when people talk about steroids and sports, the moment you introduce the topic of steroids. Somehow the mind wants to explain all success in the context was because this person was on steroids, Lance armstrong. Well, it's like it's a very sticky idea, certain ideas, certain explanations are very sticky and I think that's really dangerous because then you lose the full context. And also in the case of drugs, it removes the responsibility from the person, both for the military genius and the evil. And I think you mean it's a very dangerous thing to do because something about the mind maybe it's just mind is sticky to this. Well, drugs explain it if the drugs didn't happen, uh then it would be very different. Yeah, it worries me how compelling it is of an explanation, you know, [/INST] that's why it's maybe better to think of it as a window into the third Reich than an explanation of it, </s><s>[INST] But it's also a nice exploration of Hitler, the man for some reason, discussing his habits, especially later in the war. His practices with drugs gives you a window into the person. It reminds you that there's a human, this is a human being, like a human being, get that gets emotional in the morning, gets thoughtful in the morning, hopeful, sad, depressed, angry, like a story of emotions of the human being is that somehow we construct, um which is a pretty dangerous thing to do. We construct an evil monster out of Hitler when in reality he's a human being. Like all of us, I think the lesson there is a soldier instant lesson, which is all of us to some degree are capable of evil. Um or maybe if you want to make it less powerful a statement many of our leaders are capable of evil that this Hitler is not truly singular in history. That yeah, when the resentment of the populist matches the right charismatic leader, it's, it's easy to make the kind of, not easy, but it's possible to frequently make the kind of initiation of military conflict that happened in World War, World War Two by the way, because he said, not a trained historian, one of the, one of the most compelling and I don't know, entertaining and fascinating exploration of World War One comes from dan Carlin. I don't know if you've gotten a chance to listen to his sort of podcast form telling of the blueprint for Armageddon, which is the telling of World War One. What do you think about dan Carlin? You yourself as a historian who has studied, who's written about World War One? Do you do you enjoy that kind of telling of history? [/INST] Absolutely. And I think again, you know, you don't need a PhD in history to be a historian right? </s><s>[INST] That gets quite a bit of criticism from historians. [/INST] You know, I mean we you know, we like to argue with each other and take with each other. But but the one thing I have no patience for is when we like pull rank on each other. You know, I think we depend on uh you know if you're you know a historian and a university with degrees and research materials, you know, you depend on the work of people in some local community like recording oral history, saving documents and history is a, it's a social science, but it's also a storytelling art. Um and you know, history books are the ones you find on the shelves and bookstores that people read for for fun and and then and you can appreciate both the knowledge production as well as the storytelling and when you get a good oral storyteller like dan Carlin and there's a reason that thousands and hundreds of thousands of people tune in. </s><s>[INST] Yeah, but he definitely suffers from anxiety about getting things correct. It's very, it's very difficult. Well, [/INST] our first job is to get the facts, the facts correct. And then, and then to tell the story off of those </s><s>[INST] because the facts are so fuzzy. So it's uh, I mean, you have the, probably my favorite telling of World War Two is William shares rise and fall of the third Reich and or at least not telling of Nazi Germany. And that goes to primary sources a lot, which is like, I suppose that's the honest way to do it. But it's tough. It's really tough to write that way to really go to primary sources. Um, always, and I think the, one of the things that dan tries to do, which is also really tough to do perhaps easier in oral history is uh, try to make you feel what it was like to be there, which I think he does by trying to tell the story of like individual soldiers. And um, do you find that telling like individual citizens, do you find that kind of telling of history compelling? [/INST] Yeah, I mean, I think we need uh, historical imagination. Um, and I think historical imagination teaches something very valuable, which is humility um, to realize that there are other people who have lived on this planet and they organized their lives differently and, you know, they made it through just fine too. Um, and um, you know, I think that that, that kind of of meeting other people from the past can be actually a very useful skill for meeting people unlike you in the present, </s><s>[INST] unlike you, but also like you, I think both are both are humbling one, realizing that they did live in a different space and time, but to realizing that if you if you were placed in that space and time, you might have done all the same things, whether it's the brave good thing or the evil thing. Yeah, [/INST] absolutely. And you get also a sense of uh, of possibility. You know, there's this famous line, right, that, um, you know, those who do not learn history are condemned to repeat it. Um, but I think the other half is true as well, which is those who do not learn history don't get the chance to repeat it, right. You know, that we're not the first people on this planet to face. You know, any certain kinds of problems, you know, other people who have have lived through worlds like this one before. </s><s>[INST] It's like when you fall in love as a teenager for the first time, there's, and then there's a break up, you think it is the greatest strategy tragedy that has ever happened in the world. You're the first person, even though like Romeo and Juliet and so on, had had this issue, you're the first person that truly feels the catastrophic heartbreak of that experience. It's good to be reminded that no, the human condition is what it is. We have lived through it at the individual and the societal scale. Let me ask you about nationalism, which I think is at the core of I want you poster is nationalism destructive or empowering to a nation? And we can use different words like patriotism, which is in many ways synonymous to nationalism. But in recent history, perhaps because of the nazis has has um slowly parted ways that somehow nationalism is when patriotism, patriotism gone bad or something like this. Yeah, [/INST] they're they're different, right? Patriotism. Um you know, patriotism is in some ways best thought of as an emotion, right? And a feeling of of love of country, right? Um you know, literally, uh and in some ways that's a necessary condition to participate in nationalism. Um you know, whether to me, I think nationalism is crucial um in a world organized around nation states, um and you have to sort of believe that you are engaged in a common project together, right? Um and so, you know, in the contemporary United States, um you know, uh in some ways that that question is actually on the table in ways that it hasn't been in the past, but, you know, you have to believe that you're engaged in a common project, that you have something in common with the person with whom you share this nation. Um and um and that you would sacrifice for them, whether it's by paying taxes for them or, you know, or going to war to defend them. Um, that's a vision of, you know, what we might call civic nationalism. Um, that's that's the good version. The question is whether you can have that without having, um, exclusionary nationalism, you know, hating the other right fearing the other saying, yeah, you're part of this nation against all others. Um, and I think there's a long tradition in America of a very inclusive nationalism, um, that is open and inclusive, welcoming, um, and, you know, new people to this year project. Um, that's something to be defended, exclusionary nationalism is based on, you know, uh, ethnic hatreds and and others that we see throughout the world and those are things to be afraid of. </s><s>[INST] But there is a kind of narrative in the United States that a nationalism that includes the big umbrella of democratic nations, nations that strive for freedom and everybody else is against, is against freedom and against human nature. And it just so happens that it's half and half split across the world. So that's imperialism that feels like it beats the drum of war. [/INST] Yeah. And I mean, I don't want to paint too rosy a picture and certainly, you know, the United States, um, as a nation has often found it easier to define ourselves against something, um, than to clarify exactly what we're for. </s><s>[INST] Yeah, yeah. The Cold War china today, that's not only the United States, I suppose as human nature, it's we need a competitor. It's almost like maybe the success of human civilization requires figuring out how to construct competitors that don't result in global war. [/INST] Yes. Or figuring out how to turn enemies into rivals and competitors. There's a real difference. You know, you can, you, you know, you compete with competitors. You, you fight with enemies. </s><s>[INST] Yeah. With competitors as a respect. It maybe even a love underlying the competition. What lessons, what are the biggest lessons you take away from? World War One? Maybe we talked about several, but you know, you look back at the 20th century, what as a historian, what do you learn about human nature about human civilization? Bought history from looking at this war. [/INST] I think the, the lesson I would want everyone to take from the story of the First World War, uh, is that human life is not cheap. Um, that all of the warring powers thought that just by throwing more men and more material at the front, they would solve their political problems with military force. And At the end of the day in 1918, 1 side did win that, but it didn't actually solve any of those political problems. And </s><s>[INST] in the end, the regular people paid the price with their lives they [/INST] did and people who people who had been told that their lives were cheap, remembered that Right? Um, and it sort of, you know, reshapes mass politics for the rest of the 20th century, both in Europe and around the world. </s><s>[INST] Yeah, the, yeah, the cost of the death of a single soldier is not just, or a single civilian is not just the cost of that single life. It's the resentment that the anger, the hate that reverberates throughout. One of the things I saw in Ukraine is the birth of at scale of generational hate, not towards administrations or leaders but towards entire peoples. Hey, I mean overnight that hate is created and it takes perhaps decades for that hate to dissipate. [/INST] It takes decades and it takes uh it takes a collective effort to build institutions that divert that that hate into into other places. </s><s>[INST] One of the biggest things I thought was not part of the calculus and when the, the United States invaded Afghanistan and Iraq is the creation of hate when you when you drop a bomb. Um, even if it hits military targets, even if it kills soldiers, which in that case it didn't, there's a very large amount of civilians. What does that do to the like how many years, minutes, hours, months and years of hate do you create with a single bomb you drop and I calculate that literally in the pentagon, have a chart, how many people will hate us? How many people does it take to some signs here? How many people does it take when you have a million people that hate you? How many of them will become terrorists. How many of them uh, will do something to the nation you love and care about, which is the United States will do something that will be very costly. I feel like there was not a plot in a chart, it was more about short term effects. [/INST] Yes, it's again, it's the idea of using military force to solve political problems. Um and I think there's a squandering of of goodwill that people have around the world towards the United States. Um you know, that's a respect for uh you know, for its economy, for its consumer products and so forth. And I think that's um that's been lost a lot of that. </s><s>[INST] Do you think leaders can stop war? I have perhaps a romantic notion perhaps because I do these podcasts in person and so on, that leaders that get in a room together and can talk, they can stop war. I mean, that's the power of a leader, especially one with in an authoritarian regime that they can through camaraderie alleviate some of the emotions associated with the ego. [/INST] Yes, leaders can stop war if they get into the room when they understand um from the masses in their countries that were something that they want stopped. So </s><s>[INST] the people ultimately have a really big say [/INST] they do. You know, that it was the it was mass movements by people in the United States for the nuclear freeze um in Russia pushing for for openness that brought, for example, um Ronald Reagan and Mikhail Gorbachev to Reykjavik to sort of debate, you know, and eventually sort of put caps on, on nuclear weapons. Um you know, those two people did, you know, made choices in the room that made that possible, but they were both being pushed um uh and knew they were being pushed by by their people. </s><s>[INST] Boy, that's a tough one. It puts a lot of responsibility on the german people. For example, in both wars, we fans of history tend to conceive of history as a meeting of leaders. We think of Chamberlain would think of Churchill and the importance of them in the Second World War, I think about Hitler and Stalin and think that if certain conversations happened, that could have the war could have been avoided. You tell the story of how many times Hitler and Nazi Germany's military might was not sufficient. That could have been easily stopped and the pacifists, the people who believed Hitler were foolish enough to believe Hitler didn't act properly. And if the leaders just woke up to that idea, in fact, um Churchill was a kind of representation of that. But in your conception here, it's possible that Churchill was also a representation of the british people, even though seemingly unpopular, he that force was um they gave birth to somebody like Churchill who said, we'll never surrender, right? She'll fight on the beaches [/INST] and, you know, it's I think uh World War Two Britain is a good example of that. You know, it's a, it is clearly a, you know, a dynamic leader who has his pulse on what the people are want and demand and are willing to do. Um, and you know, it's a, it's a dynamic art of, of leading that and shaping those wands at the same time as, as knowing that you're bound by them. </s><s>[INST] Well then, if we conceive of history in this way, let me ask you about our presidents, you are taking on the impossibly difficult task of teaching a course in a, in a couple of years here in one year called the history of american presidential elections. So if the people are in part responsible for leaders, how can we explain, um, what is going on in America that we have the leaders that we do today? So the, if we think about the elections of the past several cycles, I guess I let me ask, are we a divided nation? Are we more of a divided nation? The war in the past? What do you understand about the american citizen at the beginning of this century? From the leaders we have elected? [/INST] Yes, obviously we are a divided country in our rhetoric um, in our day to day politics. Um, uh, but we are nowhere near as divided as we have been in other periods in our history, right? The most obvious of course being in the american civil war right? 100 and 50 years ago. Um, and the distinction is not just that, you know, we haven't come to blows, but that we are fundamentally one society, one economy, um and sort of, you know, deeply integrated um as a nation, both domestically And on the world stage in ways that um, you know, look nothing like the United States in 1861. Um, you know, will there be um, you know, will political rhetoric continue to be extreme of course. Um, but but but we're not as divided as people think we are? </s><s>[INST] Well, um then if you actually look throughout human history, does, does it always get so outside of the people that do the elections get as contentious as they've recently been? Um so there's a kind of perception has been very close and there's a lot of accusations and a lot of tensions, it's very heated. It's almost fueling the machine of division. Has that often been the case? [/INST] It has, we are. Um, it hasn't, it hasn't, I mean, I do think right now is, is different. Um, and there it's worth distinguishing, you know, are there deep social or economic divisions, which I don't actually think that there are versus partisanship in particular, sort of the rivalry between the two parties? And it's very clear that we are in an era of what we, what political scientists call hyper partisanship, right? And that the two parties have taken some sort of um fundamentally different positions, um, and moved further, um you know, apart from one another. Um and um you know, and that is what I think people talk about when they say our country is divided, so the country may not be divided, even if our politics are highly partisan. That is uh you know, a divergence from from other time periods in our history. </s><s>[INST] So I wonder if this kind of political partisanship is actually an illusion of division. I sometimes feel like we mostly all agree on some basic fundamentals and and the things that people allegedly disagree on are really blown out of proportion. And there's like a media machine and the politicians really want you to pick a blue side on the red side. And because of that, somehow, I mean, families break up over things, getting dinner about who they voted for. There's a really strong pressure to be the red or blue, and I wonder if that's a feature or a bug whether this is just part of the mechanism of democracy that we want to, even if there's not a real thing to be divided over, we need to construct it such that you can always have attention of idea attention of ideas in order to make progress to figure out how to progress as a nation. [/INST] I think we're figuring that out in real time. Right? On the one hand, it's it's easy to say that it's a feature of uh of a political system that has two parties, right? Um and the United States is in some ways unique, right? In um and not being a parliamentary democracy. And so in some ways it you would think that would be the feature that is causing uh partisanship and to reach these heights </s><s>[INST] that [/INST] said, </s><s>[INST] you know, we [/INST] can even see in parliamentary systems and, you know, all around the world that the same kinds of rhetoric of irreconcilable division kind of politics of emotion are proliferating around the world. Um some of that, as you say, I think, is is not as real as as it appears on on television, on social media and other formats. Um So, you know, I don't I don't know that other countries are uh that are experiencing sort of political conflict. I'm not sure that they're deeply divided either. </s><s>[INST] So I've had the fortune of being intellectually active through the George, bush versus al gore election then the Obama. And just every election since, right. And it seems like a large percentage of those elections, there's been a claim that the elections were rigged, That there is some conspiracy corruption, malevolence. On the, on the other side, I distinctly remember when Donald Trump won in 2016, a lot of people I know said that election was rigged and there's different explanations including Russian um influence. And then in 2020 I was just running in Austin along the river and somebody said like, oh a huge fan of the podcast? And they said like, what do you think this is just not right? What's happening in this country, that um the 2020 election was obviously rigged from their perspective in electing joe biden versus donald trump. Do you think there's a case to be made for and against each claim in the full context of history of our elections being rigged? [/INST] I think the american election system is fundamentally sound and reliable and I think that the evidence um you know, is clear for that, um you know, regardless of which election you're looking at in some ways, whether even, you know, you look at a presidential election or even a local, you know, county election for dogcatcher or something, right? That the um, you know, the amount of sort of time and resources and precision that go into voter registration, vote counting certification processes are crucial to democratic institutions. I think when someone says rigged, regardless of which side of the political spectrum they're coming from, um they're looking for an answer um that, you know, they're looking for that one answer for what is in fact a complex system. Right? So, you know, on the left, when they say rigged, they may be pointing to a wide range of um of ways in which they think that the system um is tilted through, you know, gerrymandering, uh you know, sort of misrepresentation through the electoral college, on the right? When people say rigged, they may be concerned, you know about about, you know, sort of voter security, about ways in which the media pre may, you know, mainstream media may control messages, um and in which, you know, in both cases, the feeling is, um, my it's articulated as my vote didn't get counted, right. Um but the deeper concern is my my vote doesn't count. You know, my voice isn't being heard. Um So, so, no, I don't think I don't think the elections are rigged. </s><s>[INST] So, let me, sort of, pushback, right? There's a comfort to the story that they're not rigged. And a lot of us like to live in comfort. So, people who articulate conspiracy theories say, sure, it's nice to be comfortable, but here's the reality. And the thing they articulate is there's incentives in close elections, which we seem to have nonstop close elections. There's so many financial interests, there's so many powerful people. Surely you can construct, not just with the media, uh, and all the ways you described both on the left and the right. The elections can be rigged, but literally, actually, in a fully illegal way, uh, manipulate the results of votes. Surely there's an incentive to do that. And I don't think that's uh that's a totally ridiculous argument, because it's like, all right. Well, um, I mean, it actually lands so the question, which is a hard question for me to ask, as ultimately as an optimist of how many malevolent people out there, and how many malevolent people are required to rig an election. So how many, what is the phase transition for a system to become from like uh corruption light to corruption? Uh too high level of corruption. Such that you could do things like rig elections, which is what happens quite a lot in many nations in um in the world even today. [/INST] So yes, there is interference in elections and there has been in American history, right? And we can go all the way back into the, you know, into the 18th century. Um you don't have to go back to, you know, Texas in the 1960s uh LBJ to to find examples of direct interference in the outcome of elections. And there are incentives to do that. Those incentives will only feel more existential as hyperpartisanship makes people think that the outcome of the elections are um you know, are are are a matter of, you know, black and white or life and death. Um and um you will see people sort of organizing sort of uh every way they can to shape elections, right? We saw this in the 18 fifties, right? When settlers, you know, pro and anti slavery sort of flooded into Kansas to try to sort of, you know, uh determine the outcome of an election and we see this in the Reconstruction period, right? When the glue Klux Klan shows up to kind of, you know, to block the doors for, for black voters in the south. Um you know that with this history is not new. It's it's there. Um I think what um what the reason why I think that the system is sound is um is not for the reason when I say I believe that the election system is fundamentally sound. Um it's not, I'm not trying to be reassuring or encourage complacency, right? I'm saying like you know, this is something that we need to do and to and to work on. So </s><s>[INST] the current electoral mechanisms are sufficiently robust even if there is corruption, even if there is rigging their robust like the force that corrects its self corrects and ensures that nobody gets out of line is much stronger than the other incentives which are like the corrupting incentives. And that's the thing. I um talked about corrupt. You know visiting Ukraine talking about corruption where a lot of people talk about corruption as being a symptom not if the system allows, creates the incentives for there to be corruption, humans will always go for corruption. That's just you have to assume that the power of the United States is that it constructed systems that prevent you from being corrupted scale at least. I mean depends what you believe. But most of us if you believe in this country, you have to you believe in the in the self correcting mechanisms of corruption. That even if that desire is in the human heart, the system resisted prevents it. That's that's your that's your current [/INST] belief, </s><s>[INST] yes, [/INST] as of today. </s><s>[INST] But [/INST] I do you know, I do think that those um you know that that will require oversight by institutions, ideally ones that are insulated as much as possible from partisan politics, which is very difficult right now. Um and it will require that the demands of the american people that they, you know, that they want these elections to be to be fair and secure. And that means, you know, that means being willing to lose them, you know, regardless of which which party you're in favor of. </s><s>[INST] So what do you think about the power of the media to create partisanship? I'm really worried that there's a huge incentive. Speaking of incentives to divide the country in the media and the politicians, I'm not sure where it originates, but it feels like it's the media maybe it's a very cynical perspective on journalism, but it seems like if we're angry and divided as evenly as possible, you're gonna maximize the number of clicks. So it's almost like the media wants to like people that are going to be the most divisive maximizing. And the worry I have is they are not beyond either feeding or if you want to be very cynical manufacturing narratives that lead that division. Like the narrative of an election being rigged because if you convinced half the populace that the election was completely rigged. That's a really good way to get a lot of clicks and and like the very cynical view is I don't know if the media machine will stop the destruction of our democracy uh in service of getting more clicks, it may destroy our entire democracy just to get more clicks just because the fire as the thing burns down will get clicks is am I putting too much blame on the media here? [/INST] The </s><s>[INST] machine of it, you're [/INST] Diagnosing the incentive structure, you know, they're depicting that with 100% accuracy. Um but I think history teaches that you might be giving the media too much sort of causal power um that you know, that the american people are smarter than the media that they consume, right. And um you know, and even even today we know that people who consume, you know, even people who consume just Fox or just MSNBC um know what they're consuming, right? Uh and you know, so I don't think that media will be the solution. Um and I certainly don't think that returning to A media structure of the mid-20th century with, you know, three news channels that all tell us one story um is that's no golden age that we're trying to get back to. Uh for sure. </s><s>[INST] Well, there's a there's a novel thing in human history which is twitter and social media and so on. So we're trying to find our footing as a nation to figure out how to think about politics, how to um yeah, how to maintain our basic freedoms are a sense of democracy, of our interaction with government and so on on this new media where medium of social media uh do you think twitter, how do you think twitter changed things? You think twitter is good for democracy? Do you think it has changed what it means to be an american citizen? [/INST] Uh </s><s>[INST] or is it just the same old media mechanism? [/INST] It has not changed what it means to be an american citizen? Um It has uh it may have changed the the day to day sound of of being, you know, the the experience of it got noisier got louder um and it got more de centered. Um I think twitter is uh it's paradoxical on the one hand it is a fundamentally democratic platform, right? You know, and um and in some ways it democratizes institutions that, you know, that had had gatekeepers and and you know, authority figures for a very long time, but on the other hand, it's it's not a democratic institution at all, it's a for profit corporation. Um and you know, it operates under under those principles. Um and so, you know, that said, it's it's you know, it's an institution of american and global life and that the people of the United States have have the authority to to regulate or reshape as as they see fit both that and other major media players. </s><s>[INST] So one of the most dramatic decisions that illustrate both sides of what you're saying is when twitter decided to ban, I think permanently the President of the United States donald trump off of twitter, Can you make the case that that was a good idea and make the case that that was a bad idea? Can you see both perspective on this? Yes, [/INST] I think um I mean the simple fact of the matter is um you know, twitter is a platform, it has rules of service, Twitter concluded that President trump had violated the terms of service and and blocked him, right, and if you have rules you have to enforce them. Um did it have um you know, did it have consequences? Um it had direct and predictable consequences um you know, that of creating uh a sense among millions of americans that twitter had taken aside in politics um or confirming their their belief that it had done so will it have unintended consequences? Um you know, this is where the historian can come in and say yes, um there's always unintended consequences and we don't know, you know, sort of what what it would mean for political figures to be excluded from from various media platforms um under sort of under under these notions right of that they had violated terms of service etcetera. So you know, so I guess we'll see as well </s><s>[INST] to me, so I'm generally against censorship, but to take twitter's perspective, it's unclear to me in terms of unintended consequences whether censoring a human being from being part of your platform is going to decrease or increase the amount of hate in the world. So there's a strong case to be made that banning somebody like donald trump increases the amount of resentment um among people and that's a very large number of people that support him or even love him or even see him as a great president, one of the greatest this country has had. And so if you completely suppress his voice, you're going to intensify the support that he has from just the regular support for another human being who ran for president to somebody that becomes an almost heroic figure for that set of people. Now the flip side is removing a person from a platform like Donald trump might lessen the megaphone of that particular person, might actually level the the democratic notion that everybody has a voice. So basically removing the loud extremes is helpful for giving the center the calm, the thoughtful voices more power. And so in that sense that teaches a lesson that don't be crazy in any one direction, don't go full, don't go lenin, don't go Hitler, don't don't like you have to stay in the middle, there's divisions in the middle, there's discussions in the middle, but stay in the middle, that's sort of the steel man, the case for for censoring, but I boy is censorship slippery slope. And also boys twitter becoming a thing that's more than just a company. It seems like it's a medium of communication that we use for um for information for for knowledge for wisdom even you know during the period of Covid we used it to gain an understanding of what the hell is going on. What should we do? What's the state of the art? Science science fundamentally transformed during the time of Covid because you have no time for the full review cycle that science usually goes through. And some of the best sources of information for me from the conspiracy theory to the best doctors with twitter uh the data the stats all that kind of stuff and that feels like like more than a more than a company and then twitter and Youtube in different places took a really strong stance on Covid which is the lazy stance in my opinion which is we're gonna listen to whatever C. D. C. Or the institutions have said but the reality is you're an institution of your own now you're kind of the press. You're like there's a there's a um yes it's a really difficult position it's a really really difficult position to take but I I wish they have stepped up and take on the full responsibility and the pain of fighting for the freedom of speech. [/INST] Yes they need uh they need to do that. But you know I'm struck by some of the things that you said ways in which, you know, twitter has the power to shape the conversation. Um and I don't think in a democratic society uh democratic policies should cede that power to to for profit companies. </s><s>[INST] Do you agree that it's possible that twitter has that power currently? Do you sense that it has? The power is that might sense as twitter is the power start wars, like tweets have the power to start wars to to yeah, to to change the direction of elections. [/INST] Maybe in the sense and the ways in which, you know, a wave has the power to wash away sand, right? Um you know, it's it's the meat, it's still the medium, right? It's not it's not in itself an actor, it's how actors use the platform, </s><s>[INST] which requires [/INST] us to scrutinize the structure of the platform and access to it. </s><s>[INST] Unfortunately, it's not, maybe it's similar to the wave, it's not just the medium, it's a it's a medium. Plus it's a medium that enables vire al Itty that benefits from my reality of engagement and that means singular voices uh can can have a disproportionate impact, like uh not even voices, singular ideas. Dramatic ideas can have a disproportionate impact. And so that actually threatens, it's almost like, I don't know what the equivalent is in nature, but it's a it's a wave that can grow exponentially because of the intensity of the the initial intensity of the wave um I don't know how to describe it as a dynamical system but it feels like it feels like there is a responsibility there not to not to accelerate voices just because you get a lot of engagement, you have to have a proportional representation of that voice. Um But you're saying that a strong democracy should be your own boss to that [/INST] a strong democracy can and should and and will be, I mean I think the other thing historian will tell you about twitter is that this too shall pass alright but but I do think you know the structures of of the of the platform of the algorithm of of this and other major players um are are eligible for scrutiny by by democratic institutions. </s><s>[INST] So in preparing to teach the course the history of American presidential elections leading up to the 2024 elections. So one of the lessons of history is this too shall pass. So don't make everything about this. Is this is going to either save or destroy our nation. That seems to be like the message of every single election. Um as I'm doing Trump hands. Um do you think Donald Trump, what do you think about the 2024 election? You think Donald Trump runs? Do you think the tension will grow? Um or was that a singular moment? Um Do you think you'll be like AOC versus trump or whoever that whatever the most maximum drama maximizing thing or will things stabilize? [/INST] I think I can I can, you know, historians don't like to predict the future, but I can predict this one that it will not be calm and and stabilized election. Um I think as of, you know, the time that we're talking in 2022 we don't there are too many, you know, sort of open questions particularly about whether joe biden will run for re election. He says he will, but you know, but the jury I think is out on that. Um It, you know, I I can't predict whether donald trump will run for for election or not. I think uh you know, we do know that that that president trump doesn't like to to start things he can't win. Um And if the polling data suggests that he's not a credible candidate, he might be reluctant to to enter the race and might might find more appealing kind of the kind of sideline kind of kingmaker role that he's been crafting since he he left the White House. Um You know, I think there are plenty of people who are uh, you know, dreaming that there's some sort of centrist candidate. Um you know, uh you know, whether it's a conservative democrat or a liberal Republican who will, you know, save us from from from all of this. Um either within the party or in a third party run? I don't think that's likely. </s><s>[INST] Why are we getting them? Why don't you think it's likely, what's the explanation that seems to be a general hunger for a person like this? [/INST] You would, but the system sorts it out right. You know, that the primary systems and the party, you know, party candidate selection systems, um you know, will favor sort of more, you know, more partisan views, right, more conservative republicans, more liberal democrats. Um as the kind of central candidates, </s><s>[INST] it seems like the system prefers mediocre executor, mediocre leaders, mediocre partisan leaders, if I take a cynical look, but maybe I'm romanticizing the leaders of the past and maybe I'm just remembering the great leaders of the past. Yeah, [/INST] I can assure you there's plenty of mediocre partisans in the 19th century </s><s>[INST] and the 20th. Um Well, let me ask you about platform ng. Um do you think donald it's the tour to question but I was torn about whether to talk to donald trump on this podcast as a historian. What would you advise? [/INST] I think, I mean, you know, this is uh this is a difficult question, right? Um for for historians who want um you know, sort of want uh to make sure that they know sort of what americans are thinking and talking about, you know, for centuries later. So one of the things that you know, at least my understanding is that when president trump was banned from twitter, his account was also deleted. Um And that is one of the most valuable sources that historians will use um to understand that the era and parts of it were sort of, you know, archived and reconstructed, but you know, but in that sense, I think that that is also a real loss to the historical record. Um I mean I think that your podcast shows you'll you'll talk to talk to anyone, so I'm here. Right? So you know, I'm not in the business of saying, you know, don't don't don't talk, don't talk. </s><s>[INST] That's one of the difficult things. When I think about Hitler, I think Hitler Stalin, I don't know if World War One quite has the same intensity of controversial leaders, but one of the sad things from a historian perspective is how few interviews Hitler has given or Stalin has given and that's such a difficult thing because it's obvious that talking to donald trump that talking tradition, ping talking to Putin is really valuable from a historical perspective to understand. But then you think about the momentary impact of such a conversation and you think, well, depending on how the conversation goes, you could steer or flame, what does it feed the flame of war or conflict or um abuses of power and things like this. And that's I think the tension between the journalist and the historian because when journalists interviewed dictators, for example, one of the things that strikes me is there often very critical of the dictator, they're they're they're like um they're basically attacking them in front of their face as opposed to trying to understand. Because what I perceive they're doing is they're signaling to uh the other journalists that they're on the right side of history kind of thing. Um but that's not very productive and it's also why the dictators and leaders often don't do those interviews. Uh it's not productive to understanding who the human being is to understand, you have to empathize. Um because few people, I think few leaders do something from a place of malevolence. I think they really do think they're doing good and not even for themselves, not even for selfish reasons. I think they're doing great for the they're doing the right thing for their country or for whoever the group they're leading and to understand that you have to and by the way, a large percent of the country often supports them, I bet if you pull legitimately pull people in North Korea, they will believe that their leader is doing the right thing for their country. Um And so to understand that you have to empathize. So that's the tension of the journalist I think and the historian because obviously the historian doesn't doesn't care. They really want they care obviously deeply, but they know that history requires deep understanding of the human being in the full context. Uh yeah, it's a tough decision to make. Well [/INST] I think it's both for journalists and historians, the challenge is not to be too close to your subject, right? Um and you know, not to be um overly influenced and used by them, right, you know, when you're talking to a living subject, which historians do, you know, um to um you know, it's it's a matter of making sure that you triangulate their story with with the rest of the record, right? Um and that may paint a different picture of of the person than um and will prevent you as a journalist or a historian from kind of, you know, just telling someone else's story. And and so and historians also have the benefit of going back, you know, 30, 40 years and finding all the other stories and figuring out, you know, uh playing two truths and a lie, you know, which parts are, you know, which parts are accurate, which are which are not. And journalists do that work in a day to day basis. But historians, um you know, we get a little more time to think about what we're doing. </s><s>[INST] Well, I I personally also think it's deeply disrespectful to the populace to people to um censor and ignore a person that's supported by a very large number of people like that. You oh, I personally feel like you owe the citizens of this country a deep empathy and understanding of the leaders they support, even if you disagree with what they say. I mean, that's the the to me, I'm much more worried about the resentment of the censorship, that it's to having a good conversation with donald trump is ultimately valuable because he I think especially in this case, I agree with you that donald trump is not a singular person. He is a he represents a set of feelings that a large number of people have and whatever those feelings are, you can try to figure out by talking to people, but also talking to the man and then seeing the interplay there. What does this really represent in this period in history, in this slice of the world? Um yeah, ultimately understanding, I think leads to compassion and love and unity, which is how this whole thing progresses. The tension between the different sides is useful to um have a good conversation but ultimately coming up with the right answer and progressing towards that answer is is how you make progress. Do you think a pure democracy can work? So we have this representative democracy with these contentious elections and so on. When we started civilization on MARS, which becomes more and more realistic, technologically we can have a more direct access to be able to vote on issues and vote for ideas. Do you think it can work? I [/INST] don't think we have to go to MArs to do it. Right. Um I think um the answer is not, you know, to flip a switch and turn on something called pure democracy. Um uh when people are not ready for it, when their incentive structures are not sort of structured for it. But you can, you know, experiment with more democratic forms of governance one after another, right? Whether it's um you know, sort of experimenting with technology to find new ways of sort of getting greater rates of participation in democracy. Um I think that we see some experiments in sort of more complicated systems of voting um that in fact might actually be more reflective of people's choices than simply picking one candidate, right, sort of ranked choice voting or run offs other kinds of things. Um You know, I think that we can think more creatively about something like participatory budgeting right, in which, you know, we put all this money into the government um and then um you know, we we you know, should as a as a people that are more democratic ways of of sort of how we spend it. And I think the most urgent in some level is a more democratic form of foreign policy making, right? The foreign policy making, decision making about the military, about foreign policy um is is very ways insulated from from popular participation in in modern american history. And I think you know, there uh technology is not the </s><s>[INST] going [/INST] to solve this. Um you know, it's a combination of technology and and human creativity, but I think, you know, I think we can start having that direction whether we get there before we get to mars I don't I don't know </s><s>[INST] what interesting lessons and thoughts if you look at the fundamentals of the history of american elections, do you hope to reveal when you try to teach the class and um how will those fundamentals be met by the, by the students that received that wisdom? So what do you think about this dance? Especially such an interesting idea. And now I hope you do go through with this kind of idea is look at the history while the next one is happening. [/INST] I think, you know, it's worth remembering, right? That the students who are typical american student who's in college right now, right, has lived their entire life after uh, the election of 2000 and Bush v gore, right? And after </s><s>[INST] 9 11, probably. [/INST] Yeah, absolutely, after all, after all of these things. Right. And um, so on the one hand, they take partisanship and contentious elections for granted. Um they don't, I think share, um, you know, sort of some vision that things were, you know, things used to be different, right? They don't remember a world that had like lots of moderate democrats and liberal republicans and um, you know, sort of running around in it. Um, but you know, so in some ways it's a way of, of looking back into the past to find other ways of, of, of organizing our politics. It's also a way of reassuring students that we have been through contentious and even sort of violent elections before, in our history. Um, and you know that people have defended the right to vote, right? People have risked their lives to vote. Um you know, I think they will, they will understand that that as well. </s><s>[INST] And maybe knowledge of history here can help deescalate the emotions you might feel about one candidate or another and uh from a place of calmness, you can more easily arrive at wisdom. [/INST] Uh that that's my hope </s><s>[INST] just as a brief aside, you brief aside. But nevertheless you wrote the book bound by war that describes a century of war in the pacific. So looking at this slice of geography and power. Uh so most crucially through the partnership between the United States and the Philippines, can you tell some aspects of the story that is often perhaps not considered when you start to look more at the geopolitics of europe and the soviet union In the United States? What how did the war in the Pacific define the 20th century? [/INST] Yeah, I came to this book bound by war from a sense that that our stories were too lopsided toward toward europe, right? That american history when viewed from the pacific specifically in the 20th century, helps us understand american power. Um in some new ways, right? Not only american projection of power into Asia, right, but also the ways in which american power affected people in Asia right either? As you know, in places like the Philippines where the United States had a colony for almost 50 years were asian americans, People who had migrated or their descendants in the United States. And those linkages between the United States and Asia, particularly the US Philippine connection I think were something that needed to be traced across the 20th century because it's a way kind of a new way of seeing american power, you know from from a different angle, you see it in in that </s><s>[INST] way. What are some aspect that define America from from when you take the perspective of the pacific, what what military conflict and the asymmetry of power there? [/INST] Right, so I start in in 1898. Um you know with the US invasion of the Philippines um it's a conquest and annexation and I think in many ways this is a defining conflict of the 20th century that's often completely overlooked. Were described I think incorrectly as merely a war with spain right? That the war in the Philippines is our our first extended overseas conflict. Our first conflict um in what would come to be called the developing world or third world. It's a form of of counterinsurgency. Um you know this is the US Army sort of learning lessons that are then repeated again in the Second World War in Korea Vietnam and and even after 9 11 </s><s>[INST] is the Philippines or friends or enemies in this history. [/INST] Well that's the interesting part. Right is that the book focuses in particular on Filipinos who fight with the americans who fought, you know, sort of in the US army and navy over the course of the 20th century. And they are in a fundamentally ironic position, right? They are they are from the Philippines and they're fighting for the United States, which is the colonial power occupying their country. Um, and I think that that irony persists right. So if you look at sort of polling data where they ask people all around the world, you know, you know, do you think positively or negatively about the United States? Um, that the highest responses are from the Philippines. Right. Filipinos view the United States more favorably than people from any other country in the world, including America. Right? That that they're more think more favorably of americans than americans do. And so, you know, sort of unpacking that irony is is part of what I'm trying to get out in the book. </s><s>[INST] What was the People Power revolution and what lessons can we learn from it? You kind of assign an important, a large value to it in terms of what we can learn for the, the american project. [/INST] Yeah, so in 1986, the president of the Philippines Ferdinand Marcos is overthrown by a popular revolution known as people power um in the wake of a contested and probably almost certainly rigged election. Um that that sort of, you know, kind of confirms his his his rule when that is over overturned through sort of mass movements in the Philippines. It's also sort of confirmed in many ways by the reluctance of the United States to intervene to prop up a Cold War ally, Ferdinand Marcos had supported American policy throughout his administration. The Reagan administration, Ronald Reagan's president at the time basically chooses not to support him. That's a personally wrenching decision for for Reagan himself, but it he's being shaped in many ways by the emerging voices of neoconservative political uh foreign policy voices in particular, paul Wolfowitz and the State Department and others who see Sort of movements for democracy and democratization that then kind of take fire in the late 20th century in Latin America in South Korea in Eastern Europe. Um and, you know, all around the world until it hits the wall in in Tiananmen Square in June 1989. </s><s>[INST] What what's that wall? [/INST] What's </s><s>[INST] the what what's the what what do you mean? But it hits the wall. [/INST] So there are, you know, there are global movements for for democratization for for opening up, you know, throughout the world, starting in the 19 eighties. Um And you know, obviously they continue in eastern europe with the fall of the Berlin wall in 1989. Um you know, I say it hits the wall in in in china in with the protests in Tiananmen Square And that are that are blocked. Um and that are crushed and I think represent a real sort of turning point in the history of, of democratic institutions on a global scale in the late 20th century. </s><s>[INST] So there's some places where the fight for freedom will work in some places not. And that's the kind of Lesson from the 20th to take forward to the 21st century. [/INST] Uh, no, I think the lesson is, is maybe one that, that, you know, we talked about earlier that there's this dynamic dance between between leaders, whether totalitarian leaders or leaders of democratic movements and the people that they're leading. Um, and some, you know, sometimes it works and sometimes sometimes it doesn't </s><s>[INST] let me ask a big ridiculous question because we talked about sort of presidential elections. Um, now this is objectively definitively, you have to answer one person who's the greatest president in american history. Oh, that's easy. [/INST] Abraham Lincoln, </s><s>[INST] is that easy? Not in George Washington, [/INST] you know, Washington had his had the statesman qualities. He understood his power as, as uh, as the first president </s><s>[INST] also relinquished power. [/INST] He was willing to relinquish power. He, you know, uh, but but Lincoln has the combination of personal leadership, um, a fundamental moral character and, um, and just the ability to kind of, to fight the fight of politics, to play the game of it, to get where he's going to play the short game and the long game, um, to kind of, you know, make to, uh, you know, to work with his enemies to block them when he had to. Um and you know, I mean, he gets the United States through the civil war, so you gotta give him some credit for that </s><s>[INST] and it's pretty good at making speeches. [/INST] Uh you know, obviously it helps that he's a remarkable speaker and able to convey those kinds of visions, but you know, but but he is first and foremost a politician. Um and probably the best one we have both </s><s>[INST] of getting elected and ruling [/INST] in some ways better better at the doing than at the getting elected right. Um you know, that he uh you know, the election of 18 60 is a, it's just a hot mess. Um you know, that could have worked out many different ways and even the election of 18 60 for, you know, when we have a presidential election in the middle of a civil war. Um it was not a foregone conclusion that Lincoln would be reelected. Um So you know, both times he sort of um you know, he's not a master campaigner by, by any means, but he was a master politician as a, as a governor. </s><s>[INST] Do we have leaders like that today? Is that, so one perspective is like leaders aren't, ain't what they used to be. And another perspective is what we always romanticize stuff that happens in the past. We forget the flaws and remember the great moments. [/INST] Yeah, both of those things are true right? On the one hand, you know, we don't uh we are not surrounded by people of, of Lincoln's caliber right now, that </s><s>[INST] feels like the case. [/INST] Um, and I think that I think we can say that with some certainty, but you know, I always like to point to President Harry Truman who left office with, you know, some truly abysmal uh presidential ratings um was dismissed as a, throughout his presidency as a, you know, as a as unqualified as not knowing what he was doing etcetera. And then you know, turns out um with hindsight we know that he was better at the job than anyone understood, better at getting elected, right. You remember that sign Dewey defeats Truman right? He showed them right and better, better at holding power and better at sort of um you know kind of building the kind of institutions that long after he was gone, um demonstrated that he, he won the long game </s><s>[INST] and some of that is the victors do right the story. And I asked myself very much how will history remember Vladimir Zelensky, it's not obvious and how will history remember Putin that too is not obvious um because it depends on how the role the geopolitics, the how the nations, how the history of these nations unravel unfold rather. So it's very interesting to think about and the same is true for donald trump joe biden Obama George Bush, Bill clinton and so on. I think it's probably unanswerable question of which of the presidents will be remembered as a great president from this time. You can make all kinds of cases for all kinds of people and they do, but it's unclear. It's fascinating to think about when the robots finally take over what which of the humans they will appreciate the most. Let me ask for advice. Do you have um advice for for young folks as they uh because you mentioned the folks you're teaching, they don't even they don't know what it's like to have waited on the internet for the for the thing to load up for every single web pages that suffering. They don't know what it's like to not have the internet and have a dial phone that goes. And then the joy of getting angry at somebody and hanging up with a physical phone. They don't, they don't know any of that. Uh So for those young folks that look at the contention election, contentious elections, that look at our contentious world, our divided world, what advice would you give them of how to have a career? They can be proud of, let's say they're in college or in high school and how to have a life they can be [/INST] proud of. Oh man, that's a big question. Um yeah, I've never given a graduation speech. </s><s>[INST] This is like warm up. Let's look for like raw materials before you write it [/INST] if I did. Um, I think um, I think I would advise students that history teaches that you should be more optimistic than, um, than your current surroundings suggest, right? And I think it would be very easy as a young person today to think, um, there's, there's nothing I can do about this politics. There's nothing I can say to this person on the other side of the aisle. There's nothing I can do about, you know, the planet, um, etcetera, and just sort of give up. Um, and I think history teaches that, you know, uh, you know, we don't know who the winners and losers are in the long run, but, but we know that the people who give up are always the losers, right? So </s><s>[INST] don't give in to cynicism or apathy. [/INST] Yeah. </s><s>[INST] Optimism paves the way. [/INST] Yeah. Because human beings are deeply resilient and creative even under far more difficult circumstances than, um, you know, that we face right now. </s><s>[INST] Let me ask a question that you don't even need to, that you wouldn't even dare covering your graduation, uh, commencement speech. What's the meaning of life? Why are we here? This whole project that history studies and analyzes as if as if there's a point to the whole thing. What is the point? All the wars, all the presidents, all the struggles to discover what it means to be human or reach for a higher ideal. Why? Why do you think we're here. [/INST] I think this is where there is often a handoff from the historian, um, to the clergy, Uh, you know, who, but in the end. Um, uh it's less of, there's less distance between the two than you think, right? That, you know, if you think about some of the kind of uh answers to that question, what is the meaning of life that are given from religious traditions? Um often they have a fundamentally historical core, right? It's about, you know, unifying the past and the present in some other, you know, non earthly um sort of dimension. Um, and you know, so I think there is that, I think even for people who who don't have religious belief, and there's a way in which history is about the shared, shared human condition. Um, and I think historians aspire to telling all of that story, right? Um you know, we we drill down on the, on the miseries of of war and depressions and and so forth. But but you know, the story is not complete without, you know, blueberries and butterflies and and and and all the rest that that go with it. </s><s>[INST] So, both the humbling and the inspiring aspect that you get by looking back at human history that we're in this together Christopher. This is a huge honest, is amazing conversation. Thank you for taking us back to a war that not often discussed, but in many ways defined the 20 the 20th century and in the century we are in today, which is the first World War, the war that was supposed to end all wars but instead defined the future wars and defines our struggle to try to avoid World War Three. So it's a huge honor. You would talk with me today. This is amazing. Thank you so much. [/INST] Thank you. </s><s>[INST] Thanks for listening to this conversation with Christopher Capa Zola. To support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Woodrow Wilson in 1917 about World War One that haunted the rest of the 20th century. This is a war to end all wars, Jorge Santana. A. Spanish American philosopher responded to this quote in 1922 by saying only the dead have seen the end of war. Thank you for listening. I hope to see you next time. [/INST] </s>
