Datasets:

ianiket23

/

podcast_llama_chat_format-5k

like 0

<s>[INST] But for most of us the basic low hanging fruit solution should be a good easy to set up, Easy to use security system simply safe is uh the best of the best for that. Like I said, I have it set up on my place and I love it. Go to simply safe dot com slash lex to get a free indoor security camera plus 20% off your order with interactive monitoring. Part of me wants to have a nearly infinite number of cameras in my house so I can do full three D reconstruction and at some point uh transfer myself into a virtual world and not know it like somebody else sets it up. So I'll be living in a virtual world with the exact same experience as I have in the physical world and I would know it would be some fascinating experiment and in that place to there would need to be security and it would be a perfect reconstruction of the simply safe system but in the virtual world that would be incredible. Anyway. It's simply safe dot com slash lex This is a lex Friedman podcast. The supporter please check out our sponsors in the description and now to your friends, here's Michael malice. Since this is a christmas special holiday special. Have you been a good or a bad boy Michael this year? Well, [/INST] that's interesting. One of the people in the book, Granville Hicks, his autobiography starts with I was a good boy and he wasn't a very good boy. Um </s><s>[INST] On a scale of 1 to 10. [/INST] I'm trying to think of what bad things I've done. </s><s>[INST] Okay. [/INST] There's that Okay, wait, that's not that was not that that's all right. I would say nine, </s><s>[INST] nine, [/INST] Yeah, I try to do the right </s><s>[INST] thing. What [/INST] Are you? It's going to be one or 0. </s><s>[INST] Yeah, no, I'm extremely self critical. I pushed the zero, I reached for the zero. Well, [/INST] mission accomplished. </s><s>[INST] So this, this episode is announcing the release of the white pill, a book you wrote, which is I've gotten the honor, the privilege, the pleasure of being one of the first people to read it. [/INST] So, I'm really, I'm not nervous is the word, but you are the first person who has read it that I am speaking to about it. </s><s>[INST] My first, my last, my [/INST] everything. Yes. </s><s>[INST] You say that to all the girls. But all [/INST] the all the fembots </s><s>[INST] Fembots. But yeah, it was a truly incredible book. It's basically a story of evil in the 20th century and throughout it you reveal a thread that gives us hope and that's the idea of the white pill. So there's the blue pill and the red pill. There's the black pill, which is a kind of deeply cynical, um maybe apathetic, just giving up in the world, given that you see behind the curtain and given that you don't like what you see, given that there's so much suffering in the world you give up. That's the black pill and the white pill, I suppose is even though you acknowledge that there's evil in the world, you don't give up. So if you're listening to this and you're a fan of this podcast, [/INST] you got a white pill book dot com, it'll go to it </s><s>[INST] white pill book dot com and if you don't know how to spell, will probably have a link that you can click on. So, for people who also don't know, Michael malice is not just a troll, not just a hilarious comedic genius who hosts his own podcast, but he is an incredible, brilliant author. Dear reader, the unauthorized autobiography, kim jong il, So that's a story of North Korea, the new right, a journey to the fringe of american politics. That's the story of the extremes of the United States uh political movements and then the anarchist's handbook that's talking about the ideologies, the different flavors of ideologies of anarchism, but on top of that you're now going in going into the darkest Aspects of the 20th century with the Soviet Union and the communism with the White Pill. So let me ask you, let's start at the beginning at the end of the 19th century, as you write the term Socialist Communists and anarchists were used somewhat loosely and interchangeably because the prophecy Marxist society was one in which the state had famously withered away. There was a great disagreement about what a socialist system would look like in practice, but two things were clear first that socialism was both inevitable and scientific the way of the future, and second, That the capitalist ruling class, we're not going down without a fight. So what are the key points of disagreement between the socialists and anarchists? The communists along that? At that time? At the beginning, at the end of the 19th century, at the beginning of the 20th century, the possibility of the century laid before us that eventually led to the first and the Second World War. [/INST] The idea when the Industrial revolution came, and Marx was very much a product of industrial revolutionary thinking, was okay now that we have technology now that we have science, we can scientifically manage society. We saw this very much with Woodrow Wilson and this kind of idea for Progressivism that, you know, we can use technology and kind of, not capitalism, in their view, unfettered capitalism was wasteful. You're making too much stuff, you have surpluses, you have uh shortages if we produce just exactly what we need and you have these people engineers, their engineering society, then, you know, everyone will be happy and you don't have to have any suffering or waste. So socialism at that time was used as a broad umbrella. It's not used in the term that means today of, um, necessarily state socialism. It just meant the idea of having society scientifically run. So you had a huge argument. They're different wings even had from the beginning with Mark's versus bakunin because Marx was for obviously state socialism, uh, the absolute state running everything. Although even with Marx and Engels, it was a means to an end after man is remade in his very nature than the state. Withers away and everyone's equal and you have this kind of heaven on earth situation. But Conan, you know, was the opposite. He regarded the state as inherently immoral. Um, and wanted to have kind of like workers collectives and things like that in ultra localized control. </s>

<s>[INST] Is there a good term for when the output is greater than the input? [/INST] Yes. Yes. There is, well, there's several special definitions of this. So one of them is that if you, if you like in a fire, if you light a match and you have it there and it's an infinitesimal amount of energy compared to what you're getting out of the fire, we call this ignition, which makes sense, right? This is like what our own son is as well too. So that was not ignition in that sense as well too. So what we call this is scientific. Well, the one that I just talked about, which is for some instance, when I get enough fusion energy released compared to the size of the match, we call this scientific breakeven. Breakeven. break even and it's because you've gotten past the fact that this is unity now at this point. </s><s>[INST] What is fusion gain or as using the notation Q from the paper overview of the Spark talk about before using just the same kind of term? [/INST] Actually, so the technical term is Q, capital Q. </s><s>[INST] People actually use Q. [/INST] We actually use capital Q or sometimes it's called Q sub P or something like this. Okay, so what it means is that it's in the plasma. So all we're considering is the energy balance or gain that comes from the plasma itself. We're not considering the technologies which are around it, which are providing the containment and so forth. So why the excitement? And so, well, because for one reason, it's a rather simple threshold to get over to understand that you're getting more energy out from the fusion, and even a theoretical sense than you were from the starting match. </s><s>[INST] So Q is taken. Do you mean conceptually simple? [/INST] It's conceptually simple that you get past one that everyone under, like when you're less than one, that's much less interesting than getting past one. So there's a really big threshold to get past. But it really is a scientific threshold because what QP actually denotes is the relative amount of self-heating that's happening in the plasma. So what I mean by this is that in the end, in these systems, and what you want is something that where the relative amount of heating, which is keeping the fuel hot, is dominated by from the fusion reactions themselves. And so it becomes, it's sort of like thinking like a bonfire is a lot more interesting physically than just holding a blowtorch to a wet log, right? There's a lot more dynamics. It's a lot more self-evolved and so forth. And what we're excited as as scientists is that it's clear that in that experiment, that they actually got to a point where the fusion reactions themselves were actually altering the state of the plasma. It's like, wow. I mean, we'd seen it in glimpses before in magnetic confinement at relatively small levels. But apparently, it seems like in this experiment, it's likely to be dominated by self seating. That's a very important, that's a very </s><s>[INST] sort of threshold to get past. [/INST] So that makes it a self-sustaining type of interaction? It's more self-sustaining. It's more self-referential system, in a sense. And it sort of self-evolves in a way. Again, it's not that it's going to evolve to a dangerous state, it's just that we want to see what happens when the fusion is the dominated heating source. </s><s>[INST] And we'll talk about that, but there's also another element, which is the inertial confinement. Laser-based inertial confinement is kind of a little bit of an underdog. So a lot of the broad nuclear fusion community has been focused on magnetic confinement. Can you explain just how laser-based inertial confinement works? So it says 192 laser beams were aligned on a deuterium, tritium DT target, smaller than a P. Yes. Or EB actually, yeah. Okay, well, you know it depends, not all Ps are made the same, but this is like throwing a perfect strike in baseball from a pitcher. This is like a journalist wrote this, I think. It's just like, no, it's not a journalist, it's DOE wrote this, a bar of energy. [/INST] Yeah, it could be, yeah. Or EB actually. Like energy. Wait, we try to use all these analogies... </s><s>[INST] This is like throwing a perfect strike in baseball from a pitcher's mount 350 miles away from the plate. There you go. Department of Energy. The United States Department of Energy wrote this. Can you explain what the laser is coming in? [/INST] What actually happens? Actually, there's usually mass confusion about this. So what's going on in this form of energy? So the fuel is delivered in a discrete, the fusion fuel, the deuterium and tritium is in a discrete spherical, it's more like a BB, let's call it a BB. So it's a small one. And all the fuel that you're going to try to burn is basically there. And it's about that size. So how are you going to get, and literally, it's like 20 degrees above absolute zero because the deuterium and tritium are kept in a liquid and solid state. So the fuel is injected not as a gas, but as a solid. It's actually, and these are particular experiments that can introduce one of these these, you know, these targets once per day, approximately something like that. Because it's very, it's very, it's a kind of amazing technology actually that I know some of the people that worked on this back in the day is they actually make these things at a BB size of this frozen fuel, it's actually at cryogenic temperatures. And they're almost like smooth to the atom level. I mean, they're amazing pieces of technology. So what you do in the end is think you, what you have is this spherical assembly of this fuel, like a ball. And what is the purpose of the lasers? The purpose of the lasers is to provide optical energy to the very outside of this. And what happens is that energy is absorbed because it's in the solid phase of matter. So it's absorbed really in the surface. And then what happens is that when it's absorbed And something called the ablator. What does that mean? It means it goes instantly from the solid phase to the gas phase. So it becomes like a rocket engine, but you hit it very uniformly. So there's rocket engines coming off the surface. Think of an asteroid, almost, where there's rockets coming off. So what does that do? Well, what does a rocket do? It actually pushes by Newton's laws, right? It pushes the other thing on the other side of it equal an opposite reaction. it pushes it in. So what it does is that the lasers actually don't heat. This is what was confusing. People think the lasers, oh, we're going to get it to a hundred million degrees. In fact, you want the exact opposite of this. What you want to do is get essentially a rocket going out like this. And then what happens is that the sphere like, and this is happening in a billionth of a second or less actually, this rapidly, that force like so rapidly compresses the fuel that what happens is that you're squeezing down on it and, and, and, you know, it's like, what was the, see BB2, that's bad. Actually BB, I should have started with a basketball basket, goes from like a basketball down to something like, like this and a billionth of a second. And when, when that, when that happens, I mean, scale that in your mind. So when that happens, and in this, this comes from almost from classical physics, so there's some quantum in it as well too. But basic, if you can do this like very uniformly and so-called adiabatically, like you're not actually heating the fuel, what happens is you get adiabatic compression such that the very center of this thing all of a sudden just spikes up in temperature because it's, it's, it's, it's actually done so fast. So why is it called inertial fusion? It's because you're doing this on such fast timescales that the inertia of the hot fuel basically is still finite so it can't like push itself apart before the fusion happens. Oh wow. Yeah. </s>

<s>[INST] that uh people sort of argue for the proof of work is that it is secure because it's much more difficult to sort of as you have highlighted is difficult to participate. Is there is, what are your thoughts about the security of the proof of stake mechanism? Is there ways to make it secure? [/INST] So I think proof of stake is very secure because in order to be able to attack the system you need to have like basically as much stake as the rest of the network, right? So that means like right now for example we have five million east staking. So you have to come up with five million each and then joined the network And then the other so five million. It is a lot right? It's like how much is it now, like $15 billion? So that's actually more than I believe the cost of attacking the Bitcoin network. And then the second thing is that recovering from attacks is much easier and proof of stake than proof of work, right? Because in proof of stake, you have like first of all we have for many kinds of attacks that you do against this network, we have this concept of like automatic slashing right, which basically means that in order to like revert a finalized block. So if there is one block that's like accepted by the network and you try to convince the network to kind of revert that block and accept a different block in order to make that kind of attack, you basically have to have your validator. Like a big portion of your validators signed two conflicting messages. And this is something that like what these messages are on the network where you can go and prove like look these people did it. And so we have this feature in the protocol called slashing where you basically take all these people who provably misbehaved and you burn their coins and you don't burn anyone else's coins. Now there are other cases like for example if instead of reverting blocks the attack just tries to censor everyone right? Then what you do, everyone who got censored would just like basically create the minority chain. Um and then the community would basically have to do a soft fork right? They would just have to say like what this chain is clearly attacking us. This chain is the one not attacking us. And so we're going to join this chain. And then what happens is that on that new chain? The Attackers also there's a lot of coins. Right? So the difference between proof of stake and proof of work is that in a proof of stake system like you can identify specific participants and you can say you know these and like this isn't like you know a human going in and saying, I don't like you, I don't like you I don't like you this is like automated, right? You can do the selection </s><s>[INST] process is automated. [/INST] Yes. </s><s>[INST] There are ways you can go wrong so that's a painful process where the coins are burned. [/INST] Um It is painful. Yes, I think you know the one big unknown of course is like if an attack actually happens and like if an attack happens that requires the community to actually choose one of these minority forks then like what would the community actually successfully coordinating on this look like? Right? Like it's like you know, we can talk about it and we can, you know right? Like science fiction novels about it, but like until that's happened, you don't really know the details of like what it looks like and how difficult it is. </s><s>[INST] What are the channels of communication for the community? If you can enlighten me a little bit like what you know uh in many ways in the political realm, twitter is often used as a way to kind of have these emergent phenomena of large groups of people coming to a consensus about a particular idea and then there's battle for consensus. What's um in the ethereum community, how do people, what are the sources of natural language based communication that have an emergent belief structure that you would say or is it all through money. Is it all through trading that the communication happens? [/INST] There's definitely talking as well, um I mean like, we have to agree on protocol changes somehow, right? Like there's twitter, there's Reddit, there's get hub, there's a all of the various ethereum forums, ethereum magicians, ethereum research, there's just in person communication, then there's just kind of like the hidden web of everyone talking to everyone on telegram or signal. So it's like some of everything right? But I think like, the thing to emphasize around, like, can you actually come to consensus on, you know, whether or not to fork the chain because the attacker is censoring some everyone just for example is like you everyone who's running a node is going to see almost the same thing, right? Like they're going to be off by a few seconds and like maybe they'll be off by a few minutes, they'll disagree by a few minutes, but like if it's a serious attack, you know, people are gonna know, right? It's not like one of those things where, you know, it we're trying to agree on, like, I don't know, did Epstein killed himself for like some, you know, read the political facts for like, in reality no one knows a single thing about what I was actually going on and they're all speculating like it is much more visible, right? So we do have that, but you know, at the same time, I'm happy to admit that like, these are fairly untested mechanisms, but at the same time, they're also untested mechanisms in proof of work, right? And like in proof of work it's even harder because in proof of work you don't have the ability to like identify and say, you know, I'm going to these miners attacked and so we're not going to let these my uh these miners and these miners not attack. So we're going to keep them in. Like you have to pretty much you know, either take out none of the miners or you do a fork that changes the proof of work algorithm which takes out all of the miners. Right? So the the economics of recovering from attacks and proof of work at least to me actually do seem more unfavorable. But you know, I'm sure the proof of work people you talk to will give very different and contradictory opinions and that's totally fine and amazing. </s>

<s>[INST] That's a beautiful, inspirational message to end on. That's why. Thank you so much for talking today. That was amazing. Thank you. [/INST] </s>

<s>[INST] And part of the vodka thing is I need to honor my ancestors. It's like, you have to, you know, you can't, you can't turn your back on your past. Um, let me ask about the 100 mile world record on the treadmill. So for most people running on a treadmill is really boring. So that's kind of their experience of it. That's probably the first thing that would say that seems like really boring to run 100 miles on the treadmill, would you say it's boring? Like what were some places your mind went to make that happen? [/INST] So this one is interesting to me because I definitely recognized the boredom and the difference, the thing that the question I can't quite answer, I think with it is like, could I have remedied that with better preparation because the scenario that put me on a treadmill for 100 miles was, you know, it was March 2020 basically a cascade of every race on the planet got canceled and I was in a position where I was going to be doing a rentable 100 miler on a track in mid to late april. So I had like the majority of my training under my belt. So I was like kind of putting the finishing touches on that and I'm like, oh great, Here we are, like, you know, what do I do with this fitness? Do I just scale back and hope the events come back and fall and then peak again? Or do I find something to use this fitness for? And the treadmill was the closest thing to what I have been training for in terms of just like a mechanical, like flat running essentially that I could, that I could think of. And uh my thought was okay, well I'll just live stream myself on a treadmill and see what happens, ended up turning into like a quite a big event, but </s><s>[INST] you don't usually incorporate treadmill running into your running into your training. [/INST] I don't not incorporate it, I just don't incorporate it in the way that would be necessarily conducive to uh you know, dealing with the mental aspects of being on a treadmill for 100 </s><s>[INST] miles. Was it that different than running on the track? [/INST] It was from the sense that here's the way I describe it is when I'm on a track, it's a controlled environment and everything can be very uniform. But there are tiny little micro adjustments and pace that that I'm doing subconsciously that give me the sense of control. No, I might run the exact same split, but there's like a fraction of a second or you know, a fraction second faster than a fraction of seconds slower, that equals the same outcome. It gives you that sense of control. Your determining how fast you're going on a treadmill, you're responding to the belt. So the advantages, you can set a pace and know you're hitting it, the disadvantages you're being told what to do by that machine and that gets very frustrating. Um I felt like I wanted to step off, like you get to like certain points where you're just </s><s>[INST] like, like [/INST] even stepping off what I noticed I learned this on the day of actually I noticed there's something where it didn't really matter how long I get off, like I get off to use the bathroom and I was a little bit longer break. Then I I had, I had like a hiccup during my event where we ran so much power through one end of the house that the screen on the treadmill was blacking out. So uh we ended up, so I ended up jumping back and forth on treadmills for quite a bit in the beginning and I noticed even turning it off, stepping over and start another one up gave me like, you know, a handful of seconds between was enough of a mental break of just like that release of being told what to do to reset. </s><s>[INST] So maybe if you were in the future you would figure out what exactly how much is needed to have them at the break, I never actually thought about that, that I mean obviously for you, but also for people like me, like amateur runners, that's a source of frustration with the treadmill that there's sometimes small adjustments and pace that we do running not on the treadmill on the ground, that feel like essential for that. Just like you said, that experience of control, like uh feeling like your control somehow, that's really, I don't know that somehow liberating in the way that a treadmill can be just a source of frustration. Funny [/INST] the funny thing though about the treadmill is I actually like to do faster workouts on the treadmill, like long intervals or something like that or temple runs because for that for that type of stuff sometimes for those, I want to release the brain power required to hit that pace and say you take care of that and for that it's fun. But those are over quick, so you don't really run into the times. </s><s>[INST] Yeah, that's fascinating for like precise control of pace. You've, you've also, during that stream got to interact, one of the greatest athletes of all time. Bert Kreisher, what's your, he's actually doing? I don't know if you're paying attention to this, but I guess he has a goal of running 2000 miles this year. I don't I've gotten, she has to talk to joe Rogan yesterday about this, which is uh, fascinating. I think he's a little bit doubtful of [/INST] profitability </s><s>[INST] to be the ultra performer that he's so naturally is, um, what's your thoughts about? But as a runner, what's your advice to him? And what was your interaction like as part of this treadmill challenge with him? [/INST] I love Burt, because he's such a nice person. I mean as a guy who's just accelerated in popularity over the last few years, like he is like super kind. So for folks are curious, like I've met Burt couple years earlier and I just randomly asked him like, hey, I'm doing this live stream thing, We're doing it for fight for the forgotten, We're trying to raise some funds for them. Would you want to come on the livestream for a bit and I thought maybe he'd come off like five or 10 minutes and I thought that would be amazing if he did that, he not coming off like over an hour, he said he went past his slot, sat in the next slot and just started talking to some of the other guests. It says he's just bert is definitely like, I feel like he's as unchanged from, like, his popularity as one can get away with and it's just like his, his lifestyle I think is very on unpredictable in the sense that like, if he wants to run like X time for a specific race, that's going to pull away from his lifestyle so much to focus on that, luckily for him, he is actually a great athlete, like it's under that layer of fat, </s>

<s>[INST] some compressed representation. And that's [/INST] what I I worry about saying, compressed because it doesn't I don't mind that it's low dimensional or not but it has to be something that's easier to think about </s><s>[INST] by us humans [/INST] or my algorithms </s><s>[INST] or the algorithms being like control optimal. [/INST] So for instance if the contact mechanics of all of those onion pieces and all the permutations of possible touches between those onion pieces, you know you can give me a high dimensional state representation. I'm ok if it's linear but if I have to think about all the possible shattering combinatorics of that, then my robot is going to sit there thinking and uh the soup is gonna get cold or something. </s><s>[INST] So um since you taught the course I've kind of entered my mind um the idea of under actuated as really compelling to see the to see the world in this kind of way. Um Do you ever you know if you talk about onions or you talk about the world with people in it in general, Do you see the world as basically an under actuated system? Do you like often look at the world in this way or is this overreach? Um [/INST] Uh huh. Under actuated as a way of life, man </s><s>[INST] Exactly. I guess that's what I'm asking. I [/INST] do think it's everywhere. I think some in some places um we already have natural tools to deal with it, you know, it rears its head. I mean in linear systems, it's not a problem. We just we just like an under actuated linear system is really not sufficiently distinct from a fully actuated linear system. It's a it's a subtle point about when that becomes a bottleneck in what we know how to do with control. It happens to be a bottleneck, although we've gotten incredibly good solutions now, but for a long time that I felt that that was the key bottleneck in legged robots. And roughly. Now the under actuated courses, you know, me trying to tell people everything I can about how to make atlas do a backflip right. Um I have a second course now in that I teach in the other semesters, which is on manipulation and that's where we get into. Now. More of the that's a newer class. I'm hoping to put it online this fall um completely. And that's going to have much more aspects about these perception problems and the state representation questions. And then how do you do control? And the the thing that's a little bit sad is that for me at least is there's a lot of manipulation tasks that people want to do and should want to do. They could start a company with it and made very successful. That don't actually require you to think that much about under dynamics at all even, but certainly under actuated dynamics once I have if I if I reach out and grab something, if I can sort of assume it's rigidly attached to my hand, then I can do a lot of interesting meaningful things with it without really ever thinking about the dynamics of that object. So they built we've built systems that kind of and reduce the need for that enveloping grasps and the like. Um But I think the really good problems of manipulation, so manipulation by the way, is more than just pick and place. That's like a lot of people think of that just grasping. I don't mean that I mean buttoning my shirt, I mean tying shoelaces. How do you program a robot to tie shoelaces and not just one shoe, but every shoe, right? That's a really good problem. It's tempting to write down like the infinite dimensional state of the of the leases that's probably not needed to write a good controller. I know we could hand design a controller that would do it, but I don't want that. I want to understand the principles that would allow me to solve another problem. That's kind of like that. But I think if we can stay pure in our approach than the challenge of tying anybody's shoes. He's a great challenge. </s><s>[INST] That's a great challenge. I mean in the soft touch comes into play there. That's really interesting. Let me ask another ridiculous question on this topic. Um How important is touch? We aren't talking much about humans, but I have this argument with my dad where like I think you can fall in love with the robot based on language alone and he believes that touch is essential, touch and smell, he says. But um so in terms of robots, you know, connecting with humans and uh we can go philosophical in terms of like a deep meaningful connection like love, but even just like collaborating in an interesting way, how important is touch? Like Uh from an engineering perspective and the philosophical one [/INST] I think it's super important. Let's even just in a practical sense if we forget about the emotional part of it. Um but for robots to interact safely while they're doing meaningful mechanical work in the present and the uh you know close contact with or vicinity of people that need help. I think we have to have them, they have, we have to build them differently. Um they have to be afraid not afraid of touching the world. So I think baby max is just awesome, that's just like the movie of Big Hero six and the concept of a max, that's just awesome. I think we should um and we have some folks at Toyota that are trying to Toyota research that are trying to build the max roughly and uh I think it's just a fantastically good project. Um I think it will change the way people physically interact the same way. I mean you you give a couple examples earlier, but if I if the robot that was walking around my home looked more like a teddy bear and a little less like the terminator. That could change completely the way people perceive it and interact with it. And maybe they'll even want to teach it. Like you said, right? You could and not quite gamify it. But somehow instead of people judging and looking at it as if it's not doing as well as a human, they're going to try to help out the cute teddy bear. Right? Who knows? But I think we're building robots wrong and being more soft and more contact is important. Right? </s>

<s>[INST] also think [/INST] my wife and I also have the benefit of being recruited uh young and together where so </s><s>[INST] over time you can start to figure out things that are very difficult to uh so you form the baseline, you start to understand the person is very, it becomes very difficult to lie. [/INST] The most difficult thing in the world is consistency. It's the most difficult thing in the world. Some people say that discipline or self discipline, What they're really talking about is consistency when you have someone who performs consistently over long periods of time, under various levels of stress. You have high, high confidence that that is the person that you can trust. You can trust. Again, you can trust them to behave within a certain pattern. You can trust an asshole to be an asshole without trusting the asshole to take care of your kids, right? So I don't ever want to mix up the idea of personal trust versus trusting the outcome. You can always trust a person to operate within their pattern of behavior. It just takes time for you to get a consistent, to get consistent feedback as to what that baseline is for them to </s><s>[INST] to form a good model, predictive model of what their behavior is going to be like, [/INST] right? And you know, it's fascinating and I think the challenge is building that model quickly. So technology is one of those tools that will be able in the future to very quickly create a model of behavior because technology can pull in multiple data points in a very short period of time that the human brain simply can't pull in at the same period at the same space at the same speed. </s><s>[INST] That's actually what I did my PhD And that's what I did a google is forming a good representation unique representation, acquired the entire world based on the behavior of the person. The specific task there is so that you don't have to type in the password. The idea was to replace the password but it also allows you to actually study human behavior and to think all right, what is the unique representation of a person? How um because we have very specific patterns and a lot of humans are very similar in those patterns. What are the unique identifies within those patterns of behavior? And that's I think that's from a psychology perspective. A super fascinating question. And from a machine learning perspective it's something that you can, as the systems get better and better and better and as we get more and more digital data about each individual, you start to get you start to be able to do that kind of thing effectively. [/INST] And it's I mean when I think of the fact that you could create a dossier on somebody in a matter of 24 or 48 hours if you could wire them for two days. Right? Internet of things, style, you put it in their underwear or whatever. Right? Some some chip that just reads everything. How heavy are they walking? How much time do they sleep? How many times they open the refrigerator when they log into their computer? How do they do it Like which hand do they use when they log in? What what's the most common swipe? What's the most visited website? You could collect an enormous amount of normative data in a short period of time where otherwise we're stuck The way that we do it now, once or twice a week, we go out for a coffee for two hours and two hours at a time. Over the course of 68 weeks, 12 weeks, you're coming up with a 50% assessment on how you think this person is going to behave just that time. Savings is immense. </s><s>[INST] Something you've also spoken about is private intelligence and the power and the, the reach and the scale and the importance of private intelligence versus government intelligence. Can you elaborate on the role of what is private intelligence and what's the role of private intelligence in the scope of all the intelligence that is [/INST] gathered and </s><s>[INST] used in the United States? [/INST] Yeah, absolutely. It's a it's something that so few people know about and it became a more mainstream topic with the trump administration because trump made it no secret that he was going to hire private intelligence organizations to run his intelligence operations and fund them. So that really brought it to the mainstream. But going all the way back to 9 11, going all the way back to 2001, when, when the 9 11 attacks happened, there was a commission that was formed to determine the reasons that 9 11 happened. And among the lists that they determined. Of course, they found out that the intelligence community wasn't coordinating well with each other. There were Fife dmS and there was infighting and there wasn't good intel sharing. But more than that they identified that we were operating uh at Cold War levels. Even though we were living in a time when terrorism was the new biggest threat to national security. So the big recommendation coming out of the 9-11 Commission was that the intelligence organizations, the intelligence community significantly increased the presence of intelligence operators overseas. And in terms of analytical capacity here in the United States. When they made that decision, it completely destroyed. It totally was incongruent with the existing hiring process because the existing hiring process for C. I. A. Or N. S. A. Is a 6 to 9 month process. The only way they could plus up their sizes fast enough was to bypass their own hiring and instead go direct to private organizations. So naturally the government contracted with the companies that they already had secured contracts with Boeing Raytheon, Northrop Grumman khaki, you know, you name it. And then over time from 1 2002 now or that started really in 2004 when they started significantly increasing their private the presence of private intelligence officers uh from there from then until now it's become a budgetary thing. It's become it's become a continuity of operations thing. And now the reason Northern Virginia has become one of the wealthiest zip codes in America is because of the incredible concentration of private intelligence that is supporting C. I. A. N. S. A. D. I. A. F. B. I. And all the slew of IC partners </s>

<s>[INST] see I like three said teenagers so we the technology I think when we move past the teenager stage enriches our ability to sense the earth to understand what's going on with the environment it's just that we're very so it's not that technology disconnects us from the environment it gives us more tools with which to understand what's going on anyway [/INST] that's true for the people who are building the tools and know how to use it should take those tools now put them in the general public with no filter which is happening with social media which is happening with a lot of things and you see the disaster </s><s>[INST] this is creating a list of the disaster it is showing if you don't you sound like a parent talking about a teenager yes the team it's it's the growing pains of a civilization that is currently becoming deeply connected with a computer can communicate all across the world even through the pain that made it good thing [/INST] about technology this is also something I wrote it's not the tools we created that are bad it's the way we use the S. </s><s>[INST] elder learning [/INST] well </s><s>[INST] the cool and what you will [/INST] do all the returning before it's too late because our response to what's going on in the environment our response to bin then makes is deeply connected to these disconnect we have with nature anyways we all agree that we are in growing pains and hopefully we can move forward because there is a fantastic universe something absolutely magical around us and I'm talking as a scientist I mean there is magic not in sense of you know trickery but instance of wonder around this in there are so many signs where we are getting so close to relations in smaller G. in astrobiology in astronomy which I think to me is this is where the hope lies in also the weakening of understanding that we need to be in the Calabria on with a plan if we want to move forward because even though we have these big dreams of going on Mars and the moon listen I am a planetary geology so I am all for exploration right now the moon or Mars is not going to save your **** because for the logistics will still depend very much on the earth and for a long time I think this time we're living in will be remembered as a pivot in our history for a for a number of reasons at the time where there is a growing consciousness where we are creating tools that are going a little bit ahead of us that we have some some difficult time to catch up on with where we have to deal with the population that's way too big for the planet we have we need to really learn a sense of balance and it in in the maturity is a civilization so how is this going to unfold right now I have no clue </s><s>[INST] I draw a lot of optimism from the similar things that happened many decades ago when nuclear weapons were developed boy it was that at the time even more terrifying you just not created weapons that could destroy the entire idea of life on earth or not entirely but a lot of it and we somehow found a balance and that the threat constantly is out there and that threat has been made more visceral in recent times and because the one you crane but we find a balance smile that the I have a thread of optimism for human civilization that we that we figure it out we're clever teenagers I think [/INST] we are clever teenagers there is definitely a threat of optimism but I think it's then </s><s>[INST] is [/INST] N. because something that has changed as well is the mentality of of humans although the threat was terrifying when a nuclear weapons where we created there was a sense of limits you were willing to push in the threats on there where there was a sense of decency of moral values it was the perfect but it was at least a time where people could come together from very different perspective and agreed that something was more important than destroying everything </s><s>[INST] but that's so hilariously say that okay yes you're talking about a small slither of humans which is the scientists in the Manhattan Project perhaps now I'm selling most of the time when over a hundred million people were tortured or murdered well I am in in Europe [/INST] absolutely absolutely I'm not talking about scientist here I shouldn't talking about petitions we've gone beyond that point now this is what I'm worried about I mean torture is such wrong unfortunately well we are apes exactly what you said so I think that you know there is a lot to beef </s><s>[INST] not not [/INST] not not to blame grandpa for that but the because we can always get better </s><s>[INST] Robert was a wild man [/INST] bloods we have to improve a lot on that side before we can claim that </s><s>[INST] we are an [/INST] a mature civilization </s><s>[INST] when you are just because you mentioned the magic when you look out there perhaps it's not a scientific question but [/INST] you don't have to be scientific all the time </s><s>[INST] yeah well this he said magic so there's a there's a magic to magic that is in part scientific and part I don't know whatever whatever fills us with awe as humans will look up at the stars do you think the universe is full of life or not thank you you know you're sitting drinking some wine looking up at the stars and and wondering as a human do you think were alone what do you think it's life is everywhere [/INST] I am going to make such an un magical response to that my response is that's the scientific response </s><s>[INST] yeah [/INST] that if we are alone then the universe is a statistical absurdity </s>

<s>[INST] Yeah. Uh, isn't there a John legend song like that? All of you and all of me, very romantic. Yeah. No, we're sticking on that theme. Okay. I'm sorry. Uh, Oh, one of the things, uh, Gordon asked, I forget how you put it because I think there was a lot of words that would need to be censored involved, but he said, ask them, um, [/INST] how it feels to have a zero five record against me with four submissions combined to me. Very romantic. Yeah. I mean, first of all, I wasn't sure he could count to five. Yeah. That's an impressive thing. Um, Oh, and five. I mean, I will say one thing. Nobody beats me four times. I love you so much. I did have a question. I did have a question for you. There was some controversy on your Twitter about a list of books. Yeah. And I was wondering why Gordon's book wasn't featured amongst that </s><s>[INST] literature. Yeah. Well, it was only the first 30 books or like the first 20 [/INST] books. And it would of course be in, uh, something interesting about Gordon. He's the first author that's written more books than he's read. Pretty good. </s><s>[INST] Uh, if you, if you face them and beat them, what, like, what's your take on what it takes to be Gordon? I mean, you guys kind of joke and they go pretty, pretty hard recently, uh, on each other. But as a fan of jiu-jitsu, I'm all in on this rivalry. It's just fun to watch. I mean, first of all, [/INST] I don't think I go really hard with him. I think Gordon is, he's pretty sensitive. You know what I mean? He's looking for a large insult in a small insult. And for me, like Australians, we just attack each other all day, every day. And for me, like, if I see someone that takes himself very seriously, that's like blood in the water. That's funny to me. To me, if I can just gently provoke and get a strong reaction, that's hilarious. Like Aussies, we would just attack each other. And the first person that gets upset, he kind of loses the exchange. So I think that is very, very entertaining. </s><s>[INST] Like if you were to beat Gordon, would the mental game off the map be part of it? [/INST] Think it would be a fact of a show. But I mean, I'm never going to come out too crazy direct with him. You know, like I don't, I, I find that like, if you get too upset on the line and you're going crazy, I find that I'd be embarrassed to do that myself. Obviously each, everyone's different. Everyone has a different style, you know, but like, yeah, I think mental, the mental aspect would play a big factor. I mean, mainly, because if I were to beat him, I would send him a message every day until I died. Yeah. Just to gently remind him that I got the last one, the last one. It's all that matters. We're not giving it, we're not giving it. </s><s>[INST] We're not giving it, we're not giving it. So like once you beat him, [/INST] you're going to run for the rest of your life. I mean, run, but look back. Yeah. </s><s>[INST] With messages, ride, ride your horse into the sunset. Okay. Oh, by the way, you've talked very lightly, you've talked shit very lightly against Alexander Volkonovski's opponent very lightly. Have you received death threats or how are you still alive? Like Gordon, I would say people from Dagestan take a joke very well. Do they really? No. Oh, [/INST] like, sorry, I'm slow. No, it's too aggressive mode in my head. No, I'm listening to you. No. Oh, like, sorry, I'm slow. No, I'm listening to you. Islam was pretty cool. I wanted to stir it up a bit, you know, because like I felt like that was a massive fight and it probably should have had more attention than it was receiving. So I wanted to just gently stir it up a bit. I feel like Sambo guys are in the same vein as catch wrestlers, very sensitive. You know, like obviously there's only three people in the world that do catch wrestling, Sambo, maybe 10 to 15. So I figured we could really provoke them with that sort of jiu-jitsu Sambo stuff. Islam took the jokes very well. The Russian fans, not so much, are very serious. </s><s>[INST] There's not many smiles in Russia, you know, they didn't take it as well. I'm trying to suppress the [/INST] anger, the rage is building up inside me slowly. So you guys mentioned steroids. I like that you bring that up after we talk about Russia for the record. Smooth, smooth segue there for the record. </s><s>[INST] Smooth, smooth segue there. I cannot condone the statements. I cannot condone that by the Aussie, [/INST] but I would love to travel with you to Russia. That would be a good time. Yeah. You might get </s><s>[INST] killed with me now. Yeah, you might. No, I would be like the first to turn to backstabbing. You're like, I got him here. All right. Are most of the top grapplers on steroids? [/INST] I mean, it's hard to say, you know, some people look like shit and they're on steroids. Some </s>

<s>[INST] as efficiently. You should probably the successful people I've known in terms of athletes, they hate rest days, but they know they have to do it for the long term. They think their opposition is getting stronger and stronger and that's the feeling. But you know, it's the right thing and usually need a coach to help you. [/INST] Yeah, totally. So I mean, I use this thing called training peaks and it's interesting because it actually mathematically shows like where you are on the curve and all this stuff, but you have to like, you have to have that rest, but it's a function of going harder for longer. Again, it's this reinforcement learning like planning the aggregate and long. But a lot of people will hide behind laziness by saying they're trying to optimize for the long run and they're not, they're just not working very hard. But again, you don't have to sign up for, it's totally cool. Like I don't think less of people for like not working super hard, just like don't sign up for things that require working </s><s>[INST] super hard. And some of that requires for the leadership to have the guts, the boldness to communicate effectively at the very beginning. I mean sometimes I think most of the problems arise from the fact that the leadership is kind of hesitant to communicate this socially difficult truth of what it takes to be at this company. So they kind of say, hey, come, come with us, there's with snacks, but [/INST] unlimited vacation. And you know, Ray at Bridgewater is always fascinating because, you know, people, it's been called like a cult on the outside or cultish and but what's fascinating is like they just don't give on their principles. They're like, listen, this is what it's like to work here, we record every meeting, we're like brutally honest and that's not gonna feel right to everyone. And if it doesn't feel Reggie totally cool, just go work somewhere else. But if you work here, you are signing up for this and that's, that's been fascinating to me because it's honesty upfront. It's a system in which you operate. Um and if it's not for you, like no one is forcing you to work there, right? </s><s>[INST] I actually did. So I did a conversation with him at uh kind of got stuck in a funny moment which is uh at the end I asked him to give me honest feedback of how I did in the interview and that was, I don't think so. He was super nice. He asked me, he's like, well tell me did you accomplish what you were hoping to accomplish? I was like that's not, that's not, I'm asking you as an objective observer of two people talking. How do we do today? Hm And then he's like, well I'm, he gave me this politician answer. Well I I feel like we've accomplished successful communication of like ideas which is I'd like, I'd love to spread some of the ideas in that principles and so on. [/INST] Back to my original point, it's really hard to get </s><s>[INST] even for radar. Really [/INST] hard to give feedback. And one of the other things I learned from him and just people in that world is like man, humans really like to pretend like they've come to uh that they've come to some kind of meeting of the minds. Like if there's conflict, if you and I have conflict, it's always better to meet face to face, right or on the phone slack is not great write emails, not great but face to face. What's crazy is you and I get together and we actively try to, even if we're not actually solving the conflict, we actively try to paper over the conflict. Oh yeah, it didn't really bother bothering me that much. Oh yeah, I'm sure you didn't mean it. I'm, but like, no in our minds were still there. Um, so this is one of the things that as a leader you always have to be digging, especially as you </s><s>[INST] ascend to the [/INST] conflict as you ascend, no one wants to tell you you're crazy, no one wants to tell your, your idea is bad and you can, you're like, oh, I'm going to be a leader. And the idea is I'm just going to ask people want tells you. So like you have to look for the markers knowing that literally just people aren't going to tell you along the way and be paranoid. I mean you asked about selling the company, I think one of the biggest differences between me and a lot of other entrepreneurs is like, I wasn't completely confident, we could do it, like we could be alone and actually be great and if any entrepreneurs honest with you, they also feel that way, but a lot of people are like, well I have to be cocky and just say I can do this on my own, I we're going to be fine, we're going to crush everyone. Some people do say that and then it's not right and they fail, but </s><s>[INST] being honest in that moment with yourself with those close to you [/INST] and also you talked about the personality of leaders and who resonates and who doesn't, it's rare that I see, uh, leaders be vulnerable, rare. And one thing I tried to do at instagram at least internally was like, say when I screwed up and like point out how I was wrong about things and point out where my judgment was off. Everyone thinks they have to about 1000, right? Like that's crazy. The best quant hedge funds in the world, about 50.1%. They just take a lot of ETS right renaissance. They might, they might get 51% right. But holy hell, like the question isn't, are you right? Every single time? And you have to seem invincible. The question is, how many at bats do you get in on average? Are you, are you better on average right? With enough bets and enough at bats that your aggregate can be very high. I mean steve jobs was wrong and a lot of stuff. The newton is too early, right max, not quite right. Um, there was even a time where, and he said like no one will ever want to watch video on the ipod totally wrong, but who cares if you come around and realize your mistake and fix it, </s>

<s>[INST] Yeah, but the difficult question is before even the fact that we don't know how life or originates. I don't think we even know what life is like definitional e like formalizing a kind of picture of in terms of the mechanism we would use to, to search for life out there or even when we're on the planet to say is this life is this rock. They just moved from where it was yesterday life or maybe not even rock something else. [/INST] I got to tell you, I want to know what life is. Okay. And I want you to show me, </s><s>[INST] I think there's a song to basically accompany every single thing we talked about today and probably half of them are love songs. Um, and somehow we'll integrate George michael into the whole thing. Okay, so your intuition is, there's life everywhere in our universe. Do you think there is intelligent life out there? [/INST] I think it's entirely plausible. I mean, it's entirely plausible. Um, I think I think there's intelligent life on Earth. Um, and </s><s>[INST] so yeah, taking that like, say whatever this thing we got on earth. Well, there's dolphins or humans say that's intelligent, [/INST] definitely dolphins. I mean, have you seen the dolphins? </s><s>[INST] Well, they do some cruel stuff to each other. So if cruelty is the definition of intelligence that they're pretty good and then humans are pretty good in that regard, Then there's like, uh, pigs are very intelligent. I gotta, I can't actually a chance to hang out with pigs recently and there, um, aside from the fact they were trying to eat me. They're very, uh, they're very, they love food. They love food, but there's an intelligence to their eyes that was kind of, uh, Like Haunts me because I also love to eat meat. And then to meet the thing I later eight and that was very intelligent and almost charismatic with the way it was expressing himself herself itself was, was quite incredible. So all that to say is if we have intelligent life here on earth, if we take dolphins, pigs, humans from the perspective of like planetary science, how unique is earth? [/INST] Okay, so earth is not a common outcome of the planet formation process. Um It's probably a something on the order of maybe a 1% effect. And by Earth, I mean not just an earth mass planet. Okay. I mean the architecture of the solar system that allows the earth to exist in its kind of very temperate um way one thing to understand this is this is pretty crucial right? That the earth itself formed well after the gas disk that formed the giant planets um had already dissipated. You see stars start out with, you know, the star and then a disk of gas and dust that encircles it. Ok from this disk of gas and dust, big planets can emerge. And we have, over the last uh 23 decades discovered thousands of extrasolar planets as an orbit of other stuff. What we see is that many of them are have these expansive hydrogen helium atmospheres. The fact that the earth doesn't is deeply connected to the fact that an earth took about 100 million years to form. So we missed that train, so to speak to get that hydrogen helium atmosphere, that's why actually we can see the sky, right? That's why the sky is uh at least in most places. That's why the atmosphere is not completely opaque Um, with that kind of thinking in mind, I would argue that we're getting the kind of emergent pictures that the earth is not. Yeah, everywhere. Right. We, there's sort of a sci fi view of things where we go to some other star and we just land on random planets and they're all Earth like that's totally not true. But the even a low probability event, even if you imagine that earth is a one in a million or one in a, You know, one in 10 million occurrence, there are 10 to the 12 stars in the galaxy, Right? So you just, you always win by, by large numbers. That's right by supply. </s><s>[INST] They say, well, you've hypothesized that our solar system once possessed a population of short period planets that were destroyed by the evil jupiter uh migrating through the solar. And I'd be like, can you explain [/INST] if I was to say, what was the kind of, the key outcome of searches for extrasolar planets, It is that most stars are encircled by short period planets that are, you know, a few earth masses, Right? So a few times bigger than the earth, um, and have orbital periods that kind of range from days to two weeks. Okay, now, if you go in and ask the solar system, what's in our region, right? In that region is completely empty, right? It's just, it's astonishingly hollow and thank you know, from the sun is not some, you know, special star that decided that it was going to form the solar system. So I think, you know, the natural thing to assume is that the same processes of planet formation that occurred everywhere else also occurred in the solar system. Following this logic, it's not implausible to imagine that the solar system once possessed a system of intra mercury in like, you know, compact system of of planets. So then we asked ourselves would such a system survived to this day? And the answer is no, at least our calculations suggest that it's highly unlikely because of the formation of jupiter and jupiter's primordial kind of wandering through the solar system would have sent this collision, all field of debris that would have pushed that system of planets onto the sun. </s><s>[INST] So it's jupiter, this primordial wandering, what did, what did you put it looked like, like why was it wandering? It didn't have the orbit as today. [/INST] Uh we're pretty certain that giant planets like jupiter when they formed, they migrate. The reason they migrate is uh, you know, on a detailed level, perhaps difficult to explain, but you know, just in a qualitative sense, they form in this fluid disk of gas and dust. So it's kind of like, okay, if I pull up down a raft somewhere in the ocean, will it stay where you plop it down or will it kind of get carried around. It's not really a good analogy because it's not like jupiter is being affected by the currents of gas and dust, but the way it it migrates is it carves out a hole in the in the disk and then through by interacting with the disc gravitationally right, it can change its orbit. The fact that the solar system has both jupiter and Saturn here complicates things a lot because it's you have to solve the problem of the evolution of the gas disk evolution of jupiter's orbit in the gas disk plus evolution of Saturn's and their mutual interaction. The common outcome of solving that problem though is pretty easy to explain jupiter forms, its orbit shrinks and then one Saturn forms its orbit catches up basically to the orbit of jupiter and then both come out. So there's this inward outward pattern of jupiter's early motion that happens sort of within the within the last million years of the lifetime of the solar system's primordial disc. So while this is happening, if our calculations are correct, uh which I think they are, you can destroy these inner, this inner system of, you know, few earth mass planets. And then in the aftermath of all this violence you form the terrestrial planets, </s>

<s>[INST] aren't those status games a source of meaning? Like what why do the games we play have to be grounded in physical reality? Like they are when you're trying to run away from lions, Why can't we in this virtuality world on social media? Why can't we play the games on social media, even the dark ones. And you're but you're saying that's great meaning crisis. [/INST] Well there's a meaning crisis in that there's two aspects of it. Number one playing those kinds of status games. Oftentimes requires destroying the planet because um it's it's it ties to consumption consuming the latest and greatest version of the thing, buying the latest limited edition sneaker and throwing out all the old ones. Maybe it keeps in the old ones. But the amount of sneakers we have to cut up and destroy every year to create artificial scarcity for the next generation, right? This is kind of stuff that's not great. It's not great at all. Um So conspicuous consumption, fueling status games is really bad for the planet, not sustainable. The second thing is you can play these kinds of status games, but then what it does is it renders you captured to the virtual environment. The status games that really wealthy people are playing are all around the hard resources where they're going to build the factories. They're gonna have the fuel in the rare earths to make the next generation of robots. They're then going to one game run circles around you and your Children. So that's another reason not to play those virtual status games. </s><s>[INST] So you're saying ultimately the Big Picture game is one if by people who have access or control over actual hard resources. So you can't, you don't see a society where most of the games are played in the virtual space will [/INST] be captured in the physical space. It's it all it all builds. It's just like the stack, the stack of human being, right? If you only play the game at the cultural and intellectual level and the people, the hard resources and access to layer zero physical are going to own you. </s><s>[INST] But isn't money not connected to or less and less connected to heart resources and money still seems to work. It's a virtual technology. [/INST] There's different kinds of money. Part of the reason that some of the stuff is able to go a little unhinged is because the big sovereignty ease where one spends money and uses money and play money games and inflates money. Um, their, their ability to adjudicate the physical resources and hard resources on land and things like that. Those who have not been challenged in a very long time. </s><s>[INST] So, you know, we went off the gold standard. Most money is not connected to physical resources. It's an idea. And that idea is very closely connected to status. Um, so what, [/INST] but it's also tied to like it's actually tied to law. It is tied to some physical hard things. So you have to pay your taxes. </s><s>[INST] Yes. So it's always at the end going to be connected to the Blockchain of physical reality. So in the case of law and taxes, it's connected to government and uh, government is what violence is. The, I'm playing Devil's advocate here. Uh, and popping one Devil off the stack at a time isn't ultimately, of course it will be connected to physical reality. But just because people control the physical reality doesn't mean the status. Lebron James in theory could make more money than the owners of the teams in theory. And to me that's a virtual idea. So somebody else constructed a game and now you're playing in the space of virtual uh, in the virtual space of the game. And so it just feels like there could be games where status, we build realities that give us meaning in the virtual space. Like I, I can imagine such things being possible. [/INST] Oh yeah, okay. So I see what you're, I think I see what you're saying there with the idea there. I mean we'll take the Lebron James side and put in like some Youtube influencer, right? So Youtube Youtube influencer. It is status games, but at a certain level it precipitates into real dollars and into like, well you look at </s><s>[INST] Mr Beast right? [/INST] He's like setting off half a million dollars worth of fireworks or something right on the Youtube video </s><s>[INST] and also like saving, you know, like saving trees and so on your right [/INST] trying to plant a million trees with mark rober or whatever it was. Yeah. Like it's not that those kinds of games can't lead to real consequences. It's that for the vast majority of people in consumer culture, they are incented by the, I would say mostly I'm thinking about middle class consumers. They're incented by advertisements. They're scented by their magnetic environment to treat the purchasing of certain things that need to buy the latest model, whatever that need to appear however they need to pursue status games as a driver of meaning. And my point would be that it's a very hollow driver of meaning and that is what creates a meaning crisis because at the end of the day, it's like eating a lot of empty calories, right? Yeah, it tasted good going down a lot of sugar but man it did not, it was not enough protein to help build your muscles and you kind of feel that in your gut and I think that's I mean all this stuff aside and setting aside the discussion on currency which I hope we get back, get back to. That's what I mean about the meaning crisis part of it being created by the fact that we don't um we're not encouraged to have more and more direct relationships. Were actually alienated from relating to even even our family members sometimes. Right? We're we're encouraged to relate to brands. Were encouraged to relate to these kinds of things that then tell us to um do things that are really of low consequence and that's where the meaning crisis comes from. </s>

<s>[INST] beginning, think of poor Charlie Darwin. Charlie, I see he is on nickname levels with you. Well, because we're talking about these big topics of sexism, racism, and hate. You should not forget about the smaller topics which might even have the much bigger impact, which is what you're speaking to, which is outlier ideas in science. So basically, welcoming controversial ideas in science. And by controversial, I mean, just stuff that most of the community doesn't agree on, it doesn't actually harm anyone at all. But even then, there's always pressure. One of the things I'm really concerned about is how little power young faculty have. That there's a kind of hierarchy, seniority, that universities have, empowered by the administration. Where the young faculty that come in, they're kind of... Pre-tenure. Yeah. There's a process in chasing tenure where you're kind of supposed to behave. And there's an incentive to kind of fit in, and to not be an outcast. And that's a really huge problem, because oftentimes, the youth is when the craziest, the biggest ideas, the revolution ideas come. And if you're forced to behave, and fit in, and not speak out, then even in the realm [/INST] of science, the innovation is stifled. Yeah. </s><s>[INST] Well, now you trigger my, having to tell you this story. You're triggered. [/INST] This is good. In the mid-1980s, I decided to take a four-month sabbatical from my law practice. Yes. Professor James Vorenburg, who was at the time Dean of the Harvard Law School, heard about it, heard about it from his wife, Elizabeth Betty Vorenburg, whom I was very friendly with, because we were both on the ACLU, the ACLU of Massachusetts Board at the time. And Betty told Jim that Harvey was taking a sabbatical. Jim called Harvey, and asked Harvey if he would like to teach a course at the Harvard Law School, because there was nobody who had teaching criminal law from the perspective of somebody who actually was in court, litigated. It was all theoretical. I said, sure, I'll do it. So I taught a semester at Harvard Law School. The student evaluations were fabulous. Why? Because it was really interesting. They were hearing a lawyer who was talking about real cases. I actually brought in a few of my clients to some of the classes. And so Jim called me and said, Harvey, the students love this course. I'd like to offer you a tenure-track position. At the law school, you'd have to give up your law practice. I turned him down. He said, did you just say no? I said, yes. I said, no. He said, how come? He says, nobody has ever, in my administration, has ever turned down a tenure-track offer at Harvard Law School. I said, because I could see that I'm not a good fit, that the administrators overrun the place, that faculty members, especially untenured, who are afraid to say things that might not help them in the tenure quest, it's not a good fit for me. </s><s>[INST] You saw this in the mid 1980s already. [/INST] Yes. 1980s already. Yes, 1985. And I went back to my law practice. I did not want to get into this me grind that I saw. After all, I started to see it before the turn of the century because I co-authored The Shadow University in 98 and then co-founded Fire in 99. </s><s>[INST] I'm an early student of this phenomenon. [/INST] What are some other aspects of the book The Shadow University that we may have not covered? Well, let me tell you a story. I believe I tell it in The Shadow University because it was part of- I'm loving these stories, Harry. The stories are fabulous. Let me tell you a story of- I did a tour of the country visiting campuses. I visited a college called Hamline University, I believe it was in Indiana or Illinois, somewhere in the Midwest, and I attended a freshman orientation. Now listen to this. This was a freshman orientation. The administrators, the deans and the deenets and the deputy assistant deans and deenets and the third deputy assistant deans and deenets lined the students up according to their skin hues. The blonde, blue-eyed white folks were at one end, darkest African Americans whose blood lines had not yet mixed with any of the whites on the other end. The exercise was you had to tell how your race affected your success in life up until that point. I thought it was the most demeaning thing that Y could imagine. Demeaning. I thought to myself, they could do the same about sexual orientation, they could do the same about religion, they could do the same about national origin. it would be demeaning no matter what. And the students actually verbalized how their race had either been a plus or a minus. They did. They did. And I thought it was so demeaning, it just confirmed all of my distaste </s><s>[INST] for this kind of approach. Let me ask you from the interviewer seat. So I get to do this podcast and I often have to think about giving a large platform and having a conversation with very controversial figures. And the level of controversy has been slowly increasing. What's the role of this medium to you? This medium of speech between two people and me speaking with a controversial figure, me or some other interviewer. What's the role of giving platform to controversial figures? Same members of the KKK or dictators, [/INST] people who are seen as evil. Well, we want to face the world with reality. And the reality is that there are some unpleasantness in the world, running from genocide right through to ordinary discrimination, to offensiveness. It's the real world as we know it exists. Are we afraid to say it? Do we want to make people think that we live in a world where those words are not used, where those animosities don't exist? </s>

<s>[INST] How long does it take If you look at the 22 fast ai courses, how long does it take to get from 0 to completing both courses. [/INST] It varies a lot. Somewhere between two months and two years. Generally </s><s>[INST] for two months. How many hours a day? So [/INST] like, so like uh, somebody who is a very competent coder can Can do 70 hours per course and </s><s>[INST] 77 0. That's it. Okay. [/INST] But a lot of people I know take a year off to study fast day, I full time and say at the end of the year, they feel pretty competent because generally there's a lot of other things you do, like, they're generally, they'll be entering cattle competitions, they might be reading in Goodfellas book, they might, you know, they'll be doing a bunch of stuff and often, particularly if they are a domain expert, their coding skills might be a little on the pedestrian side. So part of it's just like doing a lot more writing. </s><s>[INST] What do you find is the bottleneck for people usually accept getting started setting stuff up. [/INST] I would say coding. Yeah, I would say the best, the people who are strong coders pick it up the best. Although another bottleneck is people who have a lot of experience of classic statistics can really struggle because the intuition is so the opposite of what they used to. They are very used to like trying to reduce the number of parameters in their model and looking at individual coefficients and stuff like that. So I find people who have a lot of coding background and know nothing about statistics are generally going to be the best off. </s><s>[INST] So, uh, you taught several courses on deep learning and as feynman says, the best way to understand something is to teach it. What have you learned about deep learning from teaching it [/INST] a lot. That's a key reason for me to, to teach the courses. I mean obviously it's going to be necessary to achieve our goal of getting domain experts to be familiar with deep learning, but it was also necessary for me to achieve my goal of being really familiar with deep learning. I I mean, to see so many domain experts from so many different backgrounds, it's definitely, I would say taught me but convinced me something that I like to believe it's true, which was anyone can do it. So there's a lot of kind of snobbishness out there about only certain people can learn to code, only certain people are going to be smart enough to like, do a I that's definitely bullshit. I've seen so many people from so many different backgrounds get state of the art results in their domain areas. Now, it's definitely taught me that the key differentiator between people that succeed and people that fail is tenacity. That seems to be basically the only thing that matters the people, a lot of people give up and but if the ones who don't give up pretty much, everybody succeeds, you know, even if at first I'm just kind of like thinking like, wow, they really quite getting it yet, are they? But eventually people get it and they succeed. So I think that's been, I think that both things I'd like to believe was true, but I don't feel like I really had strong evidence for them to be true, but now I can say, I've seen it again and again, </s><s>[INST] so what advice do you have for someone, uh who wants to get started in Deep Learning [/INST] train lots of models. That's that's how you that's how you learn it. So like, so I think it's not just me. I think I think our course is very good, but also lots of people independently. I said it's very good. It recently won the codex award for AI courses as being the best in the world that come to our course course not fast today. I and the thing I keep on hopping on in my lessons is train models, print out the inputs to the models. Print out to the outputs to the models. Like study, you know, change change the inputs a bit. Look at how the outputs vary. Just run lots of experiments to get a, you know, an intuitive understanding if what's going on </s><s>[INST] to get hooked. Do you think you mentioned training? Do you think just running the models Inference, if we talk about getting started. No, [/INST] you've got to find you in the models. So that's that's that's the critical thing because at that point you now have a model that's in your domain area. So there's there's there's no point running somebody else's model because it's not your model, like, so it only takes five minutes to find tuna model for the data you care about. And in less than two of the course, we teach you how to create your own data set from scratch by scripting, Google image search. So we show you how to actually create a web application running online. So I create one in the course that differentiates between a teddy bear, a grizzly bear and brown bear and it does it with basically 100% accuracy. Took me about four minutes to scrape the images from google search from the script. There's a little graphical widgets we have in the notebook that help you clean up the data set, there's other widgets that help you study the results to see where the errors are happening. And so now we've got over 1000 replies in our share your work here thread of students saying here's the thing I built and so there's people who like a lot of them are state of the art. Like somebody said oh I tried looking at devon gary characters and I couldn't believe it. The thing that came out was more accurate than the best academic paper after lesson one and then there's others which are just more kind of fun. Like somebody who's doing Trinidad and tobago hummingbirds. She said that's kind of their national bird and she's got something that can now classify a Trinidad and tobago hummingbirds. So train models fine tune models with your data set and then study their inputs and outputs. </s>

<s>[INST] the existential aspect of it does not worry you deeply. The fact that this ride ends. [/INST] No, it began. I mean, the ride began, right? So there was I don't know how many billions of years before that I wasn't around. So that's okay. But </s><s>[INST] isn't the experience of life, it's almost like feels like you're immortal because the way you make plans the way you think about the future, if you if you look at your own personal rich experience, yes, you can understand, okay, eventually I died. There's people I love that have died, so surely I will die and it hurts and so on. But it sure doesn't. It's so easy to get lost and feeling like this is gonna go on forever. Yeah, it's [/INST] a little bit like the people who say they don't believe in free will, right? I mean, you can say that, but but when you go to a restaurant, you still have to pick a soup and stuff. So, right, So, so I don't know if I've actually seen that that happened at lunch with a with a well known philosopher and you didn't believe in free will. And, you know, the waitress came around and he was like, well, let me see, I was like, what are you doing? You're you're gonna choose a sandwich. Right? So um it's I think it's one of those things, I think you you can know that, you know, you're not gonna live forever, but you can't you can't it's not practical to live that way unless you know, so you buy insurance and then you do some stuff like that. But but but mostly, you know, um I think you just you just live as if as if as if you can make plans. </s><s>[INST] We talked about all kinds of life. We talked about all kinds of embodied minds. What do you think is the meaning of it all? What's the meaning of all the biological eyes we've been talking about here on earth? Why are we here? [/INST] I don't know that that's a that's a well post question other than the existential question you post before, </s><s>[INST] is that question hanging out with the question of what is consciousness and their uh retreat somewhere. [/INST] Not sure because </s><s>[INST] sipping pina coladas and because they're ambiguously defined, [/INST] maybe I'm not sure that any of these things really ride on the correctness of our scientific understanding that I mean, just just for an example, right? Um I've always found I've always found it weird that uh people get really worked up uh to find out realities about their their bodies. For for for example, write that you've seen them ex machina, right? And so there's this great scene where he's cutting his hand to find out, you know peaceful of cock now to me, </s><s>[INST] right? [/INST] If if if I open up and I find out in a fine bunch of dogs, my conclusion is not, oh crap, I must not have true cognition. That sucks. My conclusion is wow. Cogs can have true cognition. Great. So right, so so it seems to me, I guess I guess I'm with a card on this one that whatever whatever the truth ends up being of of of how is what is consciousness, how it can be conscious. None of that is going to alter my primary experience, which is this is what it is. And if and if a bunch of molecular networks can do it fantastic if it turns out that um there's a there's a non corporeal, you know, so great. We can, you know, we'll study that whatever. But but the fundamental um </s><s>[INST] existential [/INST] aspect of it is, you know, if somebody, if somebody told me today that yeah, yeah, you were created yesterday and all your memories are, you know, sort of fake, you know, kind of like uh like like Goldsman brains right? And human, you know, human skepticism and all that. Uh Yeah. Okay, well, so so but but here I am now. So, so </s><s>[INST] let's experience it's primal. So like that's the that's the thing that matters. So the backstory doesn't matter the explanation. [/INST] I think so from the first person perspective now, from a third party, like scientifically it's all very interesting from a third person perspective, I could say, wow, that's that's amazing that that this happens and how does it happen or whatever. But from a first person perspective, I could care less. Like I just, it's just what I what I learned from any of these scientific facts is okay, well I guess then that's that that then I guess that's what is sufficient to to give me my, you know, amazing first person perspective. </s><s>[INST] I think if you dig deeper and deeper and get a get surprising answers to why the hell we're here, it might give you some guidance on how to live. [/INST] Maybe maybe, I don't know. Um That would be nice. On the one hand, you might be right, because on the one hand, if I don't know what else could possibly give you that guidance, Right? So, so you would think that it would have to be that it would it would have to be science because there isn't anything else. So, so that's so maybe on the other hand, I am really not sure how you go from any, you know, what they call from is to uh not right from any factual description of what's going on this. This goes back to the natural, right? Just because somebody says, oh man, that's that's completely not natural, that's never happened on Earth before. I I'm not, you know impressed by that whatsoever. I think, I think whatever has or hasn't happened, we are now in a position to do better if we can write </s>

<s>[INST] yeah, so it builds a good foundation for a language is getting a large vocabulary. It's really interesting. There's something I do, which is called space repetition, which is a programmatic way of doing this kind of system that you've developed yourself, which is if you successfully remember a thing, it's going to be a longer time before it brings it up to you again. Now that requires a computer to keep track of the information if you have cars. That's a really interesting pile system 12345, you upgrade it 12345 maybe I wouldn't go to the archive and go to number two to pile one right away. Maybe I would go to like, I don't know pile five perhaps is probably the right place to put it because because you have to go through that full step again. But that is a really powerful way to uh learn definitely language but also facts like people that go to medical school [/INST] and you pretty much when you're done, you know what, you know, you don't have </s><s>[INST] to use it to integrate it into the music of language. That's more difficult. [/INST] There's </s><s>[INST] a charm. I mean maybe it's not good for Spycraft, but there's a charm to this kind of, to having an accent and using words incorrectly but confidently there's a, because language isn't a simple formula language is the play of words. So actually using the incorrect synonym, you know, as a, you know, if instead of saying I'm cold saying I'm chilled, something like using off beat words can actually be part of the charm. So it's interesting if you can learn how to use that correctly. Uh, because I have no a bunch of people with the Russian accent and I feel like they get away with saying a lot of ridiculous shit because they're able to sort of leverage the charm of the non sequiturs by [/INST] the way, by the way, just 11 thing you talked about using a computer when I had my first personal computer, I actually wrote a program that does, </s><s>[INST] that does that by the way, when was that one? Because you were uh world class programmer for time. Very good programmer. When when did the TTC [/INST] was probably 1984, </s><s>[INST] 1984. When did you fall in love with programming? [/INST] When I went to college in the US and part of the core curriculum was that you were required to take a course and computer and it was mostly just, you know, talk, but we also had to learn a language. We had to write some programs in FORTRAN which was what five at the time it was, it was a dumbed down FORTRAN. But listen, so </s><s>[INST] I [/INST] see the ability, I see what, what you can do with this. I programmed a sine curve and then I divided the sign curve into really, really small rectangles and then ran the program and it came up with the right area, wow, this is great. </s><s>[INST] That's incredible. It's incredible. It's so powerful. It's a, you're creating, creating a little helper, helps you understand the world to help you analyze the world and so on. Uh we'll return to that because it's interesting. So you have so many interesting aspects to your life, but Moscow. So yeah [/INST] let me let no, let me how I was sent to Moscow. Okay, so one day I had a visitor from Moscow uh and he came to visit me in my apartment together with Nikolai and he, you know, we talked and then he said, so how's your english? I said I pulled the book from the shelf and says I can read that without the help of a dictionary. Oh that's interesting. And he said you know what, we're going to send you a tape recorder and you just talk, Say something, you know for 20 minutes, whatever you want to talk about. Uh they sent this thing and two weeks later I was on a plane to Moscow because I also spoke english sort of the british variety of english with not a strong german accent because I've always had the ability to imitate others and sounds, there was an innate ability. I would uh you know, when, when, when we were in a lab and students, I would very often do uh monologues, imitating east german comedians, you know? Yes, yes, I'm not good enough to make a living out of it, but that raised in some interest. And so they sent me to Moscow, there was the first time on a plane by the way. Um And I had a conversation with two ladies who spoke English. one was Russian Professor Lamar University, she was obviously KGB that was her cover. And the other one was an american born lady by </s><s>[INST] the way she was an actual professor and using that as a cover or is it just a story? [/INST] No, I she said she was a professor, she may have taught there too. And </s><s>[INST] that's an interesting distinction. One is like a story you tell people and one is like you legit are doing the thing but also as a color. Anyway, that's that's an interesting aspect of how to be a good liar. You might you might as well live the lie. Yeah [/INST] exactly. Right. So the other one was a middle aged, the Russian was pretty young. The other one was middle aged american. And and so we talked for maybe a couple of hours and then they withdrew and I was left alone. Eventually my my liaison, he came back in and he said it was close. But the american things you can actually uh become uh you get close enough to become becoming a native speaker of american english. And he said the Russian was very doubtful. So I think wishful, it was a tie, literally wishful thinking prevailed. So within a couple of weeks I was moving to Moscow. Mhm. </s>

<s>[INST] but it's very inefficient. Kamikaze is very inefficient. You want to be very like wars, it's the same discussion to jujitsu, right? You want to be, you want to create an asymmetry of power and you want to be efficient in the way you deliver that power. It actually goes back to the picking up a cup. Currently, a lot of things we do in war, like most of the drones that you hear about, they're not autonomous, not most all, they're usually piloted by the piloted remotely by humans and humans are really good at this kind of uh what's necessary to deliver the most damage, targeted damage effective as part of the largest strategy have about bombing the area or all that kind of stuff. I don't know how difficult that is to automate. I think the biggest concern, I actually have a sense that it's very difficult to automate. The biggest concern is almost like an incompetent application of this and uh consequences that are not anticipated. So you have a drone army where you say we want to target, you give it power to target a particular terrorist. And then there's some bug in the system that has like for example has a large uncertainty about the location of that terrorist and so decides to bomb an entire city. You know, almost like there's a bug, a software bug, I'm much more concerned about like bad programming and software engineering that I am about like malevolent ai systems that destroy the world. So the more we rely on automation, this is the lesson of human history, the more we give to Ai to software to robotic systems. The more we forget how to supervise and oversee some of the edge cases, All the weird ways that things go wrong and then the more stupid software bugs can lead to huge damage like you know, even like nuclear explosions, those kinds of things. If we add a I into the launch systems for nuclear weapons for example, I think human history teaches us that software bugs is what will leave lead to World war three, not malevolent ai or human beings [/INST] interesting </s><s>[INST] by the way, I deeply appreciate how knowledgeable you are about the history of artificial intelligence. That was awesome. [/INST] It's fascinating stuff. You know, I remember reading when I was a child about you know turing tests and things like this and visionaries from the 1950s had ideas to see it come. This virus just fascinating to me. Um Yeah, Okay, so so what can we as Judah two players take away from this, we saw that when it comes to computers versus humans in chess tournaments, humans had something truly valuable to give to the computers. That was heuristic rules. In every coaching program that I run. I make an endless quest to search out and find effective heuristic rules. That's the basis of a good training program. Heuristic rules and principles give vast informational content which can rapidly increase your performance on the mat just as they rapidly increase the performance of chess computers to overcome the human adversaries. The great human weakness is computational power Most people vastly overestimate their ability to reason and problem solve under stress. In fact, numerous psychological studies have shown that humans can balance a relatively small number of of competing options in in stressful decision making. But what we do have, what is it? The great and unique human gift is this idea to come up and arrive at heuristic rules and principles which turned out to be very effective guides to behavior for both human behavior and artificially intelligent behavior. Make that your focus in study. Don't try to remember 10,000 different details on a move. Okay, that's that's human weakness, not human strength. Our strength is heuristics make that your focus not endless computations over 25 details here emerged with 27 details here. That that's not that's not what humans are good at. The uniquely human strength is arriving at these heuristic rules and principles which guide our behavior which provides simplifications which enable us to take vast amounts of information and carry it down to a few simple rules that effectively guide our behavior. Take that core insight from the discussion that lex and I just had. It was a complex discussion. We both apologize for going a little bit over. Well that was awesome and dragging you into some details there but take that away from it. It'll make you better at you did soon. Sorry, lex </s><s>[INST] That was that was a really exciting discussion and uh the depths of knowledge in the dimensions of knowledge you have an interest you have is just fascinating. Is there advice you have for complete beginners? For white belts? They're starting jitsu there, listening to this. They haven't done you yet. So I know there's a lot of people who are super curious to start. Is there advice you would give them on their journey? [/INST] Yeah, I'm just going to talk about just getting better on the mat. Okay. Because there's 1000 other things you're talking about in terms of like morale and persistence and how often they should train. There's 1000 things you get </s><s>[INST] up with your girlfriend or boyfriend. Let's put that aside. Um That's probably the best advice [/INST] we give. Um it goes back to what we said earlier, I always advocate start your training from the ground up. Okay, your first sessions and Judah to you're going to find to your horror that everyone gets on top of you and you can't get out and it's a dispiriting, crushing kind of feeling that you just have no skills and you have no prospects in the sport. So your first skill is the skill of being able to free yourself from positional pens. Mhm. Most of the escapes and judas, you go to God position. And so once you get someone your guard, they're gonna be looking to pass your guard and get back into those positional pins that you just escaped from and that's just as crushing as getting pinned. You feel like every time you try to hold someone in God, they just definitely pass you by. So your first two skills, you got about a get out of any pin and you got to hold someone in your guard. So Penn escapes and God retention are your first two skills. I generally advocate the idea of learning to fight from your back first and then learning to fight from on top second. Why? Because the brute fact is when you first start off, you just don't have enough skills to hold top positions or gain top position through a takedown. So inevitably you're gonna end up underneath people for most of your training time. Your training should reflect that in the early days as a white belt. Start with the first two skills you need, they're not the most exciting, they're not sexy skills that are going to make you look at a study in the training room, but they're going to keep your life long enough to learn those sexy skills in the future that will make you look like a start, start with pen escapes, Go to God retention and focus heavily on those two when you start to get into offense, start with bottom position. So there's a clear continuity between your pen escapes your guard retention and then you'll guard itself. Okay, you've got different options with God, some of you gonna like close guard, some of you are gonna like variations of open guard, some of you don't like to be seated, some of you would like to be supine. Some of you are going to like half guard as a general rule. This is a heavy generalization, but I'm going to give it to you in my experience, most people benefit the most by starting with half guard first. I know that traditionally judas who has been taught closed guard first and then all the other guards come after that. I'm a big believer in the idea of start with pen escapes, then go to guard retention and then start with half guard bottom. That way you get a nice continuity between your first three skills and you make good progress over those first critical six months in jujitsu. </s>