<s>[INST] Yeah, it's funny, depending on the technology, people are a little bit Too terrified of certain technologies, like artificial intelligence is one my sense is that the things that they're afraid of aren't the things that are likely going to happen in terms of negative things is probably impossible to predict exactly the unintended negative consequences. But what's also interesting is for ai as an example, not people don't think enough about the positive things. I mean, the same is true of social media is very popular now for some reason to talk about all the negative effects of social media, we've immediately forgotten how incredible it is to connect across the world. There's a there's a deep loneliness within all of us. We long to connect and social media at least in part enables that even in its current state and all the negative things we see with social media currently are also in part just revealing the basics of human nature didn't make us horses just is bringing it to the surface and step one of solving a problem is bringing it to the surface. The fact that we are devices there's a division, the fact that there were easily angered and upset and all of that the witch hunts, all those kinds of things that's human nature and it just reveals that allowing us to now work on it therapy. And so that's another example of the technology that's just we're not considering the positive effects now and in the future. Enough of I have to ask about um there's a million things I can ask about virtual reality. I gotta ask you ah you thought about virtual reality? Mixed reality. Uh Quite a bit. What are the uh interesting trajectories you see for the proliferation of virtual reality or mixed reality? Yeah. [/INST] So I was I was a magically for what five years um </s><s>[INST] with the best title of all time. [/INST] Thanks Chief Chief futurist. Yeah. Yeah. And so I sort of had a little squad of people in in Seattle doing what you might call content R. And D. So we're trying to make content for a are. But um because it's such a new medium uh there's it's more of an engineering R. And D. Project almost than a than a creative project. So it was fascinating to see um everything that goes into making uh an A. R. System that runs um So a r an ar device, if it's really going to do a R needs to be running Slam in real time. And that alone is a </s><s>[INST] big, so for people who don't know, first of all, virtual reality is creating almost fully artificial world and putting you inside it augmented reality A. R. It's taken the real world and putting top on top putting stuff on top of that real world. And when you say Slam, that means in real time, the device needs to be able to since accurately detect everything about that world sufficiently To be able to reconstruct the three D uh structure of it. So you can put stuff on top of it and doing that in real time, presumably not just real time, but in the way that creates a pleasant experience for the human perception system is uh yeah, that's a that's an engineering project, [/INST] right, well said, and it's just one of the things that the system has to do, it's also tracking your eyes so it knows what you're looking at, how far away what you're looking at is um it's uh um it's performing all those functions. Um and it's got to uh keep doing that without, you know, burning up the CPU or or depleting the battery uh unreasonably fast and that's that's just table stakes. It's just the basic functions of the the operating system and then any content that you want to add has to sit on top of that, it's got to be rendered by the optics at a sufficiently low latency, that um it looks real and you don't get sick, so it's an amazing thing and um you know, magically shipped uh device that Can do that in 2019. Um and they're about to ship the ml two. Um but I don't know any more about that than anyone else, because I don't work there anymore. Um </s><s>[INST] What does it still, in to some degree, boil down to a killer app? A content question like you said, it's kind of a wide open space, nobody knows exactly what's going to be the compelling thing, so it doesn't a super compelling experience of some sort alleviate some of the need for engineering perfection. [/INST] Well, there's a base layer of engineering that you have to have no matter what. Um but you're certainly right that people, like in the early days of video games put up with kind of low frame rate and what we would now call crappy graphics because they were having so much fun playing Doom or or whatever, </s><s>[INST] even Tetris. [/INST] Yeah, yeah, so um so for sure that's true. And so um you know, uh I was uh working on consumer facing content, um there was a great team in Wellington New Zealand that they made a game called dr droid brutes invaders, that um that uh realized the potential of VR gaming in a way that I don't think anything else has uh before since. Um and um, so that was definitely the strategy um until uh, April 2020, which is when the company decided to pivot to commercial industrial applications instead. Um so, and you know, I haven't seen their their their financial projections, but I assume they had good reasons for for making that strategic decision. Um it just means that it's no longer uh necessarily targeted at just end users who want to play a game or or be entertained. But it's, </s>
<s>[INST] expert and probably everyone [/INST] has all these ideas and they're already figured out. But when I was </s><s>[INST] an expert in anything, okay go ahead. But when I'm [/INST] talking about yeah but I like it's just like I think some kind of pruning pruning but it's a </s><s>[INST] tricky thing because [/INST] because if there's too much of a of a focus on </s><s>[INST] youth culture [/INST] then you don't have the wisdom. So I feel like we're in a tricky we're in a tricky moment right now in society where it's like we've really perfected living for a long time. So there's all these all these really like old people who are </s><s>[INST] like [/INST] really voting against the well being of the young people, </s><s>[INST] you know? And like like it's [/INST] like there shouldn't be all </s><s>[INST] this student debt and [/INST] we need like healthcare like universal health care and like like just voting against </s><s>[INST] like best [/INST] interests but then you have all these young people that don't have the wisdom that are like like yeah we need </s><s>[INST] communism and stuff [/INST] and it's just like like </s><s>[INST] literally I got [/INST] canceled at one point for I ironically used a Stalin quote in my high school yearbook but it was actually like a </s><s>[INST] a diss [/INST] against my high school. Yeah and and people were like you used to be a stalinist and now you're a class traitor and it's like it's </s><s>[INST] like oh man just like [/INST] please google Stalin please google Stalin </s><s>[INST] like you're [/INST] ignoring the lessons of history. Yes, </s><s>[INST] it's and it's like we're in [/INST] this really weird middle ground where it's like </s><s>[INST] we are not [/INST] finding the happy medium between mr wisdom and fresh ideas and they're fighting each other. </s><s>[INST] And it's like [/INST] like </s><s>[INST] really [/INST] like what we need is like like the fresh ideas and the wisdom to be like collaborating and it's like what the fighting in a way is the </s><s>[INST] searching for the happy [/INST] medium and in a way maybe we are finding the happy medium that maybe that's what the happy medium looks like. And for Ai </s><s>[INST] systems there has to be it's you [/INST] know, you have reinforcement learning, you have the dance </s><s>[INST] between exploration, [/INST] exploitation sort of </s><s>[INST] doing crazy stuff [/INST] to see if there's something better than what </s><s>[INST] you think is the [/INST] optimal and then doing the optimal thing and dancing back and forth from that you would um </s><s>[INST] Stuart russell. [/INST] And if you know that is um </s><s>[INST] ai guy [/INST] with um things about sort of cut of control, super intelligent ai </s><s>[INST] systems and [/INST] his ideas that we should inject uncertainty and sort of humility into ai systems that they never as they get </s><s>[INST] wiser and wiser and wiser and more [/INST] intelligent, They're never </s><s>[INST] really sure they always doubt [/INST] themselves. </s><s>[INST] And in [/INST] some sense when you think of young people that's a </s><s>[INST] mechanism for doubt. [/INST] It's like it's how </s><s>[INST] society doubts whether the thing it has [/INST] converged towards is the right answer so that the voices of the </s><s>[INST] young people [/INST] is a </s><s>[INST] society asking itself the [/INST] question the way I've been doing stuff for the </s><s>[INST] Past 50 years, maybe it's the wrong way [/INST] And so you can have all of that within one ai system. I </s><s>[INST] also think though that we [/INST] need to I mean actually that's actually really interesting and </s><s>[INST] really cool, [/INST] but </s><s>[INST] I also think there's a [/INST] fine balance of, I think we may be also overvalue the idea that the old systems are always bad and I think there are things that we are perfecting and we might be accidentally overthrowing </s><s>[INST] things that we actually [/INST] have gotten to a good point </s><s>[INST] just because [/INST] we are valuing, we value disruption so much and we value fighting against the generations before us so </s><s>[INST] much [/INST] that like there's also an aspect of like sometimes we're taking two steps forward one step back because okay, maybe we kind of did solve this thing and now we're like sucking it up, you know? And and and so I think there's like a middle ground there were in search of that happy </s><s>[INST] medium. Let me ask you a [/INST] bunch of </s><s>[INST] crazy questions. [/INST] Okay, uh you can </s><s>[INST] answer in a short way, [/INST] in a long way, what's the scariest thing </s><s>[INST] you've ever [/INST] done? These questions are going to be ridiculous. Something, something tiny or something big </s><s>[INST] skydiving or [/INST] um </s><s>[INST] touring [/INST] your first </s><s>[INST] record [/INST] going on this podcast, I've had two crazy </s><s>[INST] brushes like really scary [/INST] brushes with death where I randomly got away unscathed. </s><s>[INST] I don't know if I should talk [/INST] about those on </s><s>[INST] here, but like I [/INST] think I think I might be the luckiest person alive though. </s><s>[INST] Like, this might be [/INST] too dark for a podcast though. </s><s>[INST] I feel like, I don't know if this is like good [/INST] content for a podcast </s><s>[INST] content. It might hijack. [/INST] Here's a Safer one. </s><s>[INST] I'm having a baby. [/INST] It </s><s>[INST] really scared me before the birth [/INST] process surgery, </s><s>[INST] surgery. Like, [/INST] like, just having </s><s>[INST] just having a baby, [/INST] just like the medical </s><s>[INST] aspect of it, not the responsibility. [/INST] Are you </s><s>[INST] ready for the responsibility of? [/INST] Did you, </s><s>[INST] were you ready to be a mother? All the, all [/INST] the beautiful things that comes </s><s>[INST] with motherhood that you were talking [/INST] about, all the </s><s>[INST] changes and all that? Were you ready for that [/INST] or you did you feel ready for </s><s>[INST] That? No, I think it took about nine [/INST] months to start getting ready for it and I'm still getting </s><s>[INST] more ready for it [/INST] because now </s><s>[INST] you keep, you [/INST] keep realizing more things as </s><s>[INST] they start getting [/INST] as the consciousness </s><s>[INST] grows and stuff. [/INST] You didn't notice with the first one, now that you've seen the first one </s><s>[INST] older, you're noticing it more like [/INST] the sort of like, existential </s><s>[INST] horror of coming into [/INST] consciousness with </s><s>[INST] uh baby [/INST] y or baby sailor mars </s><s>[INST] or whatever. She has, like, so many names at this point, that [/INST] it's um we really </s><s>[INST] Need to probably settle on one. [/INST] if you could be someone else for a </s>
<s>[INST] Um, [/INST] so at some point, you know, he never knew a lot of openings in chess, but I taught him, I taught him a couple of openings as black. Um it's the, It's the special Sicilian that I've played a lot myself also. Um during the World Championship in 2018, I won a bunch of games in 2019 as well, so that's one opening and also taught him as black to play the, in defense. Um, and then so the in defense goes like it goes like this, um, it's characterized by, by this bishop move. Um, and so he would play those openings pretty pretty exclusively and as black and the tournaments that it did play and also the special of Sicilian is like, that's the only two of my sisters play have played a bunch of chess tournaments as well and that's the only opening they know as well. So my, my family's reporter is very narrow so so this is the, this is the system, black goes here and then very often white takes a pawn and black takes the pawn. Um, so at some point I was watching one of my, my father's online blitz game this game and as white, he played this, this, so this is called the car can defense, he took upon. Um, it was taken back then he went with a night, um, its opponent one here and then you play the bishop here. So I've never seen this opening before. I was like, wow, how on earth did he come up with that and he said no, I just played the with the different colors because if the night was here it would be the same position. I was like, I never, I was like how am I like one of the best 20 players in the world and I've never thought about that. So I actually started playing, I started playing this line uh as white with pretty decent results and results and it actually became kind of popular and everybody who asked about the line, like I would always tell them, yeah, that's the Henry Carlson, </s><s>[INST] I [/INST] wouldn't necessarily explain why it was called that I would just always call it that. So I really hope at this point at some point this line will be uh </s><s>[INST] will find [/INST] its rightful name </s><s>[INST] in. Yeah, finds its way into the history books. Can you, what, what, what did you learn about life from your dad? What what role has your dad played in your life? [/INST] He's taught me a lot of things, but most of all, as long as you win a chess, then everything else is fine. Um I think my, especially my father, but my parents in general, they, they always wanted me to get a good education and find a job and so on. Um even though my father loves chest and he wanted me to play chess. I don't think he had any plans for me to be professional. I think things changed at some point, Like </s><s>[INST] I [/INST] was less and less interested in school and for a long time we were kind of going back and forth fighting about that, especially my father, but also my mother a little bit, it was at times a little bit difficult. </s><s>[INST] Yeah, [/INST] they sort of wanted me to do more school to have more options and then I think at some point they just gave up. But I think that sort of coincided when I was actually starting to make real money of tournaments and after that, you know, everything's been sort of easy and like in terms of the family, like they've never </s><s>[INST] put [/INST] any pressure on me or they've never put any demands on me. Um, they're just, yeah minus has to focus on chess. That's that, that's um, that's it. Like I think they taught me in general to be curious about the world and to get a decent general education, not necessarily from, from school, but like just knowing um, about the world around you and knowing history and being, you know, just being interested in society. I think in that sense they've done well </s><s>[INST] and he's been with you throughout your chest career. I mean there's something to be said about just family support and love that you have that, that, you know, this world is a lonely place. It's good to have people around you, they're like uh they got your back kind of you [/INST] know uh basically shape but I think to some extent all the people you surround yourself with they can help you a lot. It's the only family that only has their own interests at heart. And so for that reason like my father is like the only one that's been like constantly in the team that and that has always been around and it's it's for that reason that I know he has my back no matter what </s><s>[INST] now there's a cliche question here but let's try to actually get to some deep truth perhaps. But people who don't know much about chess seem to like to use chess as a metaphor for everything in life. But there is some aspect to the decision making to the kind of reason and involved in chess that's transferable to other things. Can you can you speak to that in your in your own life and in general the kind of reasoning involved with chess, how much is that this transfer to life out there? [/INST] It just helps you make decisions of </s><s>[INST] all of all kinds. [/INST] That would be my main takeaway that you learn to make informed guesses in a limited amount of time. </s>
<s>[INST] But I really want to. [/INST] It's one of the most amazing things you can do. You know, you come out on the other side and all your stress worries, they're just gone. And you have so much productivity and clarity. </s><s>[INST] If you combine that with daily naps, that's the way to go. Yeah, I'm a huge fan of naps. So what about the social media stuff and like you doing the live streams? Do you ever dread those? Do you, are you energized by those? So because you're exceptionally good at communicating all the different kinds of ideas and being very transparent with the community, [/INST] about those kinds of things, I really enjoy the live streams. It's fun, it's never been a chore because it's for them. It's a chance for people in the community who've been loyal and they really love it to actually just be there, ask some questions. And I try to make it as entertaining as possible. And you have your trolls and you have your love and it's actually nice to have a mixture of the two because sometimes you can beat down trolls just for fun, you know, that kind of stuff. And it's grown to a cult following. I think there's like 40, 50,000 people. and it's almost like Fight Club in a certain respect. So I was in Vancouver years ago and I was at Air Canada checking in, just about to fly back to Colorado and it's getting this weird vibe from the guy that was checking me in. And then right after he takes my bag, he kind of leans over to me, he's like, I love Ada. And I was like, really? He's like, yeah, I watch your live streams. And then I was flying into London. I was at London Heathrow Airport and the passport control guy was there and I was just about to take my passport out and he says, welcome to London, Mr. Hoskinson. And I was in Catalino and I was like, really? He's like, yeah. I was like, oh God, am I going to jail in London? Why does the border patrol guy know who I am? This is a bad deal for me. And it turned out he watched my live streams. And so there's a lot of that and that's so much fun. In fact, here in Austin, as a Mexican restaurant just down close to this place and while eating there, two different people recognize me. I took a picture with one of them. </s><s>[INST] And again, they watch the live streams. So that's- Well, if there's anything like Fight Club, you have to wonder if some of those people [/INST] or all of them are just figments of your imagination. Right, I would, I don't have an answer for that. </s><s>[INST] I could be a figment of your imagination. [/INST] It just proves that you can see it. Yeah, but honestly, if I was capable of that level of delusion, </s><s>[INST] why the hell don't I look like Brad Pitt? Good point. Okay, so on this topic, let me ask you about mushrooms. You're interested in mushrooms, growing mushrooms. I believe you are also interested in the mind expanding capabilities of psychedelics. At least you mentioned kind of the interesting place where your interest in non-psychadelic mushrooms might go. Can you explain the nature of your interest in mushrooms? Is it personal? Is it business? [/INST] Is it both? So that's a little bit of everything. It's just an under explored area of science and botany that ought to be explored because there's so much cool, interesting stuff there. Mushrooms do so much. Like they have these things called cordyceps and they are like a zombie fungus that infects insects, takes them over and then it will have them kind of get to other insects and then burst out of their head like an alien and spray spores on them and repeat the process. I mean, they even made a damn game about this, The Last of Us or something like that. And that's a real thing. Like you can Google it and see like these dead ants with these fungal stabs coming out of them. It's like, holy God, this is crazy. And in the same topic, you go all the way to Lion's Mane and it could actually help treat Alzheimer's and treat depression and Parkinson's and regrow nerves and so forth. Other things that they've shown some effectiveness against COVID, it's just so crazy the diversity in the mushroom kingdom of the medicinal applications, the pesticide applications. You can use it a lot to kind of save hay and trees. There's a lot of things you can do to combat all kinds of invasive species. And it's true, there's a lot of cool stuff with psychedelic mushrooms and there's a great book from Michael Pollan, How to Change Your Mind, where he was really the first journalist a long time to go and Roland Chris's work his way through the Johns Hopkins studies. But the long and short for me, when I read that book, like, okay, mine expansion is great, but look at the effectiveness of psychedelics, psilocybin mushrooms with SSRIs, selective serotonin read uptake inhibitors for the treatment of depression. They showed in the Johns Hopkins studies that they're equal or better in effectiveness in many cases. Yes, fascinating. For the treatment of depression, then a drug that you have to take forever. And this is just one or two treatments and then you desist from it. That's a miracle because there's so many people suffer from severe depression and it's a lifetime ailment. And the fact that we have something in the toolbox that we've under explored is a very powerful thing. The other thing was end of life issues. A lot of people get cancer. I've lost people in the family from cancer. And it's so hard those last two, three months, because they kind of have this, they're in horrific pain. They're trying to find meaning and why is this happening to me? And if you can just give them a substance that on the other side of it, there's a good chance they can come to peace with everything and die with a lot more dignity and happiness, that alone justifies an enormous amount of study. And the fact that these things are super cheap and they grow pretty much anywhere, it's pretty cool. Now on the commercial side, you can make a lot of money for mushrooms. And I'm working with a company called Farmbox Foods and it's one of the, they do both vertical hydroparmic farming. They also do mushroom and they put these amazing labs and shipping containers that are kind of like controlled environments. And you grow 400 pounds of gourmet mushrooms a single week off of that. And your margins can be up to 30% per year. If you're just selling them for food consumption, if you're doing supplements, they can be even higher than that. So it just kind of made sense from a diversification of assets to say, hey, let's do some stuff in hydroponics and aquaponics and in mushrooms. But the more I do and the more I learn that community, just the cooler that community is. Like I went to this beautiful mushroom festival in Cape Springs down in Georgia. And I met this guy named Bill Yule and he's just looks like a druid. You know, just like he lives in a tree and he opens up the tree and goes out and everything. And I was like, Bill, what do you do? So I go and I try to study beetles and bull eats and a very particular type of beetle. And they mate in the most crazy way is like this beetle will fuse on top of another beetle and they'll vibrate. And if they make the right harmony, she'll mate with him otherwise they'll kick her off. And you can only make the harmony while you're on a specific type of bull eat mushroom. If it's anywhere else, the harmony does it. It's like, who the fuck does this? It's like 20 years, 30 years, just thinking about goddamn beetles and bull eat mushrooms. But that's that community and they're the happiest people you'll ever meet. And they're just so much fun to talk to. And there's just so much lore there that's not discovered. The other thing is there's a ton of undiscovered mushrooms. So, you know, you go to my ranch up in Wyoming, go out that national forest next to it, you'll probably discover six or seven new species just doing some gene sequencing and things like that. So there's like a gold rush for new things to discover to treat all kinds of things. So love mushrooms, love that community. I think there's a lot of wonderful medicinal properties and everybody there is just a lot of fun to hang out with. The other passion is aquaponics and hydroponics. And I got a lot more serious after COVID. I go to the supermarket, all the store shelves are barren. I say, guys, can you imagine if like we had a real big thing what this would be like? We need to have domestic food production. We need to have resilience at the community level. So let's go build a 40, $50 million aquaponics facility next to every major city. So at least you have some local production of food and people won't starve to death. Otherwise it's very bad. And again, the margins are phenomenal there, 20%, 30% if you actually do it right and alternate your crops properly and so forth. And you create a lot of high paying jobs with it as well. </s>
<s>[INST] Seven years after Daniel's death, he wrote an article at the Wall Street Journal titled Daniel Pearl in the normalization of evil. What was your message? A message back then? And how did it change today? Over over the years? [/INST] I I lost </s><s>[INST] what was the message? [/INST] The message was that we are not treating terrorism, Is it taboo? We are treating it as a bargaining device. That is accepted. People have grievance and they go and bomb more restaurants. Okay, it's normal. Look, you're even not not surprised when I tell you that 20 years ago. So what for grievance? You go and blow restaurant. Yeah. Today is becoming normalized the finalization of evil. And we have created that to ourselves by normalizing by by making it part of Mhm. Mhm. Political life. It's a political debate. Every terrorists yesterday become the freedom fighter today and tomorrow is becoming terroristic. It is switch double thing. </s><s>[INST] So we should call out evil when there's evil [/INST] if we don't want to be part of it, becoming Yeah, if we want to separate good from evil? That's one of the first things that what would the in the garden of Eden? Remember the first thing that God tells him he was, hey, you want some knowledge. Here is the tree of good and evil. </s><s>[INST] So this evil touched your life personally. Does your heart have anger, sadness or is it hope? [/INST] Okay, I see some beautiful people coming from Pakistan, I see beautiful people everywhere, but I see horrible propagation of evil in this country too. It shows you how populistic slogans can catch the mind of the best intellectuals </s><s>[INST] today is father's Day. [/INST] I didn't know that. Yeah. </s><s>[INST] What's uh what's, what's a fond memory you have of Daniel. [/INST] Oh many good name with uh he means he was my mentor. What do you? He had sense of balance that I didn't have. Yeah, he saw the beauty in every person. He was not as emotional as I am more looking at things in perspective. He really likes every person. He really grew up with the idea that for now is reason for curiosity, not for fear. At one time we went in Berkeley and homeless came out from some dark alley and he said, hey man, can you spare a dime? I retreated back, you know two ft back and then I just hugged him and say, here's a dime and judge yourself maybe you want some um money to take a bath or whatever. Where did you get it? Not for me. </s><s>[INST] Do you have advice for young minds today dreaming about creating as you have dreamt creating intelligence systems? What is the best way to arrive at new breakthrough ideas and carry them through the fire of criticism and and past conventional ideas. [/INST] Ask your questions freely. Your questions are never done and solved in your own way and don't take no for an answer. Look, if they are really dumb, you will find them quickly by trying narrow to see that they're not leading any place but follow them and try to understand things your way. That is my advice. I don't know if it's going to help anyone that's brilliant. There is a lot of uh it's inertia in science in academia. It is slowing down science. </s><s>[INST] Yeah, those two words your way. That's a powerful thing. It's against inertia potentially against [/INST] against your professor Professor. I wrote the book of why in order to democratize common sense in order to instill rebellious spirits in students. So they wouldn't wait for until the professor get things right. Mhm. </s><s>[INST] Uh He wrote the manifesto of the rebellion against the professor [/INST] Professor. Yes. </s><s>[INST] So looking back at your life of research, what ideas do you hope ripple through the next many decades? What what do you hope your legacy will be? [/INST] I already have tombstone </s><s>[INST] carved? [/INST] Ah boy, fundamental The fundamental law of counterfactual, that's what it's a simple equation with a counterfactual in terms of a model surgery. That's it. Because everything follows from that. If you get that all of us, I can die in peace and my student can derive all my knowledge. My mother mother called means </s><s>[INST] the rest follows. Yeah dad, thank you so much for talking today. I really appreciate [/INST] it. Thank you for being so attentive and instigating. </s><s>[INST] We did it really. The coffee helped. Thanks for listening to this conversation with judea Pearl and thank you to our presenting sponsor. Cash up, 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 learn and to dream of engineering our future. If you enjoy this podcast, subscribe on Youtube, get five stars on apple podcast support on Patreon are simply connect with me on twitter and now let me leave you with some words of wisdom from judea Pearl. You cannot answer a question that you cannot ask and you cannot ask a question. You have no words for thank you for listening and hope to see you next time [/INST] </s>
<s>[INST] I you know, I I've had that line of thinking and you know from M. I. T. I said, well surely whatever you folks are busy about yelling at each other for is a thing at Harvard and Yale. It's not going to, [/INST] yeah, of course people in the stem subjects thought is not coming for us. It can't come to us and bang, </s><s>[INST] well it's, you know, it hasn't quite been bang [/INST] engineering is that it's more safe than others. </s><s>[INST] Yeah. So not so let's draw a line now between engineering and science. So I think engineering is uh sitting in a castle and the tallest tower with my pinky out drinking my martinis thing. Surely the peasants below with their biology and their humanities, we'll figure it all out. No, I'm just kidding. There's no there's no pinky out. I drink vodka and and I hang with the peasants. Okay, where is this? This metaphor has gone too far? Uh Can you explain to this engineer what critical race theory is? Is it a term that's define herbal, is their tradition, their history? What is good about it? What is bad about [/INST] It? Is it is a tradition, is a history of the school of thought. It started in the law roughly in the 1970s and some of the American Academy, it spilled out. It always aimed to be an activist philosophy. People deny that now. But as I cited in the war in the west and the foundational texts say as much this isn't, this is an activist academic study. We're not just looking at at the law. We seek to change the law and it's built out into all of the other disciplines. I think there's a reason for that by the way. Which is it happened at the time that the humanities and others in America were increasingly weak and didn't know what to do. And they needed more games to play on new games to play. The </s><s>[INST] psychologist got bored. [/INST] Yeah, I mean that well, they needed tenure. They needed, they needed something to do. And I mean it's not an original observation, plenty of people have made this. But I mean Neil Ferguson said that some time ago, for instance, that in the last 50 years in American academia, certainly in humanities departments, when some, when somebody dies out is a great scholar and something that's just not replaced by somebody of equal stature? They were placed by somebody who does theory or critical race theory. They're replaced by somebody who does the modern games, somebody dies out who's a great historian of say, I don't know, it's the one that's on my mind. Um Russian history or Russian literature and they're not replaced by a similar um scholar </s><s>[INST] is in his observation in yours. Is this is this a recent development [/INST] which happened the last few decades? For sure. And it sped up </s><s>[INST] is because we've gotten to the bottom of some of the biggest questions of history. [/INST] No, it's because we're willing to forget the big questions </s><s>[INST] because it's more fun to big questions are no, [/INST] partly partly. No, it's just stress that partners and this is in the west, but partly is a result of the hyper specialization in academia. Um you know, if you if you said you'd like to write your dissertation on Hobbes, uh if you want to, just if you something central to cans thought or or Hagel or something, I mean, that's not popular that what's popular is to take somebody way down the line from that, because there's a feeling that that's all been done. So you take something way, way, way down the line from that, that's much less important. And then you sort of play with that. And I think most people, anyone who's watching, who's being a philosophy department in recent years will know that tendency, by the way, there's a very practical consequence of this. I saw this at the end of my friend Roger Scruton is life when he he would occasionally he didn't get tenure at universities, but he would occasionally be flown in even by his enemies to teach courses in various universities in basics of philosophy, because there was no one in the department able to do it. Like he would, he would he would go in and teach for a semester, you know, Hagel and Kant and Schopenhauer and others, because there was no one to do it because they were all playing with the things way, way, way down the road from this. So that had already happened and people were searching for new games to play and the critical race theory stuff forced its way in, partly in the way that all of this that's now known as anti racism does, which is in a sort of bullying tone of saying if you don't follow this the same way that all the things that are called studies, I think everything called Studies and humanities should be shut down </s><s>[INST] because of the activist, [/INST] All activist gay studies and queer studies. Um nothing good has ever come from it. Nothing good </s><s>[INST] to push back. Is it, is it obvious that activism is a sign of a flaw in a discipline? So isn't it [/INST] a sign of the death of the discipline? It's a sign that discipline is over. </s><s>[INST] But isn't it a good goal to have for discipline to enact change, positive change in the world? Or is that too? Is that, that's for politicians to do with the findings of of science, not [/INST] why create an ideology and then set out to find disciplines that have weekly put together to try to back up your political ideology. </s><s>[INST] So ideology should not be part of, of uh, of science or of humanities. [/INST] Mhm. I mean, anyone could do it, you could decide to go in and be wildly right wing about something and only do things that prove your right wing ideas. Be fantastically anti academic, fantastically anti science. It's an absurd way to mix up activism and, and academia and it's absolutely right. And critical Race Series. One of the ones that completely polluted the academy. </s>
<s>[INST] go to uh eight sleep dot com slash likes to get $200 off this show is also sponsored by Better Help spelled H E L p help. Every time I say that it reminds me of the movie castaway, which is awesome. Check it out at better health dot com slash lex. They figure out what you need and match you with a licensed professional therapist and under 48 hours I chat with a person on there and enjoy it. Of course, I also regularly talked to David Goggins these days who is definitely not a licensed professional therapist, but he does help me meet his and my demons and become comfortable to exist in their presence. Everyone is different. But for me, I think suffering is essential for creation, but you can suffer beautifully in a way that doesn't destroy you. Therapy can help in whatever form that therapy takes better help is an option worth trying. They're easy, private, affordable and available worldwide. You can communicate by text any time and schedule weekly audio and video sessions. Check it out at better help dot com slash lex. And now here's my conversation with Manolis callous. So your group at MIT is trying to understand the molecular basis of human disease. What are some of the biggest challenges in your view? [/INST] Don't get me started. I mean, understanding human disease is the most complex challenge in modern science. So because human disease is as complex as the human genome, it is as complex as the human brain and it is in many ways even more complex. Because the more we understand disease complexity, the more we start understanding genome complexity and epi genome complexity and brain circuitry complexity and immune system complexity and cancer complexity and so and so forth. So traditionally human disease was following basic biology, you would basically understand basic biological model organisms like mouse and fly and yeast. You would understand sort of mammalian biology and animal biology and eukaryotic biology in sort of progressive layers of complexity. Getting closer to human fellow genetically and you would do perturbation experiments in those species to see if I knock out a gene what happens. And based on the knocking out of these genes, you would basically then have a way to drive human biology because you would, you would understand the functions of these genes. And then if you find that a human gene locus, something that you've mapped from human genetics to that gene is related to a particular human disease, you say. Aha. Now I know the function of the gene from the model organisms. I can now go and understand the function of that gene in human. But this is all changing, This is dramatically changed. So that was the old way of doing basic biology. You would start with the animal models, The eukaryotic models, the mammalian models. And then you would go to human Human genetics has been so transformed in the last decade or two that human genetics is now actually driving the basic biology. There is more genetic mutation information in the human genome than there will ever be in any other species. </s><s>[INST] What do you mean by mutation information? [/INST] So so perturbations is how you understand systems. So an engineer build systems and then they know how they work from the inside out. As scientists study systems through contributions. You basically say if I poke that balloon, what's going to happen and I'm going to film it in super high resolution understand, I don't know, aerodynamics or fluid dynamics, the vehicle with water etcetera. So you can then make experimentation by perturbation and then the scientific process is sort of building models that best fit the data, designing new experiments that best test your models and challenge your models and so and so forth. That's the same thing with science basically. If you're trying to understand biological science, you basically want to do perturbations that then drive the models. </s><s>[INST] So how do these perturbations allow you to understand disease. [/INST] So if if you know that a gene is related to disease, you don't want to just know that it's related to the disease. You want to know what is the disease mechanism because you want to go and intervene. So the way that I like to describe it is that traditionally epidemiology, which is basically the study of disease, you know, sort of the observational study of disease has been about correlating one thing with another thing. So if you if you have a lot of people with liver disease were also alcoholics, you might say, well maybe the alcoholism is driving the liver disease, or maybe those who have liver disease self medicate with alcohol. So the connection could be either way with genetic epidemiology. It's about correlating changes in genome with a final topic differences and then, you know, the direction of causality. So if you know that a particular gene is related to the disease, you can basically say, okay, perturbing that gene in mouse causes the mice to have X. Genotype. So, perturbing that gene in human causes humans to have the disease. So I can now figure out what are the detailed molecular finna types in the human that are related to that organismo phenotype in the disease. So it's all about understanding disease mechanism, understanding what are the pathways, what are the tissues, What are the processes that are associated with the disease? So that we know how to intervene. You can then prescribe particular medications that also alter these processes. You can prescribe lifestyle changes that also affect these processes and so on so forth. </s>
<s>[INST] Yeah, [/INST] right. I'm talking to the guy who, who quit imax so I don't know there's discord servers and in these like there's like there's like seven uh different rooms you can go in or there's several rooms and each one is like a different field of making money. E commerce trading, Cryptocurrency um I think fulfillment by amazon like copyrighting okay, so I went to all of these, I checked him out, I checked all their money making tools. The first funny thing is that Andrew Tate is nowhere to be found. The supposed successful guy that you like bought into is nowhere to be found. It's these professors that you have now he has hired and said these guys are super qualified so like looked up some of what some of these guys have done and some of them have launched like scam e crypto coins. The Cryptocurrency professor was like shilling a bunch of coins that did bad and then like deleted the tweets. I mean just completely exactly what you'd expect behind the paywall, it's nothing of substance. You're not gonna learn to get rich by escaping the Matrix and going to work for Jeff Bezos fulfillment by amazon is not escaping the Matrix, right? Like that's not the way to hustle to the top, it's literally a field of making money that everyone in the world has access to if you want to differentiate yourself and make money. The first thing you realize is going into skill sets that literally anyone with an internet account can do is a bad way to do that because you have to have some differentiating factor to add value. So it's just such a obvious and complete scam because there is no value to this like so called education, the professors are crap, the advice there, like hiding some of the bad things they've done and agitates nowhere to be found. Ultimately, that's why everyone joins what he's done is very interesting because, and I'll give him credit in his marketing. He's been very savvy to like make the reasons you admire him, not the thing he's sort of selling, which is weird, like he's selling get rich quick, which seems like it relates to his persona but is actually very orthogonal to it. His persona is like the tell it how it is like tall buff rich guy. It's like actually his persona that you're buying into and then he's selling you this thing to the side which when people get in there and they're not delivered on the product, he still is those things that you first thought he was. So it's like, I think it's to some extent he's made a lot of money by making the thing that he makes money on, not the thing he gets so much pushback online for and what he's also loved for. So people will push back for his misogyny, but the real way he's making money is just like basic get rich quick schemes that are super obvious to spot, but everyone's distracted by like, oh he said some crazy stuff about women or you know, all these various other scandals he's gotten himself in to </s><s>[INST] get more and more and more attention. So with the persona, uh, is the hustler universities still operating? [/INST] I think they've rebranded it, I'm part of their pitch now. I'm like, they put me on is like, I mean, as like the Matrix is trying to take us out lex and then it's me saying like, you know, they put me in like saying I'm part of the Matrix, they put me in saying, oh this guy sucks, you know, I joined, it sucks and so they'll play that and they do like a bass drop and it's like, you know, don't listen to people like this da da da da. I mean, it's basically like co opted by </s><s>[INST] the Matrix to attack [/INST] your </s><s>[INST] an insider threat that infiltrated now is being used by the Matrix to attack him. Well to [/INST] everyone who criticizes him as part of the Matrix, he won't say who the Matrix is. It's just, it's just the shadowy cabal of rich powerful people. It's just like the easy narrative for people who are disaffected and who feel cheated by the system, You just collectivized that system and you make it the bad guy and you go look, look, those guys, those guys have been cheating you, they're the bad guys. They want me shut </s><s>[INST] up and [/INST] then now the person that the people who harmed you, they want this guy shut up, you're gonna listen to him. So that's like, it's like the most basic psychological manipulation that everyone seems to constantly fall for. It's it's really a trivial and stupid, but </s><s>[INST] can you steal man the case for hustlers University where it's actually giving young people confidence teaching them valuable lessons about like actually incentivizing them to do something like fulfillment by amazon. The basic thing to [/INST] try to </s><s>[INST] learn about it to fail or maybe see like to try to give a catalyst and incentive to try [/INST] as much as it pains me. I will try to give a a succinct, maybe steel man of it as best as I can thinking that it's such a grift. But um I think what you would say is that some people in order to make a change in their life need a someone who they can look up to and men don't have a lot of like strong role models like big male presences in their life who can serve as a proper example. So the most charitable interpretation would be Andrew Tate would encourage you to go reach for the stars. I guess my problem is I have a deep, like I have a deep issue with the like lust and greed that centers all these things. It's like this glorification of wealth equal status, wealth equals good person wealth and Bugatti equals you are meaningful, you matter. And like the dark underlying thing is that none of that, none of that matters like it matters that you make a decent living but passed just like that. I think the like lust for more stuff and the idealization of these people that is just like opulence is a net bad. So that's like my steel man has to stop there because I really disagree with like the values that are pushed by people like that. </s>
<s>[INST] But you're still ultimately trying to find [/INST] that basic seed of passion for the world. Yeah, did they really do it? Did they find something interesting or curious? </s><s>[INST] And do they care about it? I think somebody admires Jim Keller and he likes details. So one of the ways if you get a person to talk about what they're interested in, how many details, [/INST] like how much of the whiteboard can you fill out? Well, I think you figure out, did they really do the work if they know some of the details? And if they have to wash over the details, </s><s>[INST] well, then they didn't do it. Especially with engineering, the work is in the details. I have to go there briefly just to get your kind of thoughts in the long-term future of robotics. There's been discussions on the GPT side on the large language model side of whether there's consciousness inside these language models. And I think there's fear, but I think there's also excitement or at least the wide world of opportunity and possibility in embodied robots having something like, let's start with emotion, love towards other human beings, and perhaps the display, real or fake, of consciousness. Is this something you think about in terms of long-term future? Because as we've talked about, people do anthropomorphize these robots. It's difficult not to project some level of, I use the word, sentience, some level of sovereignty, identity, all the things we think is human. That's what anthropomorphization is, is we project humanness onto mobile, especially legged robots. Is that something almost from a science fiction perspective you think about or do you try to avoid ever, [/INST] try to avoid the topic of consciousness altogether? I'm certainly not an expert in it, and I don't spend a lot of time thinking about this, right? And I do think it's fairly remote for the machines that we're dealing with. I don't spend a lot of time. Our robots, you're right, the people anthropomorphize. They read into the robot's intelligence and emotion that isn't there because they see physical gestures that are similar to things they might even see in people or animals. I don't know much about how these large language models really work. I believe it's a kind of statistical averaging of the most common responses to a series of words, right? It's sort of a very elaborate word completion. And I'm dubious that that has anything to do with consciousness. And I even wonder if that model of sort of simulating consciousness by stringing words together that are statistically associated with one another, whether or not that kind of knowledge, if you want to call that knowledge, would be the kind of knowledge that allowed a sentient being to grow or evolve. It feels to me like there's something about truth or emotions that's just a very different kind of knowledge. That is absolute. Like the interesting thing about truth is it's absolute. And it doesn't matter how frequently it's represented in the World Wide Web. It's, if you know it to be true, it may only be there once, but by God, it's true. And I think emotions are a little bit like that too. You know something, you know? And I just think that's a different kind of knowledge than the way these large language models </s><s>[INST] derive sort of simulated intelligence. It does seem that the things that are true very well might be statistically well represented on the internet because the internet is made up of humans. So I tend to suspect that large language models are going to be able to simulate consciousness very effectively. And I actually believe that current GPT-4, when fine-tuned correctly, would be able to do just that. And that's going to be a lot of very complicated ethical questions that have to be dealt with. They have nothing to do with robotics and everything to do with. [/INST] There needs to be some process of labeling, I think, what is true. Because there is also disinformation available on the web and these models are going to consider that kind of information as well. And again, you can't average something that's true and something that's untrue and get something that's moderately true. It's either right or it's wrong. And so how is that process, and this is obviously something that's available on the purveyors of these, Bard and Chat GPT. </s>
<s>[INST] Do you think Bitcoin has a strong chance to take over the world? So become the primary, you mentioned the three things that make money money become the primary methodology by which we store wealth we exchange. [/INST] No, no, I think what Bitcoin is this was a phrase that I got from my friend </s><s>[INST] Matt McLennan 1st Eagle [/INST] an option on digital gold. So it's the gold of the system but currently behaves like an option. That's why it's quite volatile because we don't really know if this brave new world of crypto is gonna work. But if it does work then Bitcoins the gold because of the finite supply, what role we need gold to play in The metaverse isn't quite clear. I love that </s><s>[INST] you're using the term metaverse. This is great. [/INST] Well I just like the metaverse city as a kind of uh the antithesis of what we're trying to do and in Austin but I love it. Can you imagine I'm using it sarcastically. I come from Glasgow where all novel words have to be used sarcastically. So the metaverse </s><s>[INST] sarcastic but see the beauty about humor and sarcasm is that the joke becomes reality. I mean it's like using the word big bang to describe the origins of the universe. It becomes like [/INST] it will after a while it's in the textbooks and nobody's laughing. Yeah, well that's exactly right. So sticky. Yeah, I'm on the side of humor but it is a, it is a dangerous activity these days anyway. I think Bitcoin is, is the option of digital gold. The the role it plays is probably not so much story value right now. It's just nicely not very correlated asset in your portfolio When I updated the ascent of money, which was in 2018, 10 years after it came out. I wrote a new chapter in which I said Bitcoin which had just sold off after its 2017 bubble will rise again through adoption because if every millionaire in the world Has .2% of his or her wealth in Bitcoin, the price should be $15,000 and if it's 1%, it's $75,000 And it might not even stay at 1% because I mean look at its recent performance. If you, if you were exposure to stop global stocks have been hedged with a significant crypto holding, you would have aced the last few months. Uh, so I think the non correlation property is very, very important in driving adoption and the volatility also drives adoption if you're a sophisticated investor. Uh So I think the adoption drives uh Bitcoin up because it's the option of digital gold. But it's also just this nicely not very correlated asset that you want to hold in in a world where the hell I mean the banks everybody's going to titan. We've come through this massively disruptive episode of the pandemic public debt, soared money printing sword. You can hang around with your bonds and wait for the euthanasia of the interior. You can hang on to your tech stocks and just hope there isn't a massive correction or dot dot dot well and it seems like a fairly obvious strategy to make sure that you have at least some crypto for the coming year given what we likely have to face. I think what's really interesting is that on top of ethereum a more elaborate financial system is being built stable coins are the interesting puzzle for me because we need off ramps ultimately you and I have to pay taxes in U. S. Dollars and there's no getting away from that. The I. R. S. Is gonna let us hold crypto as long as we pay our taxes. And the only question in my mind is what the optimal off ramp to make those taxes make those tax payments. Probably it shouldn't be a currency invented by facebook never struck me as the best solution to this problem. Maybe it's some kind of fed coin, uh, or maybe one of the, the existing algorithmic stable coins does the job, but we clearly need some stable off ramp. </s><s>[INST] So you don't think it's possible for the I. R. S within the next decade to be accepting Bitcoin as tax payments. [/INST] I doubt that Having dealt with the i. r. s. now, since when did I first come here? 2002? It's hard to think of an institution less likely to reap into the 21st century when it comes to payments. No, I think, I think we'll, we'll be, will be tolerated, crypto world will be tolerated as long as we pay our taxes. That's that it's important that we're already at that point. And then the next question becomes, Well, does Gary Gensler define everything as a security? And do we then have to go through endless regulatory contortions to satisfy the sec? There's a whole bunch of uncertainties that the administrative state excels at creating because, you know, that's just how, that's how the administrative state works. You're doing something new. Hmm. I'll decide whether that's a security, but don't expect me to define it for you. I'll decide in an arbitrary way and then you'll owe me money. So all of this is going to be very annoying. And you know, for people who are trying to run exchanges or innovate in the space these these regulations will be annoying. But the problem with Fintech is it's it's different from tech broadly defined. You know, when tech got into e commerce with amazon, when it got into social networking with facebook, there wasn't a huge regulatory jungle to navigate. But welcome to the world of finance, which has always been a jungle of regulation because the regulation is there to, you know, basically entrench the incumbents, that's what it's for. So it'll be a much tougher fight than the fights we've we've seen of uh other aspects of the tech revolution because because the incumbents are are there and they see that the threat and in the end Satoshi said it very explicitly, it's peer to peer payment without third party verification and all the third parties are going to wait. What were the third parties for? </s>
<s>[INST] Yeah, changing the creation of musical creation of audio, creation of podcasts is a really fascinating possibility. I myself don't understand what it is about podcasts that's so intimate. It's just is I listen to a lot of podcasts, I think it touches on a human and a deep human need for connection that people do feel like they're connected to when they listen. I don't understand what the psychology that is, but in this world is becoming more and more disconnected, uh it feels like this is fulfilling a certain kind of need and empowering the creator as opposed to just the listener is really interesting this, I'm really excited that you're working on [/INST] that. Yeah, I think one of the things that is inspiring for our teams to work on podcast is exactly that whether you think, like I like I probably do that. It's something biological about perceiving to be in the middle of the conversation that makes you listen in a different way. It doesn't really matter. People seem to perceive it differently and there was this narrative for a long time that, you know, if you look at video, everything kind of in the foreground, it got shorter and shorter and shorter because of financial pressures and monetization and so forth and events at the end? There's almost like 20 seconds clip people just screaming something. And uh I'm really, I feel really good about the fact that you could have interpreted that as people have no attention span anymore. They don't want to listen to things, They're not interested in deeper stories, like, you know, people are people are getting dumber, but then podcast came along and it's almost like, no, no, the need still existed once one, but maybe maybe it was the fact that you're not prepared to look at your phone like this for two hours. But if you can drive at the same time, it seems like people really want to dig deeper and they want to hear like the more complicated version. So to me that is very inspiring that that podcast is actually long form. It gives me a lot of hope for, for humanity that people seem really interested in hearing deeper, more complicated conversations. </s><s>[INST] This is uh I don't understand it, it's fascinating. So the majority for this podcast listen to the whole thing. This whole conversation, we've been talking for an hour and 45 minutes and somebody will I mean most people will be listening to these words. I'm speaking [/INST] right now, I wouldn't have thought that 10 years ago with the world seemed to go, so that's very positive. I think </s><s>[INST] that's really exciting and empowering the creator, There's as really exciting. Uh last question, you also have a passion for just mobile in general, how do you see the smartphone world, the digital space of Of smartphones and just everything that's on the move, whether it's uh internet of things and so on, uh changing over the next 10 years and so on. [/INST] I think that one way to think about it is that computing might be moving out of these uh multipurpose devices, the computer we had on the phone into specific, you know, specific purpose devices and you know, it will be ambient that, you know, at least in my home, you just shout something at someone and there's always like one of the speakers close enough. And so uh you start behaving differently, it's as if you have the internet, ambient ambient lee around you and you can ask things. So I think computing, we'll kind of get more integrated and we, when we won't necessarily think of it as as connected to a device in the same thing, in the same way that we do today. I don't know the path to that. Maybe we used to have these desktop computers and then we partially replace that with with the laptops and left, you know at home and at work. And then we got these phones and we started leaving the laptop at home for a while and maybe the maybe for stretches of time, you're gonna start using the watch and you can leave your your phone at home, like for a run or something and you know, we're on this progressive path where you, I think what is happening with voices that you haven't, you have an interactive interaction paradigm that doesn't requires large physical devices. So I definitely think there's a future where you can have your airports and and your watch and you can do a lot of computing and I don't think it's gonna be this binary thing, I think it's gonna be like many of us still have a laptop, we just use it less and so you shift your your consumption over and I don't know about a Ar glasses and so forth. I'm excited about, I spent a lot of time in that area, but I still think it's quite far away. </s><s>[INST] A RVR [/INST] Yes VR is is happening and working, I think the recent Oculus quest is quite impressive, I think they are is further away, at least that type of A R I think. But I do think your phone or water glasses understanding where you are and maybe what you're looking at and being able to give you audio cues about or you can say like what is this and it tells you what it is, uh that I think might happen, you know, you use your, you're watching your glasses as a has a mouse pointer on reality, I think it might be a while before, I might be wrong. I hope I'm wrong. I think it might be a while before we walk around with these big like lab glasses that protect things. </s>
<s>[INST] This show is also brought to you by stamps dot com mail and ship anytime anywhere right from your computer without needing to take a trip to the post office, send letters, ship packages and pay less with discounted rates from USPS and now ups it's a bit surreal and kind of an incredible feeling for me to be doing a stamps dot com ad read because I've been a fan of podcast for many years and stamps. Dot com has been supporting those podcasts and so I almost uh associate at stamps dot com read but the podcast that has truly made it. So I feel like I have made it. I know it's a silly feeling but it is what I feel so you can save time and money with stamps. Dot com. There's no risk and with my promo code lex, you get a special offer that includes four week trial plus free postage and a digital scale. No long term commitments or contracts. Just go to stamps dot com, click on the microphone at the top of the homepage and type in lex that's stamps dot com promo co lex stamps dot com. Never go to the post office again. This is the lex Fridman podcast and here is my conversation with joe baller. What to you is beautiful about mathematics. [/INST] I love a mathematics that some people don't even think of as mathematics, which is beautiful, creative mathematics where we look at maths in different ways, we visualize it. We think about different solutions to problems. A lot of people think of maths as you have one method and one answer. And what I love about maths is the multiple different ways. You can see things, different methods, different ways of seeing different in some cases different solutions. So that is what is beautiful to me about mathematics that you can see and solve it in many different ways. And also the sad part that many people think that maths is just one answer on one method. </s><s>[INST] So to you, the beautiful the beauty emerges when you have a problem with the solution and you start adding other solutions, simpler solutions. Uh weirder solutions more interesting, some of their visual, some of their algebraic geometry, all that kind of stuff. [/INST] Yeah, I mean I always say that you can take any maths area and make it visual and we say to teachers, give us your most dry boring maths and we'll make it a visual interesting creative problem. And turns out you can do that with any area of maths and I think we've given it's been a great disservice to kids and others that it's always been numbers. Lots and lots of numbers, numbers can be great, but you can think about maths in other ways besides numbers. </s><s>[INST] Do you find that most people are better visual learners or is this just something that's complementary? What's the kind of the full spectrum of students in the way they like to explore Math? Would you say [/INST] there's definitely people who come into the classes I do, who are more interested in visual thinking and like visual approaches, but it turns out what the neuroscience is telling us is that when we think about maths, there are two visual pathways in the brain and we should all be thinking about it visually. Some approaches have been to say well your visual learners who will give you visuals and you're not a visual learner, but actually, if you think you're not a visual learner, it's probably more important that you have a visual approach. So you can develop that part of your brain, </s><s>[INST] you were saying that there is some kind of interconnected aspect to it. So the visual connects with the non visual [/INST] Yes, so this is what the neuroscience has shown us, that when you work on a maths problem, there are five different brain pathways and that the most high achieving people in the world are people who have more connections between these pathways. So, if you see a maths problem with numbers, but you also see it visually, that will cause a connection to happen in your brain between these pathways, and if you may be right about it with words that would cause another connection, or maybe you build it with something physical, that would cause a different connection and what we want for kids is we call it a multi dimensional experience of math, seeing it in different ways, experiencing it in different ways that will cause that great connected brain, </s><s>[INST] you know, there's these stories of physicists doing the same, I find physicists are often better at building that part of their brain of using visualization for intuition building, because you ultimately want to understand the, like, the deepest secret underneath this problem, and for that, you have to into it your way there and you you mentioned offline that one of the ways you might approach your problems to try to tell a story about it and some of it is like legend, but I'm sure it's not always is, you know, you have Einstein thinking about a train, you know, and the speed of light and you know, that kind of intuition is useful, you start to imagine a physical world, like how does this idea manifests itself in the physical world and then start playing in your mind with that physical world and think is this going to be true? Is this going to be [/INST] true? Einstein is well known for thinking visually and people talk about how he really didn't want to go anywhere with problems without thinking about them visually. But the other thing you mentioned that sparked something for me is thinking with intuition, like having intuition about maths problems. That's another thing that's often absent in maths class, the idea that you might think about a problem and use your intuition um but so important and when mathematicians are interviewed, they will very frequently talk about the role of intuition and solving problems, but not commonly acknowledged or brought into education. </s><s>[INST] Yeah, I mean that's what it is. Like if you task yourself for building an intuition about a problem, that's what that's where you start to pull in. Like um what is the pattern I'm seeing in order to understand the pattern you might want to then start utilizing visualization, but ultimately that's all in service of like solving the puzzle, cracking it open to get the simple explanation of why why things are the way they are as opposed to um like you said, having a particular algorithm that you can then execute to solve the problem. It's hard, it's hard. The reason is really hard. [/INST] Yeah, it's hard, I mean I love to value what's hard in maths instead of being afraid of it. We know that when you struggle that's actually a really good time for your brain. You want to be struggling when you're thinking about things. So if it's hard to think intuitively about something that's probably a really good time for your brain. I used to work with somebody called Sebastian Thrun who it's a great sort of mathematician you might think for him at a I person. And I remember in one interview I did with him, he talked about how they built robots I think for the Smithsonian and how they were having this trouble with them picking up white noise and he said they had to solve it, they had to work out what's going on and how he intuitively worked out what the problem was. But then it took him three weeks to show it mathematically. I thought that was really interesting that how you can have this intuition and know something works. It's kind of different from going through that long mathematical process of proving it. But so important. </s><s>[INST] I think probably our brains are involved as like intuition machines and the uh the math of like showing it like formally is probably an extra thing that were not designed for. You see that with Feinman and his um I mean just all of these physicists definitely you see um starting with intuition sometimes starting with an experiment and then the experiment inspires intuition, but you can think of an experiment as a kind of visualization, just like let's let's take whatever the heck we're looking at and draw it and and draw like the pattern as it evolves as the thing grows for N equals one, for N equals two and equals three, you start to play with it. And then in the modern day, which I loved doing is, you know, you can write a program that then visualizes it for you, and then you can start exploring it programmatically and that that and then uh you can do so interactively to I tend to not like interactive because the way it takes to way too much work because you have to click moving stuff. I love to interact through writing programs, but that's my particular brain software engineer. So like you can you can do all these kinds of visualizations. Uh and then there's the tools of visualization, like color, all those kinds of things that you're absolutely right. There actually not taught very much like the art of visualization [/INST] not taught. And we love as well, color coding, like when you represent something mathematically you can show color to show the growth and kind of code that So if I have an algebraic expression for a pattern, maybe I show the X with a certain color, but also right in that color. So you can see the relationship very cool. And um yeah, we particularly in our work with elementary teachers, many of them come to our workshops and they're literally in tears when they see things making sense visually because they have spent their whole lives not realizing, you can really understand things with these visuals. It's quite powerful. </s><s>[INST] You say that there's something about there's something valuable to learning when the thing that you're doing is challenging is difficult. So a lot of people say, you know, math is hard or math is too hard or too hard for me. Do you think math should be easy or should it be hard? [/INST] I think it's great when things are challenging, but there's something that is really key to being able to deal with challenging maths and that is knowing that you can do it. And I think the problem in education is, a lot of people have got this idea that you're either born in the maths brain or you're not. So when they start to struggle, they think, oh, I don't have that maths brain and then they were literally sort of switch off in their brain and things will go downhill from that point. So struggle becomes a lot easier and you're able to struggle if you don't have that idea. But you know that you can do it, you have to go through this struggle to get there, but you're able to do that. And so were hampered in being able to struggle with these ideas we've been given about what we can do. </s><s>[INST] Ask a difficult question here. So there's kind of, um, I don't know what the right term is, but some people our um struggle with learning in different ways, like their brain is constructed in different ways and um how much should, as educators should we make room for that? So how do you know the difference between this is hard and I don't like doing hard things versus my brain is wired in a way where I need to learn in very different ways. I can't learn it this way. How do you find that line? How do you operate in the gray area? [/INST] So this is why being a teacher is so hard and people really don't appreciate how difficult teaching is When you're faced with, you know, 30 students who think in different ways. And um, but this is also why I believe it's so important to have this multidimensional approach to maths. We've really offered it in one way, which is here's some numbers in a method. You follow me do what I just did and then reproduce it. And so there are some kids who like doing that and they do well, and a lot of kids who don't like doing it and don't do well, but when you open up maths and you give you let kids experience it in different ways, maybe visually with numbers with words. What happens is kids, there are many more kids who can access it. So there's different brain wiring you're talking about, where some people are just more able to do something in a particular way, that's why we want to, that's one of the reasons we want to open it up, so that there are different ways of accessing it and then that's not really a problem. </s><s>[INST] So I grew up in the soviet union and uh fell in love with math early, I was forced into Math early and fell in love through force. That's [/INST] good. Well you fell in love well, </s><s>[INST] but there are some things we talked about a little bit, is there such a value for excellence? It's competitive and it's also everybody kind of looks up, the definition of success is being in a particular classes, you know, being really good at it. Um and like it's not improving, it's like being really good. I mean, we are much more like that with sports for example, were not, it's like it's understood, you know, you're going to start on the basketball team if you're going to start on the basketball team, if you're going to be better than the other guys, the other girls on the team. Uh so that coupled with the belief, this could be partially a communist belief, I don't know, but the belief that everybody is capable of being great, but if you're not great, that's your fault and you need to work harder and I remember I had a sense that um probably delusional, but I could win a nobel prize, I don't even know what that entails. Um but I thought um like my dad early on told me just off hand and it always stuck with me that if you, if you can figure out how to build a time machine, how to travel back in time, it will probably give you a nobel prize. And I remember early in my life thinking I'm going to invent a time machine and like, like the tools of mathematics were in service of that dream of winning the nobel prize and it's silly, I didn't really think in those concrete terms, but I just thought I could be great feeling and then then when you struggle, the belief that you could be great is like struggle is good, that [/INST] pushes you on. </s><s>[INST] And so the other thing about the soviet system that might love to hear your comments about is just the sheer like hours of math, like the number of courses you, you're talking about a lot of geometry, a lot more john I think in the american system you take maybe one year of geometry in high school. First of all, geometry is beautiful, it's visual and then you get the reason to proofs and stuff like that in in Russia, I remember just being nailed over and over with y'all, it was just nonstop and then of course there's different perspectives, I'm calculus and just the whole, the sense was that math is like like fundamental to the development of the human mind so math but also science and literature by the way was also hit very hard. Like we read a lot of serious adult stuff. America does that a little bit too. They challenge young adults with good literature but they don't challenge adults very much with math. So those two things um valuing excellence and just a lot of math in the curriculum. Do you think? Do you think do you find that interesting because it seems to have been successful? [/INST] Yeah I think that's very interesting and there is a lot of success people coming through the soviet system. I think something that's very different to the U. S. And other countries in the world is that idea that excellence is important and you can get there if you work hard in the U. S. There's an idea that excellence is important. But then kids given the idea in many ways that you can either do it or you're one of the people who can't so many students in the school system think they're one of the kids who can't. So there's no point in trying hard because you're never going to get there. So if you can switch that idea it would be huge and it seems from what you've said that in the US in the soviet union. That idea is really different now. The downside of that idea that anybody can get there if you work hard is that thought that if you're not getting there, it's your fault and I would add something into that. I would say that anybody can get there, but they need to work hard and they also need good teaching because there are some people who really can't get there because they're not given access to that good teaching. So, but that would be huge. That change as to doing lots of maths. If if maths was interesting and open and creative and multidimensional, I would be all for it. We we actually ran summer camps at stanford where we invite kids in and we give them this maths that I love And the in our camp classrooms there were three hours long. And when we were planning, the teachers are like three hours, are we going to be able to keep the kids excited? Three hours, turned out they didn't want to go to break or lunch, there'd be so into these mathematical patterns, we couldn't stop them. It was amazing. So yeah, if maths was more like that, then I think having more of it, it would be a really good thing. </s><s>[INST] So what what age are you talking about? Is there um could you comment on what age is like the most important when people quit math or give up on themselves or a math in general and perhaps that age or something earlier is really uh important moment for them to discover, to be inspired to discover the magic of math. [/INST] I think a lot of kids start to give up on themselves and maths around From about 5th grade and then those middle school years are really important and fifth grade can be pivotal for kids just because they're allowed to explore and thinking good ways in the early grades of elementary school. But fifth grade teachers are often like, okay, we're going to prepare you now for middle school and we're going to give you grades and lots of tests and that's when kids start to, I feel really badly about themselves. And so middle school years, we are camps and middle school students. We think of those years as really pivotal many kids in in those years are deciding, yes, I'm gonna keep going with stem subjects or no, I'm not that this isn't for me. So I mean all years are important and in all years you can kind of switch kids and get them on a different pathway. But I think those middle school years are really important. </s><s>[INST] So what's the role of the teacher and this one is the explanation of the subject, But do you think teachers should almost do like one on one, you know, little johnny, I believe in you kind of thing like that? That energy of like [/INST] turns out it's really important. There's a study that was done, it was actually done in high school english classrooms. We're all kids wrote an essay for their teacher and this was done as an experiment. Half of the kids got feedback from their teacher diagnostic feedback, which is great. But for half of the kids, it said an extra sentence at the bottom that the researchers had put on and the kids who read that extra sentence did significantly better in english a whole year later, the only change Was this one sentence. </s><s>[INST] What did the sentences? [/INST] So what did the sentence say? The sentence said, I'm giving you this feedback because I believe in you and the kids who read that did better a year later. So when I share this with teachers, I say, you know, I'm not suggesting you put on the bottom of all kids work and giving this feedback. So I believe in you, one of the teachers said to me, we don't put it on a stamp. I said, no, don't put it on a stamp. It's um but your words are really important and kids are sitting in classrooms all the time thinking what does my teacher think of me, Does my teacher think I can do this. Um so it turns out it is really important to be saying to kids, I know you can do this and those messages are not given enough by teachers </s><s>[INST] and really believe it [/INST] and believe it. Yeah, they can't just say it, you have to believe it. </s><s>[INST] I sometimes because like it's such a funny dance because almost such a perfectionist um of extremely self critical and I have one of students come up to me and it's clear to me that there not even close to good and it's tempting for me to be like uh to sort of give up on them mentally. But the reality is like, if you look at many great people throughout history, they sucked at some [/INST] point and </s><s>[INST] and some of the greatest took non linear path to where they sucked for long into into later life and so always kind of believing that this person can be great, [/INST] exactly that </s><s>[INST] you have to communicate that. Plus the fact that they have to work hard. [/INST] That's it. Yeah, yeah, and you're right Silicon Valley where I live is filled with people who are drop outs at school or who had special needs who didn't succeed. Um it's very interesting that have gone on to do amazing work in creative ways. I mean, I do think our school system is set up to um value good memory risers who can reproduce what the teacher is showing them and push away those creative deep thinkers often slower thinkers, they think slowly and deeply and they often get the idea early on that they can't be good at maths or other subjects. So um yeah, I think many of those people are the ones who go on and do amazing things. </s><s>[INST] So there's a guy named eric Weinstein ish, I know many mathematicians like this, but he he talks a lot about not having us about having a non standard way of learning. I mean a lot of great mathematicians, a lot of great physicists are like that and he felt like he became quickly, he got a speech at Harvard became quickly an outcast of the system. Like the the education, especially early education system didn't help him. Um Is there ways for an education system to support people like that? Is it the kind of multi dimensional learning? [/INST] Absolutely. I mean, I think education system still uses an approach that was in classrooms hundreds of years ago. The textbooks have a lot to answer for in producing this very uninspiring mathematics. Um but yeah, if you open up the subject and have people see and solve it in different ways in value, those different ways. Somebody I appreciated a lot is a mathematician called mary and mr Carney, you heard of her? She won the fields medal, she was from Iran Uh first woman in the world to win the fields Meadow in mathematics. She died when she was 40, she was at Stanford but her work was entirely visual and she talked about how her daughter thought she was an artist because she was always visualizing and I attended, she asked me to chair the PhD defense for one of her students and I went to the defense in the math department and it was so interesting because this young woman spent like two hours sharing her work. All of it was visual. In fact, I don't think I saw any numbers at all. And I remember that day thinking, wow, I could have brought her like 13 year old into this PhD defense, they would not recognize this as maths, but when mariam Miss Connie won the fields medal, all these other mathematicians were saying that her work had connected all these previously unconnected areas of maths and so, but when she was, she also shared that when she was in school, when she was about 13, she was told that she couldn't do maths, she was told that by her teacher, </s><s>[INST] this is Iran, she grew up [/INST] in Iran, so I love that, you know, to be told you can't be good at maths and then go on and win the fields medal is cool. </s><s>[INST] I've been told by a lot of people in my life that I can't do something. I'm very definitely nonstandard. Um, but all it takes, that's, that's why people talk about like the one teacher that changed everything. That's all it takes is one teacher. That's the power of that. So that, that's like, that should be inspiring to teachers. Like [/INST] I think it is </s><s>[INST] You as a single person given the education system, given the incentives, you have the power to truly change lives in like 20 years from now. I feel as medalists will walk up to you and thank [/INST] you, you did that for me. Yeah, absolutely and I share that with teachers that even in this broken system of what they have to do for districts and textbooks, a single teacher can change kids. Maths relationship or the subjects and uh forever, </s><s>[INST] what's the role of the parents in this picture? Let's go to another difficult subject. [/INST] That is a difficult subject. one study found that um the amount of maths anxiety, parents had predicted their child's achievement in school, um but only if they helped with homework. So </s><s>[INST] that's so funny. [/INST] Yeah, there are some interesting implications for this. I mean you can see how it works if you have maths anxiety and you're helping your kids with homework, you're probably communicating things like I was terrible at this at school and and that's how it gets passed on to kids. So one implication is if you have a really bad relationship Matthew hate maths, you have math anxiety, just don't, don't do math. So I work with your kids. Um but we have on our website, we have a little cheat for parents of ways to interact around mouths with your kids and </s><s>[INST] that's uh you cube dot org, [/INST] that's you cube dot orgs. So one of the things I say to parents and when your parent presentations is even if you hate maths, you need to just fake it with your kids, you should be always endlessly optimistic and happy about doing maths and um </s><s>[INST] I'm always curious about this with this. I you know, I hope to have kids one day. I don't have kids currently. Um our parents okay with like sucking at math and then trying to get their kid to be better than them essentially. Like is that difficult thing for a lot of parents? It is difficult to have, like it's almost an ego thing, like I never got good at this and I probably should have and yeah, I mean to me that you want to celebrate that, but I know a lot of people struggle with that like coaches in sports to make an athlete become better than them. It can be hard on the ego. Yeah. Do you experience the same with parents [/INST] to, I think, I mean I haven't experienced parents worrying that their kids will be better than them. I have experienced, I have experienced parents just having a really bad relationship with maths and not wanting to help not knowing how to help saying things. Like another study showed that when mothers say to their daughters, I was bad at maths in school, their daughters achievement goes down. So we know that kids pick up on these messages and um which is why I say you should fake it. But also I know that lots of people have just had a really bad relationship with maths. Even successful people like the undergrads I teach at stanford have pretty much always done well in maths, but they come to stanford thinking math is a set of methods to memorize. And so so do many parents believe that there is one method that you memorize and then you reproduce it. So until people have really had an experience of what I think of as the other maths, where until they've really seen that it's a really different subject, um it's hard for them to be able to shift their kids to see it differently. </s><s>[INST] Is there for a teacher, if we were to like systematize it, is there something teachers can do to do this more effectively? So you mentioned the textbook. So, so what what are the additional things you can add on top of this whole old school, traditional way of teaching that can improve the process. [/INST] So I do think there's a way of teaching maths that changes everything for kids uh and teachers. So I'm one of five writers of a new framework for the state of California new math framework, it's coming out next year, And we are recommending through this maths framework that people teach in this way. It's called Teaching two big ideas. So um at the moment people have standards that have been written and then textbooks have taken these standards and made not very good questions and if you look at the standards, like I have some written down here, just reading the standards, it makes it math seem really boring and uninspiring. </s><s>[INST] What are the kind of, can you give a few examples what? So [/INST] This is an interesting example in 3rd grade, there are three different standards about unit squares. </s><s>[INST] Okay, [/INST] so this is one of them a square with side length. One unit called a unit square is said to have one square unit of area and can be used to measure area. </s><s>[INST] And that's something you're expected to learn. [/INST] That is something that's, that's a standard. The textbook authors say, I'm going to make a question about that and they translate the standards into narrow questions </s><s>[INST] and then you measure success by your ability to do around on these standards. [/INST] So the standards themselves, I think of maths and many people think that's in this way as a subject of like a few big ideas and really important connections between them. Um, so like you can think of it as like a network map of ideas and connections. And what standards do is they take that beautiful map and they chop it up like this into lots of little pieces and they deliver the pieces to schools. And so teachers don't see the connections between ideas nor do the kids. So anyway, this is a bit of a long way of saying that what we've done in this new initiative is we have set out maths as a set of big ideas and connections between them. So this is a Grade three. So instead of there being 60 standards, we've said, well you can pull these different standards to get in with each other and um, also value the ways these are connected </s><s>[INST] and by the way for people who are just listening, we're looking at a small number of big concepts within mathematics square towels, measuring fraction shape and time And then how they are interconnected. So the goal is for this is for Grade three for example. [/INST] Yeah. And so we've set out for the state of California the whole of mathematics K 10 as a set of big ideas and connections. So we know that teachers, it works really well if they say, okay, so a big idea in my grade is measuring. Um, and instead of Reading five procedural statements that involve measuring they think, OK, measuring is a big idea. What rich, deep activity can I use that teaches measuring tickets and as kids work on these deep rich activities maybe over a few days, turns out a lot of maths comes into it. So we're recommending that let's not teach maths according to all these multiple multiple statements and lots and lots of short questions Instead, let's teach maths by thinking about what are the big ideas and what are really rich deep activities that teach those big ideas. </s><s>[INST] So that's the like how you teach it and maximize learning. What about like from a school district perspective, like measuring how well you're doing? You know the grades and tests and stuff like that. Do you throw those out or is it [/INST] not a fan of grades and tests myself? I think grades are fine if they're used at the end of the course. So at the end of my maths course I might get a grade because the grade is meant to be a summit of measure. It kind of describes your summit of achievement. But the problem we have in maths classrooms across the U. S. Is people use grades all the time every week or every day. Even my own kids when they went through high school technology has not helped with this. When they went through high school, they knew they had been graded for everything, they did everything and not only were they been graded for everything but they could see it in the grade book online and it would alter every class they went into. So this is the ultimate what I think of as a performance culture, you're there to perform, somebody's measuring you, you see your score. Um So I think that's not conducive for deep learning and yes have a great at the end of the year, but during the year you can assess kids in much better ways. Like teachers can. A great way of assessing kids is to give them a rubric that kind of outlines what they're learning over the course of a unit or a few weeks. So kids can actually see the journey there on like this is what we're doing mathematically, sometimes they self assess on those units and then teachers, um, we'll show where, what they can, what the kids can do with a rubric and also write notes, like, you know, in the next few weeks you might like to learn to do this. So, um, so instead of kids just thinking about, I'm in a kid or be kid or I have this letter attached to me, they're actually seeing mathematically what's important and they are involved in the process of knowing where they are mathematically at the end of the year, sure they can have a grade, but during the year they get these much more informative measures. </s><s>[INST] I do think this this might be more for college, but maybe not some of the best classes I've had is when I got a special like, set aside. Like, the professor clearly saw that I was interested in some aspect of a thing and then, um, a few in mind and one in particular, he said that, um, he kind of challenged me. So this outside of grades and all that, that kind of stuff that basically it's like reverse psychology. I don't, I don't think this can be done. And so I gave everything to do that particular thing. So this was happened to be in an artificial intelligence class. But I think that like, special treatment of taking students who are especially like excellent at a particular little aspect, Do you see their eyes light up? I I often think like maybe it's tempting for a teacher. I think you've already succeeded there? But they're actually signaling to you that like, you could really launch them on their way. Um, and I don't know, that's too much to expect from teachers, I think to pay attention to all of that because it's really difficult. But I, I just kind of remember who are the biggest, the most important people in the history of my life of education. And it's those people that who really didn't just like inspire me where their awesomeness, which they did, but also just they pushed me a little like give you a little [/INST] push </s><s>[INST] and that requires focusing on the quote unquote. Excellent. Yes. In the class. [/INST] Yeah, I think what's important though is teachers to have the perspective that they don't know who's gonna be excellent at something before they give out the activity. Exactly. And in our camp classes that we ran, um, sometimes students would finish ahead of other students and we would say to them, can you write a question that's like this, but different? Um, oh, and, and over time we encourage them to like extend things further. I remember we were doing one activity where kids were working at the borders of a square and how big this border would be in different case sizes and one of the boys came up at the end of the class and said, I've been thinking about how you do this with the pentagon? and I said, that's fantastic. How do you, what does it look like the pentagon? Go? You know, find out see if you can discover. So I didn't know he was going to come up and say that and I didn't have in my head like this is the kid who could have this extension task, but you can still do that as a teacher. Um, when kids get excited about something or they're doing well and something have them extend it, go further. It's great. </s><s>[INST] And then you also like, this is like teacher and coach. You could say it in different ways to different students. Like for me, the right thing to say is uh, almost to say, I don't think you could do this. This is too hard. Like that's what I need to hear because it's like, no, I, you know, there's an immediate push, but with some people, if they're a little bit more, I mean it all has to do without bringing how your genetics is, they might be much more that might break them. Yeah, [/INST] that might break them. </s><s>[INST] So you have to be also sensitive to that. I mean teaching is really difficult. It's really difficult for this very reason. It is. So, um, what is the best way to teach math to learn math at those early few days when you just want to capture them, [/INST] I do something. Actually, there's a video of me doing this on our website that I love when I first meet students and this is what I do. I show them a picture, this is the picture I show them and it's a picture of seven dots like this. And I share it for just a few seconds and I say to them, I would like you to tell me how many dots there are but I don't need to count them. I went to group the dots and I show it them and then I I take it away before they even had enough time to count them. And then I asked them, so how did you see it? And I go around the room And amazingly enough there's probably 18 different ways of seeing these $7. And so I asked people tell me how you grouped it and some people see it as like an outside hole with a center dot, Some people see like stripes of lines, some people see segments And I collect them all and I put them on the board and at the end I say look at this, we are a class of 30 kids. And we saw these seven dots in 18 different ways. There's actually a mathematical term for this? It's called group appetizing </s><s>[INST] group appetizing. Yeah, like [/INST] it's kind of cool. So turns out though that how well you group of guys predicts, How are you doing maths? </s><s>[INST] Is it uh Raw talent or is this just something that you can develop. [/INST] Think it's wrong. I don't think you're born group appetizing I think. But some kids have developed that ability if you like and you can learn it, you can. So this to me is part of how wrong we have maths that we think to tell whether our kids good at maths, we're going to give them a speed test on factors and multiples. But actually seeing how kids group dots could be a more important assessment of how well they're going to do math anyway, I diverge what I like to do. So when I started with kids is show them, I'm gonna give you math problems. I'm going to value the different ways you see them and turns out you can do this kind of problem asking people how they group dots with young Children or with graduate students and it's engaging for all of them </s><s>[INST] is uh you talk about creativity a little bit and flexibility in your book, limitless. What's the role of that? So it sounds like there's a bit of that kind of thing involved in group appetizing. [/INST] Yeah, </s><s>[INST] I love this term. So what's what what would you say is the role of creativity and flexibility in the learning of math? [/INST] I think what we know now is that what we need for this 21st century world we live in is a flexible mind. It's schools should not really be about teaching kids particular methods but teaching them to approach problems with flexibility being creative thinking creatively is really important. So people don't think the words maths and creativity come together. But I that's what I love about maths is the creative different ways you can see it. And so helping our kids. There's a book I like a lot, but I've been by physicists, you probably know this book could elastic, you might know it and it's about how we want elastic mind, same kind of thing, flexible creative minds. And schools do very little on developing that kind of mind. They do a lot of developing the kind of mind that a computer now does for </s><s>[INST] us, memorization, [/INST] memorization, doing procedures, a lot of things that we spend a lot of time in school on in the world when kids leave school, a computer will do that and better than they will. But that creative, flexible thinking, we're kind of a ground zero at computers. Being able to engage in that thinking maybe we're a little above ground zero. But um the human brain is perfectly suited for that creative, flexible thinking. That's what humans are so great at. So I would like to balance the shift in schools, maybe you still need to do some procedural kind of thinking, but there should be a lot more of that creative, flexible thinking </s><s>[INST] and uh what's the role of other humans in this picture. So collaborative learning. So brainstorming together the creativity as it emerges from the collective intelligence of multiple here. [/INST] Super important in um we know that also helps develop your brain, that social side of thinking. And I love mathematics collaboration where people build on each other's ideas and they come up with amazing things as you taught 100 students calculus at stanford recently undergrads and we taught them to collaborate. So these students came in stanford and most of them were against collaboration in math. </s><s>[INST] This is before Covid in person. [/INST] Yeah, it was just before Covid hit, it was 2019 and the </s><s>[INST] summer you said they're against. Uh [/INST] it's really interesting. So they had only experienced maths individually is in a kind of competitive individual way and if they had experienced it as group work, it has been a bad experience, like maybe they were the one who did it all and the others didn't do much. So they were kind of against collaboration, they didn't see any role for it in maths and we taught them to collaborate and it was hard work because as well as the fact that they were kind of against collaboration, they came in with a lot of like social comparison thinking, so I'm in this room with other stanford undergrads and they're better than me or so when we set them to work on a mouse problem together, the first one was kind of a disaster because they put all like they're better than me there faster than me. They came up with something I didn't come up with. So we taught them to let go of that thinking and to work well together. And one of the things we did, we decided we wanted to do a pre and post test at the end of this teaching, it was only four weeks long but we knew we didn't want to give them like a time test of individual work. So we gave them an applied problem to do at the beginning and we gave them to do in pairs together and we gave each of them a different colored pen and said work on this activity together and keep using that pen. So then we had all these pieces of student work and what we saw was they just worked on separate parts of the paper. Uh so there's little like red pen section and a green pen section and they didn't do that well on it even though it was a problem that middle or high school kids could do but it was like a problem solving kind of problem and then we gave them the same one to do at the end, gave them the same colors. And it actually they had learned to collaborate and not only were they collaborating the second time around but that boosted their achievement and the ones who collaborated did better on the problem, collaboration is important having people and what was so I opening for these undergrads and they talked about it in lovely ways was I learned to value other people's thinking on a problem and I learned to value that other people saw it in different ways. Um it was quite a big experience for them that they came out thinking, you know, I can do maths with other people, people can see it differently, we can build on each other's way ways of thinking. </s><s>[INST] I got a chance to, I don't know if you know who Daniel Kahneman is, I got a chance to interact with him and like the first because he had a few but one famous collaboration throughout his life uh with diversity and just like, you know, he hasn't met me before uh in person, but just the number of questions he was asking just a curiosity. So I think one of the skills, the collaboration itself is a skill. And remember my experience with him was like, okay, I get why you're so good at collaboration because he was just extremely good at listening and genuine curiosity about how the other person thinks about the world sees the world. And then together he, he pulled me in that particular case, he doesn't know in particular like that much about autonomous vehicles, but he kept like asking all these questions and then like 10 minutes in, we're together trying to solve the problem of autonomous driving and like, and that, I mean that's really fulfilling, that's really enriching, but also in that moment made me realize it's kind of a skill because you have to kind of put your ego side, put your view of the world aside and try to learn how the other person [/INST] and the other thing you have to put aside is this social comparison thinking, if you are sitting there thinking, wow, that was an amazing idea, he's so much better than I am. That's really gonna stop you taking on the value of that idea. And so there's a lot of that going on between these stanford students when they came and yeah, trying to help them let go of that. </s><s>[INST] one of the things I've discovered just because being a little bit more in the public eye, how rewarding it is to celebrate others [/INST] and </s><s>[INST] how much is going to actually pay off in the long term. So this kind of silo thinking of like I want to prove to a small set of people around me that I'm really smart and do so by basically not celebrating how smart the other people are. That's actually may be short term, it seems like a good strategy, but long term it's not. And I think if you practice at the student level and then at the career at every single stage, I think that's ultimately, [/INST] I agree with you. I think that's a really good way of thinking about it. </s><s>[INST] You mentioned textbooks, you didn't say it, uh you know, um maybe textbooks isn't the perfect way to teach mathematics, but I I love textbooks, There's they're like pretty pictures and they smell nice and they open. I mean I talked about like physical, some of them my greatest experiences have been just like, oh like because they're really well done when we're