<s>[INST] Acacia is really different. Uh, is really interesting as an example. So insurance is a fascinating space. It seems like a very ripe still for disruption across the board. So how do you, it seems like a lot of the disruption has to do with like uh almost the first dump step of, we've been using mostly paper, like it's not digitized, you have to basically convert, create a uh infrastructure in a framework where like everybody is using the same digital system like databases and just organize the data that it seems like that's a huge leap that basically can revolutionize major industries that still hasn't been done. Insurance is obviously the great example of that. [/INST] And one of the things that struck me the founder ceo of actions guy named Greg Williams, they're out of grand rapids michigan and as we were looking at expanding our footprint and insurance, I met with a lot of insurance executives and they would talk about technology, but Greg uh truly understood the power of what would happen across actuarial sciences, uh you know, predictive analytics and using machine learning to really run every aspect of your business and then automating a lot of the, just the back office tedious steps. And as you said, one of the things that was great for us, they already had um a data collection system and departments, so it was much easier to pivot. Um and you know, I'm very excited about the future of that company. It's ah you know, they're they're doing some pretty innovative uh groundbreaking things and those are the things that I like doing right is that um yes, I want to make money. Just, you know that that's what that is, but at the same time, what did you do with your time on earth, right. Did did you do anything to leave any kind of mark that you know, you did anything interesting? I I can only speak for myself, there are many more ways to measure one's life and I can only speak about how I think about things. Um You know, I grew up poor in upstate new york with a single mom and watched her work a couple of jobs and you know had to from a young age, you know, shovel snow and mow lawns and do all kinds of things to help her make sure, make sure the lights weren't turned off in our little place. And so that's just something that I've always been driven towards and um you know, I just, I have a really eclectic tastes and interests and um you know, it's just it's just been an interesting journey. </s><s>[INST] So help be part of and help enable some cool new creations across the board, like film, music, ai manufacturing, just, you know, insurance, all the, all the specific uh industries that have disrupted. Yeah. Uh small tangent back to your childhood with your mom. Any memories kind of stand out, stick with you as is something that helped define who you are as a man [/INST] even though, you know, the university and college experience was not part of the family tree. Um and we had no connections. I didn't understand, I didn't know what a trust fund was or prep school. I didn't know what any of that was. Um but my mom from a young age would always say, you know, you're going to go to college, There's no, you know, if you choose to and I, and I think from a young age that was just an expectation. Um that that I had and that she instilled and the work ethic I watched her and then my my grandmother was, Was a janitor, a cleaning lady in a hospital for 50 years. And then I remember there were times of, you know, I'm probably 10 years old. It's freezing cold out and if I don't go out and shovel six driveways, we don't have enough money to pay the bill. So I don't know, I'm not a psychologist so I don't know how that manifests itself in my life today. But I think the grit to say I'm not in the mood to do this. I don't want to do this, but that's the work that needs to be done and no excuses not. I'm a victim and I'm gonna sit around and talk about, no, it is what it is and you have to get done what you need to get done. And again, I think it's uh you can never fully put yourself in someone else's shoes or experience because I don't know what that is or feels like, but for me, Those were two, I think formative things um that that were important in my </s><s>[INST] child, so that that's pretty, the reality of life, like that is pretty humbling. You still, you've been so exceptionally successful that it's easy to get soft now. How do you get humbled these days [/INST] by getting up? You know? You know, I think um for me personally trying to push the envelope and being weighed and measured, right? That's why I always love sports too. There's a scoreboard and you know, I'm a huge believer in opportunity, meritocracy, all those things that I think are ideals that we want to aspire to. And I think that um there's a lot of things I'm involved with right now that I just want to see if I can do it, I want to see if, you know if and, and you know, my own little mantra has caused the outcome right, as much as you can, and at the same time have the humility and not to have the hubris or arrogance to say I'm always going to cause the outcome because you'll get your ask eQt pretty quickly and and humbled the world and the universe is a big place with forces, you know, being beyond. Uh but I think, um you know, I also think a lot about being intellectually honest, which when I do university talks and so forth, I I think that's a superpower because if you find yourself making decisions based on other people's expectations based on places you don't want to go, but you know, you're you're either you feel like momentum is taking you there. Um I think that's a big problem and there there are people that go to our top universities and can't wait to get out and start their own company and they want that pressure and they want to to grind. And there are other people that are smart and talented but just say, look, I I don't want to lay awake staring at the ceiling wondering how I'm gonna make payroll. I don't want that in my life. And I think if you can square that up and be okay with it and say what what makes me tick, what makes me happy, what puts me in a bad head space, Because there's a difference between challenging yourself and going against your nature. So that's why I think that being intellectually honest and being able to really sit down and go inside your own head and say, what am I good at? What am I not good at? How am I going to put myself in a position to be successful? Because, you know, I'm working on my weaknesses, but I'm not gonna put myself career wise in a position where I I'm just fundamentally gonna have a hard time being successful. </s>

<s>[INST] The propagation of DNA. But what do you make of this unfortunate fact that we are mortal? Do you ponder your immortality? Does it make you sad? [/INST] I ponder it it makes me sad that I shall have to leave um and not see what's going to happen next. Um If there's something frightening about mortality apart from sort of missing, as I said, something more deeply darkly frightening. It's the idea of eternity. But eternity is only frightening if you're their eternity, but before we were born, billions of years before we were born and we would effectively dead before we were born. As I think it was Mark Twain said I was dead for billions of years before I was born and never suffered the smallest inconvenience. That's how it's going to be afterwards after we leave. So I think of it as really eternity is a frightening prospect. And so the best way to spend it is under a general anesthetic, which is what it'll be </s><s>[INST] beautifully put. Richard is a huge honor to meet you to talk to you. Thank you so much for your time. [/INST] Thank you very much. </s><s>[INST] Thanks for listening to this conversation with Richard Dawkins and thank you to our presenting sponsor cash app. Please consider supporting the podcast by downloading cash app and using culex podcast. If you enjoy this podcast, subscribe on youtube review with five stars on apple podcast. Support on Patreon are simply connect with me on twitter. Elex Friedman and now let me leave you with some words of wisdom from Richard Dawkins, we are going to die and that makes us the lucky ones. Most people are never going to die because they're never going to be born. The potential people who could have been here in my place, but who will in fact never see the light of day outnumber the sand grains of Arabia. Certainly those unborn ghosts include greater poets than Keats, scientists greater than Newton. We know this because the set of possible people allowed by our DNA so massively exceeds the set of actual people in the teeth of these stupefying odds. It is you and I in our ordinary nous that are here we privileged few who won the lottery of birth against all odds. How dare we wind at our inevitable return to that prior state from which the vast majority have never stirred. Thank you for listening, and hope to see you next time. [/INST] </s>

<s>[INST] I'm excited by the possibility of one day there will be for various moons and planets that would be uh like news programs reporting the weather with the fake confidence of like as if you can predict the weather. Uh, we talked quite a bit about planets and moons. Can we talk a little bit about asteroids? For sure. What is uh, what's an asteroid? And what kind of asteroids are there? [/INST] So the asteroids, let's talk about just the restricted to the main asteroid belt, which is the region, it's a region of debris basically between mars and jupiter. Um, and the, these sort of belts of debris throughout the solar system, the outer solar system, you know, the kuiper belt that we talked about, the asteroid belt as well as certain other populations where they accumulate because they're gravitationally more favored um are remnant objects from the origin of the solar system. And so one of the reasons that we are so interested in them aside from potentially the fact that they could come hit Earth. But uh, scientifically it's um, it gives us a window into understanding the composition of the material from which Earth and the other planets formed and how that material was kind of redistributed over the history of the solar system. So the asteroids, one could classify them in two different ways. Some of them are ancient objects. So they a created out of the sort of disk of material that the whole solar system formed out of um, and have kind of remained ever since, more or less the same. They've probably collided with each other and we see all these collision, all fragments and you can actually look and um based on their orbits say, you know like these 50 objects originated as the same object. You can see them kind of dynamically moving apart after some big collision. Um and so some of them are these ancient objects, maybe that have undergone collisions. And then there's this other category of object that is the one that I personally find really interesting, which is um remnants of objects that could have been planets. So early on, a bunch of potential planets secreted that we call planet decimals and they formed and they formed a lot of energy and they had enough time to actually differentiate. So some of these objects differentiated into cores and mantles and crusts uh and then they were subsequently distracted in these massive collisions and they now we have these fragments, we think fragments floating around the asteroid belt that are like bits of mantle, bits of Corbett suppressed basically. Um </s><s>[INST] puzzle pieces you might be able to stitch together or I guess it's it's all uh it's all mixed up. So you can't stitch together the original planet candidates or is that possible to try to see if they kind of, there's too many, there's too many objects in there too. [/INST] I think that there are cases where people have kind of looked at objects and by looking at their orbits, they say these objects should have originated together but they have very different compositions And so then you can hypothesis maybe they were different fragments of differentiated objects. But one of the really cool things about this is, you know, we've been talking about getting clues into the interiors of planets. We've never seen a planetary core or deep mantle directly. Some mantle material comes up on our surface and then we can see it, but you know, in sort of in bulk. Um, we haven't seen these things directly in these asteroids potentially give us a chance to look at what our own core and mantle is like or at least would be like if it had been also floating through space for a few billion years and getting irradiated and all that. But it's it's a cool potential window or like analogy into the interior of our own planet. </s><s>[INST] Well, how do you begin studying some of these asteroids? What if you were to put together a study? Like what are the interesting questions to ask that are a little more specific. Do you find a favorite asteroid that could be tracked and try to try to track it through telescopes or do you, um, is it has to be, you have to land on those things to study it. [/INST] So when it comes to the asteroids, there's so many of them and the big pictures or the big questions are answered. Um, so some questions can be answered by zooming in in detail individual object, but mostly you're trying to do with statistical studies. So you want to look at thousands of objects, even hundreds of thousands of objects and figure out what their composition is. And look at how many big asteroids there are of this composition, versus how many small asteroids of this other composition. And put together these kind of statistical properties of the asteroid belt. And those properties can be directly compared with the results of simulations for the formation of the solar system. </s><s>[INST] What do we know about the surfaces of asteroids or the the contents of the insides of asteroids? And what are still open questions. [/INST] So I would say that we don't know a whole lot about their compositions. Um most of them are small and so you can't study them in such detail with telescopes as you could a planet or moon and at the same time, because there are so many of them, you can send a spacecraft to a few, but you can't really get a statistical survey with spacecraft. And so a lot of what we, a lot of what has been done comes down to sort of classification. You look at how bright they are, You look at uh whether they're red or blue, um, simply, you know, whether their spectrum is sloped towards long wavelengths and short wavelengths, there are certain, uh, if you, if you point a spectrograph at their services, there are certain features you can see. So you can tell that some of them have silicates on them. Um and but these are the sort of, they're pretty basic questions. We're still trying to classify them based on fairly basic information in kind of combination with our general understanding of the material the solar system formed from. And so you're sort of, you're coming in with prior knowledge, which is that you more or less know what the materials are, the solar system formed from. And then you're trying to classify them into these categories. There's still a huge amount of room for understanding them better and for understanding how their surfaces are changing in the space environment. </s>

<s>[INST] So there's uh okay. I mean we probably don't have enough time to talk about the beautiful fusion of minds that happens when two people are flying controlling the plane. But at a high level this is a really interesting question for people who don't know what they're talking about like me, which is what is the difference between a human being and an ai system. Like what can what is the ceiling of current ai technology for controlling the plane? Like how much does the human contribute? Is it possible to have automated flight? For example? Like what is the hardest part about flying that a human does expertly that an Ai system cannot in warfare situations in in flying a fighter jet line. [/INST] So I would say aI systems are usually black and white when you write the algorithm for an Ai system, it's it's it's really it's basically you're taking thought and turning it into a giant math problem is really what you're doing, right? So you've got this logical math problem, math problems are there's there's there's a line that says I can or I can't and it's a it's a very finite line, you know, but you can go up to the line where a human, we all have gray areas where we go, maybe I'll try it. Um So </s><s>[INST] you just can operate within that gray. [/INST] So if you took if you take an airplane and say, and I'll just take a hornet for a while. The super hornet doesn't matter any airplane. And you go here is the flight performance model of the airplane. So if, you know, in uh an E. M. Diagram is the energy. So it basically says The airplane can fly as slow as this. It can go as fast as this. It can pull this many GS force of gravity, you know, so 1, 234567. And then based on the airfoil design and everything else and how it can pull, here's how it's going to fly because it's really physics based well if you depending on how you write the ai. But typically a I you don't want the airplane to leave controlled flight right, You want to maintain it so that it is flying in a controlled envelope where there are times and you can go back to World War One where people intentionally departed the airplane from controlled flight in order to obtain an advantage, which is that's where the human goes. Can I do this? I know it's outside of where I would normally go, but I can do that. So you can do some crazy things now, especially since the flight control logic in modern airplanes with digital flight controls, they're extremely forgiving. So you can literally, I've done things in super hornets that literally, even as a pilot inside the airplane, you're just like, wow, I cannot believe it just did that. Like it'll flop ends which defies most logic and I guess, you know, in a way you could probably program it, but I still think that when you get to the edges that may or may not give you an advantage, um there are things that a human can will do that A I won't and I don't think we've got to the point because how do you how do you map illogical solutions most ai is logical, It's based on some type of premise when you write the algorithm to control it, um there's bounds. </s><s>[INST] Yeah, there's this giant mess, like you said, the difference between the simulator in real life also gets it that somehow that there is uh somehow the fear of death, all of that beautiful mess comes into play. Is there a comment you can make on a commercial flight? Like with sully landing, uh, that plane famously versus the simulator. All of those discussions. Is there some, [/INST] well, it's, it's very, it's very similar to what I was talking about earlier. The A six. So one is when you're flying with a crew, uh, their standardization. So you remember when sully flu, when his first officer, that's the co pilot showed up, you know, first time they met and this happens all the time in the commercial world. You know, there's 6, 7000 pilots at United Airlines, you know, your chance of flying with the same guy all the time is slim and none were in the navy we recruit. So I had a primary and a secondary wiz oh, that flew with me </s><s>[INST] for how, for months? [/INST] Yeah. For like all of the deployment. So because you want, you </s><s>[INST] have to trust all of those things, [/INST] it increases the capability airplane. It's not to say we can't swap out, but for true effectiveness, especially in very complex missions like uh, forward air controller or in the air actually controlling ground assets and supporting ground troops. Um, if you're in a high threat area, which is crazy busy, you have to, you have to be melded when you do that, you have to have trained to do that job. Otherwise you're gonna be ineffective. So when you get to the commercial world and I've got tons of friends that fly commercial, um, there's a standardization. Like we know that at this point I'm gonna put this switch, you're gonna do that and everyone, they know their rules, captain is going to do this first off is going to do this. And they know that when the emergency brakes out. So in sully's case when they take the birds and they know they've got a problem. And if you listen to the cockpit recordings of him, the two of them talking, you know, you gotta remember they're talking to each other when you hear the full tapes, but they're also talking to the air traffic controllers in the new york area and it's like we got a bird strike in the first off. Sorority knows, hey, silence the alarm. They silence the alarm. The first officer is pulling out the book. He's going through the procedures while sully's actually flying the airplane known that they've lost their motors and you've got to think his decision process like they're trying to get him to go into an airport into New Jersey and he realizes not happening. We're going to put this thing and he made a decision soon enough so that he could prepare everyone on the airplane that he was going to put this thing in the Hudson river and he did it flawlessly. I mean every single person walked away from that wreck. The only thing that didn't survive was the airplane, you know, and I got fished out of the Hudson. But um, </s>

<s>[INST] It's so interesting. So, like, to push back the alternatives here. So one about the third person, not to make people self conscious, but I find that I'm so torn on that because sometimes when that person, like, um so Evan is in the room here, he's been in the room before, he's a huge fan of yours, by the way. Uh so he'll he'll nod, yeah, you'll get excited. He's like, and you can see that nodding. And for some reason for me, he's like, yeah, you get like, yeah, you get excited together. I mean, that's that third person can be, like, a really special. So, having an audience uh, when it's a friend or somebody that has that love and that [/INST] it depends on the performer. Yeah. Some people really thrive in front of an audience </s><s>[INST] and you're saying you like that simple intimacy of [/INST] what I would like, the reality of it, not being it, I want it to be as far from a performance as possible. And if if someone, I'll tell you a story, a story that just happened and it was viewed as kind of a it seemed uncool in the moment to the person that had happened to. It wasn't at all. Um we're recording new chili peppers album, which is coming out I think any day now, like, uh I don't know what today's date is, but within the next, maybe by the time this airs it will be out, and the band was playing in the studio and it was ripping because they play their incredible, and one of the members walked through the control room after a particularly great performance and the engineer said, wow, that's all, it was really great, and the person who heard this said, please don't say that and walked away, it's like, it was not, it just changed this feeling of where in this place, where we're doing this thing and there's there is no outside world, you know, we're doing this for us, we're going as deep as we can for us, and as soon as there's an acknowledgement to someone else in a way it breaks the concentration of being inside of it, </s><s>[INST] that's so well told and but it's something about saying, wow, that's always great is shows the reminds you that there's an outside world, But I feel like there's a way to enter the inside world as an audience. So you just have to do that. So it matters what you say. It matters how you look. It matters. So there's like these generic compliments. Not generic but they sound in the way and the outside world would interact as opposed to that creative thing where you're dancing around the fire together or something that [/INST] actually can tell you. There's another interesting one that happened to me and I didn't know this until I saw the film of it, which was A strange one. we were recording with the Avett brothers and um the song was called No Hard feelings and it was this recording of no hard </s><s>[INST] feelings. Mm hmm. [/INST] Okay. When my body won't hold me anymore. And finally that's smith free will. I'll be ready. </s><s>[INST] Such a great voice. [/INST] So beautiful. Kiss goodbye. Well my hands be steady when I lay down. My fears, my hopes and my doubts. The rings are my finger and the keys to my house. With no heart fear when the sun hangs low in the west and the light in my chest won't be careful. Held today any longer. So bright, so hopeful, </s><s>[INST] So lighthearted [/INST] for cash. And and it's just hallelujah and love and all loving the words love and the songs they sing in the church and no. Mhm hearings much good for anyone. Mm hmm What my body wants. Let's be free. Does </s><s>[INST] he sound as good as a [/INST] studio? Yes. Every bit tropical rain Snow. Well, I joined with ocean blue or run into save it and shake hands laughing and walk through the night straight to the light holding the love I've known in my life and no feelings. Mm hmm. Mhm No. What? This is building and building and building. Mm hmm. I have no enemies. I have no, I have no enemy, wow. </s><s>[INST] And he's got the power of like Jeff buckley with more like uh so much more sort of flavor to the voices can go so many different places. It's cool when it's like uh ac apologist mostly him. You could, you could do like hallelujah the Jeff buckley way. I could tell. It's incredible. This is that's that's incredible song. Is this a new record relative [/INST] was, I don't know, four or five years ago or something like that. But what happened with this? That happened? And I mean they're great and it's always good. But that performance in that moment was felt like the sky open. It's unbelievable. </s><s>[INST] This is a single. That [/INST] was just like that was </s><s>[INST] incredible. Yeah. [/INST] So </s><s>[INST] when [/INST] it, when it ended, I said great, what do you want to do next? And they, they said, we just need a few minutes they walked out and that's all I know is like, okay, I'm laying down, wait until they're ready to start again. And in the film, there was a film made of the sessions of this, they went out and they're like, what was that? Like? </s><s>[INST] Like, [/INST] like didn't he get what just happened? Like? Like uh because it was so heavy and </s><s>[INST] yeah, [/INST] it was just as heavy for me and in the spirit of we're here to make the most great stuff we can, we're not gonna like open champagne. Like that's not, it's like, great, What do you want to do next? It's like, let's, let's not revell in this. Let's but they took it as like, this guy just like, doesn't even understand what we're doing, but </s><s>[INST] that's not [/INST] until I saw the </s>

<s>[INST] I like, I mean it is true because somebody that played, I played tennis for many years, I do still think the highest form of excellence in tennis is when the conscious mind is a spectator. So it's the compiled code is the highest form of being human. And then consciousness is just some like specific compiler used to have like borland C plus plus compiler, you could just have different kind of compilers. Ultimately, the thing that by which we measure, um, the power of life, the intelligence of life is the compiled code and you can probably do that compilation all kinds of ways. [/INST] Yeah. I'm not saying that tennis is played consciously and table tennis is, and I'm saying that because tennis is slowed down by the, just the space on the court, you could, you could imagine that it was your conscious mind playing. But when you shrink the court, it was obvious, it becomes obvious that your conscious mind is just present rather than knowing where to put the battle. And weirdly for me, um, I would say this probably isn't true in a podcast situation, but if I have to give a presentation, especially if I have not overly prepared, I often find the same phenomenon when I'm giving the presentation. My conscious mind is there watching some other part of me present, which uh, is a little jarring, I have to say, </s><s>[INST] well, that that means you've, you've gotten good at it. Not let the conscious mind get in the way of the flow of words. [/INST] Yeah, that's, that's the sensation to be sure. </s><s>[INST] And that's the highest form of podcasting too. I mean that's why I have, that's what it looks like when a podcast is really in the pocket, like, like joe Rogan just having fun and just losing themselves. And that's, that's something I aspired to as well, just losing yourself in conversation. Somebody that has a lot of anxiety with people, like I'm such an introvert, I'm scared, I'm scared before you showed up, I'm scared right now. Um, there's just anxiety. There's just, it's a giant mess. Uh, it's hard to lose yourself. It's hard to just get out of the way of your own mind. [/INST] Yeah, actually trust is a big component of that. Your conscious mind retains control if you are very uncertain. But when you do, when you do get into that zone, when you're speaking, I realize it's different for you with english as a second language, although maybe you present in Russian and you know, and it happens. But do you ever hear yourself say something and you think, oh, that's really good, right? Like, like you didn't come up with it. Some other part of you that you don't exactly know came up with it? </s><s>[INST] I don't think I've ever heard myself in that way, because I have a much louder voice that's constantly yelling in my head at why the hell did you say that? There's a very self critical voice that's much louder. So I'm very uh, maybe I need to deal with that voice, but it's been like with what is it called, Like a megaphone just screaming, [/INST] so I can't hear, you know, </s><s>[INST] it's it's a good job, you said that thing really nicely. So I'm kind of focused right now on the megaphone person in the audience versus the the positive, that's that's definitely something to think about. It's been productive. But you know, the place where I find gratitude and beauty and appreciation of life is in the quiet moments when I don't talk, when I listened to the world around me, when I listened to others um when I talk, I'm extremely self critical in my mind when I, when I produce anything out into the world that's, that originated with me, like any kind of creation, extremely self critical, it's good for productivity, for like always striving to improve and so on. It might be bad for for like just appreciating the things you've created. I'm a little bit with Marvin Minsky on this, where he says the key to uh to a productive life is to hate everything you've ever done in the past. [/INST] I didn't know he said that, I must say I resonate with it a bit </s><s>[INST] and [/INST] you know, I unfortunately my life currently has me putting a lot of stuff into the world and I effectively watch almost none of it, I can't stand that. </s><s>[INST] Yeah, what, what do you make of that? I don't know, I just recently just yesterday read um metamorphosis Bykov reread metamorphosis by Kafka where he turns into john bug because of the stress that the world puts on him, his parents put on him to succeed and you know, I think that's you have to find the balance because if you, if you allow the self critical voice to become too heavy the burden of the world, the pressure that the world puts on you to be the best version of yourself and so on to strive, then you become a bug and that's a big problem. And then uh and then uh, and then the world turns against you because you're a bug, you become some kind of caricature of yourself, I don't know, become the worst version of yourself and then thereby end up destroying yourself and then the world moves on. That's the story, that's a lovely story, I [/INST] do think this is one of these places and frankly you could map this onto all of modern human experience, but this is one of these places where our ancestral programming does not serve our modern selves. So I used to talk to students about the question of dwelling on things, you know, dwelling on things is famously understood to be bad and it can't possibly be bad, it wouldn't exist. The tendency toward it wouldn't exist if it was bad. So what is bad is dwelling on things past, the point of utility and you know, that's obviously easier to say than to operationalize, but if you realize that your dwelling is the key in fact to upgrading your program for future well being and that there's a point, you know, presumably from diminishing returns, if not counter productivity, there is a point at which you should stop because that is what is in your best interest than knowing that you're looking for. That point is useful, right? This is the point at which it is no longer useful for me to dwell on this error. I have made, right? That is, that's what you're looking for. And um, it also gives you license, right? If some part of you feels like, you know, is punishing you rather than searching, then that also has a point at which it's no longer valuable and there's some liberty in realizing, yep, even the part of me that was punishing me knows it's time to stop. </s>

<s>[INST] You're looking forward for the, what did he say? Let's make twitter more fun. I'm looking forward to to the fun [/INST] you've talked </s><s>[INST] about. You are at a prestigious university, [/INST] Brown </s><s>[INST] University, Brown University ah [/INST] and </s><s>[INST] you've mentioned that universities might be in trouble. I think it's with Jordan's [/INST] but everywhere </s><s>[INST] else, the barbarians are at the gate or the barbarians at the gate of the university. So, first of all, [/INST] what is </s><s>[INST] to you? Beautiful [/INST] about </s><s>[INST] the idea of the university [/INST] in America </s><s>[INST] of [/INST] academia </s><s>[INST] and what is a threat? [/INST] Well, you know, the university is dedicated to </s><s>[INST] the pursuit of truth [/INST] um and to </s><s>[INST] the education [/INST] and nurturing of young people as they enter into the pursuit of truth, to doing research into </s><s>[INST] teaching in [/INST] a environment </s><s>[INST] of free [/INST] inquiry and civil </s><s>[INST] discourse. [/INST] So, free inquiry means you go wherever </s><s>[INST] the evidence and [/INST] your imagination may lead </s><s>[INST] you and civil [/INST] discourse means that you exchange arguments with people when you don't agree with them on behalf of trying to get to the bottom of things. Um I think the university is a magnificent institution. It is a relatively modern uh institution, I mean, last five </s><s>[INST] 100 years or so. [/INST] I mean there are universities that are older than that, </s><s>[INST] but the [/INST] great research universities of the world. And they're not only here in the United States are places where human ingenuity is nurtured, where new lot knowledge is created. </s><s>[INST] Um and [/INST] where young people are equipped </s><s>[INST] to uh answer [/INST] questions that are open questions about our existence in the world that we live in. You can trace to the university much, if not most, of the advances in technology </s><s>[INST] and resourcefulness [/INST] and our understanding of the origins of the species, of the nature of the universe, cosmology, etcetera, of science, of the </s><s>[INST] pursuit of [/INST] humanistic, understanding, the nurturing of traditions of inquisitive. Also, that's the university barbarians at the Gates. </s><s>[INST] The [/INST] people who are trying to shut down open inquiry at the university on behalf of their particular view about </s><s>[INST] things [/INST] are a threat to what the university stands for and they should be resisted. So </s><s>[INST] if [/INST] I'm enquiring about the nature of human intelligence </s><s>[INST] and [/INST] I want to study differences between human populations and their acquisition of or their expression of cognitive ability. That's fair game. It's an open question if I want to know something about the nature of uh gender affiliation and identity and gender dysphoria and whatnot. That's fair game to study in the university, you can't shut that down. You shouldn't be </s><s>[INST] able to [/INST] by saying, I have a particular position </s><s>[INST] here, I'm a [/INST] member of a particular identity group. </s><s>[INST] Suppose I want to study [/INST] the history </s><s>[INST] of colonialism. [/INST] Uh and there's a narrative on the progressive side, which is colonialism is about Europeans dominating and stealing or whatever, whatever. And I happen to think, well, there's another aspect to the story about colonialism, to which is that it's a mechanism for the diffusion of the best in human civilization to populations that were significantly lagging behind with respect to that. It brought literacy through the southern hemispheric populations that were dominated in the process of the colonizing thing. It's complicated. I'm not taking that position by the way, I'm just saying somebody at a university should be </s><s>[INST] able to [/INST] take it up and pursue it and engage in arguments with people about it. I'm talking about race and ethnicity, but this extends to a wide range of things supposedly talking about climate. And one person says the earth is endangered because carbon in global warming, etcetera. Seven and another person says, no, wait, no, wait, </s><s>[INST] look at where we [/INST] Stand in the 21st century were vastly richer than our ancestors. Just 250 years ago, we have much more knowledge about that and so forth, and so on. 250 years from now, human </s><s>[INST] ingenuity will have [/INST] devised in ways that we cannot even begin to anticipate all manner of technological uh means for managing the problem. There's no reason that we should shut down industrial civilization today, because we fear the consequences of it when in fact we are vastly richer than our ancestors and those who come up two centuries after us will be vastly more effective at </s><s>[INST] dealing with problems than we [/INST] are. Now. Let's it's, you know, etcetera. I'm not actually making that argument, I'm just saying the tendency </s><s>[INST] to try to say, oh [/INST] no, that person is a climate denier. They can't pursue that area of inquiry uh, is against the spirit of the university. I think the barbarians at the gates has to do with the people who think they know what the right side of history is and try to make the university stand on the right side of history. My position is, you don't know what the right side of history </s><s>[INST] is [/INST] and the purpose of a university is to equip you to be able to think about what is the right side of history, What is the solution to the dilemmas that confront us as human beings living on this planet with the billions that we are in the condition that we are. So um, the identitarians, the ones who want to make the university called </s><s>[INST] tao [/INST] to their particular understandings about their own identity. Um, we now have </s><s>[INST] at the at [/INST] Brown University and various other places. We don't do columbus day anymore. We do indigenous peoples day when that day comes up in </s><s>[INST] october, we [/INST] don't talk about columbus, they're taking down statues of columbus all across the country and so forth and so on. I'm not arguing anything here other than that, the latter day position um </s><s>[INST] by [/INST] parks black indigenous and other people of cover the latter day position that the university has to reflect a particular sensibility about these identity </s><s>[INST] questions. [/INST] I think it's a threat to the integrity of the enterprise. </s>

<s>[INST] 90s. That's just like a critical piece of this. Yeah, it has to be stable and, you know, materialize into something stable over years, over years. Yes. Another difficult conflict going on in the world is the war in Ukraine. What do you think about the Russian invasion of Ukraine in February [/INST] 2022? I don't pretend to be an expert on this issue. I think you probably know more about this than I do just from the brief conversation we had before we started filming my view as a general observer of geopolitics and the way that this area, this part of the world is related to American presidents over the last several, you know, cycles is I don't think it's controversial to say that this was a war of aggression, an invasion of aggression, an act of aggression by Vladimir Putin. I do believe that if Trump had been reelected, Putin may have seen himself as having other tools with which to try to expand influence that may have been different than geographical pursuits, geographic pursuits. But we don't know that for sure. I also have a really hard time imagining what the end of this looks like. And that's very scary because sometimes the most benign end seems to be that Putin ends up out of power, either through no longer being alive or deposed in some way. It doesn't feel like that latter is super likely the former. There's reports about his health. I don't know how accurate they are. It's just hard to imagine a face saving exit that is going to be even remotely. What's the word? It's not even a question of acceptable. Just it's not satisfying either. Just not tragic, I guess is what I'm </s><s>[INST] looking for. In terms of Putin speaking to the Russian people and being able to figure out what to say, what kind of narrative to say why this war made sense. Yes. The same on the Ukrainian [/INST] side to figure out how to exit this war. Yes. I mean, to some degree, it requires Russian troops leaving Ukraine. And that is somewhat under the control. I mean, of course, it's not up to Ukraine whether the initiative continues. But what I am not thrilled with are some of the reflexive. You know, if Trump had been in power instead of Joe Biden, a lot of the reflexive comments about, oh, you're if you if you say Ukraine is just acting defensively, you're supporting neo Nazis or some of these things that have come out of the American Republican Party seem both wacky and like they would be saying completely different things. If Trump happened to be in the Oval Office, they're really proxy attacks on Joe Biden. </s><s>[INST] Yeah. Well, that in some sense, Ukraine is also kind of political litmus test of how you speak about it, I think, because of the huge amount of funding that's going from US to Ukraine. Maybe you can correct me if I'm wrong. But it seems to it seems to me that [/INST] this topic has become politicized already. A hundred percent. There are people like Marjorie Taylor Green and others saying we should be doing nothing for Ukraine. Zelensky is a comedian and we're supporting neo Nazis. That's it. Full stop. And you either subscribe to that or you don't. And it very quickly becomes it very quickly becomes as partisan as so many other issues. And it's really the most disappointing thing is that some of these issues become incredibly divisive, divisive, but they're simple. Like, for example, a conspiracy theory that we know isn't true. It shouldn't be devices divisive because it's so simple. Other issues become divisive and they are simplified. But in reality, they are extraordinarily complex and you lose the </s><s>[INST] ability to talk about the complexity because they're becoming partisan. Do you think there will always be war in the world as a bunch of folks in the subreddit that were interested in your different complex perspectives on foreign policy? So let's talk about war. When you look at the war in Ukraine, you look at what's going on in Israel and Palestine, you look at the wars across the world. Do you think there will always be war? As the Redditor put it, is it a necessary [/INST] evil in the game of geopolitics? I used to have what I now believe is an extremely naive perspective, which is that if we somehow if intelligent aliens arrived here, it would be so momentous for Homo sapiens that all of our differences would immediately be exposed to so insignificant. We would never fight again and we would realize that intelligent life. And then I spoke to people who deal in space exploration and other other scientists and they all said that David, that's extraordinarily naive. There would be a period during which this was as momentous as you're imagining and then it would become normal. And then we would go back to many of the same conflicts that we have now, sectarian, et cetera. I think that in all likelihood, there will always be conflict between factions, whether it's what we currently think of as war, probably not. I mean, it seems as though the tactics will evolve and it will be less about missiles and I don't know where it's going to go. I don't know whether it's going to become more biological or cyber or certainly something we haven't even considered yet. But I think there will always be conflicts we would </s><s>[INST] refer to in that way. Do you agree with Chomsky on his general harsh criticism of U.S. foreign policy in war that many actions, military actions in the United States are criminal in nature, [/INST] almost terrorist in nature? I am not, it's been a decade or more since I've read any Chomsky and I don't keep up with everything that he has recently said. So I don't want to </s>

<s>[INST] Well yeah, how many pixels are we talking about? Like what you mentioned phones, there's a bunch of megapixels I think. [/INST] So for exoplanets you want to think about is like a pixel or less than a pixel. We're not getting any information but to be more technical, our telescope spreads the light out over many pixels, but we're not getting information, we're not tiling the planet with pixels, it's just like a point of light or in most cases we don't even see the planet itself, just the planet's effect on the star. But another thing that really helped was computers because transiting planets are actually quite rare. I mean they don't all go in front of their star and so to find transiting planets, we look at a big part of the sky at once or we look at tens of thousands or hundreds of thousands or even in some cases millions of stars at one time. And so, you know, you're not going to do this by hand going through a million stars counting up the brightness. So we have computer software and computer code that does the job for us and looks for a counts the brightness and looks for a signal that could be due to a transiting planet. And I just finished a job called deputy science director for the MIT led Nasa mission test. And it was my purview to make sure that we got the planet candidates. The transiting light curves out to the community so people could follow them up and figure out if their actual planets or false positives. </s><s>[INST] So publish the data so that people could just [/INST] uh published data. </s><s>[INST] All the all the data scientists out there could crunch and see if they can exactly [/INST] they can discover something. And in fact the Nasa policy for this mission is that all the data becomes public as soon as possible. So anyone could act. It's not as easy as it sounds though to download the data and look for planets. But there is a group called Planet Hunters dot org and they take the data and they actually crowd source it out to people to look for planets and they often find find signals that our computers and our team missed. </s><s>[INST] So we mentioned exoplanets. What about earth like or I don't know what the right distinction is it? Is it habitable or is it earth like planets? But what are those different categories? And how can we tell the difference and detect [/INST] each? Right. Right. So we're not at Earth like planets yet. All the planets we're finding are so different from what we have in our solar system. They're just easier planets to find. But in which way for example there could be a jupiter sized planet where on earth should be, we find planets that are the same size as earth but our orbiting way closer to their star than mercury is to our sun. And they're so close that because close to a star means they also orbit faster and some of these hot super earths we call them, they're year, their time to go around, their star is less than a day and they're heated so much by their star, their heated so much by the star. We think the surface is hot enough to melt rock. So instead of running out by the bay or the river, you'll have like liquid lava, there'll be liquid lava lakes on these planets we think </s><s>[INST] and life can't [/INST] survive way too hot. The molecules for life would just be molecules needed for life. Just wouldn't wouldn't be able to survive those temperatures. We have some other planets. one of the most mysterious things out there factoid if you will is that the most common type of planet we know about so far is a planet that's In between Earth and Neptune size. It's 2-3 times the size of earth and we have no solar system counterpart of that planet that is like going outside to the forests and finding some kind of creature or animal that just no one has ever seen before and then discovering that is the most common thing out there. Uh huh And so we're not even sure what they are. We have a lot of thoughts as to the different types of planet it could be but people don't really know, </s><s>[INST] I mean what are your thoughts about what it could be? [/INST] Well, one thought and this is more when we want to be rather than might be. Is that these so called mini neptunes, we call them that they are water worlds that they could be scaled up versions of jupiter's icy moons such that there are planets that are made of more than half of water by mass. </s><s>[INST] So yeah. And what's the connection between water and life and the possibility of seeing that from a gas perspective. [/INST] Okay, so all life on earth needs liquid water. And so there's been this idea in astronomy or astro Biology for a long time called follow the water. Find water that will give you a chance of finding life. But we could still zoom out and the kind of, the community consensus is that we need some kind of liquid for life to originate and to survive because molecules have to react. You don't have a way that molecules can interact with each other. You can't really make anything. And so when we think of all the liquids out there, water is the most abundant liquid in terms of planetary materials. There really aren't that many liquids, Like I mentioned, liquid rock way too hot for life, we have some really cold liquids, like almost gasoline, like ethane and methane lakes that have been found on one of Saturn's moons titan. That's so cold though. And for exoplanets, we can't study really cold planets because they're just simply too dark and too cold. So we usually, so we usually just left with looking for planets with liquid water. And to your point is remember as we talked about how planets are less than a pixel in that way to say. So we can't see oceans on the planet. We're going to see continents and oceans. Not yet anyway, but we can see gasses in the atmosphere. And if it's a small rocky planet and this is going into some more detail, it's a small, if we see a small rocky planet with water vapor in the atmosphere, we're pretty sure that means there has to be a liquid water reservoir because it's not intuitive in any way, but water is broken up by ultraviolet radiation from the star or from the sun and on most planets when water is broken up into HN oh, the h the hydrogen will escape to space because just like when you think of a child letting go of a helium filled balloon floats upwards and hydrogen to light gas and we'll leave from Earth's leave from the planet. So ultimately, if you have water, unless there's an ocean, like a way to keep replenishing water vapor in the atmosphere, that water vapor should be destroyed by ultraviolet radiation. </s>