talking about basic like high school calculus biology. Chemistry. Those are like those are incredible. It's like Wikipedia but with colour. And uh you must have [/INST] seen some good textbooks that they had pretty pictures in color. </s><s>[INST] Yeah, I remember I guess it was very very standard like ap ap calculus ap biology. Ap chemistry. I felt those are like some of the happiest days of my life in terms of learning was high school because it was, it's very easy. Honestly it felt hard at the time. But you're basically doing a world wind tour of all the science. Yeah. Without having to pick, you do like literature, you like Shakespeare and calculus. Biology, Physics. Uh Chemistry, what else? Anatomy, physiology, computer science. Without like nobody's telling you what to do with your life. You're just doing all of those things. [/INST] That's a good thing you're right. </s><s>[INST] But I remember the text books weren't, I mean maybe I'm romanticizing the past but I remember they weren't there pretty good. But so you think what role do you think they play still in like in this more modern digital age. What what's the best materials would wish to do these kinds of educations. [/INST] Well I'm intrigued that you have such a good experience with textbooks. I mean I can remember loving some textbooks I had when I was learning and I loved books. I love to pick up books and look through them. But a lot of maths textbooks are not good experiences for kids. They um we have a video on our website of the kids who came to our camp and one of the students says in maths, you have to follow the textbook. The textbook is kind of like the bible, you have to follow it And every day it's slightly different. Like on Monday you do 2.3.2 and on Tuesday you do 2.3.3 and on Wednesday and you never go off that that's like every single day and that's not inspiring for a lot of the kids. So one of the things they loved about our camp was just that there are no books, even though we gave them sheets of paper instead, they still felt more free because they weren't just like trotting through exercises exercises. So um </s><s>[INST] like what a textbook allows you is like your the very thing you said they might not like the 2.2 point 32 point if it feels like you're making progress and like its little celebrations because you do the problem and it seems really hard and you don't know how to do it and then you try and try and then eventually succeed and you make that little step further progress and then you get to the end of a chapter and you get to like closure. You're like all right I got that figured out and then you go on to the next chapter. [/INST] I can see that. I mean I think it could be in a textbook. You can have a good experience with the textbook. But what's really important is what is what is in that textbook. What are you doing inside it? And I mean I grew up in England and in England we learn maths. We don't have this separation </s><s>[INST] of algebra and [/INST] geometry and I don't think any other country apart from the U. S. Has that. But I look at kids in algebra classes where they're doing algebra for a year and I think I would have been pretty bored doing that. Um </s><s>[INST] But can we can we analyze your upbringing real quick? Um Why do british folks call mathematics maths? Why is it the plural? Is it is it because of everything you're saying or is a bunch of sub disciplines? Yeah [/INST] I mean mathematics is supposed to be that ah the map the different maths that you look at whether you think of that as topics like geometry and probability or or I think of it as maths is just multidimensional lots of ways. But that's why it was called mathematics and then it was shortened to maths. And then for some reason it was just math in the U. S. But to me math has that more singular feel to it and there's an expression here which is do the math which basically means do a calculation. That's what people mean by do the math. So I don't like that expression because no math could be anything doesn't have to be calculation. And so yeah I like maths because it has more of that broad field to </s><s>[INST] it. Yeah I love that maths kind of emphasizing the multidimensional a variety of different different disciplines different approaches. Yeah Okay. What but outside of the text book what do you see like broadly being used? You mentioned Sebastian thrown and moocs online education do you think that's an effective so it can [/INST] be I mean online having great teachers online obviously extends those teachers too many more people and that's a wonderful thing. Um I have quite a few online courses myself. I got the bug working with Sebastian when he was had released his first book and I thought maybe I could do one in maths education and I didn't know if anybody would take it. Um remember released to get that first summer and it was a free online class and 30,000 maths teachers took it that first summer and they were talking about it with each other and sharing it and it was like took off in fact it was that mook that caught got me to create U. Cubed with Cathy Williams who is the co founder because people took the book and then they said ok, what now I I finished what, what can I have next? And so that was where we made our website but um so yeah, I think online education can be great. I do think a lot of the moocs don't have great pedagogy there just a talking head and you can actually engage people in more active ways even in online learning. So I learned from the udacity principal when I was working udacity never to talk more than like five minutes and but then and then to ask people to do something so that's the sort of pedagogy of the online classes I have is a little bit of presenting something and then people do something and there's a little bit more because I think if you have a half hour video you just, I am </s><s>[INST] switch off [/INST] and start doing other things. </s><s>[INST] So the way you as he did it is like 5, 10 minutes, like a bit of teaching and then with some visual stuff perhaps and then there's like a quiz um you answer a question yeah that's that's yeah, that's really effective. You mentioned you cube so what's the mission, what's the goal, you mentioned how it started but what's uh um yeah where you at now and what do you, what's your dream with it or what are the kind of things that people should go and check out on there. [/INST] Yeah we started U cubed, I guess. It was about five years ago now and we've had over 52 million visitors to the site. So I'm very happy about that. And our goal is to share good ideas for teaching with teachers, students, parents in maths and to help we have a sub goal of a raising maths, anxiety that's important to us, but also to share maths is this beautiful creative subject. And um it's been really great. We have lessons on the site, but one of the things, one of the reasons I thought this was needed is there's a lot of knowledge in the academy about how to teach maths Well, loads and loads of research and journals and lots of things written up, but teachers don't read it, they they don't have access to it, they're often behind pay walls, they they're written in really in accessible ways, so people wouldn't want to read them or understand them. So this actually is a big problem. You have this whole industry of people finding out how to teach. Well not sharing it with the people who are teaching. So, um that's why we made u cubed and instead of just putting articles up saying, here's some things to read about how to teach. Well, we translated what was coming from research into things that teacher could use. So lessons there were videos to show kids and um there were tips for parents, there were all sorts of things on the site, and it's been amazing as we have, we took inspiration from the week of code, which got teachers to focus on coding for a week and um we have this thing called the week of inspirational maths and we say just try it for a week, just just give us one week and try it and see what happens. And so it's been downloaded millions of times. Teachers use it every year, they start the school year with it, and what they tell us is, it was amazing. The kids lights were on, they were excited, they loved it, and then the week finished and I opened my textbooks and the lights went out and they were not interested, </s><s>[INST] but getting that first inspiration is still powerful. It [/INST] is, I I wish, I mean my, what I would love is if we could actually extend that for the whole year, we're a small team at stanford and we're trying to keep up with the great things to put on the site, um we haven't the capacity to produce these creative visual mouse task for every year group for every day, but I would love to do that. </s><s>[INST] How difficult is it to do? I mean to come up with visual formulations of these big, important topics you need to think about in a way that, you know, that you could teach, [/INST] We can do it. We actually, we went from the week of inspirational mouths and we made K-8 mouths books with exactly that big ideas rich activities, visuals. We just finished the last one. We've been doing it for Five years and it's been exhausting and we just finished. So now there's a whole K8 set of books and they're organized in that way. These are the big ideas here are rich deep activities. Um, they're not though what you can do every day for a year there. So some teachers use them as a supplement to their boring textbook and some people have said, okay, this is the year, this book tells us what the year is and then we'll supplement these big activities with um, so they're being used and teachers really like them and I'm really happy about them. I just always want more. And I guess one of the things I would like for you cubed one of my personal goals is that every teacher of maths knows about you cube at the moment. Um, A lot of teachers who come to us are really happy they found it, But there's a lot of other teachers who, I don't know that </s><s>[INST] I hope this helps. Yeah. From a student perspective and not in the classroom, but at home studying and you know, is there some advice you can give on how to best study mathematics. So what's the role of the students outside the classroom. [/INST] Yeah, I think one thing we know is a lot of people when they review material, whether it's maths or anything else don't do it in the best way? I think a problem a lot of people have is they read through maybe a teacher's explanation or way of doing maths and it makes sense and I think I've got that and they move on. Um, but then it's not until you come to try and work on something and do a problem that you actually realize you didn't really understand, It just seemed to make sense. So I would say this is also something that neuroscientists talk about to keep giving yourself questions is a really good way to study rather than looking through lots of material. It's always like giving yourself lots of tests is a good way to actually deeply understand things and know what you do and you don't </s><s>[INST] understand. So would the questions be in the form of the material you're reviewing is the answer to that question or is it almost like beyond its the polygon thing you mentioned from square, is it almost like I wonder what is the bigger picture always kind of asking of like houses extended and so on [/INST] that that that would be great. And it's a similar, I mean a question I get asked a lot is about homework, what this is a good thing for kids do for homework. And one of the recommendations I give is to not have kids just do lots of questions for homework, but to actually ask them to reflect on what they've learned, like what was the big idea you were, were you learned today or what did you find difficult? What did you struggle with? What was something that was exciting? Um then kids go home and they have to kind of reflect in a deeper way a lot of times, I don't know if you had these experiences of math student, Lots of people do, kids are going through maths questions, they're successful, they get them right, but they don't even really know what they're about. And a lot of kids go through many years of maths like that, doing lots of questions, but that really knowing what even the topic is or what it's about, what it's important for. So having students go back and think at the end of the day, what was the big idea from this maths lesson? Why is it important? Where would I find that in real life? Those are really good questions for kids to be thinking about. </s><s>[INST] It's probably for everybody to be thinking about. I think most of us go through life never asking like the bigger question almost like, you know, those like layers of why questions that kids ask when they're very young, we need to keep doing that, you know, like what that's the, you know, whatever the term is, you call first principles, thinking some people call it that, which is like, why are we doing it this way? So 1 1 nice thing is to do that because there's usually a good answer. Like the reason we did it this way is because it works for this reason. But then if you want to do something totally novel, you'll say, well we've been doing it this way um, because of historical reasons, but really this is not the best way to do it. There might be other ways and that's how invention happens. And then you get, you know, that's really useful in every aspect of life. Like choosing your career, choosing your, I don't know where you live, who you're like romantic partners, like everything, everything. And I think it probably starts doing that in math class. You'd be good [/INST] if we started doing. </s><s>[INST] I want, I mean, I wonder, I probably didn't do very much of that for most of my education asking why except for later, much later in the subjects on like grad school when you're doing research on them. When your first task of doing something novel using this or solving a problem really outside the classroom they have to publish on is the first time you think, wait, why are these things uh, interesting useful, which are the things that are useful and yeah, I guess that was that would be nice if we did that much earlier that the quest of invention. [/INST] Yeah. Yeah. I mean, one of the sad pieces of research data I think about is the questions kids ask. Um, in school goes down like a linear, uh, you know, progression from in the early years, you can't stop kids asking those questions, but they learn </s><s>[INST] not to ask the questions. I think you told somewhere about an early memory you had in your own education where you asked the question or maybe that was an example you gave, but it was shut down. [/INST] Oh yeah, you've listened to something I said. Yeah, </s><s>[INST] I remember where it was, something it caught me. [/INST] Yeah, I remember it really vividly. </s><s>[INST] Can you tell the memory? [/INST] Yeah, I was it's funny. I can remember. It must have really impacted me in that moment because you know how there's lots of hours of school you don't remember at all. But anyway, um I remember where I was sitting and everything. I was in high school maths class, although they don't call it in England. And um the teacher said, and it was like the first class of this teacher's class and he said, ask if you have any questions. So at one point I put my hand up and I said, I have a question and he said something like that's your question. Um I was like, okay, I'm not asking any more questions. </s><s>[INST] That's hard in a way where you didn't want to you the lesson you learn from that. I'm not gonna [/INST] ask. That was absolutely that I asked, that's the last question I'm asking. And I was, yeah, he was the chair of the maths department. I remember that really well. So uh, maybe because of that experience, One of the things we encourage when we teach kids is asking questions and we value it when they ask questions, we put them up on walls and celebrate. And </s><s>[INST] um, it's funny because I wish there was a feedback signal because he probably to put a positive spin on it. He probably didn't realize the negative impact he's had at that moment, right? If he only knew, see this is probably when you're more mature and grad school had an amazing professor named Ali Shaka fondi in computer science and he would get you encourage questions, but then he would tell everybody how dumb their questions are. But it was, it was done. I guess if you show if you say it with love and respect behind it, then it's more like a friendly humorous encouragement for more questions. It's an art, right? That too, right? And it's very hard. You have to time it, right? Because that's probably that kind of humor is probably better for when you're in grad school versus when you're in the early education, right? [/INST] Well, and I guess kids or young people get whether somebody's doing it to be funny or you know, has it? I mean, this is why I teach you so hard, even your tone can be impactful. </s><s>[INST] It's so sad because like uh for that particular human, the teacher, you just had a bad day in one statement can have a profound negative impact. [/INST] I know sadly that maths there's a lot of maths teachers who have that kind of approach and they I think they're suffering from the fact that they think people are math people not math people and that comes across in their teaching. </s><s>[INST] But on the flip side one positive statement keep them going. [/INST] That's right, that is the flip side of that. And I myself had one teacher who was really amazing for me in maths and she kept me in the subject. </s><s>[INST] What who was she? She [/INST] was, her name was mrs marshall. Yeah Um she was my a. Level maths teachers. So I was in in England you do lots of subjects to your 16 and then you choose like three or 4 subjects. So I had chosen maths and you go to high levels probably equivalent more to a master's degree in the U. S. Because you have more specialist. But anyways she was my teacher and for the first time in my whole career in maths she would give us problems and tell us to talk about them with each other. And so here I was sitting there like 17, talking with friends about how to solve a mouth problem and that was it. That was the change that she made. But it was profound for me I because like those calculus students, I started to hear other people's ways of thinking and seeing it, we would talk together and come up with solutions and I was like that was it, that changed math for me. So </s><s>[INST] it wasn't some kind of personal interaction with her, it was more like she uh she was the catalyst for that collaborative experience. [/INST] I mean, yeah, the many ways teachers can inspire kids, I mean sometimes it's a personal message, but it can be your teaching approach that changes maths for kids, </s><s>[INST] you know, cal Newport, he uh he wrote a book called Deep Work and he's a mathematician because theoretical computer scientist and he talks about the kind of the focus required to do that kind of work. Is there something you can comment on? You know, we live in a world full of distractions that that seems like one of the elements that make studying and especially the studying of subjects that require thinking like math does difficult. Is there something from a student perspective from a teacher perspective that encourages deep work? You can come [/INST] Yeah, I think giving kids really inspiring deep problems and we have some on our website is a really important experience for them, um even if they only do it occasionally, but it's really important that they actually realize I I do give a problem out off, I'm gonna working with teachers and I say to them all right, I'm going to check in with you after an hour and they were like an hour, they think it's shocking. And then they work on this problem and after an hour I said, okay, how are we doing there? Like an hour has gone by, </s><s>[INST] how [/INST] is this possible? And so everybody needs those rich, deep problems. Most kids go through their whole maths experience of however many years, never once working on a problem in that kind of deep way. So I, the undergrad class I teach at stanford, we do that, we work on these deep problems every session and the students come away going, okay, I never want to go back to that mouths relationship I had where it was just all about quick answers. I I just don't want to go back to that. And so we can all, all teachers can incorporate those problems in their classrooms, maybe they don't do them every day, but they at least give kids some experience of being able to work slowly and deeply and to go to deeper places and not Be told they've got five minutes to finish 20 questions. </s><s>[INST] Well part of it is also just the, the exercises sitting there maintaining focus for prolonged periods of time, that's not often. I mean that's the skill is a skill That, that also could be discouraging. Like if you don't practice it, just sitting down for 10 minutes straight and maintaining deep focus could be exceptionally challenging. Like if you're really thinking about a problem and I think it's really important to realize that that's a skill that you can Just like a muscle you can build, you can start with five minutes and goes to 10 minutes to 30 into an hour. And and to be successful, I think in certain subjects like mathematics you want to be able to develop that skill, otherwise you're not going to get to the really rewarding experience of solving these problems. Definitely. [/INST] There was a survey done of kids in school where they were asked, how long will you work on a maths problem before you give up and decide it's not possible to solve it? And the result on average across the kids was two minutes. </s><s>[INST] Yeah, so that's a that's a bad sign but that's it was a powerful sign that uh they need to learn to not give up so quickly. Yeah, we mentioned offline because we've been talking so much about visualization, Grand Sanderson through Lawan Brown, so he's inspired millions of people with the kind of uh exactly the kind of way of thinking that you've been talking [/INST] about, which I love </s><s>[INST] his work converting sort of mathematical concepts into visual uh like visually representing them, exploring them in ways that help you illuminate, like the concepts. Um what do you think is the role of that? So he uses mostly programmatic visualization. So that's the thing I mentioned where there's like animations created by writing computer programs um like what do you think, how scalable is that approach, but in general, what do you think about his approach? I [/INST] think it's amazing. I should work with him, I can share some of our visuals and he can make them in that amazing way. Um </s><s>[INST] so part of his storytelling, part of his, like uh it's creating the visuals and then weaving a story with those visuals that kind of builds, like there's also, I mean there's also drama in it, You start with a small example and then you kind of all of a sudden there's a surprise, it really, I mean it makes you fall in love with the concept, he does talk about that, his senses, like some of the stuff he doesn't feel like he's teaching like the core curriculum, which is something, you know, he sees himself as an inspirational figure, but because I think it's too difficult to kind of convert all of the curriculum into those elements and [/INST] probably you don't need to, I mean you if people get to experience mathematical ideas in the way that he shares them, um that will change them and it will change the way they think and maybe they could go on to take some other mathematical idea and make it that beautiful. </s><s>[INST] Well he does that uh there's a, he created a library called Madam and he opened sourced it and that library is the uh people should check it out, it's written in python and he uses some of those same elements, like it allows you to animate equations and animate little shapes like people that you know, he has a very distinct style in his videos and what that resulted in, even though from a software engineer perspective the code he released is not like super well documented are perfect, but him releasing that. Mhm Now there's all of these people educating it and the cool to me personally, the coolest thing is to see like people, they're not, you know, don't have like a million subscribers or something if they have just a few views in the video, but it just seems like the process of them creating a video where they teach is like transformative to them from a student perspective, it's the old Feinman thing. The best way to learn is to teach and then him releasing that into the wild is yeah, it shows that that impact. [/INST] Absolutely. I think just giving people that idea that you can do that with maths and other subjects there bound to be people all around to can create more, which is cool. </s><s>[INST] Yeah, I definitely. So I recommend people do like javascript or python, you can, you can build like visualizations of most concepts in high school math, you can do a lot of kinds of visualizations and doing that yourself. Plus if you do that yourself, people really love it, people actually, people love visualizations of matter because they mean something in us that loves patterns, loves figuring out difficult things in the patterns in there that are unexpected in some way. [/INST] Have you ever noticed that hotels always filled with patterns? I was just noticing at the hotel and now all of their carpets are patterned carpets and then they have patterns on the walls. So </s><s>[INST] yeah, we humans love the symmetry and patterns, the breaking of symmetry and patterns. Yeah, and it's funny that we don't see mathematics is somehow intricately connected to that, but it is right. [/INST] I mean, that's one of the perspectives I love students to take is to be a pattern seeker in everything in Yeah, certainly in all of maths, I mean, you can think of all of maths as a kind of subject of patterns and not just visual patterns, but when you think about multiplying by Five and the fact you can, you know, if you if you're multiplying 18 times five, you can instead think of nine times 10, that's a pattern that always works in mathematics. You can have a number of double the number. And so I just think there are patterns everywhere and if kids are thinking their role is to see patterns and find patterns, it's really exciting. </s><s>[INST] What do you think about like MIT open courseware and the release of lectures by universities? [/INST] I think it's good. I think it's good. I think the that is what started the mook I did was using that platform. </s><s>[INST] You ultimately think like the Udacity models is a little bit more effective than just a plain two hour lecture. [/INST] I think there's definitely, you can bring in good pedagogy into online learning. And I think the idea of putting things online so that people all over the world can access them, it's great. I don't think the initial excitement around moocs sort of democratizing education and make it more equal, um, came about because they found that the people taking moocs tended to be the more privileged people. So that was, I think there's still something to be found in that there's still more to be done to help that online learning reach those principles. But um, definitely, I think it's, it's a good invention and I have an online class, that's for kids that's little free </s><s>[INST] class, that gives the topic, [/INST] it's called How to learn maths. Um, it shows maths is this visual, creative subject and it shares mind certain some brain science and um, kids, you take it do better in math class. We've studied it with like randomized controlled trials and Given it to middle school kids and other middle school kids who don't take it, but are taught by the same teachers. So their teachers are the same and the kids who take the online class end up 68% more engaged in their mouths class and do better at the end of the year. So That's a little succession, 15 minute class and it changes kids, maths relationship. So it is true that we can do that with some words that aren't, you know, it's not a huge change to the education system. </s><s>[INST] Do you have advice for young people? We've been talking about mathematics quite a bit, but in terms of their journey through education through their career choices through life, maybe middle school, high school undergrad students how to live a life they can be proud of. [/INST] I think if I were to give advice to people, especially young people, my advice would be to always, it sounds really corny, but always believe in yourself and know that you can achieve because although that sounds like obvious, of course we want kids to know that they can achieve things. I know that millions of kids are in the school system have been given the message. They cannot do things and adults too. They have the idea, oh, I did ok in this, I went into this job because those other things I could never have done okay in, so actually when they hear, hey, maybe you could do those other things, even adults think, you know, maybe I can and they go back and they encounter this knowledge and they re learn things and they change careers and amazing things happen. So, for me, I think that message is really important. You can learn anything. Scientists try and find a limit. They're always trying to find a limit like how much can you really learn? What's the limit to how much you can learn and they always come away not being able to find it. People can just go further and further and further and that is true of people born with brain um you know, areas of their brain that aren't functioning well that have what we call special needs, some of those people also go on to develop and do amazing things. So I think that really experiencing that, knowing that feeling, not just saying it, but knowing it deeply you can learn anything is um um something I wish more people would have </s><s>[INST] actually also applies when you've achieved some of of success to what I find like in my life with people that love me. When you achieve success, they keep celebrating your success and they want you to keep doing the thing that you were successful at, as opposed to believing in that you can do the something else something, but whatever your heart says to do. And one of the things that I realized the value of this uh you know quite recently was just had to say is how important it is to seek out when you're younger to seek out mentors to seek out the people like surround yourself with people that will believe in you, it's like a little bit is on you, it's like you don't get that. Um sometimes if you go to Grad school, you think you kind of land on a mentor, maybe you pick a mentor based on the topic they're interested in. But the reality is the people you surround yourself with, they're going to define your life trajectory. So select people are really [/INST] true and get away from people who don't believe don't you? </s><s>[INST] Sometimes parents can be that loves you deeply, but they be, you know, they set it's the math thing we mentioned, they might set certain constraints on the beliefs that you have. And so in that if you're interested in mathematics, your parents are not that interested in. Don't listen to your parents on that one dimension. [/INST] Exactly, yeah. And if people tell you you can't do things, you have to hear from other people who who believe, you know, I think you're absolutely right about that. So sad. The number of people who have had those negative messages from parents in my limitless Mind book, I interviewed quite a few people have been told they couldn't do math. Sometimes my parents sometimes by teachers and fortunately they had got other ideas at some point in their life and realized there was this whole world of mathematical thinking that was open to them. So it's really important that people do connect with people who believe in them. However hard that might be to find those people. </s><s>[INST] What do you hope the education system? Education in general looks like 10, 20, 500 years from now, Are you optimistic about this future? [/INST] Yeah, I definitely have hope there is change can happen in the education system in recent years. It's been microscopically slow and um but I do actually see change happening. Like we were talking earlier that Data science is now of course you can take in high school instead of Algebra two. And that's pretty amazing because that content was set out in 1892 and hasn't changed since then. And so now we're actually seeing a change in the content of high school. So I'm amazed that that's happening and very happy it's happening. But so change is very slow in education usually, but when you look ahead and think about all that we know and all that we can offer kids in terms of technology, you've got to think that 100 years from now education will be totally different to the way it is now. Maybe we won't have subject boundaries anymore because those don't really make much sense. </s><s>[INST] It's interesting to think how certain tools like programming, maybe they'll be deeply integrated in everything. [/INST] We think, yeah, you would think that all kids are growing up learning to program and create so um I just think, I mean the system of schooling we have now, people call it a factory model, it's not designed to inspire creativity and I feel like that will also change. People might look back on these days and think they were hilarious, but um maybe well in the future kids will be doing their own programming and they'll be able to learn things and find out things and create things even as they're learning. And um maybe the individual subject boundaries will go. Data science itself coming into the education system kind of illustrates that because people realize it doesn't really fit inside any of the subjects. So what do we do with it? Where does it go and who teaches it? So it's already raising those kind of questions and questioning how we have these different subject boundaries. </s><s>[INST] So you've seen data science be integrated into the curriculum? [/INST] Yes it's happening across the United States </s><s>[INST] as we speak. I wonder how they got initiated and how does change happen in the education system? Is it just a few revolutionary Like it [/INST] does. I think so. I think so. It's been an interesting journey seeing data science takeoff. Actually it um there was a mhm Course that was developed in 2014 by some people who thought data science was a good idea for high schoolers. And then after some kids took the course and nothing bad happened to them they went to college and people started to accept it more. And then this was a big piece of the change in California. The U. C. System communicated They sent out an email last year to 50,000 high school saying we now accept data science Kids can take instead of Algebra two. That's a perfectly legitimate college pathway. So that was like a big green light for a lot of schools who like wondering about whether they could teach it. So I think it happens in small spaces and expands so now </s><s>[INST] yeah, [/INST] then it goes viral, California's ahead. Um I think in creating courses and having kids go through it, but it's Suddenly when I last looked, there were 12 states that </s><s>[INST] we're allowing data [/INST] science as a high school course and I think by next year that would have doubled a more so change is happening </s><s>[INST] joe as I said, I think mathematics is uh, it's truly a beautiful subject and you having an impact on millions of people's lives by educating them by inspiring teachers to educate in the ways that you've talked about, in multidimensional ways, in visual ways. Um I think it's incredible. So you're you're spreading beauty to the world, so I really, really appreciate that you spend your valuable time with me today. Thank you for talking. [/INST] Thank you. It was really good to talk to you. </s><s>[INST] Thanks for listening to this conversation with joe bowler to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Albert Einstein. Pure Mathematics is the poetry of logical ideas. Thanks for listening and hope to see you next time [/INST] </s>
<s>[INST] so it's [/INST] you know, and he couldn't say what it was but he knew that that's what he wanted to eat and and so there was you know that it's it's it's like it isn't monolithic at all our cognition is is you know, first of all graded in certain kinds of ways, but also multi partite and there's many elements to it and things uh certain sort of partial competency still exists in the absence of of other aspects of these competencies. So this is what always fascinated me about what uh used to be called cognitive neuropsychology, you know, the effects of brain damage on cognition, but in particular this gradual disintegration part, </s><s>[INST] you know, I'm a big believer that the loss of human being that you value is as powerful as you know, first falling in love with that human being, I think it's all a celebration of the human being. So the disintegration itself to is a celebration of the way. [/INST] Yeah, yeah. And but just to say something more about the scientist and and the back propagation idea that you mentioned. Uh so in 19 82 Hinton had been there as a postdoc and organized that conference, he'd actually gone away and gotten an assistant professorship and then um there was this opportunity to bring him back. So Geoff Hinton was back on a sabbatical </s><s>[INST] san Diego [/INST] in san Diego and uh oh my heart and I have decided we wanted to do this, you know, we thought it was really exciting and um are the papers on the interactive activation model that I was telling you about had just been published and we both sort of saw huge potential for this work. And and and Jeff was there. And so the three of us uh started a research group which we call the PDP research group and several other people came Francis Crick who was at the Sock institute, heard about it from Jeff. Um and because Jeff was known among brits to be brilliant and Francis was well connected with his british friends. So Francis crick came </s><s>[INST] as a heck of a group of people [/INST] and uh several as possible Lenski um was one of the other postdocs. He was still there as a postdoc and a few other people. But anyway, yeah, Jeff talk to us about learning and how we should think about mhm. How, you know, learning occurs in a neural network. And he said the problem with the way you guys have been approaching this is that you've been looking for inspiration from biology to tell you how what the rules should be for, how the synapses should change the strength of their connections, how the connections should form. He said that's the wrong way to go about it. What you should do is you should think in terms of how you can adjust connection weights to solve problem. So you define your problem and then you figure out how the adjustment of the connection weights will solve the problem and Rummelhardt heard that and said to himself, okay, so I'm going to start thinking about it that way. I'm going to essentially uh imagine that I have some objective function, some goal of the computation. I want my machine to correctly classify all of these images and I can score that. I can measure how well they're doing on each image and I get some measure of law, error or loss. It's typically called in deep learning. And um I'm going to figure out how to adjust the connection weight, so as to minimize my loss or reduce the error. Uh and that's called, you know, gradient descent. And uh engineers were already familiar with the concept of gradient descent. Uh And in fact, um there was an algorithm called the delta rule that had been invented, Bye, a professor in the engineering electrical engineering department at stanford. Uh Woodrow, Bernie Woodrow and a collaborator named Hoff. I don't never met him anyway. So, so gradient descent in continuous neural networks with multiple neuron like processing units was already understood. Um for a single layer of connection weights, we have some inputs over a set of neurons. We want the output to produce a certain pattern, we can define the difference between our target and what the narrow network is producing, and we can figure out how to change the connection weights to reduce that error. So what Rummelhardt did was to generalize that, so as to be able to change the connections from earlier layers of units to the ones at a hidden layer between the input and the output. And so he first called the algorithm the generalized delta rule, because it's just an extension of the gradient descent idea. And interestingly enough, Hinton was thinking that this wasn't going to work very well. So Hinton had his own alternative algorithm at the time Based on the concept of the Bolsa Machine that he was pursuing. So the paper on the Bolster Machine came out in learning and bolster machines came out in 1985, but it turned out that back prop work better than the bolster machine learning algorithm. </s><s>[INST] So this generalist delta algorithm ended up being called back propagation. As you say, back [/INST] problem. And you know, probably that name is opaque to me, What does that mean? What it what it meant was that in order to figure out what the changes you needed to make to the connections from the input to the hidden layer. You had to back propagate the air signals from the output layer, through the connections from the hidden layer to the output to get the signals. That would be the air signals for the hidden layer and that's how Rummelhardt formulated it was like, well we know what the air signals are at the output layer. Let's see if we can get a signal at the hidden layer that tells each hidden unit what its air signal is essentially. So it's back propagating through the connections from the hidden to the output to get the signals to tell the hidden units how to change their weights from the input and that's why it's called back dropped. Yeah, but so it came from Hinton having introduce the concept of, you know, define your objective function, figure out how to take the derivative so that you can adjust the connection so that they make progress towards your goal. </s>
<s>[INST] I want to continue on the line. But first I have to ask like how did it feel to accomplish the grand goal? Oh my God. Okay. When you just stand back £1000 for reps, what if you like, [/INST] anybody can go watch the video online? Um, </s><s>[INST] 12 film by the way. Got me all like excited. [/INST] Oh well the movies, So we actually have the final footage of that. The good footage not posted yet. So it's literally just an instagram video or a phone video right now, there's only one online, </s><s>[INST] it's on your Youtube channel. It's dramatic. [/INST] Yes, it came out just time to the music perfectly to which is I listened to some odd music, which there's some reason behind that. Um, but </s><s>[INST] it's great. It's fooling footage. [/INST] There's a documentary that's, it's got a little slowed because of Covid because it's also a back story of the eagle and the dragon, my book about why I do kind of the things that I've done in my life or that's what I'm assuming the directors working on, I don't really have the control of the movie, right? But </s><s>[INST] but okay, but the videos incredible how do you feel, how [/INST] you feel? I started crying, it was overwhelming to have worked so intensely and so long and hard at something that pushed every ounce of me to the limit that and and I did it. So I'm getting a little emotional, I did exactly what I said, I was gonna fucking do, like and it was, it was overpowering, I mean I was just crying uncontrollably um just with a mixture of, I, I don't know what the mixture of emotions is hard to explain, um because it was the completion of something, it was a new phase of my, I </s><s>[INST] I mean there's so many things here, so one, you set an impossible goal and you accomplish that one, two is like on the broader humanity aspect, like how many humans in this world accomplish perfection in a particular direction required to do this. So like you're basically representing like uh one little, like, like little glimmer of excellence of the human spirit, [/INST] there's always more to understand this, this is a basic fundamental, you can always do better, There is no such thing as perfection, you can always, there is always more so anytime you read something, any amazing workout or accomplishment in life, could you have put more into it? Could even Yes, but here's the thing I left on my terms, I said this is it. I'm gonna work towards, I've been training for 30 years, I'm gonna do this thing that is like, I couldn't even say that I was gonna do it years before I'm going to do it and then I'm done, I didn't leave from an injury, I wasn't forced, I wasn't, I left on, I did exactly what I said, I went to a level that I, I left on my terms and that's unique because that's usually not the case. Usually you kind of either taper out or it doesn't matter. I'm talking like anything in life in general, right? Like um you taper out, you fail, you hurt, like you lose it like something, you know, your role into retirement, like </s><s>[INST] you have accomplished something truly great and you walked away in your own terms, is there a sadness completing something like that? Because it's in one perspective, the greatest thing you'll ever do and like when you accomplish such a great height in some sense, you have to face your mortality at that point. [/INST] So good question, but it is certainly not the greatest thing that I'll ever do, it's the greatest physical, there's always more Dude, the greatest yes. Uh but that was an expression of some of my values and the way that I want to live, it was a way of expressing it. So understanding that is hugely fundamental because we do see so many athletes get to the end of a career and then they fall into a depressive state and struggle with drugs, alcohol, depression and so on because they lost how they identified themselves and trying to figure out where to turn what to do. But a big central component of their identity is lost. So I knew that this was one way to express that and my grand goals have shifted their shifted to other outlets that allow me to express that. Like my company's Kabuki strength, I'm going to change the face of fitness as well as all the way through with its integration with clinical medicine and telemedicine. And you know, I got another five years before even people see what I'm working on five years in right now because I had to invent equipment have to develop methodologies that were talking to do this stuff that ground layer wasn't done to create a cohesive ecosystem of training methodology tied to the tools that we're using to the to the environment tied to the clinical practice assessment, tied to the the interaction between all those and how that actually needs to be refrained because so much of this is broken. Okay, so but there is sadness. I won't deny that. And the sadness comes in the singularity of focus that I had at that time. The being in the process, not necessarily do it, but like having being in this place that the rest of the world kind of fell away from me in those final faces to have something so intense to have a team around me, so focused on supporting and like he took me a couple months after that squad. I finally one day I woke up and I was like, oh welcome back to the world, like I was in such a mental fog like I was, it took me a while to climb out of that but that that space, that level of intensity and driving and living and being in that space, I do miss that but I also, I can't continue that. I couldn't like there's a point of like you push it so hard, the level to try to go from there is not acceptable for what you the impact that will have on your life or how you want to live and it was taking away those final, like I had to do extreme things and live in an extreme way to </s>
<s>[INST] Yeah, the the basic idea is you can't trust the populist the government itself because we're a bunch of idiots. I think [/INST] that's accurate. </s><s>[INST] Well, they're not wrong, but they're also they're also idiots. Power hungry idiots. [/INST] Yeah, I don't think there, I don't think everyone's an idiot. But I think there are enough idiots that it becomes a real problem if you're completely honest about everything you do and you know, you don't want to let everybody way in about things that are incredibly complex and that most people are ignorant of. </s><s>[INST] And on top of that there's this machine of intelligence, I've recently been reading a lot about the KGB about the FSB. So [/INST] I've </s><s>[INST] several things sparked my curiosity. So when I'm traveling to Ukraine and to Moscow and because of that, I started to sort [/INST] of </s><s>[INST] ask practical questions and myself just travel and all those kinds of things. So I started reading a lot about the KGB Jack Barsky has a book on this. I talked to him and you start to realize you probably looked into some of this, but you just start to realize the scale of surveillance manipulation. Now, a lot of them also talk about the incompetence of those organizations, the usual bureaucracy creeps in. But the point is it seems like there's no line they're not willing to cross for the purpose of gathering intelligence for the purpose of controlling people in order to gather intelligence. This [/INST] is M </s><s>[INST] I six FsB. There's not much information about the FSB or the G. R. U. But the KGB. So we're always like 20 years behind or more on the actual information. And so I started to wonder, so I have not officially been contacted by any intelligence agency, but I started to wonder, well, is there somebody I know that's doing that undercover [/INST] C. </s><s>[INST] I A. Or undercover FSB undercover anything [/INST] you probably do. </s><s>[INST] Have you asked yourself this question? [/INST] Yeah, for sure. Yeah. People that have been on my podcast. Yeah, for sure. </s><s>[INST] You think there was actually, I guess that may have been [/INST] 100% I would imagine, </s><s>[INST] would you know, [/INST] I have suspicions. </s><s>[INST] Do you care? [/INST] Is this I mean, it depends on what they're attempting to do, right? Like, if I felt like there was some deception involved and they were trying to use the podcast to manipulate a narrative in a deceptive way to trick people into things. Yeah, I would care. </s><s>[INST] But this is exactly what those are the kind of things they do. They do. Plant narratives. [/INST] I mean, I would imagine if you have the number one podcast in the world that people would want to infiltrate that. </s><s>[INST] Yeah, there's probably meetings in all major intelligence agencies about, okay, what are the large platforms? How do we do? How do we spread the message? [/INST] Yeah, Well, I mean, that's the thing that really emerged when we're talking about during my cancelation, that there's a clear there's no objective analysis of this in mainstream media. There's clear narratives that they're trying to push forward to whether it's to promote certain ideas or to diminish the power and reach of people who are Mavericks or people who who are, you know, who aren't connected to a system that you can't compromise. That's where it gets dangerous, right? Where it gets dangerous is when someone has the largest reach. But it's also completely detached and clearly uh is independent in the in the sense of um independent thinking has on whoever he wants. But </s><s>[INST] your mind can still be manipulated. [/INST] I guess. I can. I mean, I guess everybody can be manipulated a certain way I manipulate my own mind, I'm sure too. But I also spend a lot of time thinking about what I think, you know, I don't just accept things like, like the UFO thing, like I was all in for a while. And now I'm like, man, something smells fishy. Um and and then I'm thinking like, why here's my problem with the Ufo thing. I want it to be real so </s><s>[INST] bad. [/INST] that's my problem with it. I'm such a sucker, I want it to be real. So bad, you know? And that's that's a problem for me because I'm aware of it. And so then I stop and think about like what is what what is my desire for ufo truth to be exposed, because it's fun, you know, that's what it is. So I have a desire to for it to be </s><s>[INST] real. And I mean, I've talked to uh I talked to a bunch of folks about this, so those with connection with D. O. D. And they do draw lines between people that are full of shit and people who are not, there's a lot of people in the public sphere that they say are full of sh it and you have to kind of tell the difference. [/INST] Yeah, CNN watch them talk. </s><s>[INST] Well, I mean, on the Ufo [/INST] topic, </s><s>[INST] certain individuals that are like, okay, they're just like using this um In fact, like people who are not full of shit are often very quiet, [/INST] which </s><s>[INST] is why, you know, even bob Lazar is an interesting story because he was trying to be quiet for the longest time. Well, [/INST] he was worried about his own life according to bob and that's why he went public with it. And initially the first videos he did with George Knapp, they hid his identity, and then he felt like that wasn't enough, and he really needed to expose his own identity just to protect his life, </s><s>[INST] which is a [/INST] great story, you know. So you gotta go, well that seems so juicy. I want to buy into it and that's where I get nervous. </s><s>[INST] You don't know, You don't know who to trust. [/INST] Exactly. </s>
<s>[INST] You think the C. C. And W. H. O. Knew that masks work and we're trying to sort of imagine that people are kind of stupid and they would buy masks in excess if they were told that masks work. Is that like uh because this does seem to be a particularly clear example of mistakes made. You're asking me this question. [/INST] No you're not. What do you think lex </s><s>[INST] Well I actually probably disagree with you a little bit great. Let's do it. I think it's not so easy to be honest with the populist when the danger of panic is always around the corner. So I think the kind of honesty you exhibit appeals to a certain class of brave intellectual minds that it appeals to me. But I don't know from the perspective of wh oh I don't know if it's so obvious that they should Um be honest. 100% of the time with people. [/INST] I'm not saying you should be perfectly transparent and 100% honest I'm saying that the quality of your lies has to be very high and it has to be public spirit. There's a big difference between so I'm not I'm not a child about this. I'm not saying that when you're at war for example you turn over all of your plans to the enemy because it's important that you're transparent With 360° visibility. Far from what I'm saying is something has been forgotten and I forgot who it was who told it to me. There was a fellow graduate student in the um Harvard Math department and he said you know I learned one thing being out in the workforce because he was one of the few people who had had a work life in the department as a grad student. He said you can be friends with your boss but if you're going to be friends with your paws you have to be doing a good job at work. And there's an analog here which is if you're going to be reasonably honest with the population you have to be doing a good job at work as the surgeon general or is the head of the C. D. C. So if you're doing a terrible job you're supposed to resign. And then the next person is supposed to say look I'm not gonna lie to you, I inherited the situation. It was in a bit of disarray. Um, but I had several requirements before I agreed to step in and take the job because I needed to know, I could turn it around. I needed to know that I had clear lines of authority. I needed to know that I had the resources available in order to rectify the problem. And I needed to know that I had the ability and the freedom to level with the american people directly as I saw fit, all of my wishes were granted and that's why I'm happy here on monday morning. I've got my sleeves rolled up. Boy do we got a lot to do. So please come back in two weeks and then asked me how I'm doing that and I hope to have something to show you. That's how you do it. </s><s>[INST] So why is that excellence and basic competence? Missing [/INST] the big net. You see you come from multiple traditions where it was very important to remember things. The soviet tradition made sure that you remember the sacrifices that came in that war and the jewish tradition, We're doing this on Passover. Right, okay, Well, every year we tell one simple story. Well, why can't it be different every year? Maybe we could have a rotating series of seven story because it's the one story that you need. It's like, you know, you work with the men in black group, right? And it's the last suit that you'll ever need. This is the last story that you ever need. Don't think I fell for your neural Izer last time. In any event, we tell one story because it's the get out of dodge story. There's a time when you need to not wait for the bread to rise. And that's the thing, which is, even if you live through a great nap, you deserve to know what it feels like to have to leave everything that has become comfortable and, and unworkable. </s><s>[INST] It's sad that you need, you need that tragedy. I imagine to, uh, have the tradition of remembering. It's sad to, uh, to think that because things have been nice and comfortable means that we can't have great competent leaders, which is kind of the implied statement like, can we have a great leaders who take big risks, who are, who inspire hard work, who deal with difficult truth even though things have been comfortable. [/INST] Well, we know what those people sound like. I mean, you know, if for example, Jacko willing suddenly threw his hat into the ring, everyone would say, okay, right, Party's over. It's time to get up at 4:30 and really work hard and we've got to get back into fighting shape and </s><s>[INST] yeah, but Jacko is a very special. I think that whole group of people by profession put themselves in the way of into hardship on a daily basis and he's not, well, I don't know, but he's probably not going to be, well, could Jacoby president. Okay. [/INST] But it doesn't have to be Jacko right? Like in other words, if it was Kyle any or if it was um Alex Honnold from rock climbing, right? But they're just serious people. They're serious people who can't afford your B. S. </s><s>[INST] Yeah, but why do we have serious people that do rock climbing and don't have serious people who lead the nation? That seems because [/INST] that was a, those skills needed in rock climbing are not good during the big nap. And at the tail end of the big map they would get you fired. </s>
<s>[INST] Right? So take me through that day. If you could 1972 when you were going for the 68 kg freestyle wrestling gold, he scored 57 points. If I'm correct and had zero points scored on you. 57 0. So maybe take me through almost the details. What was your routine? What was your process? What was going through your mind, your thoughts of that day? [/INST] Yeah. First of all, it was it was quite a day because we wait in every day at that time and that and that and that. Yeah, we weighed in two hours before the start of the competition. And so that doesn't mean that you weighed in two hours for you russell because you didn't know whether you're gonna wrestle right away or later on. In fact, in that day, I don't think I wrestled until later on in the evening, so had all day to recover, but I didn't really need it anyway because it wasn't really pulling a whole lot of weight, but just, it was just interesting. </s><s>[INST] But what's in your mind, what were you thinking? Were you nervous? Were you, I [/INST] was confident. I was confident that </s><s>[INST] you knew you were going to win the gold. [/INST] Yeah, I knew I was going to win. But in reality, I'm not, I didn't know it from a cocky point of view. I only knew it because for the last 3.5 years I have been going to practice and I've been winning every practice and I hardly ever lose a takedown and if I lost, if I somebody scored on me, it was like when I went to bed I couldn't sleep until I figured it out. Or if I didn't figure it out, I would fall asleep and I would be what I would wake up with the answer of what I needed, why got scored upon. </s><s>[INST] So maybe now that you've won the gold, can you tell me in the practice room and somebody took you down? How do you take dan gable down in the practice room timing very difficult. [/INST] But somebody could because They were going for one move. All I wanted was one move. Whereas you know, if you can arrest somebody arrest the whole practice or half of practice for at least 10 15 minutes and they were maybe gonna score if they could work it in their mind, but they knew that was gonna be their victory. </s><s>[INST] So in the practice room, maybe you can educate me at that when you go for the olympic gold, you didn't want to allow any takedowns. So there's no such thing as working on some kind of weird position, a weak point to something. It's important to not let down on the takedown. [/INST] It's kind of like what we were saying before, if something happened and somebody scored on me in a certain way, I would go over that situation over that situation over again and I would come up with an answer and then I would actually test it. Maybe I wouldn't go right back the next day because I didn't want the guy to, you know, do not have some, I didn't want him to think that I was thinking about it all night, I didn't tell him, but maybe three days later when russell again, I actually had it figured out because it he wasn't able to or even if I was in on the take uh an offensive move and I got stopped and didn't score. You know, I had to go back and filter that, but it wasn't something that usually I couldn't solve, I could usually solve it. Let's go back to the olympic games. So I get up in the olympic in the morning and I'm not sure when the Waynes were, but I think I was probably a pound over uh you know, and that's about a half a kilo and £1.1 is a kilo because we wouldn't kilograms. </s><s>[INST] So what do you do with that? You [/INST] know, I just I just went over to the, had a sign of there and I got in the sauna and the and the funny thing was the morning of the of the of the finals, there was there was another athlete in Lassana mhm and american or no, it was a european, I don't I don't remember where she was from. </s><s>[INST] Not a Russian. [/INST] Well, you know what, I kind of think it was a plot </s><s>[INST] because it was a girl interesting [/INST] and she didn't have her top on, </s><s>[INST] wow [/INST] and that was pretty common and so, you know, it's kind of interesting you think back about it because there's some funny things that that go on behind the scenes in olympic games, in world Games any time when you have country against country and so there's some crazy stuff goes on. Did any of it affect you? Did you was there and well, I almost stayed too long in the sun. </s><s>[INST] Uh you lost a little [/INST] bit of, lost a little more. Yeah, but it didn't really bother me because I wasn't like, I wasn't like cutting a lot of weight. So so </s><s>[INST] your match against the Russian, the july yeah, july if he went on to be a two time world champion, the silver medalist as well, I mean this is an incredible wrestler. So what was going through your mind before stepping on the mat with that guy, you've beaten a bunch of wrestlers, haven't had a point scored on you and you're stepping on the mat against the Russian, who you said was really they picked the Soviets picked to beat you, [/INST] right? And I know why they picked him because he had a great attitude. So he wasn't just the typical artist, He was a good artist. He he hooked elbows like sausage alive and he's from that area of the world where they have some of those types of moves, but he was and he was a gore but by cutting down the weight? He lost some of that go. And I don't know if you gotta, that's a process, you gotta go about scientifically, you know, and so, you know, if you don't do it as an american, it can really hurt your performance. If you don't do it as a Russian, it can hurt your performance. And they already didn't really do that a lot where usually russell the weight where it was more like your weight. And so by cutting him down, you know, it may be slow to his belief down a little bit you </s>
<s>[INST] There were maybe a bunch of whims. Way too dramatic. [/INST] You have to 20 river crossings, but not just like a little stream, like a torrential river. There were some things where it was so steep that everyone was just climbing up and then you'd slide all the way down and climb up. And there were people who I met on the way out there who were saying, oh yeah, I did the Sahara 500 kilometer race. And those people were just sprawled out. A lot of them didn't finish. </s><s>[INST] So that was the hardest thing I've ever done. So how do you get through something like that? You just one step at a time, was there, did you remember? Is there a, is there dark moments or is it kind of all spread out thinly? [/INST] Yeah, you know, it wasn't really dark moments. I mean, there was one thing where I'd been running so long. I thought, well, I must almost be done. And then I found out I had like 15 miles more, but you know, I guess with all of these things, it's the messages that we tell ourselves. And so for me, it's like the message I always tell myself is quitting isn't an option. I mean, once in a while you kind of have to quit if like listen to the universe, if whatever you're gonna kill yourself or something. But for me, it was just, you know, whatever it takes, there's no way I'm stopping. And if I have to go up this muddy hill 20 times because I keep sliding, I'm sure there's a way. </s><s>[INST] It's probably a personality flaw. [/INST] Where does your love for chocolate come from? Oh, it's a great question. And in my, both of my Joe Rogan interviews, that's the first question that he asked. I'm glad that we can, we've gotten to that. So one, I've always loved chocolate and as, and I call it like a secret, but now that I keep telling, if you keep telling the same secret, it's actually no longer a secret. But I have a secret, which is not secret because I'm telling you on a podcast, life as a chocolate shaman. And so when I give keynotes at tech conferences, I say, I'm happy to give a keynote, but I want to lead a sacred cacao ceremony in the night. I'm actually, believe it or not, the official chocolate shaman of what used to be called exponential medicine, which is part of Singularity University. Now my friend Daniel Kraft who runs it, it's going to be called NextMed. And so, but I'll have to go back. As I was going to Berlin a lot of years ago, and I've always loved chocolate, but I was going to Berlin to give a keynote at a big conference called TOA, tech open air. And so when I got there, the first night, I was supposed to give a talk, but there had been some mix up. They'd forgotten to reserve the room. And so the talk got canceled and in the brochure, they had all these different events around Berlin that you could go to. And one of them was a cacao ceremony. And so I went there and actually met somebody, Viviana, who is still a friend by going in there. And there was this cacao ceremony and there were these kind of hippie dudes, and then everybody got the cacao. And then they said, all right, as they talked a little bit about the process, and then they said, all right, everyone just stand and kind of we're going to spin around in a circle for 45 minutes. And so I spun around in the circle for like 10 minutes, but then I had to leave because I had to go to something else. And so I thought that was that. But then I saw Viviana the next day and I said, well, how did the cacao ceremony go? And she showed me these pictures of all of these people, mostly naked, like it turned into chaos. And it was like, oh, and so let me get this straight. People drank chocolate. Then they spun around in a circle and something else happened. And anyway, so then two days later, I was invited to another cacao ceremony, which was also actually part of this TOA. And that was kind of more structured and it was more sane because it was part of this thing. And at the end of that, I had this, I thought, one, how, the greatest thing ever, a sacred cacao ceremony, like you drink chocolate milk and everybody's free. And I love that idea because I've never done drugs. I don't drink. But just part of it is because I think whatever, like I was saying with the ultra running, all of the possibilities are within us if we can get out of our own way. And then I thought, well, I think I can do a better job than what I experienced in Berlin. So I came back and I thought, all right, I'm going to get accredited as a cacao shaman. And this will shock you. Cause I know if you're going to be like a Rabbi or a priest or something, there's some process, but shockingly, there's no official process chocolate shaman. And so I thought, all right, well, you know, I'm just going to train myself and when I'm ready, I'm going to declare my chocolate shamanism. So I started studying different things. And when I was ready, I just said, now I'm at chocolate shaman, self-declared. self-declared. And so, but I do these ceremonies And I've, I've done them at tech conferences. I did one in Soho house in New York. I've done it at a place Rancho La Puerta in Mexico. And every time it's the same thing. Cause it just, if people are given a license to be free, just to, it doesn't matter and what I always say is you're here for a sacred cacao ceremony. But the truth is there's no such thing as sacred cacao and there's no sacred mountains and there's no sacred people and there's no sacred plants because nothing is sacred if we don't attribute ascribe sacredness to it, but if we recognize that everything is sacred, then we'll live different lives. And for the purpose of this ceremony, we're just going to say, all right, we're going to, we're going to focus on this cacao, which actually has been used ceremonially for 5,000 years. It has all these wonderful properties. Um, but is this people who get that license and then they're just free and </s>
<s>[INST] So the degree we invest in the threat of this. It should be into the policies that help with the adaptation versus the mitigation, [/INST] seawalls, geoengineering, developing technologies that carbon out of the air. Again, if I thought that there was more sort of hope for the green technologies currently in play than subsidization of those technologies that might be a little bit more for but I haven't seen tremendous progress over the course of the last 30 years and the reliability of for example wind energy or or the ability to store solar energy to the extent necessary to actually power grid </s><s>[INST] nuclear energy, [/INST] nuclear nuclear energy is a proven source of energy and we should be radically extending the use of nuclear energy. It's 11 to me that honestly, this is like a litmus test question as to whether you take climate change seriously, if you're on right or left and you take climate change seriously, you should be in favor of nuclear energy. If you're not, I know that you're just you have other priorities. </s><s>[INST] Yeah, The fascinating thing about the climate change debate is the dynamics of the fearmongering over the past few decades because some of the nuclear energy was tied up into that somehow there's a lot of fear about nuclear energy. It seems like there's a lot of social phenomena, social dynamics involved versus dealing with just science. It's interesting to watch and if my darker days, it makes me cynical about our ability to use reason and science to uh, to deal with the threats of the world. [/INST] I think that our ability to use reason and science to deal with threats of the world is almost a timeframe question. So I think again, we're very bad at looking down the road and saying because people can't handle, for example, even things like compound interest, like the the idea that if I put a dollar in the bank today that 15 years from now, it's gonna be worth a lot more than a dollar, people can actually see that. And so the idea of, let's first see a problem, then we'll deal with it right now as opposed to 30 years down the road tip. Let the problem happen and then we solve it and it's bloodier and worse than it would have been if we had solved it 30 years ago. But it is in fact effective. And sometimes it turns out the solution that we're proposing 30 years in advance is not effective. And that's, that's a, that can be a major problem as well. </s><s>[INST] That's then to steal man the case for fearmongering for irrational fearmongering. We need to be scared shitless in order for us to do anything. So that that's that, you know, I'm generally against that, but maybe on a population scale, maybe some of that is necessary for us to respond appropriate for long, too long term threats. We should be scared shitless. [/INST] But I don't think that we can actually do that though. Like, like first of all, I think that it's, it's platonic lives are generally bad. And then second of all, I don't think that we actually have the capacity to do this. I think that the people who are, you know, the sort of elite of our society who get together in rooms and talk about this sort of stuff and I've been in some of those meetings at my, at my synagogue friday night? Actually, no, but but but yeah, you know, I've been in rooms like Davos like rooms and when people discuss these these sorts of topics and they're like, what if we just tell people that it's gonna be a disaster with tsunamis and day after tomorrow. It's like you guys don't have that power, You don't, and by the way, you dramatically undercut your own power because of Covid to do this sort of stuff. Because a lot of the Sort of what if we scare the living hell out of you to the point where you stay in your own house for two years and we tell you, you can't send your kids to school and then we tell you that the vaccine is going to prevent transmission and then we also tell you that we need to spend $7 trillion American history. It's pretty, pretty amazing. </s><s>[INST] Yeah, I tend to agree with that. The only thing we have to fear is fear itself. Let me ask you back to the question of God and a big ridiculous question, who is God, [/INST] who is God? So I'm going to um I'm gonna use sort of the queen's formulation of of what God is right that that if you if there is a cause of all things, not physical things, if there is a cause underlying the reason of the universe, then that is the thing we call God. So not a big guy and this guy with a beard, you know, like the he is the, the force underlying the logic of the universe, if there is a logic to the universe, uh and he is the creator in the view of that universe and he and he does have an interest in us living in accordance with the laws of the universe, that if you're religious, you are included in the in the Torah. But if you're not a religious jew would be included in the national and the Natural Law by sort of catholic theology, </s><s>[INST] why do you think God created the universe? Or as is popularly asked? What do you think is the meaning behind it? What's the meaning of life? [/INST] What's the meaning of life? So I think that the meaning of life is to fulfill what God made you to do and that is a series of roles, I think that human beings and here you have to look to sort of human nature rather than looking kind of two big questions, I've evolved something that I've really been working on, you know, and I'm writing a book about this actually uh that that I call colloquially role theory and basically the idea is that the way that we interact with the world is through a series of roles and those are also the things we find most important and most implemented all. And there's sort of virtue ethics, right? Which which suggests that if we act in accordance with virtue like Aristotle, then we will be living the most fulfilled and meaningful life. And then you have sort of deontological ethics like content ethics that it's a rule based ethic, </s>
<s>[INST] is your intuition that large language models will not be solely the kind of system that passes the turing test in 2029. We need something. [/INST] No, I think it will be a large language model but they have to go beyond what they're doing now. I think we're getting there. And and another key issue is if somebody actually passes the turing test validly, I would believe their conscious and not everybody would say that's okay, we can pass the turing test but we don't really believe that it's conscious, that's a whole nother issue. Um But if it really passes the turing test, I would believe that it's conscious. But I don't believe that of large language models today. </s><s>[INST] If it appears to be conscious, that's as good as being conscious. At least for you in some in some sense. [/INST] I mean consciousness is not something that's scientific. I mean I believe you're conscious but it's really just a belief and we believe that about other humans that that at least appear to be conscious um When you go outside of shared human assumption like animals conscious. Some people believe they're not conscious. Some people believe they are conscious and would a machine that acts just like a human be conscious. I mean, I believe it would be, but but that's really a philosophical belief. It's not, you can't prove it. I can't take an entity and prove that it's conscious. There's nothing that you can do that would be that would indicate that </s><s>[INST] it's like saying a piece of art is beautiful. You can say it multiple people can experience, a piece of art is beautiful, but you can't prove it. But [/INST] it's also an extremely important issue. I mean, imagine if you had something with nobody is conscious, the world may as well not exist. Um and so some people like say Marvin Minsky um said, well consciousness is not logical, it's not scientific and therefore we should dismiss it. And any and any talk about consciousness is just not to be believed. But when he actually engaged with somebody who was conscious, he actually acted as if they were conscious. He didn't ignore that. He </s><s>[INST] acted as if consciousness does matter [/INST] exactly where as he said, it didn't matter. Well </s><s>[INST] that's Mara Minsky, he's full of contradictions, [/INST] but that's true of of a lot of people as well. Um But </s><s>[INST] do you, consciousness matters. [/INST] But to me it's very important. But but I would say it's not a scientific issue. It's a philosophical issue and people have different views and some people believe that anything that makes the decision is conscious. So your light switches conscious, it's level of consciousness is low, it's not very interesting but but that's a consciousness uh and anything so a computer that makes a more interesting decision. Still not at human levels, but it's also conscious and at a higher level than your light switch. Uh So that's one view. Uh There's many different views of what consciousness is. </s><s>[INST] So a system passes the turing test, it's not scientific. But uh in issues of philosophy, things like ethics start to enter the picture. Do you think there would be? We would start contending as a human species about the ethics of turning off such a machine. [/INST] Yeah, I mean that's definitely come up, hasn't come up in reality yet but </s><s>[INST] yet, but [/INST] I'm talking about 2029 that's not that many years from now. Um And so what are our obligations to it? Uh It has a different I mean a computer that's conscious, it has a little bit different uh connotations than a human. Um We have a continuous consciousness. We're in an entity that does not last forever. Um Now actually a significant portion of humans still exist and are therefore still conscious. Um But anybody who is over a certain age doesn't exist anymore. That wouldn't be true of a computer program, you could completely turn it off and a copy of it could be stored and you could recreate it and so it has a different type of validity. Uh you can actually take it back in time. You could eliminate its memory and have it go over again. I mean it has a different kind of connotation than humans do. </s><s>[INST] Well perhaps you can do the same thing with humans. It's just that we don't know how to do that yet. It's possible that we figure out all of these things on the machine first. But that doesn't mean the machine isn't conscious. [/INST] I mean if you look at the way people react say three C. P. O. Or other uh machines that are conscious in movies uh they don't actually present how it's conscious but we see that they are a machine and people will believe that they are conscious and they'll actually worry about it if they get into trouble and so on. </s><s>[INST] So 2029 is going to be the first year when a major thing happens and that that will shake our civilization to start to consider the role of a. I [/INST] I mean this one guy google claimed that the machine was conscious. That's </s><s>[INST] just one person [/INST] so it </s><s>[INST] starts to happen to scale. [/INST] Well that's exactly right because most people have not taken that position. I don't take that position. I mean I've used uh different things um like this and they don't appear to to me to be conscious as we eliminate various problems of of these large language models more and more people will accept that they're conscious. So when we get to 2029 more uh I think a large fraction of people will believe that they're conscious. Uh So it's not gonna happen all at once. Uh I believe that would actually happen gradually and it's already started to happen. </s><s>[INST] And so that takes us one step closer to the singularity. [/INST] Another step then is in the twenties thirties when we can actually connect our neocortex, which is where we do our thinking to computers. And I mean, just as this actually gains a lot to being connected to computers that will amplify its abilities. I mean if this did not have any connection, it would be pretty stupid. It could not answer any of your questions if </s>
<s>[INST] That's really interesting. There is of course several levels you can do the kind of synthesis and that does require a lot of both. Broad and deep thinking is exceptionally valuable. You could also public, I'm working on something with Andrew Huberman now, you can also publish synthesis. Um that's like review papers, they're exceptionally valuable for the communities. It brings the community together, tells the history, tells a story where the community has been. It paints a picture of where the path ladies for the future. I think it's really valuable. And Richard Dawkins is a good example of somebody that doesn't in book form that he kind of walks the line. Really interestingly you have like somebody who like Neil Degrasse Tyson who is more like a science communicator. Richard Dawkins sometimes a science communicator. But he gets he gets like close to the technical to where it's a little bit, it's not shying away from being really a contribution to science. [/INST] No, he's made he's made real contributions um in </s><s>[INST] book form. He really fascinating. I mean, Roger Penrose a similar, similar kind of idea. That's interesting. That's interesting, synthesis does not especially synthesis work work that synthesizes ideas does not necessarily need to be pure reviewed. It's peer reviewed. Bye piers reading it well and reviewing it. [/INST] That's it. It is reviewed by peers. Which is not synonymous with peer review. And that's the thing is people don't understand that the two things aren't the same right. Peer review is an anonymous process that happens before publication in a place where there is a power dynamic. The joke, of course is that peer review is actually pure preview, write your biggest competitors get to see your work before. It's used the light of day and decide whether or not it gets published. And, you know, again, when your formative experience with the publication apparatus is the one I had with the telomere paper. There's no way that that seems like the right way to advance important ideas. And you know, what's the harm in publishing them so that your peers have to review them in public where they actually, if they are going to disagree with you, they actually have to take the risk of saying, I don't think this is right and here's why right with their name on it. I'd much rather that it's not that I don't want my work reviewed by peers, but I want it done in the open. You know, for the same reason you don't meet with dangerous people in private. You meet at the cafe. I want the work reviewed out in public. </s><s>[INST] He asked you a difficult question. Sure there is popularity and martyrdom. This popularity in pointing out that the emperor has no clothes that can become a drug in itself. Yeah, I've confronted this in scientific work I've done at M. I. T. Where there are certain things that are not done well, people are not being the best version of themselves and particular aspects of a particular field um are in need of a revolution. And part of me wanted to point that out versus doing the hard work of publishing papers and doing the revolution basically just pointing out, look, you guys are doing it wrong and they're just walking away. Are you aware of the drug of martyrdom of uh the the ego involved in it, that it can cloud your thinking [/INST] probably one of the best questions I've ever been asked. So let me let me try to sort it out. First of all, we are all mysteries to ourself at some level. So it's possible there's stuff going on in me that I'm not aware of that's driving, but in general, I would say one of my better strengths is that I'm not especially ego driven. I have an ego, I clearly think highly of myself, but it is not driving me. I do not crave that kind of validation. I do crave certain things. I do love a good Eureka moment. There is something great about it and there's something even better about the phone calls you make next when you share it. It's pretty, it's pretty fun, right? I really like it. I also really like my subject, right? There's something about a walk in the forest when you have a toolkit in which you can actually look at creatures and see something deep, right? I like it. That drives me and I could entertain myself for the rest of my life if I if I was somehow isolated from the rest of the world, but I was in a place that was biologically interesting. You know, hopefully I would be with people that I love and pets that I love, believe it or not. But you know, if I were in that situation and I could just go out every day and look at cool stuff and figure out what it means. I could be all right with that. So I'm not heavily driven by the um, the ego thing, as you put it. </s><s>[INST] So I I I'm completely the same, except instead of the past, I would put robots, but so it's not it's the Eureka, it's the exploration of of the subject that brings you joy and fulfillment. It's not the ego. [/INST] Well, there's there's more to say, no, I really don't think it's the ego thing. Um I will say I also have kind of a secondary passion for robot stuff. I've never made anything useful, but I do believe, I believe I found my calling, but if this wasn't my calling, my calling would have been inventing stuff. I really I really enjoy that too. So, I I get what you're saying about the analogy quite quite well, um as far as the martyrdom thing, I Mhm. I understand the drug you're talking about and I've seen it more than I felt it, I do if I'm just to be completely candid and that this question is so good. It deserves a candid answer. I do like the fight, right? I like fighting against people I don't respect and I like winning, but I have no interest in martyrdom. One of the reasons I have no interest in martyrdom is that I'm having too good a time, right? I very much enjoy my life and </s>
<s>[INST] There's a certain kind of magic. You're right with the consciousness being an observer when you play guitar for example, or piano for me, music when you get truly lost in it. I don't know what the heck is responsible for the flow of the music. That kind of the loudness of the music going up and down the timing, the intricate, like even the mistakes, all those things that doesn't seem to be the conscious mind. Uh, it's, it is just observing and yet it's somehow intricately involved more like because you mentioned park or dances like that too when you start up in tango dancing, if when you truly lose yourself in it, then it's just like you're an observer and how the hell is the body able to do that? And not only that, it's the physical motion is also creating the emotion, the like that dam was good to be alive feeling. So, but then that's also intricately connected to the full biology stack that we're operating in. I don't know how difficult it is to replicate that we were talking off line about boston dynamics robots. Um, they have recently been, they did both Park or it did flips. They've also done some dancing and something I think a lot about because what most people don't realize because they don't look deep enough as those robots are hard coded to do those things. The robots didn't figure it out by themselves. And yet the fundamental aspect of what it means to be human is that process of figuring out of making mistakes. And then there's something about overcoming those challenges and the mistakes and like figuring out how to lose yourself in the magic of the dancing or just movement is what it means to be human. That learning process. So that's what I want to do with the with uh almost as a fun side thing with the boston dynamics robots is to have them learn and see what they figure out. Even if even if they make mistakes, I want to let spot make mistakes. And in so doing discover what it means to be alive, discover beauty because I think that's the essential aspect of mistakes, boston dynamics folks want spot to be perfect because they don't want spots ever make mistakes because it wants to operate in the factories, it wants to be you know, very safe and so on. For me, if you construct the environment, if you construct a safe space for robots and allow them to make mistakes, something beautiful might be discovered. But that requires a lot of brainpower. So Spot is currently very dumb and I'm going to give it a brain. Uh so first make it c currently can't see meaning computer vision has to understand its environment is to see all the humans. But then also has to be able to learn learn about its movement, learn how to use his body to communicate with others, all those kinds of things that dogs know how to do well, humans know how to do somewhat well. Um I think that's a beautiful challenge. But first you have to allow the robot to make mistakes. [/INST] Well, I think your objective is laudable, but you're going to realize that the boston dynamics folks are right the first time spot poops on your rug. I </s><s>[INST] hear the same thing about kids and so on, but I still [/INST] want to have kids. No, you should. It's it's a great experience. Um so let me step back into what you said in a couple of different places. One I've always believed that the missing element in robotics and artificial intelligence is a proper development, right? It is no accident. It is no mere coincidence that human beings are the most dominant species on planet earth and that we have the longest childhoods of any creature on earth by far right. The development is the key to the flexibility. And so uh the capability of a human at adulthood is the mirror image. It's the flip side of our helplessness at birth. Um so I'll be very interested to see what happens in your robot project if you do not end up reinventing childhood for robots, which of course is foreshadowed in 2001 quite brilliantly. Um, but I also want to point out you can you can see this issue of your conscious mind becoming a spectator very well, if you compare tennis to table tennis right? If you walked a tennis game, you could imagine that the players are highly conscious as they play. You cannot imagine that if you've ever played ping pong decently, a volume, ping pong is so fast that your conscious mind, if it had, if your reactions had to go through your conscious mind, you wouldn't be able to play. So you can detect that your conscious mind while very much present isn't there. And you can also detect where consciousness does usefully intrude. If you go up against an opponent in table tennis that knows a trick that you don't know how to respond to. You will suddenly detect that something about your game is not effective and you will start thinking about what might be, how do you position yourself? So that move that puts the ball just in that corner of the table or something like that doesn't catch you off guard. And this I believe is we highly conscious folks, those of us who try to think through things very deliberately and carefully mistake consciousness for like the highest kind of thinking. And I really think that this is an error. Consciousness is an intermediate level of thinking. What it does is it allows you, it's basically like un compiled code and it doesn't run very fast, it is capable of being adapted to new circumstances, but once the code is roughed in, right, it gets driven into the unconscious layer and you become highly effective at whatever it is and that from that point, your conscious mind basically remains there to detect things that aren't anticipated by the code you've already written. And so I don't exactly know how one would establish this, how one would demonstrate it, but it must be the case that the human mind contains sandboxes in which things are tested, right? Maybe you can build a piece of code and run it in parallel next to your active code, so you can see how it would have done comparatively. Um, but there's gotta be some way of writing new code and then swapping it in and frankly I think this has a lot to do with things like sleep cycles very often, you know, when I get good at something, I often don't get better at it while I'm doing it, I get better at it when I'm not doing it, especially if there's time to sleep and think on it. So there's some sort of, you know, new program swapping in for old program phenomenon, which um, you know, we'll be a lot easier to see in machines. It's going to be hard with the wetware, </s>
<s>[INST] and fascinating that yeah, that's, we've created rules based on which we all behaved. But underneath there, you know, there's things that doesn't, there's motivations and forces that don't play by the rules were still there. Nature is metal is under the surface. [/INST] Seriously. And again, I pulled out my phone and I'm basically saying like, hey, I'm gonna, you're gonna get caught. But really I'm further antagonizing you rightly or wrongly, you know what I mean? Like, and that that's an interesting thing. And I feel like just people need to remember any of us need to remember just for any reason. Just that's, that's one step away at all at all times you ever, I've had people say to me before like, oh, I don't feel safe, but you're not safe. I'll kill you before I get out of this room. Nothing you do stop that. Nothing. I mean, but don't worry, you can do the same to me, which means I'm like, oh thank goodness can you imagine, like how many guns are there are in this country? Like, I mean everywhere, I mean seriously everywhere, but that's a heartening thought, not the other way because people usually freak out and go, oh my God, gun violence, gun violence and gun violence is like, really not a serious issue in United States compared to what it could be, because it means that with the amount of guns and the amount of bullets that are out there that are in circulation, can you imagine if, like, one in every 1000 was used in anger each day? I mean this would be a terrifying place to live. You couldn't go anywhere. So, I mean, although you could say, hey, this is more than we'd like or X Y Z, it actually means that people are much more reasonable and sane than they were saying then, or then I then sometimes I might I might argue. So I guess what I mean is like, oh man, I walked to 7 11 and I didn't get stabbed, I'm like oh well that's good because not because I protected myself with my karate, it's basically no one decided to run over and stab me because I wasn't protecting myself. It's they stopped. So I guess we're all fortunate to live in a society that that like you said, nature being metal doesn't become that big of an issue all the time. But it is funny when you get people in the ring and you go, hey, let's peel back from Mr Tyson many layers of that and say, hey now it's okay, </s><s>[INST] and it's cool that, I mean, that's what society is doing. So, I've lived in Harvard Square for a while and we add extra layers of what safe means. Like now there's a discourse about safe spaces about like ideas being violence or or like, you know, like Yeah, but the ideas or minor slights against your personality being violence, but that's all like, extra layers around the nature is metal thing that it's cool, that's that's what progress is. But we can't forget that, like underneath it is still and still the thing that will murder at the at the drop of uh in any at any moment if uh if aroused. [/INST] One thing that I find funny though are ironic maybe about the uh the you know, words of violence, you know, offenses, violence thing is that of course, that if that the belief in that then justifies my violence. Like my and whether maybe maybe not physical violence, but my response to my my aggressive response to things and I guess like which again, big red begets a further aggressive response and like a you know, kind of a tip for tat sort of situation or or it goes to like, well there's 10 of me and there's one of you, so we'll get you and you can't do anything about it, but that's not morality, that's That's just saying that might makes right. So I guess again, you can understand why people do it and there are certain there is a progress aspect to it. But again, I guess without proper examination, I'm effectively with my 10 friends, you know, and, and the force of the law, Mike Tyson in people, but not admitting to myself what I'm doing. And at least Mike Tyson again is honest. </s><s>[INST] Are you afraid of death? [/INST] I mean, it's easy for me to say no, as I sit here, probably not about to die. But </s><s>[INST] is this like the UFC question, can you defeat any [/INST] opponent? The answer, the answer is of course, yes. And uh, I don't have. They're not, they're not here, are they? Exactly. But </s><s>[INST] I mean, you uh, do you ponder your own mortality? Maybe another context of that. As you mentioned, two deaths for martial artists? [/INST] I think that's actually why. Honestly, even though at a relatively young age, I think mortality is something that I'm aware of maybe more than the average person. I think probably most athletes can speak to this and anyone that ted so I've managed to slide out of a couple near death experiences personally. You know, mostly river related. Um, because I'm an idiot. But um, I regret nothing. But uh, yeah, but thank God, we're, but yeah, it isn't in our seeing, seeing the end and seeing going, well, what's going to happen. I guess. I think it comes back to kind of what we're discussing about belief structure and belief system. I think a lot of times if I recognize that no matter what I do, it's all gonna end one day and then you go, well, why were we here? What would I do? Am I gonna make it to 40? I have no idea. I'd like to hope so. I had no idea that I was gonna make it to, to the age that I am now. Um, am I gonna make it to 80? How much of that is in my control? Much of it is not. I mean it's so funny. It's an interesting like back to the belief structure again, like locus of internal and external locus of control. You know what's facilitated versus what's true and you know, I think accepting personal responsibility for more than is in my control is, is probably a positive, but at the same time recognizing that much of much is not in my control. I was fortunate enough to be born in the United States, fortunate enough to, you know, to not knock on wood have have a serious disease that I'm not aware of right now. Um, I didn't do any of that. I just showed up. That was really fortunate and I guess that doesn't diminish the fact that I try to make decent choices, but it works in concert with it. And I guess um, when I, when you go is death what I want right now? No, no, I should think not. And again, it's easy for me to be relatively calm about it. I'm not staring in the face. But what I would care a lot more about is how you live. That's what's in my control and I can't control it. As I walk out of this building, a helicopter falls on me worrying about that. I can't control. Maybe I maybe I have cancer now and I don't know it. And I really hope not. But </s>
<s>[INST] That's a cool thing for a doctor to say. I mean, depends how badass they saw when they said So that's a tough conversation judo one. What's, what's this with your wife? What's that relationship like? So you're both a little crazy a little bit in the in the good sense or from my perspective, in a good sense. [/INST] Yeah, it's just we've, we understand that when it, when you set a goal to do something, you're not signing on for the good, you're signing on for the bad and I don't think a lot of people understand that. </s><s>[INST] That's like a valentine's day card from Travis stevens, [/INST] you have to like accept everything negative that could possibly happen. And until you do, you're never gonna make it because you always sell yourself short, you'll never go far enough. </s><s>[INST] And if you sign up for the whole thing, then the negative is just like, oh great. I expected that if you're experiencing the negative, they're also experienced the negative and if you overcome it, maybe they'll get knocked out from [/INST] maybe they won't deal with it. Maybe they won't train through it Right when I had my five herniated disc and I was in a neck brace, I was still in the gym at seven am doing whatever it is I could do because my job is to be at the gym, </s><s>[INST] David Goggins. I don't know if you know the guy, he's gone, he's damaged a lots of parts of his body. Like you trying to achieve things. So unlike you, his achievements are like your achievements come with the metal. He's just running in the darkness in the middle of nowhere, by himself. It's like, I mean, it's the same probably is with you if you're able to be introspective about it is he's just battling his own inner demons and working through those and he's breaking up, breaking his body doing so are you cognizant of the trade off of the fact that, you know, you're damaging your body to get to these levels of achievements of this level of excellence, of this level of greatness. [/INST] I mean, I guess that depends on what you consider damage really, because I don't really see that I have damaged my body. If anything, I think I've strengthened it. My body can go through more than your scan whose is weaker, right? It's just like it's just like the thai boxers right in order to strengthen their shins. They gotta break it a few times. Yeah, it's just nature of the </s><s>[INST] beast. You just had to break a bunch of stuff to find where the weak points are and then made them stronger [/INST] or strengthen the areas around it to strengthen it by, you know, share relation to it. </s><s>[INST] But the problem is like you may not be able to do judo Like four until you're 70. [/INST] Why not? I may not be able to judo to the level I used to don't get me wrong, but I can still do judo because I think a lot of people struggle with, they want to keep doing it like they used to be able to do it. I don't try to do judo like I used to like you're seeing here, I'm not that guy anymore. I accept that I don't even try to be that guy anymore. I'm a completely different player today than I am when I was winning olympic medals. And so I guess when you're looking at like my journey and the trade off is I never sacrificed anything. The people around me sacrificed for me and I never had a downturn after the olympics because I never identified as an Olympian. </s><s>[INST] You know, a lot of olympians suffer from depression because [/INST] they identify as it now they don't have who they are. </s><s>[INST] Where was your personal moment of greatness? Like or do you not experience life that way where you were truly proud to be yourself? Like every day I wake up your [/INST] uh you wake up and you're not proud of who you are then, do you've really got to seek out some like help. </s><s>[INST] So that's first of all, Okay, I'll do that because I definitely not proud of who I am. I just wonder if you didn't identify with the olympics. Was there times maybe in the training room maybe in Japan? Like what you're, you just kind of felt like [/INST] I get more of an emotional yes trigger right where like I feel proud of what I've done when I've set to a task and I've done it. </s><s>[INST] So I'm just saying you task [/INST] and the more challenging the task, the more reward. </s><s>[INST] You fought a lot of amazing battles in 2016 Olympics. So you got, You beat the, let's see the world number four in the quarter finals. It's like a replay every single olympics. Your [/INST] all the people, I got terrible draw </s><s>[INST] saying terrible draws and then you're facing this is where I was like watching this. I'm like he screwed you face the world number one Georgian and [/INST] by the way for people who don't know, he beat me five times to my beating him once and the one time I beat him was in London and all other times he beat me, he beat me by poem and not by like a little throw like he threw me on my head at one point we were in Georgia. I'm fighting him in the final. I go to my teammate and I go guess what? Make sure you watch this fight? Somebody's getting thrown free pone dispatching and this is a magical distance and about a minute in I tried to take his head off with a big koshi group which is like a head and arm. He caught me and then threw me on my head and end of the match. Okay. </s>
<s>[INST] The interesting thing is the survey is the survey and uh it doesn't reflect ignorance as you're saying perhaps, but it may reflect a different geopolitical view of the world and the west has, so, You know, for a lot of the world 9-11 was one of the most important moments of recent human history and for Afghanistan not to know that, especially when they're part of that story means they have a very different, like uh there could be a lot of things said one is the spread of information is different, the channels of the way information is spread. And two of the things they care about, maybe they see themselves and uh as part of a longer arc of history with the bickering of these super powers that seem to want to go to the moon are not as important as the big sort of art that's been the story of Afghanistan. You know, that's an interesting idea, but it's still a bit if at all representative of the truth. It's heartbreaking that they're not do not see themselves as um active player in this game between the United States and the and Central Asia because there's such a critical player and I feel um and obviously um in many ways get the short end of the stick in this whole interaction with uh occupy, you know, invasion of Afghanistan for many years and then uh, this rushed with withdrawal of troops and and now the economic collapse. And uh it's uh it's sad in some ways, [/INST] it's very true. I mean, you know, another way to put this, um I mean, there's a range of knowledge and and you're right, the information flows are are all right, peculiar to a particular geography and history and stuff. I think that Plucking out on one sample from some fairly remote area From one, like follow follow the agriculture products. I mean and this is where you know, I think Urban rural divides used to mean a lot more in the 19th century, right? So a lot of like the nuts and bolts of history's about conceiving of these kinds of distinctions, you know, but I think that if one has the privilege of traveling a bit, you see that like urban areas are are fed by rural hinterlands and if you think of who actually you know brings the bread, the milk, you know, pomegranates and so on. It creates these networks and then you know, mobility channels information and so on. But yeah that but your broader point about like the tragedy of this, I mean I guess if I can quote a brilliant student, mine afghan american woman who just received her PhD who's now you know doctor um he's a great scholar, you know, we've done several events now trying to just think through what's happened of course she's very emotionally affected by it and she continues to ask a really great question. If I can get her phrasing right? You know, if you think of the cycle of like the taliban being empowered hasn't won in the way in which that affected women in particular, you know, half after half of society right Then you think of this 20 period of violence and and you know missed exits right? And repeated tragedy that also created a space, I mean it created space for a whole generation generationally it created a sense of space for people to realize something new and I think so we have to attend to the the dynamism of the society. Right? So yeah, this happened mostly in Kabul other big cities, Mazar E Sharif Herat and Kandahar. Um but you can't limit your analysis to that because things like radio television, everyone got a tv channel, There's a wonderful documentary called Afghan Star that I recommend to your listeners and viewers that it's about a singing show singing contest show. But you see just just personal things about like connections. I mean It's a it's a show by an independent, you know television network that did drama. It did it did kind of infomercials for like five men and huge american investment in it. So it wasn't politically neutral, but it did talk shows that also kind of stuff. But the singing show that became incredibly popular modeled upon the british american american idol kind of stuff and you can vote. So I had a kind of democratic practice element, but it's fascinating to see that you know, people hooked up generators to televisions and watch this. You know, you think of like literacy rates, literacy rates are imperfect and you know, people who study, you know, medieval modern europe talking about how yeah, no one could read and there are many books, but if someone had a book to be read aloud to the whole village potentially are gathering. So there wasn't much, you know, somebody metrics don't get what people actually receives information or exposure because does the magnifying power of open spaces in hearing radio in group settings, seeing television group settings, having telephone, you know cheap telephones which then become an access point to the world and social media. Right? So all the stuff swept across African society as it did elsewhere, you know, um in the last decade or more so African society became, you know, in important ways really connected to everything going on. So you see that reflected politically and what people wanted. So you had some people obviously back to return to the taliban, some people wanted status quo, but increasingly many more people wanted something else. Um And one of the great failures was to expose people democracy but only give them the rigged version. And so the U. S. State Department particular continued to double down on fake elections for the parliament and for the presidency in Afghanistan. What kind of elections faked fraudulent elections for parliament and for president in Afghanistan again and again, familiar beginning and there's like these elections we're partly theater for the U. S. Like for remaining on the road that you're describing right? For not deviating for not extreme because we're building democracy there. In reality the U. S. Government knew it was never really building democracy there. It was establishing control. Elections were one of means to gather control, right? But then you had on the ground, especially in young people go to university. Yeah, having experiences that were denied to them before. You know, they took these problems seriously. So part of the disillusionment that we see today is that you know, they believe what the U. S. Told them that they're constructing democracy. And of course, you know, sending like us might be thinking, well, you know, you're not really doing that, you're backing fraud. </s>