<s>[INST] This is the Lex Freedom podcast, and here is my conversation with Daniel Schmachtenberger. If aliens were observing Earth through the entire history just watching us, and we're tasked with summarizing what happened until now, what do you think they would say? What do you think they would write up in that summary? Like, it has to be pretty short, less than a page. Like, in Schmachtenberger's guide, there's, I think, like a paragraph or a couple sentences. How would you summarize, sorry, how would the aliens summarize, do you think, all of human civilization? [/INST] Well, my first thoughts take more than a page. They'd probably distill it, because if they watched, well, I mean, first, I have no idea if their senses are even attuned to similar stuff to what our senses are attuned to, or what the nature of their consciousness is like relative to ours, and so let's assume that they're kind of like us, just technologically more advanced to get here from wherever they are. That's the first kind of constraint on the thought experiment. And then if they've watched throughout all of history, they saw the burning of Alexandria. They saw that 2,000 years ago, in Greece, we were producing things like clocks, the anti-Catheria mechanism, and then that technology got lost. They saw that there wasn't just a steady dialectic </s><s>[INST] of progress. So every once in a while, there's a giant fire that destroys a lot of things. There's a giant, like, commotion that destroys a lot of things. [/INST] Yeah, and it's usually, yeah, and it's usually self-induced. They would have seen that. And so as they're looking at us now, as we move past the nuclear weapons age into the full globalization, anthropocene, exponential tech age, still making our decisions relatively similarly to how we did in the Stone Age as far as rivalry game theory type stuff, I think they would think that this is probably most likely one of the planets that is not gonna make it to being intergalactic because we blow ourselves up in the technological adolescence. And if we are going to, we're gonna need some major progress rapidly in the social technologies that can guide and bind and direct the physical technologies so that we are safe vessels </s><s>[INST] for the amount of power we're getting. Actually, Hitchhiker's Guide has an estimation about how much of a risk this particular thing poses to the rest of the galaxy. And I think, I forget what it was. I think it was medium or low. So their estimation would be that this species of ant-like creatures is not gonna survive long. There's ups and downs in terms of technological innovation. The fundamental nature of their behavior from a game theory perspective hasn't really changed. They have not learned in any fundamental way how to control and properly incentivize or properly do the mechanism design of games to ensure long-term survival and then they move on to another planet. Do you think there is, in a slightly more serious question, do you think there's some number or perhaps a very, very large number [/INST] of intelligent alien civilizations out there? Yes, would be hard to think otherwise. I know, I think Postrum had a new article not that long ago on why that might not be the case, that the Drake equation might not be the kind of end story on it. But when I look at the total number of Kepler planets just that we're aware of just galactically and also like when that, when those life forms were discovered in mono-like that didn't have the same six primary atoms that I think it had arsenic replacing phosphorus as one of the primary aspects of its energy metabolism, we get to think about that the building blocks might be more different. So the physical constraints, even that the planets have to have might be more different. It seems really unlikely, not to mention interesting things that we've observed that are still unexplained as you had guests </s><s>[INST] on your show discussing tic-tac. Oh, the ones that have visited. Well, let's dive right into that. What do you make sense of the rich human psychology of there being hundreds of thousands, probably millions of witnesses of UFOs of different kinds on earth, most of which I presume are conjured up by the human mind through the perception system. Some number might be true. Some number might be reflective of actual physical objects, whether it's drones or testing military technology that's secret or otherworldly technology. What do you make sense of all of that? Because it's gained quite a bit of popularity recently. There's some sense in which that's us humans being hopeful and dreaming of otherworldly creatures as a way to escape the jurorness of the human condition. But in another sense, it really could be something truly exciting that science should turn its eye towards. So where do you place it? [/INST] Speaking of turning eye towards, this is one of those super fascinating, actually super consequential, possibly, topics that I wish I had more time to study and just haven't allocated. So I don't have firm beliefs on this because I haven't got to study it as much as I want. So what I'm gonna say comes from a superficial assessment. While we know there are plenty of things that people thought of as UFO sightings that we can fully write off, we have other better explanations for them. What we're interested in is the ones that we don't have better explanations for, and then not just immediately jumping to a theory of what it is, but holding it as unidentified and being curious and earnest. I think the tic-tac one is quite interesting and made it in major media recently. But I don't know if you ever saw the Disclosure Project, a guy named Stephen Greer organized a bunch of mostly US military and some commercial flight, people who had direct observation and classified information, disclosing it at a CNN briefing. And so you saw high ranking generals, admirals, fighter pilots, all describing things that they saw on radar with visual, with their own eyes or cameras, and also describing some phenomena that had some consistency across different people. And I find this interesting enough that I think it would be silly to just dismiss it. And specifically, we can ask the question, how much of it is natural phenomena, ball lightning or something like that? And this is why I'm more interested in what fighter pilots and astronauts and people who are trained in being able to identify flying objects and atmospheric phenomena have to say about it. I think the thing, then you could say, well, are they more advanced military craft? Or is it some kind of human craft? The interesting thing that a number of them describe is something that's kind of like right angles at speed, or if not right angles, acute angles at speed, but something that looks like a different relationship to inertia than physics makes sense for us. I don't think that there are any human technologies that are doing that even in really deep underground black projects. Now one could say, okay, well, could it be a hologram? What would it show up on radar if radar is also seeing it? And so I don't know, I think there's enough. I mean, and for that to be a massive coordinated SIOP is as interesting and ridiculous in a way as the idea that it UFOs from some extra planetary source. </s><s>[INST] So it's up there on the interesting topics. To me, if it is at all alien technology, it is the dumbest version of alien technology. It's so far away, it's like the old, old crappy VHS tapes of alien technology. These are like crappy drones that just floated or even like spaced to the level of like space junk, because it is so close to our human technology. We talk about it moves in ways that's unlike what we understand about physics, but it still has very similar kind of geometric notions and something that we humans can perceive with our eyes, all those kinds of things. I feel like alien technology most likely would be something that we would not be able to perceive, not because they're hiding, but because it's so far advanced that it would be much, it would be beyond the cognitive capabilities of us humans. Just as you were saying as per your answer for alien summarizing earth, it's the starting assumption is they have similar perception systems. They have similar cognitive capabilities and that very well may not be the case. Let me ask you about staying in aliens for just a little longer, because I think it's a good transition in talking about governments and human societies. Do you think if a US government or any government was in possession of an alien spacecraft or of information related to alien spacecraft, they would have the capacity structurally would they have the processes, would they be able to communicate that to the public effectively or would they keep it secret in a room and do nothing with it, both to try to preserve military secrets, but also because of the incompetence [/INST] that's inherent to bureaucracies or either. Well, we can certainly see when certain things become declassified 25 or 50 years later, that there were things that the public might have wanted to know that were kept secret for a very long time for reasons of at least supposedly national security, which is also a nice source of plausible deniability for people covering their ass for doing things that would be problematic and other purposes. There's a scientist at Stanford who supposedly got some material that was recovered from Area 51 type area and did analysis on it using, I believe, electron microscopy and a couple other methods and came to the idea that it was a nanotech alloy that was something we didn't currently have the ability to do was not naturally occurring. So I've heard some things and again, like I said, I'm not gonna stand behind any of these because I haven't done the level of study to have high confidence. I think what you said also about would it be super low tech alien craft? Like would they necessarily move their atoms around in space or might they do something more interesting than that? Might they be able to have a different relationship to the concept of space or information or consciousness or one of the things that the craft supposedly do is not only accelerate and turn in a way that looks non-inertial, but also disappear. So there's a question as to, like the two are not necessarily mutually exclusive and it could be possible to, some people run a hypothesis that they create intentional amounts of exposure as an invitation of a particular kind. </s><s>[INST] Who knows, interesting field. We tend to assume like SETI, that's listening out for aliens out there. I've just been recently reading more and more about gravitational waves and you have orbiting black holes that orbit each other. They generate ripples in space time on my, for fun at night when I lay in bed, I think about what it would be like to ride those waves when they, not the low magnitude they are as when they reach earth, but get closer to the black holes because it would basically be shrinking and expanding us in all dimensions, including time. So it's actually ripples through space time that they generate. Why is it that you couldn't use that? It travels with speed of light, travels with a very weird thing to say when you're morphing space time. It's, you could argue it's faster than the speed of light. So if you're able to communicate by, to summon enough energy to generate black holes and to orbit the, to force them to orbit each other, why not travel as the ripples in space time? Whatever the hell that means. Somehow combined with wormholes. So if you're able to communicate through, like we don't think of gravitational waves as something you can communicate with because the radio will be, have to be a very large size and very dense, but perhaps that's it. You know, perhaps that's one way to communicate. It's a very effective way. And that would explain, like we wouldn't even be able to make sense of that, of the physics that results in an alien species [/INST] that's able to control gravity at that scale. I think you just jumped up the Kardashev scale so far. So you're not just harnessing the power of a star, but harnessing the power of mutually rotating black holes. That's way above my physics pay grade to think about including even non-rotating black hole versions of transwarp travel. I think, you know, you can talk with Eric more about that. I think he has better ideas on it than I do. My hope for the future of humanity mostly does not rest in the near term on our ability to get to other habitable planets in time. </s><s>[INST] And even more than that, in the list of possible solutions of how to improve human civilization, orbiting black holes is not on the first page for you. It's not on the first page. Okay, I bet you did not expect us to start this conversation here, but I'm glad the places it went. I am excited on a much smaller scale of Mars, Europa, Titan, Venus, potentially having very bacteria-like life forms. Just on a small human level, it's a little bit scary, but mostly really exciting that there might be life elsewhere in the volcanoes, in the oceans, all around us, teeming, having little societies. And whether there's properties about that kind of life that's somehow different than ours. I don't know what would be more exciting if those colonies of single cell type organisms, what would be more exciting if they're different or they're the same? If they're the same, that means through the rest of the universe, there's life forms like us, something like us everywhere. If they're different, that's also really exciting because there is life forms everywhere. they're not like us. That's a little bit scary. I don't know what's scarier actually. It's both scary and exciting no matter what, right? [/INST] The idea that they could be very different is philosophically very interesting for us to open our aperture on what life and consciousness and self-replicating possibilities could look like. The question on are they different or the same, obviously there's lots of life here that is the same in some ways and different in other ways. When you take the thing that we call an invasive species is something that's still pretty the same hydrocarbon-based thing, but co-evolved with co-selective pressures in a certain environment. We move it to another environment. It might be devastating to that whole ecosystem because it's just different enough that it messes up the self-stabilizing dynamics of that ecosystem. The question of would they be different in ways where we could still figure out a way to inhabit a biosphere together or fundamentally not? Fundamentally, the nature of how they operate and the nature of how we operate would be incommensurable is a deep question. </s><s>[INST] Well, we offline talked about mimetic theory, right? It seems like if they were sufficiently different where we would not even, we can coexist on different planes, it seems like a good thing. If we're close enough together to where we'd be competing, then you're getting into the world of viruses and pathogens and all those kinds of things to where one of us would die off quickly [/INST] through basically mass murder without even- Even accidentally. Even accidentally. If we just had a self-replicating single-celled kind of creature that happened to not work well for the hydrocarbon life that was here that got introduced because it either output something that was toxic or utilized up the same resource too quickly and it just replicated faster and mutated faster. It wouldn't be a mimetic theory, conflict theory kind of harm. It would just be a von Neumann machine, a self-replicating machine that was fundamentally incompatible with these kinds of self-replicating systems with faster </s><s>[INST] OODA loops. For one final time, putting your alien flash God hat on and you look at human civilization, do you think about the 7.8 billion people on earth as individual little creatures, individual little organisms, or do you think of us as one organism with a collective intelligence? [/INST] What's the proper framework through which to analyze it again as an alien? So that I know where you're coming from, would you have asked the question the same way before the Industrial Revolution or before the agricultural revolution when there were half a billion people and no telecommunications connecting them. </s><s>[INST] I would indeed ask the question the same way, but I would be less confident about your conclusions. It would be an actually more interesting [/INST] way to ask the question at that time. But I was nevertheless asked it the same way, yes. Well let's go back further and smaller then. Rather than just a single human or the entire human species, let's look at in a relatively isolated tribe. In the relatively isolated probably sub Dunbar number sub kind of 150 people tribe, do I look at that as one entity where evolution is selecting for based on group selection or do I think of it as 150 individuals that are interacting in some way? Well, could those individuals exist without the group? No, the evolutionary adaptiveness of humans was involved critically group selection and individual humans alone trying to figure out stone tools and protection and whatever aren't what was selected for. And so I think the or is the wrong frame. I think it's individuals are affecting the group that they're a part of, they're also dependent upon and being affected by the group that they're part of. And so this now starts to get deep into political theories also which is theories that oriented towards the collective at different scales, whether a tribal scale or an empire or nation state or something and ones that orient towards the individual liberalism and stuff like that. And I think there's very obvious failure modes on both sides and so the relationship between them is more interesting to me than either of them the relationship between the individual in the collective and the question around how to have a virtuous process between those. So a good social system would be one where the organism of the individual and the organism of the group of individuals is they're both synergistic to each other. So what is best for the individuals and what's best for the whole is aligned. </s><s>[INST] But there is nevertheless an individual. They're not, it's a matter of degrees, I suppose. But what defines a human more? The social network within which they've been brought up, through which they've developed their intelligence, or is it their own sovereign individual self? What's your intuition of how much, not just for evolutionary survival, [/INST] but as intellectual beings, how much do we need others for our development? Yeah. I think we have a weird sense of this today relative to most previous periods of sapien history. I think the vast majority of sapien history is tribal, like depending upon your early human model, two or three hundred thousand years of homo sapiens in little tribes, where they depended upon that tribe for survival and excommunication from the tribe was fatal. And our whole evolutionary genetic history is in that environment. And the amount of time we've been out of it is relatively so tiny. And then we still depended upon extended families and local communities more. And the big kind of giant market complex where I can provide something to the market to get money, to be able to get other things from the market, where it seems like I don't need anyone. It's almost like disintermediating our sense of need, even though your and my ability to talk to each other using these mics and the phones that we coordinated on took millions of people over six continents to be able to run the supply chains. It made all the stuff that we depend on, but we don't notice that we depend upon them. They all seem fungible. If you take a baby, obviously that you didn't even get to a baby without a mom. Was it dependent? Are we dependent upon each other without two parents at minimum? And they depended upon other people. But if we take that baby and we put it out in the wild, it obviously dies. So if we let it grow up for a little while, the minimum amount of time where it starts to have some autonomy, and then we put it out in the wild, and this has happened a few times. It doesn't learn language and it doesn't learn the small motor articulation that we learn. It doesn't learn the type of consciousness that we end up having that is socialized. So I think we take for granted how much conditioning affects us. </s><s>[INST] Is it possible that it affects basically 99.9 or maybe the whole thing? The whole thing is the connection between us humans and that we're no better than apes without our human connections. Because thinking of it that way forces us to think very differently about human society and how to progress forward if the connections are fundamental. [/INST] I just have to object to the no better than apes because better here I think you mean a specific thing which means have capacities that are fundamentally different than I think apes also depend upon troops. And I think the idea of humans as better than nature in some kind of ethical sense ends up having heaps of problems we'll table that we can come back to it. But when we say what is unique about homo sapien capacity relative to the other animals we currently inhabit the biosphere with and I'm saying it that way because there were other early hominids that had some of these capacities we believe. Our tool creation and our language creation and our coordination are all kind of the results of a certain type of capacity for abstraction. And other animals will use tools but they don't evolve the tools they use. They keep using the same types of tools that they basically can find. So a chimp will notice that a rock can cut a vine that it wants to and it'll even notice that a sharper rock will cut it better. And experientially it'll use the sharper rock and if you even give it a knife it'll probably use the knife because it's experiencing the effectiveness. But it doesn't make stone tools because that requires understanding why one is sharper than the other. What is the abstract principle called sharpness to then be able to invent a sharper thing. That same abstraction makes language. The ability for abstract representation makes the ability to coordinate in a more advanced set of ways. I do think our ability to coordinate with each other is pretty fundamental </s><s>[INST] to the selection of what we are as a species. I wonder if that coordination, that connection is actually the thing that gives birth to consciousness. That gives birth to, or let's start with self-awareness. It's more like theory of mind. Theory of mind, yeah. You know, I suppose there's experiments that show that there's other mammals that have a very crude theory of mind. I'm not sure, maybe dogs, something like that. But actually, dogs probably has to do with it. They co-evolved with humans. See, it'd be interesting if that theory of mind is what leads to consciousness in the way we think about it. Is the richness of the subjective experience that is consciousness? I have an inkling sense that that only exists because we're social creatures. That doesn't come with the hardware and the software in the beginning. That's like, that's learned as an effective tool for communication almost. Like, I think we think that consciousness is fundamental. And maybe it's not. There's a bunch of folks kind of criticize the idea that the illusion of consciousness is consciousness, that it is just a facade we use to help us construct theories of mind. You almost put yourself in the world as a subjective being. In that experience, you want to richly experience it as an individual person so that I could empathize with your experience. I find that notion compelling, mostly because it allows you to then create robots that become conscious not by being quote, unquote conscious, but by just learning to fake it till they make it. Is a creative, present a facade of consciousness and with the task of making that facade very convincing to us humans and thereby it will become conscious. I have a sense that in some way that will make them conscious if they're sufficiently convincing to humans. Is there some element of that that you find convincing? [/INST] This is a much harder set of questions and deep end of the pool than starting with the aliens was. </s><s>[INST] We went from aliens to consciousness. This is not the trajectory I was expecting nor you, [/INST] but let us walk a while. We can walk a while and I don't think we will do it justice. So what do we mean by consciousness versus conscious self-reflective awareness? What do we mean by awareness, qualia, theory of mind? There's a lot of terms that we think of as slightly different things and what do we mean by subjectivity first person? I don't remember exactly the quote, but I remember when reading, when Sam Harris wrote the book Free Will and then Dennett critiqued it. And then there was some writing back and forth between the two because normally they're on the same side of kind of arguing for critical thinking and logical fallacies and philosophy of science against supernatural ideas. And here Dennett believed there is something like free will. He is a determinist, compatibilist, but no consciousness and radical limitivist. And Sam was saying, no, there is consciousness, but there's no free will. And that's like the most fundamental kinds of axiomatic senses they disagreed on but neither of them could say it was because the other one didn't understand the philosophy of science or logical fallacies. And they kind of spoke past each other. And at the end, if I remember correctly, Sam said something that I thought was quite insightful, which was to the effect of it seems it, because they weren't making any progress in shared understanding. It seems that we simply have different intuitions about this. And what you could see was that what the words meant, right at the level of symbol grounding might be quite different. One of them might've had deeply different enough life experiences that what is being referenced. And then also different associations of what the words mean. This is why when trying to address these things, Charles Sanders Perce said the first philosophy has to be semiotics. Because if you don't get semiotics right, we end up importing different ideas and bad ideas right into the nature of the language that we're using. And then it's very hard to do epistemology or ontology together. So I'm saying this to say why I don't think we're gonna get very far is I think we would have to go very slowly in terms of defining what we mean by words </s><s>[INST] and fundamental concepts. Well, and also allowing our minds to drift together for a time so that our definitions of these terms align. I think there's a beauty that some people enjoy with Sam that he is quite stubborn on his definitions of terms without often clearly revealing that definition. So in his mind, he can like you could sense that he can deeply understand what he means exactly by a term like free will and consciousness. And you're right, he's very specific in fascinating ways that not only does he think that free will is an illusion, he thinks he's able, not thinks, he says he's able to just remove himself from the experience of free will and just be like for minutes at a time, hours at a time, like really experience as if he has no free will. Like he's a leaf flowing down the river. And given that he's very sure that consciousness is fundamental. So here's this conscious leaf that's subjectively experiencing the floating and yet there's no ability to control and make any decisions for itself. It's only the decisions have all been made. There's some aspect to which the terminology there perhaps [/INST] is the problem. So that's a particular kind of meditative experience and the people in the Vedantic tradition and some of the Buddhist traditions thousands of years ago described similar experiences and somewhat similar conclusions, some slightly different. There are other types of phenomenal experience that are the phenomenal experience of pure agency. And, you know, like the Catholic theologian but evolutionary theorist Thierry de Chardin describes this and that rather than a creator agent God in the beginning, there's a creative impulse or a creative process. And he would go into a type of meditation that identified as the pure essence of that kind of creative process. And I think the types of experience we've had and then one, the types of experience we've had make a big deal to the nature of how we do symbol grounding. The other thing is the types of experiences we have can't not be interpreted through our existing interpretive frames. And most of the time our interpretive frames are unknown even to us, some of them. And so this is a tricky topic. So I guess there's a bunch of directions we could go with it but I wanna come back to what the impulse was which was interesting around what is consciousness and how does it relate to us as social beings and how does it relate to the possibility of consciousness with it, AIs. </s><s>[INST] Right, you're keeping us on track, which is wonderful. You're a wonderful hiking partner. Okay, yes, let's go back to the initial impulse of what is consciousness and how does the social impulse connect to consciousness. Is consciousness a consequence [/INST] of that social connection? I'm gonna state a position not argue it because it's honestly like it's a long hard thing to argue and we can totally do it another time if you want. I don't subscribe to consciousness as an emergent property of biology or neural networks. Obviously, a lot of people do. Obviously, the philosophy of science orients towards that in not absolutely but largely. I think of the nature of first person, the universe of first person of qualia as experience, sensation, desire, emotion, phenomenology, but the felt sense, not the we say emotion and we think of a neurochemical pattern or an endocrine pattern, but all of the physical stuff, the third person stuff has position and momentum and charge and stuff like that that is measurable, repeatable. I think of the nature of first person and third person as ontologically orthogonal to each other, not reducible to each other. They're different kinds of stuff. And so I think about the evolution of third person that we're quite used to thinking about from subatomic particles to atoms to molecules to on and on. I think about a similar kind of in corresponding evolution in the domain of first person from the way Whitehead talked about kind of prehenchant or proto qualia in earlier phases of self-organization into higher orders of it, and that there's correspondence. But that neither like the idealists do we reduce third person to first person, which is what idealists do. Or neither like the physicalists, or do we reduce first person to third person? Obviously, Baum talked about an implicate order that was deeper than and gave rise to the explicate order of both. Nagel talks about something like that. I have a slightly different sense of that, but again, I'll just kind of not argue how that occurs for a moment. So rather than say, does consciousness emerge from? I'll talk about do higher capacities of consciousness emerge in relationship with? So it's not first person as a category emerging from third person, but increased complexity within the nature of first person and third person co-evolving. Do I think that it seems relatively likely that more advanced neural networks have deeper phenomenology, more complex, where it goes just from basic sensation to emotion to social awareness to abstract cognition to self-reflexive abstract cognition? Yeah. But I wouldn't say that's the emergence of consciousness. I would say it's increased complexity within the domain of first person corresponding to increased complexity. And the correspondence should not automatically be seen as causal. We can get into the arguments for why that often is the case. So would I say that, obviously, the sapien brain is pretty unique. And a single sapien now has that, right? Even if it took sapiens evolving in tribes based on group selection to make that brain. So the group made it now that brain is there. Now, if I take a single person with that brain out of the group and try to raise them in a box, they'll still not be very interesting, even with the brain. But the brain does give hardware capacities that, if conditioned in relationship, can have interesting things emerge. So do I think that the human biology, types of human consciousness, and types of social interaction all co-emerged and co-evolved? </s><s>[INST] Yes. As a small aside, as you're talking about the biology, let me comment that I spent, this is what I do. This is what I do with my life. This is why I will never accomplish anything, is I spent much of the morning trying to do research on how many computations the brain performs and how much energy it uses versus the state-of-the-art CPUs and GPUs arriving at about 20 quadrillion. So that's due to the 16 computations, so synaptic firings per second that the brain does. And that's about a million times faster than the, let's say, the 20-thread state-of-the-art Intel CPU, the 10th generation. And then there's similar calculation for the GPU. And all ended up also trying to compute that it takes 10 watts to run the brain about. And then what does that mean in terms of calories per day, kilocalories? That's about 250, for an average human brain, that's 250 to 300 calories a day. And so it ended up being a calculation where you're doing about 20 quadrillion calculations that are fueled by something like, depending on your diet, three bananas. So three bananas results in a computation that's about a million times more powerful than the current [/INST] state-of-the-art computers. Now let's take that one step further. There's some assumptions built in there. The assumption is that, one, what the brain is doing is just computation. Two, the relevant computations are synaptic firings, and that there's nothing other than synaptic firings that we have to factor. So I'm forgetting his name right now. There's a very famous neuroscientist at Stanford just passed away recently who did a lot of the pioneering work on glial cells and showed that his assessment, glial cells did a huge amount of the thinking, not just neurons. And it opened up this entirely different field of what the brain is and what consciousness is. You look at Damasio's work on embodied cognition and how much of what we would consider consciousness or feeling is happening outside of the nervous system completely, happening in endocrine process involving lots of other cells and signal communication. You talk to somebody like Penrose who you've had on the show. And even though the Penrose-Hamerhoff conjecture is probably not right, is there something like that that might be the case where we're actually having to look at stuff happening at the level of quantum computation of microtubules? I'm not arguing for any of those. I'm arguing that we don't know how big </s><s>[INST] the unknown unknowns that is. Well, at the very least, this has become like an infomercial for the human brain. But wait, there's more. At the very least, the three bananas buys a million times at the very least. That's impressive. And then the synaptic firings we're referring to is strictly the electrical signals. They could be the mechanical transmission of information There's chemical transmission of information. There's all kinds of other stuff going on. There's memory that's built in. That's also all tied in. Not to mention, which I'm learning more and more about, it's not just about the neurons. It's also about the immune system that's somehow helping with the computations. So the entirety and the entire body is helping with the computations. So three bananas. It could buy you a lot. It could buy you a lot. [/INST] But on the topic of sort of the very least, </s><s>[INST] and then greater degrees of complexity emerging in consciousness, I think few things are as beautiful and inspiring as taking a step outside of the human brain, just looking at systems or simple rules create incredible complexity, not create incredible complexity emerges. So one of the simplest things to do that with is a cellular automata. And there's, I don't know what it is, and maybe you can speak to it. We can certainly, we will certainly talk about the implications of this, but there's so few things that are as awe-inspiring to me as knowing the rules of a system and not being able to predict what the heck it looks like. And it creates incredibly beautiful complexity that when zoomed out on, looks like there's actual organisms doing things that operate on a scale much higher than the underlying mechanism. So a cellular automata that's cells that are born and die, born or die, and they only know about each other's neighbors. And there's simple rules that govern that interaction of birth and death. And then they create, at scale, organisms that look like they take up hundreds or thousands of cells and they're moving. They're moving around, they're communicating, they're sending signals to each other. And you forget at moments at a time before you remember that the simple rules on cells is all that it took to create that. It's sad in that we can't come up with a simple description of that system that generalizes the behavior of the large organisms. We can only come up, we can only hope to come up with the thing, the fundamental physics or the fundamental rules of that system, I suppose. It's sad that we can't predict. Everything we know about the mathematics of those systems, it seems like we can't really in a nice way, like economics tries to do, to predict how this whole thing will unroll. But it's beautiful because of how simple it is underneath it all. So what do you make of the emergence of complexity from simple rules? [/INST] What the hell is that about? Yeah, well, we can see that something like flocking behavior, the murmuration can be computer coded. It's not a very hard set of rules to be able to see some of those really amazing types of complexity. And the whole field of complexity science and some of the sub-disciplines like stigmurgy are studying how following fairly simple responses to a pheromone signal, do ant colonies do this amazing thing where what you might describe as the organizational or computational capacity of the colony is so profound relative to what each individual ant is doing. I am not anywhere near as well versed in the cutting edge of cellular automatas. I would like, unfortunately, in terms of topics that I would like to get to and haven't like ETs more, Wolfram's a new kind of science. I have only skimmed and read reviews of and not read the whole thing or his newer work since. But his idea of the four basic kind of categories of emergent phenomena that can come from cellular automaton that one of them is kind of interesting and looks a lot like complexity rather than just chaos or homogeneity or self-termination or whatever. I think this is very interesting. It does not instantly make me think that biology is operating on a similarly small set of rules and or that human consciousness is. I'm not that reductionist oriented. And so if you look at, say, Santa Fe Institute, one of the co-founders, Stuart Kaufman, his work, you should really get him on your show. So a lot of the questions that you like, one of Kaufman's more recent books after investigations and some of the real fundamental stuff was called Reinventing the Sacred. And it had to do with some of these exact questions in kind of non-reductionist approach, but that is not just silly hippie-ism. And he was very interested in highly non-ergotic systems where you couldn't take a lot of behavior over a small period of time and predict what the behavior of subsets over a longer period of time would do. And then going further, someone who spent some time at Santa Fe Institute and then kind of made a whole new field that you should have on, Dave Snowden, who some people call the father of anthropocomplexity or what is the complexity unique to humans. He says something to the effect of that modeling humans as termites really doesn't cut it. Like we don't respond exactly identically to the same pheromones stimulus using stigma G, like it works for flows of traffic and some very simple human behaviors, but it really doesn't work for trying to make sense of the Sistine Chapel and Picasso and general relativity creation and stuff like that. And it's because the termites are not doing abstraction, forecasting deep into the future and making choices now based on forecasts of the future, not just adaptive signals in the moment and evolutionary code from history. That's really different, right? Like making choices now that can factor deep modeling of the future. And with humans, our uniqueness one to the next in terms of response to similar stimuli is much higher than it is with a termite. One of the interesting things there is that their uniqueness is extremely low. They're basically fungible within a class, right? There's different classes, but within a class they're basically fungible and their system uses that very high numbers and lots of loss, right, lots of death and loss. </s><s>[INST] Do you think the termite feels that way? Do you think that termite feels that way? Don't you think where humans are deceiving ourselves about our uniqueness perhaps? Isn't there some sense in which this emergence creates different higher and higher levels of abstraction where every layer of each organism feels unique? Is that possible? [/INST] That we're all equally ampnence different scales? You think uniqueness? No, I think uniqueness is evolving. I think that hydrogen atoms are more similar to each other than cells of the same type are. I think that cells are more similar to each other than humans are, and I think that highly case-elected species are more unique than R-selected species. They're different evolutionary processes. The R-selected species where you have a whole, a lot of death, and very high birth rates, not looking for as much individuality within or individual possible expression to cover the evolutionary search space within an individual. You're looking at it more in terms of a numbers game. So yeah, I would say there's probably more difference between one orca and the next </s><s>[INST] than there is between one cape buffalo and the next. Given that it would be interesting to get your thoughts about mimetic theory where we're imitating each other in the context of this idea of uniqueness, how much truth is there to that, how compelling is this worldview to you of Girardian mimetic theory of desire where maybe you can explain it from your perspective, but it seems like imitating each other is [/INST] the fundamental property of the behavior of human civilization. Well imitation is not unique to humans, right? Monkeys imitate. So a certain amount of learning through observing is not unique to humans. Humans do more of it. It's actually kind of worth speaking to this for a moment. Monkeys can learn new behaviors. We've even seen teaching an ape sign language and then the ape teaching other apes sign language. So that's a kind of mimesis, right? Kind of learning through imitation. And that needs to happen if they need to learn or develop capacities that are not just coded by their genetics, right? So within the same genome, they're learning new things based on the environment. And so based on someone else, learn something first. And so let's pick it up. How much a creature is the result of just its genetic programming and how much it's learning is a very interesting question. And I think this is a place where humans really show up radically different than everything else. And you can see it in the, in the neoteny, how long we're basically fetal. That a, the closest ancestors to us, if we look at a chimp, a chimp can hold on to its mother's fur while she moves around day one. And obviously we see horses up and walking within 20 minutes. The fact that it takes a human a year to be walking and it takes horse 20 minutes and you say, how many multiples of 20 minutes go into a year? Like that's a long period of helplessness that wouldn't work for a horse, right? Like they do or anything else. And, and not only can we not hold on to mom in the first day, it's three months before we can move our head volitionally. So it's like, why, why are we embryonic for so long? Basically it's like, like it's still fetal on the outside had to be because couldn't keep growing inside and actually ever get out with big heads and narrower hips from going upright. So here's a place where there's a co-evolution of the pattern of humans specifically here are our neoteny and what that portends to learning with our being tool making an environment modifying creatures, which is because we have the abstraction to make tools, we change our environments more than other creatures change their environments. The next most environment modifying creature to us is like a beaver. And then you we're in LA you fly into LAX and you look at the just orthogonal grid going on forever in all directions. And we've recently come into the Anthropocene where the surface of the earth is changing more from human activity than geological activity. And then beavers and you're like, okay, wow, we're really in a class of our own in terms of environments modifying. So as soon as we started toolmaking, in terms of environments modifying, we were able to change our environments much more radically, we could put on clothes and go to a cold place. And this is really important, because we actually went and became Apex predators in every environment, we functioned like apex predators, the polar bear can't leave the Arctic, and the lion can't leave the Savannah and Orca can't leave the ocean. And we went and became apex predators in all those environments, because of our tool creation capacity, we could become better predators </s><s>[INST] in them adapted to the environment, or at least with our tools adapted to the environment. So in every aspect towards any organism in any environment, we're incredibly good at [/INST] becoming apex predators. Yes. And nothing else can do that kind of thing. There's no other apex predator that, see, the other apex predator is only getting better at being a predator through evolutionary process that's super slow, and that's super slow process creates co-selective process with their environment. So as the predator becomes a tiny bit faster, it eat's more of the slow prey. genes of the fast prey and breed and the prey becomes faster. And so there's this kind of balancing because of our tool making, we increased our predatory capacity faster than anything else could increase its resilience to it. As a result, we started outstripping the environment and extincting species following stone tools, and going and becoming apex predator everywhere. This is why we can't keep applying apex predator theories because we're not an apex predator, we're an apex predator, but we're something much more than that. that. Like just for an example, the top apex predator in the world in Orca. And Orca can eat one big fish at a time, like one tuna, and it'll miss most of the time, or one seal. And we can put a mile long drift net out on a single boat and pull up an entire school of them, right? We can deplete the entire oceans of them. That's not an Orca, right? Like that's not an apex predator. And that's not even including that we can then genetically engineer different creatures. We can extinct species, we can devastate whole ecosystems. We can make built worlds that have no natural things, that are just human built worlds. We can build new types of natural creatures, synthetic life. So we are much more like little gods than we are like apex predators now, but we're still behaving as apex predators. And little gods behave as apex predators cause us a problem, kind of core to my assessment of the world. </s><s>[INST] So, what does it mean to be a predator? So a predator is somebody that effectively can mine the resources from a place. So for their survival, or is it also just purely like higher level objectives of violence? And what is, can predators be predators towards the same, each other, towards the same species? Like are we using the word predator sort of generally, which then connects to conflict [/INST] and military conflict, violent conflict in the space of human species? Well, obviously we can say that plants are mining the resources of their environment in a particular way, using photosynthesis to be able to pull minerals out of the soil and nitrogen and carbon out of the air and like that. And we can say herbivores are being able to mine and concentrate that. So I wouldn't say mining the environment is unique to predator. Predator is generally being defined as mining other animals, right? We don't consider herbivores predators, but animal, which requires some type of violence capacity because animals move, plants don't move. So it requires some capacity to overtake something that can move and try to get away. We'll go back to the Gerard thing, then we'll come back here. Why are we neotenous? Why are we embryonic for so long? Because are we, did we just move from the savanna to the Arctic and we need to learn new stuff? If we came genetically programmed, we would not be able to do that. Are we throwing spears or are we fishing or are we running an industrial supply chain or are we texting? What is the adaptive behavior? Horses today in the wild and horses 10,000 years ago are doing pretty much the same stuff. And so since we make tools and we evolve our tools and then change our environment so quickly and other animals are largely the result of their environment, but we're environment modifying so rapidly, we need to come without too much programming so we can learn the environment we're in, learn the language, right? Which is going to be very important, learn the tool making, learn the... And so we have a very long period of relative helplessness because we aren't coded how to behave yet because we're imprinting a lot of software on how to behave that is useful to that particular time. So our mimesis, it's not unique to humans, but the total amount of it is really unique. And this is also where the uniqueness can go up, right? It's because we are less just the result of the genetics and that means the kind of learning through history that they got coded in genetics and more the result of, it's almost like our hardware selected for software, right? Like if evolution is kind of doing these, think of as a hardware selection, I have problems with computer metaphors for biology, but I'll use this one here, that we have not had hardware changes since the beginning of sapiens, but our world is really, really different. And that's all changes in software, right? Changes in on the same fundamental genetic substrate, what we're doing with these brains and minds and bodies and social groups and like that. And so now Gerard specifically was looking at when we watch other people talking. So we learn language. You and I would have a hard time learning Mandarin today or it'd take a lot of work. We'd be learning how to conjugate verbs and stuff, but a baby learns it instantly without anyone even really trying to teach it just from a mimesis. So it's a powerful thing. They're obviously more neuroplastic than we are when they're doing that and all their attention is allocated to that. But they're also learning how to move their bodies and they're learning all kinds of stuff through mimesis. One of the things that Gerard says is they're also learning what to want and they learn what to want. They learn desire by watching what other people want. And so intrinsic to this, people ended up wanting what other people want. And if we can't have what other people have without taking it away from them, then that becomes a source of conflict. So the mimesis of desire is the fundamental generator of conflict and that then the conflict energy within a group of people will build over time. </s><s>[INST] This is a very, very crude interpretation of the theory. Can we just pause on that? For people who are not familiar, and for me who hasn't, I'm loosely familiar, but I haven't internalized it, but every time I think about it, it's a very compelling view of the world, whether it's true or not. It's quite, it's like when you take everything Freud says as truth, it's a very interesting way to think about the world, and in the same way, thinking about the memetic theory of desire, that everything we want is imitation of other people's wants. We don't have any original wants. We're constantly imitating others. And so, and not just others, but others we're exposed to. So there's these like little local pockets, however defined local, of people imitating each other. And one that's super empowering because then you can pick which group you can join. Like, what do you wanna imitate? It's the old like, you know, whoever your friends are, that's what your life is gonna be like. That's really powerful. I mean, it's depressing that we're so unoriginal, but it's also liberating in that if this holds true, that we can choose our life by choosing the people we hang out with. [/INST] So, okay, thoughts that are very compelling, that seem like they're more absolute than they actually are end up also being dangerous. Who we wanna- Communism? I'm gonna discuss here where I think we need to amend this particular theory. But specifically, you just said something that everyone who's paid attention knows is true experientially, which is who you're around affects who you become. And as libertarian and self-determining and sovereign as we'd like to be, everybody I think knows that if you got put in the maximum security prison, aspects of your personality would have to adapt or you wouldn't survive there, right? You would become different. If you were, if you grew up in Darfur versus Finland, you would be different with your same genetics, like just no real question about that. And that even today, if you hang out in a place with ultra marathoners as your roommates or all people who are obese as your roommates, the statistical likelihood of what happens to your fitness is pretty clear, right? Like the behavioral science of this is pretty clear. So the whole saying we are the average of the five people we spend the most time around. I think the more self-reflective someone is and the more time they spend by themselves in self-reflection, the less this is true, but it's still true. So one of the best things someone can do to become more self-determined is be self-determined about the environments they wanna put themselves in, because to the degree that there is some self-determination and some determination by the environment, don't be fighting an environment that is predisposing you in bad directions. Try to put yourself in an environment that is predisposing the things that you want. In turn, try to affect the environment </s><s>[INST] in ways that predispose positive things for those around you. Or perhaps also to, there's probably interesting ways to play with this. You could probably put yourself like form connections that have this perfect tension in all directions to where you're actually free to decide whatever the heck you want, because the set of wants within your circle of interactions is so conflicting that you're free to choose whichever one. So, if there's enough tension [/INST] as opposed to everybody aligned like a flock of birds. Yeah, I mean, you definitely want that all of the dialectics would be balanced. So, if you have someone who is extremely oriented to self-empowerment and someone who is extremely oriented to kind of empathy and compassion, both the dialectic of those is better than either of them on their own. If you have both of them being inhabited better than you by the same person, spending time around that person probably do well for you. I think the thing you just mentioned is super important when it comes to cognitive schools, which is I think one of the fastest things people can do to improve their learning. And they're not just cognitive learning, but they're meaningful problem solving communication and civic capacity, capacity to participate as a citizen with other people and making the world better, is to be seeking dialectical synthesis all the time. And so in the Hegelian sense, if you have a thesis, you have an antithesis. So maybe we have libertarianism on one side and Marxist kind of communism on the other side. And one is arguing that the individual is the unit of choice. And so we want to increase the freedom and support of individual choice because as they make more agentic choices, it'll produce a better whole for everybody. The other side saying, well, the individuals are conditioned by their environment, who would choose to be born into Darfur rather than Finland. So we actually need to collectively make environments that are good because the environment conditions the individuals. So you have a thesis and an antithesis. And then Hegel's idea is you have a synthesis, which is a kind of higher order truth that understands how those relate in a way that neither of them do. And so it is actually at a higher order of complexity. So the first part would be, can I steel man each of these? Can I argue each one well enough that the proponents of it are like totally you got that? And not just argue it rhetorically, but can I inhabit it where I can try to see and feel the world the way someone seeing and feeling the world that way would? Cause once I do, then I don't want to screw those people because there's truth in it. Right. And I'm not going to go back to war with them. I'm going to go to finding solutions that could actually work at a higher order. If I don't go to a higher order, then there's war. And but then the order thing would be, well, it seems like the individual does affect the commons and the collective and other people. It also seems like the collective conditions individuals, at least statistically. And I can cherry pick out the one guy who got out of the ghetto and pulled himself up by his bootstraps. But I can also say statistically that most people born into the ghetto show up differently than most people born into the Hamptons. And so unless you want to argue that and take your child from the Hamptons and put them in the ghetto then like, come on, be realistic about this thing. So how do we make, we don't want social systems that make weak dependent individuals, right? The welfare argument, but we also don't want no social system that supports individuals to do better. We don't want individuals where their self-expression and agency fucks the environment and everybody else and employs slave labor and whatever. So can we make it to where individuals are creating homes that are better for conditioning other individuals? Can we make it where we have holes that are conditioning increased agency and sovereignty, right? That would be the synthesis. So the thing that I'm coming to here is if people have that as a frame and sometimes it's not just thesis and antithesis. It's like eight different views. Can I steel man each view? This is not just Can I take the perspective, but am I seeking them? Am I actively trying to inhabit other people's perspective? Then can I really try to essential it and argue the best points of it, both the sense making about reality and the values, why these values actually matter. Then, just like I want to seek those perspectives, then I want to seek, is there a higher order set of understandings that could fulfill the values of and synthesize the sense making of all of them simultaneously? Maybe I won't get it, but I want to be seeking it and I want to be seeking progressively better ones. So this is perspective seeking, driving perspective taking, and then seeking synthesis. I think that that one cognitive disposition might be the most helpful </s><s>[INST] thing. Would you put a title of dialectic synthesis on that process? Because that seems to be such a part, so like this rigorous empathy, like it's not just empathy, it's empathy with rigor, like you really want to understand and embody [/INST] different worldviews and then try to find a higher order synthesis. Okay so I remember last night you told me when we first met, you said that you looked in somebody's eyes and you felt that you had suffered in some ways that they had suffered, and so you could trust them. Shared pathos, right, creates a certain sense of kind of shared bonding and shared intimacy, so empathy is actually feeling the suffering of somebody else and feeling the depth of their sentience. I don't want to fuck them anymore, I mean I hurt them, I don't want to behave in I don't want my proposition to go through. When I go and inhabit the perspective of the other people they feel that's really going to mess them up. Right. And so the rigorous empathy it's different than just compassion, which is I generally care, like I have a generalized care, but I don't know what it's like to be them, I can never know what it's like to be them perfectly. And there's a humility you have to have which is my most rigorous attempt is still not it, my most rigorous attempt mine to know what it's like to be a woman is still not it. I've no question that if I was actually a woman, it would be different than my best guesses. I have no question. If I was actually black. It's be different than my best guesses. So there's a humility in that which keeps me listening, because I don't think that I know fully, but I want to and I'm going to keep trying better too. And then I want to across them. And then I want to say, is there a way we can forward together and not have to be in war? It has to be something that could meet the values that everyone holds. It could reconcile the partial sensemaking that everyone holds that could offer a way forward that is more agreeable than the partial perspectives that </s><s>[INST] were with each other. But the more you succeeded this empathy with humility, the more you're carrying the burden [/INST] of other people's pain, essentially. Now this goes back to the question of do I see us as one being or 7.8 billion. I think if I'm overwhelmed with my own pain, I can't empathize that much because I don't have the bandwidth. It's one of the capacity. If I don't feel like I can do something about a particular problem in the world, it's hard to feel it because it's just too devastating. And so a lot of people go numb and even go nihilistic because they just don't feel the agency. So as I actually become more empowered as an individual and have more sense of agency, I also become more empowered to be more empathetic for others and be more connected to that shared burden and want to be able to make choices on behalf of and in benefit of. </s><s>[INST] So this way of living seems like a way of living that would solve a lot of problems in society from a cellular automata perspective. So if you have a bunch of little agents behaving in this way, my intuition, there will be interesting complexities that emerge, but my intuition is it will create a society that's very different and recognizably better than the one we have today. [/INST] How much like, oh, wait, hold that question because I want to come back to it. This brings us back to Gerard, which we didn't answer the conflict theory. Yes. Because about how to get past the conflict theory. </s><s>[INST] Yes. You know, the Robert Frost poem about the two paths you never have time to return back to you that we're going to have to do that quite a lot. We're going to be living that poem over and over again. [/INST] But yes, how how to let's return back. Okay. So the rest of the argument goes you learn to want what other people want. Therefore fundamental conflict based in our desire, because we want the thing that somebody else has. And then people are in conflict over trying to get the same stuff. Power, status, attention, physical stuff, a mate, whatever it is. And then we learn the conflict by watching and so then the conflict becomes mimetic. So we become on the Palestinian side of the Israeli side or the communist, the capitalist side or the left or right politically or whatever it is. And until eventually the conflict energy in the system builds up so much that some type of violence is needed to get the bad guy, whoever it is that we're going to blame. And you know, Gerard talks about why scapegoating was kind of a mechanism to minimize the amount of violence. Let's blame a scapegoat as being more relevant than they really were. But if we all believe it, then we can all kind of calm down with the conflict energy. </s><s>[INST] It's a really interesting concept, by the way. I mean, you beautifully summarized it, but the idea that there's a scapegoat, that there's this kind of thing that actually leads to a conflict, and then they find the other, some group that's the other that's either real or artificial as the cause of the conflict. [/INST] Well, it's always artificial because the cause of the conflict in Gerard is the mimesis of desire itself. And how do we attack that? How do we attack that it's our own desire? So this now gets to something more like Buddha said, right? Which was desire is the cause of suffering. </s><s>[INST] Gerard and Buddha would kind of agree in this way. And so, but that's, that explains, I mean, again, it's a compelling description of human history that we do tend to come up with the other. [/INST] And okay, kind of, I just, I just had such a funny experience with someone critiquing Gerard the other day in such a elegant and beautiful and simple way. It's a friend who's grew up Aboriginal Australian, is a scholar of Aboriginal social technologies. He's like, nah, man, Gerard just made shit up about how tribes work. Like we come from a tribe, we've got tens of thousands of years, and we didn't have increasing conflict and then scapegoat and kill someone, we'd have a little bit of conflict and then we would dance, and then everybody'd be fine. Like we'd dance around the campfire, everyone would like kind of physically get the energy out. We'd have positive bonding, and then we're fine, and nobody, no scapegoats. </s><s>[INST] And I think that's called the Joe Rogan theory of desire, which is, he's like, all, all of human problems have to do with the fact that you don't do enough hard shit in your day. So maybe, maybe just dance it because he says like doing exercise and running on that treadmill [/INST] gets, gets all the demons out and maybe just dance and gets all the demons out. So this is why I say we have to be careful with taking an idea that seems too explanatory and then taking it as a given, and then saying well, now that we're stuck with the fact that conflict is inexorable because human, because mimetic desire and therefore how do we deal with the inexorability of the conflict and how to sublimate violence? Well, no, the whole thing might be actually gibberish, meaning it's only true in certain conditions and other conditions, it's not true. So the deeper question is, under which conditions is that true? Under which conditions is it not true? What do those other conditions make possible and look like? </s><s>[INST] And in general we should stay away from really compelling models of reality because there's something about our brains that these models become sticky [/INST] and we can't even think outside of them. So, it's not that we stay away from them. It's that we know that the model of reality is never reality. </s><s>[INST] That's the key thing. Humility again, it goes back to just having the humility that you don't have a perfect [/INST] model of reality. Humility. There's an, the model of reality could never be reality. The process of modeling is inherently information reduction. </s><s>[INST] And I can never show that the unknown unknown set has been factored. It's back to the cellular automata. You can't put the genie back in bottle. Because when you realize it's unfortunately, sadly impossible to create a model of cellular automata, even if you know the basic rules that predict to even any degree of accuracy what how that system will evolve, which is fascinating mathematically, sorry, I think about it quite a lot. It's very annoying. Wolfram has this rule 30, like you should be able to predict it. It's so simple, but you can't predict what's going to be like there's a problem he defines they try to predict some aspect of the middle middle column of the system, just anything about it. What's gonna happen in the future and you can't. You can't it sucks. Because then we can't make sense of this world in a really in a reality in a definitive way. It's always like in the striving, like we're always striving. Yeah, I don't think this sucks. [/INST] that's a feature, not a bug? Well, that's assuming a designer. I would say I don't think it sucks. I think it's not only beautiful, but maybe necessary for beauty. </s><s>[INST] Mess. So you're, uh, so you're, you disagree with Jordan Peterson, you should clean up your room. You like the rooms messy. It's, uh, it's essential for the, for beauty. [/INST] It's not, it's not that it's, it's not, it's not that it's okay. I take, I have no idea if it was intended this way. And so I'm just interpreting it away. I like the commandment about having no false idols. To me, the way I interpret that is meaningful is that re reality sacred to me, I have a reverence for reality, but I know my best understanding of it is never complete. I know my best model of it is a model where I tried to make some kind of predictive capacity by reducing the complexity of it to a set of stuff that I could observe. And then a subset of that stuff that I thought was the causal dynamics. And then some set of, you know, mechanisms that are involved. And what we find is that it can be super useful. Like Newtonian gravity can help us do ballistic curves and all kinds of super useful stuff. And then we get to the place where it doesn't explain what's happening at the cosmological scale or at a quantum scale. And at each time, what we're finding is, uh, we excluded stuff and it also doesn't explain the reconciliation of gravity with quantum mechanics and the other kind of fundamental laws and the, so models can be useful, but they're never true with a capital T meaning they're never an actual real full, they're never a complete description of what's happening in real systems. They can be a complete description of what's happening in an artificial system that was the result of applying a model. So the model of a circuit board and the circuit board are the same thing, but I would argue that the model of a cell in the cell are not the same thing. And I would say this is key to what we call complexity versus the complicated, which is a distinction Dave Snowden made well in defining the difference between simple, complicated, complex, and chaotic systems. But one of the definers in complex systems is that no matter how you model the complex system, it will still have some emergent behavior not </s><s>[INST] predicted by the model. Can you elaborate on the complex versus the complicated? [/INST] Complicated means we can fully explicate the phase space of all the things that it can do. We can program it. All human, not all, for the most part, human built things are complicated. They don't self-organize. They don't self-repair. They're not self-evolving. And we can make a blueprint for them. Sorry, for human systems? For human technologies. Human technologies. Oh, sorry. So non-analytical systems. That are basically the application of models. And engineering is kind of applied science, science as the modeling process. But humans are complex. Complex stuff with biological type stuff and sociological type stuff, it more has generator functions. And even those can't be fully explicated. Or our explantication can't prove that it has closure of what would be in the unknown, unknown set where we keep finding like, oh, it's just the genome. Oh, well, now it's the genome and the epigenome. And then a recursive change on the epigenome because of the proteome. And then there's mitochondrial DNA. And then viruses affected. And fuck, right? So it's like, we get overexcited when we think we found the </s><s>[INST] thing. Human technologies. So on Facebook, you know how you can list your relationship as complicated? It should actually say it's complex. That's the more accurate description. Self-terminating is a really interesting idea that you talk about quite a bit. First of all, what is a self-terminating system? And I think you have a sense, correct me if I'm wrong, that human civilization as it currently is, is a self-terminating system. Why do you have that intuition combined with the definition of what self-terminating means? [/INST] Okay, so if we look at human societies historically, human civilizations, it's not that hard to realize that most of the major civilizations and empires of the past don't exist anymore. So they had a life cycle, they died for some reason. So we don't still have the early Egyptian empire or Inca or Maya or Aztec or any of those, right? And so they, they terminated. Sometimes it seems like they were terminated from the outside and more sometimes it seems like they self-terminate. When we look at Easter island, it was a self-termination. So let's go ahead and take an island situation. If I have an island, and we are consuming the resources on that island faster than the resources can replicate themselves, and there's a finite space there, that system is going to self-terminate. It's not going to be able to keep doing that thing because you'll get to a place of, There's no resources left. And then you get... Now, if I'm utilizing the resources faster than they can replicate or faster than they can replenish, and I'm actually growing our population in the process, I'm even increasing the rate of the utilization of resources, I might get an exponential curve and then hit a wall and then just collapse the exponential curve, rather than do an S-curve or some other kind of thing. So self-terminating system is any system that depends upon a substrate system that is debasing its own substrate that is debasing what </s><s>[INST] it depends upon. So you're right that if you look at empires they rise and fall throughout human [/INST] history but but not this time bro where this one's gonna last forever. That's I like that idea. I think that if we don't understand why all the previous ones failed we can't ensure that and so I think it's very important to understand it well so that we can have that be a designed outcome </s><s>[INST] with somewhat decent probability. So we're it's sort of in terms of consuming the resources on the island we're a clever bunch and we keep coming up especially when on the horizon there is a termination point. We keep coming up with clever ways of avoiding disaster of avoiding collapse of constructing this is where technological innovation this is where growth comes in coming up with different ways to improve productivity and the way society functions such that we consume less resources or get a lot more from the resources we have. So there's some sense in which there's a human ingenuity is a source for optimism about the future of this particular system that that may not be self-terminating. If there's more innovation [/INST] than there is consumption. So over consumption of resources just one way I think can self-terminate we're just kind of starting here but there are reasons for optimism and pessimism then they're both worth understanding and there's failure modes on understanding either without the other. As we mentioned previously there is what I would call naive techno-optimism, naive techno-capital optimism that says stuff just has been getting better and better and we wouldn't want to live in the dark ages and tech has done all this awesome stuff and we know the proponents of those models and that stuff is going to kind of keep getting better of course there are problems but </s><s>[INST] human ingenuity rises to its supply and demand will solve the problems whatever. Would you put Ray Kurzweil on that or in that bucket is there some specific people you have in mind or naive optimism is truly naive to where you're essentially just have an optimism that's blind to any kind of [/INST] realities of the way technology progresses. I don't think that anyone who thinks about it and writes about it is perfectly naive. It's a platonic ideal. There might be a bias in the nature of the assessment. I would also say there's kind of naive techno-pessimism and there are critics of technology. I mean you read the Unabomber's manifesto on why technology can't not result in our self-termination so we have to take it out before it gets any further. But also if you read a lot of the x-risk community you know Bostrom and friends it's like our total number of existential risks and the total probability of them is going up and so I think that we have to hold together where our positive possibilities and our risk possibilities are both increasing and then say for the positive possibilities to be realized long term all of the catastrophic risks have to not happen. Any of the catastrophic risks happening is enough to keep that positive outcome from occurring. So how do we ensure that none of them happen? If we want to say let's have a civilization that doesn't collapse so again collapse theory it's worth worth looking at books like The Collapse of Complex Societies by Joseph Tainter does an analysis of that many of the societies fell for internal institutional decay, civilizational decay reasons. Baudrillard in Simulation and Simulacra looks at a very different way of looking at how institutional decay and the collective intelligence of a system happens and it becomes kind of more internally parasitic on itself. Nancy Jared Diamond made a more popular book called Collapse. And as we were mentioning, the anti-catheria mechanism has been getting attention in the news lately. It's like a 2,000-year-old clock, right? Like metal gears. And does that mean we lost like 1,500 years of technological progress? And from a society that was relatively technologically advanced. So what I'm interested in here is being able to say, okay, well, why did previous societies fail? Can we then understand that abstractly enough that we can make a civilizational model that isn't just trying to solve one type of failure, but solve the underlying things that generate the failures as a whole? Are there some underlying generator functions or patterns that would make a system self-terminating? And can we solve those, and have that be the kernel of a new civilizational model that is not self-terminating? And can we then be able to actually look at the categories of extras we're aware of and and see that we actually have resilience in the presence of those, not just resilience, but anti-fragility. And I would say for the optimism to be grounded, it has to actually be able to understand the risk space well and have adequate solutions for it. </s><s>[INST] So can we try to dig into some basic intuitions about the underlying sources of catastrophic failures of the system and over-consumption that's built in into self-terminating systems? So both the over-consumption, which is like the slow death, and then there's the fast death of nuclear war and all those kinds of things. AGI, biotech, bioengineering, nanotechnology, my favorite nanobots. Okay, nanobots are my favorite because it sounds so cool to me that I could just know that I would be one of the scientists that would be full steam ahead in building them without sufficiently thinking about the negative consequences. I would definitely be, I would be podcasting all about the negative consequences, but when I go back home, I'd be, I just, in my heart, no, the amount of excitement is a dumb descendant of ape, no offense to apes. So I want to backtrack on my previous comments about negative comments about apes, that I have that sense of excitement that would result in problems. So sorry, a lot of things said, but what's, can we start to pull a thread? Because you've also provided kind of a beautiful general approach to this, which is this dialectic synthesis or just rigorous empathy. Whatever word we want to put to it, that seems to be from the individual perspective is one way to sort of live in the world as we try to figure out how to construct non-self-termining systems. So what are some underlying sources? [/INST] Yeah, yeah, first I have to say, I actually really respect Drexler for emphasizing Grey Goo and engines of creation back in the day to make sure the world was paying adequate attention to the risks of the nanotech as someone who was right at the cutting edge of what could be. There's definitely game theoretic advantage to those who focus on the opportunities and don't focus on the risks or pretend there aren't risks because they get to market first and then they externalize all of the costs through limited liability or whatever it is to the commons or wherever happened to have it. Other people are gonna have to solve those, but now they have the power and capital associated. The person who looked at the risks and tried to do better design and go slower is probably not gonna move into positions of as much power or influence as quickly. So this is one of the issues we have to deal with is some of the bad game theoretic dispositions </s><s>[INST] in the system relative to its own stability. And the key aspect to that, sorry to interrupt, is the externalities generated. Yes. What flavors of catastrophic risk are we talking about here? What's your favorite flavor in terms of ice cream? So mine is coconut, nobody seems to like coconut ice cream. So ice cream aside, what do you most worry about in terms of catastrophic risk that will help us kind of make concrete [/INST] the discussion we're having about how to fix this whole thing? Yeah. I think it's worth taking a historical perspective briefly to just kind of orient everyone to it. We don't have to go all the way back to the aliens who've seen all of civilization, but to just recognize that for all of human history, as far as we're aware, there were existential risks to civilizations and they happened, right? Like there were civilizations that were killed in war, that tribes that were killed in tribal warfare, whatever. So people faced existential risk to the group that they identified with. It's just, those were local phenomena, right? It wasn't a fully global phenomena. So an empire could fall and surrounding empires didn't fall. Maybe they came in and filled the space. The first time that we were able to think about catastrophic risk, not from like a solar flare or something that we couldn't control, but from something that humans would actually create at a global level was World War II and the bomb. Because it was the first time that we had tech big enough that could actually mess up everything at a global level, that could mess up habitability. We just weren't powerful enough to do that before. It's not that we didn't behave in ways that would have done it. We just only behaved in those ways at the scale we could affect. And so it's important to get that there's the entire world before World War II, where we don't have the ability to make a non-habitable biosphere, non-habitable for us. And then there's World War II and the beginning of a completely new phase where global human-induced catastrophic risk is now a real thing. And that was such a big deal that it changed the entire world in a really fundamental way, which is, when you study history, it's amazing how big a percentage of history is studying war, right? In the history of wars, you study European history and whatever. It's generals and wars and empire expansions. And so the major empires near each other never had really long periods of time where they weren't engaged in war or preparation for war or something like that was humans don't have a good precedent in the post tribal phase, the civilization phase of being able to solve conflicts without war for very long. World War II was the first time where we could have a war that no one could win. And so the superpowers couldn't fight again. They couldn't do a real kinetic war. They could do diplomatic wars and cold war type stuff. And they could fight proxy wars through other countries that didn't have the big weapons. And so mutually assured destruction and like coming out of World War II, we actually realized that nation states couldn't prevent world war. And so we needed a new type of supervening government in addition to nation states, which was the whole Bretton Woods world, the United Nations, the World Bank, the IMF, the globalization trade type agreements, mutually assured destruction. That was how do we have some coordination beyond just nation states between them since we have to stop war between at least the superpowers. And it was pretty successful, given that we've had like 75 years of no superpower on superpower war. We've had lots of proxy wars during that time, we've had, you know, cold war. And I would say we're </s><s>[INST] in a new phase now, where the Bretton Woods solution is basically over or almost over. Can you describe the Bretton Woods solution? [/INST] Yeah, yeah. So the Bretton Woods, the series of agreements for how the nations would be able to engage with each other in a solution other than war was these IGOs, these intergovernmental organizations, and was the idea of globalization. Since we could have global effects, we needed to be able to think about things globally, where we had trade relationships with each other, where it would not be profitable to war with each other, it'd be more profitable to actually be able to trade with each other. So our own self interest was, you know, going to drive our non war interest. And so this started to look like, and obviously, this couldn't have happened that much earlier either, because industrialization hadn't gotten far enough to be able to do massive global industrial supply chains and ships stuff around, you know, quickly. But like we were mentioning earlier, almost all the electronics that we use today, just basic cheap stuff for us is made on six continents made in many countries. There's no single country in the world that could actually make many of the things that we have and from the raw material extraction to the plastics and polymers and the, you know, etc. And so the idea that we made a world that could do that kind of trade and create massive GDP growth, we could all work together to be able to mine natural resources and grow stuff. With the rapid GDP growth, there was the idea that everybody could keep having more without having to take each other's stuff. And so that was part of the Bretton Woods post-World War II model. The other was that we'd be so economically interdependent that blowing each other up would never make sense. That worked for a while. Now, it also brought us up into planetary boundaries faster, the unrenewable use of resource and turning those resources into pollution on the other side of the supply chain. So obviously, that faster GDP growth meant the overfishing of the oceans and the cutting down of the trees and the climate change and the mining, toxic mining tailings going into the water and the mountaintop removal </s><s>[INST] mining and all those types of things. That's the overconsumption side of the rest that we're [/INST] talking about. And so the answer of let's do positive GDP is the answer rapidly and exponentially, obviously, accelerated the planetary boundary side. And that was thought about for a long time, but it started to be modeled with the club of Rome and limits of growth. But it's just very obvious to say if you have a linear materials economy where you take stuff out of the earth faster, whether it's fish or trees or oil, and you take it out of the earth faster than it can replenish itself, and you turn it into trash after using it for a short period of time, you put the trash in the environment faster than it can process itself. And there's toxicity associated with both sides of this. You can't run an exponentially growing linear materials economy on a finite planet forever. That's not a hard thing to figure out. And it has to be exponential if there's an exponentiation in the monetary supply because of interest and then fraction reserve banking. And to then be able to keep up with the growing monetary supply, you have to have growth of goods and services. And so that's that kind of thing that has happened. But you also see that when you get these supply chains that are so interconnected across the world, you get increased fragility because a collapse or a problem in one area then affects the whole world in a much bigger area as opposed to the issues being local. So we got to see with COVID and an issue that started in one part of China affecting the whole world so much more rapidly than would have happened before Bretton Woods, before international travel supply chains, you know, that whole kind of thing. And with a bunch of second and third order effects that people wouldn't have predicted, okay, we have to stop certain kinds of travel because of viral contaminants, but the countries doing agriculture depend upon fertilizer they don't produce that is shipped into them and depend upon pesticides they don't produce. So we got both crop failures and crops being eaten by locusts in scale in Northern Africa and Iran and things like that because they couldn't get the supplies of stuff in. So then you get massive starvation or future kind of hunger issues because of supply chain shutdowns. So you get this increased fragility and cascade dynamics where a small problem can end up leading to cascade effects. And also, we went from two superpowers with one catastrophe weapon to now that same catastrophe weapon is there's more countries that have it, eight or nine countries that have it. And there's a lot more types of catastrophe weapons. We now have catastrophe weapons with weaponized drones that can hit infrastructure targets with bio with fact, every new type of tech has created an arms race. So we have not with the UN or the other kind of intergovernmental organizations, we haven't been able to really do nuclear deep proliferation. We've actually had more countries get nukes and keep getting faster nukes the race to hypersonics and things like that. And every new type of technology that has emerged has created an arms race. And so you can't do mutually assured destruction with multiple agents the way you can with two agents. Two agents, it's much easier to create a stable Nash equilibrium that's forced. But the ability to monitor and say, if these guys shoot, who do I shoot? Do I shoot them? Do I shoot everybody? Do I? And so you get a three body problem. You get a very complex type of thing when you have multiple agents and multiple different types of catastrophe weapons, including ones that can be much more easily produced than nukes, nukes are really hard to produce. There's only uranium in a few areas. Uranium enrichment is hard. ICBMs are hard. But weaponized drones hitting smart targets is not so hard. There's a lot of other things where basically the scale at being able to manufacture them is going way way down to where even non-state actors can have them. And so when we talk about exponential tech, and the decentralization of exponential tech, what that means is decentralized catastrophe weapon capacity. And especially in a world of increasing numbers of people feeling disenfranchised, frantic, whatever for different reasons. So I would say where the Bretton Woods world doesn't prepare us to be able to deal with lots of different agents, having lots of different types of catastrophe weapons, you can't put mutually assured destruction on, where you can't keep doing growth of the materials economy in the same way because of hitting planetary boundaries, and where the fragility dynamics are actually now their own source of catastrophic risk. So now we're so like there was all the world until World War Two, and World War Two is just from a from a civilization timescale point of view, it was just a second ago. It seems like a long time, but it is really not. We get a short period of relative peace at the level of superpowers while building up the military capacity for much, much, much worse war the entire time. And then now we're at this new phase where the things that allowed us to make it through the nuclear power are not the same systems that will let us make it through the next stage. So what is this next post Bretton Woods? How do we become safe vessels, safe stewards of many different types of exponential technology is a key question </s><s>[INST] when we're thinking about x-risk. Okay, so and I'd like to try to answer the how a few ways, but first on the mutually assured destruction, do you give credit to the idea of two superpowers not blowing each other up with nuclear weapons to the simple game theoretic model of mutually assured destruction or something you've said previously, this idea of inverse correlation, which I tend to believe between now you were talking about tech, but I think it's maybe broadly true, the inverse correlation between competence and propensity for destruction. So the better the the bigger your weapons, not because you're afraid of mutually assured self-destruction, but because we're human beings and there's a deep moral fortitude there that somehow aligned with competence and being good at your job that like it's very hard to be a psychopath and be good at killing at scale. Do you share any of that intuition? [/INST] Kind of. I think most people would say that Alexander the Great and Genghis Khan and Napoleon were effective people that were good at their job that were actually maybe asymmetrically good at being able to organize people and do certain kinds of things that were pretty oriented towards certain types of destruction, or pretty willing to maybe they would say they were oriented towards empire expansion, but pretty willing to commit certain acts of destruction in the name of it. </s><s>[INST] What are you worried about? The Genghis Khan? Or you could argue he's not a psychopath. Are you worried about Genghis Khan? Are you worried about Hitler? Or are you worried about a terrorist who has a very different ethic, which is not even for... It's not trying to preserve and build and expand my community. It's more about just destruction in itself is the goal. [/INST] I think the thing that you're looking at that I do agree with is that there's a psychological disposition towards construction and a psychological disposition more towards destruction. Obviously, everybody has both and can toggle between both. And oftentimes, one is willing to destroy certain things. We have this idea of creative destruction, willing to destroy certain things to create other things. And utilitarianism and trolley problems are all about exploring that space, and the idea of war is all about that. I am trying to create something for our people, and it requires destroying some other people. Sociopathy is a funny topic because it's possible to have very high fealty to your in-group and work on perfecting the methods of torture to the out-group at the same time, because you can dehumanize and then remove empathy. And I would also say that there are types. So, the reason, the thing that gives hope about the orientation towards construction and destruction being a little different in psychology is what it takes to build really catastrophic tech, even today where it doesn't take what it took to make a new small group of people could do it, takes still some real technical knowledge that required having studied for a while and some then building capacity. And there's a question of, is that psychologically inversely correlated with the desire to damage civilization meaningfully? A little bit, a little bit, I think. </s><s>[INST] I think a lot. I think it's actually, I mean, this is the conversation I had, I think offline with Dan Carlin, which is like, it's pretty easy to come up with ways that any competent, I can come up with a lot of ways to hurt a lot of people. And it's pretty easy. I alone could do it. And there's a lot of people as smart or smarter than me, at least in their [/INST] creation of explosives. Why are we not seeing more insane mass murder? I think there's something fascinating and beautiful about this. And it does have to do with some deeply prosocial types of characteristics in humans. But when you're dealing with very large numbers, you don't need a whole lot of a phenomena. And so then you start to say, well, what's the probability that X won't happen this year, then won't happen in the next two years, three years, four years? And then how many people are doing destructive things with lower tech? And then how many of them can get access to higher tech that they didn't have to figure out how to build? So when I can get commercial tech, and maybe I don't understand tech very well, but I understand it well enough to utilize it, not to create it. And I can repurpose it. When we saw that commercial drone with a homemade thermite bomb hit the Ukrainian munitions factory and do the equivalent of an incendiary bomb level of damage, that's just home tech. That's just simple kind of thing. And so the question is not does it stay being a small percentage of the population? The question is, can you bind that phenomena nearly completely? And especially now as you start to get into bigger things, CRISPR gene drive technologies and various things like that, can you bind it </s><s>[INST] completely long term? Over what period of time? Over what period of time? Not perfectly, though. That's the thing I'm trying. I'm trying to say that there is some let's call it. That's a random word love. That's inherent in that's core to human nature. That's preventing destruction at scale. And you're saying, yeah, but there's a lot of humans, there's going to be eight plus billion. And then there's a lot of seconds in the day to come up with stuff. There's a lot of pain in the world that can lead to a distorted view of the world such that you want to channel that pain into the destruction, all those kinds of things. And it's only a matter of time that any one individual can do large damage, especially as we create more and more democratized, decentralized ways to deliver that damage even if you don't know how to build the initial weapon you can. But the thing is, it seems like we're it's a race between the cheapening of destructive weapons and the capacity of humans to express their love towards each other. And it's a race that so far, I know on Twitter, it's not popular to say but love is winning. Okay. So what is the argument that love is going to lose here against nuclear weapons, biotech, and [/INST] AI and drones? Okay, I'm gonna comment the end of this to how love wins. So I just want you to know that that's where I'm oriented. That's the end. But I'm gonna argue against </s><s>[INST] why that is a given because it's not a given. I don't believe. And I think this is like a good romantic comedy. So you're gonna create drama right now. But it will end in a happy [/INST] ending. Well, it's because it's only a happy ending if we actually understand the issues well enough and take responsibility to shift it. Do I believe like there's a reason why there's so much more dystopic sci fi than protopic sci fi and the in the some protopic sci fi usually requires magic is because or at least magical tech, right? Dilithium crystals and warp drives and stuff, because it's very hard to imagine people like the people we have been in the history books with exponential type technology and power that don't eventually blow themselves up, that make good enough choices as stewards of their environment and their commons and, and each other and etc. So like it's easier to think of scenarios where we blow ourselves up than it is to think of scenarios where we avoid every single scenario where we blow ourselves up. And when I say blow ourselves up, I also, I mean, the environmental versions, the terrorist versions, the war versions, the cumulative externalities </s><s>[INST] versions. Can I and I'm sorry if I'm interrupting your flow of thought, but why is it easier? Could it be a weird psychological thing where we either was just more capable to visualize explosions and destruction and then the sicker thought which is like we kind of enjoy for some weird reason thinking about that kind of stuff even though we wouldn't actually act on it. It's almost like some weird like I love playing shooter games you know first-person shooters and like especially if it's like murdering zombies and doom you're shooting demons. I play one of my favorite games is Diablo is like slashing through different monsters and the screaming and pain and the hellfire and then I go out into the real world to eat my coconut ice cream and I'm all about love. So like can we trust our ability to visualize how all it all goes to shit as an [/INST] actual rational way of thinking? I think it's a fair question to say to what degree is there just kind of perverse fantasy and morbid exploration and whatever else that happens in our imagination but I don't think that's the whole of it. I think there is also a reality to the combinatorial possibility space and the difference in the probabilities that there's a lot of ways I could try to put the 70 trillion cells of your body together that don't make you. There's not that many ways I can put them together that make you. There's a lot of ways I could try to connect the organs together that make some weird kind of group of organs on the desk but that doesn't actually make a functioning human and you can kill an adult human in a second but you can't get one in a second. It takes 20 years to grow one and a lot of things to happen, right? I could destroy this building in a couple minutes with demolition, but it took a </s><s>[INST] year or a couple years to build it. There is a, there's a, this is just an example. It's not, [/INST] he doesn't mean it. There's a, there's a gradient where entropy is easier. And there's a lot more ways to put a set of things together that don't work than the few that really do produce higher order synergies. And so when we look at a history of war, and then we look at exponentially more powerful warfare. An arms race that drives that in all these directions. And when we look at a history of environmental destruction, and exponentially more powerful tech that makes exponential externalities, multiplied by the total number of agents that are doing it in the cumulative effects. There's a lot of ways the whole thing can break, like a lot of different ways. And for it to get ahead, it has to have none of those happen. And so there's just a probability space where it's easier to imagine that thing. So to say, how do we have a protopic future? We have to say, well, one criteria must be that it avoids all of the catastrophic risks. So can we inventory all the catastrophic risks? Can we inventory the patterns of human behavior that give rise to them? And could we try to solve for that? And could we have that be the essence of the social technology that we're thinking about to be able to guide, bind, and direct a new physical technology? Because so far, our physical technology, like we were talking about the Genghis Khans and like that, that obviously use certain kinds of physical technology and armaments, and also social technology and unconventional warfare for a particular set of purposes. But we have things that don't look like warfare, like Rockefeller and Standard Oil. And it looked like a constructive mindset to be able to bring this new energy resource to the world. And it did. And the second order effects of that are climate change, and all of the oil spills that have happened and will happen, and all of the wars in the Middle East over the oil that had been there, and the massive political clusterfuck and human life issues that are associated with it, and on and on, right? And so, it's also not just the orientation to construct a thing can have a narrow focus on what I'm trying to construct, but be affecting a lot of other things through second and third order effects </s><s>[INST] I'm not taking responsibility for. And you often on another tangent mentioned second, third, and fourth order effects. And the order cascading. Which is really fascinating. Like starting with the third order plus, it gets really interesting. Because we don't even acknowledge like the second order effects. But like thinking, because it could get bigger and bigger and bigger in ways we're not anticipating. So how do we make those, so it sounds like part of the part of the thing that you're thinking through in terms of a solution, how to create an anti-fragile, a resilient society, is to make explicit acknowledge, understand the externalities, the second order, third order, fourth order, and the order effects. How do we start to [/INST] think about those effects? The war application is harm we're trying to cause or that we're aware we're causing? The externality is harm that at least supposedly, we're not aware we're causing, or at minimum, it's not our intention. Maybe we're either totally unaware of it or we're aware of it, but it is a side effect of what our intention is, it's not the intention itself. There are catastrophic risks from both types. the direct application of increased technological power to a rival risk intent, which is going to cause harm for some out-group for some in-group to win. But the out-group is also working on growing the tech, and if they don't lose completely, they reverse engineer the tech, up-regulate it, come back with more capacity. So there's the exponential tech arms race side of in-group out-group rivalry using exponential tech that is one set of risks. And the other set of risks is the application of exponentially more powerful tech, not intentionally to try and beat an out-group, but to try to achieve some goal that we have, but to produce a second and third order effects that do have harm to the commons, to other people, to environment, to other groups that might actually be bigger problems than the problem we were originally trying to solve with the thing we were building. When Facebook was building a dating app and then building a social app where people could tag pictures, they weren't trying to build a democracy-destroying app that would maximize time on site as part of its ad model through AI optimization of a newsfeed to the thing that made people spend most time on site, which is usually them being limbically hijacked more than something else, which ends up appealing to people's cognitive biases and group identities and creates no sense of shared reality. They weren't trying to do that, but it was a second order effect. And it's a pretty fucking powerful second order effect and a pretty fast one because the rate of tech is obviously able to get distributed to much larger scale, much faster, and with a bigger jump in terms of total vertical capacity. And that's what it means to get to the verticalizing part of an exponential curve. So just like we can see that oil had these second order environmental effects and also social and political effects, war and so much of the whole, like the total amount of oil used has a proportionality to total global GDP. And this is why we have the petrodollar and so the oil thing also had the externalities of a major aspect of what happened with military industrial complex and things like that. But we can see the same thing with more current technologies, with Facebook and Google and other things. So I don't think we can run, and the more powerful the tech is, we build it for ReasonX, whatever ReasonX is. Maybe X is three things, maybe it's one thing, right? We're doing the oil thing because we want to make cars because it's a better method of individual transportation. We're building the Facebook thing because we're going to connect people socially in a personal sphere. But it interacts with complex systems with ecologies, economies, psychologies, cultures. And so it has effects on other than the thing we're intending. Some of those effects can end up being negative effects, but because this technology, if we make it to solve a problem, it has to overcome the problem. The problem's been around for a while, it's going to overcome in a short period of time. So it usually has greater scale, greater rate of magnitude in some way. That also means that the externalities that it creates might be bigger problems. And you can say, well, but then that's the new problem and humanity will innovate its way out of that. Well, I don't think that's paying attention to the fact that we can't keep up with exponential curves like that, nor do finite spaces allow exponential externalities forever. And this is why a lot of the smartest people thinking about this are thinking, well, no, I think we're totally screwed unless we can make a benevolent AI singleton that rules all of us. Guys like Bostrom and others thinking in those directions because they're like, how do humans try to do multipolarity and make it work? And I have a different answer of what I think it looks like that does have more to do with </s><s>[INST] the love, but some applied social tech align, align with love, align with love. Because I have a bunch of really dumb ideas I'd prefer to hear less. I'd like to hear some of them first. I think the idea I would have is to be a bit more rigorous in trying to measure the amount of love you add or subtract from the world in second, third, fourth, fifth order effects. It's actually, I think, especially in the world of tech, quite doable. You just might not like, the shareholders may not like that kind of metric, but it's pretty easy to measure. That's not even, I'm perhaps half joking about love, but we could talk about just happiness and well-being, long-term well-being. It's pretty easy for Facebook, for YouTube, for all these companies to measure that. They do a lot of kinds of surveys, they could do, I mean, there's very simple solutions here that you could just survey how, I mean, surveys are in some sense useless because they're a subset of the population, you're just trying to get a sense, it's very loose kind of understanding, but integrated deeply as part of the technology. Most of our tech is recommender systems, most of the, sorry, not tech, online interactions driven by recommender systems that learn very little data about you and use that data, mostly based on traces of your previous behavior to suggest future things. This is how Twitter, this is how Facebook works, this is how AdSense for Google, AdSense works is how Netflix, YouTube work and so on. For them to just track as opposed to engagement, how much you spend on a particular video, a particular site, is also to track, give you the technology to do self-report of what makes you feel good, of what makes you grow as a person, of what makes you the best version of yourself, the Rogan idea of the hero of your own movie and just add that little bit of information. If you have people, you have this like happiness surveys of how you feel about the last five days, how would you report on your experience? You can lay out the set of videos, it's kind of fascinating to work, I don't know if you ever look at YouTube, the history of videos you've looked at, it's fascinating, it's very embarrassing for me. Like, it'll be like a lecture and then like a set of videos that I don't want anyone to know about, which will be like, I don't know, maybe like five videos in a row where it looks like I watched the whole thing, which I probably did, about like how to cook a steak even though or just like with the best chefs in the world cooking steaks and I'm just like sitting there watching it for no purpose whatsoever, wasting away my life or like funny cat videos or like legit, that's always a good one and I could look back and rate which videos made me a better person and not. And I mean, on a more serious note, there's a bunch of conversations, podcasts or lectures I've watched, which made me a better person and some of them made me a worse person. Quite honestly, not for stupid reasons, like I feel dumber, but because I do have a sense that that started me on a path of not being kind to other people. For example, I'll give you for my own, and I'm sorry for ranting, but maybe there's some usefulness to this kind of exploration of self. When I focus on creating, on programming, on science, I become a much deeper thinker and a kinder person to others. When I listen to too many, a little bit is good, but too many podcasts or videos about how our world is melting down or criticizing ridiculous people, the worst of the quote unquote woke, for example, all there's all these groups that are misbehaving in fascinating ways because they've been corrupted by power. The more I watch criticism of them, the worse I become. And I'm aware of this, but I'm also aware that for some reason, it's pleasant to watch those sometimes. And so for me to be able to self report that to the YouTube algorithm, to the systems around me, and they ultimately try to optimize to make me the best version of myself, which I personally believe would make YouTube a lot more money because I'd be much more willing to spend time on YouTube and give YouTube a lot more of my money, that's great for business and great for humanity because it'll make me a kinder person. It'll increase the love quotient, the love metric, and it'll make them a lot of money. I feel like everything is aligned. And so you should do that, not just for YouTube algorithm, but also for military strategy and for whether to go to war or not, because one externality you can think of about going to war, which I think we talked about offline, is we often go to war with kind of governments with, not with the people. You have to think about the kids of countries that see a soldier. And because of what they experience, their interaction with the soldier, hate is born. When you're like eight years old, six years old, you lose your dad, you lose your mom, you lose a friend, somebody close to you, the one really powerful externality that could be reduced to love, positive and negative, is the hate that's born when you make decisions. And that's going to take fruition, that that little seed is going to become a tree that then leads to the kind of destruction that we talk about. So but in my sense, it's possible to reduce everything to a measure of how much love does this add to the world. All that to say, do you have ideas of how we practically build systems that create a resilient society? [/INST] There are a lot of good things that you shared where there's like 15 different ways that we could enter this that are all interesting. </s><s>[INST] So I'm trying to see which one will probably be most useful. Pick the one or two things that are least ridiculous. [/INST] And you were mentioning if we could see some of the second order effects or externalities that we aren't used to seeing, specifically the one of a kid being radicalized somewhere else, which engenders enmity in them towards us, which decreases our own future security. Even if you don't care about the kid, if you care about the kids, the whole other thing. Yeah, I mean, I think when we saw this, when Jane Fonda and others went to Vietnam and took photos and videos of what was happening, and you got to see the pictures of the kids with napalm on them, that like the anti war effort was bolstered by that in a way it couldn't have been without that there's a until we can see the images, you can't have a mirror neuron effect in the same way, and when you can, that starts to have a powerful effect. I think there's a deep principle that you're sharing there, which is that if we can have a rivalrous intent, where our in group, whatever it is, maybe it's our political party wanting to win within the US, maybe it's our nation state wanting to win in a war or an economic war over resource or whatever it is, that if we don't obliterate the other people completely, they don't go away, they're not engendered to like us more, they didn't become less smart. So they have more enmity towards us and whatever technologies we employed to be successful, they will now reverse engineer, make iterations on and come back. And so you drive an arms race, which is why you can see that the wars were over history employing more lethal weaponry, and not just the kinetic war, the information war and the narrative war and the economic war, like it just increased capacity and all of those fronts. And so what seems like a win to us on the short term might actually really produce losses in the long term. And what's even in our own best interest in the long term is probably more aligned with everyone else because we inter affect each other. And I think the thing about globalism, globalization, and exponential tech, and the rate at which we affect each other, and the rate at which we affect the biosphere that we're all affected by is that this kind of proverbial spiritual idea that we're all interconnected and need to think about that in some way that was easy for tribes to get, because everyone in the tribes so clearly saw their interconnection and dependence on each other. but in terms of a global level, the speed at which we are actually interconnected, the speed at which the harm happening to something in Wuhan affects the rest of the world, or a new technology develop somewhere affects the entire world, or an environmental issue, or whatever, is making it where we either actually all get, not as a spiritual idea, just even as physics, right, we all get the interconnectedness of everything in that we either all consider that and see how to make it through more effectively together, Or failures anywhere end up becoming decreased quality of life and failures and increased risk everywhere </s><s>[INST] Don't you think people are beginning to experience that at the individual level? So governments are resisting it they're they're trying to make us not empathize with each other feel connected But don't you think people are beginning to feel more and more connected? Like isn't that exactly what the technology is enabling like social networks. We tend to criticize them, but isn't there a sense which we're [/INST] experience, you know When you watch those videos that are criticizing whether it's the woke Antifa side or the QAnon Trump supporter side Does it seem like they have increased empathy for people that are outside of their ideology camp? </s><s>[INST] Not at all. So I may be I may be conflating my own experience of the world and that of that of the populace I I I tend to see those videos as feeding something. That's a relic of the past. They figured out the drama fuels clicks But whether I'm right or wrong, I don't know but I tend to sense that that is not That hunger for drama is not fundamental to human beings that we want to actually that we want to understand Antifa and we want to like empathize we want to take radical ideas and be able to empathize with them And synthesize it all [/INST] Okay, let's look at cultural outliers in terms of violence versus compassion We can see that a lot of cultures have Relatively lower in-group violence bigger out group violence and there's some variance in them and variance at different times based on the scarcity or abundance of resource and other things but you can look at say Janes Whose whole religion is around? Non-violent so much so that they don't even hurt plants. They only take fruits that fall off them and stuff or to go to a larger population you take Buddhists where for the most part with a few exceptions for the most part across three millennia and Across lots of different countries and geographies and whatever you have 10 million people plus or minus who don't hurt bugs The whole spectrum of genetic variance that is happening within a culture of that many people and head traumas and whatever and nobody hurts bugs and Then you look at a group where the kids grew up as child soldiers in Liberia or Darfur We're to make it to adulthood pretty much. Everybody's killed people hand-to-hand and killed people who were civilian or innocent type of people and you say Okay, so we were very in the oddness we can be conditioned by our environment and humans can be conditioned Where almost all the humans show up in these two different bell curves. It doesn't mean that the Buddhists had no violence it doesn't mean that these people had no compassion, but the they're very different Gaussian distributions and so I think one of the important things that I like to do is look at the examples of the Populations with Buddhism shows regarding compassion or what Judaism shows around education the average level of Education that everybody gets because of a culture that is really working on conditioning it or various cultures What are the positive deviance outside of this statistical deviance to see what is actually possible and then say? What are the conditioning factors and can we condition those across a few of them simultaneously and could we build a civilization like that? becomes a very interesting question, so there's this kind of real politic idea that humans are violent large groups of humans become Violent they become irrational specifically those two things rivalrous and violent and irrational and so in order to minimize the total amount of violence and have some good decisions in need ruled somehow and That not getting that as some kind of naive utopianism that doesn't understand human nature yet This gets back to like mimesis of desire as an inexorable thing I think the idea of the masses is actually a kind of propaganda that is useful for the classes that control to popularize the idea that most people are too violent lazy Undisciplined and irrational to make good choices and Therefore their choices should be sublimated in some kind of way I think that if we look back at these conditioning environments we can say okay, so the kids They go to a really fancy school and have a good developmental environment like Exeter Academy There's still a Gaussian distribution of how well they do on any particular metric but on average they become senators and The worst ones become high-end lawyers or whatever and then I look at an inner city school with a totally different set of things And I see a very very differently displaced Gaussian distribution, but a very different set of conditioning factors So then I say the masses Well if all those kids who were one of the parts of the masses got to go to Exeter and have that family and whatever Would they still be the masses? Could we actually condition more social virtue more? more civic virtue, more orientation towards dialectical synthesis, more empathy, more rationality, widely. Yes. Would that lead to better capacity for something like participatory governance, democracy, or republic, or some kind of participatory governance? Yes. Yes. Is it necessary for it, actually? Yes. And is it good for class interests? No, not really. </s><s>[INST] Oh, by the way, when you say class interests, this is the powerful leading over the less powerful, that kind of idea. [/INST] Anyone that benefits from asymmetries of power doesn't necessarily benefit from decreasing those asymmetries of power and kind of increasing the capacity of people more widely and so when we talk about power, we're talking about </s><s>[INST] asymmetries in agency, influence, and control. Do you think that hunger for power is fundamental to human nature? I think we should get that straight before we talk about other stuff. So like this this pickup line that I use at a bar office, which is power corrupts and absolute power corrupts. Absolutely. Is that true or is that just a fancy thing to say? In modern society, there's something to be said, have we changed as societies over time? [/INST] In terms of how much would crave power? That there is an impulse towards power that is innate in people and can be conditioned one way or the other, yes. But you can see that Buddhist society does a very different thing with it at scale. That you don't end up seeing the emergence of the same types of sociopathic behavior and particularly then creating sociopathic institutions. And so it's like is eating the foods that were rare in our evolutionary environment to give us more dope mean hit because they were rare and they're not anymore, salt, fat, sugar. Is there something pleasurable about those where humans have an orientation to overeat if they can? Well, the fact that there is that possibility doesn't mean everyone will obligately be obese and die of obesity, right? Like it's possible to have a particular impulse and to be able to understand it, have other ones and be able to balance them. And so to say that power dynamics are, are obligate in humans and we can't do anything about it is very similar to me to saying like we could, everyone is going to be obligately obese. </s><s>[INST] Yeah, so there's some degree to which those, the control of those impulses has to do with the conditioning early in life. [/INST] Yes, and the culture that creates the environment to be able to do that and then the recursion on that. </s><s>[INST] Okay, so what if we were to bear with me, just asking for a friend, if we're to kill all humans on Earth and then start over, is there ideas about how to build up? Okay, we don't have to kill it, let's leave the humans on Earth, they're fine and go to Mars and start a new society. Is there ways to construct systems of conditioning, education, of how we live with each other that would that would incentivize us to do that? With each other that would that would incentivize us properly to not seek power, to not construct systems that are of asymmetry of power and to create systems that are resilient to all kinds of terrorist attacks to all kinds of destructions? I believe so. So is there some inklings we can, of course, you probably don't have the all the answers, but you have insights about what that looks like. I mean, is it just rigorous practice of dialectic synthesis as essentially conversations with assholes of various flavors until they're not assholes anymore because you become deeply empathetic with their experience? [/INST] Okay, so there's a lot of things that we would need to construct to come back to this, like what is the basis of rivalry? What how do you bind it? How does it relate to tech? If you have a culture that is doing less rivalry, does it always lose in war to those who do war better? And how do you make something on the enactment of how to get there from here? </s><s>[INST] Great, great. So what's rivalry? Why is rivalry bad or good? So is another word for rivalry competition? [/INST] Yes, I think, roughly, yes, I think bad and good are kind of silly concepts here. Good for some things, bad for other things, for some contexts and others, even that. </s><s>[INST] Let me give you an example that relates back to the Facebook measuring thing you were mentioning a moment ago. [/INST] First, I think what you're saying is actually aligned with the right direction and what I want to get to in a moment. But it's not the devil is in the details here. </s><s>[INST] So I enjoy praise, it feeds my ego, I grow stronger. So I appreciate that. [/INST] I will make sure to include one piece every 15 minutes as we go. Thank you. So it's easier to measure their problems with this argument, but there's also utility to it. So let's take it for the utility it has first. It's harder to measure happiness than it is to measure comfort. We can measure with technology that the shocks in a car are making the car bounce less that the bed is softer and material science and those types of things. And happiness is actually hard for philosophers to define because some people find that there's certain kinds of overcoming suffering that are necessary for happiness. There's happiness, it feels more like contentment and happiness, it feels more like passion. and is passion the source of all suffering or the source of all creativity? Like there's deep stuff and it's mostly first-person, not measurable third-person stuff, even if maybe it corresponds to third-person stuff to some degree, but we also see examples of some of our favorite examples as people who are in the worst environments who end up finding happiness, right? Where the third-person stuff looks to be less conducive and there's some, Victor Frankel, Nelson Mandela, whatever. But it's pretty easy to measure comfort and it's pretty universal. And I think we can see that the Industrial Revolution started to replace happiness with comfort quite heavily as the thing it was optimizing for. And we can see that when increased comfort is given, maybe because of the evolutionary disposition that expending extra calories, when for the majority of our history, we didn't have extra calories was not a safe thing to do. Who knows why? When extra comfort is given, it's very easy to take that path, even if it's not the path that supports overall well-being longterm. And so we can see that, when you look at the techno-optimist idea that we have better lives than Egyptian pharaohs and kings and whatever, what they're largely looking at is how comfortable our beds are and how comfortable the transportation systems are and things like that, in which case is massive improvement. But we also see that in some of the nations where people have access to the most comfort, suicide and mental illness are the highest. And we also see that some of the happiest cultures are actually some of the ones that are in materially lame environments. And so there's a very interesting question here, and if I understand correctly, you do cold showers. And Joe Rogan was talking about how he needs to do some fairly intensive kind of struggle that is a non-comfort to actually induce, being better as a person, this concept of hormesis, that it's actually stressing an adaptive system that increases its adaptive capacity, and that there's something that the happiness of a system has something to do with its adaptive capacity, its overall resilience, health, well-being, which requires a decent bit of discomfort. Yet in the presence of the comfort solution, it's very hard to not choose it, and then as you're choosing it regularly to actually down-regulate your overall adaptive capacity. And so when we start saying, can we make tech where we're measuring for the things that it produces beyond just the measure of GDP or whatever particular measures look like the revenue generation or profit generation of my business, are all the meaningful things measurable, and what are the right measures? And what are the externalities of optimizing for that measurement set? What meaningful things aren't included in that measurement set that might have their own externalities? These are some of the questions we actually have to take seriously. </s><s>[INST] Yeah. Yeah. And I think they're answerable questions, right? Progressively better, not perfect. Right. So first of all, let me throw out happiness and comfort out of the discussion, those seem like useless. The distinction, so I, because I said they're useful, well-being is useful, but I think I take it back. I propose new metrics in this brainstorm session, which is, so one is like personal growth, which is intellectual growth. I think we're able to make that concrete for ourselves. Like, you're a better person than you were a week ago, or a worst person than you were a week ago. I think we can ourselves report that and understand what that means. It's this gray area, and when you try to define it, but I think we humans are pretty good at that because we have a sense, an idealistic sense of the person we might be able to become. We we all dream of becoming a certain kind of person. And I think we have a sense of getting closer and not towards that person. Maybe this is not a great metric, fine. The other one is love, actually. Fuck if you're happy or not, or you're comfortable or not. How much love do you have towards your fellow human beings? I feel like if you try to optimize that and increasing that, that's going to have, that's a good metric. How many times a day, sorry, if I can make quantify, how many times a day have you thought positively of another human being? Just put that down as a number and increase that number. [/INST] I think the process of saying, okay, so let's not take GDP or GDP per capita as the metric we want to optimize for because GDP goes up during war and it goes up with more healthcare spending from sicker people and various things that we wouldn't say correlate to quality of life. </s><s>[INST] Addiction drives GDP awesomely. By the way, when I said growth, I wasn't referring to GDP. [/INST] I know, I'm giving an example now of the primary metric we use and why it's not an adequate metric because we're exploring other ones. So the idea of saying, what would the metrics for a good civilization be? If I had to pick a set of metrics, what would the best ones be if I was gonna optimize for those? And then really try to run the thought experiment more deeply and say, okay, so what happens if we optimize for that? Try to think through the first and second and third order effects of what happens, it's positive. And then also say what negative things can happen from optimizing that? What actually matters that is not included that or in that way of defining it because love versus number of positive thoughts per day. I could just make a long list of names and just say positive thing about each one. It's all very superficial. Not include animals or the rest of life have a very shallow total amount of it, but I'm optimizing the number and if I get some credit for the number. And this is when I said the model of reality isn't reality. When you make a set of metrics, they were going to optimize for this. Whatever reality is that is not included in those metrics can be the areas where harm occurs, which is why I would say that wisdom is something like the discernment that leads </s><s>[INST] to right choices beyond what metrics based optimization would offer. Yeah, but another way to say that is wisdom is constantly expanding and evolving set of metrics. [/INST] Which means that there is something in you that is recognizing a new metric. It's important that isn't part of that metric set. So there is a certain kind of connection, discernment, awareness. And this is- This iterative game theory. There's a girdles in completeness theorem, right? Which is if the set of things is consistent, it won't be complete. So we're going to keep adding to it, which is why we were saying earlier, I don't think </s><s>[INST] it's not beautiful. [/INST] This iterative game theory. And especially if you were just saying one of the metrics you want to optimize for at the individual level is becoming, right? That we're becoming more. Well, that then becomes true for the civilization and our metric sets as well. our definition of how to think about a meaningful life and a meaningful civilization. I can tell you what some of my favorite metrics are. What's that? Well, love is obviously not a metric. It's like you could bench. Yeah, it's a good metric. Yeah. I want to optimize that across the entire population, starting with infants. So in the same way that love isn't a metric, but you could make metrics look at certain parts of it. The thing I'm about to say isn't a metric, but it's a consideration. Because I thought about this a lot. I don't think there is a metric, a right one. I think that every metric by itself without this thing we talked about of the continuous improvement becomes a paperclip maximizer. I think that's why what the idea of false idol means in terms of the model of reality not being reality, then my sacred relationship is to reality itself, which also binds me to the unknown forever. To the known, but also to the unknown. And there's a sense of sacredness connected to the unknown that creates an epistemic humility that is always seeking not just to optimize the thing I know, but to learn new stuff and to be open to perceive reality directly. So my model never becomes sacred. My model is useful. So the model can't be the false idol. Correct. And this is why the first verse of the Tao Te Ching is the Tao that is nameable is not the eternal Tao. The naming then can become the source of the 10,000 things that if you get too carried away with it can actually </s><s>[INST] obscure you from paying attention to reality beyond the models. It sounds a lot like Steven Wolfram, but in a different language, much more poetic. I can imagine that. No, I'm referring. I'm joking. But there's echoes of cellular automata, which you can't name. You can't construct a good model cellular automata. You can only watch in awe. I apologize. I'm distracting your train of thought horribly and miserably making a difference. By the way, something robots aren't good at and dealing with the uncertainty of uneven ground. You've been okay so far. You've been doing wonderfully. So what's your favorite metrics? That's why I know [/INST] you're not a robot. That's why I know you're not a robot. So one metric, and there are problems with this, but one metric that I like to just as a thought experiment to consider is because you're actually asking, I mean, I know you ask your guests about the meaning of life because ultimately when you're saying what is a desirable civilization, you can't answer that without answering what is a meaningful human life and to say what is a good civilization because it's going to be in relationship to that, right? And then you have whatever your answer is. How do you know? What </s><s>[INST] is the epistemic basis for postulating that? There's also a whole other reason for asking that question. I mean, that doesn't even apply to you whatsoever, which is it's interesting how few people have been asked questions like it. We joke about these questions as silly, right? It's funny to watch a person, and if I was more of an asshole, I would really stick on that question, right? It's a silly question in some sense, but like we haven't really considered what it means just a more concrete version of that question is what is a better world? What is the kind of world [/INST] we're trying to create? Really? Have you really thought? I'll give you some kind of simple answers to that that are meaningful to me, but let me do the societal indices first because they're fun. We should take a note of this meaningful thing because it's important to come back to. </s><s>[INST] Are you reminding me to ask you about the meaning of life? Noted. [/INST] Let me jot that down. Because I think I stopped tracking it like 25 open threads. Okay. Let it all burn. One index that I find very interesting is the inverse correlation of addiction within the society. The more a society produces addiction within the people in it, the less healthy I think the society is as a pretty fundamental metric. And so the more the individuals feel that there are less compulsive things in compelling them to behave in ways that are destructive to their own values. And insofar as a civilization is conditioning and influencing the individuals within it, the inverse of addiction. Probably defined. Correct. Compulsive behavior that is destructive towards things that we value. Yeah. I think that's a very interesting one to think about. That's a really interesting one, yeah. And this is then also where comfort and addiction start to get very close. And the ability to go in the other direction from addiction is the ability to be exposed to hypernormal stimuli and not go down the path of desensitizing to other stimuli and needing that hypernormal stimuli, which does involve a kind of hormesis. So I do think the civilization of the future has to create something like ritualized discomfort. And ritualized discomfort. Yeah. I think that's what the sweat lodge and the vision quest and the solo journey and the ayahuasca journey and the Sundance were. I think it's even a big part of what yoga asana was, is to make beings that are resilient and strong, they have to overcome some things. To make beings that can control their own mind and fear, they have to face some fears. But we don't want to put everybody in war or real trauma. And yet we can see that the most fucked up people we know had childhoods of a lot of trauma. But some of the most incredible people we know had childhoods of a lot of trauma, whether or not they happen to make it through and overcome that or not. So how do we get the benefits of the stealing of character and the resilience and the whatever that happened from the difficulty without traumatizing people, a certain kind of ritualized discomfort that not only has us overcome something by ourselves, but overcome it together with each other where nobody bails when it gets hard because the other people are there. So it's both a resilience of the individuals and a resilience of the bonding. So I think we'll keep getting more and more comfortable stuff, but we have to also develop resilience in the presence of that for the anti-addiction direction and the fullness of </s><s>[INST] character and the trustworthiness to others. You have to be consistently injecting discomfort into the system, ritualize. I mean, this sounds like you have to imagine Sisyphus happy. You have to imagine Sisyphus with his rock, optimally resilient from a metrics perspective in society. [/INST] So we want to constantly be throwing rocks at ourselves. Not constantly. You didn't have to- Frequently. Periodically. Periodically. And there's different levels of intensity, different periodicities. Now, I do not think this should be imposed by states. I think it should emerge from cultures. And I think the cultures are developing people that understand the value of it. So the people, so there is both a cultural cohesion to it, but there's also a voluntaryism because the people value the thing that is being developed </s><s>[INST] to understand it. Periodically. And that's where conditioning. So conditioning is conditioning [/INST] some of these values and- Conditioning is a bad word because we like our idea of sovereignty, but when we recognize the language that we speak and the words that we think and the patterns of thought built into that language and the aesthetics that we like and so much is conditioned in us, just based on where we're born, you can't not condition people. So all you can do is take more responsibility for what the conditioning factors are, and then you have to think about this question, of what is a meaningful human life? Because we're unlike the other animals born into an environment that they're genetically adapted for. We're building new environments that we are not adapted for, and then we're becoming affected by those. Then we have to say, well, what kinds of environments, digital environments, physical environments, social environments, would we want to create that would develop the healthiest, happiest, most moral, noble, meaningful people? What are even those sets of things that matter? So you end up getting deep existential consideration at the heart of civilization design when you start to realize how powerful we're becoming and how much </s><s>[INST] What we're building it in service towards matters before I pull it I think three threads you just laid down is there another metric index a year [/INST] I'll tell you one more that I tell you one more that I really like there's a there's a number But the one then the next one that comes to mind is I have to make a very quick model healthy human bonding Say we were in a tribal type setting my positive emotional states and your positive emotional states would most of the time be corollated your negative emotional states in mind and so you start laughing I start laughing you start crying my eyes might tear up and We would call that the compassion Compersion axis I would this is a model life I find useful So compassion is when you're feeling something negative. I feel some pain. I feel some empathy something in relationship Compersion is when you do well, I'm stoked for you, right? Like I actually feel happiness at your happiness. I like compersion. Yeah, the fact that it's such an uncommon word in English </s><s>[INST] is actually a problem culturally. Cause I feel that often and I think that's a really good [/INST] feeling to feel and maximize for actually. That's actually the metric I'm going to say is the compassion compersion access is the thing I would optimize for. Now there is a state where my emotional states and your emotional states are just totally decoupled. And that is like sociopathy. I don't want to hurt you, but I don't care if I do or for you to do well or whatever. But there's a worst state and it's extremely common which is where they're inversely coupled. Where my positive emotions correspond to your negative ones and vice versa. And that is the, I would call it the jealousy sadism axis. The jealousy axis is when you're doing really well, I feel something bad. I feel taken away from less than upset, envious, whatever. And that's so common. But I think of it as kind of a low grade psychopathology that we've just normalized. The idea that I'm actually upset at the happiness or fulfillment or success of another is like a profoundly fucked up thing. No, we shouldn't shame it and repress it so it gets worse. We should study it. Where does it come from? And it comes from our own insecurities and stuff. But then the next part that everybody knows is really fucked up is just on the same axis. It's the same inverted, which is to the jealousy or the envy is the I feel badly when you're doing well. The sadism side is I actually feel good when you lose, or when you're in pain I feel some happiness that's associated and you can see when someone feels jealous, sometimes they feel jealous with a partner and then they feel they want that partner to get it, revenge comes up or something. So sadism is really like jealous is one step on the path sadism from the healthy compassion-compersion axis. So, I would like to see a society that is inversely, that is conditioning sadism and jealousy inversely, right? The lower that amount and the more the compassion-compersion. And if I had to summarize that very simply, I'd say it would optimize for compersion, which is, because notice, that's not just saying love for you, where I might be self-sacrificing and miserable and I love people, but I kill myself, which I don't think anybody thinks a great idea, or happiness, where I might be sociopathically happy, where I'm causing problems all over the place, or even sadistically happy, but it's a coupling, right? That I'm actually feeling happiness in relationship to yours, and even in causal relationship, where my own agentic desire to get happier wants to support </s><s>[INST] you too. That's actually, speaking of another pickup line, that's quite honestly what I... This is a guy who's single. This is going to come out very ridiculous, because it's like, oh yeah, where's your girlfriend, bro? But, oh yeah, that's what I look for in a relationship, because it's such an amazing life, where you actually get joy from another person's success, and they get joy from your success, and then it becomes like, you don't actually need to succeed much for that to have a cycle of just happiness that just increases exponentially. It's weird, so just enjoying the happiness of others, the success of others. The first person that drilled this into my head is Rogan. Joe Rogan. He is the embodiment of that, because I saw somebody who is successful, rich, and non-stop. I mean, you could tell when somebody's full of shit and somebody's not, really genuinely enjoying the success of his friends. That was weird to me. That was interesting, and I mean, the way you're kind of speaking to it, the reason Joe stood out to me is I guess I haven't witnessed genuine expression of that often in this culture, of just real joy for others. I mean, part of that has to do, there hasn't been many channels where you can watch or listen to people being their authentic selves, so I'm sure there's a bunch of people who live life with compassion. They probably don't seek public attention also, but yeah, if there was any word that could express what I've learned from Joe, why he's been a really inspiring figure is that of a comparison, and I wish our world had a lot more of that. Sorry to go on a small tangent, but you're speaking how society should function, but I feel like if you optimize for that metric in your own personal life, you're going to live a truly fulfilling life. I don't know what the right word to use, [/INST] but that's a really good way to live life. You will also learn what gets in the way of it and how to work with it, that if you wanted to help try to build systems at scale or apply Facebook or exponential technologies to do that, you would have more actual depth of real knowledge of what that takes. And this is, as you mentioned, that there's this virtuous cycle between when you get stoked on other people doing well, and then they have a similar relationship to you, and everyone is in the process of building each other up. And this is what I would say, the healthy version of competition is versus the unhealthy version. The healthy version, right, the root, I believe it's a Latin word that means to strive together. And it's that impulse of becoming where I want to become more, but I recognize that there's actually a hormesis. There's a challenge that is needed for me to be able to do that. But that means that yes, there's an impulse where I'm trying to get ahead, And maybe I'm even trying to win, but I actually want a good opponent. And I want them to get ahead too, because that is where my ongoing becoming happens and the win itself will get boring very quickly. The ongoing becoming is where there's aliveness and for the ongoing becoming, they need to have it too. And that's the strive together. The, so in the healthy competition, I'm stoked when they're doing really well, because my becoming is supported by it. Now this is actually a very nice segue into a model I like about what a meaningful human life is. If you want to go there. </s><s>[INST] Let's go there. We can go to some point. I have three things I'm going elsewhere with, but if we were first let us take this short stroll through the park of the meaning of life, Daniel. Uh, what is the meaningful life? [/INST] I think, um, The semantics ended up mattering. Cause a lot of people will take the word meaning and the word purpose almost interchangeably and they'll talk, uh, they'll think kind of, what is the meaning of my life? What is the meaning of human life? What is the meaning of life, what's the meaning of the universe and what is the meaning of existence rather than non-existent so there's a lot of kind of existential considerations there. And I think there's some cognitive mistakes that are very easy like taking the idea of purpose, which is like a goal. It is utilitarian concept. The purpose of one thing is defined in relationship to other things that have assumed value. And to say what is the purpose of everything well, it's a purpose is too it's fundamentally a relative question within everything, what is the purpose of one thing relative to another? What is the purpose of everything? And there's nothing outside of it with which to say it, you actually just got to the limits of the utility of the concept of purpose. It doesn't mean it's purposeless in the sense of something inside of it being purposeless it means the concept is too small, which is why you end up getting to, you know, like in Daoism talking about the nature of it, rather the... there's a fundamental what, where the why can't go deeper is the nature of it. But I'm going to try to speak to a much simpler part, which is when people think about what is a meaningful human life, and kind of if we were to optimize for something at the level of individual life, but also, how does optimizing for this at the level of the individual life lead to the best society for in so far as people living that way affects others and long term the world as a whole? And how would we then make a civilization that was trying to think about these things? Because you can see that there are a lot of dialectics, where there's value on two sides, individualism and collectivism or the ability to accept things and the ability to push harder and whatever. And there's failure modes on both sides. And so when you're starting to say, okay, individual happiness, you're like, wait, fuck, sadists can be happy while hurting people. It's not individual happiness, it's love. But wait, some people can self sacrifice out of love in a way that actually ends up just creating codependency for everybody. Or, okay, so, so how do we think about all those things together? One, like, this kind of came to me as a simple way that I kind of relate to it is that a meaningful life involves the mode of being, the mode of doing and the mode of becoming. And it involves a virtuous relationship between those three. And that any of those modes on their own, also have failure modes that are not a meaningful life. The mode of being, the way I would describe it, if, if we're talking about the essence of it is about taking in and appreciating the beauty of life, that is now to mode that is in the moment, and that is largely about being with what is. It's fundamentally grounded in the nature of experience and the meaningfulness of experience, the prima facia meaningfulness of when I'm having this experience, I'm not actually asking what the meaning of life is. I'm actually full of it. I'm full of experiencing it. </s><s>[INST] The momentary experience, the life action. [/INST] Yes, so taking in the beauty of life. Doing is adding to the beauty of life. I'm going to produce some art, I'm going to produce some technology that will make life easier, more beautiful for somebody else. I'm going to do some science that will end up leading to better insights or other people's ability to appreciate the beauty of life more because they understand more about it or whatever it is, or protect it, right? I'm gonna protect it in some way. So that's adding to, or being in service of the beauty of life through our doing. And becoming is getting better at both of those, being able to deepen our being, which is to be able to take in the beauty of life more profoundly, be more moved by it, touched by it and increasing our capacity with doing to add to the beauty of life more. And so I hold that a meaningful life has to be all three of those. where they're not in conflict with each other, ultimately it grounds in being, it grounds in the intrinsic meaningfulness of experience. And then my doing is ultimately something that will be able to increase the possibility of the quality of experience for others. And my becoming is a deepening on those. So, it grounds in experience and also the evolutionary possibility of experience. </s><s>[INST] And the point is to oscillate between these, never getting stuck on any one. Yeah. Or I suppose in parallel, well, you can't really, attention is a thing. You can only allocate attention. [/INST] I want moments where I am absorbed in the sunset and I'm not thinking about what to do next. And then the fullness of that can make it to where my doing doesn't come from what's in it for me. Because I actually feel overwhelmingly full already. And then it's like, how can I make life better for other people that don't have as much opportunities I had? How can I add something wonderful? How can I just be in the creative process? And so I think where the doing comes from matters. And if the doing comes from a fullness of being, it's inherently going to be paying attention to externalities, or it's more oriented to do that than if it comes from some emptiness that is trying to get full in some way that is willing to cause sacrifices other places, and where a chunk of its attention is internally focused. And so, when Buddha said desire is the cause of all suffering, then later the vow of the bodhisattva, which was to show up for all sentient beings in universe forever, is a pretty intense thing like desire. I would say there's a kind of desire, if we think of desire as a basis for movement, like a flow or a gradient, there's a kind of desire that comes from something missing inside, seeking fulfillment of that in the world. That ends up being the cause of actions that perpetuate suffering. But there's also not just nondesire, there's a kind of desire that comes from feeling full, at the beauty of life and wanting to add to it, that is a flow, this direction. And I don't think that is the cause of suffering. I think that is, you know, and the western traditions, right? The eastern traditions focused on that and kind of unconditional happiness outside of in the moment outside of time. Western tradition said, no, actually desire is the source of creativity. And we're here to be made in the image, and likeness of the Creator, we're here to be fundamentally creative but creating from where and in service of what creating from a sense of connection to everything and homeless in service of the well-being of all of it is very </s><s>[INST] different which is back to that compassion-compersion axis. Being, doing, becoming it's pretty powerful also could potentially be algorithmatized into a robot just saying where does um where does death come into that? Being is forgetting I mean the the concept of time completely there's a there's a sense of doing and becoming that has a deadline and built in the urgency built in do you think death is fundamental to this to a meaningful life uh acknowledging or um feeling the terror of death like Ernest Becker or just acknowledging the uncertainty the mystery the the melancholy nature of the fact that the right ends is that part of this equation or it's not necessary. [/INST] Okay look at how it could be related. I've experienced fear of death. I've also experienced times where I thought I was going to die. It felt extremely peaceful and beautiful and um it's funny because if we we can be afraid of death because we're afraid of hell or battery incarnation or the bardo or some kind of idea of the afterlife we have or we're projecting some kind of sentient suffering but if we're afraid of just non-experience I notice that every time I stay up late enough that I'm really tired I'm longing for deep deep sleep and non-experience right like I'm actually longing for experience to stop and it's not morbid it's not a bummer it's and and I don't mind falling asleep and I sometimes when I wake up want to go back into it and then when it's done I'm happy to come out of it so um when we think about death and having finite time here and we could talk about if we live for a thousand years instead of a hundred or something like that it'll be finite time the one bummer with the age we die is that I generally find that people mostly start to emotionally mature just shortly before they die um but um there's if I get to live forever I can just stay focused on what's in it for me forever and if life continues and consciousness and sentience and people appreciating beauty and adding to it and becoming continues my life doesn't but my life can have effects that continue well beyond it then life with a capital L starts mattering more to me than my life my life gets to be a part of and in service to and the whole thing about when old men plant trees the shade of which they'll never get to be in um I remember the first time I read this poem by Hafez the Sufi poet written in like 13th century or something like that and he talked about that if you're lonely to think about him and he was kind of leaning his spirit um into years across the distance of a millennium and would come for you with these poems and I was thinking about people millennium from now and caring about their experience and what they'd be suffering if they'd be lonely and could he offer something that could touch them? And it's just fucking beautiful. And so, like, the most beautiful parts of humans have to do with something that transcends what's in it for me. And death forces you to that. </s><s>[INST] So not only does death create the urgency, it, urgency of doing, you're very right, it does have a sense in which it incentivizes the compassion and the compassion. [/INST] Mm-hmm. And the widening, you remember Einstein had that quote something to the effect of it's an optical delusion of consciousness to believe there are separate things. There's this one thing we call universe and something about us being inside of a prison of perception that can only, you know, see a very narrow little bit of it. But this might be just some weird disposition of mine. But when I think about the future after I'm dead, and I think about consciousness, I think about young people falling in love for the first time and their experience, and I think about people being awed by sunsets, and I think about all of it, right? I can't not feel connected </s><s>[INST] to that. Do you feel some sadness to the very high likelihood that you'll be forgotten completely by all of human history? You, Daniel, the name that, that which cannot be named? [/INST] Systems like to self perpetuate. Ego's do that. The idea that I might do something meaningful that future people appreciate, of course, there's like a certain sweetness to that idea. But I know how many people did something, did things that I wouldn't be here without, and that my life would be less without, whose names I will never know. And I feel a gratitude to them. I feel a closeness. I feel touched by that. And I think to the degree that the future people are conscious enough, there is a, you know, a lot of traditions had this kind of, are we being good ancestors and respect for the ancestors beyond the names? I think that's a very healthy idea. </s><s>[INST] But let me return to a much less beautiful and much less pleasant conversation. You mentioned prison. Back to x risk. Okay. And conditioning. You mentioned something about the state. So what role, let's talk about companies, governments, parents, all the mechanisms that can be a source of conditioning, which flavor of ice cream do you like? Do you think the state is the right thing for the future? So governments that are elected democratic systems that are representing representative democracy? Is there some kind of political system of governance that you find appealing? Is it parents? Meaning a very close knit tribes of conditioning. That's the most essential. And then you and Michael Malice would happily agree that it's anarchy or the state should be dissolved or destroyed or burned to the ground if you're Michael Malice giggling, um, holding the torch as the fire burns. So which, which is it? Is the state, can state be good? Or is the state bad for the condition of a beautiful world? A or B? [/INST] This is like an essay test. You like to give these a simplified good or bad things. Um, what I like the state that we live in currently, the United States federal government to stop existing today. No, I would really not like that. Um, I think that'd be not quite bad for the world in a lot of ways. Uh, do I think that it's a optimal social system and maximally just and humane and all those things. And I wanted to continue as is no, also not that. Um, but I am much more interested in it being able to evolve to a better thing without going through, um, the catastrophe phase that I think it's just non existence would give. </s><s>[INST] So what size of state is good in a sense? Like do we, should we, as a human society, as this world becomes more globalized, should we be constantly striving to reduce the set? We can, we can put on a map like right now, literally, like the, the, the centers of power in the world. Some of them are tech companies. Some of them are governments. Should we be trying to, as much as possible, decentralize the power to where it's very difficult to point on the map, the centers of power. And that means making the state, however, there's a bunch of different ways to make the government much smaller. That could be reducing in the United States, reducing the, the funding for the government, all those kinds of things. There's set of responsibilities, the, the set of powers. It could be, I mean, this is far out, but making more nations or maybe nations, not in the space that are defined by geographic location, but rather in the space of ideas, which is what anarchy is about. So anarchy is about forming collectives based on their set of ideas and doing so dynamically, not based on where you were born and so on. [/INST] I think we can say that the natural state of humans, if we want to describe such a thing, was to live in tribes that were below the Dunbar number, meaning that for a few hundred thousand years of human history, all of the groups of humans mostly stayed under that size. And whenever it would get up to that size, it would end up cleaving. And so it seems like there's a pretty strong, but there weren't individual humans out in the wild doing really well, right? So we were a, a group animal, but with groups that had a specific size. So we could say, in a way, humans were being domesticated by those groups. They were learning how to have certain rules to participate with the group without which you'd get kicked out, but that, that's still the wild </s><s>[INST] state of people. And, and maybe it's useful to do as a side statement, which I've recently looked at a bunch of papers around Dunbar's number, where the mean is actually 150. If you actually look at the original paper, it's a range. It's really a range. So it's actually some, somewhere under a thousand. So it's a range of like two to 500 or whatever it is. But like, you could argue that the, I think it actually is exactly two, two, the range is two to 520, something like that. And this is the mean that's taken crudely. It's not a very good paper, the, the, in terms of the actual numerical, numerically speaking. But it'd be interesting if there's a bunch of Dunbar numbers that could be computed for particular environments, particular conditions, so on. It is very true that they're likely to be something small, you know, under a million, but it'd be interesting if we can expand that number in interesting ways that will change the fabric of this conversation. I just want to kind of throw that in there. I don't know if the one fifties baked in somehow in the heart into the hardware. [/INST] We can talk about some of the things that it probably has to do with up to a certain number of people. And this is going to be variable based on the social technologies that mediate it to some degree. We can talk about that in a minute. Up to a certain number of people, everybody can know everybody else pretty intimately. So let's go ahead and just take 150 as a, as an average number. Everybody can know everyone intimately enough that if your actions made anyone else do poorly, it's your extended family, and you're stuck living with them, stuck living with them, and you know who they are. And there's no anonymous people. There's no just them and over there. And that's one part of what leads to a kind of tribal process where what's good for the individual and good for the whole has a coupling. Also below that scale, everyone is somewhat aware of what everybody else is doing. There's not groups that are very siloed. And as a result, it's actually very hard to get away with bad behavior. There's a forced kind of transparency. And so you don't need kind of like the state in, in that way. But lying to people doesn't actually get you ahead. Sociopathic behavior doesn't get you ahead because it gets seen. And so there's a conditioning environment where the individuals behaving in a way that is aligned with the interest of the tribe is what gets conditioned. When it gets to be a much larger system, it becomes easier to hide certain things from the group as a whole as well as to be less emotionally bound to a bunch of anonymous people. I would say there's also a communication protocol where up to about that number of people, we could all sit around a tribal council and be part of a conversation around a really big decision. Do we migrate? Do we not migrate? Do we, you know, some, something like that? Do we get rid of this person? And why, why would I want to agree to be a part of a larger group where everyone can't be part of that council and so I am going to now be subject to law that I have no say in. If I could be part of a smaller group, they could still survive and I get a say in the law that I'm subject to. So I think the cleaving, and a way we can look at it beyond the Dunbar number two is we can look at that a civilization has binding energy that is holding them together and has cleaving energy. And if the binding energy exceeds the cleaving energy that civilization will last. And so, there are things that we can do to decrease the cleaving energy within the society, things we can do to increase the binding energy. I think, naturally, we saw that had certain characteristics up to a certain size kind of tribalism. That ended with a few things. It ended with people having migrated enough that, when you started to get resource wars, you couldn't just migrate away easily. And so, tribal warfare became more obligated. It involved the plow in the beginning of real economic surplus. So there were a few different kind of forcing functions. But we're talking about what size should it be, right? What size should a society be? And I think the idea, like if we think about your body for a moment as a self-organizing complex system that is multi-scaled, we think about- Our body is a wonderland. </s><s>[INST] Our body is a wonderland, yeah. You have- That's a John Mayer song, I apologize. But yes, so if you think about our body and the [/INST] billions of cells that are in it. Well, you don't have, like think about how ridiculous it would be to try to have all the tens of trillions of cells in it with no internal organization structure, right? Just like a sea of protoplasm. It would work. Pure democracy. And so you have cells and tissues, and then you have tissues and organs and organs and organ systems, and so you have these layers of organization, and then obviously the individual and a tribe in a ecosystem. And each of the higher layers are both based on the lower layers, but also influencing them. I think the future of civilization will be similar, which is there's a level of governance that happens at the level of the individual. My own governance of my own choice. I think there's a level that happens at the level of a family. We're making decisions together, inter influencing each other and affecting each other taking responsibility for the idea of an extended family. And you can see that like for a lot of human history, we had an extended family, we had a local community, a local church or whatever it was, we had these intermediate structures, whereas right now, there's kind of like the individual producer consumer taxpayer voter, and the massive nation state global complex, and not that much in the way of intermediate structures that we relate with and not that much in the way of real personal dynamics, all all impersonalized made fungible. And so I think that we have to have global governance, meaning I think we have to have governance at the scale we affect stuff, and if anybody is messing up the oceans that matters for everybody so that can't only be national or only local. Everyone is scared of the idea of global governance because we think about some top-down system of imposition that now has no checks and balances on power, I'm scared of that same version. So I'm not talking about that kind of global governance. It's why I'm even using the word governance as a process rather than government as an imposed phenomena. And so I think we have to have global governance, but I think we also have to have local governance and there has to be relationships between them that each where there are both checks and balances in power flows of information. So I think governance at the level of cities will be a bigger deal in the future than governance at the level of nation states. I think nation states are largely fictitious things that are defined by wars and agreements to stop wars and like that. I think cities are based on real things that will keep being real. We're the proximity of certain things together. The physical proximity of things together gives increased value of those things. So you look at like Jeffery West's work on scale and finding that companies and nation states and things that have a kind of complicated agreement structure get diminishing return production per capita as the total number of people increases beyond about the tribal scale, but the city actually gets increasing productivity per capita, but it's not designed. It's kind of this organic thing, right? So there should be governance at the level of cities because people can sense and actually have some agency there, probably neighborhoods and smaller scales within it and also verticals, and some of it won't be geographic. It'll be network-based, right? Networks of affinities. So I don't think the future is one type of governance. Now, what we can say more broadly is, say, when we're talking about groups of people that inter-effect each other, the idea of a civilization is that we can figure out how to coordinate our choice-making to not be at war with each other and hopefully increase total productive capacity in a way that's good for everybody. Division of labor and specialties, so we all get more better stuff and whatever. But it's a coordination of our choice-making. I think we can look at civilizations failing on the side of not having enough coordination of choice-making. So they fail on the side of chaos, and then they cleave and an internal war comes about or whatever, or they can't make smart decisions and they overuse their resources or whatever. Or it can fail on the side of trying to get order via imposition, via force. And so it fails on the side of oppression, which ends up being for a while functional-ish for the thing as a whole, but miserable for most people in it until it fails either because of revolt or because it can't innovate enough or something like that. And so there's this like toggling between order via oppression and chaos. And I think the idea of democracy, not the way we've implemented it, but the idea of it, whether we're talking about a representative democracy or a direct digital democracy, liquid democracy, a republic or whatever, the idea of an open society, participatory governance, is can we have order that is emergent rather than imposed so that we aren't stuck with chaos and infighting and inability to coordinate and we're also not stuck with oppression. And what would it take to have emergent order? This is the most kind of central question for me these days because if we look at what different nation states are doing around the world and we see nation states that are more authoritarian that in some ways are actually coordinating much more effectively. So for instance, we can see that China has built high speed rail not just through its country but around the world and the US hasn't built any high speed rail yet. You can see that it brought 300 million people out of poverty in a time where we've had increasing economic inequality happening. You can see like that if there was a single country that could make all of its own stuff, if the global supply chains failed, China would be the closest one to being able to start to go closed loop on fundamental things, Belt and Road Initiative, supply chain on rare earth metals, transistor manufacturing that is like, oh, they're actually coordinating more effectively in some important ways in the last call it 30 years. And that's imposed order. Imposed order. And we can see that if in the US if, let's look at why real quick. We know why we created term limits so that we wouldn't have forever monarchs. That's the thing we were trying to get away from and that there would be checks and balances on power and that kind of thing. But that also has created a negative second order effect, which is nobody does long term planning because somebody comes in who's got four years, they want reelected. They don't do anything that doesn't create a return within four years that will end up getting them elected, reelected. And so the 30 year industrial development to build high speed trains or the new kind of fusion energy or whatever it is just doesn't get invested in. And then if you have left versus right, where whatever someone does for four years, then the other guy gets in and undoes it for four years. And most of the energy goes into campaigning against each other. This system is just dissipating as heat, right? Like it's just burning up as heat. And the system that has no term limits and no internal friction in fighting because they got rid of those people can actually coordinate better. But I would argue it has its own fail states eventually and dystopic properties that are not the thing we want. </s><s>[INST] So the goal is to accomplish, to create a system that does long term planning without the negative effects of a monarch or dictator that stays there for the long term and accomplish that through not doing the imposition of a single leader, but through emergence. So that perhaps, first of all, the technology in itself seems to maybe disagree, allow for different possibilities here, which is make primary the system, not the humans. So the basic, the medium on which the democracy happens, like a platform where people can make decisions, do the choice making, the coordination of the choice making, where emerges some kind of order to where like something that applies at the scale of the family, the extended family, the city, the country, the continent, the whole world, and then does that so dynamically, constantly changing based on the needs of the people that are always evolving and it would all be owned by Google. Is there a way to, so first of all, are you optimistic that you could basically create, that technology can save us. Technology and creating platforms, by technology I mean like software network platforms that allows humans to deliberate, like make government together dynamically without the need for a leader that's on a podium screaming stuff. That's one. And two, if you're optimistic about that, are you also optimistic about the CEOs of [/INST] such platforms? The idea that technology is values neutral, values agnostic, and people can use it for constructive or destructive purposes, but it doesn't predispose anything. It's just, it's just silly and naive. Technology elicits patterns of human behavior because those who utilize it and get ahead end up behaving differently because of their utilization of it. And then other people, then they end up shaping the world or other people race to also get the power of the technology. And so there's whole schools of anthropology that look at the effect on social systems and the minds of people of the change in our tooling. Marvin Harris's work called cultural materialism looked at this deeply, obviously Marshall McLuhan looked specifically at the way that information technologies change the nature of our beliefs, minds, values, social systems. I will not try to do this rigorously because there are academics who will disagree on the subtle details, but I'll do it kind of like illustratively. You think about the emergence of the plow, the ox drawn plow in the beginning of agriculture that came with it where before that you had hunter-gatherer and then you had horticulture kind of a digging stick, but not the plow. Well the world changed a lot with that, right? And a few of the changes that at least some theorists believe in is when the ox drawn plow started to proliferate, any culture that utilized it was able to start to actually cultivate grain. Because just with a digging stick, you couldn't get enough grain for it to matter. Grain was a storable caloric surplus. They could make it through the famines. They could grow their population. So the ones that used it got so much ahead that it became obligate and everybody used it. That corresponding with the use of a plow, animism went away everywhere that it existed because you can't talk about the spirit of the buffalo while beating the cow all the day long to pull a plow. So the moment that we do animal husbandry of that kind, we have to beat the cow all day, we have to say, it's just a dumb animal, man has dominion over earth, and the nature of even our religious and spiritual ideas change. You went from women primarily using the digging stick to do the horticulture or gathering before that, men doing the hunting stuff, to now men had used the plow because the upper body strength actually really mattered, women would have miscarriages when they would do it when they were pregnant. all the caloric supply started to come from men where it had been from both before and the ratio of male-female gods changed to being mostly male gods following that. Obviously, we went from that particular line of thought then also says that feminism followed the tractor and that the rise of feminism in the West started to follow women being able to say we can do what men can because the male upper body strength wasn't differential once the internal combustion engine was much stronger and we can drive a tractor. So I don't think to try to trace complex things to one cause is a good idea. So I think this is a reductionist view, but it has truth in it. And so the idea that technology is values agnostic is silly. Technology codes patterns of behavior that code rationalizing those patterns of behavior and believing in them. The plow also is the beginning of the Anthropocene. It was the beginning of us changing the environment radically to clear-cut areas to just make them useful for people, which also meant the change of the view of where the web </s><s>[INST] of life, we're just a part of it, et cetera. So all those types of things. So that's brilliantly put, by the way, that was just brilliant. But the question is, so it's not agnostic, but... [/INST] So we have to look at what the psychological effects of specific tech applied certain ways are and be able to say, it's not just doing the first order thing you intended. It's doing the effect on patriarchy and animism and the end of tribal culture in the beginning of empire and the class systems that came with that. We can go on and on about what the plow did. The beginning of surplus was inheritance, which then became the capital model and lots of things. So we have to say when we're looking at the tech, what are the values built into the way the tech is being built that are not obvious? Right. So you always have to consider externalities. And the externalities are not just physical to the environment, they're also to how the people are being conditioned and </s><s>[INST] how the relationality between them is being conditioned. The question I'm asking you, so I personally would rather be led by a plow and a tractor than Stalin. That's the question I'm asking you is in creating an emergent government where people where there's a democracy that's dynamic, that makes choices, that does governance at at like a very kind of liquid, like there's a bunch of fine resolution layers of abstraction of governance happening at all scales and doing so dynamically, where no one person has power any one time that can dominate and impose rule. Okay, that's the Stalin version. I'm saying isn't there the isn't the alternative that's emergent empowered or made possible by the plow and the tractor, which is the modern version of that is like the internet, the digital space where we can the monetary system where you have the cryptocurrency and so on, but you have much more importantly, to me at least is just basic social interaction, the mechanisms of human transacting with each other in the space of ideas. So yes, it's not agnostic. Definitely not agnostic. You've had a brilliant rant there. The tractor has [/INST] effects. But isn't that the way we achieve an emergent system of governance? Yes, but I wouldn't say we're on track. You haven't seen anything promising. Another haven't seen anything promising is that to be on track requires understanding and guiding some of the things differently than is currently happening and it's possible. That's actually what I really care about. So you couldn't have had a Stalin without having certain technologies emerge. He couldn't have ruled such a big area without transportation technologies, without the train, without the communication tech that made it possible. So when you say you'd rather have a tractor or a plow than a Stalin, there's a relationship between them that is more recursive, which is new physical technologies allow rulers to rule with more power over larger distances historically. </s><s>[INST] But some things are more responsible for that than others. Stalin also eats stuff for breakfast, but the thing he ate for breakfast is less responsible for the starvation of millions than the train. The train is more responsible for that. And then the weapons of war are more responsible. So some technology, let's not throw it all. You're saying technology [/INST] has a responsibility here, but some is better than others. I'm saying that people's use of technology will change their behavior. So it has behavioral dispositions built in. The change of the behavior will also change the values in the society. It's very complicated, It will also, as a result, both make people who have different kinds of predispositions with regard to rulership and different kinds of new capacities. And so we have to think about these things. It's kind of well understood that the printing press and then early industrialism ended feudalism and created kind of nation states. So one thing I would say as a long trend that we can look at is that whenever there is a step function, a major leap in technology, physical technology, the underlying techno-industrial base with which we do stuff, it ends up coding for... it ends up predisposing a whole bunch of human behavioral patterns that the previous social system had not emerged to try to solve. And so it usually ends up breaking the previous social systems. The way the plow broke the tribal system, the way that the industrial revolution broke the feudal system. And then new social systems have to emerge that can deal with that, the new powers, the new dispositions, whatever with that tech. Obviously, the nuke broke nation state governance being adequate and said, we can't ever have that again. So then it created this international governance apparatus world. So I guess what I'm saying is that the solution is not exponential tech following the current path of what the market incentivizes exponential tech to do, being a previous social tech. I would say that exponential tech, if we look at different types of social tech, so let's just briefly look at that democracy tried to do the emergent order thing, right? At least that's the story. And this is why if you look at this important part to build first. </s><s>[INST] It's kind of doing it. It's just doing it poorly, you're saying. I mean, it is emergent order in some sense. I mean, that's the hope of democracy versus other forms of government. [/INST] Correct. I mean, I said at least the story because obviously it didn't do it for women and slaves early on. It doesn't do it for all classes equally, etc. But the idea of democracy is that is participatory governance. And so you notice that the modern democracies emerged out of the European enlightenment. And specifically, because the idea that a lot of people, some huge number, not a tribal number, huge number of anonymous people who don't know each other or not bonded to each other, who believe different things, who grew up in different ways can all work together to make collective decisions well, that affect everybody. And where some of them will make compromises and the thing that matters to them for what matters to other strangers. That's actually wild. Like it's a wild idea that that would even be possible. And it was kind of the result of this High Enlightenment idea that we could all do the philosophy of science, and we could all do the Hegelian dialectic. Those ideas had emerged, right? And it was that we could all, so our choice making, because we said a society is trying to coordinate choice-making. The emergent order is the order of the choices that we're making. Not just at the level of the individuals but what groups of individuals, corporations, nations, states, whatever do. Our choices are based on, our choice-making is based on our sense-making and our meaning-making. Our sense-making is what do we believe is happening, in the world. And what do we believe the effects of a particular thing would be—our meaning-making is, what do we care about? Right? Our values generation. What do we care about that we're trying to move the world in the direction of? If you ultimately are trying to move the world in a direction that is really, really different than the direction I'm trying to, we have very different values, we're going to have a hard time. And if you think the world is a very different world, if you think that systemic racism is rampant everywhere and one of the worst problems and I think it's not even a thing. If you think climate change is almost existential, and I think it's not even a thing, we're We're going to have a really hard time coordinating. And so we have to be able to have shared sense making of can we come to understand just what is happening together? And then can we do shared values generation? Okay, maybe I'm emphasizing a particular value more than you, but I can see how I can take your perspective and I can see how the thing that you value is worth valuing and I can see how it's affected by this thing. So can we take all the values and try to come up with a proposition that benefits all of them better than the proposition I created just to benefit these ones that harms the ones that you care about, which is why you're opposing my proposition. We don't even try in the process of crafting a proposition currently to see, and this is a reason that the proposition we vote on, it gets half the votes almost all the time. It almost never gets 90% of the votes. Is because it benefits some things and harms other things. And we can say all theory of trade-offs, but we didn't even try to say could we see what everybody cares about and see if there was a better solution. </s><s>[INST] So how do we fix that try? I wonder, is it as simple as the social technology of education? [/INST] Well, no. The proposition crafting and refinement process has to be key to a democracy or a part of the core governance. </s><s>[INST] And it's not currently. Or part of the core governance. And it's not currently. But isn't that the humans creating that situation? So there's two ways to fix that. One is to fix the individual humans, which is the education early in life. And the second is to create somehow systems that. Yeah, it's both. So I understand the education part. But creating systems, that's why I mentioned the technologies is creating social networks essentially. [/INST] Yes, that's actually necessary. OK, so let's go to the first part, and then we'll come to the second part. So democracy emerged as an Enlightenment-era idea that we could all do a dialectic and come to understand what other people valued, and so that we could actually come up with a cooperative solution rather than just, fuck you, we're going to get our thing in war. And that we could sense-make together. We could all apply the philosophy of science, and you weren't going to stick to your guns on what the speed of sound is. If we measured it and we found out what it was, there's a unifying element to the objectivity in that way. And so this is why I believe Jefferson said, if you could give me a perfect newspaper and a broken government, or I'm paraphrasing, or a broken government perfect newspaper, I wouldn't hesitate to take the perfect newspaper. Because if the people understand what's going on, they can build a new government. If they don't understand what's going on, they can't possibly make good choices. And Washington, I'm paraphrasing again, first president said the number one aim of the federal government should be the comprehensive education of every citizen and the science of government. Science of government was the term of art. Think about what that means, right? Science of government would be game theory, coordination theory, history. It wouldn't called game theory yet. History, sociology, economics, right. All the things that lead to how we understand human coordination. I think it's so profound that he didn't say the number one aim of the federal government is rule of law. And he didn't say it's protecting the border from enemies. Because if the number one aim was to protect the border from enemies, it could do that as military dictatorship, quite effectively. And if the goal was rule of law, it could do it as a dictatorship, as a police state. And so if the number one goal is anything other comprehensive education of all the citizens in the science of government, it won't stay democracy long. You can see, so both education and the fourth estate, the fourth estate being the – so education, can I make sense of the world? Am I trained to make sense of the world? The fourth estate is what's actually going on currently. The news, do I have good, unbiased information about it? Those are both considered prerequisite institutions for democracy to even be a possibility. And then at the scale it was initially suggested here. The town hall was the key phenomena where, there wasn't a special interest group crafted a proposition and the first thing I ever saw was the proposition to know anything about it and I got to vote yes or no. It was in the town hall, we all got to talk about it and the proposition could get crafted in real time through the conversation, which is why there is that founding father's statement that voting is the death of democracy. Voting fundamentally is polarizing the population in some kind of sublimated war, and we'll do that as the last step, but what we want to do first is to say, how does the thing that you care about that seems damaged by this proposition, how could that turn into a solution to make this proposition better? This proposition still tends to the thing it's trying to tend to and tends to that better. Can we work on this together? In a town hall we could have that. As the scale increased, we lost the ability to do that. Now, as you mentioned, the internet could change that. The fact that we had representatives that had to right a horse from one town hall to the other one to see what the colony would do, that we stopped having this kind of developmental propositional development process when the town hall ended, the fact that we have not used the internet to recreate this is somewhere between insane and aligned with class interests. </s><s>[INST] I would push back to say that the internet has those things, it just has a lot of other things. I feel like the internet has places where that encourage synthesis of competing ideas and sense making, which is what we're talking about. It's just that it's also flooded with a bunch of other systems that perhaps are out competing it under current [/INST] incentives, perhaps has to do with capitalism and the market. Linux is awesome, right? And Wikipedia and places where you have, and they have problems, but places where you have open source sharing of information, vetting of information towards collective building. Is that building something like, how much has that affected our court </s><s>[INST] systems, or our policing systems, or our military systems, or our- First of all, I think a lot, but not enough. I think that's something I told you offline yesterday, perhaps this is a whole other discussion, but I don't think we're quite quantifying the impact on the world, the positive impact of Wikipedia. You said the policing, I just think the amount of empathy, knowledge, I think can't help but lead to empathy. Just knowing, okay. Just knowing, okay, I'll give you some pieces of information. Knowing how many people died in various wars. Already that delta, when you have millions of people have that knowledge, it's a little slap in the face, like, oh, my boyfriend or girlfriend breaking up with me is not such a big deal when millions of people were tortured. Just a little bit. And when a lot of people know that because of Wikipedia, or the effect their second order effects of Wikipedia, which is, it's not that necessarily people read Wikipedia, it's like YouTubers who don't really know stuff that well, will thoroughly read a Wikipedia article and create a compelling video describing that Wikipedia article that then millions of people watch. And they understand that holy shit, a lot of there were such, first of all, there was such a thing as World War Two in World War One, okay. Like, they can least like learn about it, they can learn about. This was like, recent, they can learn about slavery, they can learn about all kinds of injustices in the world. And that I think a lot of effects to the way, whether you're a police officer, a lawyer, a judge, in the jury, or just a regular civilian citizen, the way you approach every other communication you engage in, even if the system of that communication is very much flawed. So I think there's a huge positive effect on Wikipedia. That's my case for Wikipedia. So you should donate to Wikipedia. I'm a huge fan, [/INST] but there's very few systems like it, which is sad to me. So I think it would be a useful exercise for any listener of the show to really try to run the dialectical synthesis process with regard to a topic like this and take the techno concern perspective with regard to information tech that folks like Tristan Harris take and say what are all of the things that are getting worse and are any of them following an exponential curve and how much worse how quickly could that be. And then do that fully without mitigating it. Then take the techno-optimist perspective and see what things are getting better in a way that Kurzweil or Diamandis or someone might do and try to take that perspective fully and say are some of those things exponential? What could that portend, and then try to hold all that at the same time. And I think there are ways in which, depending upon the metrics we're looking at, things are getting worse on exponential curves and better on exponential curves for different metrics at the same time, which I hold as the destabilization of a previous system. And either an emergence to a better system or a collapse to a lower order are both possible. And so I want my optimism not to be about my assessment. I want my assessment to be just as fucking clear as it can be. I want my optimism to be what inspires the solution process on that clear assessment. So I never want to apply optimism in the sensemaking. I want to just try to be clear. If anything, I want to make sure that the challenges are really well understood. But that's in service of an optimism that there are good potentials, even if I don't know what they are that are worth seeking, right? There's kind of a, there is some sense of optimism that's required to even try to innovate really hard problems. But then I want to take my pessimism and red team my own optimism to see is that solution not going to work? Does it have second order effects, and then not get, not get upset by that, because I then come back to how to make it better. So there's just a relationship between optimism and pessimism and the dialectic of how they how they can work. So when I, of course, we can say that Wikipedia is a pretty awesome example of a thing. We can look at the places where it has limits or has failed where on a celebrity topic or corporate interest topic, you can pay Wikipedia editors to edit more frequently and various things like that. But you can also see where there's a lot of information that was kind of decentrally created that is good information that is more easily accessible to people than everybody buying their own encyclopedia Britannica walking down to the library, and they can be updated in real time faster. And I think you're very right that the business model is a big difference. Because Wikipedia is not a for profit corporation, it is a it's tending to the information commons and it doesn't have an agenda other than tending to the information commons. And I think the two masters issue is a tricky one when I'm trying to optimize for very different kinds of things, where I have to sacrifice one for the other. And I can't find synergistic satisfies, which one, and if I have a fiduciary responsibility to shareholder profit maximization, and you know, what does that end up creating? I think the ad model that Silicon Valley took, I think, Jaron Laney, or I don't know if you've had him on the show, but he has interesting assessment of the nature of the ad model. Silicon Valley wanting to support capitalism and entrepreneurs to make things, but also the belief that information should be free. And also the network dynamics with the more people you got on, you got increased value per user per capita as more people got on. So you didn't want to do anything to slow the rate of adoption. Some places actually, you know, PayPal paying people money to join the network because the value of the network would be there'd be a Metcalf like dynamic proportional to the square of the total number of users. So the ad model made sense of how do we make it free, but also be a business get everybody on, but not really thinking about what it would mean to and this is now the whole idea that if you aren't paying for the product, you are the product. If they have a fiduciary responsibility to their shareholder to maximize profit, their customer is the advertiser, the user who it's being built for is to do behavioral mod for them for advertisers. That's a whole different thing than that same type of tech could have been if applied with a different business model or different purpose. I think there's because Facebook and Google and other information and communication platforms end up harvesting data about user behavior that allows them to model who the people are in a way that gives them more sometimes specific information and behavioral information, then even a therapist or a doctor or a lawyer or a priest might have in a different setting, they basically are accessing privileged information, there should be a fiduciary responsibility. And in normal fiduciary law, if there's this principal agent thing, if you are a principal, and I'm an agent on your behalf, I don't have a game theoretic relationship with you, right? If you're sharing something with me, and I'm the priest, or I'm the therapist, I'm never going to use that information to try to sell you a used car or whatever the thing is. But Facebook is gathering massive amounts of privileged information and using it to modify people's behavior for a behavior that they didn't sign up for wanting the behavior, but what the corporation did. So I think this is an example of the physical tech evolving in the context of the previous social tech, where it's being shaped in particular ways. And here, unlike Wikipedia that evolved for the information commons, this evolved for fulfilling particular agentic purpose. Most people when they're on Facebook think it's just a tool that they're using, they don't realize it's an agent, right? It is a corporation with a profit motive. And, and as I'm interacting with it, it has a goal for me different than my goal for myself. And I might want to be on for a short period of time, its goal is maximize time on site. And so there is a rivalry that is take but where there should be a fiduciary contract. I think that's actually a huge deal. And I think if we said, could we apply Facebook like technology to develop people's citizenry capacity, right to develop their personal health and well being and habits as well as their cognitive understanding the complexity with which they can process the health of their relationships, that would be amazing to start to explore. And this is now the thesis that we started to discuss before is every time there is a major step function and the physical tech, it obsoletes the previous social tech and the new social tech has to emerge. What I would say is that when we look at the nation state level of the world today, the more top down authoritarian nation states are, as the exponential tech started to emerge, the digital technology started to emerge. They were in a position for better long term planning and better coordination. And so the authoritarian state started applying the exponential tech intentionally to make more effective authoritarian states. And that's everything from like an internet of things surveillance system, going into machine learning systems to the sesame credit system to all those types of things. And so they're upgrading their social tech using the exponential tech. Otherwise within a nation state like the US, but democratic open societies, the countries, the states are not directing the technology in a way that makes a better open society meaning better emergent order. They're saying, Well, the corporations are doing that. And the state is doing the relatively little thing it would do aligned with the previous corporate law that no longer as relevant because there wasn't fiduciary responsibility for things like that. There wasn't antitrust. Because This creates functional monopolies because of network dynamics, right? Where YouTube has more users than Bimeo and every other video player together. Amazon has a bigger percentage of market share than all of the other markets together. You get one big dog per vertical because of network effect, which is a kind of organic monopoly that the previous antitrust law didn't even have a place. That wasn't a thing. Anti-monopoly was only something that emerged in the space of government contracts. So what we see is that the new exponential technology is being directed by authoritarian nation states to make better authoritarian nation states and by corporations to make more powerful corporations. Powerful corporations, when we think about the Scottish enlightenment, when the idea of markets was being advanced, the modern kind of ideas of markets, the biggest corporation was tiny compared to what the biggest corporation today is. So, the asymmetry of it relative to people was tiny. And the asymmetry now in terms of the total technology, it employs total amount of money, amount of information processing is so many orders of magnitude. And rather than there be demand for an authentic thing that creates a basis for supply. As supply started to get way more coordinated and powerful, and the demand wasn't coordinated because you don't have a labor union of all the customers working together, but you do have a coordination on the supply side, supply started to recognize that it could manufacture demand. It could make people want shit that they didn't want before, that maybe wouldn't increase the happiness in a meaningful way, it might increase addiction. Addiction is a very good way to manufacture demand. And so as soon as manufactured demand started, through this is the cool thing and you have to have it for status or whatever it is, the intelligence of the market was breaking. Now it's no longer collective intelligence system that is up regulating real desire for things that are really meaningful. You're able to hijack the lower angels of our nature rather than the higher ones. The addictive patterns drive those and have people watch it that doesn't actually make them happier, make the world better. And so we really also have to update our theory of markets because behavioral econ showed that homo economicus, the rational actor is not really a thing, but particularly at greater and greater scale can't really be a thing. Voluntaryism isn't a thing where if my company doesn't wanna advertise on Facebook, I just will lose to the companies that do because that's where all the fucking attention is. And so then I can say it's voluntary, but it's not really if there's a functional monopoly, same if I'm gonna sell on Amazon or things like that. So what I would say is these corporations are becoming more powerful than nation states in some ways. And they are also debasing the integrity of the nation states, the open societies. So the democracies are getting weaker as a result of exponential tech and the kind of new tech companies that are kind of a new feudalism, tech feudalism because it's not a democracy inside of a tech company or the supply and demand relationship. When you have manufactured demand and kind of monopoly type functions. And so we have basically a new feudalism controlling exponential tech and authoritarian nation states controlling it. And those attractors are both shitty. And so I'm interested in the application of exponential tech to making better social tech that makes emergent order possible. And where then that emergent order can bind and direct the exponential tech in fundamentally healthy, not x-risk oriented directions. I think the relationship of social tech and physical tech can make it. I think we can actually use the physical tech to make better social tech, but it's not given that we do. If we don't make better social tech, then I think the physical tech empowers really shitty social tech </s><s>[INST] that is not a world that we want. I don't know if it's a road we wanna go down but I tend to believe that the market will create exactly the thing you're talking about which I feel like there's a lot of money to be made in creating a social tech that creates a better citizen. It creates a better human being. Your description of Facebook and so on, which is a system that creates addiction, which manufacturers demand, is not obviously, inherently, the consequence of the markets. I feel like that's the first stage of us, like baby deer trying to figure out how to use the internet. I feel like there's much more money to be made with something that creates comparison and love, honestly. I can make the business case for it. I don't know if, I don't think we wanna really have that discussion, but do you have some hope that that's the case? I guess, if not, then how do we fix the system of markets that work so well for the United States for so long? [/INST] Like I said, every social tech worked for a while, like tribalism worked well for 200,000 or 300,000 years. I think social tech has to keep evolving. The social technologies with which we organize and coordinate our behavior have to keep evolving as our physical tech does. So I think the thing that we call markets, of course, we can try to say, oh, even biology runs on markets, but the thing that we call markets, the underlying theory, homo economicus, demand, driving supply, that thing broke. It broke with scale, in particular, and a few other things. So it needs updated in a really fundamental way. I think there's something even deeper than making money happening, that in some ways will obsolete money making. I think capitalism is not about business. So if you think about business, I'm gonna produce a good or a service that people want and bring it to the market so that people get access to that good or service. That's the world of business. But that's not capitalism. Capitalism is the management and allocation of capital, which financial services was a tiny percentage of the total market is become a huge percentage of the total market, it's a different creature. So if I was in business and I was producing a good or service and I was saving up enough money that I started to be able to invest that money and gain interest or do things like that, I start realizing I'm making more money on my money than I'm making on producing the goods and services. So I stopped even paying attention to goods and services and start paying attention to making money on money, and how do I utilize capital to create more capital? Capital gives me more optionality because I can buy anything with it than a particular good or service that only some people want. Capitalism more capital ended up meaning more control. I could put more people under my employment. I could buy larger pieces of land, novel access to resource minds and put more technology under my employment. increased agency and also increased control. I think attentionalism is even more powerful. So rather than enslave people, where the people kind of always want to get away and put in the least work they can, there's a way in which economic servitude was just more profitable than slavery, right? Have the people work even harder voluntarily because they want to get ahead, and nobody has to be there to whip them or control them or whatever. However, this is a cynical take, but a meaningful take. So capital ends up being a way to influence human behavior, right? And yet where people still feel free in some meaningful way, they're not feeling like they're going to be punished by the state if they don't do something. It's like punished by the market via homelessness or something. But the market is this invisible thing I can't put an agent on, so it feels like free. And so if you want to affect people's behavior and still have them feel free, capital ends up being a way to do that, but I think affecting their attention is even deeper. Because if I can affect their attention, I can both affect what they want and what they believe and what they feel. And we statistically know this very clearly. Facebook has done studies that based on changing the feed, it can change beliefs, emotional dispositions, et cetera. And so I think there's a way that the harvest and directing of attention is even a more powerful system than capitalism. It is effective in capitalism to generate capital, but I think it also generates influence beyond what capital can do. And so do we want to have some groups utilizing that type of tech to direct other people's attention? If so, towards what? Towards what metrics of what a good civilization and good human life would be? </s><s>[INST] What's the oversight process? What is the transparency? I can answer all the things you're mentioning. I can build, I guarantee you if I'm not such a lazy ass, I'll be part of the many people doing this as transparency and control, giving control to individual people. [/INST] Okay. So maybe the corporation has coordination on its goals that all of its customers or users together don't have. So there's some asymmetry where it's asymmetry of its goals, but maybe I could actually help all of the customers to coordinate almost like a labor union or whatever by informing and educating them adequately about the effects, the externalities on them. This is not toxic waste going into the ocean of the atmosphere. It's their minds, their beings, their families, their relationships, such that they will in group change their behavior. And I think the one way of saying what you're saying I think is that you think that you can rescue Homo economicus from the rational actor that will pursue all the goods and services and choose the best one at the best price, the kind of Rand von Mises Hayek that you can rescue that from Dan Ariely and Behavioral Econ that says that's actually not how people make choices. They make it based on status hacking largely, whether it's good for them or not in the long term. And the large asymmetric corporation can run propaganda and narrative warfare that hits people's status buttons and their limbic hijacks and their lots of other things in ways that they can't even perceive that are happening. They're not paying attention to that. This site is employing psychologists and split testing and whatever else. So you're saying I think we can </s><s>[INST] recover Homo economicus. And not just through a single mechanism technology. Not to keep mentioning the guy, but platforms like Joe Rogan and so on that help make viral the ways that the education [/INST] of negative externalities can become viral in this world. So interestingly, I actually agree with you that... Got him. Four and a half hours in. Tech can do some good. Tech can do it. Well, see what you're talking about is the application of tech here, broadcast tech, where you can speak to a lot of people. And that's not going to be strong enough because the different people need spoken to differently, which means it has to be different voices that get amplified to those audiences more like Facebook's tech. But nonetheless, we'll start </s><s>[INST] with broadcast tech. Plants to first seed and then the word of mouth is a powerful thing. You need to do the first broadcast shotgun and then it lands a catapult or whatever. I don't know what the right weapon is, but then it just spreads the word of mouth with all kinds of tech, [/INST] including Facebook. So let's come back to the fundamental thing. The fundamental thing is we want to order at various scales from the conflicting parts of ourself actually having more harmony than they might have to family, extended family, local, all the way up to global. We want emergent order where our choices have more alignment. We want that to be emergent rather than imposed or rather than we want fundamentally different things or make totally different sense of the world where warfare of some kind becomes the only solution. Emergent order requires us in our choice making, requires us being able to have related sense making and related meaning making processes. Can we apply digital technologies and exponential tech in general to try to increase the capacity to do that? Where the technology called a town hall, the social tech that we'd all get together and talk obviously is very scale limited and it's also oriented to geography rather than networks of aligned interest. Can we build new better versions of those types of things? And going back to the idea that a democracy or participatory governance depends upon comprehensive education in the science of government, which includes being able to understand things like asymmetric information warfare on the side of governments and how the people can organize adequately. Can you utilize some of the technologies now to be able to support increased comprehensive education of the people and maybe comprehensive informateness? So both fixing the decay in both education and the fourth estate that have happened so the people can start self-organizing to then influence the corporations, the nation states to do different things and or build new ones themselves. Yeah, fundamentally that's the thing that has to happen. The exponential tech gives us a novel problem landscape that the world never had. The nuke gave us a novel problem landscape and so that required this whole Bretton Woods world. The exponential tech gives us novel problem landscape. Our existing problem-solving processes aren't doing a good job. We have had more countries get nukes, we haven't a nuclear deep proliferation, we haven't achieved any of the U.N., sustainable development goals. We haven't kept any of the new categories of tech for making arms races. So our global coordination is not adequate to the problem landscape. So we need fundamentally better problem-solving processes and market or a state is a problem solving process. We need better ones that can do the speed and scale of the current issues. Right now, speed is one of the other big things, is that by the time we regulated DDT out of existence or cigarettes not for people under 18, they'd already killed so many people and we let the market do the thing. But as Elon has made the point that won't work for AI, by the time we recognize afterwards that we have an autopoetic AI that's a problem, you won't be able to reverse it. There's a number of things that when you're dealing with tech that is either self-replicating and disintermediates humans to keep going, doesn't need humans to keep going, or you have tech that just has exponentially fast effects, your regulation has to come early. It can't come after the effects have happened, because the negative effects could be too big too quickly. So we basically need new problem solving processes that do better at being able to internalize externality, solve the problems on the right time scale and the right geographic scale. And those new processes to not be imposed have to emerge from people wanting them and being able to participate in their development, which is what I would call kind of a new cultural enlightenment or renaissance that has to happen, where people start understanding the new power that exponential tech offers the way that it is actually damaging current governance structures that we care about and creating an extra landscape, but could also be redirected towards more protopic purposes. And then saying, how do we rebuild new social institutions? What are adequate social institutions where we can do participatory governance at scale and time? And how can the people actually participate to build those things? </s><s>[INST] The solution that I see working requires a process like that. And the result maximizes love. So again, Elon would be right that love is the answer. Let me take it back from the scale of societies to the scale that's far, far more important, which is the scale of family. You've written a blog post about your dad. We have various flavors of relationships with our fathers. [/INST] What have you learned about life when your dad... Well, people can read the blog post and see a lot of individual things that I learned that I really appreciated. If I was to kind of summarize at a high level, I had a really incredible dad, like very, very unusually positive set of experiences. He was committed, we were homeschooled, and he was committed to work from home to be available and prioritize fathering in a really deep way. And as a super gifted, super loving, very unique man, he also had his unique issues that were part of what crafted the unique brilliance, and those things often go together. And I say that because I think I had some unusual gifts and also some unusual difficulties. And I think it's useful for everybody to know their path probably has both of those. But if I was to say kind of at the essence of one of the things my dad taught me across a lot of lessons was like the intersection of self-empowerment, ideas and practices that self-empower towards collective good, towards some virtuous purpose beyond the self. And he both said that a million different ways, taught it in a million different ways when we were doing construction, and he was teaching me how to build a house. We were putting the wires to the walls before the drywall went on, he made sure that the way that we put the wires through was beautiful. Like the height of the holes was similar, that we twisted the wires in a particular way, and it's like no one's ever gonna see it. And he's like if a job's worth doing, it's worth doing well and excellence is its own reward and those types of ideas. And if there was a really shitty job to do, he'd say, see the job, do the job, stay out the misery, just don't indulge in any negativity, do the things that need done. And so there's like, there's an empowerment and a nobility together. And yeah, extraordinarily </s><s>[INST] fortunate. Is there ways you think you could have been a better son? Is there things you regret? That's an interesting question. Let me first say, just as a bit of a criticism, that what kind of man do you think you are not wearing a suit and tie? A real man should. Exactly. I grew with your dad at that point. You mentioned offline that he suggested a real man should wear a suit and tie. But outside of that, is there ways you could have been a better son? [/INST] Maybe next time on your show, I'll wear a suit and tie. My dad would be happy about that. Please. I can answer the question later in life, not early. I had just a huge amount of respect and reverence for my dad when I was young. So I was asking myself that question a lot. So I weren't a lot of things I knew that I wasn't seeking to apply. There was a phase when I went through my kind of individuation differentiation, where I had to make him excessively wrong about too many things. I don't think I had to, but I did. And he had a lot of kind of non-standard model beliefs about things, whether early kind of ancient civilizations or ideas on evolutionary theory or alternate models of physics. And they weren't irrational, but they didn't all have the standard of epistemic proof that I would need. And I went through, and some of them were kind of spiritual ideas as well, I went through a phase in my early 20s where I kind of had the attitude that Dawkins or Christopher Hitchens has that can kind of be excessively certain and sanctimonious, applying their reductionist philosophy of science to everything and kind of brutally dismissive. I'm embarrassed by that phase, not to say anything about those men and their path, but for myself. And so during that time, I was more dismissive of my dad's epistemology than I would have liked to have been. I got to correct that later, </s><s>[INST] apologize for it. But that was the first thought that came to mind. You've written the following. I've had the experience countless times, making love, watching a sunset, listening to music, feeling the breeze. I would sign up for this whole life and all of its pains just to experience this exact moment. This is a kind of world-less knowing. It's the most important and real truth I know, that experience itself is infinitely meaningful and pain is temporary. And seen clearly, even the suffering is filled with beauty. I have experienced countless lives worth of moments worthy of life, such an unreasonable fortune. A few words of gratitude from you, beautifully written. Is there some beautiful moments? Now you have experienced countless lives worth of those moments. But is there some things that if you could, in your darker moments, you can go to to relive to remind yourself that the whole ride is worthwhile? Maybe skip the making love part. We don't know about that. [/INST] I mean, I feel unreasonably fortunate that it is such a humongous list. Because, I mean, I feel fortunate to have had exposure to practices and philosophies and way of seeing things that makes me see things that way. So I can take responsibility for seeing things in that way and not taking for granted really wonderful things. But I can't take credit for being exposed to the philosophies that even gave me that possibility. You know, it's not just with my wife. It's with every person who I really love when we're talking, I look at their face. I, in the context of a conversation, feel overwhelmed by how lucky I am to get to know them. And like, there's never been someone like them in all of history, and there never will be again and they might be gone tomorrow, I might be gone tomorrow, and like I get this moment with them. And when you take in the uniqueness of that fully and the beauty of it, it's overwhelmingly beautiful. And I remember the first time I did a big dose of mushrooms, and I was looking at a tree for a long time. And I was just crying, with overwhelm, at how beautiful the tree was. And it was a tree outside the front of my house that I'd walked by a million times and never looked at like this. And it wasn't the dose of mushrooms where I was hallucinating like where the tree was purple. Like the tree still looked like, if I had to describe it, it'd say it's green and it has leaves looks like this. But it was way fucking more beautiful, like capturing than it normally was. And I'm like, why is it so beautiful if I would describe it the same way? And I realized I had no thoughts taking me anywhere else. What it seemed like the mushrooms were doing was just actually shutting the narrative off. They would have me be distracted so I could really see the tree. tree. And then I'm like, fuck, when I get off these mushrooms, I'm going to practice seeing the tree because it's always that beautiful and I just miss it. And so I practice being with it and quieting the rest of the mind and then being like wow. And if it's not mushrooms, like people have peak experiences where they'll see life and how incredible it is, it's always there. </s><s>[INST] It's funny that I had this exact same experience on quite a lot of mushrooms, just sitting alone and looking at a tree. And exactly as you described it, appreciating the undistorted beauty of it. And it's funny to me that here's two humans very different with very different journeys or at some moment in time both looking at a tree like idiots for hours and just in awe and happy to be alive. And yeah, even just that moment alone is worth living for. But you did say humans and we have a moment together as two humans and you mentioned shots. [/INST] Well, I have to ask what are we looking at? When I went to go get a smoothie before coming here, I got you a keto smoothie that you didn't want because you're not just keto but fasting. But I saw the thing with you and your dad where you did shots together. Yeah. And this place happened to have shots of ginger turmeric cayenne juice of some kind. I didn't necessarily plan it </s><s>[INST] for being on the show. I just brought it. We can do it that way. I think we should toast like heroes. Daniel, it's a huge honor. What do we toast to? We toast to this moment. This unique moment that [/INST] we get to share together. I'm very grateful to be here in this moment with you and grateful that </s><s>[INST] you invited me here. We met for the first time and I will never be the same for the good and the bad. That is really interesting. That feels way healthier than the vodka. My dad and I were drinking. So I feel like a better man already. Daniel, this is one of the best conversations I've ever had. I can't wait to have many more. Likewise. This has been an amazing experience. Thank [/INST] you for wasting all your time today. I want to say in terms of what you're mentioning about like the you work in machine learning and the optimism that wants to look at the issues but wants to look at how this increased technological power could be applied to solving them and that even thinking about the broadcast of like, can I help people understand the issues better and help organize them? Like, fundamentally, you're oriented like Wikipedia, what I see, to really try to tend to the information commons without another agentic interest distorting it. And for you to be able to get guys like Lee Smolin and Roger Penrose and like the greatest thinkers of that are alive and have them on the show and most people would never be exposed to them and talk about it in a way that people can understand. I think it's an incredible service. I think you're </s><s>[INST] doing great work. So I was really happy to hear from you. Thank you. Thank you, Daniel. Thanks for listening to this conversation with Daniel Schmocktenberger and thank you to Ground News, NetSuite, Four Sigmatic, Magic Spoon, and BetterHelp. Check them out in the description to support this podcast. And now let me leave you with some words from Albert Einstein. I know not with what weapons World War III will be fought, but World War IV will be fought with sticks and stones. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] Wow this is so there is some bullying going [/INST] on. It was totally material in the antitrust case but javascript escaped into the standard setting where there was a fairly good cooperation. Microsoft had a really good guy on it and you know Guy Steele was there for a time and there was some good work but after the antitrust case and you know an escape kind of dissolving into a and not really going anywhere quickly, Mozilla took years to really bring up um the standard froze and by 2000 and three even though they've been sort of noodling around with advanced versions, javascript to given the keys to the kingdom to another M. I. T. Grad Baltimore whore watt, Very big brain and still google I think he won that putting him in 86 he's. Yeah mathematics yet. Um he designed his successor language too. But it only showed up in a mutated form in Microsoft's sp on that server side and it didn't last there and it showed up in flash and that's what became action script three, </s><s>[INST] which action script interesting. And then, and then Flash of course declined. And so how do we arrive at es six where it's, it's like there's so many where everyone okay. There's this history of javascript that people were, it was just like cool when you're like having beers to talk crap about javascript. Everyone loves to hate. Like people who are married, say married sucks is they just want to get let off some steam even though everyone uses the language. But yeah, six, it's become this like [/INST] uh </s><s>[INST] reputable. Like it fix major pain points. I think it [/INST] added things to the language and added something that was already es five, strict mode but made it implicit in class bodies and module bodies. It was a big jump, but it accumulated some of the S four designs that we've done with adobe four. What we hoped would be the 4th edition of the script that we're supposed to fold in some of these old javascript to ideas that had come into actions for three. So you look at the family tree and you see these forks and the main ones are the ones that go into adobe Flash acquired from Macromedia and the one that went into the service side of Microsoft's stack which kind of died. Um and then trying to bring them back into the standard and not quite succeeding. S four was mothballed but all the good parts that everyone liked made it into es six and so that that was a success and I said earlier I had the wrong year I think it's 2015 so it's off by </s><s>[INST] four. Yes. [/INST] Yeah it was done finalized in 2015 it took a little longer than we hoped but um because he has five was 2000 and nine and that was a smaller increment from E. S. Three. We skipped four again we mothballed in and we had a split in the committee where some people said you know he? S four is too big, we're gonna work on incremental improvements. No new syntax in particular. They promised not quite true but they added a bunch of interesting a. P. I. S. Allen west brom I co author of the Hubble paper and he was at Microsoft time. I ended up hiring Mozilla, he wanted to get to Mosul and keep doing the sort of editing editor job of the job ship standard Eggman script. Um And when we got six done it was a little late 2015 and we switched to your numbers so people still call it S six. I call it S six but if you remember you know off by nine plus two </s><s>[INST] 1000 I mean yes six is such a big, I mean like you said there's a thought that connects all of it. But yeah, six is when it's like became this language that almost feels ready to take over the world. Completely [/INST] more programming in the large features, more features you need for larger teams and its software engineering Microsoft did something smart to they Anderson company luke Hoban who's left Microsoft also did typescript and they realized uh something I think that Gilad Bracha is also popularized and and he was involved in darted google. If you don't worry about soundness in the type system, you don't try to enforce type checks at runtime in particular just using a sort of a warning system, a tool time type system. You can still have a lot of value for developers, especially in large projects. So typescript been a roaring success for Microsoft. </s><s>[INST] Well what do you think about, what do you think about typescript? Is it uh adding confusion or is it ultimately beneficial? [/INST] I think it's beneficial. Now it's technically a super set of javascript. So of course I love it. The shortest javascript program is still a typescript program. Any javascript program is a typescript program which is brilliant cause then you can start incrementally adding type annotations, getting warnings, learning how to use them. Microsoft had to kind of look around corners at the standards body and guess how their version of modules or decorators should work and the standards body then they change things a bit. So I think they're obligated with typescript either to carry their own version or to bring it back with incompatible changes toward the standard over time. And I think they've played generally fair. There there's some sentiment that why don't they standardized typescript? Well they've been clear, they don't want to, they have a proprietary investment. It's valuable. They have controlled the ball and in some ways you can say the same thing to any of the other big companies in the standards body. Why isn't google standardize its stuff? </s>

<s>[INST] Yeah, I think God will hear that question back. Alright, fine. You get in that's that's the right, that's the right [/INST] question asked humility </s><s>[INST] and selfishness. Alright, you're [/INST] mean </s><s>[INST] but [/INST] well you're gonna be </s><s>[INST] fine, don't worry. [/INST] But I mean one of the things that I think you strive I struggle with at least is on the one hand, that's probably the most the thing that's closest to me and maybe the most common human experience, but I don't know one of the things that I just struggle with in terms of running this large enterprises, like should the thing that I care more about b that responsibility and I think it's shifted over time, I mean like before I really had a family that was like the only thing I cared about and now at this point it's I mean, I'm I mean I care deeply about it, but like Yeah, I think that that's that's not as obvious as a question. </s><s>[INST] We humans are weird, you get you get you get this ability to uh impact millions of lives and it's definitely something billions of lives, it's something you care about. But the weird humans that are closest to us, those are the ones that mean the most. And I suppose that's the dream of the metaverse is to connect form small groups like that, where you can have those intimate relationships. Let me ask you the big ridiculous [/INST] 1 to be able to be close, not just based on who you happen to be next to. I think that's what the internet is already doing is allowing you to spend more of your time, not physically proximate. I mean, I always think when you think about the the metaverse, people ask this question of the real world, it's like do the virtual world versus the real world and it's like, no, the real world is a combination of the virtual world in the physical world. But I think over time as we get more technology, the physical world is becoming less of a percent of the real world. And I think that that opens up a lot of opportunities for people because you know, you can you can work in different places, you can stay more close to stay closer to people who are in different places that's good </s><s>[INST] removing barriers of geography and then barriers of language. That's that's a beautiful vision. Big ridiculous question. What do you think is the meaning of life? [/INST] I think that well there are probably a couple of different ways that that I would go at this, but I think it gets back to this last question that we talked about about the duality between you have the people around you who you care the most about. And then there's like this bigger thing that maybe you're building. Um and I think that in my own life, I mean, I I sort of think about this tension, but just look, I mean, I started this whole company and my life's work is around human connection. So um I think it's intellectually probably the thing that I go to first is just that human connection is the meaning. And I mean, I think that it's a thing that are society probably systematically undervalues. I mean, I just remember, you know, when I was growing up and in in school it's like do your homework and then go play with your friends after. And it's like, no, well what if what if playing with your friends is the point? Like that sounds like an </s><s>[INST] argument your daughter doesn't make. [/INST] Well, I mean, I don't know, I just I just think it's interesting doesn't even </s><s>[INST] matter, man. [/INST] Well, I think it's interesting because it's, you know, and people, I think people tend to think about that stuff is wasting time or that's like what you do in the free time that you have. But like what if that's actually the point? So that's one. But but here's the here's maybe a different way of counting at this, which is maybe more like religious in nature. And I always like there's a a rabbi who I've studied with, who kind of gave me this, we're talking through genesis and the the bible and the Torah and um and they're basically walking through, it's like, okay, you go through the seven days of creation. And and it's basically it's like why does the bible start there, Right? It's like it could have started anywhere right in terms of like how to live. Um but basically it starts with talking about how God created people in his her image. But the bible starts by talking about how God created everything. So I actually think that there's like a a compelling argument that I think I've always just found meaningful and inspiring that a lot of the point of what sort of religion has been telling us that we should do is to create and build </s><s>[INST] things. [/INST] So these things are not necessarily at odds. I mean, I think like, I mean that's and I think probably to some degree you'd expect me to say something like this because I've dedicated my life to creating things that help people connect. So, I mean that's sort of the fusion of of um I'm getting back to what we talked about earlier. It's I mean, what I studied in school or psychology and computer science, right? So it's I mean these are, these are like the two themes that that I care about. But I don't know for me. That's what, that's what I think about. That's what matters to </s><s>[INST] create and to ah to love, which is the ultimate form of connection. I think this is one hell of an amazing replay experience in the metaverse. So whoever is using our avatars years from now, I hope you had fun and thank you for talking today. [/INST] Thank you. </s>

<s>[INST] from what seemed to be some very salient lessons. I should mention one thing is that I also know that you're interested in Russian culture a little bit. Yes. Churchill said, I cannot forecast to you the action of Russia. It is a riddle wrapped in a mystery inside an enigma. So what do you are some interesting differences between, so this eastern part of the world of Russia, Ukraine, the Slavic countries, the former Soviet Union, all of that versus sort of the US culture. What stands out to you from the literature, [/INST] from the music, from the science, all that kind of stuff. I think there's so much intensity, intensity and I guess I would say fearlessness of expression that I see in the Slavic culture, maybe it's across cultures, because there's a different way that expression occurs. We say like, oh, it's different in the French than the Spanish or is different than in parts of Africa. And I think when you take that part of the world for whatever reason, and maybe it's just totally random or maybe it's aspects of geography and experience and migration, but there's such an intensity. And I remember listening to Tchaikovsky very early on, maybe not for the very first time, but early on in my life or reading Dostoyevsky and feeling like, oh, Dostoyevsky's willingness, his ability and his willingness to express and create such powerful, aberrant states of human experience. Tchaikovsky in his music, the depths of suffering that it expresses has always stood out to me as a way that like, if that's like the brightest light, so to speak, communicating information, that that's a place to look. And it's also a place that resonated with me so strongly because I think for some people who are informative years and having very difficult feelings, right? Of like a depth of feeling of like fear and how's the world going to be? Am I going to be annihilated? Am I, what do I even want? What do I feel inside of me? To encounter that being expressed so intensely, I found to be very, very moving. So I don't know if that's a good answer or not, but I think there's an intensity of expression and a fearlessness. You know, Dostoyevsky wrote about terrible things. You know, what happens in the person, is there a person who is brilliant intellectually and very persuasive and very capable of being effective, who also just chooses to be a child rapist, right? I mean, he wrote about that. He wrote about the truths of, this is what we can be as humans. And I think there's so many lessons, including the truth. Like people will tend to think, oh, evil is not very bright or not very intelligent. That's a way to let evil propagate, right? Evil can be effective and attractive and very compelling, but evil nonetheless. And I just think there's a fearless willingness to look at that and to describe it, </s><s>[INST] that I see primarily I've studied in Russian culture. Yeah, the fearless exploration of this whole human drama, definitely Dostoyevsky and others since in the 20th century and the 19th century have done an incredible job of that. Some of that, just like you said, is the language, the culture. I think that intense romanticism is there. That is almost an overdramatic exploration of human nature. It can err on the side or falter when it goes into a kind of cynical view of life. You know, life is suffering. I think that also has to do with the way you deal with the trauma of the world wars and so on. This is something the different nations throughout Europe had to deal with that in different ways. Some of them have channeled into envy and resentment. Some of them channeled into a kind of nihilism or cynicism. And ultimately the intensity of feeling is there, which is sort of interesting to see and interesting how that manifests itself in the kind of governments it builds up. You know, there's more authoritarianism in that part of the world versus the Western world that's more focused on the individual versus the collective. And when more focused on the individual, you have a propensity to value individual rights with democracy and so on. It's interesting to watch and to reconstruct how that all came to be. Is it in the blood? Is it in the mind? Is it in some kind of thing that more ethereal, a collective set of ideas that we pass from generation to generation between each other, sort of the collective of it? Yeah, it's fascinating to see. But now reinvigorated because there's conflict [/INST] in that part of the world. </s><s>[INST] Right, right. You've also thought about the Cold War. What lessons about the human mind, about psychiatry, psychology, and about looking at the Cold War, can we take forward in the 21st century so that we can avoid World War III? Right. [/INST] A major cold or hot war in the 21st century. Right. Well, I think unspoken animosities are very, very, very dangerous, right? It was a Cold War. There was fighting through proxies, right? The superpowers were fighting surrogate wars through proxies, which of course, in and of itself, causes immense suffering. But there's, it becomes the opposite of an exchange of ideas or an exchange of thought. You know, Chris Jeff, right? Not believing that the kitchen could look like it did at the World's Fair, right? And some of the misconceptions here of like what things were like in Russia, right? It was an utter, it was a thought that those other people are not actually people, right? There's an enemy society of evil, which then paints with a broad brush in a way that makes it easy, too easy for the Cold War to go from being cold, right? To having boiling over into utter destruction. And, you know, I wrote, it was really a true story that when I was in, it was still the Soviet Union, but it was right around the time of the Soviet Union coming to an end. And I had gone on a trip for students from England and we got to go places that people like hadn't gone. You know, foreigners hadn't gone in many, many years. It was just kind of the right timing to experience that. And like it really is true that someone said on short notice to these poor kids that like these group of Americans were coming and I have a picture somewhere of the kid in a gas mask. Like they went under their desks and put on a gas mask and they thought, right, that's what, I mean, that's what they're taught to think about us and we're taught to think about them. And like now we're back in an us, them, right? When, you know, we're all trying to survive and we're all such, you know, human life is so delicate, right? You know, let alone human happiness. And we make these divisions and we create this aggression and latent aggression. I mean, during the Cold War, we developed, right, the ability to destroy the earth, right? And then just sat looking at one another, you know, with further growing misunderstanding and the opportunity for the proxy fights, like when they say the Cuban Missile Crisis, which I know wasn't a war, but it's an aspect of that, right? Where we just have ourselves wildly, you know, at risk of destruction without any mutual understanding. And again, I would argue that that is the opposite of the counter entropy, right? Like we are setting everything up for less lack of communication, lack of understanding. How do those feelings of love and shared humanness happen? They don't, right? If you separate people and then we push ourselves more and more and more towards reinstating the state of entropy </s>

<s>[INST] I talked to jocko on this podcast, I told him about a song called Brothers in Arms by dire straits. And uh the question I asked them, I'd like to ask you the same question is um like the song goes, do you think we're fools to wage war in our brothers in arms? And Jaco said our enemy is not our brothers in arms that are the enemy. And so this kind of notion that we're all human. That's a notion that's a luxury you can have. But there is good and bad in this world. According to Jaco, I hear that anger and hate when I was in Ukraine amongst some people were, there was a sense where you could be brothers and sisters, you can have family, you can have love for, from Ukraine to Russia. Um, but now that everything's changed and generational hate for some people have taken over. So I guess the question is um when you think about the enemy [/INST] is </s><s>[INST] there hate, their acknowledge that they're human. I [/INST] had never had any hate or just content, you know, when I was doing my job, I'll say, but I was also never in a true life for death situation where they were gonna kill me if I didn't kill them. Um but you know, I think that environment isn't one born out of hate, you know, being in that type of scenario, you know, since it's how to be alive, right? I mean, that's the our our natural state is fighting for survival in a sense. And so I think there's there's great power and strength and clarity perhaps in that. And it's not always born out of hate, but out of necessity and we can't always control that. And I think as we focus on ourselves so much, we only dance on that pinhead when we find ourselves fighting for things that we need and we're always taking from someone else at this point. And so as someone that's been in combat and very high above it, I'll say right where I didn't feel like I was in particular danger, um I rationalized it and I made my wife do it knowing that there were people on the other side that we're going to die that were on our side than not. So it was always a very human thing. It was never um a reaction emotional reaction of any sense. So </s><s>[INST] you do, you were able to see the basic, it's human versus human. There's some aspect of war that is basically um, one people fighting each other. [/INST] Yes. At the end of the day, you know, especially I would say in aviation tackle aviation, there's almost a kinship with your, your enemies in a sense because you know that, you know them in a sense, right? You know what they've been through, you know, what training they've been through, you know, where they failed. Um, and you know what type of person they are because it's a very unique person that does that job and usually can spot them. </s><s>[INST] I guess it's the kind of respect you have for the craftsmanship of the job they've taken on [/INST] certainly. And that person didn't come out in $100 million jet because I picked them off. You know, it's not an emotional response were both there maybe because we chose to be in some sense, but at the behest of, of someone else and outside of our control and power. And so in a sense for me, it's almost a challenge that we've engaged upon agreeably, but that's such a romantic version that I have the luxury to have being high in my castle and the jet up there, not on the ground. So I understand that it's a bit more romantic than perhaps, you know, someone on the ground experiencing all the horrors down there because everything looks very small from above </s><s>[INST] and that's another aspect of war with greater autonomy when you're controlling the mission versus uh, you know, have agendas, con type of intimacy in terms of the actual experience of war, where you directly have you murdered with a sword versus a gun versus a remotely controlled drone versus a strategic mission assignment to an autonomous drone that executes [/INST] abstracted away until it's just a small decision. </s><s>[INST] And my worry is the people without a voice are, are completely forgotten and silenced in all these calculations. I spoke to a lot of people, poor people, they feel like they've never really had a voice and um, and they're too easily forgotten even within the country of Ukraine. It's the, the big city versus the world divide. You know, it's easy to forget the people that don't have a twitter account and don't, um, that their basic existence is just trying to survive. Trying to put food on the table and they don't have anything else. Um, anything else in the day are the ones that truly feel the pain of war, of the supply chain going down of the food supply is going down of the cold winter without power. Um, [/INST] you're </s><s>[INST] still young, but you've seen some things. So let me ask you to put on your wise sage hat and uh, give advice to young people whether they're fascinated by technology or fascinated by fighter jets, whether they're fascinated by sort of engineering or the way the stars look at night, What advice would you give them? How to have a career that can be proud of or how to have a life they can be proud of. [/INST] I'd suggest that they don't fear looking foolish. I spent a large portion of my life, uh, considering the laughter or the comments of my statements as an indication that I shouldn't pursue that. </s><s>[INST] And [/INST] so, you know, I didn't, I kind of woke up to that fact a bit later, but I would encourage, you know, I would advise that people, you know, trust in themselves and trust in the things that they care about. It doesn't matter if they're good at it. All that matters is that they find something that they can apply love and care to and they will grow better at it and they'll most likely make the world better because of it </s>