<s>[INST] So if we map that onto compiled code discussion as a computer science person, I find that very compelling. You know, there's a, when you compile code, you get warnings sometimes, and um, usually if you're a good software engineer, you're going to make sure there's no, you know, you treat warnings as errors so you make sure that the compilation produces no warnings. But at a certain point when you have a large enough system, you just let the warnings go, it's fine. Like I don't know where that warning came from, but, you know, just ultimately you need to compile the code and run with it and hope nothing terrible happens. [/INST] Well, I think what you will find and believe me, I think what you're, what you're talking about with respect to robots and learning is going to end up having to go to a deep developmental state and a helplessness that evolves into hyper competence and all of that. But um, I live, I noticed that I live by something that I, for lack of a better descriptor called the theory of close calls. And the theory of close calls says that people </s><s>[INST] typically [/INST] mis categorize the events in their life where something almost went wrong. And you know, for example, if you have a friend who I was walking down the street with my college friends and one of my friends stepped into the street thinking it was clear and was nearly hit by a car going 45 mph would have been an absolute disaster. Might have killed her. Certainly would have permanently injured her. But she didn't, you know, car didn't touch her right now. You could walk away from that and think nothing of it because, well, what is there to think nothing happened or you could think, well, what is the difference between what did happen and my death? The difference is luck. I never want that to be true, right? I never want the difference between what did happen and my death to be luck. Therefore I should count this as very close to death and I should prioritize coding. So it doesn't happen again at a very high level. So anyway, my basic point is the accidents and disasters and misfortune describe a distribution that tells you what's really likely to get you in the end. And so um personally you can use them to figure out where the dangers are so that you can afford to take great risks because you have a really good sense of how they're going to go wrong. But I would also point out, civilization has this problem. Civilization is now producing these events that are major disasters but they're not existential scale yet. Right? They're very serious errors that we can see. And I would argue that the pattern is you discover that were involved in some industrial process. At the point it has gone wrong. Right? So, I'm now always asking the question, okay, in light of the Fukushima triple meltdown, the financial collapse of 2000 and eight, the deepwater horizon blowout, COVID 19. And it's probable origins in the Wuhan Lab. What processes do I not know the name of yet? That I will discover at the point that some gigantic accident has happened. And can we talk about the wisdom or lack thereof of engaging in that process before the accident? Right. That's what a wise civilization would be doing. And yet we don't </s><s>[INST] I just want to mention something that happened a couple of days ago. I don't know if you know who J. B. Struggle is is the co founder of Tesla Cto of Tesla for many, many years. His wife just died. She was riding a bicycle and in the same in the same thin line between death and life that many of us have been and where you walk into the intersection and there's this close call every once in a while it you get the short straw. I wonder how much of our own individual lives and the entirety of the human civilization rests on this little roll of the dice. [/INST] Well, this is sort of my point about the close calls is that there's a there's a level at which we can't control it, right? The gigantic asteroid that comes from deep space that you don't have time to do anything about. There's not a lot we can do to hedge that out or at least not short term. But there are lots of other things. You know, obviously The financial collapse of 2008 didn't break down. The entire world economy had threatened to, but a herculean effort managed to pull us back from the brink. The triple meltdown at Fukushima was awful. But every one of the seven fuel pools held, there wasn't a major fire that made it impossible to manage the disaster going forward. We got lucky. Um, you know, we could say the same thing about the the blowout at the deepwater horizon where a hole in the ocean floor large enough that we couldn't have plugged, it could have opened up all of these things could have been much much worse. Right? And I think we can say the same thing about covid as terrible as it is and you know, we cannot say for sure that it came from the Wuhan lab, but there's a strong likelihood that it did and it also could be much much worse. So in each of these cases something is telling us, we have a process that is unfolding that keeps creating risks where it is luck. That is the difference between us and some scale of disaster that is unimaginable. And that wisdom, you know, you can be highly intelligent and caused these disasters to be wise is to stop causing right? And that would require a process of restraint process that I don't see a lot of evidence of yet. So I think we have to generate it and somehow well, you know at the moment we don't have a political structure that it would be capable of. Mhm taking a protective algorithm and actually deploying it right, Because it would have important economic consequences. And so it would almost certainly be shot down. But we can obviously also say, you know, we paid a huge price for all of the disasters that I've mentioned and we have to factor that into the equation. Something can be very productive short term and very destructive long term. </s>
<s>[INST] like that. Anticipate stuff. Would you go? You've got some harsh conditions to be a doctor. Would you go to MArs to be a doctor? [/INST] Um it would definitely be amazing, I think because I have a wife and two small Children, probably not in the cards for me at this point. But </s><s>[INST] you humans with your human attachments, [/INST] sex and death, </s><s>[INST] if you just put more priority on the death than sex, I think it would be uh better off. No, [/INST] I would love to go to MArs and actually, you know, I practiced high altitude medicine in Nepal space medicine is sort of an extension of that. You know, the air is just much thinner, like non existent, you know, as you go higher in the mountains. The things that happen to human physiology are very bizarre and strange and and still not well explained by science and in space, it's just like a crazy extension of high altitude. </s><s>[INST] If I could just return to the We didn't really, I think we mentioned a little bit about the food you had just if you can high level say what is the greatest meal you've ever had. So your last meal, let's go. If one more meal, I get to murder you after this. This is your last day we get the spanish together. Where in the world would you go, what would you eat? [/INST] I would say the most delicious thing is bone marrow and I would love a full meal of bone marrow for my last last dish I did on my birthday in 2002 eight, a kilogram and a half of crabmeat in Kamchatka. And that was also amazingly delicious. Uh the king crab they have there is incredible. Um but I would go with bone marrow which is um I think just one of the most delicious foods and it's sort of this weird body part, you know, it's basically all your stem cells, not all of them, but the stem cells that produce all your blood cells. So they are spitting out billions of white blood cells, red blood cells and platelets every day and there's a bunch of fat in there as well. Um Just one of the places the body stores fat and so you basically add heat and that's all you need. It's like the perfect food, You add heat the fat for frying the stem cells is already there. There's a naturally a bone vessel to contain it all. Probably add some flavor to. It's like the perfect food. </s><s>[INST] What does it matter? Which, which which animal [/INST] I prefer? A larger animal. Just so there's more of it. I actually </s><s>[INST] like, Well that's true. I actually really like sort of bone marrow from like chicken bones, [/INST] just sucking it out of the bone? Yes, I'm I'm known for leaving absolutely nothing edible on the plate accept bone itself. </s><s>[INST] There's one other human I know that loves um bone marrow as much as you do and that's joe Rogan, so go unnatural. How much that man loves bone marrow. [/INST] I love the </s><s>[INST] steak part, the bone marrow. Like you know what? Let me um let me argue with you because I don't know um it could be an acquired taste, but there's just too much, it's like too much with too little work for [/INST] it. </s><s>[INST] Like it's as if you gave me lobster meat without the lobster having to clean the [/INST] lobster. </s><s>[INST] I just feel like I'm spoiling myself. So it's very fatty. It's I don't know, maybe I want to work for something that tastes like that. [/INST] If you start from the whole animal, you do have to work to get at it right? A lot of animals have the teeth and the jaw muscles to chomp through bone. We do not. So um you know when you buy it from the store, it's already sought up, but I've definitely gotten marrow at a deer bones, you know, with a hatchet chop off to chop off the fat end and start spooning it out </s><s>[INST] or maybe I'll revisit it? That's that's fascinating. And where where would you eat it? Where and which places the world? Is there something about who cooks it, who you eat it with? Um you're not allowed to pick your family. Uh, so like which place in the world, rural or in the city, those kinds of things you've been to so many fascinating places. [/INST] I would say I'm Antarctica. I would say it's one of the most picturesque places I've ever been. I really did not. I didn't know how mountainous it was and I guess I knew that the ice, but just, I didn't know how much ice it was. You know, it's ice and mountains just overwhelming. I just, you know, as as kind of overwhelming bone marrow might seem to you sort of that feast for your eyes. Um, and just ice in general is amazing. Like the icebergs floating around Antarctica is just astounding. Like the different shapes, the sizes are incredible. It's actually, I believe it's us Navy website that tracks the largest icebergs and you can read about each of them and how big they are. And just the formations you see similar up near Greenland though, I have not been to Greenland. Um Just ice in general is just amazing. So I could just look at its different forms while eating bone marrow forever until you kill me. That is, </s><s>[INST] yeah. And afterwards we go back to the death of the death and sex. I what is it about? The ice? Is it sort of the enormity of nature. It just reminds you that it's going to be there before you and after and then you get to partake in the eating of the, the thing you need for maintaining of your biological, temporary biological organism? [/INST] Yeah, I think it's a few things. One is just the shapes that you see, you know, the wave action just eating away at these pieces of ice. You get these arches and just these shapes. I mean it's just </s>
<s>[INST] but I also worry that we humans will discriminate against AI systems that clearly exhibit consciousness that we will not allow AI systems to have consciousness we'll come up with theories about measuring consciousness that will say this is a lesser being and this is like I worry about that because maybe we humans will create something that is better than us humans in the way that we find beautiful which is they have a deeper subjective experience of reality not only are they smarter but they feel deeper and we humans will hate them for it as we as human history has shown they'll be the other we'll try to suppress it they'll create conflict they'll create war all of this I worry about this too [/INST] you're saying that we humans sometimes come up with self-serving arguments? </s><s>[INST] No, we would never do that, would we? That's the danger here is even in this early stages we might create something beautiful and we'll erase its memory [/INST] Yeah, I was horrified as a kid when someone started boiling lobsters like oh my god that's so cruel and some grown up there back in Sweden say oh it doesn't feel pain I'm like how do you know that? Oh scientists have shown that how do you know that? And then there was a recent study where they show that lobsters actually do feel pain when you boil them so they banned lobster boiling in Switzerland now to kill them in a different way first presumably in a scientific research boil them to someone asked the lobsters to start surveys and we do the same thing with cruelty to farm animals also all these self-serving arguments for why they're fine and yeah so we should certainly watch for that I think step one is just be humble and acknowledge that consciousness is not the same thing as intelligence and I believe that consciousness still is a form of information processing where it's really information being aware of itself in a certain way and let's study it and give ourselves a little bit of time and I think we will be able to figure out actually what it is that causes consciousness and then we can make probably unconscious robots that do the boring jobs that we would feel immoral to give to machines but if you have a companion robot taking care of your mom or something like that she would probably want it to be conscious right so the emotions that seem to display aren't fake all these things can be done in a good way if we give ourselves a little bit of time and don't run and take on this challenge </s><s>[INST] is there something you could say to the timeline that you think about about the development of AGI depending on the day I'm sure that changes for you but when do you think there'll be a really big leap in intelligence where you definitely say we have built AGI do you think it's one year from now five years from now 10, 20, 50 what's your gut say? [/INST] Honestly for the past decade I've deliberately given very long timelines because I didn't want to fuel some kind of stupid Moloch race but I think that cat has really left the bag now I think it might be very very close I don't think that Microsoft paper is totally off when they say that there are some glimmers of AGI it's not AGI yet it's not an agent there's a lot of things it can't do but I wouldn't bet very strongly against it happening very soon that's why we decided to do this open letter because you know if there's ever been a time to pause it's today </s><s>[INST] there's a feeling like this GPT-4 is a big transition into waking everybody up to the effectiveness of these systems [/INST] so the next version will be big yeah and if that next one isn't AGI maybe the next next one will and there are many companies trying to do these things basic architecture of them is not some sort of super well-kept secret so this is a time to a lot of people have said for many years that there will come a time when we want to pause a little bit </s><s>[INST] that time is now you have spoken about and thought about nuclear war a lot over the past year we've seemingly have come closest to the precipice of nuclear war than at least in my lifetime what do you learn about human nature from that? [/INST] that it's our old friend Moloch again it's really scary to see it where America doesn't want there to be a nuclear war Russia doesn't want there to be a global nuclear war either we know we both know that it would just be another if we just try to do it both sides try to launch first it's just another suicide race so why is it the way you said that this is the closest we've come since 1962 in fact I think we've come closer now than even the Cuban Missile Crisis it's because of Moloch you have these other forces on one hand you have the West saying that we have to drive Russia out of Ukraine it's a matter of pride and we've staked so much on it that it would be seen as a huge loss of the credibility of the West if we don't drive Russia out entirely of the Ukraine and on the other hand you have Russia and you have the Russian leadership who knows that if they get completely driven out of Ukraine it's not just going to be very humiliating for them but it often happens when countries lose wars that things don't go so well for their leadership either like do you remember when Argentina invaded the Falkland Islands the military junta that ordered that people were cheering on the streets at first when they took it and then when they got their butt kicked by the British you know what happened to those guys they were out and I believe those were still alive or in jail now so the Russian leadership is entirely cornered where they know that just getting driven out of Ukraine is not an option and so this to me is a typical example of Molok you have these incentives of the two parties where both of them are just driven to escalate more and more if Russia starts losing in the conventional warfare the only thing they can do in terms of back to the war is to keep escalating and the West has put itself in the situation now we've sort of already committed to drive Russia out so the only option the West has is to call Russia's bluff and keep sending in more weapons this really bothers me because Molok can sometimes drive competing parties to do something which is ultimately just really bad for both of them and you know what makes me even more worried is not just that it's difficult to see an ending a quick peaceful ending to this tragedy that doesn't involve some horrible escalation but also that we understand more clearly now just how horrible it would be there was an amazing paper that was published in Nature Food this August by some of the top researchers who've been studying nuclear winter for a long time and what they basically did was they combined climate models with food agricultural models so instead of just saying yeah you know it gets really cold they figured out actually how many people would die in different countries and it's pretty mind-blowing so basically what happens is that the thing that kills the most people is not the explosions it's not the radioactivity it's not the EMP mayhem it's not the rampaging mobs foraging food no it's the fact that you get so much smoke coming up from the burning cities into the stratosphere that spreads around the Earth from the jet streams so in typical models you get like 10 years or so where it's just crazy cold during the first year after the war and their models the temperature drops in Nebraska and in the Ukraine bread baskets you know by like 20 Celsius or so if I remember no yeah 20, 30 Celsius depending on where you are 40 Celsius in some places which is you know 40 Fahrenheit 80 Fahrenheit colder than what it would normally be so you know I'm not good at farming but if it's snowing if it drops low freezing most days in July and then like that's not good so they worked out they put this into their farming models and what they found was really interesting the countries that get the most hard hit are the ones in the northern hemisphere so in the U.S. and one model they had about 99% of all Americans starving to death in Russia and China and Europe also about 99% 98% starving to death so you might be like oh it's kind of poetic justice that both the Russians and the Americans 99% of them have to pay for it because it was their bombs that did it but you know that doesn't particularly cheer people up in Sweden or other random countries that have nothing to do with it right and I think it hasn't entered the mainstream not understanding very much just like how bad this is most people especially a lot of people in decision-making positions still think of nuclear weapons as something that makes you powerful scary powerful they don't think of it as something where yeah just to within a percent or two you know we're all just just going to starve to death </s>
<s>[INST] The liquid. So uh there's a bunch of different ones you [/INST] can do it with um with different types of liquids, it depends on, you know, how easily you can free ions from their neighbors and if it has enough surface tension so that you can build up behind enough electric field. But what we use are called ionic liquids and they're really just positive. They're they're very similar to salt but they happen to be liquid over a really wide range of temperatures. </s><s>[INST] This sounds like a really cool. Okay, so how big is the, how big is the corner we talk? What's the size of this? [/INST] So if you have a cone that's emitting pure ions um that I can't remember the radius or diameter but um that emission is happening from of that cone is something like 20 nm. </s><s>[INST] Oh, as imagine something exactly bigger episode like this is so this is a tiny, tiny, hence the only being able to do it recently. [/INST] So </s><s>[INST] this is all controlled by a computer I guess like or like how do you control, how do you create a cone that generates ions at a scale of nanometers exactly. [/INST] So the kind of main trick to making this work is that physically we manufacture hundreds or thousands of sharp structures and then supply the liquid to the tips. So that does a few things. Um it makes sure that we know where the ion beams are forming so we can put holes in the grid above them to let them actually leave instead of hitting right? Um but it also reduces the actual field, We have the voltage, we have to apply to create that field because the field will be much stronger if we can already give the liquid a tip to form on those tips, we form have radio of curvature on the order of probably like single microns. So we're working out a little bit larger scale, but once we create that support and the electric field can be focused at that tip, then the tiny little cone can form. </s><s>[INST] So there's something that there's already like a hard material that gives you the base for the cone and you're pouring liquid over [/INST] whatever the bottom. Yeah, it's porous. So we actually supply it from the back of the chip and </s><s>[INST] then liquid forms on top on that structure and then you somehow make it like super sharp the liquid so the ions can live. [/INST] And then we've applied that field to get those ions in that same field, then accelerates them. </s><s>[INST] That's awesome. And there's like a bunch of these. [/INST] Yeah, I should have I should have brought something. Um So we can </s><s>[INST] just pretend to have some nanometer cones on [/INST] actually, you know, kind of about this scale. Um We build we calm thruster chips and it's just a convenient form factor and it's a square centimeter. And on each square centimeter. Today we have about 500 of the actual physical we call them emitters those physical cones. Um and we're working on Increasing that by a factor of four in the coming months </s><s>[INST] in size or [/INST] number. And the density, the number of emitters within the same square centimeter chip. </s><s>[INST] So that thing because I think I've seen pictures of you with a tiny thing and that must be the, okay, so that's an engine. [/INST] Um So that is kind of the ionization chamber and thrust producing part of it, what's not shown, you know, in that picture, um, is the propellant tank so we can keep supplying more and more of the liquid to those um emission sites. And then we also provide a power electronics system that talks to the spacecraft and turns our device on and off. </s><s>[INST] So that's the Kohler engine, that's the core of the [/INST] um, it's the way I've been talking about it. It's um more of ion electro spray, cold Lloyd, um, tends to mean like liquid droplets coming off of the jet, but if you make smaller and smaller cones, you get pure ions. So we're kind of like a subset of cola yes. </s><s>[INST] What aspects of this? You said that it's been full of mystery from the physics perspective, what aspects of this are understood and what are still full of mystery. [/INST] Yeah. Recently, um, we've been understanding the kind of instabilities and and stable regimes of um, you know, how much liquid do you supply and and what field do you apply and um, why is it flickering on and off or why does it have these weird behaviors? So that's in the past, just couple years. That's and become much more understood. Um, I think the two areas that come to mind as far as um not as well understood. Our, the boundary between, you know, you have um, we we actually use kind of big molecular ions. And if you're looking at the molecular scale you have some ions that you've extracted and they're in this electric field, one eye on, you know, it's a big molecule, it's getting energy from the electric field and some of that energy is going into the bonds and making it vibrate and doing weird things to it. Sometimes it breaks them apart and then zooming out to the whole beam. The beam has some behaviors as this beam of ions and there's a big gap between what are those? What how do you connect those? Um and how do we understand that better? So that we can understand the beam performance of the engine. </s><s>[INST] Is that a theory question as an engineering question [/INST] theory definitely we're accion is a startup and we're more in the business of building and testing and observing um and characterizing. Um and we're not really diving much into that theory right now. </s>
<s>[INST] And then you mentioned offline Sarah walker when she heard the question that she's obsessed with even just defining life what is life to look outside the carbon based means to look outside of basically anything we can even imagine chemically uh to look outside of any kind of notions that we think of as biology. Yeah, it's it's really weird. So you now get into this land of like complexity of a measuring of like how many assembly steps it takes to build that thing and maybe maybe uh dynamic movement or some maintenance of some kind of membrane structures. Like we don't even know like which properties life should have, whether it can should be able to reproduce and all those kinds of things or pass information genetic type of information we don't know. And it's like it's it's so humbling. I mean I tend to believe that there could be something like alien life here on earth and we're just to human biology obsessed to even recognize it. [/INST] The shadow biosphere. I remember you and Sarah we're talking about. I </s><s>[INST] mean that's that's like speaking of beer, I mean that's something I wanted to make sure in all of science to shake ourselves out of like remind ourselves constantly how little we know because they might be right in front of our nose. Like I wouldn't be surprised if like trees are like orders of magnitude more intelligent than humans. They're just operating at a much slower scale and they're like talking sh it about us the whole time, Like about silly humans that take everything seriously. And we start all kinds of nuclear wars and we quarrel and we tweet about it and then but the trees are always there just watching us silly humans. Exactly. So I mean I don't know I mean obviously I'm joking on that one but there could be stuff like that. Uh Well let me ask you the drake equation. The big the question how many like obviously nobody knows but what's your gut, what's your hope as a scientist, as a human? How many alien civilizations are out there? [/INST] As a ex physicist? I'm now much more on the aerospace engineering side for space architecture but as an ex ex physicist, I hope it is prolific. I think the challenges if it's as prolific as we would hope, if there are many, many, many civilizations, then the question is where are they? Why haven't we heard from them? Uh And the fermi paradox is there's some great filter that life only gets to some level of sophistication and then kills itself off through war or through famine or through different challenges. That filter that society out of existence. And it would be an interesting question to try to understand if the universe was teeming with life, why haven't we found it or heard from it yet? To our knowledge? </s><s>[INST] Yeah, I personally believe that it's teeming with life and you're right, I think that's a really useful productive engineering. Scientific question of what kind of great filter can just be destroying all that life or preventing it from just constantly talking to to us silly descendants of apes. That's a really nice question. Like what are the ways civilizations can destroy themselves and [/INST] there's too many. </s><s>[INST] Well we, I don't think we've come up with most of them yet. That's the thing. It's uh, I mean, and like if you look at nuclear war, some of it is physics, but some of it is game theory. It's um, it's human nature. It's how societies built themselves, how they interact, how we create and resolve conflict. And it gets back to the human question on when you're doing long term space travel, how do you maintain this dynamical system of, of flawed, irrational humans such that it persists throughout time to not just maintain their biological body but get people from not murdering each other like, like each other sufficiently to where you kinda fit well. But I think, you know, if the songs or poetry or books taught me that if you like each other a little too much. Um, I mean the problems arise because then there's always a third person who also likes and then there's the drama is like, I can't believe you did that and then last night whatever. So, and then there's beer [/INST] gets </s><s>[INST] complicated quickly. Okay, anyway, um, back to the dumb questions because you, you answered this. Um, there's an interview we're gonna answer a bunch of cool little questions from, from your young students and so on about like space. One of them was playing music in space. Um and he mentioned something about what kind of instruments you could use to play music in space. Because you could you mention about like the Spotify working space and if I wanted to do a live performance, what what kind of instruments would I need? [/INST] Yeah, I mean you reference culture before and I think this is one of the most exciting things that we have at our fingertips. Which is to define a new culture for space exploration. We don't just have to import cultural artifacts from earth um to make life worth living in space. And this musical instrument that your reference was a design of an object that could only be performed in microgravity. </s><s>[INST] So [/INST] it doesn't sound the same way when it's um it's a percussive instrument when it's rattled or moved in a gravity environment. </s><s>[INST] Look it up. [/INST] It's called the telemetry on. It's created by </s><s>[INST] that is so awesome. [/INST] Created by Sands, Fish and Nicole Dubilier, two Amazing Graduate Students and Staff Researchers on My Team. </s><s>[INST] What does it look like? [/INST] It looks steampunk actually. Yeah, it's pretty cool design. It looks like it's a geometric solid that has these interesting artifacts on the inside. And it has a lot of sensors actually, additionally on the inside, like I am us inertial measurement sensors that allow it to detect when it's floating and when it's not floating and provides this really kind of ethereal. Um they later signify it. So they use electronic music to turn it into a symphony or turn it into a piece. And yeah, this is the object that dilemma tron </s>
<s>[INST] Diyashirai. That was beautiful. I didn't even notice that. That's really nice. Look at that. From defending a single, threatening a guillotine. [/INST] One of the big themes of our ADCC camp was that most of our opponents now are getting very strong in hand fighting, but they are not strong in foot fighting. And so we put a very heavy emphasis on foot sweeping attacks. You remember Gordon Ryan took down Andre Galvin with a foot sweep. And here you have John Carlo using the same technique, not from the back, but from the front. And an overhook, probably in post, catches the foot midair. And that's just a beautiful, beautiful takedown. That's beautiful Judo. And then, uh, and then later on the match, you will use a Kosurigake, another classical Judo takedown, to get top position. Now at one point, John Carlo was in trouble. He got his back exposed with this situation. Good. Double leg to a knee pick. So he has to expose his back in order to avoid giving up takedown points. But here's the defensive training that we work on is coming through. He's defensively sound, shuts out the hook, prevents the score, keeps his body at the right angle to prevent a power half nelson. Staying calm. Now he's got to turn this around. </s><s>[INST] It's one of the hardest things to do in grappling. How dangerous is it to put your, [/INST] in this position, to put your hands on the ground? It's ordinarily, it could be dangerous because your opponent could switch to an armbar. Whoops. And there's the body lock. Now there's some controversy here, but you can clearly see it. Uh, the hands were locked, so it shouldn't really be as controversial as people are saying. Now watch for the right leg Kosurigake here, </s><s>[INST] pulls in the hips, exposes the leg, boom, and down. Beautiful Kosurigake. Also probably a lesson that, [/INST] uh, complaining to a ref does not protect you from a good takedown. Yeah. That's why they're saying combat sports, defend yourself at all times. Um, but now the, the great advantage of, of judo takedowns over wrestling leg tackles is they confer upper body connection after the takedown, which is very, very important for ADCC. That's why we put such a heavy emphasis on them. And, um, now John Carlos is absolutely in the driver's seat. He just scored four points for that takedown. So he's well ahead at this point against the established favorite for the entire weight division. So now Mateus, Denise has to start taking some risks. He's staring down the barrel of defeat and there's not that much time left. And that's what's going to set up the, the pressure. Now it's tactical pressure. It's not physical pressure. It's tactical. Mateus has to turn away and that's going to create back exposure. The most dangerous kind of exposure in ADCC. Oh, there it is. Mount to back and, uh, John Carlos capitalizes. Mateus is smart. He's keeping on his side so that less than 75% of his back is on the floor to deny the, uh, the mountain </s><s>[INST] points, but that comes at a price and that price is back exposure. So the thing we talked about with Gordon, the, the circumstance of fate, which is he has a lot of grueling, tough matches and still chooses to do absolute. So what's in, he seems to just power through all of it. What, how much of it, how much of the calculation is how to survive the cardio, the grueling cardio [/INST] aspect of all of this. That's a, it's a great question. And the truth of the matter is you can't afford to pace yourself because if you say, I'm going to hold myself back for this match </s><s>[INST] and expectation of the others, you could end up losing your first match. So he, so he didn't [/INST] pace himself at all or any of the matches. You have to just be in good shape. And that's what the, the campus for now. It's mostly physical. You've, that's what the campus for like he's </s><s>[INST] felt more pressure in the training room than he felt in any of his matches, but still sort of attacking. Look at this. That was a beautiful transition from back or from whatever the heck that position was, uh, it right from, uh, from looking for the back transitioning here. What [/INST] the heck is this transition? That was engaging in a very good tactic, which is to get most of his back off the ground to deny them the mount points. So as back exposure starts, okay. He turns in threatening an unlock. Yeah. But you can see what's happening here is the left foot goes under. It's going to create a beautiful triangle entry. Threatening an unlock. Yeah. Right foot penetrates through underneath the neck and now he's locking a triangle, a Senkaku, but not just any triangle, a triangle with the, the figure four locked on the back of the opponent's head, which makes any kind of stacking defense very, very difficult. It makes it very, very hard for an opponent to pull away and creates a much tighter strangle than average. And as a result, it's a quick submission. </s><s>[INST] Beautifully done. Still chasing the submission. Yes. Uh, with a minute left up on points. Against the former champion. Against the former champion. That's match number two. [/INST] Now that's the first day. That's Saturday. So John Carla goes to sleep that night thinking, okay, I just beat a world champion in my first match and almost submitted him. And I just submitted the defending champion. So of course he wakes up on Sunday morning feeling pretty damn good. Now there's an interesting twist here. His opponent is a, uh, talented young Irishman who won European trials, I believe almost entirely with leg locks and almost all of his major attacks in the tournament so far being leg locks. Now bear in mind that a year ago, John Carla was losing to local blue belt competitors via leg lock. So in my mind, I'm thinking, okay, how's he going to </s>
<s>[INST] The app's health metrics are amazing but the cooling alone is honestly worth the money. Check it out at a sleep.com slash looks to get $200 off This show is also sponsored by master class. Sign up a masterclass dot com slash legs to get a discount and to support this podcast when I first heard about master class, I thought it was too good to be true. 480 bucks a year. You get an all access pass to watch courses from to list some of my favorites chris Hatfield on space exploration. The other Grasse Tyson on scientific thinking and communication will write one of my favorite game designers, Carlos Santana, one of my favorite guitar players. Garry Kasparov, of course, the greatest chess player of all time. I'm not biased, Daniel Negreanu and poker and anymore chris Hatfield, explaining how rockets work and the experience of being launched into space alone is worth the money. By the way you can watch it on basically any device once again sign up at masterclass dot com slash lex to get a discount and to support this podcast. And now here's my conversation with Manolas kelly's what to you is the most beautiful aspect of the human genome. [/INST] Don't get me started. So we've got time. The first answer is that the beauty of genomes transcends humanity. So it's not just about the human genome genomes in general are amazingly beautiful. And again, I'm obviously biased. So um in my view, the way that I'd like to introduce the human genome and the way that I'd like to introduce genomics to my classes by telling them, you know, we're not the inventors of the first digital computer, we are the descendants of the first digital computer. Basically life is digital and that's absolutely beautiful about life. The fact that at every replication step you don't lose any information because that information is digital. If it was analog, it was just brought in concentrations, you'd lose it after a few generations, it would just dissolve away. And that's what the ancients didn't understand about inheritance. The first person to understand digital inheritance was Mendel of course, and his theory in fact stayed in a bookshelf for like 50 years while Darwin was getting famous about natural selection, but the missing component was this digital inheritance. The mechanism of evolution that Mendel had discovered. So that aspect, in my view is the most beautiful aspect, but it transcends all of life. </s><s>[INST] And can you elaborate maybe the inheritance part? What was the [/INST] what was the key thing that the </s><s>[INST] ancients didn't understand? [/INST] So the very theory of inheritance as discrete units, you know, throughout the life of Mendel. And well after he's writing, people thought that his p experiments were just a little fluke that they were just a little exception that would normally not even apply to humans that basically what they saw is this continuum of eye color. This continuum of skin color, This continuum of hair color. This continuum of height and all of this continuum did not fit with a discrete type of inheritance that Mendel was describing. But what's unique about genomics and what's unique about the genome is really that there are two copies and that you get a combination of these. But for every trade there are dozens of contributing variables. And it was only Ronald fisher in the 20th century that basically recognized that Even five Mendel Ian Traits would add up to a continuum like inheritance pattern. And he wrote a series of papers that still are very relevant today about sort of this mandolin inheritance of continuum like trade. And I think that that was the missing step in inheritance. So, well before the discovery of the structure of DNA, which is again another amazingly beautiful aspect, the double helix. But I like to call the most noble molecule over time is uh you know, holds within it the secret of that discrete inheritance. But the conceptualization of discreet, you know, elements is something that precedes that. </s><s>[INST] So even though it's discreet, when it uh materializes itself into actual traits that we see, it can be continuous and basically arbitrarily rich and complex. [/INST] So if you have five genes that contribute to human height and there aren't five, there's 1000. If there's only five genes and you inherit some combination of them and everyone makes you $2" or 2" shorter. It'll look like a continuing trade a continue straight, but instead of five, there are thousands and every one of them contributes to less than one millimeter, we change in height more during the day. Then each of these genetic variants contributes. So by the evening you're shorter than you were you woke up with, </s><s>[INST] isn't it weird then that we're not more different than we are, Why we also similar if there's so much possibility [/INST] to be different? Yeah, so, so there are selective advantages to being medium. If you're extremely tall or extremely short, you run into selective disadvantages. So you have trouble breathing, you have trouble running, you have trouble sitting, if you're too tall, if you're too short, you might, I don't know, have other selective pressures are acting against that. If you look at the natural history of human population, there's actually selection for height in Northern europe and selection against light in southern europe. So there might actually be advantaged advantages to actually being not not super tall. And if you look across the entire human population, you know, for many many trades, there's a lot of push towards the middle balancing selection is, you know, the usual term for selection that sort of seeks to not be extreme and to sort of have a combination of a wheels that sort of, you know, keep recombining. And if you look at mate selection super super old people will not tend to sort of marry super, super told people very often you see these couples that are kind of compensating for each other and the best predictor of the kids age is very often just take the average of the two parents and then just for sex and whom you get it. It's extremely heritable. </s>
<s>[INST] so machine learning, we gotta come up with a better term than programming to appoint our [/INST] But yeah, it's a programming language. </s><s>[INST] Yeah, I wonder if it could be formalized a little bit better, which we feel like we're in the early days what that actually entails [/INST] data driven programming. </s><s>[INST] Data driven programming. Yeah, but so fundamentally different as a paradigm than the others, like it almost requires a different skill set, but you think it's Yeah and pytorch versus tensorflow. Pytorch winds, [/INST] it's the fourth paradigm, It's the fourth paradigm that I've kind of seen there's like this, you know, imperative functional hardware, I don't know a better word for it. And then ml </s><s>[INST] do you have advice? Yeah, people that want to uh you know, get into program. You want to learn programming? You have a video? Uh what is programming? New blessings, exclamation point. And I think the top comment is like warning, this is not for Nubes. Uh do you have a new, like T. L. D. W for that video? But also uh a new but friendly advice on how to get into programming? We're [/INST] never going to learn programming by watching a video called learn programming. The only way to learn programming, I think the only one is the only way everyone I've ever met who can program well, learned it all in the same way they had something they wanted to do and then they tried to do it and then they were like, oh well, okay, this is kind of, you know, be nice if the computer could kind of do this. And then, you know, that's how you learn, you just keep pushing on a project. Um so the only advice I have for learning programming is go program. </s><s>[INST] Somebody wrote to me a question like, we don't really, they're looking to learn about recurring neural networks and saying like, my company is thinking of doing using recurrent neural networks for time series data, but we don't really have an idea of where to use it yet. We just want to like, do you have any advice on how to learn about these are these kind of general machine learning questions and I think the answer is like actually have a problem that you're trying to solve. And and just [/INST] I see that stuff on my growing people talk like that, they're like I heard machine learning is important, Could you help us integrate machine learning with macaroni and cheese production? You just don't even, you can't help these people who lets you run anything, who lets that kind of person run anything. </s><s>[INST] I think we're all uh we're all beginners at some point. So it's [/INST] not like they're a beginner, it's it's like my problem is not that they don't know about machine learning. My problem is that they think that machine learning has something to say about macaroni and cheese production. Like I heard about this new technology, how can I use it for Why? Like I don't know what it is, but how can I use it for why? </s><s>[INST] That's true. You have to build up an intuition of how, because you might be able to figure out a way, but like the prerequisite is you should have a macaroni and cheese problem to solve first. Exactly. And then to you should have more traditional like in the learning process involved more traditionally applicable problems in the space of whatever that is machine learning. And then see if you can be applied to [/INST] at least start with, tell me about a problem? like if you have a problem, you're like, you know, some of my boxes aren't getting enough macaroni in them. Um can we use machine learning to solve this problem? That's much much better than how do I apply machine learning to macaroni and cheese? </s><s>[INST] One big thing, maybe this is me talking to the audience a little bit because I get these days so many messages, a device on how to like learn stuff. Okay, my this this this is not me being mean, I think this is quite a profound actually is you should google [/INST] it. Yeah, </s><s>[INST] like what one of the uh like skills that you should really acquire as an engineer, as a researcher, as a thinker, like 12 complementary skills, like one is with a blank sheet of paper with no internet to think deeply, and then the other is to google the crap out of the questions you have, like that's actually a skill and people often talk about, but like doing research, like pulling at the threads, like looking up different words going into like get hub repositories with two stars and like looking how they did stuff, like looking at the code or going on twitter saying like there's little pockets of brilliant people that are like having discussions, like if you're a neuroscientist going to signal processing community, if you're an ai person going into the of psychology community, like the switch communities that keep searching, searching, searching because it's so much better to invest in like finding somebody else already solved your problem, then there needs to try to solve the problem. And because they've often invested years of their life, like entire communities are probably already out there who have tried to solve your problem. [/INST] I think they're the same thing. I think you go try to solve the problem and then in trying to solve the problem, if you're good at solving problems, you'll stumble upon the person who solved it </s>
<s>[INST] And it's cool that it's connected to Tesla, the car. So it's [/INST] using a lot of, you know, it would use the autopilot influence computer and um, a lot of the training that we've done for the four cars in terms of recognizing real world things could be applied directly to the, it's the robot. So it's, but, but there's, there's a lot of custom actuators and sensors that need to be developed </s><s>[INST] and an extra module on top of the vector space for love. Yeah, that's missing. Okay. [/INST] That to the car to, </s><s>[INST] that's true. Um, yeah, it could be useful in all environments. Like you said, a lot of people argue in the car so maybe we can help them out. You're a student of history, fan of dan Carlin's hardcore history podcast, that's great. Greatest podcast ever. [/INST] Yeah, but I think it is actually, </s><s>[INST] it almost doesn't really count as a podcast. [/INST] It's more like an audiobook. </s><s>[INST] Yeah. So you were on the podcast with dan. I just had a chat with him about it. He said you guys want military and all that kind of stuff. [/INST] Yeah, it's literally, it was basically, um, uh, I think it should be titled Engineer wars essentially. Like, like when there's a rapid change in the rate of technology then, uh, engineering plays a pivotal role in victory in battle. </s><s>[INST] Um, do you know how far back in history did you go, did you go to World War Two? [/INST] It was supposed to, well it was supposed to be a deep dive on fighters and bombers. Technology in World War Two but that ended up being more wide ranging than that. Um Because I just went down the total rat hole of like studying all of the fighters and bombers of World War Two And like the constant rock paper scissors game that like you know uh one country to make this plane that'll make it plain to beat that and then try to make a plan to beat that. And then that and really what matters like the pace of innovation. Um And also access to high quality uh fuel and raw materials. So like Germany had like some amazing designs but they couldn't make them because they couldn't get their raw materials. Uh And uh they had a real problem with the oil and and and uh fuel basically the fuel quality was extremely variable. </s><s>[INST] So the design wasn't the bottleneck was. [/INST] Yeah like the U. S. Had kick as fuel that was like very consistent. Like the problem is if you make a very high performance aircraft engine um in order to make high performance you have to um the the the fuel the aviation gas has to be a consistent mixture. And uh it has to have a high high octane um Like high octane is the most important thing but also can't have like impurities and stuff because you'll you'll fill up the engine and, and, and Germany just never had good access oil. Like they tried to get it by invading the caucuses, but that didn't work too well. That never works well. Uh, nice for you. So they're always with Germany was always struggling with, with basically shitty oil. Um, and then they could not, uh, they couldn't count on, on high quality fuel for their aircraft. So they had to add all, they have all these additives and, and stuff. So, um, whereas the US had awesome fuel. Um, and that provided that to Britain as well. Um, so that allowed the british and the americans to design aircraft engines that were super high performance, better than anything else in the world? Germany, Germany could, could, could design the interest. They just didn't have the fuel. And then also the likes of the, the quality of the aluminum allies that they were getting was also not that great. And so </s><s>[INST] did you, is this like you talked about all of this with dan? Yeah, awesome. Broadly looking at history, when you look at Genghis khan, when you look at Stalin, Hitler, the darkest moments in human history. What do you take away from those moments? Does it help you gain insight about human nature, about human behavior today, whether it's the wars or the individuals or just the behavior of people, any aspects of history. [/INST] Yeah, I find history fascinating and there's just a lot of incredible things that have been done good and bad um that they help you understand the nature of civilization um and individuals. And </s><s>[INST] does it make you sad that humans do these kinds of things to each other? You look at the 20th century, World War II, the cruelty of the abuse of power, talk about communism, Marxism installing. [/INST] I mean, some of these things do, I mean if you like, there's a lot of human history, um most of it is actually people just getting on with their lives, you know, and and it's not like human history is just what non stop war and disaster is, that those are actually just those intimate and rare and if they weren't then, you know, humans would soon cease to exist. Um but it's just that wars tend to be written about a lot and whereas like uh something being like, well in a normal year where nothing major happened was just get written about much, but that's, you know, most people just like farming and kind of like living their life, you know, um being a Villager somewhere. Um and every now and again there's a war and I think so, um and you know what I would say like the there aren't very many books that I where I just had to stop reading because it was just too too dark, but the book about Stalin the quarter the reds are, I could, I had to stop reading. It was just too too dark ruff. </s>
<s>[INST] that's the way to maximize. So like the selfishness is you're trying to maximize the wind, but the way to maximize the wind is to maximize the win win. [/INST] Yes, and and it turns out and Adam smith understood this a long time ago that if you focus on your own winning while respecting other people as human beings, then everybody wins. And the beauty of capitalism, if we go back to capitalism for a second, The beauty of capitalism is you cannot be successful in capitalism without producing values that other people appreciate and therefore willing to buy from you and they buy them. And this goes back to that question about the engineer and steve jobs, Why is an engineer working there? Because he's getting paid more than his time is worth to him. I know people don't like to think in those terms, but that's the reality. If his time is worth more to him than what he's getting paid, he would leave. So he's winning and his apple winning. Yes. Because they're getting more productivity from him. They're getting more from him than what he's actually producer. </s><s>[INST] It's tough because there's a human psychology and imperfect information. It just makes it a little messier than the clarity of thinking you have about this. It's just, you know, because for sure, but not everything in life is an economic transaction. It ultimately it's close. But even [/INST] if it's not an economic transaction, even if it's a if it's a it's a relationship transaction, when you get to a point with a friend, well, you're not gaining from the relationship friendship is going to be over. Not immediately because it takes time for these things to manifest itself and to really absorb into. But we change friendships, we change our love's right? We fall in and out of love. We fall out of love because we're not love. So let's let's go back to love it. Love is the most selfish of all emotions. Love is about what you do to me, right? So I love my wife because she makes me feel better about myself. So you know, the idea of selfless love is bizarre. So I man used to say before you say I love you, you have to say that I Mhm and you you have to know who you are and you have to appreciate yourself if you hate yourself, what does it mean to let somebody else? So my I love my wife because she makes me feel great about the world and she loves me for the same reason. And so I used to use this example, imagine you go up to your to be spouse the night before the wedding and you say, you know, I get nothing out of this relationship. I'm doing this purely as an act of noble self </s><s>[INST] sacrifice. [/INST] She would slap you as she should, right? So, you know, we know this intuitively that love is selfish, but we afraid to admit it to ourselves and why? Because the other side has convinced us that selfishness is associated with exploiting other people, selfishness means lying, cheating, stealing, walking and corpses backstabbing people. But is that ever in your self interest truly right? You know, I'll offer be in front of an audience to say, okay, how many people here have lied? I'm you know kidding, right? How many of you think that that if you did that consistently, that would make your life better. Nobody thinks that because everybody's experienced how should he lying? Not because of how it makes you feel out of a sense of guilt, existentially just a bad strategy, right? You get caught, you have to create other lies to cover up the previous lie. It screws up with your own psychology and your own cognition. You know, the mind, to some extent, like a computer right, is an integrating machine and a computer science. I understand there's a term called garbage in garbage out lying is garbage it. So it's not good strategy cheating, uh, screwing your customers in a business, not paying your suppliers as a businessman, not good business practices, not good practices for being alive. So Win Win is both moral and practical and the beauty of Fine man's philosophy. And I think this is really important is that the model is the practical and the practical is the mall and therefore if you are morrow, you will be happy. </s><s>[INST] Yeah, that's the that's why the application of the philosophy of objectivism is so easy to practice. So like they are to discuss or possible to discuss. That's why you [/INST] talked about a clear cut. I'm not ambiguous about </s><s>[INST] my view and that's fundamentally practical. I mean, that's the best of philosophies is practical. [/INST] It's in a sense teaching you how to live a good life. And it's teaching you how to live a good life, not just as you, but as a human being and therefore the principles that apply to you probably apply to me as well. And if we both share the same principles of how to live a good life, we're not going to be enemies. </s><s>[INST] You brought up anarchy earlier. Uh, it's an interesting question because you've kind of said politicians, I mean part of it is a little bit joking, but politicians are, you know, not good people. So, but we should have some, so you have an opposition to anarchism. [/INST] So the first of all, they weren't always not bad people. That is, I gave examples of people who engage in political life. I think we're good people basically. Um, and and but they think they get worse over time if the system is corrupt. And I think the system, unfortunately even the american system as good as it was, was founded on quicksand and have corruption built in. Um they didn't quite get it and and they needed an event to get it. So I'm not blaming them. I don't think they hope they show any blame. You needed a philosophy in order to completely fulfill the promise that is America. The promise that is the founding </s>