<s>[INST] try [/INST] crazier stuff. I don't know even if it doesn't work like hopefully you'll um you're advance the state of affairs like something interesting will happen and so most people today, they look at, they look at people trying this stuff and they're like oh my God, they're so they're a genius or whatever and it's like they're an idiot, like one of one of the two, neither neither one are true, It's just like um anybody can start by thinking about what they want and then like go for it and then once you get that, like go for something a little bigger and like you just have fun with it </s><s>[INST] and the universe is a way of smiling and helping you out if you just write it down and and you dream big. So there's something about just karma, about the energy you put into this world, other people will help you out, doors will open, you'll notice that the doors opened and you you can actually have a shot at making it happen. It's a funny world. [/INST] Yeah, I mean I don't I don't really subscribe to all like the wu interpretations of this, but my my very rational brain interpretation of it is that if you just wake up every day and write down like what you want to get done and towards your longer goals at your larger goals, it's just, it's just on your mind that day, so you start to notice opportunities and you think about it more so </s><s>[INST] so brian, thank you for drinking big um thank you for doing what you're doing, doing incredible engineering at scale trying to help out people from all over the world and um actually helping me personally get more into crypto just because it's so easy. So um thank you so much and thank you so much for giving your extremely valuable time today to this awesome conversation. [/INST] Thanks for your awesome podcast. I love it and I listen to it </s><s>[INST] often. Thanks for listening to this conversation with brian Armstrong Support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Benjamin franklin, an investment in knowledge pays the best interest. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] The ad reads today are great. So simply safe is the protection of physical space. Expressly pianist. The initial protection in digital space. How cool would it be if there is not like a hybrid physical digital space. And then we have tools that we can carry from the physical to the digital and back. The protection will come along with us. And of course, if the anarchists have their say that will be provided by private companies and we'll compete over their customers and through that process of capitalism would then create the best product and the most affordable product that is if the anarchists have their way Michael malice has entered the chat anyway, go to simply safe dot com slash legs to customize your system and get a free security camera. Yes, friends. I said free again, that's simply safe dot com slash lex. And now here's my conversation with cal Newport's what is deep work. Let's start with a big question. [/INST] So, I mean, it's it's my term for when you're focusing without distraction on a cognitive demanding task, which is something we've all done. But we had never really given it a name necessarily that was separate from other type of work. And so I gave it a name and said, let's compare that to other types of efforts you might do while you're working and see that the deep work efforts actually have a huge benefit that we might be underestimating </s><s>[INST] what does it mean to to work deeply on something. [/INST] You know, I have been calling it hard focus in my riding before that. Well, so the context you would understand I was in the theory group in C sale at MIT. Right? So I was surrounded at the time when I was coming up with these ideas by these professional theoreticians and that's like a murderer's row of thinkers. They're right. I mean it's like turing award turing award, macarthur turing award. I mean, you know the crew, right? Theoretical computer science. Theoretical computer science. Yeah. Yeah. So so I'm in the theory group right? Doing theoretical computer science. And I published a book. So you know, so I was in this milieu whereas being exposed to people, We're focused was their tier one skill. Like that's what you would talk about right? Like how how intensely I can focus. That was the Wiki Skill. It's like you're 4:40 time or something if you were an athlete. Right? </s><s>[INST] So this is something that people were actually the theory folks are thinking [/INST] about really </s><s>[INST] like they're openly discussing. Like how do you focus? [/INST] I mean, I don't know if they would, you know, quantify it but but focus was the tier one Skill. So you you would come in here would be a typical that you'd come in uh and eric domain would be sitting in front of a white board right? With a whole group of visitors who had come to work with them and maybe they projected like a grid on there because they're working on some graph theory problem. You go to lunch, you go to the gym, you come back. They're sitting there staring at the same same white board, right? Like that's the tier one skill. This is the </s><s>[INST] difference between different disciplines. Like I I often feel for many reasons like a fraud but I definitely feel like a fraud. When I hang out with like either mathematicians or physicists, it's like, it feels like they're doing the legit work because when you talk closer and computer science to get to programming or like machine learning, like the the experimental machine learning or like just the engineering version of it, it feels like you're gone so far away from what's required to solve something fundamental about this universe. It feels like you're just like cheating your way into like some kind of trick to figure out how to solve a problem in this one particular case. That's how it feels like it's uh I'd be interested to to hear what you think about that because um programming doesn't always feel like you need to think deeply to work deeply. But sometimes it does, it's a weird dance [/INST] for sure code does right? I mean, especially if you're coming up with original algorithmic designs. I think it's a great example of deep work. I mean yeah, the hardcore theoreticians, they push it to an extreme. I mean I think it's like knowing that athletic endeavor is good and then hanging out with an olympic athlete like, Oh I see that's what it is now for the grad students like me, we're not anywhere near that level, but the faculty, the faculty in that group, these were the cognitive olympic athletes, but Cody and I think is a classic example of deep work because I got this problem I want to solve, I have all of these tools and I have to combine them somehow creatively and on the fly, but so basically I had been exposed to that. So I was used to this notion when I was in grad school and I was writing my blog, I write about hard focus, you know, there was a term I used, Then I published this book, so good, they can't ignore you, which came out in 2012. So like, right, as I began as a professor and that book had this notion of skill being really important for career satisfaction, that it's not just following your passion, you have to actually really get good at something and then you use that skills as leverage. And there's this big follow up question to that book, Okay, well how do I get really good at that? And then I look back to my grad school experience, I was like, huh, there's this focus thing that we used to do, I wonder how generally applicable that is into the knowledge sector. And so as I started thinking about it, it became clear there is this interesting storyline that emerged, okay, actually undistracted concentration is not just important for esoteric theoreticians, it's important here and support here and support here and that involved to the deep work hypothesis, which is across the whole knowledge work sector, focus is very important and we've accidentally created circumstances where we just don't do a lot of it. </s><s>[INST] So focus is the sort of prerequisite for basically you say knowledge work, but basically any kind of skill acquisition, any kind of major effort in this world, Can we break that apart a little bit? [/INST] Yeah, so, key key aspect of focus is not just that you're you're concentrating hard on something, but you do it without distraction. So, a big theme of my work is that contact shifting kills the human capacity to think. So if if I if I change what I'm paying attention to do something different really, even if it's brief and then try to bring it back to the main thing I'm doing that causes a huge cognitive pilot, that makes it very hard to think clearly. So, even if you think, okay, look, I'm writing this code, I'm writing this essay and I'm not multitasking and all my windows are closed and have no notifications on, but every five or six minutes, you quickly check like an inbox or your phone that initiates a contact shift in your brain, right? We're gonna start to suppress some neural networks are gonna try to amplify some others. It's a pretty complicated process actually, there's a neurological cascade that happens, You rip yourself away from that halfway through and go back to what you're doing. And I was trying to switch back to the original thing even though it's also in your brains in the process of switching to these emails and trying to understand those context and as a result your ability to think clearly just goes really down and it's fatiguing too. I mean you do this long enough, you get midday and like okay, I can't, I can't think anymore. You've exhausted yourself. </s><s>[INST] Is there some kind of perfect number of minutes would you say? So we're talking about focusing on a particular task for You know, one minute, five minutes, 10 minutes, 30 minutes. Is it possible to kind of context switch while maintaining deep focus, you know, every 20 minutes or so. So if you're thinking of like this again, maybe it's a selfish kind of perspective, but if you're thinking about programming, you know, you're focused on a particular design of a little bit, maybe a small scale on a particular function or large scale on a system and then the shift of focus happens like this, which is like wait a minute, is there a library that can achieve this little task or something like that? And then you have to look it up, this is the danger zone, you go to the internet and and so you have to now you it is a kind of contact switch because as opposed to thinking about the particular problem, you not have switched Thinking about like uh consuming and integrating knowledge that's out there that can plug into your solution to a particular problem. It definitely feels like a context which but is that is that a really bad thing to do? So should you be setting it aside always and really trying to as much as possible go deep and stay there for like really long period of time? [/INST] Well, I mean, I think if you're looking up a library that's relevant to what you're doing, that's probably okay. And I don't know that. I would count that as a full context shift because the semantic networks involved are relatively similar, right? You're thinking about this type of solution, you're thinking about coding, you're thinking about this type of functions where you're really going to get hit is if you switch your context to something that's different And if there's unresolved obligation, so really the worst possible thing you could do would be to look at like an email inbox, right? Because here's 20 emails I can't answer most of these right now, they're completely different. Like the context of these emails, like okay, there's a grant funding issue or something like this is very different than the coding I'm doing and I'm leaving it unresolved, like someone needs something from me and I'm gonna try to pull my attention back. The second worst would be something that's emotionally arousing so if you like, let me just glance over at twitter, I'm sure it's nice and calm and peaceful over there right? That can be devastating because you're gonna expose yourself to something that's emotionally arousing. That's going to completely mess up the cognitive plateau there. And when you come back to okay let me try to code again. It's really difficult. </s><s>[INST] So it's both the information and the emotion. [/INST] Both both can be killers if what you're trying to do. So I would recommend at least an hour at a time because it could take up to 20 minutes to completely clear out the residue from whatever it was you were thinking about before. So if you're coding for 30 minutes you might only be getting 10 or 15 minutes of actual sort of Peake what's going on there? Right? So an hour at least you get a good 40 45 minutes plus I'm partial to 90 minutes is a really good really good chunk. We can get a lot done but just before you get exhausted you can sort of pull back a little bit. </s><s>[INST] Yeah and one of the beautiful and you know people can read about in your book deep work but and I know this has been out for a long time and people are probably familiar with many of the concepts but it's still pretty profound. It has stayed with me for a long time. Uh there's something about adding the terms to it that actually solidifies the concepts like words matter. It's pretty cool and uh just for me sort of as a comment, there is uh it's a struggle and it's very difficult to maintain focus for a prolonged period of time, but the days on which I'm able to accomplish several hours of that kind of work, I'm happy, so forget being productive and all that. I'm just satisfied with my life. I'm I feel I feel fulfilled. Its like joyful and then I, I can be, I'm less of a dick to other people in my life afterwards. It's a, it's a beautiful thing and there I find the opposite when I don't do that kind of thing. I'm much more irritable. Like I feel like I didn't accomplish anything and there's the stress that then the negative emotion builds up to where you're no longer able to sort of uh enjoy the hell out of this amazing life. So, so that sounds deep. Work has been a source of a lot of uh happiness? I'd love to ask you, how do you, again, you cover this in the book? But how do you integrate deep work into your life? What are different scheduling strategies that you would recommend? Just at a high level? What are different ideas there? [/INST] Well, I mean, I'm a big fan of time blocking, right? So if you're facing your workday, don't allow your inbox or to do list to sort of drive. You don't just come into your day and think what do I want to do next? I mean, I'm a big plan is saying, here's the time, here's the time available. Let me make a plan for it, right? So I have a meeting here of an appointment here, here's what's left, what do I actually want to do with it? So in this half hour I'm going to work on this for this 90 minute block, I'm gonna work on that and during this hour I'm going to try to fit this in and then actually this half hour gap between two meetings. So why don't I take advantage of that to go run five errands? I can kind of match those together, but blocking out in advance. This is what I want to do at the time available. I mean, I find that's much more effective now, once you're doing this, once you're in a discipline of time blocking, it's much easier to actually see. This is where I want, for example, to deep work and I can get a handle on the other things that need to happen and find better places to fit them so I can prioritize this and you're gonna get a lot more of that done then if it's just going to your day and saying what's </s><s>[INST] next schedule every single day kind of thing. So it's like try to in the morning to try to uh have a plan. [/INST] Yeah, so, you know, I do a quarterly weekly daily planning. So at the semester or quarterly level, I have a big picture vision for what I'm trying to get done during the fall, let's say. Or during the winter like I wanted, these are, there's a deadline coming up for academic papers at the end of the season. Here's what I'm working on. I want to have this many chapters done of a book, something like this. Like you have the, the big picture vision of what you want to get done. Then weekly you look at that and then you look at your week and you put together a plan for like, okay, what am I gonna, what's my week going to look like? What do I need to do? How am I gonna make progress on these things? Maybe maybe I need to do an hour every morning or I see that monday is my only really empty day. So that's gonna be the day that I really need to nail on writing or something like this. And then every day you look at your weekly plan and so we block off the actual hours. So you do that, that three scales the quarterly down the weekly down to daily. </s><s>[INST] And we're talking about actual times of day versus so the alternative is what I end up doing a lot and I'm not sure it's the best way to do it is uh, scheduling the duration of time. This is, this is called the luxury when you don't have any meetings. I'm like religiously don't do meetings? [/INST] All other academics are jealous of you? </s><s>[INST] Yeah, no, no zoo meetings. I find those are, that's one of the worst tragedies. Tragedies of the pandemic is both the opportunity to okay, the positive thing is to have more time with your family, you know, sort of reconnect in many ways. And that's really interesting be able to remotely sort of not waste time on travel and all those kinds of things. The negative, actually, both those things are also sources of the negative, but the negative is like, it seems like people have multiplied the number of meetings because they're so easy to schedule and there's nothing more draining to me intellectually, philosophically. Just my spirit is destroyed by even a 10 minute Zoom meeting. Like, what are we doing here? [/INST] What's the meaning of life? </s><s>[INST] I have every zoom meeting is I have an existential crisis. [/INST] So, Kierkegaard with internet connection. </s><s>[INST] Uh, so, uh, what the hell are we talking about? Uh So, when you don't have meetings, there's a luxury to really allow for certain things if they need to, like the important things like deep work sessions to last way longer than you may be planned for. I mean, that's my goal is to try to schedule. The goal is to schedule to sit and focus for a particular task for an hour and hope I can keep going and hope I can get lost in it. And uh, do you, do you find that this is at all an okay way to go and uh, the time blocking is just something you have to do to actually be an adult and operate in this real world Or is there some magic to the time blocking? [/INST] Well, I mean there's magic to the intention. There's magic to it if you have varied responsibilities, right? So I'm often juggling multiple jobs essentially. There's, there's academic stuff, there's teaching stuff, there's books stuff, there's the, the business surrounding surrounding my book stuff, but I'm of your same mindset. If a deep work session is going well, yes, rock and roll and let it, let it go on. So like one of the big keys of time block, at least the way I do it. So I even, you know, sell this planner to help people time block. It has many columns because the discipline is, oh, if your initial schedule changes, you just move over one next time you get a chance to move over one column and then you just fix it for the time that's remaining. So in other words, there's not, there's no bonus for I made a schedule and I stuck with it. Like there's actually just like you get a prize for it, right? Like for me, the prizes, I have an intentional plan for my time. And if I have to change that plan, that's fine. Like the state I want to be is basically at any point in the day I thought about what time remains and and gave it some thought for what to do because I'll do the same thing even though I have a lot more meetings and other types of things I have to do with my various jobs and I basically prioritized the deep work and they get yelled at a lot. So that's my strategy is like just be okay, just be okay getting yelled at a lot because I feel you if you're rolling. Yeah, well that's that's what it is for me like with writing, I think it's writing so hard in a certain way that you don't really get on a roll in some sense. Like it's just difficult but working on proofs, it's very hard to pull yourself away from a proof. If you start to get some traction, just, you've been at it for a couple hours and you feel the depends and tumbler starting to click together and progress is being made. It's really hard to pull away from that. So I'm willing to get yelled at by almost everyone. </s><s>[INST] Of course there is also a positive effect too, pulling yourself out of it when things are going great because then you're kind of excited to resume, you're supposed to stopping in a dead end. There's the yeah, there's a, there's an extra force of procrastination that comes with, if you stop on a dead end to return to the [/INST] task or, or a cold start, get whenever I feel like I'm at a stage now. I submitted a few papers recently. So now we're sort of starting something up from cold and it it takes way too long to get going because it's very hard to it's very hard to get the motivation to schedule a time when it's not Yeah, we're in it, here's where we are. We feel like something is about to give here and in the very early stages where it's just, I don't know, I'm going to read hard papers and it's gonna be hard to understand them and I have no idea how to make progress is not, it's not motivating. </s><s>[INST] What about deadlines? Can we uh Okay, so this is like a therapy session uh Why? It seems like I don't I only get stuff done that has deadlines. And so the one of the implied powerful things about time blocking is there's a kind of deadline or there's uh artificial or real sense of urgency. Do you think it's possible to get anything done in this world without deadlines? Why why deadlines work so? Well? [/INST] Well, it's I mean it's a clear motivational signal, but in the in the short term you do get an effect like that in time blocking. I think the strong effect you get by saying this is the exact time I'm going to work on this is that you don't have the debate with yourself every three minutes about should I take a break now, right? Like this is the big issue is just saying, you know, I'm going to go, right, I'm going to write for a while and that's it because your mind is saying, well obviously we're going to take some breaks. We're not just going to write forever. And so why not? Right now, you have to like, well not right now, let's go a little bit longer, five minutes. Why don't we take a break now? Like we should probably look at the internet now. You have to constantly have this battle. On the other hand, if you're in a time block schedule, like I've got these two hours put aside for writing, that's what I'm supposed to be doing. I have a break scheduled over here. I don't have to fight with myself. Right? And maybe at a larger scale deadlines give you a similar sort of effect is I know this is what I'm supposed to be working on because it's uh it's do </s><s>[INST] perhaps but we are describing as much healthier sort of giving yourself over and you talk about this in in the new email book. The process. I mean general, you talk about it all over is creating a process and then giving yourself over to the process. The but then you have to be strict with yourself. Yeah, [/INST] but what are the deadlines you're talking about like with papers like what's the main type of deadline work? </s><s>[INST] Uh also papers, definitely. But you know, publications like say this, this podcast. Uh I have to publish this podcast next early next week one because your book is coming out. I'd love to serve uh support this amazing book. But the other is I have to fly to Vegas on thursday To run 40 miles with David Goggins. And so I want this podcast that this conversation we're doing now to be out of my life. Like I don't want to be in the hotel in Vegas, like editing the like freaking out while David Goggins [/INST] is yelling hour an hour and 43 your terror. Exactly. But </s><s>[INST] actually it's possible that I still will be doing that, you know, because it's that's not a heart. That's a software deadline, right? But those are sort of life imposes these kinds of deadlines. Um I'm not so yeah, papers are nice because there's an actual deadline. Uh but I am almost referring to like the pressure that people put on you. Hey man, you said you're going to get this done two months ago. Why? And you've gotten it [/INST] done. I don't see, I don't like that pressure. Yeah, I mean, first, I think we can hate it too. We can agree by the way having David Goggins yell at you is probably the top productivity technique. I think we'd all get a lot more done if he was yelling. But see I don't like that. So I I will try to get things done early. I like, I like having flex. I also don't like the idea of this has to get done today, right? Like it's due at midnight and we've got a lot to do as the night before because then I get in my head about what if I get sick or like what if you know what if I I don't get a bad night's sleep and I can't think clearly. So I'd like to have the flex. So I'm all process and that's like the philosophical aspect of that book, deep work is that there's something very human and deep about just wrangling with the world of ideas. I mean Aristotle talked about this. If you go back and read the ethics, he's trying to understand the meaning of life and he eventually ends up ultimately at the human capacity to contemplate deeply. It's kind of a theological argument is the things that only humans can do and therefore it must be somehow connected to our ends. And he said ultimately that's where that's re found his meaning. But you know, he's touching on some sort of information there. That's correct. And so what I try to build my life around is regularly thinking hard about stuff that's interesting just like if you get a fitness habit going, you feel off when you don't do it. I try to get that cognitive habit. So it's like, I gotta, I mean look, I have my bag here somewhere in my notebook in it because I was thinking on the Uber ride over? I was like, you know, I could get some, I'm working on this new proof and it just so you train yourself, you train yourself to appreciate certain things. And then over time the hope is that it creates </s><s>[INST] well, let's talk about some demons because I wonder if there's like deep work, which uh and uh the world without email books that to me symbolize the life I want to live okay. And then there is, I'm like despite appearances adult at this point and this is the life I actually live and I it's I'm in constant chaos. You said you don't like that anxiety? I hate it too. But it seems like I'm always in it. It's a giant mess. It's like, it's almost like whenever I established whenever I have successful processes for doing deep work, I'll add stuff on top of it just to introduce the chaos and and like, I don't want to, but you know, it's so you have to look in the mirror at certain point and you have to say like who the hell am I Like, I keep doing this. Is this something that's fundamental to who I am or do I really need to fix this? [/INST] What's the chaos right now? Like I've seen your video about like your routine, it seemed very structured and deep and in fact I was really envious of it. So like what's the chaos now? That's not in that video, </s><s>[INST] many of those sessions go way longer. I don't get enough sleep. And then the main introduction of chaos is it's taken on too many things on the to do list. It's I mean, I suppose it's a problem that everybody deals with was just saying not saying no, but it's not like I have trouble saying no. It's that there's so much cool ship in my life. Okay, listen, there's nothing I love more in this world than the boston dynamics robots. [/INST] Yeah. </s><s>[INST] And they're giving me spot. So there's a lot to do with what am I going to say? No. So they're getting the spot and I want to do some computer vision stuff for the hell of it. Okay, so that's not what to do item [/INST] and then you go to texas for a while and there's texas and everything is happening at all the interesting people down there. </s><s>[INST] And then there's surprises right there, power outage in texas, there's constant changes to plans and all those kinds of things and you sleep less and then there's personal stuff like just, you know, people in your life sources of stress all those kinds of things and but it does feel like if I'm just being introspective that I bring it onto myself. I suppose a lot of people do this kind of thing is, is they, they flourish under pressure and I wonder if that if that's just a hack I've developed as a habit early on in life that needs, you need to let go of, you need two things. [/INST] But it's all interesting things. Yeah, that's, that's, that's interesting because these are all interesting things. </s><s>[INST] Well, one of the things you talked about deep work, which is like really important, like having an end to the day, like putting it down. I think that I don't think I've ever done in my life. [/INST] Yeah. Well, see I started doing that early because uh, I got married early, so you know, I didn't have a real job. I was a grad student, but my wife had a real job. And so I just figured I should do my work when she's at work because you know, when, when work's over, she'll be home. I don't want, I don't want to be, you know, on campus or whatever. And so real early on, I just got in that habit of this is when this is when you didn't work. And then when I was a postdoc, which is kind of an easy job, right? Um, I put artificial, I was like, I want to train, I was like, well I'm a professor is going to be busier because there's demands that professors have beyond research. And so as a postdoc, I added artificial large time consuming things into the middle of my day. I basically exercise for two hours in the middle of the day and do all this productive meditation and stuff like this While still maintaining the 9-5 because I was like, Okay, I want to get really good at putting artificial constraints on so that I stay, I didn't want to get flabby when my job was easy, so that when I became a professor and now all of that's paying off because I have a ton of kids, so so now I don't really have a choice. That's what's probably keeping me away from cool things is I just don't have time to do them. And then after a while people, you know, stop bothering </s><s>[INST] well, but you know, but that's how you have a successful life, otherwise you're going to, it's too easy to then go into the full hunter as Thompson like to wear no, nobody wants, nobody functional wants to be in your vicinity, like you're driving your attract the people that have a similar behavior pattern as you. So if you, if you live in chaos, you're going to attract chaotic people and then then it becomes like this self fulfilling prophecy and it feels like I'm not bothered by it, but I guess this is all coming around to exactly what you're saying, which is like, I think one of the big hacks for productive people that I've met is to get married and have kids. Honestly, it's, it's very, perhaps counterintuitive, but it gets, it's like the ultimate timetable and enforcer. [/INST] Yeah, it enforces a lot of time tables. Uh though it has a huge kids have a huge productivity, hit those, you gotta weigh it, but you're okay. Here's the complicated thing though, like you can think about in your own life, starting the podcast is one of these just cool opportunities that you put on yourself, right? Like, you know, I could have been talking to at M. I. T. Four years ago and like don't do that, like your research is going well, right? But then everyone who watches you was like, okay, this podcast is the direction that's taking you is like a couple of years from now, it's gonna be something really monumental that you're probably going to probably lead to, right? There'll be some really, it just feels like your life is going somewhere, </s><s>[INST] it's going somewhere, it's interesting, unexpected. [/INST] Yeah, So how do you balance those two things? And so what I try to throw at it, is this this motto of do less, do better know why, right? So do do less, do better know why it used to be the motto of my website years ago, so do a few things, but like an interesting array, right? So I was doing uh M. I. T. Stuff, but I was also writing, you know, so a couple of things are, you know, they were interesting, like I have a couple bets placed on a couple different numbers on the roulette table, but not too many things and then really try to do those things really well and see where it goes like with my writing, I just spent years and years and years of training, I want to be a better right, I want to be a better writer. I started writing student books and I was a student um I really wanted to write hardcover idea books. I started training, I would, I would use like new yorker articles to train myself, I'd break them down and then I'd get commissions with much smaller magazines and practice the skills and and it took forever until you know, but now today like I actually get it right for the new yorker but it took like a decade, so a small number of things try doing really well and then you know why is have a connection to some sort of value like in general, I think this is worth doing. Uh and then seeing where it leads </s><s>[INST] and so the choice of the few things is grounded in what like a little like a like a little flame of passion, like a love for the thing, like a sense that you say you wanted to write, get good at writing, you had that kind of introspective moment of thinking this section brings me a lot of joy and fulfillment. [/INST] Yeah, I mean it gets complicated cause I wrote a whole book about Following your passion being bad advice which is like the first thing I kind of got infamous for, I wrote that back in 2012. But, but the argument there is like passion cultivates, right? So what I was pushing back on was the myth that the passion for what you do exist full intensity before you start. And then that's what propels you, or actually the reality is as you get better at something, as you gain more autonomy, more skill and more impact of passion grows along with it. So that when people look back later and say, oh, follow your passion, what they really mean is I'm very passionate about what I do and that's a worthy goal. But how you actually cultivate that is much more complicated than just introspection can identify. Like for sure you should be a writer or something like that. So </s><s>[INST] I was actually quoting I was on a social network last night, uh, in the clubhouse and in front [/INST] of it, I was like, I have to, I have to ask you about this because I was invited, I'm invited to do a clubhouse. I don't know what that means. A tech reporter has invited me to do a clubhouse about my new book. </s><s>[INST] That's awesome. Uh, well let me know what, because I'll show up, but what is it? Okay, so first of all, let me just mention that I was in a club house room last night and I kept plugging your exactly what exactly you said about passion. So we'll talk about it, it was a room that was focused on burnout. Uh, but first clubhouse is kind of fascinating place in terms of your mind would be very interesting to analyze this place because, you know, we talk about email without about social networks, but clubhouse is something very different and I've encountered in other places discord and so on. That's voice by only communication. So it's a bunch of people in the room, they're just eyes closed. All you hear is their voices real time, real time live. It only happens live, you're technically not allowed to record, but some people still do and, you know, especially when it's big, big conversations, but the whole point is that they're live and there's different structures like on discord, it was so fascinating. I have this discord server that would have hundreds of people in a room together, right? We're all just little icons that commute and a mute our mix. And so you're sitting there not. So it's it's just voices and you're able, with hundreds of people to not interrupt each other. First of all, like as a dynamic system, like [/INST] you see icons just like mike's muted or not muted basically. </s><s>[INST] So everyone is muted and they knew and they start, it starts flashing. [/INST] And so you're like, okay, let me get precedence. So it's the digital equivalent of when you're in a conversation, like a faculty meeting and you sort of uh kind of make some noises like all the other person's finishing. And so people realize like, okay, this person wants to talk next. But now it's purely digital, you see a flashing, </s><s>[INST] but in a faculty meeting, which is very interesting. Like even as we're talking now, there's a visual element that seems to increase the probability of interruption when it's just darkness, you actually listen better and you don't interrupt. So like if you create a culture, there's, there's always gonna be assholes, but they're, they're actually exceptions. Everybody adjust. They kind of evolved to the beat of the room. Okay, that's one fascinating aspects like, okay, that's weird because it's different than like a zoom call with this video. Uh, it's just audio, you think video ads, but actually seems like it subtracts. The second aspect of it. That's fascinating is when it's no video, just audio, there's an intimacy. It feels as weird because with strangers, you connect, you know, in a much more real way. It's very similar to podcast, but [/INST] a lot of people with </s><s>[INST] a lot of people and new people and then you and they, they bring, okay, first of all different voices, like low voices and like high voices and, and it's more difficult to judge in this court, you couldn't even see, uh, the people, it was a culture where you do funny profile pictures as opposed to your actual face, your clubhouse, it's your actual face. So you can tell like as an older person, younger person in discord, you couldn't, you just have to judge based on the Voice, but there's a, there's something about the listening and the intimacy of being surprised by different strangers that feels almost like, uh, a party with friends and friends of friends you haven't met yet, but you really like now club house also has an interesting innovation where there's a large crowd that just listens and there's a stage and you can bring people up on the stage. So only people on stage you're talking and you could have like 5678, sometimes 2030 people on stage. And then you can also have thousands of people just listening. So [/INST] there's a, I don't know, </s><s>[INST] a lot of people are being surprised by this, [/INST] what I call the social network. It seems like it doesn't have, there's not social links, there's not a feed that's trying to harvest attention. It feels like a communication. </s><s>[INST] Uh, so the social network aspect is you follow people and the people you follow. Now this is like the first social network that's actually correct use of follow, I think you're more likely to see the rooms they're in. So there's a, your feed is a bunch of rooms that are going on right now and the people you follow are the ones that will increase the likelihood that you'll see the room they're in and so the final result is like there's a list of really interesting rooms like um I have all these, I've been speaking Russian quite a bit. They're practicing, but also just like talking politics and philosophy and Russian. I've never done that before, but it allows me to connect with that community and then uh there's a community of like, it's funny, but like I'll go in a community of all african american people talking about race and I'll be welcomed. I've never had like I've literally never been in a difficult conversation about race, like with people from all over the place. It's like fascinating and musicians, jazz musicians, I don't know, you could say that a lot of other places could have created that culture, I suppose twitter and facebook, a lot of that culture. But there's something about this network as it stands now because no android users, it's probably just because it's iphone people. Uh it's a conspiratorial or something like less listen, I'm an android person. So I I got an iphone just for this network. This is funny uh is for now it's all like there's very few trolls, there's very few people, they're trying to manipulate the system and so on. So I don't know, it's it's interesting now, the downside, the reason you're going to hate it is because it's so intimate because it pulls you in and pulls in very successful people like you just like really successful, productive, very busy people. Uh it it's a huge time sink. It's very difficult to pull yourself out [/INST] interesting. You mean once you're in a room? </s><s>[INST] Well no, they're leaving the room is actually easy. The beautiful thing about a stage with multiple people. There's a little button that says leave quietly. So culture, uh no adequate wise, it's okay to just leave. So you and I in the room when it's just you and I, it's a little awkward to leave if you're asking [/INST] Questions on this one, </s><s>[INST] but, and actually, if you're being interviewed for the book, that's weird because you're now in the event and you're supposed to, but usually the person interviewing would be like, okay, it's time for you to go, it's more normal, but the normal way to use the room, it's like you're just opening the app and they'll be like, I don't know, Sam Harris, ah eric Weinstein, I think joe Rogan showed up to their bill gates and these people on stage, just like randomly just plugged in and then you step up on stage. Listen, maybe you won't contribute at all, Maybe you'll say something funny and then you would just leave and there's the addicting aspect to it. The reason it's a time sink is you don't want to leave. What I've noticed about exceptionally busy people that they loved this, this the there I think might have to do with the pandemic because there's a little, there's a loneliness there longer, but also it's really cool people, like when was, when was the last time you talked to Sam Harris or whoever, like I think of anybody. Uh Tyler like any any faculty. [/INST] This is like what universities strive to create, but it's taken because you don't have a cultural evolution and try to get a lot of interesting smart people together that run into each other. We have really </s><s>[INST] strong faculty in a room together with no scheduling. This is the power of it is like you just show up, there's no none of that baggage of schedule and so on and there's no pressure to leave. Uh Sorry, no pressure to stay. It's very easy for you to leave. You realize that there's a lot of constraints on meetings and like faculty, there's uh like even stopping by before the pandemic, a friend or faculty colleague and so on. You know, there's a weirdness about leaving. Uh but here there's not a weirdness about leaving. So they've discovered something interesting, but the final result when you observe it is uh it's very fulfilling. I think it's very beneficial, but it's very addicting. So you have to make sure you moderate. [/INST] Yeah, that's interesting and Okay, well, so maybe I'll try it. I mean look, there's no the things that make me suspicious about other platforms aren't here. So the feed is not full of user generated content that is going through some sort of algorithmic rating process with all the weird incentives and Nudging that does uh And you're you're not producing content that's being harvested to be monetized by another company. I mean, it seems like it's more ephemeral, right? You're you're here, you're talking the feed is just actually just showing you here's interesting things happening, right? You're not jockeying in the feed for, look, I'm being clever or something and I'm going to get a light count that goes up and that's going to influence and and there's more friction. There's more cognitive friction, I guess, involved in listening to smart people versus scrolling through. Yeah, there's something there. </s><s>[INST] So there's no why [/INST] are people? So I say, all right, there's all these articles that seem I haven't really read them. Why are why are reporters negative about this </s><s>[INST] competition? The new york Times wrote this article called Unfettered conversations happening on clubhouse is uh, [/INST] I'm right. And picking up a tone from, even from the headlines that there's some negative vibes from the press </s><s>[INST] know. So I can say, let's say, well, I'll tell you what the article was saying, which is uh, they're having cancel herbal conversations like the biggest people in the world almost trolling the press and the press is destined for the press by saying that you just you guys are looking for Clickbait from our genuine human conversations. And so the I think the honestly the press is just like what do we do with this? We can't um first of all, it's a lot of work for the, okay, uh it's what novel says, which is like, this is skipping the journalist, like the interview you, if you go on clubhouse to interview, you might do for the book would be with somebody who is like a journalist and interviewing you. That's more traditional. It would be a good introduction for you to try it. But I like the way to use clubhouse as you just show up and it's like, again like me, I'm sorry. Like I keep mentioning Sam Harris as if it's like the only person I know, but like a lot of these, uh, major faculty, I don't know, max tech mark. Just just major faculties. You're sitting there and then you show up and then I'll ask like, oh, don't you have a book coming out or something? And then you'll talk about the book and then you leave five minutes later because you have to go get coffee and with the pastor. So like that's the, it's not the journalist that you're not going to actually enjoy the interview as much because it'll be like the normal thing, like you're there 40 minutes or an hour and there will be questions from the audience. [/INST] Like I'm doing an event next week for the book launch where it's like Jason freed and I are Talking about email, but it's using some more like 1000 people who are there to watch virtually. But it's using some sort of traditional webinar clubhouse would be a situation where that could just happen informally, like I jumped in like Jason's there and then someone else jumps in and Yeah, that's interesting. </s><s>[INST] But for now it's still closed. So even though there's a lot of excitement and there would be quite famous people just sitting there listening to you, but the numbers aren't exactly high. So you're talking about rooms like even the huge rooms are like just a few 1000. [/INST] And this is, this is probably soho in the 50s or something to just because of the exponential growth, give it seven more months and if you let one invite gets to invites, begets for advice because pretty soon it'll be everyone and then all the rooms in your feet are going to be whatever </s><s>[INST] marketing, [/INST] performance enhancing drugs or something </s><s>[INST] Like that. But then, and a bunch of competitors, there's already like 30-plus competitors sprung up Twitter spaces or Twitter is creating a competitor that's going to likely destroy clubhouse because they just have a much larger user base and and they already have a social network. So I would be very cautious, of course, the addict development, but it doesn't just like you said, this particular implementation in its early stages, doesn't have the like the uh it doesn't have the context switching problem. [/INST] Yeah, you'll just switch to it, you'll be stuck. Keep a context is great. </s><s>[INST] Yeah, and but then I think the best way I've found to use it is uh to acknowledge that these things pull you in. So I've used it in the past, uh like almost, you know, I'll go get a coffee and I'll tune into a conversation as if that's how I use podcast. Sometimes I'll just play a little bit of a podcast and then, you know, I can just turn it off. The problem with these is suppose you, and it's really interesting. And then the other problem that you'll experience is like, somebody will recognize you and then they'll be like, oh, lex, come on up, come on. No way. I had a question for you. And then it takes a lot for you to go, like, to ignore that. Yeah. So, and then you pulled in and it's fascinating and it's really cool people. So it's like a source of a lot of joy, but it, uh, it's yet to be very, very heavy, very careful. The reason I brought it up is we, uh, there's a room this entire club actually on burnout and I brought you up and I brought David Goggins is the process I go through, which is, you know, my passion goes up and down. It dips. And I don't think I trust my own mind too to tell me whether I'm getting close to burnout or exhaustion or not. I kind of go with David Goggins model of, I mean, he's probably more applying it to running, but uh, when it feels like your mind can't take anymore that you're just 40% at your capacity. It's just like arbitrary levels. The navy seal thing. And then navy seal thing. I mean, you could put that at any percent. But it is remarkable that if you just take it one step at a time, just keep going. It's it's uh similar to this idea of a process. If you just trust the process and you just keep following, even if the passion goes up and down and so on, then ultimately, if you look in aggregate, the passion will increase, your self satisfaction will increase, [/INST] I think. And if you have two things, this has been a big strategy of mind so that you can, what you hope for is off phase, a phase alignment like that sometimes is in phase and that's a problem. But a phase alignments Good. So, okay, my research, I'm struggling out of my book stuff is going well. Right. And so when you, when you add those two waves together, like we're doing pretty well, and then, uh, in other periods, like on my riding, you know, I feel like I'm just not getting anywhere. But I've had some good papers, I'm feeling good over there. So having two things that they can counteract each other. Sometimes they fall into sync and then it gets rough then when, you know, when everything, because everything for me is cyclical, you know, good periods bad periods with all this stuff. So, uh, typically they don't coincide. So it helps compensate when they do coincide. You get really high highs like everything is clicking and then you get these really low lows where like your research is not working, your program is not clicking, you feel like you're nowhere with your writing. Uh, and then it's a little rougher </s><s>[INST] is do you do you think about the concept of burnout? Because so I personally never experienced burnout in the way that folks talk about, which is like, it's not just the up and down. It's like you don't want to do anything ever again. It's like, it's for some people, it's like physical, like to the hospital kind of thing. [/INST] Yeah. So I do worry about it. So when I used to do student writing like writing about students, a student advice. It came up a lot with students at elite schools and I used to call it deep procrastination. But it was a real, really vivid, very replicate herbal syndrome where they stop being able to do schoolwork. Yeah. Like this is, do the professor gives you an extension and the professor gives an incomplete and says you got, you were going to fail the course. You have to hand this in. They can't do it right. It's like it's a complete stop on the ability to actually do work. And I used to counsel students, you have that issue and often it was a combination of this is my the best analysis is you have just the physical and cognitive difficulties of their usual under a very hard load right there. Doing too many majors to an extracurricular is just, you know, really pushing themselves and the motivation is not sufficiently intrinsic. So if you have a motivational center that's not completely on board. So a lot of these kids like what I'm doing with my kids, they would be, you know, their whole town was shrewd enough fireworks that they got in there. Everyone's hope that they were going there. Uh and that they're in three majors, don't wanna let people down, but they're not really interested in being a doctor or whatever. So your, your motivation is not in the right place. The motivational psychologists would say the locus of control was more towards the extrinsic end of the spectrum and you have hardship and you could just fritz out the whole system and so I would always be very worried about that. So I think about that a lot. I do a lot of Multiphase or multi scale seasonality. So I'll go hard on something for a while and then for a few weeks ago, easy, I'll have semesters that are hard and semesters that are easier. I'll take the summer really low. So on multiple scales and in the day I'll go really hard on something, but then have a hard cut off at five. So like every scale, it's all about rest and recovery because I really want to avoid that and I do burnout? I burnt out pretty recently. I get minor burnt out. I got a paper a couple papers that was trying to work through for a deadline a few weeks ago and I wasn't sleeping well and um there's some other things going on and it just, it knocks out and I get sick usually is how I know I pushed myself too far and so I kind of pulled it back and I'm doing this book launch then after this book launch and pulling it back again. So I like I seasonality for rest and recovery, I think it's crucial and at every scale daily, monthly, you know, and then at the annual scale, like an easy summer for example, I think it's like a great idea if that's possible. </s><s>[INST] Okay, you just made me realize that that's exactly what I do because I feel like I'm not even close to burnout or anything even though I'm, I'm in chaos, I feel the right exact ways the seasonality is the, not even the seasonality, but like you always have multiple seasons operating, it's like you said like because when you have a lot of cool ship going on, you, there's always at least one thing that's a source of joy that there's always a reason, I suppose the fundamental thing and I've known people that suffer from depression to the fundamental problem with like the experience of depression and burnout is like why do like life is meaningless? And I always have an answer of like why, why today could be cool [/INST] and you have to contrive it right? If you don't have it, you have to contrive it. I think it's really important. Like okay, well this is going bad. So now is the time to start thinking about. I mean look, I started a podcast during the pandemic is like, this is going pretty bad. But you know what, This could be something really interesting. </s><s>[INST] Deep questions with colony apart. Uh do it all in that voice. I love the podcast by the way. But yeah, I think David Foster Wallace said uh the key to life is to be unbearable. Uh I've always kind of taken that to heart which is like, you should be able to maybe artificially generate anything. Like uh find something in your environment, in your surroundings that's a source of joy. Like everything is fun. [/INST] Yeah. Did you read the pale king? It goes deep on board? Um it means it's like uncomfortable. It's like an uncomfortable meditation on boredom. Like the characters in that are just driven to the extremes of, I just bought three books on board. Um the other day. Uh so now I'm really interested in this topic because I was anxious about my book launch happening this week. I was like, okay, I need something else. So I have this idea for a might do as an article first, but as a book like okay, I need something cool to be thinking about because I was worried about like I don't have a lot going to work the pandemic, what's going to happen, I don't know if it's going to get to. So this is exactly what we're talking about. So I went and I bought a bunch of books and I'm beginning like a whole uh sort of intellectual exploration. </s><s>[INST] Well, I think that's one of the profound ideas and deep work that you don't expand on too much is uh boredom. [/INST] Yeah, well, so the deep work had a superficial idea about boredom which was I had this chapter called embrace boredom and very functional list idea was basically you have to have some boredom in your regular schedule or your mind is going to form a Pavlovian connection between as soon as I feel boredom again, stimuli and once it forms that connection is never going to tolerate deep work. So there's this very pragmatic treatment of boredom of your mind better be used to the idea that sometimes you don't get stimulated because otherwise you can't write for three hours, like it's just not going to tolerate it, but more recently. What I'm really interested in boredom, is it as a fundamental human drive, right? Because it's incredibly uncomfortable and think about the other things that are incredibly uncomfortable like hunger or thirst, they serve a really important purpose for a species, right. Like if something is really distressing, there's a reason, pain is really uncomfortable because we need to worry about getting injured, thirst is really uncomfortable because we need water to survive. So what's boredom? Why is that uncomfortable? And and I've been interested in this notion that boredom is about driving us towards productive action like as a species. I mean think about it like what what got us to actually take advantage of these brains? What got us to actually work with fire? What got us to start shaping stones and the hand axes and figuring out if we could actually sharpen a stick sharp enough that we could throw it as a meal, a weapon or a distance weapon for hunting mammoth, right? Boredom drives us towards action. So now I'm fascinated by this fundamental action instinct because I have this theory that I'm working on that were out of sync with it just like we got, we have this drive for hunger but then we introduce junk food and got out of sync with hunger and it makes us really unhealthy. We have this drive towards action but then we overload ourselves and we have all of these distractions and then that causes uh it's like a cognitive action obesity type things because it short circuits this system that wants us to do things but we put more things on our plate and we can possibly do and then we're really frustrated, we can't do them and we're short circuit all of our wires. So it all comes back to this question. Well what would be the ideal, the ideal, the amount of stuff to do in type of things to do? Like if we wanted to look back at our ancestral environment and say if I could just build from scratch, what type, how much work I do and what I work on to be as in touch with that as like paleo people are trying to get their diets in touch with that. And so now I'm just but see this is I'm just it's something I made up but now I'm going deep on it and one of my podcast listeners I was I was talking about on the show and I was like well I am trying to learn about animals and boredom. And she sent me this cool article from an animal behavioralist journal about what we know about human boredom versus animal boredom. So trying to figure out that puzzle is the wave that's high so I can get through the wave that's low of like I don't know about this pandemic book launch and you know and my research and my research is stumbling a little bit because of the pandemic. And so I needed a nice, you know, high so there we go. There's a case study. </s><s>[INST] Well it's both a case study and very interesting set of concepts because I didn't even realize that it's so simple. I'm one of the people that has uh interesting push and pull dynamic with hunger, trying to understand the hunger with myself. Like I probably have an unhealthy relationship with food, I don't know, but there's probably probably a perfect, that's a nice way to think about diet as action. There's probably an optimal diet response to the the experience that our bodies telling us the signal that the body's sending, which is hunger in that same way boredom is sending a signal. And most of our intellectual activities in this world are creative activities are essentially a response uh, to that signal. [/INST] Yeah. And think about this analogy that we have this hunger instinct that junk food short circuits, right? It's like, oh, well we'll satisfy that hyper palatable e and it doesn't end up well now, think about modern attention engineered, digitally mediated entertainment. We have this board of instinct, oh, we can we can take care of that with a hyper palatable alternative. Is that gonna lead to a similar problem? </s><s>[INST] So, I've been fasting a lot lately, like uh I'm doing um eating once a day. I've been doing that for over a month, just, you know, eating one meal a day. And primarily meat, but it's very uh fasting has been incredible for me for focus for well being for a few, I don't, I don't know, just for feeling good, okay, we'll put on a chart, what makes me feel good and uh that fasting and eating primarily a meat based diet makes me feel really good. And so, but that ultimately what fasting did. I haven't fasted super long yet, like a seven day diet, which I really like to do. But even just fasting for a day for 24 hours gets you in touch with your, with the signal. It's fascinating. Like you get to listen to your, learn to listen to your body that like, you know, it's okay to be hungry. It's like a little signal that sends your stuff and then, and then, uh, I get to listen to how it responds when I put food in my body. Like, and I get to like, okay, cool. So like, food is a thing that pacify, is this signal? Like it sounds ridiculous. [/INST] Okay. You could do that with two different types of food. It feels different. So you learn about what your body. </s><s>[INST] Yes. For some reason fasting, it's similar to the deep or embrace boredom. Fasting allowed me to go into mode of listening of trying to understand the signal that I could say I have an unhealthy appreciation of fruit. Okay, I love apples and cherries. Like I don't know how to moderate them. So if you take just same amount of calories, I don't know calories matter, but they say calories. 2000 calories of cherries versus 2000 calories of steak. If I eat 2000 calories of steak maybe it was just a little bit of like green beans, two cauliflower. I'm going to feel really good, fulfilled, focused and happy, five cherries. I'm going to be, I'm gonna wake up behind a dumpster crying with like naked and like it's just [/INST] all around with everything </s><s>[INST] just like bloated, just not an unhappy and also the mood swings up and down, I don't know. Uh and I'll be much hungrier the next day. Uh, sometimes it takes a couple of days, but when I introduced carbs into the system too many cards, it starts, it's just unhealthy. It's going to this roller coaster as opposed to calm boat ride along the river and the amazon or something like that. So fasting was the mechanism of, for me to start listening to the body. I wonder if you can do that same kind of, I guess that's what meditation a little bit is [/INST] a little bit. But yeah, listen to boredom. But so two years ago I had a book out called digital minimalism And one of the things I was recommending that people do is basically a 30 day fast, but from digital, personal entertainment, social media, online videos, anything that captures your attention into spells boredom and people were thinking like, oh, this is a detox. Like I just want to teach your body not to need the distraction, this or that, but it really wasn't what I was interested in. I wanted there to be space that you could listen to your boredom. like okay, I can't just dispel it can't just look at the screen and revel in it a little bit and start to listen to it and say what is this really pushing me towards? And you take the new stuff, the new technology off the table and sort of ask what is this, what am I craving? Like what's the activity equivalent of 2000 calories of meat with a little bit of green beans on the side. And I had 1700 people go through this experiment, like spend 30 days doing this and it's hard at first, but then they get used to listening to themselves and sort of seeking out what is this really pushing me towards and was pushing people towards, connection was pushing people towards, I just want to go be around other people. It was pushing people towards high quality leisure activities. Like I want to go do something that's complicated and it took weeks sometimes for them to get in touch with their boredom but then it completely rewired how they thought about what do I want to do with my time outside of work. And then the idea is when you're done with that then it was much easier to go back and completely change your digital life because you have alternatives, right? You're not just trying to abstain from things you don't like but that's basically listening to boredom experiment and just be there with the boredom and see where it drives you when you don't have, you know, the digital cheez, its okay, so I can't do that. Where is it going to drive me? Well, I guess I kinda wanna go the library which came up a lot by the way, a lot of people rediscovered the library. </s><s>[INST] You know, physical books, [/INST] physical books, like you can </s><s>[INST] just go borrow them [/INST] And like there's like low pressure and you can explore and you bring them home and then you read them and you can like sit by the window and read them and it's nice weather outside and I used to do that 20 years ago. They're listening to boredom. </s><s>[INST] So can you maybe elaborate a little bit on the different experiences that people had when they quit social media for 30 days? Like, is that if you were to recommend that process, what is ultimately the goal? [/INST] Digital minimalism, that's, that's my philosophy for all this tech and it's working backwards from what's important. So it's you figure out what you're actually all about, like what you want to do, what you want to spend your time doing. And then you can ask, okay, is there a place that tech could amplify or support some of these things and that's how you decide what tech to use. And so the process is let's actually get away from everything, let's be bored for awhile, let's let's really spend a month getting really figuring out what do I actually want to do, what I want to spend my time doing, what's important to me, you know, what makes me feel good and when you're done, you can bring back in tech very strategically to help those things, right? And that was the goal that turns out to be much more successful than when people take abstention only approach. So if you come out your tech life and say, you know, whenever I look at instagram too much, like I don't like how much on instagram, that's a bad thing, I want to reduce this bad thing. So, so here's my new thing, I'm gonna spend less time looking at instagram, much less likely to succeed in the long term. So we're much less likely at trying to reduce this sort of amorphous negative because you know, in the moment you're like, yeah, but it's not that bad, it would be kinda interesting. Look at it now when you're instead controlling behavior because you have a positive that you're aiming towards is very powerful for people like I want my life to be like this, here's the role that tech plays in that life, the connection to one in your life to be like, that is very, very strong and there's much much easier to say. Yeah, like using instagram is not part of my plan for how I have that life and I really want to have that life. So of course I'm not gonna use instagram. So it turns out to be a much more sustainable way to tame what's going on. </s><s>[INST] So if you quit social media for 30 days you kind of have to do the work, you have to do the work of thinking like what am I actually, you know what makes me happy in terms of these tools that I have previously used and when you try to integrate them back, how can I integrate them to maximize the thing that [/INST] actually or what makes me happy unrelated to technology? Like what do I actually, what do I want my life to be like, well maybe what I want to do is be you know outside of nature two hours a day and spend a lot more time like helping my community and sacrificing on behalf of my connections and then have some sort of intellectually engaging leisure activity like I'm reading or trying to read the great books and having more calm and seeing the sunset you create this picture and then you go back and say well I still need my facebook group because that's how I, I keep up with my cycling group but twitter is just you know toxics not helping any of these things and well I'm an artist so I kinda need instagram to get inspiration but if I know that's why I'm using instagram, I don't need it on my phone, it's just on my computer and I just followed 10 artists and check it once a week. Like you really can start to point it was the number one thing that differentiated in that experiment. The people who ended up Sustainably making changes and getting through the 30 days. And those who did it was two people who did the experimentation in the reflection. Like let me try to figure out what's positive, They were much more successful than the people that just said, I'm sick of using my phone so much. So I'm just gonna white knuckle it just 30 days will be good for me. I just gotta just gotta get away from it or something that doesn't last. </s><s>[INST] So you're doing your social media currently. Uh do you find that a lot of people going through this process? Well, uh will seek to basically arrive at a similar place to not use social media primary. About half. [/INST] Right. So about half when they went through this exercise and these aren't quantified numbers, you know this is just they sent me reports and yeah, </s><s>[INST] That's pretty good though. 1700. [/INST] Yeah. Yeah. So, so so roughly half probably got rid of social media altogether. Once they did this exercise, they realize these things I care about. I don't social media is not the tools that's really helping the other half kept some there are some things in their life or some social media was useful. But the key thing is if they knew why they were deploying social media, they could put fences around it. So for example of those half that kept some social media, almost none of them kept it on their phone. </s><s>[INST] Oh, interesting. I [/INST] can't optimize if you, if you don't know what is the function you're trying to optimize. So it's like this huge hack, like once you know this is why I'm using twitter, then you can have a lot of rules about how you use twitter and and suddenly you take this cost benefit ratio and it goes like way from the company's advantage and way over towards your advantage. </s><s>[INST] It's kind of fascinating because I've been Torn on social media but I did this kind of process. I haven't actually done it for 30 days, which I probably should. I'll do it for like a week at a time and regularly and thinking what what kind of approach the twitter works for me. What I am distinctly aware of the fact that I really enjoy posting once or twice a day and at that time checking from the previous post, it like it makes me feel even when there's like negative comments, they go right past me and when there's positive comments, makes you smile, I feel like love and connection with people, especially people I know, but even just in general, it's like it makes me feel like the world is full of awesome people. Okay, when you increase that from checking from two to like I don't know what the threshold is for me, but it probably five or six per day. It starts going to anxiety world, like where negative comments will actually stick to me, my mentally uh and and positive comments will feel more shallow. Yeah, it's kind of fascinating. So I uh I've been trying to, there's been long stretches of time, I think, december in january where I did just post and check post and check. That was that makes me really happy most of 2020 I did. That made me really happy recently, I started like, I'll go, you know, you go right back in like a drug addict, will you check it? Like, I don't know what that number is, but that number is [/INST] high, you don't come out happy, you don't, No one comes out of a day full of twitter celebrating humanity and it's not </s><s>[INST] even because I'm very fortunate to have a lot of just positivity in my the twitter, but I there's just a general anxiety, I wouldn't even say, I wouldn't even say it's, it's probably the thing that you're talking about with the context switching, it's almost like and exhaustion, I wouldn't even say it's like a negative feeling, it's almost just an exhaustion to where I'm not creating anything beautiful in my life, Just exhausted. An existential exhaustion, existential exhaustion, but I wonder do you think it's possible to use from the people you've seen from yourself too to use social media in the way I'm describing moderation or is it always going to become [/INST] when, when people do this exercise, you get lots of lots of configurations. So for people that have a public presence, for example, like what you're doing is not that not that unusual. Okay. I post one thing a day and my audience likes it and, and that's kind of it, which, but you thought through like, okay, this supports something of value, which is like having a sort of informal connection with my audience and being exposed to some sort of uh, positive randomness. Okay, then if that's my goal, what's the right way to do it? Well, I don't need to be on twitter on my phone all day. Maybe what I do is every day at five. I do my post and check on the day. So I have a writer friend, um, Ryan Holliday who writes about the Stokes a lot and he has this similar strategy. He post-1 quote every day from usually from a famous stoic and sometimes from contemporary figure and that's just what he does. He just posted and it's a very positive thing like his readers really love it because it's just like a dose of inspiration. He doesn't spend time, he's never interacting with anyone on social media, right. But that's an example of I figured out what's important to me, what's the best way to use tools to amplify it and then you get advantages out of the tools. So I like what you're doing. I looked you up if I looked up your twitter feed before I came over here, I was curious, you're not on there a lot. I don't see him yelling at people. Do you think social media as a medium change the cultural standards? And I mean it in a, have you read Neil postman at all? Have you read like amusing ourselves to death? He was a social critic, technology critic um and wrote a lot about sort of technological determinism. So the ways which is a really influential idea to a lot of my work, which is actually a little out of fashion right now in academia, but the ways that the properties and presence of technologies change things about humans in a way that's not really intended or planned by the humans themselves. And that book is all about how different communication medium fundamentally just changed the way the human brain understands and operates. And so he sort of gets into the, what happened when the printed word was widespread and how television changed it. And this was all pre social media by this. One of these ideas I'm having is like what the degree to which I get into it. Sometimes I'm a show you get a little bit like the degree to which twitter in particular just change the way that people conceptualized what for example debate and discussion was like it introduced a rhetorical dunk culture or sort of more about tribes not giving ground to other tribes and and it's like it's a completely, there's different places and times when that type of discussion with thought of differently. Right. </s><s>[INST] Well, yeah, absolutely, but I I tend to believe, I don't know what you think that there's a technological solutions, like there's literally different features in twitter that could completely reverse that there's so much power in the different choices that are made and it could still be highly engaging and have very different effects, perhaps more negative or hopefully more positive. [/INST] Yeah, I'm trying to pull these two things apart. So there's these two ways social media, let's say could change the experience of reading a major newspaper today. One could be a little bit more economic, right? So so the internet made it cheaper to get news, The newspapers had to retreat to a paywall model because it was the only way they were going to survive, but once you're in a paywall model than than what you really want to do is make your tribe which is within the paywall very, very happy with you. So you want to work to them. But then there's the sort of the terminus point of view which is the properties of twitter, which were arbitrary Jack and Evan just whatever. Let's just do it this way, influence the very way that people now understand and think about the world </s><s>[INST] so that the one influenced together, I think they kind of started adjusting together. I did this thing, I mean I'm trying to understand this part of the, part of the, I've been playing with the entrepreneurial idea. There's a very particular dream I've had of a startup that this is a longer term thing. Uh, it has to do with artificial intelligence but more and more, it seems like there's some trajectory through creating uh social media type of technology is very different than what people are thinking I'm doing. But uh, it's a kind of challenge to the way the twitter is done, but it's not obvious what the best mechanisms are to still make an exceptionally engaging platform. My clubhouse is very engaging and not have any other negative effects. For example, there's Chrome extensions that allow you to turn off all likes and dislikes and all of that from twitter. So all you're seeing is just the content [/INST] on </s><s>[INST] twitter that to me creates. That's not a compelling experience at all because I still need, I would argue, I still need the likes to know what's a tweet worth reading because I don't only have a limited amount of time. So I need to know what's valuable, it's a great yelp reviews on tweets or something, but I've turned off on, for example, on my account on youtube. I've turned uh I wrote a Chrome extension that turns off all likes and dislikes and just views, I don't know how many views the video gets and so unless [/INST] it's on my phone, but you take off the recommendations. </s><s>[INST] Uh, [/INST] the youtube, some people that distraction free tube is a big one. Right? No, I'm </s><s>[INST] not worried about the distraction because I'm able to control myself on youtube rabbit hole and I don't rabbit hole. So you have to know your demons or your addictions or whatever and youtube. I'm okay. I don't have, I don't keep clicking. The negative feelings come from seeing the views on stuff you've created have created. [/INST] So you don't want to see your views. </s><s>[INST] Yeah. So like I'm just like speaking to the things that I'm aware of myself that are helpful and things that are not helpful emotionally. And I feel like there should be, we need to create actually tooling for ourselves. That's not me with javascript, but anybody is able to create sort of control the experience they, that they have. [/INST] Yeah. Well, so, so my, my big unified theory on social media is I'm very, I'm very bearish on the big platforms having a long </s><s>[INST] future. You are, [/INST] I think the moment, I think the moment of three or four major platforms is, uh, not going to last. Right. So I don't, okay. This is just perspective. Right? So you can start shorting these stocks on my financial, yeah. Don't do Robin Hood. Um, so here's, here's, I think the big mistake, the major platforms made as when they took out the network effect advantage. Right? So the original pitch, especially something like facebook or instagram was the people, you know, are on here. Right? So like what you used as far as you can connect to people that you already know is what makes the network useful. So therefore the value of our network grows quadratic lee with the number of users and therefore it's such a head start that there's no way that someone else can catch up. But when they shifted and when facebook took the lead, if they were going to shift towards a news feed model, they basically said we're going to try to in the moment get more data and get more likes like what we're going to go towards is actually just uh seeing interesting stuff like seeing diverting information. So people took the social internet impulse to connect to people digitally to other tools, group text messages and WhatsApp and stuff like this. Right? So you don't think about these tools as this is where I connect with people once it's just a feed that's kind of interesting. Now you're competing with everything else that can produce interesting content that's diverting and I think that is a much fiercer competition because now for example, you're going up against podcast, right? I mean like, okay, I guess, you know, the twitter feed is interesting right now, but also a podcast is interesting or something else could be interesting too. I think it's a much fiercer competition when there's no, there's no more network effects. Right? And so my sense is we're going to see a fragmentation into what I call long tail social media where if I don't need everyone I know to be on a platform then why not have three or four bespoke platforms I use where it's 1000 people and it's all we're all interested in, you know, whatever ai or comedy and we've, we've perfected this interface and maybe it's like clubhouses, audio or something and when we all pay $2 so we don't have to worry about attention harvesting and that's going to be wildly more entertaining. Like I mean I'm thinking about comedians on twitter, it's not the best internet possible format for them expressing themselves and being interesting that you have all these comedians that are trying to like, well I can do like little clips and little whatever, like I don't know if there was a long tail social media islands really. This is where the comedians are in this podcast and the comedians around podcast now. So this is my thought is that there's really no, there's really no strong advantage to having one large platform this everyone is on, if all you're getting from it is I now have different options for diversion and like uplifting aspirational or whatever type of entertainment, that whole thing of fragment and I think the glue that was holding together with network effects, I don't think they realize that when network effects have been destabilized, they don't have the centrifugal force anymore and the spinning faster and faster. But it is a twitter feed really that much more interesting than all these streaming services. Is it really that much more interesting than clubhouse? Is it that much more interesting than podcast? I feel like they don't realize how unstable their ground actually is. </s><s>[INST] Yeah, that's fascinating. But uh, the thing that makes twitter and facebook work, I mean the news feed, you're exactly right like that. You can just duplicate the news. Like if it's, if it's not the social network and it's the news feed then why not have multiple different feeds that are more that are better at satisfying. There's a dopamine Gamification that they've figured out the and uh so you have to, whatever you create, you have to provide some pleasure in that same Gamification kind of way. It doesn't have to have to do with scale of large social networks. But I mean I guess you're implying that you should be able to design that kind of uh mechanism in other forms [/INST] or people are turning on the Gamification. I mean, so people are getting wise to it and are getting uncomfortable about it right? So if I'm offering something there, these existing sugar, people realize sugar's bad, drinking a lot of great too. But it also after a while you realize there's there's problems. So some of the long tail social media networks that are out there that I've looked at, they offer usually like a deeper sense of connection. Like it's usually interesting people that you share some affinity and you have these carefully cultivated, I wrote this new yorker piece a couple years ago about the indie social media movement that really got into some of these different technologies but I think the technologies are a distraction. We focus too much on you know, mastodon versus you know whatever like forget or discord like actually let's forget the protocols right now. It's the idea uh okay and there's a lot of these long tail social media groups, what people are getting out of it, which I think can outweigh the dopamine Gamification is strong connection and motivation. Like you're in a group with other guys that are all trying to be you know, better dads or something like this and and you talked to him on a regular basis and you're sharing your stories and there's interesting talks and that's a powerful thing to. </s><s>[INST] One interesting thing about scale of twitter is you have these viral spread of information. So sort of twitter has become a newsmaker in itself is the problem. Well yes, but I don't wonder what replaces that because because then you immediately [/INST] well </s><s>[INST] no reports [/INST] that have to do some work. You </s><s>[INST] know the problem with reporters and journalism is that they're intermediary, they have control. I mean this is the problem in Russia currently you have uh it creates a shield between the people and the news. The the interesting thing and the powerful thing about twitter is that the news originates from the individual that's creating the news like you have the president of that is the former president of the United States on twitter creating news. You have elements creating news. You have people announcing stuff on twitter as opposed to talking to a journalist and that feels much more genuine and uh it feels very powerful but actually coming to realize that it doesn't need the social network, you can just put that announcement on the Youtube type. [/INST] This is what I'm thinking. Right? So this is my point about that because that's right. The democratizing power of the internet is fantastic. I'm an old school internet nerd a guy that was you know, tell meeting in the servers and go offering before the World wide Web was around. Right. So I'm a huge internet booster and that's that's one of its big power. But when you put everything on twitter, I think the fact that you've you've taken uh you homogenized everything right? So everything looks the same moves with the same low friction is very difficult. You have no, what I call distributed curation, right? The only curation that really happens there's a little bit with likes and also the algorithm. But if you look back to pre web two point or early web 2.0 when a lot of this was happening, let's say on blogs where people own their own servers and you had your different blogs, there was this distributed curation that happened where in order for your blog to get on people's radar and this had nothing to do with any gatekeepers or legacy media, it was Over time you got more links and people respected you and you would hear about this blog over here and there's this whole distributed curation and filtering going on. So if you think like the 2004 presidential election, most of the information people gained from the Internet, one of the first big Internet news driven elections was from, you know, you had like the daily costs and and drudge but there was like blogs that were out there and this was back as recline was just running a blog out of his uh you know a dorm room at this point, right? And you would in a distributed fashion gain credibility because okay people have paid, it's very hard to get people to pay attention, blog are paying attention. I get linked to this kid Ezra or whatever, it seems to be really sharp and now people are noticing it and now you have a distributed curation that solves a lot of the problems we see when you have a completely homogeneous low friction environment like friction where I mean twitter where any random conspiracy theory or whatever that people like can just shoot through and spread whereas if you're starting a blog to try to push Q and on or something like that. It's probably gonna be a really weird looking blog. You have a hard time. Like it's just never gonna show up on people's </s><s>[INST] radar, right? I mean, so everything you said up until the very last statement, I would, I would agree with [/INST] this is a topic I don't know a ton about, I guess </s><s>[INST] there's uh, I think I forget Q and on uh, what your name is, Kenan, It could be that I also don't know, I should know more apologized. I don't know more. I mean, that's the power and uh, the downside. You can have, I mean Hitler could have a blog today and you would have potentially very large following if he's charismatic, if he's has, you know, is good with words, is able to express the ideas, whatever. Maybe he's able to channel the frustration, the anger that people have about a certain thing. And so I think that's the power of blogs, but it's also the limitation, but that doesn't, we're not trying to solve that. You can't solve that. The fundamental problem you're saying is not the problem that your your thesis is that there's nothing special about large scale social networks that guarantees that they will keep existing. [/INST] And it's important to remember for a lot of the older generation of internet activists are the people who are very pro internet in the early days, they were completely flabbergasted by the rise of these platforms. Say, well, why would you take the internet and then build your own version of the internet where you own all the servers. And we built this whole, distribute the whole thing with open protocols. Everyone, anywhere in the world to use the same protocols. Your machine can talk to any other machine is the most democratic communication system that's ever been built. And then these companies came along and said, we're gonna build our own, we just own all the servers and put them in buildings that we own and the internet will just be the first mile. This gets you into our private internet where we own the whole thing. It was completely against the entire motivation of the internet was like, yes, we it's not going to be one person owns all the servers and you pay to access them. It's anyone server that they own can talk to anyone else's server because we all agree on a standard set of protocols. And so the old guard of pro internet people never understood this move towards, let's build private versions of the internet, uh, build three or four private internet and that's what we'll all use. It was the opposite, basically. </s><s>[INST] Well, it's funny enough, I don't know if you follow, but Jack Dorsey is also uh, as a proponent and is helping to fund, create fully distributed version's to twitter essentially. I think that would potentially destroy twitter, but I think there, you know, there might be financial are like business cases to be made there. I'm not sure. But that seems to be another alternative as as opposed to creating a bunch of like the long tail creating like the ultimate long tail of like fully distributed [/INST] Yeah. Which, which is what the internet is. But that's, that's sort of like, I'm thinking about long tail social media, I'm thinking it's uh, like the text not so important. Like there's groups out there, right? I, I know where the tech, they used to actually implement their digital only social group, whatever they might use slack. They might use some combination of zoom or it doesn't matter. I think in the tech world we want to build the beautiful protocol that okay, everyone's gonna use is just a Federated server protocol in which we've worked out X, y, and z and no one understands it because then the engineers needed all to make, I get it because I'm a nerd like this, like, okay, every standard has to fit with everything else and no one understands what's going on. Meanwhile, you know, you have this group of bike enthusiasts, they're like, yeah, we'll just jump on a zoom and have some slack and put up a blog detect doesn't really matter. Like we built the world with our own curation, our own rules, our own sort of social ecosystem that's generating a lot of value. I don't know if it'll happen, there's a lot of money at stake with obviously these large, but I just think they're more, they're so I mean look how quickly americans left facebook, right facebook was savvy to buy other properties and the and to diversify, right, but how quick did that take for just standard facebook news to everyone under the age of something we're using it and no one under a certain age is using it now. It took like four years. I mean this stuff is </s><s>[INST] actually, I believe people can leave facebook overnight, like I I think facebook hasn't actually messed up like enough to there's two things they haven't messed up enough for people to really leave aggressively and there's no good alternative for for them to leave, I think it's good alternatives pop up, it was just immediately happened. [/INST] The stuff is a lot more culturally fragile I think. I mean twitter is having a moment because it was feeding a certain type of there's a lot of anxiety that was in the sort of political sphere anyways that twitter was working with. Um but its moment could go to as well, I mean it's a really arbitrary thing, short little things and I read a wired article about this earlier in the pandemic, like this is crazy that the way that we're trying to communicate information about the pandemic is all these weird arbitrary rules where people are screen Shotting pictures of articles that are part of a tweet thread where you say one slash in under it. Like we have the technology guys feel like really clearly convey in for long form information to people. Like why are we, why do we have these? And I know this because it's the game ified, dopamine hits. But what a weird medium. There's no reason for us to have to have these threads that you have to find and pin with your screenshot. I mean we have technology to communicate better using the internet. I mean why are epidemiologists having to do tweet threads </s><s>[INST] because these mechanisms of publishing that make it easier on twitter? I mean we're evolving as a species and the internet is a very fresh thing. And so it's kind of interesting. I think that as opposed to twitter, this is what Jack also complains about, it is twitter is not innovating fast enough. And so it's almost like the people are innovating and thinking about their productive life faster than the platforms on which they operate can catch up. And so that the point the gap grows sufficiently, they'll jump a few people fumigated folks will just create an alternative and perhaps distributed perhaps just many little silos and then people jump and then we'll just continue this [/INST] kind of way. See I think like substack for example what they're going to pull out of twitter among other things is the audience that was let's say like slightly left of center. but um slightly off center don't like trump uncomfortable with like, postmodern critical theories made into political action, right? And they're like, yeah, twitter, there was people on there talking about this and it made me feel sort of heard because I was feeling a little bit like a nerd about. But honestly, I'd probably rather subscribe to four subs, you know, I'm gonna have like berries and Andrew Sullivan. I have like a jesse signals, like I have a few sub stacks I can subscribe to. And honestly, that's I'm a knowledge worker who's 32 anyways, probably that's an email all day. And so like, there's an innovation that's going to that group, you know, it's gonna suck him off, which </s><s>[INST] is actually a very large group. [/INST] Yeah, that's a lot of that's a lot of energy and then once trump's gone, I guess that's probably going to drive that drove a lot of uh more like trump people off twitter, like this stuff is fragile. So </s><s>[INST] I but the fascinating thing to me because I've hung out on parler for a short amount enough to to know that the interface matters is so fascinating. Like that, that it's not just about ideas, it's about creating like substack too, creating a pleasant experience addicting [/INST] experience, You're right, you're right about that and it's hard and that's why the interest is one of the conclusions from that India's social media article is it's just the ugliness matters and I don't mean even just aesthetically, but just the clunkiness of the interface is the um, and I don't know, it's to some degree that social media companies have spent a lot of money on this and to some degree, it's a survivorship bias, right? Like twitter, every time I hear Jack talks about this, it seems like he's as surprised as anyone else the way twitter is being used and it's basically the way, you know, they had it uh years ago and then, you know, it's great to be status is right, this is what I'm doing, you know, and my friends can follow me and see it and without really changing anything, it just happened to hit everything right </s><s>[INST] to support this other type of interaction. Well, there's also the Javascript model which Brendan Eich talked about, he's just implemented javascript uh like the crappy version of javascript in 10 days throughout there and just ah changed it really quickly, involved it really quickly and now it's become, according to stock exchange, the most popular programming language in the world that drives like most of the internet and even the back end and now mobile and so that that's an argument for the kind of thing you're talking about where like, like the bike club people could literally create the thing that would, you know, run most of the internet 10 years from now. Yeah, so there's something to that, like, as opposed to trying to get lucky or trying to think through stuff is just to, uh, to solve a particular problem, [/INST] do stuff and then do stuff, do something, keep tinkering til you love it. </s><s>[INST] Yeah. And then, uh, and of course the sad thing is timing and luck matter and that you can't really control the problem, but [/INST] You can't go back to 2007. Yeah, that's like the number one thing you could do to have a lot of success with the new platform is go back in time, 14 years. </s><s>[INST] So the thing you have to kind of think about is what is the, like, what's the totally new thing that, uh, 10 years from now, it would seem obvious. I mean, some people saying clubhouses that there's been a lot of stuff like clubhouse before, but it, it hit the right kind of thing. It's similar to Tesla, actually, what clubhouse did is it got a lot of relatively famous people on there quickly. And um, and then the other effect is like, it's invite only. So like, oh, all those, like famous people are on there, I wonder what's, it's the fomo like, fear that you're missing something really profound exciting happening there. So those social effects and then once you actually show up, I'm a huge fan of this, it's the javascript model is like, clubhouse is so dumb, like, so simple in its interface, like, you literally can't do anything except mute mute as a mute button and there's a leave quietly button and that's it. It's [/INST] kind of, I love single use technology that, </s><s>[INST] yeah, there's no, like, there's no, it's just like trivial and uh, you know, twitter kind of started like that facebook started like that, but they've evolved quickly to add all these features and so on and you know, I do hope clubhouse stays that way. [/INST] Be interesting or there, there's alternatives. I mean, I mean, even with clubhouse though, the, so one of the issues with a lot of these platforms, I think is, uh, bits are cheap enough now that we don't really need a unicorn investor model. I mean, the, the investors need that model, there's really not really an imperative of, we need something that can scale 200 million plus a year revenue. So because it was gonna require this much seed and angel investment and, and you're not going to get this much seed Angel investments, you can have a potential exit this way because you have to be part of a portfolio that depends on one out of 10 exiting here. If you don't actually need that and you don't need to satisfy that investor model, which I think is basically the case. I mean bits are so cheap, everything is so cheap. You don't know. So even like with clubhouse, it's investor back, right? This notion of like, this needs to be a major platform. Um, but the bike club doesn't necessarily need a major flat. So that's where I'm interested. I mean, I don't know, there's so much money. That's the only problem that bets against me is that you can concentrate a lot of capital if you do these things, right? So facebook was like a fantastic capital concentration machine. It's crazy how much where it even found that capital in the world, that it could concentrate and ossified in the stock price at a very small number of people have, you know, access to, Right? That's, that's incredibly powerful. So when there, when there is a possibility to, to, to consolidate and gather a huge amount of capital, that's a huge imperative. That's very hard for the bike club to go up again. So, </s><s>[INST] but there's a lot of money in the bike club, you see with the Wall Street bets. Yeah. And then when a bunch of people get together, I mean, it doesn't have to be a, but it could be a bunch of different clubs, just kind of team up to overtake [/INST] is what we're doing now. Yeah. Or we're gonna repurpose off the shelf stuff that's not you we're gonna we're gonna repurpose whatever it is for office productivity or something. And then like the clubs using slack just to build out these. Yeah, </s><s>[INST] yeah. Let's talk about email. [/INST] Yeah, that's right. I wrote a book you wrote, </s><s>[INST] uh, had another amazing book world without email. Maybe one way to enter this discussion is to ask what is the hyperactive Hive mind, which is the concept, you open the book [/INST] with the devil. It's the scourge of hundreds of millions. So I think so, I I called this book a World Without email. The real title Should Be A World Without the hyperactive Hive Mind workflow, but my publisher didn't like that. So we had to get a little bit more pithy. I was trying to answer the question after deep work, why is it so hard to do this if this is so valuable, if we can produce much higher? If people are much happier, um why do we check email a day? Why are we on slack all day? You know? And so I started working on this book immediately after deep work. And so my my initial interviews were done in 2016. So it took five years to pull the thread together. I was trying to understand why is it so hard for most people to actually find any time to do this stuff? It actually moves to Neil? And the story was, and I thought this was I hadn't heard this report anywhere else. That's why it took me so long to pull together. Is email arrives on the scene, email spreads. I trace it, it really picks up steam in the early 19 nineties between like 1919 1995. It makes its move, right? And it does. So for very pragmatic reasons it was replacing existing communication technologies, that it was better than it was mainly the fax machine, voice mail and memos. Right? So this was just better. Right? So it was a killer app because it was useful in its wake came a new way of collaborating and that's the hyperactive Hive mine. So, it's the, like the virus that follows the rats that went through western europe for the black pig. As emails spread through organizations in its weight came the hyperactive hive mind workflow, which says, okay guys, here's the way we're going to collaborate. We'll just work things out on the fly with unscheduled back and forth messages. Just let's go back and forth. Hey, what about this? You see this? What about that client? Let's see what's going on over here that followed email. It completely took over office work. And the need to keep up with all of these asynchronous back and forth unscheduled messages. As those got more and more and more, we have more. There's a service, the need to service those required us to check more and more and more and more. Right? And so by the time and I go through the numbers. But by the time you get to today now the average knowledge worker has to check one of these channels once every six minutes because every single thing you do in your organization, how you talk to your colleagues, how you talk to your vendors, how you talk to your clients, how you talk to the HR department, it's all this asynchronous unscheduled back and forth messaging and you have to service the conversations and it spiraled out of control and it has sort of evolved a lot of work in the office. Now to all I do is constantly tend </s><s>[INST] communication channels. So it's fascinating what you're describing is uh nobody ever paused in this whole evolution to try to create a system that actually works, that it was kind of like a huge fan of cellular automata. So it's just kind of started very very simple mechanism, just accelerator tom. And I just kind of grew to overtake all the fundamental communication of how we do business and also personal life. [/INST] That's one of the big ideas. Is that the un intentionality. Right? So this goes back to technological determinism. And this is a weird business book because I go deep on philosophy, I go deep on for some reason we get in the paleo anthropology for a while. We do a lot of neuroscience. It's it's kind of a weird book. Uh but I got real into this technological determinism, right? This notion that just the presence of a technology can change how people act. That's my big argument about what happened with the high fine and I can document specific examples. Right? So I document this example in IBM 1987, maybe 85. But it's in like the mid to late 80s IBM Army headquarters, we're gonna put an internal email, right, because it's convenient and so they ran a whole study and so I talked to the engineer who ran the study, Adrian stunt. We're gonna run this study to figure out how much do we communicate because it was still an era where it's expensive. Right? So you have the provision of mainframe so you can't over provisions. We want to know how much communication actually happened. So they went and figured it out how many memos, how many calls, how many notes? Great. We'll provision of mainframe to handle email that can handle all of that. So if all of our communication moves to email, the mainframe will still be fine. In three days they had melted it down. People were communicating six times more than that estimate. So just in three days, the presence of a low friction digital communication tool drastically changed how everyone collaborated. So that's not enough time for, you know, an all hands meeting guys, we figured it out, you know, this is what we need to communicate a lot more is what's gonna make us uh more productive, we need more emails. It's emergent, </s><s>[INST] isn't that just on the positive end amazing to you. Like isn't an email amazing. Like in those early days, like just a frictionless communication, I mean email is awesome. Like people say that there's a lot of problems with emails, just like people say a lot of problems with twitter and so on. It's kind of cool that you can just send a little note. [/INST] It was a miracle, right? This was so I so I I wrote a there's originally was a new yorker piece from a year or two ago called was email a mistake and then it's in the book too. But I go into the history of email like why did it come along and it solved a huge problem. So it was it was the problem of fast asynchronous communication and it was a problem did not exist until I got large offices. We got large offices. Synchronous communication like let's get on the phone at the same time, there's too much overhead to it. Just too many people you might have to talk to asynchronous communication. Like let me send you a memo when I'm ready and you can read it when you're ready, took too long and it was like a huge problem. So one of the things I talked about is the way that when they built the C. I. A headquarters there is such a need for fast asynchronous communication that they built a pneumatic powered email system. They had these pneumatic tubes all throughout the headquarters with electromagnetic routers. So you would put your message in a plexiglass tube and you would turn these brass dials about the location, you would stick it in these things and pneumatic tubes and it would shoot and sort and work its way through these tubes to show up in just a minute or something at the floor and at the general office suite where you wanted to go. And my point is the fact that they spent so much money to make that work. Show how important fast asynchronous communication was large offices. So when email came along it was a productivity silver bullet. It was a miracle. I talked to the researchers who are working on computer supported collaboration in the late eighties trying to figure out how are we going to use computer networks to be more productive? And they were building all these systems and tools, emails showed up, it just wiped all that research off the map. There's no need to build these custom internet applications, there's no need to build these communication platforms, email could just do everything right? So it was a miracle application which is why it spread everywhere. That's one of these things where okay, unintended consequences, right? You have this miracle productivity Silver bullet, it spread everywhere, but it was so effective. It just, you know, I don't know like a drug, I'm sure there's some pandemic metaphor here, analogy here of a drug, like it's so effective at treating this, that it also blows up your whole immune system and then everyone gets sick, but well </s><s>[INST] ultimately it probably significantly increase the productivity of the world, but there is a kind of hump that it now is plateau owed. And then what were the fundamental question you're asking is like, okay, how do we take the next, how do we keep increasing the product [/INST] section now? I think it brought it down. So my, my think so my contention and uh so again there's a little in the book, but I have a more recent wired article that put some newer numbers to this, I subscribe to the hypothesis that the hyperactive hive mind was so detrimental. So yeah, it helps productivity at first, right, when you could do fascinating close communication, but very quickly there was a sort of exponential rise in communication amounts. Once we got to the point where the hive mind meant you had to constantly check your email. I think that made us so unproductive that it actually was pulling down non industrial productivity and I think the only reason why, so it certainly has not been going up that metrics been stagnating for a long time now while all this was going on, I think the only reason why it hasn't fallen is that we added these extra shifts off the books. I'm going to work for three hours in the morning, I'm going to work for three hours at night and only that I think has allowed us to basically maintain a stagnated non industrial growth, we should have been shooting up the charts. I mean this is miraculous innovations, a computer networks and then we built out these $100 billion ubiquitous worldwide high speed wireless internet infrastructure with supercomputers in our pockets where we can talk to anyone at any time, like why did our productivity not shoot off the charts? Because our brain can't context, which once every six minutes. </s><s>[INST] So it's fundamentally back to the context switching is the poison in Contact switching is poisonous. The what is it about email that forces contact switching is in both our psychology that drags us in [/INST] expectation of. Yeah. Right, right. Because it's not, I think we've seen this through a personal personal will or failure lens recently, like am I addicted to email? Uh I have bad etiquette about my email. No, it's the underlying workflow. So the tool itself, I will exonerate. I I think I would rather use pop three than a fax protocol. Right? I think it's easier. The issue is the hyperactive hive mind workflow. So if I am now collaborating with 20 or 30 different people With back and forth, unscheduled messaging, I have to tend those conversations, right? It's like you have 30 metaphorical ping pong tables and when the balls come back across you have to pretty soon hit it back or stuff actually grinds to a halt. So it's it's the workflow. That's the problem. It's not the tool is the fact that we use it to do all of our collaboration, let's just send messages back and forth, which means you can't be far from checking that because if you take a break, if you batch, if you try to have better habits, it's going to slow things down. So my whole villain is this hyperactive hive mind workflow, the tool is fine, I don't want the tool to go away, but I want to replace the hyperactivity of my work, but I think this is going to be one of the biggest value generating productivity revolutions of the 21st century, like quote, an anonymous Ceo is pretty well known. Who says this is going to be the moon shot of the 21st century is going to be of that importance. There's so much latent productivity that's being suppressed because we just figure things out on the fly and email that as we figure that out. I think it's going to be uh hundreds of billions of dollars. </s><s>[INST] You're so absolutely right. The question is, what does the world without email look like? How do we fix email? [/INST] So what happens is at least in my vision, you identify, Well actually there's these different processes that make up my workday. Like these are things that I do repeatedly, often in collaboration with other people that do useful things for my company or whatever right now, most of these processes are implicitly implemented with the hyperactive Hive mind, how do we do this thing like answering client questions to shoot messages back and forth, you know, how do we do this thing posting podcast episodes, we'll just figure it out on the fly. My main argument is we actually have to do like they did in the industrial sector take each of these processes and say, is there a better way to do this and by better, I mean a way that's going to minimize the need to have unscheduled back and forth messaging. So we actually have to do process engineering. This created a massive growth and productivity in the industrial sector during the 20th century. We have to do it in knowledge work. We can't just rock and roll in in boxes. We actually have to say, how do we deal with client questions? Well, let's put in place a process that doesn't require us to send messages back and forth. How do we post podcast episodes? Let's automate this to a degree where I don't have to just send you a message on the fly and you do this process by process and the pressure on that inbox is released and now you don't have to check it every six minutes. You still have email. I mean like I need to send you a file share, I'll use email but we're not coordinating and collaborating over email or slack, which is just a faster way of doing the hive mind. I mean slack doesn't solve anything there. Uh you have better structured bespoke processes. I think that's what's going to unleash this massive productivity </s><s>[INST] bespoke. So the interesting thing is like if for example, you and I exchanged some emails. So obviously I uh let's just say my particular case, I scheduled podcast, there's a bunch of different tasks fascinating enough that I do that can be converted to processes. Is it up to me to create that process or do you think we also need to build tools just like email was a protocol for helping us create prosperity for the different tasks. [/INST] I mean, I think ultimately the whole organization, the whole team has to be involved. I think ultimately there's certainly a lot of investor money being spent right now to try to figure out those tools. Right. So I think Silicon Valley has figured this out in the past couple of years. This is the difference between when I was talking to people after deep work and now five years later is this scent is in the air, right? Because there's so much light in productivity. So yes, there are going to be new tools which I think could help, they're already tools that exist. I mean the different groups I profile use things like trailer or base camp or asana or flow and you know, our schedule wants and acuity like there's, there's a lot of tools out there. The key is not to think about it in terms of what tool do I replace email with instead you think about it with, I have a problem with a process that reduces back and forth messages. So what tool might help us might help us do that. Yeah, and I would push, it's not about necessarily efficiency. In fact, some of these things are going to take more time. So writing a letter to someone is like a high value activity is probably worth doing the thing. That's killer is the back and forth, because now I have to keep checking, right? So we scheduled this together because I knew you from before. But like most of the, the interviews I was scheduling for this, actually, I have a process with my publicist where we use a shared document and she put stuff in there and then I check it twice a week and there's scheduling options and say, here's what I want to do this one, or this will work for this one or whatever. And it takes more time in the moment than just. But it means that we have almost no back and forth messaging for podcast scheduling, which without this. So like with my UK publisher, I didn't put this process in the place because we're not doing as many interviews, but it's all the time. And I'm like, oh man, I could really feel the difference, right? It's the back and forth. That's killer. </s><s>[INST] I suppose it is up to the individual people involved, like you said, uh knowledge workers, like they have to carry the responsibility of creating processes, like how always asking the first principles question, how could this be converted into a process. [/INST] Yeah, So you can start by doing this yourself, like just with what you can control. I think ultimately, once the teams are doing that, I think that's probably the right scale. If you try to do this at the organizational scale, you're gonna get bureaucracy right? So if it's all right, if if if Elon musk is going to Dictate down to everyone at Tesla or something like this, that's too much remove, you get bureaucracy. But if it's where a team of six that's working together on, you know, whatever powertrain software, then we can figure out on our own, what are our processes? How do we want to do this? </s><s>[INST] So it's ultimately also creating a culture were saying like an email, sending an email just for the hell of it, it should be taboo. Like, so like you are being uh, you're being destructive to the productivity of the team by sending this email as opposed to helping develop uh, process and so on. That, that will ultimately automate this. [/INST] That's why I'm trying to spread this message of the context switches, it's poison. I get so much into the science of it. I think we underestimate how much it kills us. You have to reach away our context looking a message and come back. And so once you have the mindset of it's a huge thing to ask of someone To have to take their attention off something and look back at this and if they have to do that for three or four times, we're just gonna figure this out on the fly and every message is going to require five checks of the inbox while you wait for it. Well now you've created whatever it is at this 50.25 or 30 contact shifts, like you've just done a huge disservice to someone's day. This would be like if I had a professional athlete, like, hey, do me a favor, I need to go do this press interview. But to get there, you're gonna have to carry this sandbag and sprint up this hill, like completely exhaust your muscles and then you have to go play a game. Like of course, I'm not going to ask an athlete to do like an incredibly physically demanding thing right before a game, but something as easy as thoughts, question mark or like, hey, do you want to jump on a call and it's going to be six back and forth messages to figure it out. It's kind of the cognitive equivalent, right? You're taking the wind out of someone. </s><s>[INST] Yeah. And by the way, for people who are listening because I recently posted a few job openings for and so on to help with this thing. And one of the things that people are surprised when they work with me is how many spreadsheets and processes are involved. [/INST] It's like Claude Shannon, right? I talked about communication theory, Information theory. It takes time to come up with a clever code upfront. You spend more time up front figuring out those spreadsheets and trying to get people on board with it, but then your communication going forward is all much more efficient. So over time you're using much less bandwidth, right? So you you do paint up front, </s><s>[INST] it's quicker [/INST] Just right now to send an email, but if I spend a half day to do this over the next six months, I've saved myself 600 emails. </s><s>[INST] Now, here's a tough question for, you know, from the computer science perspective, we often over optimize. So you create processes and you okay, just like you're saying it's so pleasurable to increase uh in the long term productivity that sometimes you just enjoyed that process in itself, but just creating processes and you actually never uh like it has a negative effect on product tv long term because you're too obsessed with the processes. Is that is that uh a nice problem to have, essentially. [/INST] I mean it's a problem because let's look at the one sector that does do this which is uh developers. Right, So agile methodologies like scrum or combo on our basically workflow methodologies that are much better than the hyperactive hive mind, but man, some of those programmers get pretty obsessive, I don't know if you've ever talked to whatever level three scrum master they get really obsessive about, like it has to happen exactly this way, and it's probably seven times more complex than it needs to be. I'm hoping that's just because nerds like me, you know like to do that but it's it's a a broadly probably an issue right? We have to be careful because you can just go down that that fiddling path like so it needs to be, here's how we do it, let's reduce the messages and let's roll, you know, um you can't save yourself through if you can get the process just right. Right. So I wrote this article kind of recently called the Rise and Fall and getting things done And I profiled this productivity guru named Merlin Mann and I talked about this movement called productivity prawn as like elite speak term in the early 2000s where people just became convinced that if they could combine their productivity systems with software and they could find just the right software, just the right configuration where they could offload most of the difficulty of work, what happened with the machines we kind of figured out for and then they could just sort of crank widgets and b and the whole thing fell apart because work is hard and it's hard to do and making decisions about what to work on is hard and no system can really do that for you. So you have to have this this sort of balance between uh context which is our poisoned so we got to get rid of the context which is once like something's working good enough to get rid of the context which is then </s><s>[INST] get after it. Yeah, there's a psychological process there for me, the O. C. D. Nature, like I've literally embarrassing enough have lost my ship before when. So in in many of the processes that involve python scripts, the rule is to not use spaces underscores are there like rules for like how you format stuff? Okay. And like I should not lose my ship when somebody had a space and maybe capital letters like it's okay to have a space because there's this feeling like something is not perfect and uh as opposed to in the python script allowing some flexibility around that you create this programmatic way that's flawless and when everything's working perfectly it's perfect. But actually if you strive for perfection it has the same stress. Like has a lot of the stress that you were seeking to escape with the context switching because you're almost stressing about errors Like when the process is functioning your there's always this anxiety of like I wonder if it's gonna succeed. Yeah. I wonder if it's going to succeed. [/INST] Yeah. No, no I think some of that's just you and I probably, I mean it's just our mindset, right? We're in we do computer science, right? So chicken and egg and a lot of the processes and of working here much rougher. It's like okay instead of letting clients just email me all the time, we have a weekly call and then we send them a breakdown of everything we committed to, right? That's a process that works okay. I get asked a lot of questions because I'm the javascript guy in the company. Instead of, you know by email, I have office hours. This is what base camp does. All right. So you come to my office hours that cuts down a lot of back and forth. All right. We're gonna, instead of emailing about this project will have a Trela board and we'll do a weekly really structure status meeting real quick. What's going on? Who needs what? Let's go. And now everything's on there. Not our inboxes. We want to send as many messages. So like that rough level of granularity that gets you most of the way there. </s><s>[INST] So the parts that you can't automate and turn into a process. So how many parts like that do you think should remain in a perfect world? And uh, for those parts were emails still useful. What do you recommend those emails look like? How how should you write emails? When should you send [/INST] them? Yeah, I think email, email is good for delivering information. Right. So I think about like a fax machine or something. You know, it's a really good fax machine. So if I need to send you something and you just send you a file, I need to broadcast a new policy or something. Like email is a great way to do it. It's bad for collaboration. So you're having a conversation, we're trying to reach a decision on something. I'm trying to learn about something. I'm trying to clarify what something, what this is that it's more than just like a one answer type question then I think that you shouldn't be doing an email. </s><s>[INST] But see here's the thing like you and I don't talk often and so we have a kind of new interaction. It's not so sure. Yeah, you have a book coming out so there's a process and so on. But say there don't you think there's a lot of novel interactive experiences? It's fine. So you can just for every novel experience, it's okay to have a little bit of exchange. [/INST] It's fine. Like I think it's fine. Uh, if stuff comes in over the transom or you hear from someone you haven't heard from in a while they call, that's fine. I mean, that's that's email at its best, where it starts to kill us, is where all of our collaboration is happening with the back and forth when you moved the bulk of that out of your inbox. Now, you're back in that meg Ryan movie, like you've got mail or it's like, all right, let's load this up and you wait for the boat. I'm like, oh, we got </s><s>[INST] a message. Yeah, let's send me a message. This is interesting, right? Your back to the ol days. So you're talking about the bulk of the business world where like, email has replaced the actual uh, communication, all the communication protocols required to accomplish anything. [/INST] Everything is just happening with messages. If you now get most stuff done, repeatable collaborations with, with other processes that don't require you to check these in boxes. Then the inbox can serve like an inbox which includes hearing from interesting people, right? Or sending something. Hey, I don't know if you saw this. I thought you might like it. Like it's great for that. </s><s>[INST] So there's, there's probably a bunch of people listening to this. They're like, uh yeah, but I work in a team and they're all, they use this email. How do you start the revolution from like the ground [/INST] up? Yeah, we'll do it do asymmetric optimization first. So identify all your processes and then change what you can change and be socially very careful about it. So don't necessarily say like, okay, this is a new process. We all have to do. You're just, you know, hey, we gotta get this report ready here. So I think we should do like, I'll get a draft into our dropbox folder by like noon on monday, grab it. I won't touch it again until Tuesday morning and then I'll look at your changes. I have this office hours always scheduled Tuesday afternoon. So if there's anything that catches your attention grab me then. But I've told the designer who succeed on this that by C o b Tuesday, the final version will be ready for them to take and polish or whatever, like the person on the other end is like, great, I'm glad, you know, cal is a plan. So I just, what I need to do, I need to edit this tomorrow, whatever. Right? But you've actually pulled them into a process that means we're gonna get this report together without having to just go back and forth. You just asymmetrically optimize these things and then you can begin the conversation and maybe that's where my book comes in place. You just sort of </s><s>[INST] yeah, slide [/INST] it, slide it </s><s>[INST] across to buy the book and just leave it, leave it, give it to everybody on your team. Okay, So we solved the ball because he's my problem with this. Is there a case to be made that even for like communication between you and I, we should move away from from email. For example. There's a guy ever recently, I don't know if you know comedians, but there's a guy named Joey Diaz that I've had an interaction with recently and that guy, first of all, the sweetest human, despite what his comedy sounds like. He's the sweetest human being and he's a big proponent of just pick up the phone and call and it makes me so uncomfortable people call me, it's like, I don't know what to do with this thing. Uh but it kind of gets everything done quicker. I think if I remove the anxiety from that, is there a case to be made for that or his email could still be the most efficient way to do [/INST] this. No. Look, if you if you have to interact with someone, there's a lot of efficiency in synchrony, right? And there's something from distributed system theory where, you know, if you go from synchronous to asynchronous networks, there's a huge amount of overhead to the asynchronous. So actually the protocols required to solve things in a synchronous networks are significantly more complicated and fragile. The synchronous protocol. So if we can just do real time it's usually better. And also from uh interaction like social connection standpoint, there's a lot more information in the human voice, in the back and forth. Uh Yeah, if you just call some very generational right? Like our generation will be comfortable talking on the phone in a way that like a younger generation isn't but an older generation is more comfortable with, well you just call people whereas we so there's a happy medium. But most of my good friends, we just talk we have regular phone calls. Yeah, it's not, I don't just call them, we schedule, we schedule it just on text like yeah, you want to talk sometime soon. </s><s>[INST] Do you do you ever have a process that around friends? [/INST] Not really. </s><s>[INST] I feel like I should, I feel like [/INST] when you have like a lot of interesting friend possibilities as you have. Like an interesting problem, Right? Like really interesting people you can talk </s><s>[INST] to. Well that's, that's one problem. The other one is the introversion where I'm just afraid of, people get really stressed, like I freak out. And so [/INST] you picked a good line of </s><s>[INST] work? Yeah, Now perhaps it's the Goggins thing, it's like facing your fears or whatever. Uh, but it's almost like there's uh, it has to do with the timetables thing and the deep work that the nice thing about the processes is it not only automates sort of uh automates away the contact switching, it ensures you do the important things to like it's like prioritized, the thing is with email because everything is done over email. You can be lazy in the same way with like social networks and and do the easy things first that are not that important. So the process also enforces that you do the important things. And for me, the important things is like it sounds weird, but like social [/INST] connection, that's one of the most important things in all of human existence. And doing it. The paradoxical thing, I got into this for digital minimalism. Uh, the more you sacrifice on behalf of the connection, the stronger the connection feels right? So sacrificing nontrivial time and attention on behalf of someone is what tells your brain that this is a serious relationship, which is why social media had this paradoxical effect making people feel less social because it took two friction out of it. And so the brain just doesn't like, yeah, you've been commenting on this person's whatever you've been retweeting them or sending them some text, you haven't, it's not hard enough. And then then the perceived strength of that social connection diminishes where if you talk to them or go spend time with them or whatever, you're going to feel better about it. So the friction is good. I have a thing with some of my friends where at the end of each call, we take a couple days to schedule the next, then, you know, it's like I do with haircuts or something, right? Like if I don't schedule it, then I'm never gonna get my haircut right. And so it's like, okay, when you want to talk next, you know? </s><s>[INST] Yeah, that's a, that's a really good idea. I I just don't call friends and uh like every 10 years I do something dramatic for them so that we maintain the French, like I'd murder somebody that they really don't like. [/INST] I just think Joey might ask </s><s>[INST] you. Yeah, that's right. Well, that's one of my favorite lex, you gotta come out [/INST] of New Jersey. </s><s>[INST] That's exactly, we're [/INST] going to do that robot dog of yours, we're </s><s>[INST] going to go down to Jersey. There's especially human, I love the comedian world, they've been shaking up, I don't know if you listen to joe Rogan, all those folks, they kind of uh are doing something interesting form it and, and academia there shaking up this world a little bit like podcasting because comedians are paving the way for podcasting. And so you have like Andrew Huberman who's a neuroscientist at stanford in front of mind now, he's like into podcasting now and you're into podcast. Of course, you're not necessarily podcast about computer science currently, right? But that it feels like you could have a lot of the free spirit of the comedians implemented by the people who are academically [/INST] trained to actually have a nice specialty. </s><s>[INST] Yeah. And then, and then that results, I mean who knows what the experiment looks like, but that results me being able to talk about robotics with Joey Diaz when he says, you know, drops f bombs every other sentence and I, the world is like, I've seen actually a shift within uh colleagues and friends with an M. I. T. Where they're becoming much more accepting of that kind of thing. It's very interesting. [/INST] That's interesting. So you're seeing, okay, </s><s>[INST] because they're seeing how popular it is, they're [/INST] like, well you're popular. I don't know how they think about it at Georgetown for example. </s><s>[INST] I don't know, it's interesting, but I think what what happens is the popularity of it, combined with just good conversations with people they respect like uh okay, this is the thing. Yeah. And this is [/INST] more fun to listen </s><s>[INST] to than a shitty zoom lecture about their work. It's like there's something here, there's something interesting and we don't, nobody actually knows what that is just like with like clubhouse or something. Nobody's figured out. Like where is this medium take because it's a legitimate medium of education? Or is this just like a fun? [/INST] Well, that's your innovation I think was we can bring on professors and I know Joe Rogan does some of that too, but, but you know, but your professors in your field, like bring all these guys who I remember, you know, </s><s>[INST] well that's been the big challenge for me is I don't is I feel I would, I would ask big like philosophical questions of people like yourself, they're like really well public, like this is, so for example, you have a lot of excellent papers on, uh, you know, that has a lot of theory in it, right? And there is some temptation to just go through papers and I think it's possible to actually do that. I haven't done that much, but I think it's possible. It just requires a lot of preparation and I can probably only do that with things that I'm actually like in the field I'm aware of. But there's a dance that I would love to be able to try to hit right where it's actually getting to the core of some interesting ideas as opposed to just talking about philosophy at the same time, there's a large audience for people that just want to be inspired by, like by disciplines where they don't necessarily know the details, but there's a lot of people that are like, I'm really curious. I've been thinking about pivoting careers into software engineering. They would love to hear from people like you about computer science, even if it's like theory, [/INST] but just like the idea that you can have big ideas, you push them through and it's interesting you fight for it. </s><s>[INST] But there's some, there's, what is the computer file and uh, Uh, number file, these YouTube channels. There's uh, channels I watch, I'm like chess, exceptionally popular where I don't, I don't understand maybe 80% of the time, what the hell they're talking about because they're talking about like why this move is better than this move, but I love the passion and the genius of those people are just overhearing it. I don't know why that's so exciting. [/INST] Do you look at like scott Aaronson blog at all the subtle optimized. Yeah, it's like hardcore complexity theory, but it's, there's an enthusiasm or like terry towels blog. I'm </s><s>[INST] a little bit of humor. Terry tao has a blog [/INST] he used to, yeah, uh, it would just be, I'm going all in on, you know, here's a new, a fine group with which you can be whatever. But I mean it was just equations. Well in </s><s>[INST] the case of scott Harrison, he's good. He's able to turn on like the inner troll and comedian and so on. He keeps the fund, which is the [/INST] best of the philosophical guy that turns over philosophy. </s><s>[INST] Yeah. So you know, we're exploring these different ways of communicating science and and exciting in the world. Speaking of which I gotta ask you about computer science. That's [/INST] right, I do some of that. </s><s>[INST] Uh so I mean a lot of it, a lot of your workers would inspire this deep thinking about productivity from all the different angles because some of the most rigorous work is mathematical work. And in computer science, that theoretical computer science let me ask the scott Anderson question of like is there something to you that stands out in particular that's beautiful, inspiring or just really inside football, computer science or or maybe mathematics. [/INST] I mean I like theory and in particular what I've always liked in theory is the notion of impossibilities, that's kind of my specialty. So within the, within the context of distributed algorithms, my specialty is impossibility results. The idea that you can argue nothing exists that solves this or nothing exists that can solve this faster than this. And that's I think that's really interesting and that goes all the way back to turing there's his original paper on computable numbers with their connection to the it's in german I slipped on problem but basically the german name that Hilbert called the decision problem. This was pre computers, but he was he's english. So it's right in english. So it's very accessible paper and it's it lays the foundation for all of theoretical computer science. He just has this insight. He's like, well if we think about like an algorithm and he figures out like all effective procedures or turning machines are basically algorithms. We could really describe a turing machine with a number which we can now imagine with like computer code. You can just take a source file and just treat the binary version of the file is like a really long number, right? But he's like every program is just a finite number. It's a natural number. And then he realized like one way to think about a problem is you have this is like kind of the mic sips her approach but you have a sort of it's a language. So of an infinite number of strings. Some of them are in the language and some of them aren't. But basically you can imagine a problem is represented as an infinite binary string or in every position like a one means that string is in the language and zero means it isn't. And then he applied cantor from the 19th century and said, Okay, the natural numbers are countable. So it's accountably infinite and infinite binary strings. You can use a diagonal Ization argument. And so they're they're uh they're uncountable. So there's just vastly more problems than there are algorithms. So basically anything you can come up with for the most part almost certainly is not solvable by a computer, you know. And then and then he was like, let me give a particular example and he figured out the very first compute ability proof. And let's just walk through with a little bit of simple logic. The halting problem can't be solved by an algorithm. And that kicked off the whole enterprise of some things can't be solved by algorithms, some things can't be solved by computers. And we've just been doing theory on that Since the that was the 30's he wrote that. </s><s>[INST] So proving that something is impossible uh is sort of a stricter version of that? Is that like proving bounds on on the performance of [/INST] different algorithms? Those are so bounds or upper bounds. Right? So you say, uh this algorithm does at least as well and no worse than this. But you're looking at a particular algorithm and possibility proof. Say no algorithm ever could ever solve this problem. So no algorithm could ever solve the halting problem. </s><s>[INST] This problem centric it's making something different. Making a conclusive statement about the problem and that's somehow satisfying because it's uh [/INST] just philosophically interesting. Yeah, I mean, it all goes back to you get back to plato it's all reducto ad absurdum So all these arguments have to start, the only way to do it is there's an infinite number of solutions. You can't go through them. As you say, let's assume for the sake of contradiction that there existed something that solves this problem and then you turn the crank a logic until you blow up the universe and then you go back and say, okay, original assumption that this solution exists can't be true. I don't think philosophically, it's like it's really exciting, kind of beautiful thing is what I specialize in within distributed algorithms is more like a time bound impossibility results like no, no algorithm can solve this problem faster than this in this setting of all the infinite number of ways you might ever do </s><s>[INST] it. So you have many papers, but the one who caught my eyes smooth analysis of dynamic networks in which you write a problem with the worst case perspective is that it often leads to extremely strong lower bounds. These strong results motivated key question is this bond robust in the sense that it captures the fundamental difficulty introduced by dynamism or is the bond fragile in the sense that the poor performance it describes depends on an exact sequence of adversarial changes fragile, lower bounds leave open the possibility of algorithms that might still perform well in practice. That's a in the sense of the impossible And the balance discussion presents the interesting question just like the idea of robust and fragile bounds. But uh what do you make about this kind of tension between what's probably like what bounds you can prove there are like robust and something that's a bit more fragile. And and also by way of answering that for this particular paper, can you say, What the hell are dynamic networks? What are distributed? You don't know this. Come on now and I have no idea. And what is smooth analysis. [/INST] Yeah, well, okay, so so smooth analysis, it wasn't my idea. So Spielman and paying came up with this in the context of sequential algorithms, just like the normal world of an algorithm that runs on a computer. Uh and they were they were looking at there is a well known algorithm called the simplex algorithm, but basically you're trying to whatever, find a hole around a group of points and there's an algorithm that worked really well in practice. But when you analyze it, you would say, you know, I can't guarantee it's going to work well in practice because you have just the right inputs. This thing could run really long, Right? But in practice it seemed to be really fast. So smooth analysis as they came in and they said, let's assume that bad guy chooses the inputs. That could be anything like really bad ones. And all we're gonna do is because and and simplex their numbers, we're going to just randomly put a little bit of noise on each of the numbers. And they said, if you put a little bit of noise on the numbers, suddenly simplex algorithm goes really fast, like that explains this. This lower bound. This, this idea that it could sometimes run really long was a fragile bound because it could only run a really long time if you had exactly the worst pathological input. So then my collaborators and I brought this over to the world. The distributed algorithms. We brought him over the general lower bounds. Right? So so in the world of dynamic networks, so distributed algorithms, a bunch of algorithms on different machines, talking to each other, trying to solve a problem sometimes during a network. So you imagine them connected with network links and a dynamic network, those can change. Right? So, I was talking to you, but now I can't talk to you anymore. And I'm connected to a person over here. It's a really hard environment, mathematically speaking. And there's a lot of really strong lower bounds. But you can imagine if the network can change all the time and the bad guys doing it. It's like hard to do things well. </s><s>[INST] So there's an algorithm running on every single node in the network. And then you're trying to say something of any kind that makes any kind of definitive sense about the performance of the algorithm. [/INST] So, like we're So I just submitted a new paper on this a couple weeks ago and we were looking at a very simple problem. There's there's a some messages in the network. We want everyone to get them if the network doesn't change, you can do this pretty well, you can pipeline them. There's some algorithms that work basic values that work really well, so that we can change every round. There's these lower bounds that says uh it takes a really long time. There's a way that like no matter what album you come up with theirs away, the network can change in such a way that just really slows down your progress basically. Right? So smooth analysis there says Yeah, but that seems like a really, really bad luck if your network was changing like exactly in the right way that you needed to screw your algorithm. So we said what if we uh randomly just add or remove a couple edges in every round? The adversary is trying to choose the worst possible network. We're just tweaking it a little bit and in that case this is a new paper. I mean it's a blinded submission. So maybe I shouldn't it's not whatever. Um we basically showed an anonymous friend of yours submitted a paper anonymous friend of yeah, newspaper should be accepted. So that even just adding like one random edge per round you uh here's the cool thing about the simplest possible solution to this problem blows away that lower bound. It does really well. So that's like a very fragile lower bound because we're like, it's it's almost impossible to actually keep things slow. I </s><s>[INST] wonder how many lower bounds you can smash open with this kind of analysis and show that they're fragile. It's [/INST] my interest because in and distributed algorithms there's a ton of really famous, strong lower bounds but things have to go wrong really really wrong for these lower bound arguments to work. And so I like this approach. So there's this whole notion of fragile verse robust. I was like let's go in and just throw a little noise in there and if it becomes solvable and maybe that lower bound wasn't really something we should worry about. </s><s>[INST] You know that's kind of embarrassed. That's really uncomfortable. It's really embarrassing to a lot of people because okay this is the O. C. D. Thing. The spaces. It feels really good when you could proven eyes bound. And if you say that that bond is fragile that that's that's like there's going to be a sad kid that walks uh like with their lunch box back home. Like my my lower bond doesn't [/INST] matter. I don't think they care it's all and I don't know it feels like to me a lot of theory is just math machismo. Yeah it's like whatever this was a hard bound to </s><s>[INST] proof. What do you think about that? Like so if you show that something is fragile that's more important, that's really important in practice. Right? Uh So do you think kind of theoretical computer science is living its own world just like mathematics and their main effort which I think is very valuable to develop ideas. It's not necessarily interesting whether it's applicable in the real world. We don't care about the [/INST] applicability. Yeah we kind of do but not really were terrible with computers and can't do anything useful with computers that we don't know how to code. And, you know, we're not we're not productive members of like technological society. But I do think things percolate, percolate from the world of theory into the world of algorithm design, which will pull on the theory and now suddenly it's useful. Uh and then the algorithm design gets pulled into the world of practice where they say, well, actually we can make this algorithm a lot better because in practice really these servers do X, Y, Z. And now we can make this super efficient. And so I do think, I mean, I tell my, I teach theory to the PhD students at Georgetown. I showed him the sort of funnel of like, okay, we're over here doing theory, but it eventually some of this stuff will percolate down in effect at the very end, you know, a phone. But it's a long, it's a long tunnel. </s><s>[INST] But the very question you're asking at the highest philosophical level is fascinating. Like, if you take a system, a distributed system or a network and introduced a little bit of noise into it. Like, how many problems of that nature are fundamentally changed by that little introduction of noise. [/INST] Yeah, because it's all especially distributed algorithm. The model is everything like, the way we work is we're incredibly precise about here's exactly it's mathematical. Here's exactly how the network works and it's a state machine algorithms are state machines, there's rounds and schedules were super precise. We can prove lower bounds, but often those lower those impossibility results really get at the hard edges of exactly how that model works. So we'll see if that's so we we we published a paper on this, that paper you mentioned, um they kind of introduced the idea to distribute algorithms world and I think that's got some traction and there's been some follow ups and we've just submitted our uh our next, honestly the issue at the next is that like the result fell out so easily and this is just a mathematical machismo problem in these, in these fields is there's a good chance the paper won't be accepted because there wasn't enough mathematical self flagellation. </s><s>[INST] That's such a nice finding. So even just showing that very few just very little bit of noise going to have a dramatic, make a dramatic statement about [/INST] the physical big surprise to us. But once we figured out how to show it, it's not too hard. </s><s>[INST] And these are, these are venues that for theoretical for theoretical. Okay, so the fascinating tension that exists in other disciplines, like one of them is machine learning now, which despite the power of machine learning and deep learning and all, like the impact of it in the real world. The main conference is a machine learning are still resistant to application papers, I'm not uh sort of and application papers broadly defined meaning like finding almost like you would like Darwin did by like uh going around collecting some information saying, huh isn't this interesting? Uh like those are some of the most popular blogs. And yet as the paper, it's not really accepted. I I wonder what you think about this whole world of deep learning from a perspective of theory. What do you make of this whole discipline of the success of neural networks of how to do science on them? Are you excited by the possibilities of what we might discover about neural networks? Do you think is fundamental and engineering discipline? Or is there something theoretical that we might crack open one of these days in understanding something deep about how system optimization, when how systems learn. [/INST] I am convinced by is it time to market at M I T, whose tag Mark? Yeah. Mark. Right. So his notion has always been convincing to me uh that the fact that some of these models are inscrutable is not fundamental to them and that we can we're gonna get better and better because in the end, you know, the reason why practicing computer scientists often who are doing ai or working at a an industry aren't like worried about so much existential threats is because they see the reality, is there multiplying matrices with numpy or something like this? Right? Yeah. And and tweaking constants and hoping that the classifier fitness for God's sakes before the submission deadline actually like it's above. Something like it feels like it's it's linear algebra and, and TDM right. Um, but anyways, I'm really convinced with his idea that once we understand better and better, what's going on from a theory perspective, it's going to make it into an engineering discipline. So in my mind where we're going to end up is okay, forget these metaphors of neurons and these things are gonna get put down into these mathematical kind of elegant equations, differential equations that just kind of work well. And then it's going to be when I need a little bit of a I in this thing plumbing, like let's get a little bit of a pattern, recognize er, with a noise module and let's connect, you know, this feels better than me. So I don't know if this is like a reasonable, a reasonable prediction, but that we're going to it's gonna become less inscrutable and then it's going to become more engineer a ble and then we're going to have a I and more things because we're gonna a little bit more control over how we piece together these different classification </s><s>[INST] black box. So one of the problems and there might be some interesting parallels that you might provide. Intuition on is, you know, neural networks are very large and they have a lot of it, you know, we were talking about uh, you know, dynamic networks and distributed algorithms. One of the problems with the analysis of neural networks is uh you know, you have a lot of nodes and you love a lot of edges to be able to interpret and to control different things are very difficult. There is uh uh there's fields and trying to figure out like mathematically how you form uh clean representations that are like like one node contains all the information about a particular thing and no other nodes is correlated to it. So like it has unique knowledge and like but that ultimately boils down to trying to simplify this thing into that goes against the very nature which is like deeply connected and uh like dynamic and just, you know, hundreds of millions, billions of nodes. And in a distributed sense, like when you zoom out the thing has a representation and understanding of something, but the individual notes are just doing their little exchanging thing. And it's the same thing with Stephen Wolfram, when you talk about Celia Tamara, it's very difficult to do math when you have a huge collection of distribute things, each acting on their own. And it's almost like it feels like it's almost impossible to do any kind of theoretical work in the traditional sense. It almost becomes completely like uh like a biology, you become a biologist as opposed to a theoretician, you just study it [/INST] experimentally. Yeah. So I think that's the big question, I guess. Right? Yeah. So, so is the large size and interconnectedness of the like a deep learning network fundamental to that task or we're just not very good at it yet because we're using the wrong metaphor. I mean the human brain learns with much fewer examples and with much less tuning of the whatever, whatever whatever probably that requires to get those like deepmind networks up and running. But yeah, so I don't really know. But the one thing I have observed is that the you know, there's a the mundane nature of some of the working with these models tends to lead people to think that to do it. Like it could be skynet or it could be like a lot of pain to get, you know, the thermostat to do what we wanted </s><s>[INST] to do. And there's a lot of open questions in between there and then of course the at a distributed the distributed network of humans that use these systems. So like you can have the system itself then the neural network but you can also have like little algorithms controlling the behavior of humans which is what you have a social networks, it's possible that a very what is a toaster, whatever the opposite of sky net when taking a scale was used by individual humans and controlling their behavior can actually have the sky net effect. So the scale there, [/INST] we might have that now </s><s>[INST] we might have that now we just don't know like it's [/INST] twitter creating a little mini skynet. I mean because what happens? it twirls out ramifications in the world. And is it really that much different if it's a robot with tentacles or a bunch of servers that </s><s>[INST] Yeah and the destructive effects could be I mean it could be political but it could also be like you know you could probably make an interesting case that the virus, the coronavirus spread on twitter too in the minds of people like the fear and the misinformation in some very interesting ways mixed up and maybe this pandemic wasn't sufficiently dangerous to where that could have created a weird like on instability but maybe other things might create instability like somebody God forbid detonates a nuclear weapons somewhere and then maybe the destructive aspects of that would not as much be the military actions, but the way those news are spread on twitter and the panic that creates. [/INST] Yeah. Yeah. I mean I think that's a great case study right? Like what what happened? Not what I'm not suggesting that likes to go let off a nuclear bomb. I meant the coronavirus but okay. But but yeah, I think that's a really interesting case study. Um I'm interested in the counterfactual of 1995 like do the same virus in 1995. So first of all it would have been I get to hear whatever the nightly news we'll talk about it and then they'll be by local health board, we'll talk about it, that meant mitigation decisions would probably necessarily be very sort of localized, okay, our communities trying to figure out what are we going to do, what's going to happen? Like we see this with schools like where I grew up in New Jersey, there's very localized school districts. So even though they had sort of really bad viral numbers, they're, my school I grew up in has been open since the fall because it's very localized. Like these teachers and these parents, what do we want to do? What are we comfortable with? I live in a school district right now in Montgomery County, that's a billion dollar a year. Budget, 250,000 kids school district just can't it's closed, you know, because it's it's too. So I'm interested in that counterfactual, yes, you have all this information moving around and then you have the the, the effects on discourse that we were talking about earlier that that the Neil postman style effects of twitter, which shifts people into a sort of a dunk culture mindset of uh don't give an inch to the other team and we're used to this and was fired up by politics and the unique attributes of twitter. Now throwing the coronavirus and suddenly we see decades of public health knowledge, a lot of which was home during the HIV epidemic was thrown out the window because a lot of this was happening on twitter and suddenly we had public health officials using a don't give an inch to the other team mindset of like, well, if we say this, That might validate something that was wrong over here and we need to, if we say this and maybe like that'll stop them from doing this. That's like very twittering in a way that in 1995, it's probably not the way public health officials would be thinking right now. It's like, well this is if we said this about mass, but the other team said that about mask. We can't give an inch so we gotta be careful and like we can't tell people it's okay after they're vaccinated because that might give them an inch on this. And that's very twittering in my mind, right? That is the the impact of twitter on the way we think about discourse, which is a dunking culture. If don't give any answer to the other team. And it's all about slam dunks were completely right and they're completely wrong. It's as a rhetorical strategy is incredibly simplistic, but it's also the way that we think right now about how we do debate it combined terribly with Election year pandemic. </s><s>[INST] Yeah. Election year pandemic. I wonder if we can do some smooth analysis, lets run the simulation over a few times. A little noise. Yeah. You see, you see if it can dramatically change the behavior of the system, Okay, we talked about your love for proving that something is impossible. So there's quite a few still open problems in complexity of algorithms. Uh So let me ask does P equals np problem? Probably not if P equals np what kind of, you know, and you'll be really surprised somebody proves it. What would that proof look like and why would that even be? What would that mean? What would that proof look like and what possible universe could be equals Np. Is there something inside? So you can say there? [/INST] It could it could be true. I mean, I'm not a complexity theorist, but every complexity theorist I know is convinced they're not equal And are basically not working out anymore. I mean there is $1 million Millennium Prizes. Okay, so here here's how I think the P not equals M. P. Proof is going to eventually happen. I think it's going to fall out and it's going to be not super simple, but not as hard as people think because my my theory about a lot of theoretical computer science based on just some results I've done. So this is a huge extrapolation is that a lot of what we're doing is just a few skating deeper mathematics. So like this happens to me a lot, not a lot of what's happened to me a few times in my work where we obfuscate it because we say, well there's an algorithm and has this much, you know, memory and they're connected on a network and okay, here's our setup and now we're trying to see how fast it can solve a problem and people do bounds about. And then the end, it turns out that like we were just obfuscating some underlying, you know, mathematical thing that already existed, right? So this has happened to me. I had this paper was quite fond of a while ago. It was looking at this problem called contention resolution, where you you you put an unknown set of people on a shared channel and they're trying to break symmetry. So it's like an ethernet, whatever. Only one person can use it at the time. You try to break symmetry. There's all these bounds people have proven over the years about how long it takes to do this. Right? And like I discovered at some point there's this one combinatorial results From the early 1990s, all of these lower bound proofs all come from this. In fact, it improved a lot of them and simplified a lot. You can put it all in one paper, you know, it's like, are we really And then Okay, so this new paper that I submitted a couple weeks ago, I found you could take some of these same lower bound proofs for this contention resolution problem. You could reprove them using Shannon's source code theorem That actually when you're breaking contention, what you're really doing is building a code over, you know, uh if you have a distribution on the network sizes is the code over that source. And if you plug in a high entropy information source and plug in from 1948, the source code theorem that says on a noiseless channel, you can't send things at a faster rate than the entropy allows. The exact same lower bounds fall back out again. Right. So like this type of thing happens. There's a there's some famous lower bounds and distributed algorithms that turned out to all be algebraic topology underneath the covers and they won the girdle prize. We're working on that. So, my sense is what's going to happen is at some point, someone really smart to be very exciting is going to realize there's some sort of other representation of what's going on with these turing machines trying to sort of efficiently </s><s>[INST] usually follow a lot of that [/INST] there will be an existing mathematical result that </s><s>[INST] apply someone or something. I guess it could be a I theo improvers kind of thing. [/INST] It could be Yeah, I mean, well, yeah, there's the're improvers like what that means now, which is not fun. </s><s>[INST] It's just a bunch of very [/INST] carefully formulated postulates that. But I take your point, </s><s>[INST] Yeah. So, okay, uh you know, a small tangent on them then you're kind of implying the mathematics. It almost feels like a kind of weird evolutionary tree that ultimately leads back to some kind of ancestral if you fundamental ideas that all they're just like they're all somehow connected uh in that sense, do you think uh math is fundamental to our universe and we're just like slowly trying to understand these patterns? Or is it is it discovered? Or is it just a little game that we play amongst ourselves to try to fit little patterns to the world? [/INST] Yeah, that's the question. Right? That's the physicist question. I mean, I'm probably I'm in the discovered camp, but I don't do theoretical physics. So I know they have a they feel like they have a stronger claim that the answering that question. So you don't come back to it. Everything comes back to it. I mean, all of physics, the fact that the universe is well, Okay, yeah, it's a complicated question. </s><s>[INST] So, how often do you think, how deeply does this result describe the fundamental reality of nature? [/INST] So, the reason I hesitated because it's something I'm I taught the seminar and did a little work on what are called biological algorithms. So, there's this notion of Yeah, so physicists used mathematics to explain the universe, Right. And it was unreasonable that mathematics works so well, yeah. All these differential equations, why does that explain all we need to know about thermodynamics and gravity and all these, all these types of things? Well, there's this there's this movement within the intersection of computer science and biology? Uh just kind of Wolfram e um I guess really that algorithms can be very explanatory, right? Like if you're trying to if you're trying to explain parsimonious lee something about like an ant colony or something like this, you're not going to ultimately it's not going to be explained as an equation, like a physics equation, it's gonna be explained by an algorithm. This algorithm run distributed lee is going to explain the behavior. So that's mathematical, but not quite mathematical. But it is if you think about an algorithm, like a lambda calculus, which brings you back to the world of mathematics, I'm thinking out loud here, but basically abstract math is unreasonably effective at explaining a lot of things. And that's just what I feel like I glimpse I'm not a uh not like a super well known theoretician, I don't have really famous results. So even as a sort of middling, you know, career theoretician, I keep encountering this where we think we're solving some problem about computers and algorithms and it's some much deeper underlying math. It's Shannon, but Shannon is entropy but entropy was really, you know, goes all the way back to whatever it was boiling all the way back to looking at the early physics. And and it's it was to me, I think it's amazing. </s><s>[INST] Yeah, but it could be the flip side of that could be just our brains draw so much pleasure from the uh deriving generalized theories and simplifying the universe, that would just naturally see that kind of simplicity and everything. [/INST] Yeah, so that's the whole, you know, Newton to Einstein, so you can you can say this must be right because it's so predictive, well it's not quite predictive because Mercury wobbles a little bit. I think we have it set and then you turn out now Einstein and then and then you get more like, no, not Einstein, it's actually statistical and yeah, so </s><s>[INST] it's hard to also know like where smoothed analysis fits into all that, where a little bit of like you can say something very clean about a system and then a little bit of noise, like the average case is actually very different. And so, I mean that's where like the quantum mechanics comes in, it's like uh why does it have to be randomness in this? Yeah. [/INST] This complex statistics. </s><s>[INST] Yeah. So to be determined. [/INST] Yeah, that'll be my next book will be ambitious. The fundamental the fundamental core of reality comma and some advice for being more productive at </s><s>[INST] work. Can I ask you just if it's possible to do an overview and just some brief comments of wisdom on the process of publishing a book, what's that process entail? What are the different options and what's your recommendation? Uh for somebody that wants to write a book like yours, a nonfiction book that discovers something interesting about this world. [/INST] So what I usually advise is follow the follow the process as is don't try to reinvent. I think that happens a lot where you'll try to reinvent the way the publishing industry should work. Like this is kind of not like in a business model ways, but just like this is what I want to do. I want to write 1000 words a day and I want to do this and I'm gonna put on the internet and the publishing industry is very specific about how it works. And so like when I got started writing books was at a very young age. So you know, I sold my first book at the age of 21. The way I did that is I found the family friend, there was an agent and I said I'm not trying to make you be my agent. Just explain to me how this works, not just how the world works. But give me the hard truth about how would they 21 year old under what conditions could a 21 year old sell a book, what would that look like? And she just explained it to me well you have to do this and have to be a subject that it made sense for you to write and you would have to do this type of writing for other publications, the validated and blah blah blah. And you have to get the agent first. And I learned a whole game plan and then executed. And so the rough game plan is with nonfiction, you get the agent first and the agents going to sell it to the publishers. So like you're never sending something directly to the publishers and nonfiction, you're not writing the book first, right? You're going to get an advance from the publisher once sold. And then you're going to do the primary writing the book. In fact it will in most circumstances hurt you if you've already </s><s>[INST] written written. So you're you're trying to say, well, I guess the agent first yourself to the agent and the agent sells [/INST] it to the publishers. It's much easier to get an agent than a book deal. So that the thought is if you can't get an agent and why would you? So you start with you. And also in the way this works with a good agent is they know all the editors and they have lunch with the editors and they're always just look at what projects you have coming. What are you looking for here is when my authors, that's the way all these deals happen. It's not you're not emailing a manuscript to a slush pile. </s><s>[INST] Yeah. And so so first of all, the agent takes a percentage and then the publishers, this is where the process comes in. They take also cut, that's probably ridiculous. So if you try to reinvent the system, you'll probably be frustrated by the percentage of everyone takes relative to how much bureaucracy and efficiency ridiculous sisters in the system. Your recommendation is like you're just one ant stop trying to build your own and colony [/INST] well or or if you create your own process for how it should work. It's not going to the book is not going to get published. So there's a separate question, the economic question, like, should I create my own like self publish it or do something like that? But putting that aside, there's a lot of people I encounter that want to publish a book with the main publisher, but they invent their own rules for how it works. </s><s>[INST] So then the alternative though, is self publishing and the downside, there's a lot of downsides. It's like, it's almost like publishing an opinion piece in the new york Times versus writing our blog, there's no reason why writing a blog post on medium can get way more attention and legitimacy and long lasting prestige than the New york Times article. But nevertheless, for most people writing in a prestigious newspaper, quote unquote, prestigious uh is is just easier [/INST] and well and depends on your goal. So, you know, like I push you towards a big publisher because I think your goal is it's huge ideas. You want impact. You can have more impact </s><s>[INST] even though like actually, so there's different ways to measure impact on the world of ideas in the world of ideas and also, yeah, in the world of ideas, it's kind of like the clubhouse thing Now, even if the audience is not large, the people in the audience are very interesting as it's like the conversation feels like there has long lasting impact among among the people who in different in desperate industries that are also then starting their own conversations and all that [/INST] kind of because you have other, so like, so like self publishing the book, um the goals that would solve you have much better ways of getting to those goals might be part of it, right? So if there's the financial aspect of what you get to keep more of it, I mean the podcast is probably gonna crush what the book is gonna do anyways, right? Yeah, if it's uh wanna get directly to certain audiences or crowds, that might be harder through a traditional publisher, there's better ways to talk to those crowds. It could be on columbus with all these new technologies, self published books, not going to be the most effective way to find your way to a new crowd, but if the idea is like, I want to have a leave a dent in the world of ideas, then they have a vulnerable old publisher, you know, put out your book in a nice hardcover and do the things they do that goes a long way and they do do a lot. I mean there's it's it's very difficult actually, there's so much involved in </s><s>[INST] putting together a book, they get books into bookstores and all that kind [/INST] of stuff, all this. And from an efficiency standpoint, I mean, just a time involved in trying to do this yourself is </s><s>[INST] there no process, right? Like you [/INST] said they have a process, you've got a process. I mean I know like Jacko did this recently started his own imprint and I have a couple other but it's a huge overhead. I mean if you like if you run a business and you so like Jaco is a good case study right? So he got you know fed up with Simon and Schuster dragging their feet and said I'm gonna start my own imprint then if you're not gonna publish my kid's book. Um But he what does he do? He runs businesses right. So I think in his world like I already run I'm I'm a partner and whatever in origin and I have this and that. And so it's like yeah we can run businesses that's what we know how to do. That's what I do. I run businesses. I have people but for like you or I we don't run businesses would be terrible. Yeah </s><s>[INST] well especially these kinds of businesses right? So I do want to launch a business. Very different technology business [/INST] is very very different. Very very different. Yeah I mean this is like okay and you copy editors and and graphic book binders and I need to contract with the printer but the printer doesn't have slots and so now I have to try to I mean it's </s><s>[INST] I guess so I need to shut this off in my brain but I get so frustrated when the system could clearly be improved. It's the thing that you're mentioning. It's like this is so inefficient every time I go to the D. M. V. Or something like that. You think like this could be done so much better. Uh But you know in the same thing as the worry with with an editor which I guess would come from the publisher who would who would uh how much supervision on your book did you receive? Like hey do you think this is too long or do you think the tight like title? How much choice do you have in the title? In the cover in the presentation of the branding and all that kind [/INST] of stuff? Yeah. I mean all of it depends, right? So when it comes on uh the relationship on the with the editor on the writing it depends on the editor and it depends on you. It's like at this point I'm on my seventh book and I write for a lot of major publications and at this point I have what I feel like as a voice that I've a level of craft that I'm very comfortable with. Right? So my editor is not going to be, She kinda is going to trust me and it's gonna be more big picture like uh I'm losing the thread here or this seems like it could be longer. Whereas the first book I wrote when I was 21, I had notes such as you start a lot of sentences with. So uh you don't use any contractions because I've been doing scientific writing, use contractions like you should probably use contractions. It was way more, you know, I had to go back and rewrite the whole thing. </s><s>[INST] But ultimately the recommendation, I mean we talked offline and sort of, I was thinking loosely not really sure, but I was thinking of writing a book and there's a kind of desire to go self publishing, not for financial reasons. [/INST] And the money can be good by the way. Right? I mean, it's very it's very power law type just distributed. Right? So, so the money on a hard cover somewhere between one or $2 a book. </s><s>[INST] So the thing is I [/INST] personally don't, but do you give up 15% of the agent? </s><s>[INST] So I personally don't care about money as I've mentioned before. But I for some reason really don't like spending money on things that are not worth it. Like I don't care if I get money. I just don't like spending money on like feeding a system that's inefficient. It's like I'm contributing to the problem. That's my biggest problem. [/INST] So you think that you're you're worried about the inefficiencies of the yeah. The fact that uh over has a number of people involved or </s><s>[INST] the overhead the emails. Again, the fact that they have this way of speaking, which I'm allergic to many people. like that's very marketing speak like, you could tell they have been having zoom meetings all day. It's like as opposed to a sort of creative collaborators that are like, also a little bit crazy, I suppose some of that is finding the right people, [/INST] finding the right people. That's what I would say. I say there's definitely maybe it's just good fortune good fortune in terms of like, my agents and editors I've worked with theirs. Really good people who they see the vision or smart or incredibly literary. They Yeah. And like, yeah, I had a great editor when I was first moving in the hardcover books, for example, it was my first, you know, big book advance and my first sort of big deal. And uh he was like a senior editor and it was very useful. You know, he was like, we had a lot of long talks, right? I was this was my fourth book. So good. They can't ignore. It was my first a big hardcover idea book. Um and we had a lot of talks like even before I started writing it, just, let's talk about books and his philosophy had been in the business for a long time. It was the head of the head of the imprint. It was useful. </s><s>[INST] Yeah. But I mean, the other frustrating thing is how long the whole thing takes a long time. Yeah, I suppose that's he just had to [/INST] accept Yeah, I handed in this manuscript for the book that comes out now? Like, when I handed it in, I mean, over the summer, like, during the pandemic. So it's not it's not terrible, right? And we were editing during the pandemic and I finished it in the spring. </s><s>[INST] We've talked most of today, except for a little bit computer science. Most of today about a productive life. Um how does love friendship and family fit into that? Is there um do you find that there is a tension? Is it possible for relationships to energize the whole process to benefit? Or is it ultimately a trade off? But because life is short and ultimately we seek happiness, not productivity, that we have to accept that tension. [/INST] I mean, I think relationships is the that's the that's the whole deal. Like, I thought about this the other day. I don't think context was I was thinking about if I was gonna give like, an advice speech, like a commencement address or like, giving advice to young people. And uh like, the big question I have for young people is if they haven't already, bad things are gonna happen that you don't control. So what's the plan? Right? Like, let's start, let's start figuring it out now, because it's not all, you know, some people get off better than others, but eventually stuff happens, right? You get sick. Something falls apart. The economy creators, the someone like, you know, die, like, all sorts of bad stuff is going to happen right? So how are we gonna do this? Like how do how do we like live life and life is hard and in ways that is unfair and unpredictable um relationships is the that's the buffer for all of that because we're wired for it. I went down this rabbit hole with digital minimalism. I went down this huge rabbit hole about the human brain and sociology. It's all we're wired. It's like all of our brain is for this like everything, all of our mechanisms, everything is made to service social connections because what kept you alive, you know I mean you have to your travel connections is how you didn't starve during the famine. People share food, et cetera. Um and so you can't neglect that and it's like everything and and people feel it right? Like there's no our social networks are hooked up to the pain center. That's why it feels so terrible when you miss someone like someone dies or something right? That's like how seriously we take it. There's a pretty accepted theory that the default mode network like a lot of what the default mode network is doing. So that's sort of the default state our brain goes into when we're not doing something in particular is practicing sociology practicing interactions because it's it's so crucial to what we do. It's like at the core of human thriving. So I've more recently the way I think about is like relationships first. Mm okay, given that foundation of putting like, and I don't think we put nearly enough time into it. I worry that social media is reducing relationships, strong relationships, strong relationships with your sacrificing nontrivial time and attention and resources whatever on behalf of other people. That's the net that is gonna allow you to get through anything then All right now, what do we want to do with uh the surplus that remains, may want to build, build some fire, build some tools. </s><s>[INST] So put relationships first, I like the worst case analysis from the computer science perspective. Put relationships first. Yeah, because everything else is just uh assuming average case, assuming things kind of keep going as they were going [/INST] and you're neglecting the fundamental human drive. Like we we have to talk about the boredom and stink, we want to build things, we want to have impact, we want to productivity, that's not nearly as clear cut of a drive of we need people, </s><s>[INST] but if we look at the real worst case analysis here is one day you're pretty young now but that's not gonna last very long. You're gonna die one day. Is that something you think about? [/INST] Little bit, </s><s>[INST] are you afraid of death? [/INST] Well I'm of the mindset of, let's make that a productivity hack. I'm of the mindset of um we need to confront that soon. So let's do what we can now so that when we really confront and think about it, we're more likely to feel better about it. So in other words like, let's, let's focus now on living and doing things in such a way that we're proud of. So that when it really comes time to confront that were more likely to say like, okay, I feel kind of good about the situation. So </s><s>[INST] what, when you're laying on your deathbed, would you looking back, what would make you think like, oh, I did a, I did okay, I'm proud of that. I optimized the hell out of that. That's a [/INST] good, I mean, it's a good question that the go backwards on. I mean, this is like David Brooke's eulogy virtues versus resume virtues. Right? So his argument is that that's another interesting dc area person I keep thinking of of interesting to Syria people. All right, David brooks is going to um his argument, he thinks eulogy virtues is, so what we eulogize is different than what we promote on the resume. That's his whole thing now, right? His Second Mountain Road, the character both these books are, he has this whole premise that there's like this professional phase and there is the phase of giving of yourself and sacrifice on behalf of other people. I don't know, maybe it's all mixed together, right? You want to, I think living by a code is important, right? I mean, uh, there's something is not emphasized enough. I always think of advice that my undergrad should be given, that they're not given, especially a place like Georgetown that has this like deep history of, you know, trying to promote human flourishing because of the Jesuit connection. Uh, there's such, there's such uh, resiliency and pride that comes out of living well, even when it's hard, like living according to a code living accord to which, which, you know, I think religion used to structure this for people, but in its absence, you need some sort of replacement. But uh, even when things were soldiers get this a lot, right? The experience is a lot. Even when things were tough, I was able to persist in living in this way that I knew was right, even though it wasn't the easiest thing to do in the moment. Like fewer things give humans more resilience is like having done that, Your relationships were strong, right? Many people coming to your funeral is the standard, like a lot of people are gonna come to your funeral. Like, I mean, you matter to a lot of people and then maybe having done to, to the extent of whatever capabilities you are happen to be granted. You know, and they're different for different people and some people can sprint real fast and some people can do math problems trying to actually do something of impact. </s><s>[INST] I'll just promise to give gift cards, anybody shows up to the funeral, [/INST] you're going to hack it. I'm </s><s>[INST] gonna hack even the [/INST] Funeral, there's going to be a lottery wheel you spend when you come in and someone goes away with $10,000. </s><s>[INST] The see the problem is like with, with all the living by principles, living in principle, life focusing on relationships and kind of thinking of this life as this perfect thing. Kind of forgets the notion that none of it, you know, makes any sense. Right? Like the, like it kind of implies that this is like a video game and you want to get a high score as opposed to none of this even make sense. Like why would he like what that like, like what does it even mean to die? It's gonna be over. It's like everything I do all of these productivity hacks all this life, all these efforts, all these creative efforts kind of assuming it's going to go on forever. There's a kind of sense of immortality and I don't even know how to intellectually makes sense that it ends of course, got to ask you in that context, what do you think is the meaning of it all, Especially for computer scientists, I mean, you just got to be some mathematical [/INST] Uh, or what's the Douglas Adams? 22, is a better number. I should read more sci fi. Um, </s><s>[INST] You're on to something with the 20 [/INST] seven people want to give away </s><s>[INST] too much, but just [/INST] Trust me. 27 </s><s>[INST] invisible. Yeah. [/INST] Um, so I mean, I don't know, obviously. Right? I mean, I'm hoping, Yeah, I I don't know, but but going back to what you're saying about the sort of the existentialist or sort of the more nihilist style approach, the one thing that that there is our intimations, right? So there's these intimations that human have of somehow this feels right and this feels wrong, this feels good, this feels like I'm doing. I mean, aligned with something, you know, when I'm acting with courage to save whatever, right? It's not these intimations are grounding against arbitrariness. Like when the ideas are really interested in is that ah when you look at religion, right? So I'm interested in world religions. For for my my grandfather was uh like a theologian that studying to write all these books, I'm very interested in this type of stuff. And there's this great book that's it's it's not um specific to a particular religion, but as Karen Armstrong wrote this great book called The Case for God. She's very interesting. She was a catholic nun who sort of left that religion and is but one of the smartest thinkers in terms of like, accessible theological thinking, that's not tied to any particular religion. Her whole argument is that the way to understand religion, you first, we have to go way back pre enlightenment where all this was formed, we got messed up thinking about religion post enlightenment, right? And and um these were operating systems for making sense of intimations. The one thing we had all these different informations of this field like ah and mystical experience and this feels there's something you feel when you act in a certain way and don't act in this other way. And it was like the scientists who are trying to study and understand the model of the atom by just looking at experiment and try to understand what's going on like the great religions of the world were basically figuring out how do we make sense of these intimations and live in alignment with them and build a life of meaning around that? What were the tools they were using? They were using ritual, they were using belief, they were using action. But all of it was like an os it was like a liturgical model of the atom that it's hard to put it </s><s>[INST] in. So it did uh through the evolutionary process [/INST] of what they wanted, they would have called it that back then or Yeah, I mean whether they said they didn't have that is pre enlightenment, They just say this is here and and the directive is to try to live in alignment with that. </s><s>[INST] Well then I want to ask who wrote the original code. Yeah, So question. [/INST] So armstrong lays out this good argument and where it gets really interesting is that she emphasizes that all this was considered inevitable, right? So the whole notion and this is like rich and jewish tradition in particular and also an Islamic tradition we can't comprehend and understand what's going on here, right? And so the best we can do to approximate understanding live in alignment as we like act as if this is true. Do these rituals have these actions or whatever post enlightenment? A lot of that got once we learned about enlightenment, we grew these suspicions around religion that are very much of the modern era. Right? So like the the Karen armstrong, like uh Sam Harris's critique, religion makes no sense, right? The critiques based on, well this is you're making the ascent of propositions that you think are true for which you do not have evidence that they are true. So like that's an enlightenment thing, right? This is not the context and this is not the religion is the Rutherford model of the atom, like it's not actually maybe what is underneath happening, but this model explains why your chemical equations work. And so this is like the way religion was you you there is a god will call it this, this is how it works, We do this ritual, we act in this way, it aligns with it just like the model of the atom predicted why you know in A. And C. L. Is going to become salt. This predicts that you're going to feel and live in alignment, right? This beautiful sophisticated theory which actually matches how a lot of great theologians have you thought about it. Um but then when you come forward in time, yeah, maybe it's evolution. I mean, this is like what Peterson hints at, right? Like he's basically is not big. He doesn't like to get super pinned down on this, but I'm just kind of seems where </s><s>[INST] he was almost like searching for the words. [/INST] He focuses more like young and other people. But I mean, I know he's very union, but but that same type of analysis, I think roughly speaking like Armstrong is sort of a it's kind of like a peter Sony in analysis, but she's looking more at the deep history of religion than uh but yeah, he throws in an evolutionary </s><s>[INST] and I wonder what home it finds. I wonder what the new home is. If religion dissipates what the new home for these kinds of natural inclinations are. Uh yeah, well there's technology, whether [/INST] and if it's evolution, I mean, this is Francis Collins book also. He's like, well that's a religious, that could be a very religious notion. I don't think this stuff is interesting. Not a very religious person, but I'm I'm thinking it's not a bad idea. Maybe. Maybe what replaces honestly, like maybe what replaces religion is a return to religion, but in this sort of more sophisticated. I mean if you went back. Yeah, I mean, it's the issue with like a lot of the recent critiques, I think is it's a it's a straw man could critique in a complicated way, right? Because the whole way these the way this works. I mean, the theologians, if you're reading paul Tillich, if you're reading Heschel, if you're reading these people, they're they're thinking very sophisticatedly about religion in terms of this, it's ineffable and we're just these things and this is this deep, connects us to these things in a way that puts life in the line, man, we can't really explain what's going on because we, our brains can't handle it right. For the average person though, this notion of live as if it's kind of how religions work live as if this is true, it's like an os for getting in alignment with, because through a cultural evolution like you behave in this way, do these rich and live as if this is true, um, gives you the what the goal you're looking for. But that's a complicated thing live as if this is true, because if you, especially if you're not a theologian to say, uh, yeah, this is not true in an enlightenment sense, but I'm living as if it kind of takes the heat out of it. But of course it's what people are doing, because, you know, highly religious people still do bad things where if you really were no, there's absolutely a hell, and I'm definitely gonna go to it if I do this bad thing, you would never have, you know, no one would ever murder anyone if they were evangelical christian. Right? So, so it's like what? This is kind of a tangent that I'm I'm on shaky ground here, but it's something I've been interested off and on a lot </s><s>[INST] was as fast. I mean, I think we're in some sense searching for because it is, it does make for a good operating system. We're searching for a good live as if X is true and we're searching for a new X and maybe artificial intelligence will be the very, the new gods that were so desperately looking [/INST] For. Or it'll just spit out 42 </s><s>[INST] I thought it was 27. Yeah, that's as uh, as you know, I've been a huge fan. Uh, so are a huge number of people that I've spoken with, they telling me I absolutely have to talk to you. This is a huge honor. This was really fun. Thanks for wasting all this time with [/INST] me And I likewise, man, I've been a longtime fan. So this is a lot of fun. </s><s>[INST] Yeah, Thanks man. Thanks for listening to this conversation with CAL Newport's Thank you to our sponsors express VPN lin owed Lennox virtual machines, sun basket meal delivery service and simply safe home security, click the sponsor links to get a discount and to support this podcast and now let me leave you with some words from cal himself, clarity about what matters provides clarity about what does not thank you for listening and hope to see you next time [/INST] </s>

<s>[INST] well psychoanalyze those folks, but I, I really want to maybe lingering it a little bit longer of how you feel because it is such a, such a special moment in [/INST] your life. I really appreciate. It's a great question. So if we can pair off some of that other, those other issues, um, it's new being able to say what the observers is, which is my attempt to replace space time, that's something that is both closely related to spacetime and not spacetime. Um, so I used to carry the number 14 is a closely guarded secret in my life and Where 14 is really four dimensions of space and time Plus 10 extra dimensions of rulers and pro tractors or For the cool kids out there symmetric two Tensors. </s><s>[INST] So you had a geometric, complicated, beautiful geometric view of the world that you cared with you for a long time. Did you, did you have friends that you uh colleagues essentially no talked [/INST] no. In fact part of the, part of some of these stories are me coming out to my friends. Um and I used the phrase coming out because I think that gays have monopolized the concept of the closet, many of us are in closets having nothing to do with their sexual orientation. Um, yeah, I didn't really feel comfortable talking to almost anyone. So this was a closely guarded uh secret and I think that I lead on in some ways that I was up to something and probably, but it was it was a very weird life. I had to have a series of things that I pretended to care about so that I could use that as the stalking horse for what I really cared about. And to your point. Um, I never understood this whole thing about theories of everything. Like if you were going to go into something like theoretical physics, isn't that what you would normally pursue? Like wouldn't it be crazy to do something that difficult and that poorly paid if you were going to try to do something other than figure out what this is all about. </s><s>[INST] I have to reveal my cards on my sort of weaknesses and lack and an understanding of the music of physics and math departments, but there's an analogy here to artificial intelligence and often folks come in and say, okay, so there's a giant department working on quote unquote artificial intelligence, but why is nobody actually working on intelligence? Like you're all just building little toys, you're not actually trying to understand? And that breaks a lot of people. Uh they it confuses them because like, okay, so I'm at M I T I'm at stanford, I'm at Harvard, I'm here. I dreamed of being working on artificial intelligence. Why is everybody not actually working on intelligence? And I have the same kind of sense that that's what working on the theory of everything is. That's strangely you somehow become an outcast for even, but [/INST] we know why this is right. Why? Well, it's because let's take the artificial, let's let's play with a G I for example, I think that the idea starts off with nobody really knows how to work on that. And so if we don't know how to work on it, we choose instead to work on a program that is tangentially related to it. So we do a component of a program that is related to that big question because it felt like at least I can make progress there. And that wasn't where I was where I was in It's funny there was this book of called Freedom Hollenbeck and it had this weird mysterious line in the beginning of it. And I tried to get clarification of this weird mysterious line and everyone said wrong things and then I said, okay, well, so I can tell that nobody's thinking properly because I just asked the entire department and nobody has a correct interpretation of this. And so, you know, it's a little bit like you see a crime scene photo and you have a different idea, like there's a smoking gun and you figure that's actually a cigarette lighter, I don't really believe that. And then there's like a pack of cards and you think, oh that looks like the blunt instrument that the person was beaten with. You know, so you have a very different idea about how things go and very quickly you realize that there's no one thinking about that, </s><s>[INST] there's a few human size to this and technical size both of which I'd love to try to uh Get down to. So the human side, I can tell from my perspective, I think it was before April 1st April Fool's maybe the day before I forget. But I was laying in bed in the middle of the night and somehow it popped up, you know, uh my feed somewhere that your beautiful face is speaking live and I clicked and you know, it's kind of weird how the universe just brings things together in this kind of way and all of a sudden I realized that there's something big happening at this particular moment. It's strange like any on a day, like any day. Yeah. And all of a sudden you were thinking of, you had this somber tone like you were serious. Like you were going through some difficult decision and it seems strange. I almost thought you were maybe joking, but there was a serious decision being made and it was a wonderful experience to go through with you. I really appreciate [/INST] it was april </s>

<s>[INST] So you mentioned the human condition, speaking of which you happen to be a human being who is unfortunately not immortal, that seems to be a fundamental part of the human condition that this right ends. Do you think about the fact that you're going to die one day? Are you afraid of death? [/INST] Uh I would say that I am not as much afraid of death as I am of um degeneration. Uh and uh I say that in part for reasons of having, you know, seeing some tragic degenerative situations uh unfold. It's exciting when you can continue to participate and uh feel like you're you're near the the place where the the wave is breaking on the shore. I feel like, you know, um and and I I think about, you know, my own future potential. Um if I were to undergo a uh begin to suffer from dementia, uh Alzheimer's disease or semantic dementia or some other conditions, you know, I would sort of gradually lose the thread of that ability. And uh so so one can live on for several for a decade after, you know, sort of having to retire because one no longer has uh these kinds of abilities to engage. And uh I think that's the thing that I feared the most </s><s>[INST] the losing of that like that, that um the breaking of the way the flourishing of the mind where you have these ideas and they're swimming around, you're able to play with them, [/INST] you know, and and and and collaborate with other people who you know are themselves uh mm hmm. Um really helping to push these ideas forward. So yeah, </s><s>[INST] what about the edge of the cliff? The the end, I mean the mystery of it. I mean [/INST] the migrated sort of conception of mind and you know sort of continuous sort of way of thinking about most things. Makes it so that uh to me the the the discrete nous of that transition is less </s><s>[INST] less, less less [/INST] apparent than it seems to be to most people. </s><s>[INST] Yeah. Yeah, I wonder so. I don't know if you know the work of Ernest Becker and so on. I wonder what what role mortality and our ability to be cognizant of it anticipated and perhaps be afraid of it. What role that plays in in our well the reasoning of the world, [/INST] I think that it can be motivating to people to think they have a limited period left. Um I think in my own case, you know, it's like seven or eight years ago now that I was I was sitting around doing experiments on decision making that were um satisfying in a certain way because I could really get closure on what, whether the model fit the data perfectly or not. And I could see how one could test, you know, the predictions and monkeys as well as humans and really see what the neurons were doing. But I just realized, Hey, wait a minute, you know, I may only have about 10 or 15 years left here and I don't feel like I'm getting towards the answers to the really interesting questions while I'm doing this this particular level of work. And that's when I said to myself, okay, um, let's pick something. That's hard. You know, So that's when I started working on mathematical cognition. And um, I think it was more in terms of while I got 15 more years possibly of useful life left, let's imagine that it's only den, I'm actually getting close to the end of that now, Maybe three or four more years. Um, but I'm beginning to feel like, well I probably have another five after that. So okay, I'll give myself another another six or eight. </s><s>[INST] Um, but a deadline is looming and they're going to [/INST] go on forever. And so, um, so yeah, I got to keep thinking about the questions that I think are the interesting and important ones. For sure. </s><s>[INST] What do you hope your legacy is? You've done some incredible work in your life as a man as a scientist. When the aliens and the human civilization is long gone and the aliens are reading the encyclopedia about the human species. What do you hope is the paragraph written about you? [/INST] I would want it to sort of highlight um a couple of things that I was you know able to see um one path that was more exciting to me than the one that seemed already to be there for a cognitive psychologist, but not for any super special reason other than that I'd had the right context prior to that, but that I had gone ahead and followed that lead, you know, and then I forget the exact wording. But I said in this preface that the the joy of science is the moment in which you know, of partially formed thought in the mind of one person gets crystallized a little better in the discourse and becomes the foundation of some exciting concrete piece of actual scientific progress. And I feel like that, you know, moment happened when Rummelhardt and I were doing the interactive activation model and when Rummelhardt heard him and talk about gradient descent and um having the objective function to guide the learning process. And um it happened a lot in that period and I sort of seek that kind of thing in my collaborations with my students. Right? So um you know, the idea that this is a person who contributed to science by finding exciting collaborative opportunities to engage with other people through um is something that I certainly hope is part of the paragraph </s>