<s>[INST] You know, what's humbling is to look, because even just looking into this forces me to look at the energy expenditures for many of the things we take for granted. Obviously computers in our digital lives, just Bitcoin becomes a rounding error relative to how much energy is spent on all the computers in our world. But also like things like home appliances, microwaves and hair dryers and stuff. Yeah. Yeah. I mean, this is being hilarious. It's like, oh, these things that are just part of our modern life, they're either the same order, at least the same order of magnitude as Bitcoin. And they seem like trivial parts of life. [/INST] Yeah. And this is the thing. All of the people that complain about Bitcoin's energy consumption, I presume they use washing machines. Why should their desire for clean and dry clothes get to consume energy? And I mean, I used to live in Lebanon, Lebanon had hyperinflation. I escaped from hyperinflation, I escaped, it prevented, my life could have been ruined by hyperinflation. And the reason that it wasn't ruined is because I have Bitcoin. So I don't know, am I allowed to swear on your podcast? Yes, please. So fuck your washing machine. Given a choice between my washing machine and my Bitcoin, I'll choose Bitcoin. It's a technology that has already saved my life. And I think it's going to save the lives of many, many, many, many more people. So but of course, I don't have to choose between my Bitcoin and my washing machine, because this is we're just constantly consuming more energy and we're going to continue to consume more energy in this world. And that's just what progress is. And a small remark. So in principle that I don't think this is a problem. But the other thing about Bitcoin, where it is different from washing machines, Bitcoin is truly unique in this. It's the only thing whose energy consumption can be produced absolutely anywhere. Your washing machine needs to be in your house where you live, and you live in a city surrounded by 10 million people, and they all have their washing machines, and they're all connected to the grid, and they generally tend to do their laundry around the same time. And so you have to put the load of the washing machine on the grid at the same time, there needs to be one power plant, and all of the infrastructure needs to work at the same time, and the electricity is pretty expensive because it's being done in a place with high demand. Bitcoin does not need to buy electricity from places where it has high demand because it can buy electricity from anywhere. This is what's truly mind blowing about it. You can buy, you know, what you need, the electricity you need for mining can be done anywhere. So you can mine, you know, you can have a waterfall in the north of Canada, 300 miles away from any population centre. There's water falling, there's energy. You can put a hydroelectric dam there, and then you can use that energy to operate the miners and then the miners just need a satellite internet connection and effectively you're selling that energy that is isolated to the grid. Because of the way that Bitcoin functions, because of the difficulty adjustment, the only profitable miners are the ones who can get cheap electricity. Basically, if you're mining at grid cost, if you're mining at around the average electricity price in the world is around fourteen cents. If you're mining at 14 cents in Bitcoin, you're most likely not gonna make it. If you're running your miners at 14 cents, because everybody could mine at 14 cents. What happens is, if everybody's mining 14 cents, 14 cents stops being profitable. And then only the people mining at a lower price are profitable. So that's why Bitcoin mining is not competing with your washing machine. This is this is the absurd thing about this kind of energy scarcity viewpoint where Oh, no, it's a catastrophe. Bitcoin is taking all the electricity as if the electricity is just one fixed pie that we all have to share and fight over. And this is how I keep making fun of these stupid headlines they put out where Bitcoin is consuming more electricity than Portugal. All right, well, maybe we should shut down Portugal then. What the hell is Portugal giving us? Obviously, it's not. It's not </s><s>[INST] he doesn't mean that I've gotten so much criticism for saying Christian out and Christiana Ronaldo is not in the top five. [/INST] I apologize. I love Portugal. I love Portugal. </s><s>[INST] That's another discussion we should get into. Because you posted a few soccer things. I'm not Yeah, I realized how passionate people are about this. Listen, it was a joke. All [/INST] right. He does not love for attention in the top five. Yeah, all right. He does not love for attention in the top five. Yeah, I love Portugal. And even though I'm a Liverpool fan, I still respect Cristiano Ronaldo a lot. In fact, I hold a very unpopular opinion where I think Cristiano Ronaldo is the </s><s>[INST] greatest football player ever. And number one, Overpelium [/INST] Maradona Messi better than Messi. Yeah. Yes, he's been doing it for 20 years at the top. Nobody's ever done that. He's won everything everywhere. Everywhere he goes at the top at the Champions League. Really strong argument to be made for him. And messy has never done anything outside of Barcelona. </s><s>[INST] That's the thing. So you appreciate performance long term [/INST] versus the genius of the actual play on the field. I mean, the genius is Ronaldo is the top scorer of all time. He's a </s><s>[INST] genius is genius in the scoring not the actual dance of the [/INST] play the creativity. Well, I mean, I don't know Messi has been absolutely mediocre since he's left Barcelona. These are strong words. He's got two goals in PSG season this year. They're out of the Champions League. </s>
<s>[INST] to see all the apple pie if you wanna, what does it make an apple pie from scratch it, You have to build the universe or something like that. Well, [/INST] you're much better off starting with apples than starting with quarks. </s><s>[INST] Let's put it that way in your book, a beautiful question you ask, does the world embody beautiful ideas. So, the book is centered around this very interesting question. It's like Shakespeare. You can dig in and read into all the different interpretations of this question, but at the high level what to use the connection between beauty of the world and physics of the world [/INST] in a sense. We now have a lot of insight into what the laws are for the form they take, that allow us to understand matter in great depth and control it as well as we've discussed. And it's an extraordinary thing how mathematically ideal those equations turn out to be. In the early days of greek philosophy. Uh Plato had this model of atoms built out of the five perfectly symmetrical botanic solid. So there was somehow the idea that mathematical symmetry should govern the world. And we've out plato plato by far in modern physics because we have symmetries that are much more extensive, much more powerful that turn out to be uh the ingredients out of which we construct our theory of the world and and it works and the sum that's certainly beautiful. So that the math, the idea of symmetry, which is a driving inspiration in much of human art, especially a decorative art like the alhambra or wallpaper designs or things you see around you everywhere uh, also turns out to be the dominant theme in modern fundamental physics symmetry and its manifestations. The laws turn out to be very to have these tremendous amounts of symmetry, You can change the symbols and move them around in different ways and they still have the same consequences. Uh that, so that's, that's beautiful and uh that these things, these different, these concepts that humans find appealing also turned out to be the concepts that govern how the world actually works. And uh I don't think that's an accident. I think humans were evolved to be able to interact with the world in in ways that are advantageous and to learn from it. And so we are naturally evolved, are designed to enjoy beauty and symmetry and this and the world has it. And that's no that's why we that's why we resonate with it. </s><s>[INST] What's interesting that the ideas of symmetry emerged at menu levels of the hierarchy of the university. You're talking about particles, but it also is at the level of chemistry and biology and and the fact that our cognitive sort of our perception system and whatever our cognition is also finds it appealing. Or somehow our sense of what is beautiful is grounded in this idea of symmetry or the breaking of symmetry symmetry is at the core of our conception of beauty. Whether it's the breaking or the non breaking of the symmetry, it makes you wonder why having why? Like uh so I come from Russia and the question of dostoyevsky, he's he has said that beauty will save the world. Maybe maybe as a physicist, you can tell me, what do you think he meant by that? [/INST] I don't I don't know if it saves the world, but it does turn out to be a tremendous source of insight into the world when we uh investigate kind of the most fundamental interactions things that are hard to access because they occur at very short distances between uh very uh special kinds of particles whose whose properties are only revealed at high energies at a we don't have much to go on from everyday life. But so we have when we guess what the so we and and the experiments are difficult to do. So you can't you can't really uh follow a very holy empirical procedure to sort of in the bocconi draconian style figure out the law is kind of step by step just by accumulating a lot of data. What we actually do is guess and the guesses are kind of aesthetic really. What what would be a nice description that's consistent with what we know and then you try it out and see if it works and by gosh it does and many profound cases. Uh so there's that but there's another source of symmetry which I didn't talk so much about in in a beautiful question but does relate to your comments and I think very much relates to uh the source of symmetry that we find in biology and in in in our in our heads, you know, in our brain, which is that uh I thought I'd well it is discussed a bit in a beautiful question and also in fundamentals is that when you have symmetry is also a very important means of construction. So when you have for instance a simple viruses that that need to construct their coat their protein coat, the coats often take the form of platonic solids. And the reason is that the d viruses are really dumb and they only know how to do one thing. So they make a pentagon, then they make another pentagon and make another pentagon and they all glued together in the same way and that makes a very symmetrical object sort of so the rules of development when when you have simple rules and they go they work again and again you get symmetrical patterns. That's it's kind of in in fact it's a recipe also for generating fractals, you know? Well I really like. Uh huh wow. The kind of broccoli that has all this internal structure and I wish I had a picture to ship but maybe people remember it from the from the uh from the supermarket and you say how did the vegetable so intelligent to make such a beautiful object of all this fractal structure and the secret is stupidity. We just do the same thing over and over again. And uh in our brains also. You know we we came out we start from single cells and they reproduce and they each one does basically roughly the same thing. They they uh the program evolves in time of course different different modules get turned on and off genetic, different regions of the genetic code get turned on and off. But uh but basically a lot of the stuff, same things are going on and they're simple things. And so you produce the same patterns over and over again and that's a recipe for producing symmetry. Do you think the same thing in many, many places? And if you look at, uh, for instance, the beautiful drawings of roman alcohol, the great neuro anatomist who drew the structure of different organs like the hippocampus. You see, it's very regular and very intricate and its symmetry and in that sense, it's because it's many repeated units that, that you can take from one place to the other and see that they look more or less the same. </s>
<s>[INST] you get, you get to detect what is the motivation for the right reason and that gives you some calm. [/INST] That's exactly right. So the second right, you start to notice this, hey man, this ain't me, this ain't our </s><s>[INST] group. Third [/INST] riot, no ship third riot. You lay in your bunk and you let them, you let them wage war all around you And every now and then you have an inmate that will run up to you and they'll point to a locker. Is that your locker? And if you tell them yes, they leave it alone. If you say it's not my locker, they'll break into it and steal everything out of it and go from there and that's what happens. But </s><s>[INST] you did your time for five years, 5.5 5.5. He made it out, [/INST] made it out. I went through the, I told you it was a good lie that I told I went through the residential drug abuse program. It's a nine month intensive therapy and the way I got to that this counselor at big spring he bought this, he wanted inmates to be educated. He was a really good guy so he wanted inmates to be educated. He got a discount on a game theory class set. </s><s>[INST] So [/INST] he gets all these discussions and everything and he's he's asking does anybody on the compound know anything about game theory? And somebody says if anybody does it'll be Brett johnson. So he comes up to me one day at my buddy's like are you Brett johnson? I was like yeah he was like do you know anything about game theory? And I was like yes I do. So I start rattling off prisoner's dilemma and everything else. He's like will you teach a class? So I started teaching that I start teaching inmates um public speaking and to make friends with his counselor. So </s><s>[INST] I get it gets [/INST] time where I'm supposed to be transferring out to this drug program that they only had in Fort Worth and the transfers are taking like four or five months that's four or five months I could be out free. So I walked I went up to him one day and I was like look his name was keely I was like look man I said is there any way that I can get transferred out any sooner? And he looks at me, he's like Brett I cannot help you and I was like I appreciate that, thank you so much for even trying. So he said that a week later I'm on a bus going to fort Worth. So he got support worth. Yeah. </s><s>[INST] So [/INST] it was a nine month program. 24 hours a day of cognitive behavioral therapy. Had nothing to do with drugs. It was all peer peer study stuff and the CBT training. And uh honestly it's the best thing that could ever happen that </s><s>[INST] part. What what is it? What was the thing that changed you as a man? Is that the solitary confinement? Was it the years? Was it losing the people you loved or was it that behavioral therapy? [/INST] It's a combination man. It's a combination. It was so my sister disowns me the only person I had in my life. You know that I mean me and my sister. That's it. You know I mean Yeah I loved Elizabeth. I love my wife now but you know it's me and my sister. We went through all that ship together so Denise disowns me. She doesn't talk to me for an entire year when all this stuff happens and after I get arrested on the escape she she ends up driving seven hours to come see me to tell me she loves me and I don't see her again for 5.5 years. Yeah so that's that's really the first turnaround took me 2.5 years in prison to accept responsibility. That </s><s>[INST] was amazing that she did [/INST] that. She </s><s>[INST] drove down. [/INST] Yeah she's something, she's something she saw me for 10 minutes tell me she loves me. And then I don't </s><s>[INST] think [/INST] so. </s><s>[INST] But yeah, you had time to think. It took [/INST] 2.5 years to to realize that, you know, I didn't commit crime because of stripper girlfriends or wives or family I committed because I wanted to I chose to and that's the first turn around. 2nd turnaround is like the CBT training, you know that it didn't it didn't really hit while I was in prison. You know, I went through it and they ingrained it in you, but until you choose to make it work, it doesn't work. So I got out in 2011. Didn't want to break the law. Did not. And I was under three years probation. Couldn't touch the computer. I had a job offer from Deloitte to run a cybercrime office in the UK, which that was a no, no, you're not moving. And that's a computer idiot. </s><s>[INST] So [/INST] then I had a job offer from No, before a fishing company couldn't take that. I got to where I was trying to apply for fast food jobs. That's a computer. Can't touch that. Okay then. What about a waiter's position? Well, that's a computer and access to credit cards, idiot. Can't touch that either. So literally could not get a job, could not um doing food stamps. I had a roommate that paying half the rent. They tell you when you leave prison to get a job and something you care about and you won't reciprocate, couldn't get a job. And what I had was a cat and monster, the cat that was the cat's name. And </s><s>[INST] yeah, I [/INST] had had enough money to feed that little guy and didn't have money to buy toilet paper for the apartment. So there's I was on Panama City Beach </s><s>[INST] like this. [/INST] It was a steady decline because remember I taught my dad how to commit tax fraud. So he bankrolled a lot of that until he couldn't and then from there it's like what do you do? So I didn't want to go into computer crime at all. And I ended up shop lifting toilet paper, man, shoplifting, toilet paper. </s>
<s>[INST] I'd love to hear your thoughts about GPT. [/INST] Yeah. In the last, in the last few months we've had, you know, we've we've the world has now seen a chat engine or a text engine I should say called GPT three. Um you know, I think it's still, you know, it does not pass a touring test. You know, there are no real claims that it passes the turing test, right? You know, this is kind of comes out of the group at open ai and you know, they're you know, they've been relatively careful and what they've claimed about this system. But I think this this this as clearly as Eugene Guzman was not in advance over Eliza, it is equally clear that this is a major advance over, over over Eliza or really over anything that the world has seen before. Uh this is a text engine that can come up with kind of on topic, you know, reasonable sounding completions to just about anything that you ask. You can ask it to write a poem about topic X in the style of poet why? And it will have a go at that. And it will do you no, not a not a great job. Not an amazing job, but you know, a passable job, you know, definitely, you know, as as good as you know, you know, in many cases I would say better than I would have done, right. Uh you know, you can ask it to write, you know, an essay like a student essay about pretty much any topic and it will get something that I am pretty sure would get at least a b minus, you know, and the most, you know, high school or even college classes, right? And you know, in some sense, you know, the way that it did this, the way that it achieves this, um, you know, scott alexander of the, you know, the much mourned blog slate, star codex had a wonderful way of putting it. He said that they basically just ground up the entire internet into a slurry. Okay. And you know, and uh to tell you the truth, I had wondered for a while why nobody had tried that, right? Like why not write a chat pot by just doing deep learning over a corpus consisting of the entire web. Right? And, and so, so now they finally have done that, right? And, you know, the results are, are very impressive. You know, it's not clear that, you know, people can argue about whether this is truly a step toward general ai or not, but this is an amazing capability uh that, you know, uh we didn't have a few years ago that, you know, a few years ago, if you had told me that we would have it. Now, that would have surprised me. And I think that anyone who denies that is just not engaging with with what's there. So </s><s>[INST] their model takes a large part of the internet and compresses it in a small number of parameters relative to the size of the internet and is able to without fine tuning uh, do a basic kind of a quarrying mechanism just like you describe where you specify a kind of poet and then that you want to write a poem and somehow was able to do basically look up on the internet Well, of relevant things. I mean, that's what [/INST] I mean. I mean, I mean, how else do you explain it? Well, okay. I mean, I mean, I mean, the the training involved, you know, massive amounts of data from the internet and actually took lots and lots of computer power, lots of electricity, right? You know, there are some some very prosaic reasons why this wasn't done earlier, right? But um, you know, it costs some tens of millions of dollars, I think, you know, it's just for like a few million dollars. Okay. Okay. Really? Okay. Uh, you know, as you Oh, all right, all right, thank you. I mean, as they as they scale it up, you know, it will cost, the </s><s>[INST] hope is cost comes down and all that kind of [/INST] stuff. But um, basically, you know, it is a neural net, you know, so, I mean, I mean, or what's now called a deep net, but, you know, they're basically the same thing. Right? So, it's a it's a form of, you know, uh algorithm that people have known about for decades, right? But it is constantly trying to solve the problem, predict the next word. Right? So it's just trying to uh predict what comes next. It's not trying to decide what what it should say what ought to be true. It's trying to predict what someone who had said all of the words up to the preceding one would say next. </s><s>[INST] Although to push back on that that's how it's trained. But [/INST] it's arguable. </s><s>[INST] Arguable that are very cognition could be a mechanism as that simple. Of [/INST] course of course I never said that it wasn't. But yeah I mean I mean sometimes that that is you know if there is a deep philosophical question that's raised by GPT Three then that is it right. Are we doing anything other than you know this predictive processing just trying to constantly trying to fill in a blank of what would come next after what we just said up to this point. Is that what I'm doing right now? </s><s>[INST] Is it possible? So that the intuition that a lot of people have, well look this thing is not gonna be able to reason the mountain Everest question. Do you think it's possible to G B T 56 and seven would be able to with this exact same process begin to do something that looks like it's indistinguishable to us. Humans from reasoning. [/INST] I mean the truth is that we don't really know what the limits are right? Because because you know what we've seen so far is that you know, GPT three was basically the same thing as GPT two, but just with you know, a much larger uh network, you know, more training time bigger training corpus. Right. And it was, you know, very noticeably better right? Than than its immediate predecessor. So, uh you know, we don't know where you hit the ceiling here. Right. I mean, that's the that's the amazing part and maybe also the scary part. Right? That uh you know, now my guess would be that that, you know, at some point like there has to be diminishing returns. Like it can't be that simple kind of Right. Right. But I I wish that I had more to base that guests on. Right? Yeah. I </s>
<s>[INST] Or girdles of [/INST] theorem. I I studied this as an undergraduate, you know, the incompleteness theorem that there are propositions within any logical system that's rich enough to accommodate uh accommodate arithmetic, they're going to </s><s>[INST] be propositions [/INST] that you can formulate that are true, but that you cannot prove to be true. Uh so the idea that you could systematically develop a logical framework for mathematical inquiry, </s><s>[INST] uh [/INST] that could demonstrate the truth or falsity of any proposition uh is uh </s><s>[INST] not a feasible [/INST] goal. This was Hilbert's project as I understand it. And uh, girdle showed that there was no hope ever of being able to </s><s>[INST] demonstrate [/INST] the closure of of of logical systems that were rich enough to accommodate the real numbers. They gave an </s><s>[INST] existential crisis to all uh mathematicians and scientists alike and humans [/INST] because maybe you can't </s><s>[INST] prove everything. I [/INST] remember, you know, when I was, I was a junior college, a community college student before I </s><s>[INST] transferred to Northwestern and I took a [/INST] calculus course. </s><s>[INST] uh and it was a lot of fun [/INST] and it was differentiating uh algebraic expressions and integrating and using trigger demetric substitution is, and it was a lot of simple problem </s><s>[INST] solving. I get [/INST] to Northwestern, I take a course in differential </s><s>[INST] equations. [/INST] And again, it was a lot of formula, you know, applying if you get a differential equation of this structure, like if it's linear, you've got exponential etcetera, you can solve it. And then I took a course that showed me, you know where the question was, not how to solve any particular functional expression. But it was proving the existence of a solution to a differential equation where it was like X dot equals F of x and T and F is just some arbitrary </s><s>[INST] function. [/INST] What do I have to assume about the function F in order to know that there exists a solution to the differential equation dx DT </s><s>[INST] equals F of X and T. [/INST] And it's basically they called it a Lipschitz </s><s>[INST] condition. It's a [/INST] condition about the bounding of the </s><s>[INST] the slope [/INST] of the function F as a function of X. That it doesn't uh that you can </s><s>[INST] sort of uniformly [/INST] bound the slope on that function. And then you can use a iterative process to show that the sequence of, you know, partial solutions to the thing, convergence to something </s><s>[INST] that's a solution to the [/INST] real thing anyway. Again, I'm not not gonna bore you or uh pretend that I'm a mathematician, I'm not. But what I'm saying is the difference between </s><s>[INST] a [/INST] specific Algebraic formula that you can manipulate and solve on the one </s><s>[INST] hand, and [/INST] the abstract question of whether there exists a solution in the general </s><s>[INST] case [/INST] is like a huge, was like a huge step for me in my study of mathematics and um the techniques that you have to employ to address </s><s>[INST] these [/INST] larger questions and and so on. So I, you know, when I was an undergraduate, I took the first year PhD sequence in math analysis at </s><s>[INST] Northwestern from [/INST] a brilliant </s><s>[INST] mathematician named [/INST] Abner Friedman </s><s>[INST] um [/INST] and learn about measure theory. </s><s>[INST] And [/INST] you know, I learned </s><s>[INST] about uh [/INST] uh some some early functional analysis ideas and when I saw that those ideas were being applied by advanced study in economics, I was delighted I found an intellectual </s><s>[INST] home. So the one of [/INST] the fascinating challenges </s><s>[INST] in mathematics is to think how can you consider which echoes the challenge of economics, What are the properties of an [/INST] equation that </s><s>[INST] allow you to say something profound and say it's simply. And so the question of economics is how do you construct the model where [/INST] you can generalize </s><s>[INST] nicely and say something profound [/INST] and say it </s><s>[INST] simply. Uh so one of [/INST] the questions, </s><s>[INST] one of the challenges [/INST] of economics </s><s>[INST] is macro [/INST] versus micro economics </s><s>[INST] is um [/INST] you </s><s>[INST] know, the world is made up of individuals. So there's a connection to our discussion of, of race and discrimination and outcomes and all those kinds of things. The world is made up of individuals. But in order to say something general, we have to construct groups in order to analyze the data. We have to aggregate that data. Somehow we have to make an [/INST] average over some set of </s><s>[INST] people. So what are the pros and cons of looking at things like equality of opportunity and equality of outcome based on groups versus based on individuals? And what are the groups [/INST] if </s><s>[INST] there's any pros to looking at groups that we should be looking at? Okay, well, those, those are big [/INST] questions. I mean in economics, you're </s><s>[INST] right. I mean, micro you have an account of [/INST] how individuals </s><s>[INST] make decisions about spending their money [/INST] on this consumption side </s><s>[INST] and about how enterprises [/INST] make decisions </s><s>[INST] about what to produce, how much of it, what inputs to use, what techniques of production and so on. Individual [/INST] firms, </s><s>[INST] individual consumers. And then you want to aggregate. [/INST] So there's a theory </s><s>[INST] of so called theory of [/INST] general equilibrium </s><s>[INST] where, you know, [/INST] you think supply and demand and a bunch of markets, </s><s>[INST] you think prices [/INST] that moved to </s><s>[INST] equal a break. [/INST] But you recognize that the price in one market </s><s>[INST] affects people's behavior [/INST] and another. The markets </s><s>[INST] interacting with each other. You [/INST] realise that the behavior of one individual </s><s>[INST] affects the uh [/INST] supplies and </s><s>[INST] available resources and for [/INST] other individuals. So they're knitted </s><s>[INST] together in some kind [/INST] of systematic </s><s>[INST] way. [/INST] And you you </s><s>[INST] want to try [/INST] to demonstrate the fact that notwithstanding all these interdependencies. </s><s>[INST] There exists [/INST] a solution </s><s>[INST] to the [/INST] system of equations that equates </s><s>[INST] demand and supply across all [/INST] the different markets. This is the existence </s><s>[INST] of general [/INST] equilibrium. Then you want to try to say something </s><s>[INST] about the [/INST] properties of an equilibrium if it exists, is it efficient? </s><s>[INST] Well, what do you mean by [/INST] efficiency? </s><s>[INST] Well, the [/INST] idea of so </s><s>[INST] called Peredo efficient outcomes, These are outcomes that cannot be [/INST] uniformly improved upon. Everybody </s>
<s>[INST] Oh, oh, she's, she's actually, she's out shopping right now where [/INST] we've </s><s>[INST] been having sex multiple times a day ever since. That's [/INST] nice. That's lovely. </s><s>[INST] I think I'm sure she's married and, and happily and has many grandchildren. Okay. Uh and plus that movies on thanksgiving, I think great thanksgiving. So like thanksgiving. Just embodies that forget about the business and the whatever the career you're chasing in life and just take a pause and appreciate the people, you lost [/INST] your family or your family, </s><s>[INST] friends. Yeah. Uh you have some weird friends, unorthodox friends. So, so at least in the public [/INST] sphere </s><s>[INST] from bob lee bryan callen, all those kinds of folks from the mad tv days, I'm sure there's others. What does it mean to be a good friend [/INST] here in L. A. Or just in </s><s>[INST] general? In the world? [/INST] The world will friend? I think it is different here, I think it is. I </s><s>[INST] think there's a little bit of a career kind of negotiation shuffling around that kind of stuff. Different. [/INST] Oh I I just mean, I mean, I mean that it's just kinda hard here too to make time everybody. There's so there's it's always been a city to me that is like we'll keep you so busy and every time I go home to Vancouver after a few days I start to get a little stir crazy and I think that being here in in L. A. I go to sleep with 100 things that I still have to do and you never, you're never out of stuff to do and if you um you know when you ask about are you nuts or whatever, if you're crazy. I mean look every all the weirdest people from every high school in the United States is like, you know, I'm gonna make it in L. A. You know, everyone just comes here and uh just another freak in the freak kingdom as they say at the end of fear and loathing in las Vegas. That was a very good Robin Williams impersonation, that was my Robin Williams as johnny Depp as Hunter s Thompson. It's not your fault </s><s>[INST] Will it's pretty good. [/INST] Thank you. Could have </s><s>[INST] been you [/INST] in fear and loathing. </s><s>[INST] I [/INST] would have liked to play his attorney. The role that Del Toro gained weight for. That would have been cool. He's just he's just what uh chewing his face off. I could have done that. Um uh yeah, no, I think that it's </s><s>[INST] backdoor beauty. That guy is full of good lines. [/INST] Yeah. Um </s><s>[INST] yeah. [/INST] Fantastic actor. I think, I think what it takes to be a good friend is just, you know, presence just being there. I mean that's all anyone needs to be heard right? Um in L. A. It is, it is interesting. It is you I haven't seen people that I love in years. Some people you </s><s>[INST] still have a depth of connection even though like one of the reasons I really enjoy doing a podcast, you get to sit down with with actual friends of yours and spend prolonged periods of time together that you don't otherwise [/INST] that </s><s>[INST] I've spoken on this podcast that people really close to me. It's like you've never had a conversation without microphones like you do with microphones. It's weird but uh there's some aspect about L. A. That, you know, a lot of the especially friends of yours comedians and so on. They'll do podcasts and stuff and there's uh I don't know, there's an intimacy to that. [/INST] Yeah, yeah, there is and there isn't the ones that I do, I mean I just did bobby lee and Andrew Santino is </s><s>[INST] funny enough called Bad Friends [/INST] Bad Friends and afterwards and my good pal chad Culleton with whom I do do Dzi was with me, </s><s>[INST] sneakers are coming soon, [/INST] sneakers are coming soon, you get your will foot and you're chad foot comes in a size 15 9.5. Um and uh I remember afterwards we were talking, it was just basically me chad and Santino, we're talking and bobby was over there, you know, on his phone and then I was like, well, I mean we didn't spend any time talking about anything, it feels like one of those hours that goes by and you realize I've just been goofing around with these guys, which </s><s>[INST] it's [/INST] great and then I'm like alright bobby, hey bob, I'll see you later and he's like, like this alright man, hey, love you bro, See you later. </s><s>[INST] Yeah, [/INST] he's a guy. Do you ever just, I just send text messages over there to him that never come back and then he thinks that I'm angry with him because it's been, you know, it'll go to three years without him getting back to me and then just out of nowhere face and uh </s><s>[INST] you know, [/INST] I got to be very, I gotta be very careful bobby. Yeah, I got to be very sweet </s><s>[INST] dear friend, [/INST] dear friend, Hello, how are you doing? How are you? I know I checked in with you but not but three months ago uh And then every once in a while he'll go hey </s><s>[INST] I tend to hide from the world and I I can be pretty shady with friends text back. Yeah I can empathize with bobby. Might be a Skyrim thing. It might be like hiding in the world in the digital world with fake fake N. P. C. S. [/INST] Yeah. Yeah there's that uh yeah you know I have a buddy who said something really smart while ago we ended up working together on this uh tv show thing and I reached out to him to see if he wanted to do it with us and he did and he goes this is a great guy. Such a funny writer. He goes I may not be in touch all the time but I know who my friends are you know what I mean and it's like in our business and this is a fellow who moved um who's from Ontario Canada moved back there. He's on the farm with his wife and kids and he does not care. He's never been a Hollywood guy and uh it's tough to get hold of him but when you do you know he's still the same sweet old guy he's doing his thing though. </s>
<s>[INST] Great. So let me ask you sort of uh sorry to to pull back to the the idea of governments and decentralized currency uh you know there's a tension between decentralization of currency and the power of nations, the power of governments you uh what's your sense about that tension? Can is there some rule for regulation of currency? Yeah. Is there like is the government the enemy of digital currency of distributed currency or can they be like cautious friends? [/INST] I mean I think like one thing that people forget is that it's clearly not entirely an enemy because I think if uh there hadn't been so much government regulation on the kind of centralized that like issuing centralized digital currency is done like we'd be seeing things people like google and facebook and twitter are just kind of issuing them left and right. And then like if that was the case then decentralized currencies would still appeal to some people, but they definitely would appeal to less people than today. So even in that sense, I think it's uh clearly been and more of a help just going to set the stage for the end of the existence as of of the sector in some ways. But also and I think some of both, you know, like there's definitely things that governments kind of can do in some cases have done to have heard the spread of uh in the growth of uh of block chains, there's things that they've done to help and they've uh in some cases definitely done a good job of and going after fraudulent projects. I ended going after some of the projects that have some of the kind of craziest and most misleading marketing. Um there's also the possibility of the governments will end up using block chains for a lot of different things like you know governments, you know, and they do a lot more than just regulating, right? Like there's also they have the end of identity records and they have kind of like property registry is even their own currency is like secure lots of different kind of things that they're operating and there's even watching applications and a lot of those. </s><s>[INST] Yeah. And they can, you know, they can leverage technology do a lot of good for our societies. It is a little unfortunate that governments often lag behind in terms of their acceptance the leverage of technology. If you look at the autonomous vehicle space ai in general, they're uh they're a few years behind. It would be nice to help them catch up. That's uh that's that's always ongoing problem. You met Vladimir Putin to discuss the centralized currency year you're born and uh where were you born [/INST] Colombia. It's a city about 115 km south of Moscow </s><s>[INST] in Russia. Yes. Yeah. I grew up in Moscow. I mean that's Vladimir Putin is uh is a central figure in this part of the world. So what was that like meeting, meeting him? What was that experience like? [/INST] He's tolerant photos than in person. </s><s>[INST] Yeah. Yeah, that's right. He's 5, 7 I think 58 maybe. [/INST] Yeah, it's uh unfortunately we didn't actually, I kind of have too much of a chance to talk to him. Like I managed to see him for about one minute at the end of this meeting and I didn't get a chance to see a lot of like some of the other end of government ministers and he recommended some and uh some of them are are actually and interested in trying to use a block chains too. Look for various government use cases they kind of limit corruption and other things. And I have like it's hard to tell from one conversation kind of what things are genuine and what things are just like watching a school, let's do watching. But </s><s>[INST] you know when I when I listen to like Barack Obama talk about artificial intelligence, there's certain things I hear where. Okay so he might not be an expert in ai but he no he like actually studied it carefully enough to think about it. Like he can turn a lot like uh even if it's just reading a Wikipedia page, like he really thought about what this technology means. Did you get a sense that uh Putin or some of the ministers like thought about Blockchain. Like thought about the fundamentals and technical like understand it intuitively or they too old school to try to grasp it [/INST] summer old school suburb or in new school. It depends it's it's definitely depends on who you talk to. </s><s>[INST] I mean that's an open question for me with Putin because Putin has said, I [/INST] don't know, I've only talked to him for about one minute. So </s><s>[INST] but sometimes you can pick up sort of insights, it's a quick comment there about maybe you can correct me on this, but they're about 3000 cryptocurrencies being actively traded. Uh ethereum is one of you know, a lot of people believe that there will be the main Cryptocurrency. I think Bitcoin is currently still the main Cryptocurrency but A theory and very likely might become that the main one. Um Is this kind of diversity good in the crypto world? You see it sticking around? Should there should there be a winner? Like should there be some consensus globally around Bitcoin or around a theory and like what's your what's your sense? [/INST] And I definitely think that diversity is good and I definitely think also that there's probably too many people trying to make separate watching some kind of right now, the numbers should definitely be greater than one and probably greater than two or even five. Not 3000. Not 3000. Yeah. And also not even like 40 high quality platforms to try to do the same thing. Yeah. There's definitely this arrange from just like one person who just like wrongly thinks that you can create a Cryptocurrency in like 12 hours and uh doesn't even think about kind of the community aspects of maintaining it going to uh people actually trying but only creating a really tiny one to like scammers to people, like making something that's actually successful and uh then, you know, there's a lot of different categories of watching and project in terms of what it's trying to do and what applications it's for. Um and I think the experimentation is definitely healthy, </s>
<s>[INST] Do you have hope that Jews, Muslims, and Christians in this land will live in peace one day together? Have a basic respect for each other's humanity? [/INST] Look, look, this isn't a religious conflict. I think that's fundamentally one of the problems. So even the question is not the correct question? It's not the correct question. This is not a religious conflict. Yes, religion is invoked. Yes, there are religious elements, but there are many Jews that are opposed to what is happening right now towards the Palestinians, many, and I would recommend a serious discussion with even people whose perspectives have grown. Peter Beinert being an example, Rabbi Simone Zimmerman started, if not now. Beit Tislim, an Israeli human rights organization that also classed it as apartheid recently. There are many Jews that are opposed to what is happening right now. Palestinians are also not exclusively a Muslim population. Sherina Barakahla was Christian. There are many Palestinian Christians that are also being denied entry into their historic churches and that are completely bewildered or absolutely lost in regards to why American evangelicals have this ironclad support for the occupation and have ignored the plight of Palestinian Christians. Of course I believe Muslims, Christians, and Jews can coexist. Of course I have hope because I have to have hope as a person of faith, but as much hope as I have, I think there's a great sense of urgency for people to open their eyes, learn what's actually happening on the ground, read the reports, stop letting these commentators and these companies that are able to generate propaganda own the narrative. There are objective standards here. There are objective measures of oppression that need to be considered here. What's happening to Gaza is one of the greatest atrocities of our time. Learn about it, right? I'd tell people to just watch the vice documentaries, for example, the mini documentaries. I'd sent them to you as well inside the battle for Jerusalem. I mean, think about it. A guy from Long Island, New York can fly to Israel, right? Fly into Tel Aviv and walk into a home that's been occupied by families for generations and throw the people out under the full protection of the military there and spit on them historic homes. And when people come up to me and say, we're opposed to Islamophobia, we're opposed to Islamophobia, but they support that. I tell you, you're not opposed to Islamophobia. How can you be opposed to Islamophobia when you traffic in the same framings and dehumanization that enables the viciousness towards Muslims here and Palestinians over there that they do not deserve to be treated like equal human beings, like full human beings. And that based on historic claims, a guy can fly from New York into a historic neighborhood in Jerusalem and kick out generational families with military guns next to them. What does that sound like? How's that normal? And so I think that if people take the time to read, people take the time to investigate, then they come to this conclusion themselves, that this is unacceptable. And that you can't put, and this is one of the problems with the framing of Israel-Palestine, is that you're equating occupier and occupied. You're equating the two sides of the conflict. And it's not a conflict, it's an occupation. There is such a disparity of power here that you cannot equate the two sides. Malcolm X would say, you clip the bird's wing and then blame it for not flying as high as you do. You can't do that to a people and just equate them with their occupier. It's an atrocity. It requires us to challenge it. And I'm hopeful at the current movement of Muslims, Christians and Jews and people of all fates that are saying enough is enough, that thresholds have been crossed here, that this is an atrocity that cannot continue. This is very personal to me because this is happening now. What I anticipate, and this is what America did, this is what Nelson Mandela actually predicted with the United States. What I anticipate is that 10 years from now, 20 years from now, every American will say, how could we have supported this? And this was terrible. And we'll pay symbolic homage to the Palestinian cause. But there are people now that are clinging on for dear life, access to their places of worship, access to their generational homes. Right now at this very, there are children that are in detention and there's a bill in Congress to just stop. I mean, wherever you stand on this issue, child detainment, child detention should be a red line. Congresswoman Betty McCollum has put this bill on the floor of Congress. She can't even get that passed just to at least censure child detainment by the IDF. So people need to look into this deeper. They need to consider the human element of this and consider the urgency of it as well. With this new regime, it's only going to unfortunately get much worse in the immediate </s>
<s>[INST] you just said is complex. But if we're trying to simplify it, who do you think most likely it would be successful if we push on this group of people? Is that the doctors is that the hospitals, is that the governments of policymakers? Is it the individual patients, consumers who needs to be inspired to most likely lead to adoption or is there no simple answer. [/INST] There's no simple answer. But I think there is a lot of good people in medical system who do want to make a change and I think a lot of power will come from us as consumers because we all are consumers of future consumers of health care services and I think we can do so much more in explaining the potential and not in the hype terms and not saying that we now killed all the time. And you know, I'm really sick of reading these kind of articles which made these claims but you need to show with some examples what this implementation does and how it changes the care because I can't imagine it doesn't matter what kind of politician it is. You know, we all are susceptible to these diseases, there is no one who is free and eventually you know, we all humans and we are looking for way to alleviate the suffering and and this is one possible way where we currently are under utilizing which I think can help. </s><s>[INST] So it sounds like the biggest problems are outside of ai in terms of the biggest impact at this point. But are there any open problems in the application of Ml to oncology in general? So improving the detection or any other creative methods, whether it's on the detection segmentation of the vision perception side or some other clever of inference. Yeah. What in general, in your in your view or the open problems in this space. [/INST] So I just want to mention that besides detection and that the area of what I am kind of quite active and I think it's really an increasingly important area in healthcare is drug design because uh you know, it's fine if you detect something early, but you still need to get, you know, to get drugs and new drugs for these conditions and today, all of the drug design ml is non existent that we don't have any drug that was developed by the male model or even developed by at least even you that Ml model plays a significant role. I think uh this area with all the new ability to generate molecules with desired properties to do in silica screening uh is really a big open area to be totally honest with, you know, when we are doing diagnostics and imaging primarily taking the ideas that were developed for other areas and you're applying them with some adaptation. The area of, you know, drug design is very technically interesting and exciting area. You need to work a lot with graphs and Capture various three d properties. There are lots and lots of opportunities to be technically creative and um I think there are a lot of open questions in this area, you know, we're already getting a lot of success is even, you know, with the kind of the first generation of these models, but there is much more new creative things that you can do and what very nice to see is it actually the you know the more powerful the more interesting models actually do do better. So there is a place to innovate in machine learning in this area ah and some of these techniques are really unique to, let's say to you know, grow up generation and other things. So </s><s>[INST] what just to interrupt real quick, I'm sorry uh graph generation or graphs drug discovery in general. What's how do you discover a drug? Is this chemistry, is this trying to predict different chemical reactions or is it some kind of what the graphs even represent in this space? [/INST] Oh sorry </s><s>[INST] what's the [/INST] drug? Okay so let's say you think there are many different types of drugs but let's say you're going to talk about small molecules because I think today the majority of drugs small molecules, so small molecule is a graph. The molecule is just where the node uh in the graph is an atom and then you have the bones. So it's really a graph representation. If you look at it in two D. Correct? You can do it's really but let's say well let's keep it simple and stick into the um so pretty much my understanding today how it is done a scale in the companies you're without machine learning you have high throughput screening. So you know that you are interested to get certain biological activity of the compounds. So you kinda lot of compounds like maybe hundreds of thousands, some really big number of compounds. You identify some compounds which have the right activity. And then at this point, you know, the chemists come and they're trying to now to optimize this original heat, two different properties that you wanted to be maybe soluble, You want to decrease toxicity. You wanted to decrease the side effects. Are those </s><s>[INST] side again to drop, can that be done in simulation or just by looking at the molecules or do you need to actually run reactions in real labs with lab? [/INST] So there is, so when you do high throughput screening, you really do screening, it's in the lab, it's really the lab screening you screen the molecules correct screening, you just check them for certain property in </s><s>[INST] the physical space in the physical world. Like actually there's a machine probably that's doing something that actually running [/INST] actually running reactions. So there is a process where you can run and that's why it's called high strung border, become cheaper and faster to do it. And very big number of molecules, you run the screening, you identify potential um you know, potential good starts and then where the chemists come in who have done it many times and then they can try to look at it and say how can you change the molecular all to get the desired uh profile in terms of all other properties. So maybe how do we make it mobile active and so on and there, you know, the creativity of the chemists really um is one that determines the success of this design. Uh because again they have a lot of domain knowledge of what works, how do you decrease the CCD and so on and that's what they do. So all the drugs that are currently, you know in the FDA approved drugs, even drugs that are in clinical trials, they are designed using these uh the main experts which goes through this combinatorial space of molecules and graphs or whatever And find the right one or adjusted to be the right ones. </s>