<s>[INST] So what does it mean that there is now more degrees of freedom as they become more integral? [/INST] Yeah. So </s><s>[INST] as the universe [/INST] expands, that's right. So there's more and more degrees of freedom. They're entangled, that are playing part playing the role of part of the entangled space time structure. So the basic, the underlying philosophy is that space time itself arises from the entanglement of some fundamental quantum degrees of freedom, </s><s>[INST] wow, okay, so at which point is most of the, the, the entanglement happening and we're talking about close to the Big Bang, are we talking about throughout the, the time of the [/INST] Yeah, so the idea is that at the Big Bang, almost all the degrees of freedom that the universe could have were there, but they were un entangled with anything else. And that's a reflection of the fact that the Big Bang had a low entropy was very simple, very small place. And as space expands more and more degrees of freedom become entangled with the rest of the world. </s><s>[INST] Well, I have to ask john carroll, what do you think of the thought experiment from Nicb Ostrom, that we're living in a simulation. So uh I think let me contextualize that a little bit more. I think people don't actually take this thought experiments, I think it's quite interesting, it's not very useful, but it's quite interesting from the perspective ai a lot of the learning that can be done usually happens in simulation, artificial examples. And so it's a constructive question to ask, how difficult is our real world to simulate right, which is kind of a dual part of for living in a simulation and somebody built that simulation. If you were to try to do it yourself, how hard would [/INST] it be. So obviously we could be living in a simulation. If you just want the physical possibility then I completely agree that it's physically possible. I don't think that we actually are so take this one piece of data into consideration. You know, we We live in a big universe. Okay. Um, there's two trillion Galaxies in our observable universe with 200 billion stars in each galaxy, et cetera. It would seem to be a waste of resources to have a universe that big going on just to do a simulation. So in other words, I want to be a good position. I want to ask under this hypothesis. What do I expect to see? So the first thing I would say is I wouldn't expect to see a universe that was that big. Okay. The second thing is I wouldn't expect the resolution of the universe to be as good as it is. So it's always possible that if they are superhuman simulators only have finite resources that they don't render the entire universe Right? That that the part that is out there that two trillion Galaxies isn't actually being simulated fully. Okay. But then the obvious extrapolation of that is that only I am being simulated fully Like the rest of you are just part non player characters. Right? I'm the only thing that is real. The rest of you are just chatbots beyond this wall. I see the wall but there is literally nothing on the other side of the wall that is sort of the basin prediction. That's what it would be like to do an efficient simulation of me. So like none of that seems quite realistic. There's that, I don't see, I hear the argument that it's just possible and easy to simulate lots of things. I don't see any evidence from what we know about our universe that we look like a simulated universe. Now. Maybe you can say, well, we don't know what it would look like, but that's just abandoning your position responsibilities. Like your, your job is to say under this theory here is what you would expect to see. </s><s>[INST] Yeah. So certainly if you think about simulation is a thing that's like a video game where only a small subset is being rendered. But say, uh, the entire, all the laws of physics at the entire closed system of the quote unquote universe. It had a [/INST] creator. It's always possible. Right? </s><s>[INST] So that's not useful to think about when you're thinking about physics the way Nicb Ostrom phrases it, if it's, if it's possible to simulate the universe, eventually we'll do it right. You can use that by the way for a lot of things. Well, yeah, but I guess the question is how hard is it to create a universe. [/INST] I wrote a little blog post about this and maybe maybe I'm missing something. But there's an argument that says not only that it might be possible to simulate a universe. But probably if you imagine that you actually attribute consciousness and agency to the little things that we're simulating to our little artificial beings. There's probably a lot more of them than there are ordinary organic beings in the universe or there will be in the future. Right? So there's an argument that not only is being a simulation possible, it's probable because in the space of all living consciousnesses, most of them are being simulated, right? Most of them are not at the top level. I think that argument must be wrong because it follows from that argument that, you know, if we are simulated, but we can also simulate other things well, but if we can simulate other things, they can simulate other things, right? If we give them enough power and resolution and ultimately will reach a bottom because the laws of physics in our universe have a bottom made of atoms and so forth. So there will be the cheapest possible simulations. And if you believe the original argument, you should conclude that we should be in the cheapest possible simulation because that's where most people are. But we don't look like that doesn't look at all like we're at the edge of resolution, you know, that were 16 bit, you know, things, but it seems much easier to make much lower level things that than we are. So. And also, I I questioned the whole approach to the anthropic principle that says, we are typical observers in the universe. I think that that's not actually, I think that there's a lot of selection that we can do that were typical within things we already know, but not typical within all the universe. </s>

<s>[INST] I thought it's like 12 rounds, right? Isen't this the thing in, in, in Russia? [/INST] It's a big thing in the UK UK UK. I don't, I don't know why. And there's a lot of Youtuber events just for boxing. So youtubers just learn to box and then they just box no chest. They just straight up box each other. Like jake paul for example. You ever gonna get jake paul in here? Yeah, </s><s>[INST] I'm sure. Okay. [/INST] I feel like so many different guests have been mentioned. Uh, jake jake paul would be would be a fun guess, but he's obviously the biggest scale. He's legitimately boxing people, he's not, but chess players never gonna learn to box to that level. And all of us are starting basically from zero and Lord would talk to me behind the scenes say, hey, how would you feel about being in a chess boxing match? I said, okay. Yeah, maybe when is it gonna be? He said five months from now. I've always wanted to train combat. I've weight lifted. I've done cardio. Yeah, but </s><s>[INST] do you admire [/INST] fighting? Yeah, I would enjoy it. I just have a really bad lower back and that makes a lot of different combat difficult. But I said, you know what screw this. I'm going to contact a few local gyms and one of them, the guy emailing me back and forth, had actually watched my Youtube videos. So he was the first to respond and he said, yeah, like come in, do a couple classes, like see how you feel. So first I did conditioning, which killed me because fighting conditioning as you know, it kills you. It's, it's a completely different type of conditioning, but I felt good and I really wanted to come back and since july, I've been training 34 days a week, </s><s>[INST] pretty good. [/INST] I love it feels good. Everything the whole body got stronger. So </s><s>[INST] what you're saying is you're going to, [/INST] is </s><s>[INST] he training, [/INST] I'm not fighting. So I talked to eric about it and the truth is we're both concerned about head trauma. I haven't actually sparred. I like sparring shadowboxing, but I go there, I do personal training, I don't do a group class, I'm not fighting, I'm fighting the bag, I'm doing shadowboxing, my form is improving but I haven't been punched, I got hit in the stomach, you know, I get hit in the side with kicks, nobody's punched me in the face yet, so I think we both were adequately concerned about that and there was not some ridiculous amount of money on the table, so we decided it's just not worth pursuing, how </s><s>[INST] does come into the picture [/INST] because he's </s><s>[INST] a possible competitor. [/INST] People ask me all the time, who would you fight, Would you? People are like, oh Andrea Benitez would kick your ass, that's a tough one, because I can't, what am I gonna say? I'm gonna fight a woman who I'm larger than and you know, so I just have to take the l against any time a woman is mentioned, that's why I'm like </s><s>[INST] that one. [/INST] Right, Exactly, so I've lost both both tests is anna Rudolph and a crumbling. They're all chest creators </s><s>[INST] like hypothetically, [/INST] yeah, I get </s><s>[INST] a hypothetical fight. Yeah, [/INST] um that's been </s><s>[INST] training I think Andrea has been training, that's [/INST] because the event got announced this this event that I was hypothetically going to be the main event against eric Rosen </s><s>[INST] Yeah, it was announced and then you kind of like thought like maybe let's not do this, [/INST] No, I knew once I declined to fight eric that I would not be participating and I even knew, you know, I knew who was going to be the main event um because I was kind of offered both of those guys, so I'm on Hambleton is </s><s>[INST] still going on, [/INST] the chess boxing event will happen in december in Los Angeles. Yeah, </s><s>[INST] so who is the main event? [/INST] It's Amman Hambleton who's also Chesbro. So </s><s>[INST] they have a couple [/INST] of guys this part of the channel and Lawrence Trent. Lawrence Trent is a international master from England. He's a, I think he's done some boxing a little bit. He's a commentator, brash guy, controversial guy. Yeah. Uh it's funny because they started Lawrence put out some videos and I went, damn, I should have done this. Yeah, </s><s>[INST] I think, but I mean, you're right, first of all, there's so many things to say, One of which [/INST] is if </s><s>[INST] you're, if you want to take it seriously, you know, it does pull you in, like, you know, if you train a lot, it's gonna affect the rest of your life and then, and then there's, it changes you, I think taking combat sports seriously changes you in good and there's negative cost to it, I think because it's a whole nother thing, man, it's like uh it's like doing a marathon running or something, it really pulls you in and the other thing is the, is the head trauma like yeah, you have to take that kind of stuff seriously, especially if you're doing sparring and all that kind of stuff. Um still some of the celebrities, I don't know why, but it's pretty exciting, right? I don't know why it would be fun to watch a car, like there's something I [/INST] always said if Hikaru and Magnus did a boxing event and I was the co main event against, I don't know who that would, that'd be, that'd be </s><s>[INST] as Magnus said anything about it, like about doing chest box. [/INST] Uh well, first of all, he's gonna commentate the Ludwig event, which he which he said he he kind of said, oh, there's been people in the past that are my level in chess, not my his level in chess and have wanted to get physical with him. I think he's talking about Hikaru, it's it's, I don't think anybody else is. That'd be that'd be a good one, man. That'd be a good one. I think Magnus, I think Magnus is in better physical shape. He's also a little bit bigger I think than Hikaru. </s>

<s>[INST] So speaking of egalitarian, last time we talked four years ago, it was just after you step down from your role as the benevolent dictator for life Be DFL, Looking back, what are your insights and lessons you learn from that experience about python developer community, about human nature, about human civilization, life itself. Oh [/INST] my uh I probably held onto the position too long. I remember being just extremely stressed for a long time and it wasn't very clear to me what was leading what was causing the stress. And looking back, I I should have sort of relinquished my central role as B. D. F. L. Sooner. What </s><s>[INST] were the pros and cons of the B. D. F. L. Role? Like, what were the you're not relinquishing it? What are the benefits of that for the community and what are the drawbacks? [/INST] Well, the benefits for the community would be things like uh clarity of vision and sort of a clear direction because I I had certain ideas in mind when I created python and well, I sort of let myself be influenced by many other ideas as python evolved and became more successful and more complex and more used. I also stuck to certain principles and it's still hard to say what our python's core principles, but the fact that I was playing that role and sort of always very active group community in a certain way. It modeled to the community how to think about how to how to solve a certain problem. Well, </s><s>[INST] that was a source of stress, but it was also beneficial. [/INST] It was a source of stress for me personally, but it was beneficial for the community because uh people, people sort of over time had learned how I was thinking and could predict, but how how, how would would decide about a particular issue and not always perfectly of course. But there was like, there wasn't a lot of jerking around like this year were all this year, the democrats are in power and we're doing these kind of things. And now the republicans are in power and they roll all that back and do those kind of things. There is a clear, fairly straight path </s><s>[INST] ahead. [/INST] And so, fortunately, the the successor structure with the steering council </s><s>[INST] has [/INST] has sort of found a similar way of of leading the community in a fairly steady direction without stagnating. And and for me personally, it's more fun because there are there are things I can just ignore. Yeah. Yeah. There's a bug in multi processing. Let someone else decide whether that's important to solve or not. I'll stick to typing in </s><s>[INST] the [/INST] and the faster interpreter. </s><s>[INST] Yeah. It allows you to focus a little bit more uh what our interesting differences in culture, if you can comment on between google, dropbox and Microsoft. From a python programming perspective, all places you've been to the [/INST] positive. </s><s>[INST] Is there a difference or is it just about people and there's great people everywhere or is their culture differences [/INST] sort of Dropbox is much smaller than the other two in your list. So that's that is a big difference. The </s><s>[INST] set of products they provide is is narrower, so they're more focused. [/INST] Yeah. And and Dropbox sort of at least during the time I was there had the tendency of sort of making a big plan, putting the whole company behind that plan for a year and then evaluate and then suddenly find that everything was wrong about the plan and then they had to do something completely different. So there were there was </s><s>[INST] like the [/INST] annual Engineering reorg was was sort of an unpleasant tradition at Dropbox because like there's a new VP of Engineering and so now all the directors are being reshuffled </s><s>[INST] and this [/INST] Guy was in charge of Infrastructure one year and the next year he was made in charge of, I don't know, product development. </s><s>[INST] It's fascinating because like, you don't think about these companies internally, but I, you know, Dropbox to me from the very beginning was one of my favorite uh services. There's certain like programs and online services that make me happy make me more efficient and all that kind of stuff. But one of the powers of those kinds of services, they disappear, that you're not supposed to think about how it all works. But it's incredible to me that you can think stuff effortlessly across so many machines so quickly and like don't have to worry about conflicts, they take care of, you know, as a person that comes from version of repositories and all that kind of stuff or emerge is super difficult. And uh just keeping different versions, different files is very tricky. The fact that they could take care of that just, I don't know, the the engineering behind the scenes must be super difficult, both on the computer infrastructure and the software, a [/INST] lot of internal sort of hand wringing about things like that. But the, the product itself always worked very smoothly. </s><s>[INST] Yeah. But there's probably a lot of lessons to that. You can have a lot of turmoil inside on the engineering side. But if the product is good, the product is good and don't maybe don't mess with that either, you know, when it's good, keep it's like with google focus on the search and ads, right? Yeah. And make sure that's done extremely well and don't forget what you do extremely well in what ways do you provide value and happiness to the world, make sure you do that well. Um, is there something else to say about google and Microsoft? Microsoft has had a very fascinating shift recently with a new Ceo uh, with, you know, recent ceo with purchasing, get hub, embracing open source culture, embracing the developer culture is pretty interesting to see. [/INST] That's like why I joined Microsoft. I mean after retiring and thinking that I would stay retired for the rest of my life, which of </s>

<s>[INST] Mhm. So let me ask how hard do you think is two D. Image understanding? So if we can kind of into it handwritten recognition, how big of a step leap journey is it from that if I gave you good if I solved your challenge for handwriting recognition, how long would my journey than be from that to understanding more general natural images. [/INST] Immediately. You will understand this as soon as you will make a record because it is not for free. As soon as you will create several invariants. This will help you to get the same performance. That's the best narrow net did Using hundreds and maybe more than 100 times less examples. You have to have something smart </s><s>[INST] to do that. And you're saying that [/INST] that doesn't worry, it is predicated because you should put some idea you have to do that. </s><s>[INST] But okay, let me just pause. Maybe it's a trivial point. Maybe not. But handwritten recognition feels like a two D two dimensional problem. And it seems like how much complicated is the fact that most images are projection of a three dimensional world onto too deep plane. It feels like for a three dimensional world was we need to start understanding common sense in order to understand an image. It's no longer visual shape and symmetry. It's having to start to understand concepts of understand life. [/INST] You're you're you're talking that there are different in various different indicates. </s><s>[INST] Yeah. And potentially much larger number, [/INST] you know, maybe. But let's start from simple. </s><s>[INST] Yeah. But you said [/INST] that, you know, I cannot think about things which I don't understand this. I understand, but I'm sure that I don't understand everything there. Yeah, I can stay in say do as simple as possible, but not simpler. And that is exact case </s><s>[INST] with handwritten, handwritten. Yeah. But never that's the difference between you and I I uh I welcome and enjoy thinking about things that completely don't understand because to me it's a natural extension without having solved handwritten recognition to wander how, um, how difficult is the the next step of understanding two D, three D images because ultimately, while the signs of intelligence is fascinating, it's also fascinating to see how that maps to the engineering of intelligence and recognizing handwritten digits is not doesn't help you. It might, it may not help you with the problem of general intelligence. We don't know you a little bit. I [/INST] don't know. It's unclear. It's unclear. Yeah, but I would like to make a remark. I started not from very primitive problem like uh challenge problem, I started this very general problem this plateau. So you understand and it comes from plateau to digit recognition. So </s><s>[INST] you basically took Plato and the world of forms and ideas and mapped and projected into the clearest simplest formulation of that big world. [/INST] You know, I would say that I did not understand Plata until recently and until I consider weak convergence and then predicate and they know this is what bloody told. </s><s>[INST] Yeah. So you linger on that like why? How do you think about this world of ideas and world of things in plato? [/INST] No, it is metaphor. It's </s><s>[INST] a metaphor for sure, compelling. It's a poetic and beautiful but what can you [/INST] But it is a way of you, you should try to understand how attack idea since the world. So, from my point of view, it is very clear, but it is lying all the time. People looking for that say plateaus and Hagel, whatever reasonable it exists, whatever existed as reasonable. I don't know what you have in mind reasonable. </s><s>[INST] Right? This philosopher's again, no, no, no, [/INST] no, no, no, no. It is, it is next stop of Wagner that what you might understand something of reality, it is the same plot, a line and then it comes suddenly. Vladimir Propp Look 31 Ideas. 31 units and describes everything. </s><s>[INST] There's abstractions, ideas that represent our world and we should always try to reach into that. [/INST] Yeah, but what you should make a projection on reality. But understanding because it is abstracted years, you have in your mind several abstracted years which you can apply to reality </s><s>[INST] and reality in this case, if you look at machine learning, is data data data. Okay, let me let me put this on you because I'm an emotional creature. I'm not a mathematical creature like you. I find compelling. The idea forget the space the sea of functions. There's also a sea of data in the world and I find compelling that there might be like you said teacher, small examples of data that are most useful for discovering good, whether it's predicates or good functions at the selection of data. Maybe a powerful journey, a useful mechanism, you know, coming up with a mechanism for selecting good data might be useful to do you find this idea of finding the right dataset interesting at all. Or do you kind of take the data set as a given. [/INST] I think that it is, you know, my scheme is very simple. You have huge set of functions if you will apply and you have not too many data. If you pick up function which describes this data, you will do not very well </s><s>[INST] randomly. [/INST] Yeah, yeah, it will be over feeding. So you should decreased set of function from which year picking up one so you should go some have to admissible set of functions. This what about the conversions? So but from another point of view to make admissible set of function, you know, just added you just function material take an inner product which you will measure property of your function and that is how it works. </s><s>[INST] So I get it. I get to understand it. But do you the reality is [/INST] let's discuss let's think about examples. You have huge set of functions. You have several examples if you just trying to keep take function which satisfies these examples you still do over feet. You need decreases, you need admissible set of </s>

<s>[INST] Let me ask you a question about hubert Bert Dreyfus. He is a friend, colleague and mentor of yours. Unfortunately no longer with us. You wrote with him the book titled All Things shining, Reading the Western classics to find meaning in a secular age first. Can you maybe speak about who that man was, What you learned from him and then we can maybe ask, how do we find through the classics meaning in a secular age. Okay, [/INST] so Bert Dreyfus was uh very important philosopher Of the late 20th, early 21st century. He, he died in um 2017, about a little over four years ago. Uh he was my teacher, I met him in 1989 when I went away to graduate school in Berkeley. That's where he taught. He plays in an interesting and important role in the history of philosophy in America because uh in a period when most philosophers in America, uh and in the english speaking world, we're not taking seriously 20th century french and german philosophy he was and he was really probably the most important english speaking interpreter of Heidegger, the german philosopher that we're talking about, we've been talking about. He, it was an incredible teacher. A lot of his influence came through his teaching and one of the amazing things about him as a teacher was his um sort of mix of intellectual humility With sort of deep, insightful authority and he would stand up in front of a class of 300 students, you taught huge classes because people love to go see him and I taught for him for many years and say, you know, I've been reading this text for 40 years, but the question you asked is one I've never asked and it would be true. Like he would, he would, he would find in what people said things that were surprising and new to him and </s><s>[INST] that's humility actually, [/INST] that is </s><s>[INST] listening to the world. [/INST] Absolutely, absolutely. He was always ready to be surprised buy something that someone said and this is something astonishing about that. So his influence was, you know, for people who didn't know him through his interpretations of these texts, he wrote about a huge range of stuff, but for people who didn't know him, it was through his presence, it was through the way he carried himself in his life. And uh so in any case that that's who he was. We we I graduated after many years as a graduate student, I didn't start in philosophy. I started in Math, math and computer science actually. And then I did a lot of work in computational neuroscience for a few years, </s><s>[INST] which a fascinating journey. We'll get to it through our friendly conversation about artificial intelligence, I'm [/INST] sure </s><s>[INST] because you're you're basically fascinated with philosophy of mind, of the human mind, but rooted in a curiosity of mind through the it's artificial, through the engineering of mind. [/INST] Yeah, yeah, that's right, sober, sober. I mean, the reason I was attracted to him actually is because of his, to begin with was because of his criticisms of what was called traditional symbolic ai in the seventies and eighties. So I came to Berkeley as a graduate student who had done a lot of math and a lot of computer science, a lot of computational neuroscience. I noticed that you had you interview a lot of a lot of people in this world. And I had a teacher at Brown as an undergraduate, Jim Anderson who wrote with Geoff Hinton a big book on neural networks. Um so I had I was interested in that not so interested in traditional ai like sort of lisp programming things that went on in the eighties, because it felt sort of, you know, when you made a system do something all of a sudden it was an under an interesting thing to have done the fact that you solve the problem that made it clear that the problem wasn't an interesting one to solve. And I had that experience and and Burt had criticisms of um symbolic ai what he called, good old fashioned day, I go fi and um and I was attracted to those criticisms because it felt to me that there was something lacking in in in that project and I think that I didn't know what it was, I just felt its absence. And uh then I learned that all his arguments came from his reading of this phenomenal logical and existential tradition. And so I had to try to figure out what those folks were saying. And it was a long road, let me tell you, it took me a long time, but it was because of birth, that I was able to do that. So I own that that huge debt of gratitude. And eventually we went on to write a book together, which was a great experience. And yes, we published all things shining in 2011 and that was that's a book that I definitely would not have had the chutzpah to try to write if it weren't for Bert, because it was really about, you know, great literature in the history of the west, From homer and Virgil and Dante to Melville. There's a huge chapter on Melville, a big chapter on David Foster Wallace who didn't care about at all. But I was fascinated by and so learning to think that way while writing that book with him uh was an amazing experience. </s><s>[INST] So I have to admit is one of my feelings in life, one of many failings is I've never gotten through Moby Dick or or any of Melville's works. So maybe can you comment on before we talk about David David Foster Wallace, who I have gotten through um what are some of the sources of meaning in these classics? [/INST] Good, So Moby Dick, I think is the other great novel of the 19th century. So the Brothers Karamazov in Moby Dick and and they're diametrically opposed, which is one of the really interesting things. So that the Brothers Karamazov is kind of intense, It's a kind of existential interpretation of Russian orthodox Christianity. How do you live that way and find joy in your existence Moby Dick is not at all about Christianity. It's about it sort of starts with the observation that that that the form of Christianity that uh that Ishmael is familiar with is is broken, it's not gonna it's not gonna work in his, living his life, he has to leave it, he has to go to sea in order to find what needs to happen. And </s>

<s>[INST] because that's actually what I love to do the best. Yeah, I mean, it's like views aside, those are just works of genius and you're getting better and better at them. And like, that's the, that, in terms of the beautiful things you can create in this world, those are that. So like, if you continue, especially where the way space travels developing, that your voice is very much needed. So I think it's wise to do what you do best. [/INST] And I think I'm feeling more and more, especially this last year, I did a lot of like live streaming and traveling back and forth between Florida and California and here and just handling major like big live streams, really stressed myself out. And at the end of the day, I was like, all of this is taking away from my ability to make videos. And that's ideally, honestly, if I like had my choice of things, I would just ignore everything else and just sit and lock myself in my house for a year and just sit there and make videos and go and travel every other month, for fun, like not for space stuff, </s><s>[INST] just go and do some light traveling, for fun. [/INST] Like around the moon or what? </s><s>[INST] Yeah, just some light traveling. What advice would you give to young folks or just folks struggling to find their way in life, whether they're in high school, college, or beyond, like how to have a life that can be proud of, how to have a career that can be proud of? You've had a really interesting journey yourself. What from that can you draw? [/INST] Give good advice to others, give good advice to others. To be honest, like I feel like it's so painfully obvious to follow your heart and follow like what makes you happy that I'm just shocked that people allow themselves to sit on like mediocrity, you know, like to just sit there and be like, well, this is just what I do. You know, and something, for a lot of people, that's perfectly fine. Like I have, you know, some of my best friends are clocking in and out and they're perfectly happy. They have a wonderful life. Absolutely no judgment there, of course. But for people that are stuck feeling like they're not sure of, you know, what's next and how to bring light into their world, you really just got to listen to like, what does make you happy? You know, people feel guilty about, oh, I play video games for eight hours. Then start learning how to make a video game, learn how to do reviews of video games, or make, there's so many, you can work in the video game industry. You know, you don't have to isolate your love from your work, you know? And it's just funny that, we, you know, maybe you feel guilty that you drink too much. Okay, I don't know if there's a good advice. Go learn how to make alcohol, you know? Be at Start A Liquor Company. Yeah, Start A Liquor Company, </s><s>[INST] I mean, make it that terrible. Start A Liquor Company. Yeah. It's great advice. But it's also in your own story, it seems like you've almost stumbled on, Like, some of it is just exploration and keeping your mind and heart open to discovering that thing that grabs you, right? [/INST] It's not- </s><s>[INST] What do you fall asleep thinking about? You know, like- But you stumbled on the space almost accidentally, right? I mean- Yeah, yeah. Like, would you, when you were doing a, being a professional photographer, would you have known? [/INST] Oh no, yeah, yeah. Well, do you wanna know what I wanted to be when I was a kid? What's that? Well, first, when I was young, I wanted to be a tractor. I'm not quite sure I understood. Yeah. Oh, that works. That worked. Then I wanted to be a scorpion trainer. Yeah. Thought I could train him to cut people's lawns. Better and better. Yep, yep. And then, honestly, the majority of my childhood- </s><s>[INST] People's lawns, God. I think your understanding of physics early on was just a little- [/INST] The pinchers, man. The pinchers, man. Pinchers. Straight off. Then, from, like, probably six until, like, early college, I wanted to be a prosthetic engineer. And never once did I think about anything rockets, really. You know, I had, like, a space shuttle poster. I had some space shuttle Legos. You know, I liked space and, you know, I knew of the space shuttle, but, you know, it was far down the list as far as things that I thought were cool. Ninja Turtles, Lamborghini Countach, B-17G Flying Fortress. </s><s>[INST] Yeah, I guess that means- If you just keep your heart open to falling in love with an idea, with a passion, yeah. You could start from that, from Ninja Turtles and Scorpions going on to being one of the best, one of the top educators, inspirational figures in space, and actually traveling around the moon. And who knows, maybe one day stepping foot on the moon and Mars, even though you say you're not interested. It seems like you stating that you're not interested [/INST] in certain things somehow results in you doing those things. In me. In you doing those things. My friends joke that, like, I'm gonna be the first person to go to the moon against their will. Like, oh, yeah. </s><s>[INST] Like, oh, all right. [/INST] What's the food? Like, guys, I'm gonna start a fundraiser. Please, like, Tim just doesn't gonna go, </s>

<s>[INST] Got it. And you're getting information about IEDs. [/INST] You're getting a lay of the land as to what's been going on in the country for the past six months. </s><s>[INST] And you know nothing. You're just like, this is your first time you're getting deployed. So what was your deployment like? Can you tell the story of your deployment to Afghanistan? [/INST] Like the whole deployment? Getting like actual deploying, not the deployment itself. </s><s>[INST] What's the difference between the two? [/INST] Well, actually getting ready to deploy is a little different. </s><s>[INST] So I mean, the emotional build up to it. Got it. And some of the memorable things that kind of you remember from that experience, both on the excitement. I get to see battle. I get to be part of this and the fear and also like being surprised, like with the Tim Hortons and all those kinds of things. So like the lead up before everything went shit. [/INST] So like the lead up before everything shit hit the fan kick hole. So.. </s><s>[INST] You're such a fascinating person. But yes, something like that. I think called many things. Yeah. That start with the letter F. Yeah. No, I don't know. I don't know many words with F. [/INST] OK. So the buildup, so the deployment something like that. I think called the yeah. Fascinating to start with the letter F. Yeah. So so for the buildup for the deployment, I was in Quebec and my unit was deploying from Quebec And at that time, you kind of get your marching orders, you know you're deploying. I knew I was deploying before I even graduated. That's how much they needed people. So once I did all that training, on graduation parade day, a couple men from Quebec in uniforms came over and said, you, you, you, and you are all being posted at Bacciazzi, and you're gonna deploy with us in April. </s><s>[INST] So that's how I found it, I was deploying. Why was there such a need for troops in Afghanistan? That was a well-known thing, [/INST] that there's a scaling up of troops. 2007 on, Canada really started taking a combat role. Before it was very much more a UN type deal, where doing what we normally do in most wars, where we just, we wear blue and we don't shoot anyone. And so we're there to help. And so they were really, they were scaling up. And there wasn't a lot of people in those trades, initially, I think when the war kind of started. So Canada really started to scale. And so when I got to Quebec, we've kind of found, oh yeah, we're deploying. And it was a weird situation because I've never actually been at a unit on a non-deployable unit. So I don't know what they do day to day. That's different from what I did. I just know what I did. So we would do things like in the morning, we would get up and we would meet for PT at 5 a.m. And that would include going for a 10K run or playing ball hockey for a few hours in the gym or lifting weights together, or just going on a rock march, a long rock march. Just stuff like that. You would have a shower, you would meet, and then you would just sit around the regiment. You would just sit around the regiment. And you would, if there was busy work, you'd mop the floors, you would clean weapons. There wasn't a whole lot until there was a whole lot to do. We did a lot for a while. And then we went away on workup training to Texas for a week. We came down here and we did live fire with our other troop that was gonna be with us. So Alpha had two guns and two guns has two groups of people. And so we all would go down to Texas and we did live fire here for a week. And I ended up getting gastro, which was awesome. So thanks for that. From? Oh, apparently there were having water problems and sanitary problems, so everyone was getting it on the base. From, okay, so it just makes your life way harder. I didn't get it towards the end, till towards the end. So that was fortunate. So we would fire live fire. We would go out to the middle of nowhere. The guns would be there and we would get, offload a truck of rounds and we would do live fire and we would just practice. Just constant practice. What's that saying? </s><s>[INST] Perfect practice makes perfect. Yeah, so this is a sensory, like a shooting range for. Artillery. For artillery. For long range. So what does practice look like? [/INST] So you're gonna have to like for long range. So you roll up in your trucks, you've got each group of people, you've got two trucks and then you've got like a medik vehicle and then you've got like an officer vehicle and a comms vehicle. And you go to your prospective guns and then you offload your ammo and then you basically wait for them to send you like a fire mission. Wow, get that together. They would call them and miss you and sit. So it'd be a fire mission. So we'd wait for that. And once we got that then you all run like a bunch of scattered rats to the gun like it's like the greatest thing you've ever seen. And then you just wait you wait for the call for the search to say And then you'll hear it, cause it's not headphones, you can hear it on a speaker and it'd be like, I'm not going to do it French, don't ask. It'd be like so and so, 10 rounds, fire when ready. And then you would get your rounds ready and everyone would have them ready, it would be in their respective, respective positions. And then you would wait. And then they would say fire when ready. And as soon as they say fire when ready, that means just start going, just start. </s>

<s>[INST] Austin. Thanks, thanks for listening to this conversation with Scott Aaronson and thank you to our sponsors eight Sleep, simply safe express VPN and better help please check out these sponsors in the description to get a discount and to support this podcast. If you enjoy this thing, subscribe my Youtube, review it with five stars on Apple podcast, follow on Spotify, support on Patreon or connect with me on twitter Elex Friedman and now let me leave you with some words from Scott Aaronson that I also gave to you in the introduction, which is if you always win, then you're probably doing something wrong. Thank you for listening and for putting up with intro and outro in this strange room in the middle of nowhere, in this very strange chaos of a time we're all in and I very much hope to see you next time In many more ways than one. [/INST] </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] What about what's your take on unity 2020, that Britain Weinstein uh pushed forward, [/INST] it was D. O. A. Uh he couldn't even stand up to Twitter and on arrival on arrival he couldn't even stand up to Twitter let alone or to Facebook they got blocked let alone two </s><s>[INST] hugely problematic by the way that twitter would block that. [/INST] Not at all. Um I don't know why they blocked it, but I believe I don't know problematic means that's the word, that there's a lot of work that people wanted to do conceptually um the idea that like Unity is like taking the rejects from each party and we're gonna like have something that no one likes and therefore it's going to compromise is absurd. The last time we had this kind of Unity ticket was the Civil war when you had Andrew johnson from the democrats and Lincoln from the republicans. This was not something that ended well, particularly nicely for both halves of the country. </s><s>[INST] So that that's the way you see it as like the way I saw, I guess I haven't looked carefully [/INST] at it. I haven't either, to be fair. Yeah, </s><s>[INST] the way I saw it as emphasizing centrists, which is [/INST] House Tulsi, a centrist </s><s>[INST] Tulsa was involved. Yes, [/INST] he's trying to Tulsa and like jesse ventura or something. </s><s>[INST] So, okay, I don't know. I don't know the [/INST] specific as a scientist. You also know, centrism is not a coherent term in </s><s>[INST] politics. But I see now you're like, uh, what is it pleading to authority? Not [/INST] leading my ego. No, no, I'm pleading to how you approach data. If someone is saying the mean is accurate, that only means, I mean, the mean could be anywhere. It's a function of what's around It doesn't mean. It's true, </s><s>[INST] I don't even know what centrist is supposed to mean, but what it means to me, there's no idea a sense, centrist, there's more of a center right or center left. To me, what that means is somebody who is um a liberal or conservative, but is um open minded and empathetic to the other side, [/INST] joe biden had the crime Bill joe biden voted for Republican Supreme Court justices, joe biden voted for a balanced budget. Joe biden voted for Jeb Bush's war and I'm sure probably I've been looking stuff. The patriot act job. If you want a centrist, you have joe biden. </s><s>[INST] Yeah, he's worked very well with the Republican argument could be made. Of course they'll everybody will always resist [/INST] that argument. It's undeniable. In fact, during the campaign, some um, uh, activists started yelling at him at a town hall, not yelling, just saying, hey, we need open borders, joe biden says, I'm not for open borders, go vote for trump and literally turned his back on the man. And this is during the primaries where it would behoove you to try to appeal to the base. </s><s>[INST] And of course you can probably also make the argument that donald trump is center right, if not center left. [/INST] Well, I mean, he's very, uh, unique as a personality, but if you look at his record and his first name is rhetoric, you can say it's not centrist at all. But in terms of how he governs the budgeting, I mean, has been very moderate. It certainly hasn't been like draconian budget cuts. Uh, the Supreme Court, you could say, okay, he's hard right, immigration, you could say in certain capacities, his hard right. But in terms of pro life, what has he done there in terms of, you know, so it's in many other aspects he's been very much this kind of meat to Republican, but certainly the rhetoric, it's very hard to make the case that he's a centrist. </s><s>[INST] So, you don't like, uh, is there any other idea you find compelling? Like what I like about you and G 2020, is this an idea for a different way for like a different party, a different path forward? So ideas just like anarchy is an interesting idea that that leads to discourse at least. [/INST] I don't think it's interesting at all. And here's why I think it's interesting. Sweden has eight parties in its parliament, Iceland populations like 150,000. They've got nine, I think it was Czech Republic has nine Britain has five. Um, so the claim that two parties is the censorious of speech, but three oh, now, all of a sudden it makes no sense. Doesn't point to the data. Number one. Number two is donald trump demonstrated that you can be basically a third party candidate, sees the machinery of existing party and appropriate to your own hands as Bernie Sanders, almost that Bernie Sanders has never been a democrat. Uh, major credit to him for that's not easy to be elected as senator as an independent. He's done it repeatedly. So, these are two examples of Ossified elites, right? For the picking. So to have a third party makes uh, no real sense. </s><s>[INST] Speaking of which party you talk about quite a bit. Uh, let's like, this is a personal challenge to you. Let me bring up the libertarian party and the personal challenge is to go five minutes without mocking them. Okay, in discussing and discussing this idea. So, first of all, what [/INST] I'm being trolled the troll. Okay, I'm controlled. </s><s>[INST] I'm [/INST] controlled. Okay. Remember the fun friends? There was an episode where Chandler had to not make fun of people like, can you go one day Chandler and Phoebe starts telling him about like this Ufo she saw, and he's like, that's very interesting. Nice </s><s>[INST] for you. This is exactly that. So, a true master would be able to play within the game within the constraints. So, um, no, I'm pretty sure you'll still mock them. But no, [/INST] No, I'll stick to the rules five minutes. </s>

<s>[INST] So he talked about this like most of the time rivals just like avoiding violence and hating each other in peace. So this is this what piece just answer? My question is what peace looks like. [/INST] Not always, but I mean it's it's what it's kind of my worry to go back to like the Russia Ukraine example. Like I kind of it's really hard, it's going to be really hard to find an agreement that both sides can feel they can honor, that they can be explicit about that they'll hold to, that will enable them to move on. </s><s>[INST] Yeah, it feels like a first step in a long journey towards greatness for both nations and a peaceful time flourishing, that kind of thing. [/INST] I mean, you can think of like what the what's going on in, in Israel Palestine, there's a stalemate. Both, both of them are exhausted from the violence that has occurred. Neither one of them is quite willing to for various reasons, to create this sort of stable agreement. There's a lot of really difficult issues to resolve and um and maybe the sad thing, maybe we'll end up in the same situation with Russia Ukraine. This is this is where, you know, if every if they stop fighting one another, but Russia holds the east of the country and Crimea and nobody really acknowledges their right to that, That that might within they're just gonna be a lot of tension and skirmishing and violence, but that never really progresses the war for 30 years, that would be a sad but maybe possible outcome. Um so that's kind of where Israel Palestine looks to me and so someone, if we're going to talk about why we fight, then the question we have to ask is like why? You know, like the second intifada, like that was the most violent episode, like why did that happen and why did that and why did that last several years? That would be like, we could analyze that and we could say what was it about these periods of violence that led there to be prolonged, intense violence because there was nobody's interest that didn't need to happen. And part, I don't talk about that in the book. I wanted to avoid really contemporary conflicts for two reasons. One is i things can change really quickly. I didn't want the book to be dated. I wanted this to be a book that had like longevity and That that would be relevant still in 10 years or 20 years maybe before someone writes a better one or before </s><s>[INST] the human civilization. And [/INST] exactly, and circumstances can change really quickly. So I wanted it to be enduring. And meant partly just avoiding changing things and changing these and and avoiding these controversial ones, but of course I think about them. And so, like a lot of my time I decided actually last year to teach a class where I take all these contemporary conflicts that wasn't working on the book and when I wasn't really an expert whether it's India Pakistan china Taiwan, Israel, Palestine, mexican cartel state, drug wars um and a few others and then teach a class on them with students. And we'd work through it will read the book and then we'd say all right, none of us are experts. How do we make sense of these places? And we focused on the Israel Palestine case of mostly trying to understand why it got so violent and spend a little bit of time on what the prospects are for something that's more enduring, </s><s>[INST] hard to know that stuff now, I mean, it's easier to do the full analysis when [/INST] looking </s><s>[INST] back when it's over. [/INST] Well, Israel is in like a tough place. They have this attachment to being part of the West, They have these attachment to liberal ideals. They have an attachment to democracy and they have an attachment to a jewish state and that those things are not so easily compatible because to recognize the rights of non jewish citizens right or to record or to create or to have a one state solution to the current conflict undermines the long term ability to have a jewish state um and to do anything else and to deny that denies their liberal democratic ideals and and that's a really hard contest of priorities to sort out. </s><s>[INST] Yeah, it's complicated course everything you just said probably has multiple perspectives on it from other that would phrase all the same things, but using different words. [/INST] Well, I'm trying to I try to analyze these things in like a dispassionate way, </s><s>[INST] but unfortunately, just having been enough conversations, even your dispassionate description would be seen as a as a as one that's already picked a side. And I'll say this because there's holding these ideals, I'll give you another example. The United States also has ideals of freedom and and other like human rights. Uh so it has those ideals and it also sees itself as a superpower and as a deploy er of those enforcer of those ideas in the world. And so the kind of actions from the perspective of a lot of people in that world, from Children, they get to see drones drop bombs on their house where the where their father is not mother dead. I have a very different view of this. Uh [/INST] well you're beginning to see why I didn't I just I wanted to I wanted to write about those things and think about those things, but I wanted this, I wanted this book to do something different and I didn't want to follow along one of these Polaroids. I might, you know, on a personal level because I think I'm kind of a liberal democratic person at heart, my sympathies in that sense, lie in many ways with the Palestinians despite the way I I mean, I I'm just the fact that people are they're not representative and and they, you know, uh and they got a very raw real politik kind of feel like most people in history have gotten like this raw real politik kind of deal in the past, right? Where somebody took </s>

<s>[INST] So it is, you know, swap in some sense, a competitive coin base, in which way is it? Which way is it not? So because for people who don't know, coin base is centralized. So let me ask, uh doesn't that go against the spirit of crypto since Kryptos is decentralized, what are the pros and cons of being centralized as an exchange? So [/INST] I don't think Coinbase is fully centralized, We have many different products. And the way that I think about it is that our exchange or brokerage is a centralized regulated financial service business and it's actually important for the crypto ecosystem to have that because you want to allow a lot of the fiat money in the world to flow into the crypto economy. So we, you know, we're very proud of that and I think we've helped a lot of that money flow in now, once people have money in crypto, they can choose to hold it in a variety of ways and they can choose to hold it in a self custodial wallet which is more decentralized, they can choose to use um decentralized exchanges, which um we we love and you know swap is not really, I don't think of them as like a direct competitor to us, we basically have integrated um you know, swap into a number of our products. We love defi decentralized exchanges, all the whole thing. So Coinbase wallet, which is a self custodial wallet is more decentralized and it allows people to um hold their own crypto, they don't have to trust us. </s><s>[INST] Can you explain what a self custodial wallet is? What is the wallet and what is the self custodial wallet? [/INST] Yeah, so it's it's confusing. So um so a custodial wallet means you're trusting coin base to store your crypto, the private keys themselves and you know, for some people and institutions and everything just meeting them where they are today, that's nice because it's simpler, you know, um they're not afraid of losing their crypto if they make some accident, accidental mistake or so, you know, a custodial um, crypto products are important to help get a bunch of people into the ecosystem, but I'm very supportive of self custodial wallets and I think in some ways that they are the future because more and more people are gonna want to store their own crypto, not trust a third party institutions do it. And in some ways that is much more authentic to the the ethos of crypto. So coin base will help you convert the fiat to crypto in a frankly that's a more centralized thing, but once you have crypto, you can then go to the self custodial world, store it yourself in a to get into the technical details just for a second it's basically saying um you're going to store the keys on your own device. And so um even if coin base you know get some court order to seize it we actually can't like from an architecture point of view we can't do it um Or you know if Coinbase gets hacked or something we can't lose your funds. Like now you the thing is you have to take the responsibility because we're not taking it so the individual person could get hacked right and there's a whole bunch of really cool research happening to make self custodial wallets more resilient to accidental loss um hacks and just user error like you know um I don't know how much you've looked at like various cryptography things but there's like basically um you can have multiple key multi sig multiple signatures from different keys on different devices where you need like two of the three or three of the five. There's a whole technology called multi party computation or threshold signing signatures which is really cool. Um </s><s>[INST] But those are the things you would run locally [/INST] like </s><s>[INST] what these are all security measures like cryptography measures to protect you without a centralized component. [/INST] Right? So like a simple example would be let's say you had a two of three key signature and you know one key might be sort of coin based but that's not a quorum so we couldn't unilaterally move your funds but in another key is on your device on your phone let's </s><s>[INST] say. [/INST] Um So that so in a normal situation you have a key on your phone. We have one. Um but you and so two out of three now just you know it can all get signed very quickly for day to day use. But let's say you lose your phone or something now there has to be a third key and that's where you know you could store it in a backup somewhere. Um Like in google drive or iCloud you could trust a third party that's not coin based. Also have that one key and they can't do anything unilaterally with that one key. So that's a simple example you can get you can get way more complicated. </s><s>[INST] Yeah. That's an awesome idea. And so like if your funds get seized coin base can't you can't do anything but you better not lose your phone maybe in that case. Yeah [/INST] but it provides there is so even if you lose your phone then there is a recovery mechanism because you can get the one key from Coinbase, the one from your backup provider and recover a new one back on your phone. </s><s>[INST] But but what if coin base is no longer but because of government because of say it's in north Korea government says you're no longer like coin base is shut down in that country or something like that then you can get it even if you have access to those two. So uh, again, perhaps a silly question, but isn't a self custodial wallet a competitor as a notion to coin base? [/INST] No, I mean we so we offer a self custodial wallet, we've built one and it's like, but </s>

<s>[INST] and don't treat people like they're Children and need to be told lies because they won't understand the full complexity of the truth. People I think are pretty good at or actually, you know, people with time are good understanding data, but better than anything there there are better at. They're extremely good at detecting arrogance and bullshit and give them [/INST] either one of those? I mean, I'll give you one that's where I think it's greatly undermined vaccine has great, greatly undermined the demand for the vaccine is this weird denial that if you are recovered from covid you have extremely good immunity both against infection and access And that denial leads to people distrusting the message given by like the CDC director for instance, in favor of the vaccine. Right? Why would you deny a thing? That's such an obvious fact. Like you can look at the data and it's just, I mean just just pops out at you that people that are Covid recovered are not getting infected again at very high rates, much lower rates </s><s>[INST] after these kinds of conversations. Um, I'm sure after this very conversation I often get a number of messages from joe joe Rogan and from Sam Harris, Who to me are people I admire, I think are really intelligent, thoughtful human beings. They also have a platform and I believe at least in my mind about this covid set of topics they represent a group of people. Um, right. Each group has smart, thoughtful, well intentioned human beings and I don't know who is right, but I do know that they're kind of tribal a little bit uh, those groups. And so the question I want to ask is like, what do you think about these two groups and this kind of tension over the vaccine. Um, that sometimes it just keeps finding different topics on which to focus on like whether kids should get vaccinated or not, whether there should be vaccine mandates or not, which seemed to be often very kind of specific policy kinds of questions that it's the bigger [/INST] picture. I think it's a symptom of the distrust that people have in public health. I think this kind of schism over the the vaccine does not happen in places where the public health authorities have been much more trustworthy. Right? So you don't see this vaccine hasn't seen Sweden, for instance. Um, what what's happened in the United States is the vaccine has become, um, uh, first because of politics, but then also because of the scientific arrogance. This sort of Touchstone issue and people line up on on both sides of it and the different language you're hearing is structured around that. So, before the election, for instance, I did I was I did a testimony in the house on on measurement of vaccine safety. And I I was I was invited by the republicans. There were, I think of four other experts invited by the democrats. With three other experts invited by democrats, each of whom had a lot of experience in measuring vaccine safety. I was really surprised to hear them each doubt whether the FDA would do a reasonable job in assessing vaccine safety, including by people who have long records of working with the FDA. I mean, these are professionals, great scientists whose main goal in life is to make sure that safe vaccine that unsafe vaccines don't get released into the world. And if they are they get pulled and they were casting down on the vaccine, the ability to track vaccine safety before the election and then after the election, the rhetoric switched on a dime, right? All of a sudden it's republicans that are cast as if they're vaccine hesitant, that kind of political shift the public notices if if all it takes is an election to change how people talk about the safety of the vaccine. Well, we're not talking science anymore. Many people think, right? I think that creates created its hesitancy. The other thing, I think the the hesitancy some politicians viewed it as a political as sort of like a political opportunity to sort of demonize people who are hesitant and that itself fueled presidency, right? Like the if you're if you're telling me, I'm a rube that just doesn't want the vaccine because I want everyone to die. Well, I'm gonna I'm gonna react really negatively. And if you're talking down to me about my legitimate, you know, sort of concerns about whether this vaccine safety time, you know, I've heard from women who are thinking about getting pregnant. Should I take the vaccine? I don't know. I mean, there are all kinds of questions, legitimate questions that I think, um, should have good data to answer that we don't necessarily have a good day to answer. So what do you do in the face of that? Well, one reaction is to pretend like we know for a fact that it's safe when we don't have the data. And I know for a fact in that particular group with that particular set of clinical circumstances, you know, and that I think breeds hesitancy, people can detect that bullshit. Um, whereas if you just tell people, you know, I don't know. Yeah. Leave it with humility. Yeah. You've got to you, you will end up with a better result. </s>

<s>[INST] So okay, that's really cool. But that's work from a few years ago. So you uh you did work in your mental with Jeff Hawkins uh with hierarchical temporal memory. How is your just if you could give a brief history, how is your view of the way the models of the brain changed over the past a few years leading up to to know is there some interesting aspects where there was an adjustment to your understanding of the brain? Or is it all just building on top of each other [/INST] in terms of the higher level ideas, especially the ones Jeff wrote about in the book, if you if you blur out right </s><s>[INST] in our [/INST] intelligence on intelligence, if you if you blur out the details and and if you just zoom out under the high level idea, uh things are, I would say consistent with what he wrote about, but but many things will be consistent with that because it is it's a blur you know, when you when you, you know, deploying systems are also you know multilevel hierarchical, all of those things. Right? So so at the but um in terms of the detail, a lot of things are different uh and and and those details matter a lot. Um so so one point of difference I had with Jeff uh was how to approach, you know, how much of biological plausibility and realism do you want in the learning algorithms? Um So uh when I was there this was you know, almost 10 years ago now. So I don't know, I don't know what just thinks now. But 10 years ago the difference was that I did not want to be so constrained on saying uh my learning algorithms want need to be biologically plausible uh based on some filter of biological possibility available at that time. To me that is a dangerous cut to make because we are, you know, discovering more and more things about the brain all the time. New biophysical mechanisms, new channels are being discovered all the time. So I don't want to upfront kill off uh learning algorithm </s><s>[INST] just because we don't really understand the full uh full of biophysics or whatever of how the brain learns. Exactly. Exactly. Let me ask sergeant drop like what's our what's your sense, what's our best understanding of how the brain learns? So [/INST] things like back propagation. Credit assignment. So, so many of these algorithms have learning algorithms have things in common. Right? It is a back propagation is one way of credit assignment. There is another algorithm called expectation maximization which is, you know, another VTA adjustment algorithm. But </s><s>[INST] is it your sense? The brain does something like this [/INST] has to there's no way around it in the sense of saying that you do have to are just the the connections. </s><s>[INST] So and you're saying credit assignment, you have to reward the connections that were useful in making a correct prediction and not. Yeah I guess what but yeah it doesn't have to be differentiable. I mean it [/INST] doesn't have to be different. Yeah but you have to have a you know you have a model that you start with. You have data comes in and you have to have a way of adjusting the model such that it better fits the data so that that is all of learning right? And and some of them can be using back prop to do that. Some of it can be using uh you know very local uh graph changes to do that. Uh That can be you know many of these learning algorithms have similar update properties locally in terms of what the neurons need to do locally. </s><s>[INST] I wonder if small differences in learning algorithms can have huge differences in the actual effect. So the dynamics of I mean sort of the reverse like spiking like uh if credit assignment is like a lightning versus like a rainstorm or something like whether whether there's a like a looping local type of situation with the credit assignment whether there is like regularization like how how how many injects for boston's into the whole thing like whether it's chemical or electrical or mechanical uh all those kinds of things like that. I feel like that. Yeah. Yeah. I feel like those differences could be essential right? [/INST] It could be it's just that you don't know enough to on the learning side, you don't know enough to say that is definitely not the way the brain does it. </s><s>[INST] So you don't want to be stuck to it. So that yeah, So you've been open minded on that side [/INST] of things. On the inference that on the recognition said I am much more unable to being constrained because it's much easier to do experiments because you know, it's like, okay, here's a stimulus, you know, how many steps did it get to take the answer? I can trace it back, I can I can understand the speed of that computation etcetera. Much more readily on the inference side. </s><s>[INST] Got it. And then you can't do good experiments on the learning side. So that let's let's go right into the cortical microcircuits right back. So what uh what are these ideas beyond recursive cortical network that you're looking at now? [/INST] So we have made a pass through multiple of the steps that you know, as as I mentioned earlier, you know, we were looking at perception from the angle of cognition, right? It was not just perception for perception's sake. How do you how do you connect it to cognition? How do you learn concepts? And how do you learn abstract reasoning similar to some of the things fans we uh talked about, right? So um so we have taken one passed through it basically saying what is the basic cognitive architecture That you need to have which has a perceptual system which has a system that learns dynamics of the world and then has something like a routine program learning system on top of it to learn concepts. So we have built one of the you know the version .1 of that system. Uh this was another science robotics paper. It is, it's a the title of that paper was you know something like cognitive programs. How do you build cognitive programs? Uh and </s>

<s>[INST] relationship, [/INST] you know, but, but he, he says that I changed his life. I mean, he was going down a very dark path and I gave him an option that one night and he made the right choice. I mean he's, he now does penetration testing, he does a lot of good work and uh, you know, he's turned his life around. </s><s>[INST] Do you worry about Cyber War in the 21st Century? [/INST] Absolutely. If there is a global war, it'll start with cyber. You know, if it's not already started. </s><s>[INST] Do you feel like there's a, like a boiling, like the drums of war beating, what's happening in Ukraine with Russia? It feels like the United States becoming more and more involved in the conflict in that part of the world and china is watching very closely is starting to get involved geopolitically and probably in terms of cyber um, do you worry about this kind of thing happening in the next decade or two? Like where it really escalates, You know, people in the, in the 1920s were completely terrible at predicting the World War II. Do you think we're at the precipice of war potentially? I [/INST] think we could be, I mean, I, I would hate to just be, you know, fearmongering out there. Um, you know, Covid's over. So the next big thing in the media is war and all that. But I mean there's some, some flags going up that are very strange to me. Is </s><s>[INST] there ways to avoid this? [/INST] I hope so. I hope smarter people than I are figuring it out. I hope people are playing their parts and and and talking to the right people. Um because that's the war is the last thing I want. </s><s>[INST] Well there's two things to be concerned about the cyber side. One is the actual defense on the technical side of cyber and the other one is the panic that might happen when something like some dramatic event happened because of cyber some major hack that becomes public. I'm honestly more concerned about the panic because I feel like if people don't think about the stuff, the panic can hit harder. Like if if they if they're not conscious about the fact that we're constantly under attack. I feel like it'll come like a much harder surprise. [/INST] Yeah, I think people will be really shocked on things. I mean, so we talked about today and it was 2011 they had access into a water, the water supply system of a major US city. They didn't do anything with it. They were sitting on it in case someone got arrested and they were gonna maybe just exposed that it's that insecure maybe they were gonna do something with it. I don't know. But you know that that's that's 2011, you know, I don't think it's gotten a lot better since then </s><s>[INST] and there's probably nation states or major organizations that are sitting secretly on hacks like [/INST] 100% they're sitting seriously waiting to expose things. </s><s>[INST] I [/INST] mean I again I don't want to scare the sh out of people but people have to understand the cyber threat. I mean there are you know there are there are thousands of nation state hackers in some countries. I mean we have to we have offensive hackers, you </s><s>[INST] Know the terrorist attacks of 9 11, there's planes that actually hit actual buildings and it was visibly clear and you can trace the information with cyber attacks. Say something that would result in the in a major explosion in new york city. How the hell do you trace that? Like if it's well done it's going to be extremely difficult. The problem is there's so many problems one of which the U. S. Government in that case has complete freedom to blame anybody they want and then to to go start war with anybody. Anybody that actually see uh that's sorry that's one cynical take on it. Of course. No [/INST] but you're going down the right path. I mean the guys that flew planes in the buildings wanted attribution. They took credit for it when we see the cyber attack. I doubt we're going to see attribution. Maybe the victim's side, the U. S. Government on this side might come out and try to blame somebody but you know like you brought up like they could blame anybody they want there's not really a good way of verifying that, </s><s>[INST] can I just ask for your advice? So in my personal case am I being tracked, How do I know? How do I protect myself? Should I care [/INST] you are being tracked? Um I wouldn't say you're being tracked by the government. You're you're definitely being tracked by big Tech. Uh </s><s>[INST] No, I mean, me personally lex and an escalated level. So like uh like you mentioned there's an FBI file on people. Sure, I'd love to see what's in that file. Uh Who didn't have the argument? Oh, let me ask you FBI um How's the cafeteria food? And FBI at [/INST] the academy? It's bad. Um </s><s>[INST] What about like at [/INST] headquarters a little bit better because that's what the director, I mean, he eats up on the seventh floor. </s><s>[INST] Have you been like a google? Have you been in the Silicon Valley? Those like those? I've [/INST] been to the google in Silicon Valley. I've been to the google in new york. </s><s>[INST] The food is incredible. [/INST] It is great. </s><s>[INST] So FBI is worse. [/INST] Well, when you're going through the academy, they don't let you outside of the building. So you have to eat it. Um But I think that's the only reason people eat it. Um It's it's it's pretty bad. </s><s>[INST] I got it. But [/INST] there's also a bar inside the FBI academy, people don't know that yes alcohol bar. And if you, as long as you've passed your P. T. And uh and going, well you're allowed to go to the bar. </s>

<s>[INST] And that's uh like you said the little bump that that seems to be a very small fraction of the human experience. Right? So it's kind of fascinating to study it because most of us move through life without ever experienced in that kind of focus. [/INST] Well, everything is in a peak state there. I really think that's where optimal performance lies. </s><s>[INST] There's so many interesting words here, but what's performance and what's optimal performance? We're talking about mental ability to what to perceive the environment quickly, to make actions quickly. What's optimal performance. [/INST] Yeah, well it's very subjective and it varies depending on um task and environment. So one way we can make it a little bit more operational and concrete is to say um there is a sweet spot if you will where the level of internal autonomic arousal, ak stress or alertness, whatever you wanna call it is ideally matched to the speed of whatever challenge you have to be facing in the outside world. So we all have um perception of the outside world is extra reception and the perception of our internal real estate interception. And when those two think when interception and Xterra reception are matched along a couple dimensions, performance uh tends to increase, it tends to be in a optimal range. So for instance, if you're, I don't play guitar but I know you play guitar. So let's say you're trying to learn something new on the guitar, I'm not saying that being in these super high states of activation are the best place for you to be in order to learn. It may be that you your internal arousal needs to be at a level where your analysis of space and time has to be well matched to the information coming in and what you're trying to do in terms of performance in terms of playing chords and notes and so forth. Now in these cases of high threat where things are coming in quickly and animals and humans need to react very quickly, the higher your state of autonomic arousal the better because you're slicing time more. Finally, just because of the way the economic system works, it, you know, the people dilation for instance and movement of the lens essentially changes your optics that's obvious. But in with the change in optics is a change in how you been time and slice time, which allows you to get more frames per second readout with the guitar learning for instance. It might actually be that you want to be almost sleepy almost in a uh kind of drowsy state to be able to and I don't play music so I can I'm guessing here but send some of the nuance in the chords or the ways that you're to be relaxed enough that your fingers can follow an external cues so matching the movement of your fingers to something that's pure extra reception. And so there is no perfect autonomic state for performance. This is why I don't favor terms like flow because they're not well operationally defined enough. But I do believe that optimal or peak performance is going to rise when internal state is ideally matched to the spacetime features of the external demands. So </s><s>[INST] there's some slicing of time that happens and then you're you're able to adjust the slice time more finally, or more les finally, in order to adjust to the stimulus, the dynamics of the stimulus. What about the the realm of ideas. So like, you know, I'm a big believer, this guy named cal Newport's who wrote a book about [/INST] deep work </s><s>[INST] that Yeah, he's great. Uh he I mean one of the nice things, I've always practice deep work, but he it's always nice to have words put to the concepts that you've practiced it somehow makes them more concrete and allows you to uh to get better. It turns it into a skill you can get better at. But you know, I also value deep thinking where you I think it's almost meditative. You think about a particular concept for long periods of time, the programming you have to do that kind of thing for. Yes, you have to hold this concept. Thank you. Like you you hold it and then you take steps with it, you take further steps and you're you're holding relatively complicated things in your mind as you're thinking about them. And there's a lot of I mean the hardest part is there's a frustrating things like you take a step and it turns out to be the wrong directions. You have to calmly turn around and take a step back and then it's your kind of like exploring through the space of ideas. Is there something about your study of optimal performance that can be applied to the act of thinking as opposed to action? [/INST] Well, we haven't done too much work there. But what um but I think I can comment on it from a neuroscience which is really all I do is uh Well I mean we do experiments in the lab but um looking at things through the lens of neuroscience. So what you're describing um can be mapped fairly well to working memory. Just keeping things online and updating them as they change in information is coming back into your brain. Uh Jack Feldman who I'm a huge fan of and um fortunate to be friends with is a professor at U. C. L. A. Works on respiration and breathing. But he has a physics background and um and so he thinks about respiration and breathing in terms of ground states and how they modulate other states. Very very interesting. I think important work. Jack has an answer to your question So I'm not going to get this exactly right because this is lifted from a coffee conversation that we had about a month ago. But so um apologies in advance for the but I think I can get mostly right. So we were talking about this about how the brain updates cognitive states depending on demands and thinking in particular. And he used an interesting example, I'd be curious to know if you agree or disagree. Uh He said you know most great mathematics is done by people in there late teens and twenties even you could say early twenties sometimes into the late twenties but not much further on. Maybe I just insulted some mathematicians. </s>

<s>[INST] hmm. [/INST] Um both of which are involved blinders. And so there's all kinds of blinders that we live in and that that's part of ideology is what what don't we even see, </s><s>[INST] and that would prevent us from seeing some deep objective scientific truth, [/INST] some truth. </s><s>[INST] And it's actually just to mention there's some people including Elon, who are saying there's not too many people, there's not enough people right, that if you just look at the birth rates, it's and so it's like some of this is actually very difficult to figure out because that there's there's these narratives you want your tobacco obesity with sugar has been narratives throughout the history and it's very um there are certain topics in which it's um one easy to almost become apathetic because, like you just see in history how narratives take hold and fade away. You know, people were really sure what that tobacco is is not at all a problem and then it fades and then they figure it out and then other things come along, what other things came along now, you know? Well, [/INST] you asked about ideology and one of the things I always ask students before class whether I'm teaching Agni Atala ji or world history of sciences, what makes fish move? and 90% of Americans will say some version of muscles, fins, you know, neurons when the reality is at least in salt water, fish don't swim places, they're moved by currents, fish removed by currents. That's what makes fish move. This is not even counting the rotation of the earth on its axis, sort of the rotation of the earth around the sun or the rotation of the solar system around the galaxy. You know, ignore all that. Even on earth, fish arrive up in Alaska. They didn't, they don't swim there. They come by currents. And this is known to people who understand the ecology of, of, of fish. But we as sort of individualistic americans think that </s><s>[INST] the fish pulled, pulled itself up by his boots, [/INST] pulled himself up by his bootstraps, right? And whatever, you know, gumption and courage, you know, made his own world instead of thinking of something like uh cigarettes, for example, hitting a village like an epidemic hitting the village like cholera or pneumonia or something like that. So there's a big ideology we have of personal choice. A great example of that is in the tobacco world where people always, there's a whole field called cessation that always means cessation of consumption, never cessation of production. All blame is put on the individual smoker. Instead of looking at how they get smoked. And looking at that bigger picture, I think is part of the story. </s><s>[INST] So a few years ago you wrote that the cigarette is the deadliest object in the history of human civilization, Cigarettes kill about six million people every year. A number that will grow before it shrinks, Smoking in the 20th century killed 100 million people and a billion could perish in our century unless we reverse the course. Can [/INST] you </s><s>[INST] explain this idea that it's the deadliest object in the history of human civilization? Maybe just also talk about big tobacco and your efforts there? [/INST] Well, cigarettes have killed more than any other object than all the world of iron and all the world of gunpowder, nuclear bombs have only killed a few 100,000 people, cigarettes have killed hundreds of millions and every year kill about as many as Covid. They're they're sort of neck and neck. But if you took the last five years, there's no contest, cigarettes have killed far more and are far more preventable. So what we're in a world, this bizarro world where every night there's a covid report and cigarettes would never be mentioned, cigarettes would no more likely to be mentioned than if we were talking about chewing gum on a sidewalk. There'd be no more likely to be in a presidential debate. Then, you know, sneezing in the wrong place. So we live in this world where most things are invisible. You know, we we are the eyes are in the front of the head, We don't see what's behind us. We have a phobia, which means not only do we only see what's in front of us, We see in a very narrow tunnel and that's because we're predators. We don't have the eternal watchfulness of prey. We have a zeroed targeted focus and that leads to a kind of myopia or a tunnel vision and all kinds of things. Then when you get something like a very powerful tobacco industry, which is a multi, multi billion dollar industry, which still spends many billions of dollars advertising every year but nonetheless manages to make themselves invisible. You have this powerful agent that is producing, producing this engine of death that is invisible. It's been reduced to the fish that move themselves. In other words, there's not really a tobacco industry, there's just people who smoke and that's a personal choice like what food we're gonna have for dinner tonight. And so it's erased from the policy world. It's as if it doesn't exist and creating that sense of invisibility. two failure to understand the causes of causes is what allows the epidemic to continue. But also not even to be acknowledged. </s><s>[INST] How's the invisibility created? Is it natural? Is it just human nature that ideas just fade from [/INST] our </s><s>[INST] attention or is it malevolent still going on kind of um action by the tobacco companies to keep this invisible? [/INST] It's still going on. Even when you see an ad against cigarettes on television that's dramatically curtailed because the law that made those even possible required that there will be, there's an anti villainy clause the industry can't be made in even visible in those ads in some they get away with it. But the industry operates through very powerful agents, you know, powerful senators. Um, they used to count uh, three quarters of the members of, of Congress as you know, grade a contacts. They had most of the senators in their pocket. A lot of the senators sometimes they'll play both sides of the aisle basically Tobacco is Democratic Democratic Party until basically The 70s and Ronald Reagan then it shifts over to becoming um Republican. They create bodies like the Tea Party. They emerged with big oil, the Koch brothers in the 19 80s and 90s to form the tea party and a whole series of fronts which fight against all regulation and all taxation in order to prevent gas taxes and cigarette taxes, which are bonded in the convenience store and walmart. Most cigarettes are actually sold in places like walmart and pharmacies and seven elevens, things like that And through that locust then you have gasoline and tobacco sort of in this micro architectural collaboration. So there's multiple, multiple means that they is plus a lot of their targeting is hyper specific. They use the internet very effectively. They use email and think that our customer customer targeting </s>

<s>[INST] Well, yeah, I mean that's currently humans are very good at that kind of first principles thinking was stepping back, but I think ai is really good at, you know, collect a huge amount of data and a huge amount of data of observation of planets and figure out that Earth is not at the center of the universe, that there's actually a son, we're orbiting the sun. But then you can as a human being asked, well how did how do solar systems come to be? How do you um what are the different forces that are required to make this kind of pattern emerge? And then you start to invent things like gravity or I mean obviously I mixed up the ordering of of gravity wasn't considered as a thing that connects planets but um we are able to think about those big picture things as human beings, ai just very good to infer simple models from a huge amount of data. Um and and the question is with biology, you know, we kind of go back and forth and how we solve biology. Listen, protein folding was thought to be impossible to solve. And there's a lot of brilliant PhD students that worked one protein at a time trying to figure out the structure and the fact that was able to do that, [/INST] oh I'm not I'm not knocking it at all but but but I think that people have been asking the wrong question </s><s>[INST] but then as the people start to ask better and bigger questions, they I kinda enters the chat and says I'll help you out with that. Can [/INST] I give you another example for my own work um the risk of getting a disease as we get older, um there are genetic aspects to it. You know, if you spend your whole life over eating and smoking and whatever, that's a whole separate question. But there's a genetic side to the risk. And we know a few genes that increase your risk of certain things. And for for probably 20 years now, people have been doing what's called G was, which is a genome wide association studies. So you you've effectively scanned the entire genome for any single nucleotide polymorphisms, which is to say, a single letter change in one place that has a higher association of being linked with a particular disease or not. And you can come out with thousands of these things across the genome. And if you add them all up and try and say, well, so, so do they add up to uh to explain the the known genetic risk of this disease? And the known genetic risk often comes from twin studies. And you can say that if this twin gets epilepsy, there's a 40 or 50% risk that the other twin identical twin will also get epilepsy. Therefore the genetic factor is about 50%. Uh, and so the gene similarities that you see should account for 50% of that known risk. Very often it accounts for less than 1/10 of the known risk. And there's two possible explanations. And there's one which people tend to do, which is to say, well we don't have enough statistical power if we maybe there's maybe there's a million we've only found 1000 of them. But if we find the other million their weekly related, but there's a huge number of them. And so we'll account for that whole risk. Maybe there's, you know, maybe there's a billion of them. So so that's one way. The other way is to say, well hang on a minute, you're missing a system here. That system is the mitochondrial D. N. A. Which people tend to dismiss because it's small and it's not it doesn't change very much. Um but a few single letter changes in that mitochondrial DNA. It controls some really basic processes. It controls not only all the energy that we need to live and to move around and do everything we do, but also bio synthesis to make the new building blocks to you know, to to to make new cells and cancer cells very often kind of take over the mitochondria and rewire them So that instead of using them for making energy, they're effectively using them as precursors for the building blocks. With bio synthesis you need to make new amino acids nucleotides for D. N. A. You want to make new lipids to make your membranes and so on. So they kind of rewire metabolism. Now the problem is that we've got all these interactions between mitochondrial DNA and the genes in the nucleus that are overlooked completely because people throw away literally throw away the mitochondrial genes and we can see in in fruit flies that they interact and produce big differences in risk. So you can set, you can set a I onto this question of exactly what uh you know, how many of these base changes there are. And that's just one possible solution that maybe there are a million of them and it does account for the greater part of the risk or the other one is they aren't that, it's just not there, that actually the risk lies in something you weren't even looking at. And this is where human intuition is very important. And just this feeling that, well, I'm working on this and I think it's important and I'm bloody minded about it. And in the end, some people are right, it turns out that it was important. Can you get a I to do that? To be bloody minded? </s>

<s>[INST] But the fundamental question of panspermia is, do we have the machine here on earth to build life? It is the vents enough. It is oxygen and hydrogen and whatever the heck else we want and some source of energy and heat, is that enough to build life or? Well, that's of course you would say that as a human, but there could be aliens right now chuckling at that idea. Maybe you need some special um special sauce, your senses, We have everything. [/INST] I mean this is precisely the question. So I like to when I'm, when I'm talking in schools, I like to start out with the idea of we make we can make a time machine, we go back four billion years and we go to these environments that people talk about. We go to a deep sea hydrothermal event, we go to a kind of Yellowstone park type place environment and we find some slime that looks like we can test it is made of organic molecules. It's got a structure which is not obviously cells but you know, it's is this a stepping stone on the way to life or not? How do we know? Unless we've got an intellectual framework that says this is this is a stepping stone and that's not a step, You know, we never know, we wouldn't know which environment to go to what to look for, how to say this? So all we can ever hope for because we're never going to build that time machine is to have an intellectual framework that can explain step by step, experiment by experiment how we go from a sterile inorganic planet to living cells as we know them. And in that framework every time you have a choice it could be this way or it could be that way or you know, there's lots of possible fox down that road um did it have to be that way, Could it have been the other way and would that have given you life with very different properties. Um So if you if you come up with, you know, it's a long hypothesis because as I say, we're going from really simple prebiotic chemistry all the way through to genes and molecular machines. That's a long, long pathway. And nobody in the field would agree on the order in which these things happened. Which is not a bad thing because it means that you have to go out and do some experiments and try and demonstrate that it's possible or not possible. </s><s>[INST] It's so freaking amazing that it happened though. It feels like there's a direction to the thing. Can you try to answer from a framework perspective of what is life? So you said there's some order and yet there's complexity. So it's not perfectly ordered. It's not boring, there's still some fun in it. And it also feels like the processes have a direction through the selection mechanism. They seem to be building something always better. Always improving. I mean maybe it's I [/INST] mean that's a perception </s><s>[INST] that's our romanticization of things are always better things are getting better. We'd like to believe that. [/INST] I mean you think about the world from the point of view of bacteria and bacteria are the first things to emerge from whatever environment they came from and they dominated the planet very very quickly and they haven't really changed four billion years later, they look exactly the same. </s><s>[INST] So about four billion years ago bacteria started to to really run the show and then nothing happened for a while. [/INST] Nothing happened for two billion years. Then after two billion years we see another single event origin if you like of our own type of cell that eukaryotic cells are cells with a nucleus and lots of stuff going on inside another singular origin. It only happened once in the history of life on earth. Maybe it happened multiple times and there's no evidence, everything just disappeared. But we have to at least take it seriously is that there's something that stops bacteria from becoming more complex because they didn't you know that's the fact that they emerged four billion years ago and something happened two billion years ago. But the bacteria themselves didn't change. They remain bacterial. So there is no trajectory necessary trajectory towards great complexity and human beings at the end of it is very easy to imagine that without photosynthesis arising or without you characterizing that the planet could be full of bacteria and nothing else. </s><s>[INST] We'll get to that because that's a brilliant invention. And there's a few brilliant invention along the way. But what is life if you were to show up on earth? But to take that time machine? And you said asking yourself the question is this a stepping stone towards life as you step along when you see the early bacteria, how would you know it's life is And then this is really important question When you go to other planets and look for life? Like what what is the framework of telling the difference between Iraq and bacteria? [/INST] I mean the question is kind of both impossible to answer and trivial at the same time and I don't like to answer it because I don't think there is an answer I think we're trying to </s><s>[INST] describe. [/INST] I mean there's lots of at least 40 or 50 different definitions of life out there and most of them are well </s><s>[INST] not [/INST] obviously bad in one way or another. </s><s>[INST] I [/INST] mean there's there's for I can never remember the exact words that people use but there's a nasa working definition of life which more or less says a system which is capable of self sustaining system capable of evolution or something along those lines. And I immediately have a problem with the words self sustaining because it's sustained by the environment and I know what they're getting at. I know what they're trying to say but but I pick a hole in that and there's you know, there's always wags who say but you know by that definition a rabbit is not alive, only a pair of rabbits would be alive because a single rabbit is incapable of copying itself. There's all kinds of pedantic, silly but also important objections to any hypothesis. The real question is what what is you know, we can argue all day or people do argue all day about is a virus alive or not and it depends on the content but most biologists could not agree about that. So then what about a jumping gene? A retro element is even simpler than a virus but it's capable of converting its environment into a copy of itself. And that's about as close this is not a definition, but this is a kind of a description of life is that it's it's able to parasite ties the environment and that goes for plants as well as animals and bacteria and viruses. Um to make a relatively exact copy of themselves. Informational, exact copy of themselves by </s>