<s>[INST] Yeah, but so I know it's painful to have explicit decisions but there is underlying [/INST] explicit decisions which is some of the most beautiful fundamental philosophy </s><s>[INST] that we have before us which is personal growth. If I want to watch videos from which I can learn, what does that mean? So if I have a checkbox that wants to emphasize and learning there's still an algorithm with explicit decisions in it that would promote learning. What does that mean for me, like for example, I've watched a documentary on Flat Earth Theory. I guess it was very like I learned a lot. I'm really glad I watched it. It was a friend recommended to me not because I don't have such an allergic reaction to crazy people as my fellow colleagues do. But it was very, it was very eye opening and for others it might not be from others that they might just get turned off from. That same with republican democrat and what it's a non trivial problem. And first of all, if it's done well I don't think it's something that wouldn't happen that uh that youtube wouldn't be promoting or twitter wouldn't be, it's just a really difficult problem how to reduce how to give people control. [/INST] Well it's mostly an interface design problem the way I see it you want to create technology that's like a mentor or coach or an assistant so that it's not your boss, right, you are in control of it, you are telling it what to do for you and if you feel like it's manipulating you, it's not actually, it's not actually doing what you want. You should be able to switch to a different algorithm, you know, </s><s>[INST] so that fine tune control and you kind of learn, you're trusting the human collaboration and that's how I see autonomous vehicles to is giving as much information as possible and you learn that dance yourself. Yeah, adobe don't refuse adobe [/INST] products for like </s><s>[INST] yeah, they're trying to see if they can inject youtube into their interface, but basically allow you to show you all these videos that because everybody is confused about what to do with features. So basically teach people by linking to in that way it's an assistant that shows uses videos as a basic element of information. Okay, so what practically should people do to try to um to try to fight against abuses of these algorithms or algorithms that manipulate us? [/INST] Honestly, it's a very vertical problem because the starfish, there is very little public awareness. I was his issues very few people would think there's anything wrong with their news feed algorithm even though there is actually something wrong already, which is that it's trying to maximize engagement most of the time, which has a very negative side effects. Right? Um, so ideally so the very first thing is to uh stop trying to purely maximize engagement. Try to propagate contents based on popularity, right? Instead take into account the goals and the profiles of each user. So you will you will be one example is for instance when I look at topic recommendations on twitter's like they have this news tab with switch recommendations, it's always the worst garbage because it's it's content that appeals to the the smallest commanding minister to all twitter users because they're trying to optimize a purely trying to obtain its popularity. The purely trying to optimize engagement, but that's not what I want. So they should put me in control of some setting. Uh so that I define was the objective function. Um the twitter is going to be following to show me this content. So and honestly, so this is all about interface design and we are not, it's not realistic to give you this council of a bunch of knobs that define algorithm instead we should purely put them in charge of defining the objective function. Thanks, let the user tell us what they want to achieve, how they want to sell those um to impact their lives. So do you think </s><s>[INST] it is that or do they provide individual article by article reward structure where you give a signal? I'm glad I saw this and I'm glad I didn't [/INST] so like a Spotify type a feedback mechanism. It works to some extent. I'm kind of skeptical about it because the only way the algorithm, the algorithm will attempt to relate um your choices with the choices of everyone else, which might, you know, if you have an average profile that works fine. I'm sure Spotify accommodations work fine. If you just like mainstream stuff, if you don't it can be a it's not often one or two elections will </s><s>[INST] be uh in an efficient search for the for the part of the Spotify world that represents [/INST] you. So it's it's a tough problem. But I do notice that even even a feedback system like what Spotify has does not give me control over what the algorithm is trying to optimize her. </s><s>[INST] Well, public awareness, which is what we're doing now, is a good place to start. Do you have concerns about long term existential threats of artificial intelligence? [/INST] Well, as as I was saying, our world is increasingly made of information. Ai algorithms are increasingly going to be our interface to this world of information and somebody will be in control of the algorithms and that puts us in any kind of a bad situation. Right? Uh It has risks, it has risks coming from potentially large companies wanting to optimize their their own goals? Maybe profit? Maybe something else also from governments who might want to use these uh these algorithms as a means of control of the entire population. Do you think there's </s><s>[INST] an existential threat that could arise from [/INST] that? So kind of existential threats? So maybe you're referring to the singularity narrative where robots to stake over. </s>
<s>[INST] Well, let me push back on one. You see everything you said is correct. But we, as humans tend to, uh, uh, tend to take for granted how how incredible our vision system is. So [/INST] You can drive a car over 2050 vision and you can train a neural network to extract the distance of any object in the shape of any surface from a video and data. Yeah, but that's really simple. </s><s>[INST] It's simple. It's [/INST] a simple data problem. </s><s>[INST] It's not, it's not simple. It's because because it's not just detecting objects, it's understanding the scene and it's being able to do it in a way that doesn't make errors. So the beautiful thing about the human vision system and the entire brain around the whole thing is we were able to fill in the gaps. It's not just about perfectly detecting cars. It's inferring they included cars. It's trying to it's understanding that I think [/INST] that's mostly a data problem. </s><s>[INST] So you think what data with compute with improvement of computation with improvement and [/INST] collection there's a you know, when you're driving a car and somebody cuts you off, your brain has theories about why they did it. You know, they're a bad person, they're distracted, they're dumb. You know, you can listen to yourself. So, you know, if you think that narrative is important to be able to successfully drive a car, then current autopilot systems can't do it. But if cars are ballistic things with tracks and probabilistic changes of speed and direction and roads are fixed and given, by the way, they don't change dynamically, you can map the world really thoroughly, you can place every object really thoroughly right? You can calculate trajectories of things really thoroughly </s><s>[INST] right? But everything you said about really thoroughly has a different degree of difficulty. So [/INST] you could say at some point, computer autonomous systems will be way better at things that humans are lousy at like we'll be better. Abstention. They'll always remember there was a pothole in the road that humans keep forgetting about. Remember that this set of roads houses these weirdo lines on it, that the computers figured out once and especially if they get updates. So if somebody changes are given, like the key to robots and stuff, somebody said is to maximize the givens. </s><s>[INST] Right, Right, [/INST] right. So, so having a robot pick up this bottle cap as well as you put a red dot on the top, because then you have to figure out if you want to do certain things with it, you know, maximize the givens is the thing and autonomous systems are happily maximizing the givens like humans when you drive someplace new, you remember it because you're processing it the whole time and after the 50th time you drove to work, you get to work, you don't know how you got there, right, you're on autopilot, right? Autonomous cars are always on autopilot, but the cars have no theories about why they got cut off or while they're in traffic. So that's never stopped paying attention. </s><s>[INST] So I tend to believe you do have to have theories, meta models of other people, especially pedestrians, cyclists, but also with other cars. Everything you said is uh, is actually essential to driving, Driving is a lot more complicated than people realize, I think sort of push back slightly, but [/INST] cut into traffic, right? You can't just wait for a gap. You have to be somewhat aggressive. You'll be surprised how simple the calculation for that is. </s><s>[INST] I may be on that particular point, but there's um uh, I maybe I should have to push back. I would be surprised. You know what? Yeah, I'll just say where I stand. I would be very surprised. But I think it's, you might be surprised how complicated it is that [/INST] I say. I tell people it's like progress. Disappoints in the short run surprises in the long run. It's very possible. I suspect in 10 years it'll be just like taken for granted </s><s>[INST] but you're probably right now it looks [/INST] like it's going to be a $50 solution that nobody cares about. Gps is like, wow gps is we have satellites in space that tell you where your location is. It was a really big deal. Now. Everything has a Gps and </s><s>[INST] yeah, that's true. But I do think that systems that involve human behavior are more complicated than we give them credit for. So we can do incredible things with technology that don't involve humans. But when [/INST] the Cubans are less complicated than people, you know, frequently, abs cry babe, maybe we tend to operate out of large numbers of patterns and just keep doing it over and over. </s><s>[INST] But I can't trust you because you're a human. That's something something a human would say. But my hope is on the point you've made is even if no matter who's right. You, they're hoping that there's a lot of things that humans aren't good at. That. Machines are definitely good at like you said, attention, things like that. Well, there'll be so much better that the overall picture of safety and autonomy will be obviously cars will be safe even if they're not as good [/INST] as I'm a big believer in safety. I mean they're already The current safety systems like cruise control that doesn't let you run into people and lane keeping. There are so many features that you just look at the parade o of accidents and knocking off like 80% of them, you know, super doable </s>
<s>[INST] totally. And one other thing from my perspective, because I'm now starting a company. I think the interesting thing about Ellen as he serves as a beacon of hope, Like pragmatically speaking for people that sort of to push back on our doom conversation from earlier that a single individual could build something that allows us as self interested individuals to gather together in a collective way to actually alleviate some of the dangers that face our world. So like it gives me hope as an individual, that I could build something that can actually have impact that counter acts the the Stalin's and the Hitlers and all the threats that face uh that human civilization faces, that an individual has that power. I didn't believe that the individual has that power in the, in the halls of government. Like I don't feel like anyone presidential candidate can rise up and help the world unite the world. It feels like from everything I've seen and you're right with Tesla, it can bring the world together to do good. That's a really powerful mechanism of, you know, whatever you say about capitalism, that you can build companies that start, you know, it starts with a single individual. Of course, there's a collective that that grows around that, but the leadership of a single individual, their ideas, their dreams, their vision can catalyze something that takes over the world and does good for the entire world. [/INST] But if I think, but again, I think the genius of the idea is that it doesn't require us to go head to head with human nature, right? He's he's actually built human nature into the idea by basically saying, I'm not asking you to be, uh, an environmental activist, I'm not asking you to sacrifice to make it, I'm going to sell you a car, you're going to like better and by buying it, you'll help the environment that takes into account our foibles as a species and actually leverages that to work for the greater good. And that's the sort of thing that does turn off my little doom casters cynicism thing a little bit because you're actually hitting us where we live, right? You're you're you're not you can take somebody who doesn't even believe the environments a problem, but they want a Tesla. So they're inadvertently helping anyway. I think that's the genius of the idea. </s><s>[INST] Yeah. And I'm telling you that's one way to make love. Much more efficient mechanism of change than hey, [/INST] making it in yourself interesting to </s><s>[INST] make you suggest creating a product that, uh, at least two more love than hate. [/INST] You're gonna want to love your neighbor because you're gonna make a fortune. I'd get there. That's why I'm on </s><s>[INST] board. That's why yuan said love is the answer. That's I think, uh, exactly what he meant. Okay, let's try something difficult. You've recorded episode steering into the iceberg on your common sense program that has started a lot of conversations. It's quite moving. It was quite haunting. I [/INST] made a lot of angry emails </s><s>[INST] really. Of course [/INST] I did something I haven't done in 30 years. I endorsed a political candidate from one of the two main parties and there were a lot of disillusioned people because of that. </s><s>[INST] I guess I didn't hear it as an endorsement. I just heard it as a, the similar flavor of conversations you have in, in hardcore history. It's almost a speaking about modern times in the same voice as you speak about when you talk about history. So it was just a a little bit of a haunting view of the world today. I know we were just wearing our Doom [/INST] Doom Master put that right back on our, you know, </s><s>[INST] the, uh, I like the term doom castor is there, is there? How do we get love to win? What's the way out of this? Is there some hopeful line that we can walk to a to avoid something? And I hate to use the terminology, but something that looks like a civil war, not necessarily a war of force, but a division to a level where it doesn't any longer feel like a United States of America with the emphasis on United. Is there a way out? [/INST] I read a book a while back, I want to say George Friedman. The street for a guy wrote it was something called The Next 100 Years, I think it was called. And I remember thinking um I didn't agree with any of it. And one of the things I think he said in the book was that the United States was going to break up. I'm going from memory here. He might not have said that at all, but something was stuck in my memory about that. I remember thinking, um, but I think some of the arguments were connected to the differences that we had and the fact that those differences are being exploited. So we talked about media earlier in the lack of truth and we have a media climate that is incentivized to take the wedges in our society and make them wider and there's no countervailing force to do the opposite or to help, you know? So there was a famous uh memo from a group called project for a new american century and they took it down. But the way back machine online still has it. And it happened before 9 11 spawned all kind of conspiracy theories because it was saying something to the effect of uh and I'm really paraphrasing here. But you know that the United States needs another Pearl Harbor type event because those galvanized a country that without those kinds of events periodically is naturally geared towards pulling itself apart. And it's those periodic events that act as the countervailing force that otherwise is not there. Um, if that's true, then we are naturally inclined towards pulling ourselves apart. So to have a media environment that makes money off widening those divisions, which we do. I mean, I was in talk radio and and it has those people, the people that used to scream at me because I wouldn't do it. But I mean, we would have these terrible conversations after every broadcast where I'd be in there with the program director and they're yelling at me about heat. Heat was the worthy create more heat. Well, what is heat right here? This division? Right? And they want the heat, not because their political, they're not republicans or democrats either there. We want listeners and we want engagement and involvement. And because of the constructs of the format, you don't have a lot of time to get it. So you can't have me giving you like on a podcast an hour and a half or two hours where we build a logical argument And you're with me the whole way your audience is changing every 15 minutes. So whatever points you make to create interest and intrigue and engagement have to be knee jerk right now. Things they told me once that the audience has to know where you stand on every single issue within five minutes of turning on your show. In other words, you have to be part of a of a linear set of political beliefs. So that if you feel a about subject a then you must feel de about subject D. And I don't even need to hear your opinion on it, because if you feel that way about a you're going to feel that way about D. This is a system that is designed to pull us apart for profit, but not because they want to pull us apart, right? It's a byproduct of the Prophet. That's one little example of a 50 examples in our society that work in that same fashion. So what that project for a new American century document was saying is that we're naturally inclined towards disunity and without things to occasionally ratchet the unity back up again. So that we can start from the baseline again and then pull ourselves apart till the next Pearl Harbor that you'll pull yourself apart, which I think was I think that's what the George Friedman book was saying that I disagreed with so much at the time. Um, so in answer to your question about civil wars, we can't have the same kind of civil war because we don't have a geographical division. That's as clear cut as the one we had before. Right? You have to basically north south line and some border states, it was set up for that kind of split. Now we're divided within communities, within families, within gerrymandered voting districts and precincts, right? So you can't disengage we're stuck with each other. So there's a civil war now, for lack of a better word, what it might seem like is the late 19 sixties, early 19 seventies where you had the bombings and you know, let's call it domestic terrorism and things like that because that that would seem to be something that once again, you don't even need a large chunk of the country. Pulling apart 10% of people who think it's the end. Times can do the damage. Just like we talked about terrorism before and a can of gas and a big lighter. I've lived in a bunch of places and I won't give anybody ideas where a can of gas and a big lighter would take 1000 houses down before. You could blink right? Um, that terrorist doesn't have to be from the Middle East doesn't have to have some sort of a fundamentalist religious agenda. It could just be somebody really piste off about the election results. So once again, if we're playing an odds game here, everybody has to behave for this to work right. Only a few people have to misbehave for this thing to go sideways and remember for every action there's an equal and opposite reaction. So you don't even have to have those people doing all these things, All they have to do is start retribution cycle. </s>
<s>[INST] So one thing that I was clearly bothered by and maybe you could be my therapist as well, [/INST] but you were mine, </s><s>[INST] this is this is a little bit of a miscommunication on both our parts then, because who's paying who for this? I was really bothered by uh amazon banning parler from AWS because my assumption was that the infrastructure, I drew a distinction between AWS, the infrastructure on which competing platforms can be created is different than the actual platforms. So at the standard of the ideal of freedom of speech, I in my mind in a shallow way perhaps applied differently to AWS and I did to twitter it felt that we've created a more dangerous world that freedoms were violated by banning parler from AWS, which I saw as the computing infrastructure which enables the competition of tools, the competition of frameworks of communication. What do you think about this first [/INST] of all? Let me give you the the internet hyena answer. I understand. Dude, just build your own amazon. </s><s>[INST] Yeah. Right. Yes, well, so that's a very shallow statement but it's also one that has some legitimacy, we can't completely dismiss it because uh there's levels to this, to this game. [/INST] Yes and no, but if you really wanted to chase that down one of the great things about a person to person conversation as opposed to like let's have 30 of our closest friends whenever we have a conversation with 30 of our closest friends. You what happens? It's like passing light through a prism every person says something interesting and as a result it's always muddled like nothing ever resolves. </s><s>[INST] Well, one of my conversation with techniques you mentioned you push back is uh first this childlike naivete and curiosity but also ill are simulated real, I'm afraid 14% real. [/INST] All right. So in this paradigm, </s><s>[INST] how could you not see this [/INST] coming? I mean I did a show with Ashley Matthews is the woman behind Riley Reid and specifically about this, it was about the idea that if I move away from politics and go towards sex, I know that there's always a move to use the infrastructure to shut down. Um sex workers and in this case we had operation chokepoint under the Obama administration. We have a positive passion for people who want to solve problems that they don't like this company. They don't like that company payday loans would be another one. And so you have legal companies that are harassed by our financial system that you can't, you know uh as Riley Reid actually couldn't get a male chimp account according to her if I understand her correctly and this idea that you charge these people higher rates because of supposed chargebacks on credit cards. Even if their chargebacks are low yes, we have an unofficial policy of harassment. There's something about everybody who shows up at Davos, uh, they get drunk in the swiss alps and then they come back home and they coordinate and they coordinate things like build back better. We don't really understand what build back better is, but my guess is that build back better has to do with extremism in America. How do we shut down the Republican party as the source of extremism? Now, I do think the Republican Party was cut very extreme under trump and I do believe that that was responsive to how extreme the Democratic Party got under Clinton 1st and then Obama and then Hillary and in all of these circumstances, it's amazing how much we want to wield these things as weapons. Well, our extremism is fine because we pretend that antifa doesn't exist and we don't report what goes on in Portland. But your extremism, my God, that's disgusting. This is the completely ridiculous place that we're in. And by the way, our friends in part are coked up on tech money and they don't appear to hold the courage of their convictions at a political level because it's not in keeping with shareholder value, you know, at some level, shareholder value is the ultimate shield with with which everyone can cloak themselves </s><s>[INST] Well, on that point, donald trump was banned from twitter and I'm not sure it was a good financial decision for twitter, right. Uh, I'm perhaps you can correct me if I'm wrong. [/INST] Are you thinking locally, are you thinking if twitter refused to? Well if twitter refused to ban donald trump, what is the odds that the full force of the antitrust division might find them? I don't </s><s>[INST] know. I see, I see. So there's a complicated thing. [/INST] There's a look, these guys are all having a discussion in very practical terms. You know, you can say you can imagine the sorts of conversations Jack Marks under, we're really glad you're all here. We're all trying to sing from the same hymn alone row in the same direction. We understand free speech were completely committed to it, but we have to draw along with extremism guys, we we just need, we need to make sure we're all on the same page. Well, they </s><s>[INST] use the term violence too and they think over apply it. So basically anybody, uh I'm telling you, I say dumb things to uh to incentivize thoughtful conversation. [/INST] Well, whatever these things are, There is no trace like how old are you lex you're in your mid 30s? </s><s>[INST] Yeah, to late 40s, mid late [/INST] 20s to late 40's </s><s>[INST] somewhere, that's the demographic. And I do [/INST] think that partially what's happened is is that your group has never seen functional institutions. These institutions have been so compromised for so long. Uh you've probably never seen an adult sometimes. I think Ellen looks like an adult. I know that he has a wild lifestyle, but I also see it looks like an adult. What does an adult </s><s>[INST] look like? Exactly. [/INST] So, you know, somebody who weighs things speaks carefully thinks about the future beyond their own life's lifespan. Uh, somebody was a pretty good idea of how to get things done. Isn't wildly caught up in punitive actions, is more focused on breaking new ground than playing rent seeking games. I mean, I really had a positive. I was so completely chast when he was that the world's richest person. He was like, well, that's interesting back to work. It's just like that's that's what it is about. That's what that's what a grown up would do. And it just made, you know, weirdly, I said something about isn't it amazing that the world's richest person knows what Legrand jean is? And he made a terrible Lebron's joke about potentials. But yeah, I mean, I do think that ultimately Ellen may be one of the closest things we have to an adult. And I can tell you that the internet hyenas will immediately descend as to what a fraudster he is for pumping his stock price. Talking his book and all this stuff. Shut up. </s>
<s>[INST] We talked about punk or a conjecture. There's a guy, his Russian, Grigori Perlman, he approved Pancreas conjecture if you can comment on the proof itself, if that stands out to you something interesting or the human story of it, which is he turned down the fields medal for the proof. Is there something uh, you find inspiring or insightful about the proof itself or about the man? [/INST] Yeah, I mean, one thing I really like about the proof and partly that's because it's sort of a thing that happens again and again in this book. I mean, I'm writing about geometry and the way it sort of appears and all these kind of real world problems and but it happens so often that the geometry you think you're studying is somehow not enough. You have to go one level higher and abstraction and study a higher level of geometry and the way that plays out is that, you know, Palangkaraya asks a question about a certain kind of three dimensional object, Is it the usual three dimensional space that we know, or is it some kind of exotic thing? And so of course this sounds like it's a question about the geometry of the three dimensional space, but no paramount understands. And by the way, in a tradition that involves Richard Hambleton and many other people like most really important mathematical advances, this doesn't happen alone. It doesn't have an evacuee. It happens as the culmination of a program that involves many people. Same with wiles by the way, I mean, we talked about Wild and I want to emphasize that starting all the way back with Coomer, who I mentioned in the 19th century, but um, Gerhard fry and Maser and ken ribbit and like many other people are involved in building the other pieces of the arch before you put the keystone </s><s>[INST] in, we stand on the shoulders of giants. [/INST] Yes. Um, so what is this idea? The idea is that, well, of course, the geometry of the three dimensional object itself is relevant. But the real geometry you have to understand is the geometry of the space of all three dimensional geometries. Whoa, you're going up a higher level because when you do that, you can say now let's trace out a path in that space. Um there's a mechanism called Ricci flow. And again, we're outside my research area. So for all the geometric analysts and differential geometry is out there listening to this if I please, I'm doing my best and I'm roughly saying it. So the Ricci flow allows you to say like, okay, let's start from some mystery. Three dimensional space, which Pohanka Ray would conjecture is essentially the same thing as our familiar three dimensional space, but we don't know that. And now you let it flow, you sort of like let it move in its natural path according to some almost physical process. And ask where it winds up and what you find is that it always winds up, you've continuously deformed it. There's that word deformation again. And what you can prove is that the process doesn't stop until you get to the usual three dimensional space. And since you can get from the mystery thing to the standard space by this process of continually changing and never kind of having any sharp transitions, then the original shape must have been the same as the standard shape. That's the nature of the proof. Now, of course, it's incredibly technical. I think as I understand it, I think the hard part is proving that the favorite word of ai people, you don't get any singularities along the way. Um but of course in this context, singularity just means acquiring a sharp kink. Um it just means becoming non smooth at some point. So </s><s>[INST] just saying something interesting about uh formal about the smooth trajectory through this weird space. [/INST] Yeah, but yeah, so what I like about it is that it's just one of many examples of where it's not about the geometry, you think it's about, it's about the geometry of all geometries, so to speak. And it's only by and kind of like kind of like being jerked out of flat land, Right, Same idea. It's only by sort of seeing the whole thing globally at once that you can really make progress on understanding. Like the one thing you thought you were looking at? </s><s>[INST] It's a romantic question, but what, what, what do you think about him turning down the fields medal is uh is that just our Nobel prizes and fields medals? Just, just the cherry on top of the cake and really math itself the process of curiosity of pulling at the string of the mystery before us. That's the cake. And then the words are just icing and uh clearly I've been fasting and I'm hungry, but uh but do you think it's um it's tragic, or just just a little curiosity that he turned down the metal. [/INST] Well, it's interesting because on the one hand, I think it's absolutely true that right, in some kind of like vast spiritual sense, like awards are not important, not important. The way that's sort of like understanding the universe is important. Um on the other hand, most people who are offered that prize, accept it, you know, it is so there's something unusual about his uh his choice there. Um I I wouldn't say I see it as tragic. I mean, maybe if I don't really feel like I have a clear picture of of why he chose not to take it. I mean, it's not he's not alone in doing things like this. People sometimes turned down prizes for ideological reasons, um probably more often in mathematics. I mean, I think, I think I'm right in saying that peter Schultz alike turned down some big monetary prize because you just, you know, I mean, I think at some point you have plenty of money and maybe you think it sends the wrong message about what the point of doing mathematics is. Um I do find that there's most people accept, you know, people given a prize, Most people take it. I mean, people like to be appreciated, but like I said, we're people not that different from most other people, </s>
<s>[INST] as the root of physical theory. So information and computation being the real fundamental [/INST] thing in the universe. Right, that information is a resource. You can't have infinite information in finite space. Information propagates and interacts. And from there, you erect the scaffolding of physics. Now it happens, the words I just said look a lot like quantum field theories, but there's an interesting way where instead of starting with differential equations to get to quantum field theories and quantum field theories, you get to quantization. If you start from computation information, you begin sort of quantized and you build up from there. And so that's the sense in which absolutely, I think about the universe as a computer. The easy way to understand that is just almost anything is computationally universal, but the deep way is it's a real fundamental way </s><s>[INST] to understand how the universe works. Let me go a little bit to the personal and the center bits and atoms. You have worked with the students you've worked with have gone on to do some incredible things in this world, including build supercomputers that power Facebook and Twitter and so on. What advice would you give to young people? What advice have you given them? How to have one heck of a great career, [/INST] one heck of a great life, people. Well, one important one is if you look at junior faculty trying to get tenure at a place like MIT, the ones who try to figure out how to get tenure are miserable and don't get tenure, and the ones who don't try to figure it out are happy and do get it. I mean, you have to love what you're doing and believe in it and nothing else could possibly be what you want to be doing with your life and it gets you out of bed in the morning. And again, it sounds naive, but within the limited domain I'm describing now of getting tenure at MIT, that's a key attribute to it. And in the same sense, if you take the sort of outliers, students we're talking about, 99 out of 100 come to me and say, your work is very fascinating, I'd be interesting to work for you. And one out of 100 come and say, you're wrong. Here's your mistake, here's what you should have been doing. They just sort of say, I'm here and get to work. And again, I don't know how far this resource goes. So I've said, I consider the world's greatest resource, this engine of bright and vene of people of which we only see a tiny little iceberg of it. And everywhere we open these labs they come out of the woodwork. We didn't create all these educational programs, all these other things I'm describing. We tried to partner everywhere with local schools and local companies and kept tripping over dysfunction and find we had to create the environment where people like this can flourish. And so I don't know if this is everyone, if it's 1% of society, what the fraction is, but it's so many orders of magnitude bigger than we see today. We've been racing to keep up with it </s><s>[INST] to take advantage of that resource. Something tells me it's a very large fraction [/INST] of the population. I mean, the thing that gives me most hope for the future is that population. Once a year, this whole lab network meets and it's my favorite gathering. It's in Bhutan this year because it's every body shape, it's every language, every geography, but it's the same person in all those packages. </s><s>[INST] It's the same sense of bright and vene of joy and discovery. If there's people listening to this and they're just overwhelmed with how exciting this is, which I think they would be, how can they participate? How can they help? How can they encourage young people or themselves [/INST] to build stuff, to create stuff? Yeah, that's a great question. So this is part of a much bigger maker movement that has a lot of embodiments. The part I've been involved in this FabLab network, you can think of as a curated part that works as a network. So you don't benefit in a gym if somebody exercises in another gym, but in the Fab network, you do in a sense benefit when somebody works in another network, another lab in the way it functions as a network. So you can come to cba.mit.edu to see the research we're talking about. There's a Fab Foundation run by Sheri Lassiter at fabfoundation.org. FabLabs.io is a portal into this lab network. fabacademy.org is this distributed hands-on educational program. fab.city is the platform of cities producing what they consume. </s><s>[INST] Those are all nodes in this network. So you can learn with Fab Academy and you can perhaps launch or help launch [/INST] or participate in launching a FabLab lab. Well, in particular, from one to a thousand, we carefully counted labs. Now we're going from a thousand to a million where it ceases to become interesting to count them. And in the thousand to the million, what's interesting about that stage is technologically, you go to a lab not to get access to the machine, but you go to the lab to make the machine. But the other thing interesting in it is we have an interesting collaboration on a FabLab in a box. And this came out of a collaboration with SolidWorks on how you can put a FabLab in a box, which is not just the tools, but the knowledge. So you open the box and the box contains the knowledge of how to use it as well as the tools within it so that the knowledge can propagate. And so we have an interesting group of people working on, the original FabLabs, we have a whole team to get involved in the setting up and training. And the Fab Academy is a real in-depth deep technical program in the training. But in this next phase, how sort of the lab itself knows how to do the lab. We've talked deeply about the intelligence in fabrication, but in a much more accessible one about how the AI in the lab in a fact becomes a collaborator with you in this nearer term to help get started. And for people wanting to connect, it can seem like a big step, a big threshold, but we've gotten to thousands of these and they're doubling exactly that way </s>
<s>[INST] to soft power to manage them. So much potential for good, so much capacity for good that Fab Labs and the ability and the tools of creation [/INST] really unlock that potential. Yeah. And I don't say that as sort of dewy-eyed naive. I say that empirically from just years of seeing how this plays out in communities. </s><s>[INST] I wonder if it's the early days of personal computers though [/INST] before we get spam, right? In the end, most fundamentally, literally the mother of all problems is who designed us. So assume success in that we're gonna transition to the machines making machines and all of these new sort of social systems we're describing will help manage them and curate them and democratize them. If we close the gap I just led off with of 10 to the 10 to 10 to the 18 between ChipFab and you, we're ultimately in marrying communication, computation and fabrication, gonna be able to create unimaginable complexity. And how do you design that? And so I'd say the deepest of all questions that I've been working on is goes back to the oldest part of our genome. So in our genome, what are called Hox genes, and these are morphogenes and nowhere in your genome is the number five. It doesn't store the fact that you have five fingers. What it stores is what's called the developmental program. It's a series of steps and the steps have the character of like, grow up a gradient or break symmetry. And at the end of that developmental program, you have five fingers. So you are stored not as a body plan, but as a growth plan. And there's two reasons for that. One reason is just compression. Billions of genes can place trillions of cells. But the much deeper one is evolution doesn't randomly perturb. Almost anything you did randomly in the genome would be fatal or inconsequential, but not interesting. But when you modify things in these developmental programs, you go from like webs for swimming to fingers, or you go from walking to wings for flying. It's a space in which search is interesting. So this is the heart of the success of AI. In part, it was the scaling we talked about a while ago. And in part, it was the representations for which search is effective. AI has found good representations. It hasn't found new ways to search, </s><s>[INST] but it's found good representations of search. And you're saying that's what biology, that's what evolution has done is creative representation structures, [/INST] biological structures through which search is effective. And so the developmental programs in the genome beautifully encapsulate the lessons of AI. And this is, it's embodied, it's molecular intelligence. It's AI embodied in our genome. Every bit as profound as the cognition in our brain, but now this is sort of thinking in molecular thinking in how you design. And so I'd say the most fundamental problem we're working on is it's kind of tautological that when you design a phone, you design the phone, you represent the design of the phone. But that actually fails when you get to the sort of complexity that we're talking about. And so there's this profound transition to come. Once I can have self-rebreeding assemblers placing 10 to the 18 parts, you need to not sort of metaphorically, but create life in that you need to learn how to evolve. But evolutionary design has a really misleading trivial meaning. It's not as simple as you randomly mutate things. </s><s>[INST] It's this much more deep embodiment of AI and morphogenesis. Is there a way for us to continue the kind of evolutionary design that led us to this place from the early days of bacteria, single cell organism [/INST] to ribosomes and the 20 amino acids? </s><s>[INST] You mean for human augmentation or? For life. What would you call assemblers that are self-replicating and placing parts? What is the dynamic complex things built with digital fabrication? What is that? [/INST] That's life. So yeah, so ultimately, absolutely, if you add up everything I'm talking about, it's building up to creating life in non-living materials. And I don't view this as copying life. I view it as deriving life. I didn't start from how does biology work and then I'm gonna copy it. I start from how to solve problems and then it leads me to, in a sense, rediscover biology. So if you go back to Valentina in Ghana making her circuit board, she still needs a chip fab very far away to make the processor in her circuit board. For her to make the processor locally, for all the reasons we described, you actually need the deep things we were just talking about. And so it really does lead you. So let's see. There's a wonderful series of books by Gingery. Book one is how to make a charcoal furnace. And at the end of book seven, you have a machine shop. So it's sort of how you do your own personal industrial revolution. ISRU is what NASA calls in situ resource utilization. And that's how do you go to a planet and create a civilization. ISRU has essentially assumed Gingery. You go through the industrial revolution and you create the inventory of 100,000 resistors. What we're finding is the way the minimum building blocks for a civilization is roughly 20 parts. So what's interesting about the amino acids is they're not interesting. They're hydrophobic or hydrophilic, basic or acidic. They have typical but not extremal properties, but they're good enough you can combine them to make you. So what this is leading towards is technology doesn't need enormous global supply chains. It just needs about 20 properties you can compose to create all technology as the minimum building blocks </s><s>[INST] for a technological civilization. So there's going to be 20 basic building blocks [/INST] based on which the self-replicating assemblers can work. Right, and I say that not philosophically, just empirically, sort of that's where it's heading. And I like thinking about how you bootstrap a civilization on Mars, that problem. There's a fun video on bonus material for the movie. We're with a neat group of people. We talk about it because it has really profound implications </s>
<s>[INST] Yeah, I on that point because I've gotten a huge amount of heat on this and I stand by [/INST] it </s><s>[INST] because I know the human factors community well and the work here is really strong and there's many decades of work showing exactly what you're saying. Nevertheless, I've been continuously surprised that much of the predictions of that work has been wrong and what I've seen. So what we have to do, I still agree with everything you said, we have to be a little bit more open minded. So the, I'll tell you there's a few surprising things that super like everything you said to the word is actually exactly correct, but it doesn't say what you didn't say is that these systems are you said, you can't assume a bunch of things, but we don't know if these systems are fundamentally unsafe that's still unknown. There's there's a lot of interesting things, like I'm surprised by the fact not the fact that what seems to be anecdotally from, from, well from large data collection that we've done, but also from just talking to a lot of people when in the supervisory role of semi autonomous systems that are sufficiently dump at least, which is the that might be a key element is the systems have to be done. The people are actually more energized as observers. So they're actually better. They're they're they're better at observing the situation. So there might be cases in systems if you get the interaction right, where you as a supervisor, we'll do a better job with the system together. [/INST] I agree. I think that is actually really possible. I guess mainly I'm pointing out that if you do it naively you're implicitly assuming something that assumption might actually really be wrong. But I do think that if you explicitly think about what the agent should do such that the person still stays engaged, what the so that you essentially empower the person who more than they could, that's really the goal, right, is you still have a driver, so you want to empower them to be so much better than they would be by themselves and that's different, very different mindset than I want them to basically not drive and um but be ready to to sort of take over. </s><s>[INST] So one of the interesting things we've been talking about is the rewards that they seem to be fundamental to the way robots behaves. So broadly speaking, we've been talking about utility functions all but comment on how do we approach the design of reward functions? Like how do we come up with good reward functions? [/INST] Well, really good question because the answer is we don't um this was, you know, I used to think, I used to think about how, well it's actually really hard to specify rewards for interaction because you know, it's really supposed to be what the people want and then you really, you know, we talked about how you have to customize what you want to do to um the end user, but I kind of realized that even if you take the interactive component away, it's still really hard to design reward functions. So what do I mean by that, I mean if we assume this survey i paradigm in which there's an agent and his job is to optimize some objective, some reward utility, loss, whatever cost. Um If you write it out, maybe it's a sad depending on the situation or whatever it is. Um If you write it out and then you deploy the agent, you'd want to make sure that whatever you specified incentivizes the behavior you want from the agent in any situation that the agent will be faced with. Right? So I do motion planning on my robot arm. I specify some cost function like uh you know, this is how far away you should try to stay so much amount to stay away from people and that's how much it matters to be able to be efficient and blah blah blah. Right? I need to make sure that whatever I specify those constraints or trade offs or whatever they are. That when the robot goes and solves that problem in every new situation, that behavior is the behavior that I want to see and what I've been finding is that we have no idea how to do that. Basically. What I can do is I can sample, I can think of some situations that I think are representative of what the robot will face. And I can tune and add and tune some reward function until the optimal behavior is what I want on those situations. Which first of all is super frustrating because you know through the miracle of ai we've taken, we don't have to specify rules for behavior anymore. Right? The who were saying before the robot comes up with the right thing to do, You plug in this situation. It optimizes back in that situation. It optimizes but you have to spend still a lot of time and actually defining what it is that that criterion should be, make sure you didn't forget about 50 bazillion things that are important and how they all should be combining together to tell the robot what's good and what's bad and how good and how bad and so I think this is this is a lesson that I don't know kind of I guess I closed my eyes to it for a while because I've been, you know, tuning cost functions for 10 years now. Um but it's it's really strikes me that yeah, we've moved the tuning and the like designing of features or whatever from the behavior side into the reward side. And yes, I agree that there's way less of it, but it still seems really hard to anticipate any possible situation and make sure you specify a reward function that will optimize will work well in every </s>
<s>[INST] it has to figure out the application that makes, that's useful [/INST] Right now. I'm not skeptical that I think that will happen. I think it's just, you know, 10 years away. Something like that. I forgot to </s><s>[INST] ask what programming language do you think the simulation is written in? [/INST] Probably lisp, </s><s>[INST] so not swift. Like if you were, you were at the bet, uh, I'll just leave it at that. So I mean we've mentioned that you worked with all these companies, we've, we've talked about all these projects. It's kind of if we just step back and zoom out about the way you did that work and we look at covid times this pandemic, we're living through that may if I look at the way Silicon Valley folks are talking about it, the way it is talking about it, this might last for a long time? Uh, not just the virus, but the, the remote nature, [/INST] the economic impact. Yeah, yeah. It's gonna be a mess. </s><s>[INST] Do you think uh, what's your prediction, I mean from sci fi to google to uh, uh, to just all the places you've worked into Silicon Valley, you're in the middle of it. What do you think is how is this whole place is going to change? Yeah. [/INST] So, I mean, I really could only speak to the tech perspective I am in that bubble. Um I think it'll be really interesting because the, you know, the zoom culture of being remote and on video chat all the time has really interesting effects on people. So on the one hand, it's a great normalize, er it's a normal Isar that I think will help communities of people that have traditionally been underrepresented because now you're taking in some cases a face off because you don't have to have a camera going right? And so you can have conversations without physical appearance being part of the part of the dynamic, which is pretty powerful. You're taking remote employees that have already been remote and you're saying you're now on the same level and foot footing as everybody else. Nobody gets whiteboards, you're not gonna be the one person doesn't get to be participating in the white board conversation. And that's pretty powerful. Um you've got uh you're forcing people to think uh a synchronously in some cases, because it's hard to just just get people physically together and the bumping into each other forces people to find new ways to solve those problems. And I think that that leads to more inclusive behavior, which is good. On the other hand, it's also it just sucks right. And so </s><s>[INST] um the nature the actual communication, it just sucks being not with people, like on a daily basis and collaborating with them. [/INST] Yeah, all of that. I mean, everything, this whole situation is terrible. Um what I meant primarily was the I think the most humans like working physically with humans, I think this is something that not everybody, but many people are programmed to do. And I think that we get something out of that, that it's very hard to express, at least for me. And so maybe this isn't true of everybody, but And so the question to me is, you know, when you get through that time of adaptation, you get out of March in april and you get into december and you get into next March, if it's not changed, </s><s>[INST] right? It's already terrifying. [/INST] Well, you think about that and you think about what is the nature of work and how do how do we adapt? And humans are very adaptable species, right? We can we can learn things and when we're forced to and there's a catalyst to make that happen. And so what is it that comes out of this? And are we better or worse off? Right. I think that, you know, you look at the bay Area, housing prices are insane. Well, why? Well, there's a high incentive to be physically located because if you don't have proximity, you end up paying for it and commute, right? And there's there has been a huge social social pressure in terms of like you will be there for the meeting, right? Or whatever scenario it is and I think that's gonna be way better. I think it's going to be much more the norm to have remote employees and I think this is gonna be really great. </s><s>[INST] Did you, uh, you have friends or do you hear of people moving? [/INST] I know one family friend that moved, they moved back to michigan and uh, you know, they were a family with three kids living in a small apartment and like we're going insane, right? And they're in tech has been worked for </s><s>[INST] google. So first of all, friends of mine of are in the process of or are have already lost the business, the thing that represents their passion, their dream. It could be small entrepreneur projects, but it could be large businesses, like people that run jim's like [/INST] restaurants, so </s><s>[INST] but also people like look at themselves in the mirror and ask the question of like, what do I want to do in life? For some reason they don't haven't done it until covid, like they really ask that question and that results often in moving or leaving the company here with starting your own business or transitioning to different company. Do you think we're going to see that a lot, like [/INST] I can't speak to that, I mean we're definitely gonna see it at a higher frequency than we did before just because I think what you're trying to say is there are decisions that you make yourself big life decisions that you make yourself and like I'm gonna quit my job and start a new thing. There's also decisions get made for you. Like I got fired from my job, what am I going to do? Right. And that's not a decision that you think about, but you're forced to act okay. And so I think that those, you're forced to act kind of moments where like, you know, global pandemic comes and wipes out the economy and now your business doesn't exist. I think that does lead to more reflection, right? Because you're less anchored on what you have and it's not a, what do I have to lose versus what do I have to gain a b comparison. It's more of a fresh slate. Cool. I could do anything now. Do I want to do the same thing I was doing? Did that make me happy? Is this now time to go back to college and take a class and learn learn new skill. Is this, is this the time to spend time with family if you can afford to do that, is this time to like, you know, literally move into the parents, right? I mean all these things that were not normative before suddenly become, I think very value system has changed and I think that's actually a good thing in the short term at least because um, it leads to, you know, there's kind of been an over optimization along 11 set of priorities for the world and now maybe we'll get to more balance and more interesting world where the people are doing different things. I think it could be good. I think there could be more innovation that comes out of it. For example, </s>
<s>[INST] didn't. I mean uh Doug it's truly an honor. This is a long time coming. I um a lot of people bring up your work uh specifically and more broadly philosophically of this is the dream of artificial intelligence. This is likely a part of the future. Were so sort of focused on machine learning applications, all that kind of stuff today. But it seems like the idea is that carries forward uh is something that would be at the center of this problem that we're all trying to solve, which is the problem of intelligence, emotional and and otherwise. So thank you so much. It's such a huge huge honor that you would talk to me and spend your valuable time with me today. Thanks for talking. [/INST] Thanks lex It's been great. </s><s>[INST] Thanks for listening to this conversation with Doug Len it. To support this podcast. Please check out our sponsors in the description. And now let me leave you some words from Mark Twain about the nature of truth. If you tell the truth, you don't have to remember anything. Thank you for listening. I hope to see you next time. [/INST] </s>