<s>[INST] that. Yeah, that was really, really, really refreshing to hear. So this is me speaking. But there's a sense when companies take on these issues publicly from a ceo position and anywhere else that it does seem to optimize for virtue signaling versus solving a particular problem because to solve a particular problem, you really have to really put in, you have to hire a huge number. You basically have to create a company with a company to take on a particular thing. But if you allow yourself to internally care about a particular issue, you're basically pacifying some number of employees. Like making sure slack doesn't get out of hand and then you're doing this kind of from my perspective, especially on issues I care about fake virtue signaling basically trying to understand what will make me look the best, what would make the company look the best in this particular aspect. And it it just seems very shallow and it's optimizing for the wrong thing, not for the solving of the problems but for the making yourself look like the good guy and trying to leverage that to say I'm the good guy in all situations and it's just it's it's it's the wrong thing. And perhaps from your perspective as a ceo as a leader, it's also creating division, unnecessary division within people. Like they get, yeah, there's something about us, we get extremely argumentative about certain topics. They really bring out the emotion. And I think that probably as you were saying that emotion is even probably okay maybe productive when that emotion has to do with the mission of the company. Like you really care about those disagreements versus like something that has nothing to nothing to do with a particular with with increasing economic freedom uh using crypto. Yeah, it's fascinating but it was so refreshing because it's rare. Why do you think that's a rare? So you the city you're mentioning we could I mean there's a bunch of cities but you know SAn Francisco is one such city when, when, when that culture and it's sad because SAn Francisco is also the Bay Area is also the hub historically of some of the greatest innovation in human history so that there's that tension. How did that culture emerge there where like the innovation was done by people that are very mission driven. You get a bunch of smart people together to solve a difficult problem. They get maybe sometimes too much blinders on but they try to balance that because it requires that focus to solve an actual problem. And yet that's also the place where this culture emerge. It's a fascinating human dynamic. I don't know, somebody will one day tell the history of of Silicon Valley not just the innovation but the social dynamics that occurred there anyway. Why do you think that's so rare? [/INST] Well because people don't wanna get attacked it's like super you don't wanna get canceled right, it's super uncomfortable. You know, nobody wants to be called a racist or whatever whatever you know people want to say on twitter so um Yeah. Yeah I definitely got attacked. I mean and I knew it, I knew it would be controversial. The only reason I did it frankly was that um I was kind of at my wit's end. I was like well like I said earlier like the job the ceo job sucks like either I don't want to do it or they have to go and I'm gonna make the company to something that I want and You know I spent um I'd spent eight or 90 years of my life at that point kind of building this thing. I was like well I could go start another company but it takes a long time to get momentum with these things. And you know Coinbase is a very rare thing that happened in the world. I feel very passionate about it. So um yeah I'm not gonna go like I need to make this the company that I want to work at. And what was really interesting was that there was such a huge outpouring of support that so I knew that it would be controversial and I would get attacked and predictably, you know, there was some um some journalists and you know, new york times and all these people who kind of like went and started writing hit pieces on on the company after shortly thereafter. And they basically just called people who left the company and like you know can get quotes on whatever they want and then they'll write a story. So mainstream media, I lost a lot of trust in mainstream media frankly after that. And of course it's kind of become obvious since then that um most mainstream media is like hyper politicized at this point. It's basically either super left or super right. And it's not really that focused on um truth. So that's that's kind of unfortunate because I think journalism is actually like really important in society so that that whole thing got eroded in the U. S. Luckily there's sort of new media people like you. Um And a whole bunch of people did </s><s>[INST] That blog post help that statement. The 95 people that remained. Is this still something you struggle with? Because it's also culture the broader tech space. [/INST] Okay so that was an interesting thing which was that. So the 95% of people stayed. I got a huge outpouring of support from people who said thank God you finally spoke up and said something because frankly it was making not a very fun place to work either. And I realized that there is I think there was I think is the same taleb has this blog post about the tyranny of the 1% or something like that. But there's basically a relatively small group 15% or something like that that is really upset about something. It's not the majority of company it's like 5%. There's another 15% or something that are sympathetic to the cause they're they're actually somewhat suggestible. They will go along with whatever because it sounds reasonable. You know these are like real issues they're talking about. It's not not to say that it's not real and they'll kind of get swept up in it. But there's an 80% of the company that basically doesn't agree or just wants to get their work done without all this drama and or distraction and they're afraid to speak up because if they speak up they're afraid of being again called a racist like fired, you know, ostracized amongst their peers. And so it did require um it to get to a bad enough place for me to finally say, you know what I I just I feel like I have to do this lived through the short term attacks of the press, which ultimately was very freeing for me because now I don't really care and now I can actually just build the company that I want to build without like caring about that. So and then what was cool was a lot of really great people reached out to the queen base to after that and we're like, I, you know, I'm an early engineer at google or whatever and like this culture has gotten kind of messed up and like I want to work at a company that's willing to stand for that. And so we've gotten a lot of good people come over basically what I realized and by the way, our diversity numbers and all that stuff, like people told me when I was drafting this post are like, don't post this, You're like people underrepresented groups will never want to work at this company again. And I was like, I don't think that's true. Like I talked to like R. E. R. G. Groups and they're not telling me they care about this stuff that much. They're telling me they just want to like be respected at work and do good work and contribute. So my gut was telling me that that advice was wrong and like I can tell you a year a year after doing it. Like our diversity numbers are basically either the same or better in every category. So that turned out to be false. Um Look I I hate to be like I'm like I'm you know polarizing on in either dimension here. Like I just want to get good work done and build good stuff with technology. So You know um I think companies should just have like reasonable policies like you want to get rid of bias in hiring you want to attract great people from all different backgrounds. Like you know, we have pledged 1%. We put 1% of the company equity into a foundation. Like I hope we're able to do good stuff with that. That's you know give back in some way. But like the main the main message I guess for me is like The core the core mission, the core work that we're doing on economic freedom and just all of our products are that is like the main value that we're contributing in the world. Like let's just do that more and hopefully we can get from 89 million verified users to a billion or whatever and then um I just think that's how we'll have the biggest impact. </s>

<s>[INST] So even if you start a perfect understanding of the system, your own experience will make a drift. I mean, that's a big concern over a year, over two years. Even, it doesn't have to be months. [/INST] And I think that as this technology moves from, well, I'd say it's kind of the more technology savvy ownership group to, you know, the mass market, you may be able to have some of those folks who are really familiar with technology, they may be able to internalize it better. Uh and, you know, you're kind of immunization against this kind of false risk assessment might last longer. But as folks who are who aren't as savvy about that, you know, read the material and they compare that to the personal experience. I think there that, you know, it's it's going to mhm. It's going to move more quickly. </s><s>[INST] So your work, the program that you created a google. And now at Aurora has focused more on the second path of creating full autonomy. So it's such a fascinating, I think it's one of the most interesting ai problems of the century. Right. It's uh, I just talked to a lot of people, just regular people. I don't know my mom about autonomous vehicles and you begin to grapple with ideas of giving your life control over to a machine. It's philosophically interesting. It's practically interesting. So let's talk about safety. How do you think we demonstrate? You've spoken about metrics in the past? How do you think we demonstrate to the world that autonomous vehicle under our system is safe? [/INST] This is one where it's difficult because there isn't a sound byte answer that we have to show a combination of uh work that was done diligently and thoughtfully. And this is where something like a functional safety process as part of that is like, here's, here's the way we did the work that means that we were very thorough. So, you know, if you believe that we, what we said about this is the way we did it, then you can have some confidence that we were thorough in in, in the engineering work we put into the system and then on top of that, you know, to kind of demonstrate that we weren't just thorough. We were actually good at what we did. There will be a kind of a collection of evidence uh in terms of demonstrating that the capabilities work the way we thought they did, you know, statistically and to whatever degree we can we can demonstrate that both in some combination of simulation, some combination of, of unit testing and decomposition testing and then some part of it will be on road data. And, and I think the way we're will ultimately convey this to the public is there'll be clearly some conversation with the public about it. But well, you know, kind of invoke the kind of the trusted nodes and that will spend more time being able to go into more depth with folks like Nitze and other federal and state regulatory bodies and kind of given that they are operating in the public interest and they're trusted that if we can, you know, show enough work to them that they're convinced, then, you know, I think we're in a, in a pretty good place. </s><s>[INST] That means you work with people that are essentially experts at safety to try to discuss and show. Do you think, uh, the answer is probably no. But just in case do you think there exists a metric? So currently people have been using a number of this engagements and it quickly turns into a marketing scheme to, to sort of, you alter the experience you run to adjust. I think you've spoken that you don't like, I don't love [/INST] it. No. In fact, I was on the record telling D. M. V. That I thought this was not a great metric. </s><s>[INST] Do you think it's possible to create a metric? A number that that could demonstrate safety outside of fatalities? [/INST] So, so I I do. And I think that it won't be just one number. So as we are internally grappling with us and, and at some point we'll be, we'll be able to talk more publicly about it is how do we think about human performance in different tasks, say detecting traffic lights or um, safely making a left turn across traffic? And what do we think the failure rates are for those different capabilities for people and then demonstrating to ourselves and then ultimately, uh, focus on regulatory role and then ultimately the public that we have confidence that our system will work better than that. And so these these individual metrics will, can tell a compelling story. Ultimately, I do think at the end of the day, what we care about in terms of safety is life saved, uh, and injuries reduced. And then, and then ultimately, you know, kind of casualty dollars that people aren't having to pay to get their car fixed. And I do think that you can, you know, in aviation, they look at a kind of an event pyramid where, you know, crashes at the top of that. And that's the worst event, obviously. And then there's injuries and, you know, near miss events and whatnot. And, and, you know, violation of operating procedures and you kind of build a a statistical model of, of the relevance of the the low severity things of the high speed of things. I think that's something where we'll be able to look at as well because You know an event per 85 million miles, you know statistically a difficult thing even at the scale of the US um to to to kind of compare directly </s>

<s>[INST] Somebody who works on and cares about autonomous and semi-autonomous vehicles, tell me about it. So, and there again, we return to the number of Elon Musk's per year generated. That's the M, coincidentally, same initials as the M, very suspicious, very suspicious. We're gonna have to look into that. All right, two more fields that I would like to force and twist your arm to look for viewquakes and for beautiful ideas, economics. What is a beautiful idea to you about economics? You've mentioned a lot of them. [/INST] Sure. So as you said before, there's gonna be the first viewcake most people encounter that makes the biggest difference on average in the world, because that's the only thing most people ever see is the first one. And so, with AI, the first one is just how big the problem is. But once you get past that, you'll find others. Certainly for economics, the first one is just the power of markets. You might've thought it was just really hard to figure out how to optimize in a big complicated space and markets just do a good first pass for an awful lot of stuff. And they're really quite robust and powerful. And that's just quite the viewquake, where you just say, you know, just let up, if you wanna get in the ballpark, just let a market handle it and step back. And that's true for a wide range of things. It's not true for everything, but it's a very good first approximation. Most people's intuitions for how they should limit markets are actually messing them up. They're that good in sense, right? Most people when you go, I don't know if we wanna trust that, </s><s>[INST] well, you should be trusting that. What about, what are markets? Like just a couple of words. [/INST] So the idea is if people want something, then let other companies form to try to supply that thing. Let those people pay for their cost of whatever they're making and try to offer that product to those people. Let many people, many such firms enter that industry and let the customers decide which ones they want. And if the firm goes out of business, let it go bankrupt and let other people invest in whichever ventures they wanna try to attract customers to their version of the product. And that just works for a wide range of products and services. </s><s>[INST] And through all of this, there's a free exchange of information too. There's a hope that there's no manipulation of information [/INST] and so on, that you're making these- Even when those things happen, still just the simple market solution is usually better than the things you'll try to do to fix it. Then the alternative. That's a view crank. It's surprising. It's not what you would initially thought. </s><s>[INST] That's one of the great, I guess, inventions [/INST] of human civilization that trust the markets. Now, another view cake that I learned in my research that's not all of economics, but something more specialized is the rationality of disagreement. That is basically people who are trying to believe what's true in a complicated situation would not actually disagree. And of course, humans disagree all the time. So it was quite the striking fact for me to learn in grad school that actually rational agents would not knowingly disagree. And so that makes disagreement more puzzling and it makes you less willing to disagree. Humans are to some degree rational and are able to- Their priorities are different than just figuring out the truth, </s><s>[INST] which might not be the same as being irrational. That's another tangent that could take an hour. In the space of human affairs, political science, what is a beautiful, foundational, interesting idea to you, [/INST] a view quake in the space of political science? The main thing that goes wrong in politics </s><s>[INST] is people not agreeing on what the best thing to do is. That's the wrong thing. [/INST] So that's what goes wrong. That is when you say, what's fundamentally behind most political failures? It's that people are ignorant of what the consequences of policy is. And that's surprising because it's actually feasible </s><s>[INST] to solve that problem, which we aren't solving. So it's a bug, not a feature, that there's an inability to arrive at a consensus. [/INST] So most political systems, if everybody looked to some authority, say, on a question and that authority told them the answer, then most political systems are capable of just doing that thing. But that is, and so it's the failure to have trustworthy authorities. That is sort of the underlying failure behind most political failure. We invade Iraq, say, when we don't have an authority to tell us that's a really stupid thing to do. And it is possible to create more informative, trustworthy authorities. That's a remarkable fact about the world of institutions </s><s>[INST] that we could do that, but we aren't. Yeah, so that's surprising. [/INST] We could and we aren't. Another big view, correct, about politics is from the Elf in the Brain that most people, when they're interacting with politics, they say they want to make the world better and to make their city better, their country better. And that's not their priority. What is it? They want to show loyalty to their allies. They want to show their people. They're on their side, yes. Are there various tribes they're in? That's their primary priority. </s>

<s>[INST] 62,000 years. What time flies when you're having fun? Okay, but you you write that they're about 16,000 molecules we care about when looking for a new earth or when we try to detect alien biosignatures. If we want to detect any molecules from here, we need to know their spectra and we currently don't solving this particular problem. That's my job [/INST] is the hat that I mean that's absolutely correct. I could have could have not said it better myself. Did you take that from my website? </s><s>[INST] And your website is excellent. So it's worthy place to steal stuff from. How do you solve this problem of for the 16,000 molecules would care about. of which fasting is one. And so um, so taking a step a little bit out of fossil mean is there [/INST] uh, but we were having so much fun </s><s>[INST] Having so much fun. No, we're not saying by its taking around, I'm just saying we're joined more friends coming to the party. How do you choose other friends to come to the party that are interesting to study as we solve one puzzle at a time through the space of 16,000. [/INST] So we've already started out of the 16,000, we understand water quite well, methane quite well, ammonia quite well. Carbon dioxide. I could keep going and then we understand molecules like to settle in hygiene cyanide more or less. And that takes us to about 4% of those 16,000. We have the sound about 4% of them, more or less, phosphene is one of them But the other 96%, we just really have barely any idea at all of where in the spectrum of light they would leave a mark. I can't spend the next 62,000 years doing this work. Um, and I don't want to even if you know somehow I was able that that's not, that wouldn't feel good. So one of the things that I try to do now is move away from how I did fast for him. So I did fast food and really the best that I could, the best that could be done with the computer power that we have, you know, trying to get each one of those 16.8 billion transitions mapped accurately calculated. And then I thought what if I do a worse job? What if I just do a much worse job? Can I just make it much faster and then it's still worth it? Like how bad can I get before it's worthless? And then could I do this for all the other molecules? So I created exactly this terrible, terrible </s><s>[INST] system. How bad? So how what's the answer? That question? That fundamental question. I ask myself all the time in other domains, [/INST] how crappy can I be </s><s>[INST] before I'm useless before somebody noticed. It [/INST] turns out pretty crappy because no one has any idea of what these molecules look like, Anything is better than nothing. And so I thought, how long will it take me to create? Better than nothing spectra for all of these molecules. So I create a rascal rapid approximate spectral calculations for all. Um and what I do is I use organic chemistry and quantum chemistry and kind of cheat and then both, I just try to figure out what is the fastest way I could run this and I simulate rough spectra for all of those 16,000. So I've managed to get it to work. It's really shocking how well it works considering how bad </s><s>[INST] it is. Their insights you could give to like the tricks involved in making it fast. Like what are the um maybe some insightful shortcuts taken that still results in some useful information about the spectrum. [/INST] The insights came from organic chemistry from decades ago when organic chemists wanted to know what a compound might be. They will look at a spectrum and see a feature and they would go, I've seen that feature before. That's usually what happens when you have a carbon triple bonded to another carbon. And they were mostly right. Almost every molecule that has a carbon triple bonded to another one looks like that has other features different that distinguish them from one another. But they have that that feature in common, we call these functional groups. And so most of that work ended up being abandoned because now we have mass spectrometry, we've got nuclear magnetic resonance spectroscopy, so people don't really need to do that anymore. But these ancient text books still exist and I've collected them all as many as I could. And there are hundreds of these descriptions where people have said, oh whenever you have a uh iodine atom connected to this one, there's always a feature here and it's usually quite sharp and it's quite strong and some people go, oh yeah, that's really broad feature every time that combination of atoms and bonds. So I've collected them all and I've created this giant dictionary of all these kind of puzzle pieces, these lego parts of molecules and I've written a code that then puts them all together in some kind of like Frankenstein's monster of molecules. So you asked me for any molecule and I go, well it has these bonds and this atom dangling off this atom and this cluster here and I tell you what it should look like and it kind of works. </s><s>[INST] So this creates a whole portfolio of just kind of signatures that we could look for but still useful enough to analyze the atmospheres. The telescope generated images of of other planets [/INST] close right now it is So complete. So it has all of these molecules that I can tell you say you look at an alien atmosphere and there's a feature there, it can tell you, oh, that feature that's familiar. It could be one of these 816 molecules. Best of luck. So I think the next step, which is what I'm working on, is telling you something more useful than it could be one of those 816 molecules. That's still true. I wouldn't say it's useful so I can tell you, but only 12% of them also have a feature in this region. So go look there and if there's nothing there, it can't be those. And so on. It can also tell you things like you will need this much accuracy to distinguish between those 816. So that's what I'm working on. But it's a lot of work. </s>

<s>[INST] Yeah, so that's a beautiful statement, but at the same time by moving the paddle, we also anthropomorphize flaws to inject into the system that will then flip how impressed we are by it. What I mean by that is to me, the entire games were to me deeply impressive that that was possible at all. So like after first pause on that and people should look at that just like the game of go, which is fundamentally different to me than um, then we're deep blue did, even though there is still no matter cause there's still tree search, it's just everything in Deepmind has done in terms of learning however limited it is still deeply surprising to me. [/INST] Yeah, I'm not, I'm not trying to say that what they did wasn't impressive. I think it was incredibly impressive </s><s>[INST] to me. It's interesting is moving the board. Just another, another thing that needs to be learned. So like we've been able to maybe maybe been able to through the current neural networks learn very basic concepts that are not enough to do this general reasoning and then maybe with more data. I mean the data that, you know, the interesting thing about the examples that you talk about beautifully is they often flaws of the data. Well [/INST] that's the question. I mean I I think that is the key question whether it's a flaw of the data or </s><s>[INST] not because because the the [/INST] reason I brought up this example was because you were asking do I think that you know, learning from data could go all the way and that this was why I brought up the example because I think um and this was is not at all to to take away from the impressive work that they did. But it's to say that when we look at what these systems learn could do they learn the human the things that we humans consider to be the relevant concepts and in that example it didn't sure if you train it on uh movie, you know the paddle being in different places, maybe it could deal with, maybe it would learn that concept. I'm not totally sure. But the question is you know scaling that up to more comp complicated worlds uh to what extent could a machine that only gets this very raw data learn to divide up the world into relevant concepts and I don't know the answer, but I would bet that that that without some innate notion that it can't do it. </s><s>[INST] Yeah, 10 years ago I 100% agree with you as the most experts in and I system, but now I have one like I have a glimmer of hope, you know, and I think I think that's what deep learning did in the community is known. I still, if I had to bet all my money it's 100% deep learning will not take us all the way, but there's still uh it's still, I was so personally sort of surprised by the tar games by go by by the power of self play of just game playing against that. I was like many other times just humbled of how little I know about what's possible. [/INST] Yeah, I think fair enough self play is amazingly powerful and you know, that's that goes way back to Arthur Samuel right with his checkers playing program and that, which was brilliant and surprising that it did so well. </s><s>[INST] So just for fun, let me uh ask in the topic of autonomous vehicles, it's the area that that I work at least these days most closely on. And it's also area that I think is a good example that you use is sort of an example of things. We, as humans don't always realize how hard it is to do. It's like the concentrated ai different problems that we think are easy when we first try them and then you realize how hard it is. Okay, so why you've talked about this a thomas driving being a difficult problem, more difficult than we realize humans give it credit for. Why is it so difficult. What are the most difficult parts in your view? [/INST] I think it's difficult because of the world is so open ended as to what kinds of things can happen. So you have sort of what normally happens, which is just you drive along and nothing, nothing surprising happens and autonomous vehicles can do the ones we have now evidently can do really well on most normal situations, as long as long as you know, the weather is reasonably good and everything. Um, but if some, we have this notion of educates or, or you know, things in the tail of the distribution called the long tail problem, which says that there's so many possible things that can happen that was not in the training data of the machine that it won't be able to handle it because it doesn't have common sense. </s><s>[INST] It's the old paddle moved. [/INST] Yeah, it's the paddle moved problem. Right. And so my understanding and you probably are more of an expert than I am on this. Is that current self driving car, vision systems have problems with obstacles, meaning that they don't know which obstacles which quote unquote obstacles they should stop for and which ones they shouldn't stop for. And so a lot of times I read that they tend to slam on the brakes quite a bit. And the most common accidents with self driving cars are people rear ending them because they were surprised they weren't expecting the machine, the car to stop. </s>

<s>[INST] when you look at when you take a bigger picture. Yeah. So, uh, the writing process, uh, is it fundamentally lonely. So, no, [/INST] because you're with your characters, </s><s>[INST] you are, so you really put yourself in the world [/INST] absolutely. You know, uh I've written about this before that I used to have my desk used to face a wall instead of seeing and people would say, well don't you want to look out the window, but I'm in here. I mean, I'm seeing, you know, the Spartans, I'm seeing, you know, whatever and The characters that are on the page or that you create are not accidents. You know, they're coming out of some issue, some deep issue that you have, whether you realize it or not, you might not realize until 20 years later or somebody explains it to you. So, your characters are kind of fascinating to you and their dilemmas are, are fascinating to you and you're also trying to to um come to grips with them, you know, you sort of see them through a glass darkly, you know, and you really want to see them more clearly. Um, so yeah, no, it's not lonely at all. In fact, I'm more lonely sometimes later, going out to dinner with some people and actually talking to people, </s><s>[INST] do you miss the characters after it's over? [/INST] Uh, let's say I have, I have affection for them, kind of like Children that have gone off to college and now are, you know, you only see him at thanksgiving. Uh definitely I have affection for him. Even the bad guys, maybe, </s><s>[INST] especially the bad guy, [/INST] especially the bad guys. </s><s>[INST] Uh you've said that writers, even successful writers are often not tough minded enough. I've read that in the post, that you have to be a professional in the way you handle your emotions. You have to be a bit of a warrior to be a writer. So what are, what do you think makes a warrior? Is that as a warrior born or trained in the realm, in the bigger realm, in the realm of writing, in the creative process? [/INST] I think, I think they're born to some extent you have the gift, like, you might have a gift as a martial artist to do whatever martial artists do, but the training is, is the big thing, 90% training 10% 10% genetics and uh you know, I use another analogy other than Warrior two as far as writers and it's like to be a mother, if you think about if you're a writer or any creative person giving birth to something that you're carrying a new life inside you and in terms of bravery, if you're child, your two year old child is underneath, a car is coming down the street, the mother's gonna like stop a buick, you know, with their bare hands. So that's a that's another way to think about how how a writer has to think about or any creative person has to think about, I think what they're what they're doing, what this this child, this new creation that they're bringing forth. </s><s>[INST] Yeah, so the hard work that's underlying that I've just a couple weeks ago talked to just happened to be in the same room, both gave talks Arianna Huffington, I did this conversation with her uh I didn't know much about her before then, but she has recently been short a couple of books have been promoting a lifestyle Where she basically she created a Huffington post and she gave herself like, I don't know, 20 hours a day, just obsessed with her work. And then she she fainted passed out and kind of uh there was some health issues and so she wrote this book saying that, you know, sleep basically you want to establish a lifestyle that doesn't sacrifice health, that's productive but doesn't sacrifice health. She thinks you can have both productivity and health criticizing Elon musk who have also spoken with for working too hard and thereby sacrificing, um you know, being less effective than he could be. So I'm trying to get this balance between health and obsessively working at something, I'm really working hard. So what Ariana is talking about, it makes sense to me, but I'm a little bit torn to me, passionate reason do not overlap much or at all sometimes, uh, maybe I'm being too Russian, but uh, I feel madness and obsession does not care for health or sleep or diet or any of that and hard work, it's hard work and everything else can go to house. So if you're really focused on whether it's writing a book and it should, everything should just go to hell. Uh where do you stand on this balance? How important is health for productivity? How important is it to sort of get sleep and so on? [/INST] I'm from on the, on the health side. Uh I mean, there was a period of my life when I was just uh uh had no obligations and I was just living in a little house and just working nonstop, you know, but even then I would get up in the morning and I would have liver and eggs for breakfast every day and I would do my, you know exercise whatever it was, but although I was still doing like, you know, 18 hours a day, but I I'm definitely, yeah, I kind of think of it sort of like an athlete does, I'm sure that like Steph curry um is totally committed to winning championships and stuff like that. But he has his family, he sees his fan, you know, family is always there. He I'm sure he eats, you know, perfect, great stuff, gets asleep, you know, gets the the train, you know, whatever a trainer does to him for his knees and his ankles and whatever. So I or Kobe Bryant or anybody that's uh it's operating at a high level. So I do think I'm from that kind of the health school, the good thing about being a writer is you can't work very many hours a day, you know, four hours is like the maximum I can work. I've never been able to work more than that. I don't know how people do it. I've heard of people do 10, 12, I don't know how they do it. So that gives you a lot of other time to </s>

<s>[INST] giant sort of ball of interesting ideas. There's probably a million of interesting ideas in there that individually could be explored effectively. [/INST] And to be clear, you should be interested in fundamental questions. I think that's a good habit to ask what the fundamentals of things are, but I think it takes a lot of steps to like, certainly you shouldn't be trying to answer that unless you actually understand quantum field theory and you actually understand general relativity. </s><s>[INST] That's the cool thing about like your videos, people haven't done mathematics. Like if you really give it time watching a couple of times and like try to try to reason about it, you can actually understand the concept that's being explained. [/INST] And it's not a coincidence that the things I'm describing aren't like the most up to date progress on the Riemann hypothesis cousins or um like there's context in which the analog of the room and hypothesis has been solved in like more uh discreet feeling finite settings that are more well behaved. I'm not describing that because it just takes a ton to get there and instead, I think It'll be like productive to have an actual understanding of something that you can pack into 20 minutes. </s><s>[INST] I think that's beautifully put ultimately. That's where like the most satisfying thing is when you really understand, um, yeah, really understand [/INST] build the habit of feeling what it's like to actually come to resolution. </s><s>[INST] Yeah. As opposed to which it can also be enjoyable, but just being in awe of the fact that you don't understand anything. [/INST] Yeah, that's not like, I don't know, maybe people get entertainment out of that, but </s><s>[INST] it's not as fulfilling as understanding. [/INST] You won't grow. </s><s>[INST] Yeah. And, but also just the fulfilling. It really does feel good when you first don't understand something and then you do. That's a beautiful feeling. Hey, let me ask you one last last time I got awkward and weird about a fear of mortality that you made fun of me of. But let me ask you on the, the other absurd question is, um, what do you think is the meaning of our life of meaning of life? [/INST] I'm sorry if I made fun of you about words. </s><s>[INST] No, you didn't. I'm just joking. It was great. [/INST] I don't think life has a meaning. I think like meaning, I don't understand the question. I think meaning is something that's described to stuff that's created with purpose. There's a meaning to like this water bottle label and that someone created it with the purpose of conveying meaning and there was one consciousness that wanted to get its ideas into another consciousness. Um, most things don't have that property. It's a little bit like if I ask you what is the height? </s><s>[INST] All right? So it's all relative, [/INST] You'd be like the height of what you can't ask. What is the height without an object? You can't ask what is the meaning of life without like an intent full consciousness putting it. I guess I'm revealing. I'm not very religious, </s><s>[INST] but you know, the mathematics of everything seems kind of beautiful. It seems like it seems like there's some kind of structure relative to which I mean, you could calculate the height [/INST] well. So, but what I'm saying is I don't understand the question, what is the meaning of life in that? I think people might be asking something very real. I don't understand what they're asking and asking why does life exist? How did it come about? What are the natural laws? Are they asking? Um, as I'm making decisions day by day for what should I do? What is the guiding light that inspires? Like, what should I do? I think that's what people are kind of asking, but </s><s>[INST] also like why the thing that gives you joy about education about mathematics? What the hell is that? Like, what [/INST] interactions with other people interactions with like minded people? I think is the meaning of in that sense </s><s>[INST] bringing others joy essentially? Like in something you've created, it connects with others somehow and the same in the vice versa. [/INST] I think that that is what when we use the word meaning to mean like you sort of filled with a sense of happiness and energy to create more things like I have so much meaning taken from this like that. Yeah, that's what fuels fuels my pump at least. </s><s>[INST] So life alone on a deserted island will be kind of meaningless. [/INST] You want to be alone together with someone. </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] I think there's an atrophy, a spiritual atrophy in that. For the sake of spiritual flourishing, this conversation too has come to an end. I think a beautiful way to end it. And I'm a huge fan of yours. Thank you for being a man with a life well-lived and for talking with me today. It's an honor, man. It was an awesome conversation. Thank you for having me on. Thanks for listening to this conversation with Ed Calderon. To support this podcast, please check out our sponsors in the description. And now, let me leave you with some words from Al Pacino's character in Scarface, Tony Montana. You don't have the guts to be what you want to be. You need people like me so you can point your fingers and say, that's the bad guy. Thanks for listening. [/INST] I hope to see you next time. I hope to see you next time. </s>

<s>[INST] So uh you're gonna Schmidt who will propose something called gato machines which is a self improving program that rewrites its own code. Well sort of mathematically philosophically. What's the relationship in your eyes if you're familiar with it between my ex and the good old machines? [/INST] Yeah, familiar with it. He developed it while I was in his lab. Yeah. So the girl machine uh explain it briefly. Um You give it a task. It could be a simple task. Is you know finding prime factors in numbers right? You can formally write it down there is a very slow album to do that. Just try all the factors. Yeah or play chess right optimally. You write the algorithm too many marks to the end of the game. So you write down what the google machine should do then it will take part of its resources to run this program and other part of resources to improve this program. And when it finds an improved version which provably computes the same answer, so that's the key part. It needs to prove by itself that this change of program still satisfies the original specification and if it does so then it replaces the original program by the improved program and by definition does the same job, but just faster. Okay. And then, you know, it proves over it and over it and it's developed in a way that um all parts of this girl machine can self improve, but it stays provably consistent with the original specification. So um from this perspective it has nothing to do with ICSI but if you would now put exile is the starting ax jumps in, it would run our CSI but you know, that takes forever. But then if it finds a provable speed up of ICSI, it would replace it by this and this and this and maybe eventually it comes up with a model which is still the ICSI model. It cannot be, I mean, just for the knowledgeable reader access in computable and I can prove that therefore there cannot be a computable exact um algorithm computers that needs to be some approximations and this is not dealt with the google machine. So you have to do something about it, but there's the ICSI T L. Model, which is finally computable, which we could put in </s><s>[INST] which part of X is uh non computable. [/INST] The Solomon of induction part </s><s>[INST] in action. Okay, so [/INST] but there's ways of getting computable approximations of the ICSI model. Um so then it's at least computable, it is still way beyond any resources anybody will ever have. But then the google machine could sort of improve it further and further in an exact </s><s>[INST] way. So this is this is theoretically possible that the girl machine process could improve. Isn't uh isn't uh isn't actually already optimal? [/INST] It is optimal in terms of the river collected over its interaction cycles, but it takes infinite time to produce one action and the world, you know, continues whether you want it or not. So the model is assuming had an oracle which you know, solve this problem and then in the next 100 milliseconds or direction time you need gives the answer. Then ice is optimal. So it's ultimately in sense of state are also from learning efficiency and um data efficiency but not in terms of computation time. </s><s>[INST] And then the other government sheen in theory but probably not provably could make it go faster. Yes. Okay, interesting. Those two components are super interesting. The sort of the perfect intelligence combined with uh self improvement sort of provable self improvement. Since they're always like you're always getting the correct answer and you're improving beautiful ideas. Okay, so you've also mentioned that different kinds of things in in the chase of solving this reward sort of optimizing for the goal, interesting human things can emerge. So is there a place for consciousness within a galaxy? What where does uh maybe you can comment? Because I I suppose we humans are just another extension nation by ex CIA agents and we seem to have consciousness. [/INST] You say humans are in sensation of an ice agent, so that would be amazing. But I think that it's not for the smartest and most rational humans. I think maybe they are very crude approximations </s><s>[INST] interesting. I mean I tend to believe again I'm Russian, so I tend to believe our flaws are part of the optimal so the we tend to laugh off and criticize our flaws and I tend to think that that's actually close to an optimal behavior. [/INST] But some flaws, if you think more carefully about it are actually not flaws. Yeah, but I think there are still enough flaws. </s><s>[INST] I don't know, it's unclear as a student of history, I think all the suffering that we've been endured as a civilization, it's possible that that's the optimal amount of suffering we need to endure to minimize the long term suffering. That's [/INST] that's your Russian </s><s>[INST] background. That's the Russian whether humans are or not instant creations of an ex CIA agent. Do you think there's uh consciousness is something that could emerge in the computational formal framework like ICSI [/INST] let me also ask your question, do you think I am conscious? </s><s>[INST] Uh yeah, that's a good question. Your that that tie is confusing me, but [/INST] I think I think that makes me unconscious because it strangles me or </s><s>[INST] if an agent were to solve the imitation game posed by touring, I think that would be dressed similarly to you that because there's uh there's a kind of flamboyant, interesting complex behavior pattern that sells that you're human and you're conscious. But why do you ask? [/INST] Was it a Yes, I was gonna know. Yes, I think I think you're </s><s>[INST] conscious. Yes, [/INST] Yeah. So and you explain sort of somehow why, but you infer that from my behavior, right? You can never be sure about that. And I think the same thing will happen with any intelligent, it can be developed if it behaves in a way sufficiently close to humans or maybe if not humans. I mean, you know, maybe a dog is also sometimes a little bit self conscious. Right? So, so if it behaves in a way where we attribute typically consciousness, we would attribute consciousness to these intelligent systems and you know, actually probably in particular that of course doesn't answer the question whether it's really conscious and that's the big, hard problem of consciousness. You know, maybe I'm zombie, I mean not the movie zombie, but the philosophical zombie </s>

<s>[INST] One of the most fascinating, what does Courant mean? Oh, nice. That's a nice word. [/INST] Oh, Courant. I'm probably mispronouncing it. But yeah. </s><s>[INST] We'll edit it in post. Sure, sure. So pronounce it correctly, with AI. We'll copy your voice and it will pronounce it perfectly correctly. Yeah. [/INST] In post, to pronounce it correctly, with AI. In post. One thing that I do think was interesting is Craig Venter a while back tried to make a minimum and viable cell, where he just tried to delete all of the genes that were that were not considered essential. And so it's like a new life form. And this was like almost 20 years ago, and so on. And that thing was a was viable in the lab, right. And so it's possible that you could you kind of reverse engineer so you're coming out the problem from different directions, like RNA molecules can do quite a lot. You've got some, you know, reasonable assumptions as to how that could come together. You've got like, sort of stripped down minimum viable life forms and so it's it's not there isn't stuff here, you can see micro evolution, you can see at the sequence level, you know, if you do molecular phylogenics, you can actually track back the basis, there's actually so it's not like there's no evidence, there's a lot of tools to work with. But this in my view, is a fascinating area, and actually, also relevant to AI, because another form of a bio genesis would be if we are able to give rise to a different branch of life form, the Silicon based as opposed to carbon based, you know, to stretch your point, you give rise to something that actually does meet the definition of life for some </s><s>[INST] definition of life. What do you think that definition is for an artificial life form? Because you mentioned consciousness. Yeah. When will it give us pause that we created something that feels by some definition or by some spiritual poetic romantic philosophical mathematical definition that it is alive. [/INST] Right. And we wouldn't want to kill it. So a couple of remarks on that. One is Francis Crick of Watson and Crick. Before he died, I think his last paper was published on something called the Klaustrum. Okay. And the thing is that, you know, sometimes in biology or in any, you know, domain, people are sort of discouraged from going after the big, the big questions. Right. But he proposed the Klaustrum is actually the organ that is the seat of consciousness. It's like this sheath that like covers the brain. And for mice, if you, and again, I may be recollecting this wrong. So, but you can look, but at my recollection is in mice, if you disrupt this, the mouse is like very disoriented, right? It's like, it's the kind of thing which, you know, Watson and Crick were all about structure implies function, right? They found the structure of DNA, this amazing thing. And, you know, they were marked in this very under understated way at the end of the paper that, well, obviously this gives a basis for how the genetic material might be replicated and error corrected because, you know, helix unwinds and you copy paste, right? So he was a big structure function person. And that applies not just at the protein level, not just at the level of DNA, potentially also at the level of organs, like the classroom is kind of this system integrated level, right? It's like the the last layer in the neural network or something, you know. And, and so that's, that's the kind of thing that I think is worth studying. So consciousness is another kind of big, a biogenesis, a big question, the prime number maze consciousness is a big question. And, you know, then definition of life, right? There's folks, gosh, there's I think, so this one is something I'd have to Google around, but there was a guy, I think at Santa Fe Institute or something who had some definition of life and like some thermodynamic definition. But you're right that it's going to be a multi feature definition. We might have a Turing test like definition, frankly, which is just if enough humans agree it's alive, it's alive, right? And that might frankly be the operational definition. Because, you know, viruses are like this boundary case, you know, are they are they alive or not? Most people don't think they're alive, but they're, they're, they're on, they're kind of, they're more alive than a rock, </s><s>[INST] in a sense. Well, I think in a world that we'll talk about today quite a bit, which is the digital world, I think the most fascinating philosophically and technically definition of life is life in the digital world. So chatbots, essentially creatures, whether they're replicas of humans or totally independent creations, perhaps in an automatic way, I think there's going to be chatbots that we would ethically be troubled by if we wanted to kill them. They would have the capacity to suffer. They would be very unhappy with you trying to turn them off. And then there will be large groups of activists that will protest and go to the Supreme Court of whatever the Supreme Court looks like in 10, 20, 30, 40 years. And they will demand that these chatbots would have the same rights as us humans. [/INST] Do you think that's possible? I saw that Google engineer who's basically saying this had already happened and I was surprised by it because it just, when I looked at the chat logs of it, it didn't seem particularly interesting. On their hand, I can definitely see it. I mean, GPT-3 for people who, you know, haven't paid attention shows that serious step ups are possible. And obviously, you know, you've talked about AI in your podcast a ton. Is it possible that GPT-9 or </s>

<s>[INST] If you own a business, try them out, schedule your free product tour at net suite dot com slash lex. That's N E T S U [/INST] I T E dot </s><s>[INST] com slash lex. This show is sponsored by Graham Early, a writing assistant tool, the check, spelling, grammar, sentence structure and readability grandma, lee premium the version you pay for offers a bunch of extra features. My favorite is the clarity check which helps detect rambling, overcomplicated chaos that many of us can descend into like this very thing that I wrote for myself. Most of these reeds, I go off the top of my head but some of them are right down. The parts I write down are even worse than the parts that go off the top of my head. I wish I had something like real time Graham early for spoken word. But in the medium of the written word, I truly value simplicity. I find simplicity to be just beautiful and so Graham early is a kind of nudge towards simplicity and clarity with the tools that their premium service provides. I recommended highly even if you don't agree with the suggestion makes Ultimately I think the debate with a suggested change will create a better written piece. Anyway, Graham Early is available on basically any platform in major sites and apps like gmail and twitter and so on. Do more than just spell check, say what you really mean with grandma lee premium get 20% off Graham early premium by signing up at Graham early dot com slash lux. That's 20% off at grandma lee dot com slash lex. This show is also sponsored by Express VPN. They put a layer of protection between you and powerful technology companies that control much of what we do online. The suggested talking points that Express VPN keeps sending me really make these like big tech companies into the enemy. I think we should definitely be skeptical, especially skeptical of the surveillance state, but I think these companies bring a lot of good too. But yes, it is good to have a layer of protection in terms of your data that said, I do think there's a lot of money to be made by companies to actually be transparent and actually give you control over your data. I think it's a win win and I have no idea why facebook is doing what it's doing, I have no idea why twitter is doing what he's doing. I think it was just the momentum of the past and hopefully we're going to see a pivot towards companies giving individual users more control over their data anyway, go to express VPN dot com slash flex pod to get an extra three months free. That's express VPN dot com slash like spot. This is the lex Friedman podcast and here is my conversation with brian johnson. [/INST] You ready lacks? Yes, I'm ready. I just want to come in and put the interfaces on our heads and then I will proceed to tell you a few jokes. </s><s>[INST] So we uh, we have two incredible pieces of technology and A machine running bond to 2004 in front of us. What are we doing? Alright. Are these going on our [/INST] heads? They're going on our heads. Yeah and they will place it on our heads for proper alignment. </s><s>[INST] Does this support giant heads because I kind of have a giant head is [/INST] as like an eagle or you staying physically both. Can we drop it on? Really? </s><s>[INST] It's a nice massage. Okay, how does it feel if you if it's okay to move around it feels Oh yeah, this feels awesome. [/INST] Thank you. That feels good. </s><s>[INST] So this is big head friendly [/INST] suits you well lex </s><s>[INST] thank you. I feel like I need to uh I feel like when I wear this and you just sound like Sam Harris, calm collected. Eloquent. I feel smarter actually. I don't think I've ever felt quite as much like I'm part of the future. Is now [/INST] have you ever worn a brain interface </s><s>[INST] or had your brain image? Oh, never had my brain imaged. The only way of analyzing my brain is by talking to myself and thinking no direct data. [/INST] Yeah, yeah, that is that is definitely a brain interface </s><s>[INST] that [/INST] has a lot of blind spots, </s><s>[INST] some blind spots. Yeah, psychotherapy, [/INST] that's right. All right. Are we recording? Forget. All right, select the objective of this. I'm going to tell you some jokes and your objective is to not smile, which has a Russian. You should have an edge. </s><s>[INST] Make the mother. I'm proud. I got you. Okay, let's hear the jokes [/INST] lex. And this is from the Colonel crew. We've been working on a device that can read your mind and we would love to see your thoughts. </s><s>[INST] Is that the joke? [/INST] That's the opening. Okay. If I'm if I'm seeing the muscle activation correctly on your, on your lips you're not going to do well on this. Let's see. Alright, here, here comes the first screwed. Here comes the first one </s><s>[INST] is going to break the device. Is it resilient to uh to laughter [/INST] lex what goes through a potatoes brain? </s><s>[INST] I already failed. That's the hilarious opener. Okay, what [/INST] tater thoughts. What kind of fish performed brain surgery? I don't know, a neurosurgeon. </s><s>[INST] Mhm. And so we're getting data of everything that's [/INST] happening in my brain right now. Lifetime. Yeah. We're getting activation patterns of your entire cortex. </s><s>[INST] I want to try to do better. I'll let it out all the parts where I left in Photoshop. You a serious [/INST] face over me, you can recover. Yeah. All right. Lex What do scholars eat when they're hungry? </s><s>[INST] I don't know what [/INST] academia nuts. </s><s>[INST] That was pretty good wine. [/INST] So what we'll do is so you're wearing Colonel Flow, which is an interface built using technology called spectroscopy. So it's similar to what we wear wearables on the wrist using light. So using light are as you know, and we're using that to image. It's a functional imaging of brain activity. And so as your neurons fire electrically and chemically. It creates blood oxygenation levels were measuring that. And so you'll see in the reconstructions we do for you. You'll see your activation patterns in your brain as throughout this entire time we were wearing it. So in the reaction to the jokes and as we were sitting here talking. So it's a we're moving towards a real time feed of your cortical brain activity. </s><s>[INST] So there's a bunch of things that are in contact with my skull right now. How many of them are there? And so how many of them are? What are they what are the actual sensors? [/INST] There's 52 modules and each module has one laser and six sensors. And they're the sensors fire uh about 100 PICO seconds and then the photons scatter and absorb in your brain. And if you go in if you come back out a bunch go in and if you come back out and we since those photons and then we do the reconstruction for the activity overall. There's about 1000 plus channels that are sampling your activity. </s><s>[INST] How difficult is it to make it as comfortable as it is because it's surprisingly comfortable. I would not think it would be comfortable. Something that's measuring brain activity. I would not think it would be comfortable. But it is. I agree. In fact I want to [/INST] take this home. Yeah. Yeah that's right. So people are accustomed to being in big systems like Fmri where there's 100 20 decibel sounds and you're in a and a claustrophobic encasement or E. G. Which is just painful or surgery. And so yes I agree that this is a convenient option to be able to just put on your head, it measures your brain activity in the contextual environment you choose. So if we want to have it during the podcast that we want to be at home in a business setting. So we its freedom to be where to record your brain activity in the setting that you choose. </s><s>[INST] Yeah, but sort of from an engineering perspective are these uh what is it? There's a bunch of different modular parts and they're kind of, there's like a rubber band thing where they mold to the shape of your head. [/INST] That's right. So we built this this version of the mechanical design to accommodate most adult heads, </s><s>[INST] but I have a giant head and if it's fine it feels fits well actually. So I don't think I have an average head. Okay, maybe I feel I feel much better about my head now, maybe I'm are more average than I thought. Okay, so what else is there interesting that you could say, well it's while it's on our heads, I can keep this on the whole time. This is kind of awesome. And it's amazing for me as a fan of avanti, I use a bunch of matt. You guys use that too, but it's amazing to have code running to the side measuring stuff and collecting data. I mean I just, I feel like much more important now that my data is being recorded, like somebody like you know when you have a good friend that listens to you that actually like listens like actually is listening to you, this is what I feel like I'm like a much better friend because it's like accurately listening to me do ponto. [/INST] What a cool perspective I hadn't thought about that of feeling understood, heard you heard deeply by the mechanical system that is recording your brain activity versus the human that you're engaging with. That your mind immediately goes to that there's this dimensionality and depth of understanding of this software system which you're intimately familiar with and now you're able to communicate with this system in ways that you couldn't before. </s><s>[INST] Yeah, I feel hard. I [/INST] mean I guess what's interesting about this is your intuitions are spot on. Most people have intuitions about brainer faces that they've grown up with this idea of people moving cursor on the screen or typing or changing the channel or skipping a song. It's primarily been anchored on control. And I think the more relevant understanding to bring interfaces and neural imaging is that it's a measurement system and once you have numbers for a given thing, a seemingly endless number of possibilities emerge around that of what to do with those numbers. </s><s>[INST] So before you tell me about the possibilities, this was an incredible experience, I can keep this on for another two hours but I'm being told that for a bunch of reasons just because we probably want to keep the data small and visualize it nicely for the final product, we want to cut this off and take this take this amazing helmet away from me. So brian thank you so much for this experience and let's uh let's continue without helmet lys. Alright, so that was an incredible experience. Uh Can you maybe speak to what kind of opportunities that opens up that stream of data? That rich stream of data from the brain [/INST] 1st? I'm curious what is your reaction? What what comes to mind when you put it on your head? What does it mean to you and what possibilities emerge and what significance might have. I'm curious where your orientation is at. </s><s>[INST] Well for me, I'm really excited by the possibility of various information about my body about my mind being converted into data. Such that data can be used to create products that make my life better. So that that to me is really exciting possibility. Even just like a Fitbit that measures I don't know some very basic measurements about your body is really cool but it's the bandwidth of information. The resolution of that information is very crude so it's not very interesting. The possibility of recording. I was just building a data set coming in a clean way and a high bandwidth way from my brain opens up all kinds of you know at the very I was kind of joking where we're talking but it's not really is like I feel heard in a sense that it feels like the full richness of the information coming from my mind is actually being recorded by the machine. I mean there's a I can't I can't quite put it into words, but there is genuinely for me there's not some kind of joke about me being a robot. It's just genuinely feels like I'm being heard in a way that that's going to improve my life as long as the thing that's on the other end can do something useful with that data. But even the recording itself is like once you record, it's like taking a picture that moment is forever saved in time. Now picture cannot allow you to step back into that world. But perhaps recording your brain is a much higher resolution thing, Much more personal recording of the information that a picture that would allow you to step back into that uh where you were in that particular moment in history and then map out a certain trajectory to tell you certain things about uh about yourself. That could open up all kinds of applications. Of course there's health that I consider. But honestly to me, the exciting thing is just being heard. My state of mind, the level of focus, all those kinds of things being heard. [/INST] What I heard you say is you have an entirety of lived experience, some of which you can communicate in words and in body language, some of which you feel internally, which cannot be captured in those communication modalities and that this measurement system Captures both. The things you can try to articulate in words maybe in a lower dimensional space. Using one word for example, to communicate focus when it really may be represented in a 20 dimensional space of this particular kind of focus and that this information is being captured. So it's a closer representation to the entirety of your experience captured in a dynamic fashion. That is not just a static image of your conscious experience. </s><s>[INST] Yeah, that's that's that's the promise. That's the hope. That was the feeling and it felt like the future. So it's a pretty cool experience and from the sort of mechanical perspective it was cool to have an actual device that feels pretty good. That doesn't uh doesn't require me to go into the lab. And also the other thing I was I was feeling there's a guy named danger Huberman is a friend of mine, amazing podcast. People should uh should listen to a human lab podcast. We're working on a paper together about eye movement and so on and we're kind of, he's a neuroscientist and I'm a data person when she learning person or we're both excited by how much the that how much the data measurements of the human mind and the brain and all the different metrics that come from that could be used to understand human beings and in a rigorous scientific way. So the other thing I was thinking about is how this could be turned into a tool for science sort of not just personal science not just like Fitbit style. Like how am I doing my personal metrics of health but doing larger scale studies of human behavior and so on. So like data not at the scale of an individual but day to the scale of many individuals with a large number of individuals. So so it's personal being heard was exciting. And also just for science is exciting. It's very easy like like that there's a very powerful thing to it being so easy to just put on that. You can scale much easier [/INST] if you think about that second thing you said about the science of the brain most we've done a pretty good job like we the human race has done a pretty good job figuring out how to quantify the things around us from distant stars to calories and steps and our genome so we can measure and quantify pretty much everything in the known universe except for our minds and we can do these one offs if we're going to get enough MRI scan or uh huh do something with the low rez E. G system but we haven't done this at population scale. And so if you think about human thought or human cognition is probably the single law largest raw input material into society at any given moment. It's our conversations with our with ourselves and with other people and we have this this raw input that we can't I haven't been able to measure yet and if you when I think about it through that frame it's remarkable. It's almost like we live in this wild Wild West oven quantified communications within ourselves and between each other when everything else has been grounded me. For example, I know if I buy an appliance at the at the store or on a website I don't need to look at the measurements on the appliance and make sure it can fit through my door. That's an engineered system of appliance, manufacturing and construction. Everyone's agreed upon engineering standards and we don't have engineering standards around cognition is not has not entered as a formal engineering discipline that enables us to scaffold in society with everything else we're doing including consuming news, our relationships, politics, economics, education all the above. And so to me that the most significant contribution that Colonel technology has to offer would be the formal scott the introduction of the formal engineering of cognition as it relates to everything else in society. </s><s>[INST] I love that idea that you kind of think that there is just this ocean of data that's coming from people's brains as being in a crude way of reduced down to like tweets and texts and so on. It's a very hard core, many scale compression of actual the raw data but maybe you can comment because you usually work cognition? I think the first step is to get the brain data but is there a leap to be taking to sort of interpreting that data in terms of cognition. So is your is your idea is basically you need to start collecting data at scale from the brain and then we start to really be able to take little steps along the path to actually measuring some deep sense of cognition because it's, you know, as I'm sure, you know, we don't, we understand a few things but we don't understand most of what makes up cognition. [/INST] This has been one of the most significant challenges of building Colonel and Colonel wouldn't exist if I wasn't able to fund it initially about myself because when I engage in conversations with investors, the immediate thought is what is the killer app. And of course I understand that heuristic, that's what they're looking at is they're looking to de risk is the product solve? Is there a customer base? Are people willing to pay for it? How does it compare to competing options? And in the case with Brainer faces, when I started the company, there was no known path to even build a technology that could potentially become mainstream. And then once we figure out the technology, We could even, we could commence having conversations with investors and it became what is the killer app. And so what has been uh, so I I funded the 1st $53 million 228 investors. One said yes, it was remarkable and it was mostly around this concept around what is a killer app. And so internally the way we think about it is we think of the </s><s>[INST] the go to market strategy much more [/INST] like the drake equation where if we can build technology that has the characteristics of it has the data quality is high enough. It meets some certain threshold cost, accessibility, comfort, it can be worn in contextual environments. If it meets the criteria of being a mass market device, then the responsibility that we have is to figure out how to create the algorithm that enables the human to enable humans to find value with it. So it's so the analogy is like brainer faces are like early 90s of the Internet is you you want to populate an ecosystem with a certain number of devices. You want a certain number of people who play around with them who do experiments of certain data collection parameters. You want to encourage certain mistakes from experts and non experts. These are all critical elements that ignite. Discovery. And so you we believe we've accomplished the first objective of building technology that reaches those thresholds. And now it's the drake equation component of how do we try to generate 20 years of value discovery in a two or three year time period. How do we compress that? </s><s>[INST] So just to clarify? So when you mean the drake equation which for people who don't know, I don't know why you, if you listen to this, I bring up aliens every single conversation, so I don't know how you wouldn't know what the drake equation is. But you mean like the killer app, it would be one alien civilization that equation. So meaning like this is in search of an application that impact transformative, by the way it should be. We need to come up with a better term than killer app as a it's also [/INST] violent, right? </s><s>[INST] You can go like viral app. That's horrible to write some very uh inspiring lee impactful application. How about that? Okay, so let's stick with killer app. That's fine. Nobody's I concur [/INST] with you. I dislike the chosen words in capturing the concept. </s><s>[INST] You know, it's one of those sticky things that is as effective to use in the tech world. But when you now become a communicator outside of the tech world, especially when you're talking about software and hardware and artificial intelligence applications, it sounds for, [/INST] you know, it's interesting. I actually regret now having called attention cause I regret having used that word in this conversation because it's something I would not normally do. I used it in order to create a bridge of shared understanding of how others would, what terminology others would use. </s><s>[INST] Yeah, but yeah, I concur let's go with impactful application [/INST] or the value creation? </s><s>[INST] Value creation something people love using? There we go, that's it love app. Okay, so what do you have any idea? So you're basically creating a framework where there's a the possibility of a discovery of uh an application that people love using is they have ideas. [/INST] We began to play a fun game internally where when we have these discussions we begin sir circling around this concept of does anybody have an idea? Does anyone have intuitions? And if we see the conversation starting to veer in that direction we flag it and say human intuition alert, stop it. And so we really want to focus on the algorithm of there's a natural process of human discovery that that when you populate a system with devices and you give people the opportunity to play around with it and expected and unexpected ways we are thinking that is a much better system of discovery than us, exercising tuitions And it's interesting we're also seeing a funeral scientists who have been, have been talking to us while speaking just one young associate professor and I approached a conversation and said hey we have these five data streams that were pulling off when you hear that, what weighted value do you add each data source? Like which one do you think is going to be valuable for your objectives and which ones not. And he said I don't care, just give me the data. All I care about is my machine learning model but importantly he did not have a theory of mind, he did not come to the table and say I think the brain operates, you know, in this way and these reasons we have these functions, he didn't care, he just wanted the data and we're seeing that more and more that certain people are devaluing human intuitions for good reasons as we've seen in machine learning over over the past couple years and we're doing the same in our value creation market </s><s>[INST] charging, so more collect more data, clean data, make the products such that the collection of data is easy and and and fun and then the rest will just spring to life through humans. Playing around with [/INST] the objective is to create the most valuable data collection system of the brain ever and with that then applying all the best tools of machine learning and other techniques to extract out, you know, to try to find insight. But yes, our objective is really to systematize the discovery process because we we can't put definite timeframes on discovery, the brain is complicated and science is not a business strategy and so we really need to figure out how to, this is the difficulty of bringing bringing you know technology like this to market, that's why most of time, it just link it languishes in academic academic for quite some time, but we hope that we will over cross over and make this mainstream in the coming years? </s><s>[INST] The thing was cool to wear but what are you chasing a good reason for millions of people to put this on their head and keep on their head regularly? Is there like who's going to discover that reason? Is it going to be people just kind of organically or is there going to be uh angry birds style application? That's just too exciting to not use [/INST] if I think through the things that have changed my life most significantly over the past few years when I started wearing a wearable in my wrist, that would give me data about my heart rate, heart rate, variability, respiration rate, ah metabolic approximations etcetera. For the first time in my life I had access to information sleep patterns that were highly impactful. They told me for example, if I eat close to bedtime, I'm not going to get deep sleep and not getting deep sleep means you have all these following consequences in life. And so it opened up this window of understanding of myself that I cannot self introspect and deduce these things. This is information that was available to be acquired. But it just wasn't, I would have to get expensive sleep study that it's an end like one night and that's not good enough to run all my trials. And so if you look just at the information that one can acquire on their wrist and now you're planning to the entire cortex in the brain and you say, what kind of information could we acquire? It opens up a whole new universe of possibilities. For example, we did this internal study at Colonel where I wore a prototype device and we were measuring the cognitive effects of sleep. So I had a device measuring my sleep. I performed with 13 of my coworkers. We perform four cognitive tasks over 13 sessions and we focused on reaction time, impulse control, uh short term memory and then arresting state task. And we with mine, we found for example, that my impulse control, it was independently correlated with my sleep outside of behavioral measures of my ability to play the game. The point of the study was I had the brain study eidetic. Colonel confirmed my life experience that if I my deep sleep determined whether or not I would be able to resist temptation the following day. And my brain didn't show that as one example. And so if you start thinking, if you actually have data on yourself on your entire cortex, you can control the settings. I think there's probably an a large number of things that we could discover about ourselves. Very, very small and very, very big. Just for example, like when you read news, what's going on? </s><s>[INST] Like when you use social media, when you use news, like uh all the ways we allocate attention. That's right with the computer. I mean that seems like a compelling place to where you would want to put on uh Colonel, whether what is it called Colonel flux Colonel, Like what [/INST] flow? We have two technologies, you're flow flow. </s><s>[INST] Okay, so when you when you put on the kernel flow, it is seems like to be um compelling time and place to do. It is when you're behind the desk behind a computer, you could probably work for prolonged periods of time as you're as you're taking in content and there could a lot of, because some of our so much of our lives happens in the digital world. Now, that kind of coupling the information about the human mind with the consumption and the behaviors in the digital world might give us a lot of information about the effects of the way we behave and navigate the digital world to the actual physical meet space, uh effects on our body. It's interesting to think in terms of both. Like for work, I'm a big fan of uh cal Newport has ideas of deep work that I spent uh with few exceptions, I try to spend the first two hours of every day. Usually if I'm like at home and have nothing on my schedule is going to be up to eight hours of deep work of focus, zero distraction. And for me to analyze the I mean I'm very aware of the uh the waning of that. The ups and downs of that and it's almost like you're surfing the ups and downs of that as you're doing programming as you're doing. Thinking about particular problems, you're trying to visualize things in your mind. You're trying to stitch them together. You're trying to uh when there's a dead end about an idea, you have to kind of calmly like walk back and start again all those kinds of processes. It would be interesting to get data on my mind is actually doing. And also recently started doing um I just talked to Sam Harris a few days ago and been building up to that. I started using started meditating using his app. Waking up very much recommend it and be interesting to get data on that because it's you're very it's like you're removing all the noise from your head and you very much it's an active process of active noise removal, active noise canceling headphones. And it would be interesting to see what is going on in the mind before the meditation during it and after all those kinds of things [/INST] and all of your examples. It's interesting that everyone who has designed an experience for you. So whether it be the meditation app or the deep work or all the things you mentioned, they constructed this product with a certain number of knowns. Yeah. Now what if we expanded the number of knowns by 10 X or 20 x 30 X. They would reconstruct their product, we'll incorporate those known. So it be and so this is the dimensionality that I think is the promising aspect is people will be able to use this quantification. Use this information to build more effective products. And this is I'm not talking about better products to advertise to you or manipulate you. I'm talking about our focus is helping people individuals have this contextual awareness and quantification and then to engage with others who are seeking to improve people's lives that the objective is, its betterment across ourselves, individually and also with each other. </s><s>[INST] So it's a nice data stream to have. If you're building an app, like if you're building a podcast listening app, it would be nice to know data about the listener so that like if you're bored or you fell asleep, maybe pause the podcast. It's like really dumb, just very simple applications that could just improve the quality of the experience of using the app. [/INST] I'm imagining if you have you have your neural um this is lex and you there's a statistical representation of you and you engage with the app and it says lex your best to engage with this meditation exercise in the following settings at this time of day after eating this kind of food or not eating fasting with this level of blood glucose and this kind of night sleep. But all these data combined to give you this contextually relevant experience, just like we do with our sleep, you've optimized your entire life based upon what information you can acquire and know about yourself. And so the question is, how much do we really know of the things going around us and I would venture to guess in my own my life life experience. I capture my self awareness, captures an extremely small percent of the things that actually influenced my conscious and unconscious experience. </s><s>[INST] Well in some sense, the data would help encourage you to be more self aware, not just because you trust everything the data saying, but is it will give you a prod to start investigating. Like I would love to get a like a rating like a ranking of all the things I do and what are the things It's probably important to do without the data, but the data will certainly help is like rank all the things you do in life and which ones make you feel shitty, which must make you feel good. Like you're talking about evening brian like this. It's a good example of somebody like I do pig out at night as well and uh never [/INST] make like you're in a safe </s><s>[INST] space. Is this is the same. It's never no, I I definitely have much less self control at night. It's interesting and the same. You know, people might criticize this, but I know my own body, I know when I eat carnivore, just eat meat, I feel much better uh than if I eat more more carbs, the more carbs I eat the worse I feel. I don't know why that is, I don't, there is science supporting, but I'm not leading on science. I'm leaning on personal experience that's really important. I don't need to read. I'm not gonna go in the whole rant about nutrition science. But many of those studies are very flawed. They're doing their best. But nutrition science is a very difficult field of the study because humans are so different and the mind has so much impact on the way your body behaves and it's so difficult from a scientific perspective to conduct really strong studies that you have to be almost like a scientist of an inch of one have to do these studies and yourself. That's the best way to understand what works for you or not. And I don't understand why because it sounds unhealthy but eating only meat always makes me feel good. Just mean that's it. And uh I don't have any allergies and you know that kind of stuff. I'm not full like Jordan Peterson where like if he like deviates a little bit that he goes off like deviate a little bit from the carnivore diet. He goes off like the cliff. No, I can I can have like chuck, I can I can go off the diet. I feel fine. It's a it's a gradual uh it's a gradual worsening of how I feel. But what he only meet, I feel great and it'll be nice to be reminded of that. There's a very simple fact that I feel good when I eat carnivore and I think that repeats itself in all kinds of experiences, like I feel really good uh when I exercise not, I hate exercise okay. But in the rest of the day the the impact it has on my mind and the clarity of mind and the experiences and the happiness and all those kinds of things. I feel really good. And to be able to concretely expressed that through data would be nice. It would be a nice reminder. Almost like a statement like remember what feels good and what not. And there could be things like uh that I'm not many things like you're suggesting that I could not be aware of, there might be sitting right in front of me. That makes me feel really good and makes me feel not good. And the data would show that [/INST] I agree with you. I've actually Employed the same strategy. I fired my mind entirely from being responsible for constructing my diet. So I started doing a program where I now track over 200 biomarkers every 90 days and it captures of course the things you would expect that cholesterol, but also DNA methylation and all kinds of things about my body, all the processes that make up me. And then I let that data generate the shopping list. Uh huh. And so I never actually ask my mind what it wants. It's entirely what my body is reporting that it wants. And so I call this goal alignment within Brian and there's 200 plus actors that I'm currently asking their opinion of. And so I'm asking my liver, how are you doing? And it's expressing via the biomarkers. And so then I construct that diet and I only eat those foods until my next testing round. And that has changed my life more than I think anything else because in the demotion of my conscious mind that I gave primacy to my entire life, it led me astray because like you're saying the mind then goes out into the world and it navigates the dozens of different dietary regimens people put together in books and it all has there. I'll have their supporting science in certain contextual settings, but it's not the end of one. And like you're saying this dietary really is an end of one. These what people have published scientifically of course can be used for nice groundings, but it changes when you should end up one level. And so that's what gets me excited about brainer faces is if you if I could do the same thing for my brain where I can stop asking my conscious mind for its advice or for its decision making, which is flawed. And I'd rather just look at this data that and I've never had better health markers in my life than when I stopped actually asking myself to be in charge of it and </s><s>[INST] the idea of demotion of the conscious mind is uh it's such a sort of engineering way of phrasing like meditation with what that's what we're doing, right? Yeah, that's beautiful. That means really beautifully put. Uh by the way testing round what does that look like? What's that? Well you mentioned uh [/INST] yeah that the very the test I do so includes a complete blood panel, do a microbiome test, I do a food inflammation, a diet induced inflammation. So I look for saddle kind expressions. So foods that produce inflammatory reactions. I look at my neuro endocrine systems. I look at all my neurotransmitters. Uh I do yeah there's several micronutrient test to see how I'm looking at the various nutrients. </s><s>[INST] What about like self report of like how you feel, you know almost like uh you can't demote your you still exist within your conscious mind, right? So that that lived experience of is a lot of values. You measure [/INST] that, do a temporal sampling over some duration of time. So I'll think through how I feel over a week, over a month over three months. I don't do a temporal sampling of if I'm at the grocery store in front of a cereal box and be like you know what Captain crunch is probably the right thing for me today because I'm feeling like I need a little fun in my life. And so it's a temporal sampling. If the data sets large enough then I smooth out the function of my natural oscillations of how I feel about life where some days I maybe feel upset or depressed or down or whatever and I don't want those moments to then rule my decision making. That's why The demotion happens. And it says really if you're looking at health of a 90 day period of time, All my 200 voices speak up on that interval and they're all given voice to say this is how I'm doing and this is what I want. And so it really is an accounting system for everybody. So that's why I think that if you think about the future of being human, there's two things I think that are really going on. one is the design manufacturing and distribution of intelligence Is heading towards zero gonna cost curve over over a certain design over a certain time frame. But our ability to, you know, evolution produced us an intelligent, the form of intelligence. We are now designing our own intelligence systems And the design, manufacturing distribution of that intelligence over a certain time frame is going to go to a cost of zero </s><s>[INST] design manufacture, distribution of intelligent cost is going to zero again, just give me a second. That's brilliant. Okay, an evolution is doing the design manufacturing distribution of intelligence and now we are doing the design manufacturing distribution of intelligence and the cost of that is going to zero. That's a very uh nice way of looking at life on earth. [/INST] So if that that's going on. And then now in parallel to that, then you say, okay, what what then happens if when that cost curve is heading 20, our existence becomes a goal alignment problem ago alignment function. And so the same thing I'm doing where I'm doing go alignment within myself of these 200 biomarkers where I'm saying when when brian exists on a daily basis and this entity is deciding what to eat what to do and etcetera, it's not just my conscious mind which is opening its 200 biological processes and there's a whole bunch of more voices involved. So in that equation we're going to increasingly automate the things that we spend high energy on today. It's easier. And now we're going to then negotiate the terms and conditions of intelligent life. Now we say conscious existence because we're biased because that's what we have. But it will be the largest computational exercise in history because you're now doing go alignment with planet Earth, within yourself, with each other. Within all the intelligence agents were building boats and other voice assistants. You basically have to have a trillions and trillions of agents working on the negotiation of goal alignment. </s><s>[INST] Yeah, this this is in fact true. Uh What was the second thing [/INST] that was it? So the cost design, manufacturing distribution of intelligence going to zero, which then means what's really going on? What are we really doing? We're negotiating the terms and conditions of existence. </s><s>[INST] Do you worry about the survival of this process? Mhm. That life as we know what on earth comes to an end or at least intelligent life. That as the cost goes to zero. Uh Something happens where all of that intelligence is thrown in the trash by something like nuclear war or development of AGI systems that are very dumb. Not A G I guess, but a isIS, that's the paperclip thing, what unmasked is dumb but has unintended consequences to where destroys human civilization. Do you worry about those kinds of things? I [/INST] mean it's it's unsurprising that a new thing comes into the sphere of human consciousness. Humans identify the foreign object in this case artificial intelligence, our amygdala fires up and says scary foreign, we should be apprehensive about this. And so it makes sense from a biological perspective of humans. For the the knee jerk reaction is fear. What I don't think has been properly weighted with that is that we are the first generation of intelligent beings on this earth that has been able to look out over their expected lifetime and see there is a real possibility of evolving into entirely novel forms of consciousness. Yeah, so different that it would be totally unrecognizable to us today. We don't have words for it, we can't hint at it, we can't point at it, we can't you can't look in the sky and to see that thing that is shining? We're gonna go up there. You you cannot even create an aspirational statement about it. And instead we've had this knee jerk reaction of fear about everything that could go wrong. But in my estimation, this should be the defining aspiration of all intelligent life on earth that that we would aspire that basically every generation surveys the landscape of possibilities that afforded given the technological, cultural and other contextual situation that they're in. We're in this context. We haven't yet identified this and said, this is unbelievable. We should carefully think this thing through not just of mitigating the things will wipe us out like we have this potential. And so we just haven't given voice to it even though it's within the realm of possibilities. </s><s>[INST] So you're excited about the possibility of super intelligence systems and what the opportunities that bring. I mean, these parallels to this. You think about people before the internet as the internet was coming to life. I mean there's kind of a fog through what you can't see, what does the future look like predicting collective intelligence, which I don't think we're understanding that we're living through that now is that there is now with with in some sense stopped being individual intelligences and become much more like collective intelligences because ideas travel much much faster now and they can in a viral way, like sweep across the populations. And so it's almost I mean it almost feels like a thought is had by many people know thousands or millions of people as opposed to an individual person. And that's changed everything. But to me, I think we're realizing how much that actually changed people or societies, but like to predict that before the internet would have been very difficult. And in that same way we're sitting here with the fog before us thinking what is uh super intelligence systems, how is that going to change the world? What is uh, increasing the band with like, um, plugging our brains into this whole thing? How is that going to change the world? And it seems like, uh, it's a fog, you don't know? And it could be, it could, uh, whatever comes to be, could destroy the world that we could be the last generation. But it also could transform in in ways that creates a, an incredibly fulfilling life experience that's unlike anything we've ever experienced, it might involve dissolution of ego and consciousness and so on. You're no longer one individual, it might be more, you know, that might be a certain kind of death and ego, death. But the experience might be really exciting and enriching maybe we'll live in a virtually like, it's like, it's funny to think about a bunch of sort of hypothetical questions of, would it be more fulfilling to live in a virtual world? Like if you were able to plug your brain in a very dense way into a video game, which world would you want to live in in the video game or in the physical world. For most of us, we kind of touring with the idea of the video game, but we still want to live in the physical world, have friendships and relationships in the physical world, but we don't know that again, it's a fog and maybe maybe in 100 years we're all living inside a video game, Hopefully not Call of Duty, hopefully more like, like Sims five, which which version is it on for you individually though? Does it make you sad that your brain ends That you die one day very soon? That the whole thing that that that that data source just goes offline sooner than you would like. [/INST] That's a complicated question, I would have answered it differently In different times in my life, I, you know, had chronic depression for 10 years. And so in that 10 year time period I desperately wanted lights to be off. And the thing that made it even worse is I was in a religious, I was born into a religion. It was the only reality I ever understood. And it's difficult to articulate to people when you're born into that kind of reality. And it's the only reality you're exposed to. You are literally blinded to the existence of other realities because it's so much the in group out group thing. And so in that situation, it was not only that I desperately wanted lights out forever, it was that I couldn't have lights out forever. It was there was an afterlife and this afterlife. Had this system that would either penalize or or reward you for your behaviors. And so it's almost like this is indescribable hopelessness of not only being in hopeless despair of not wanting to exist, but they're also being forced to be to exist. And so there was the duration of my time of the creation of life and say, yes, I have no remorse for lights being out and actually wanted more than anything in the entire world. There are other times where I'm looking out at the future and I say, this is an opportunity for future evolving, human conscious experience that is beyond my ability, understand. And, and I jump out of bed and I raced to work and I can't think about anything else. But I I think the the reality for me is I don't know what it's like to be in your head, but in my head when I wake up in the morning, I don't say Good morning Brian, I'm so happy to see you. Like, I'm sure you're just going to be beautiful to me today. You're not going to make a huge long list of everything you should be anxious about. You're not gonna repeat that list to me 400 times. You're not going to have me relive all the regrets I've made in life. I'm sure you're not doing any of that. You're just going to just help me along all day long. I mean, it's a brutal environment in my brain and we've just become normalized to this environment that we just accept that this is what it means to be human. But if we look at it, if we try to muster as much soberness as we can about the realities of being human, it's brutal if it is for me. And so am I sad that the brain may be off one day? You know, it depends on the contextual setting like how am I, what moment are you asking me that? And that's it's my mind is so fickle and this is why again, I don't trust my conscious mind. I have been given realities. I was given a religious reality that was a video game. And then I figured out it was not a real reality. And then I lived in a depressive reality which delivered this terrible hopelessness. That wasn't a real reality that I discovered Behavoural psychology. And I figured out how biased 188 chronicle biases and how my brain is distorting reality at the time. I have gone from one reality to another. I don't trust reality. I don't trust realities are given to me. And so to make try to make a decision on what I value or not value that future state. I don't trust my response. </s><s>[INST] So not fully, not fully listening to the conscious mind at any one moment as the ultimate truth, but allowing you to go up and down as it does. It's kind of being observing it. [/INST] Yes, I assume that whatever my conscious mind delivers up to my awareness is wrong on upon landing, and I just need to figure out where it's wrong, how it's wrong, how wrong it is, and then try to correct for it as best I can. But I assume that on impact, it's mistaken in some critical ways. </s><s>[INST] Is there something you can say by way of advice when the mind is depressive, when the conscious mind serves up something that uh you know, the dark thoughts, how you deal with that by calling your own life, you've overcome that, and others who are experiencing that you can overcome it. [/INST] Two things one that those depressive states are biochemical states, it's not you. And the suggestions that these things that the state delivers to you about suggestion of the hopelessness of lives or or the meaninglessness of it, or that you should hit the eject button. That's a false reality. Yeah. And that it's when I I completely understand the rational decision to commit suicide there, it is not lost on me at all, that that is and that is an international situation. But the key is when you're in that situation of those thoughts are landing to be able to say, thank you, you're not real. I know you're not real. And so I'm in a situation where, for whatever reason, I'm having this this uh neurochemical state, but that state can be altered. And so it again, it goes back to the realities of the difficulties of being human. And like when I was trying to solve my depression, I tried literally, if you name it, I tried it systematically and nothing would fix it. And so this is what gives me hope with brainer faces. For example. Like could I have numbers on my brain, Can I see what's going on? Because I go to the doctor, it's like how do you feel? I don't know, terrible. Like on a scale of 1 to 10 to have that you want to commit suicide 10? Like, </s><s>[INST] okay, at [/INST] this moment here, here's his bottle how much I take. I don't know, like just </s><s>[INST] yeah, it's very, very crude. And this data opens up the the yeah, it opens up the possibility of really helping in those dark moments to first understand the ways of the ups and downs the most document was on the complete flip side of that. Yeah, I am very conscious in my own brain and deeply, deeply grateful that what they're it's it's almost like a chemistry thing, a biochemistry thing that I go many times throughout the day. I'll look at like this cup and I'll be overcome with joy how amazing it is to be alive. Like I actually think I'm my biochemistry is such that it's not as common. Like I've talked to people and I don't think that's that common. Like it's a it's not a rational thing at all. It's like I feel like I'm on drugs and I'll just be like whoa a lot of people talk about like the meditative experience will allow you to sort of, you know, look at some basic things like the movement of your hand as deeply joyful because it's like that's life. But I get that from just looking at a cup, like I'm waiting for the coffee to brew and I'll just be like fuck life is awesome and I'll sometimes tweet that, but then I'll regret it later. Like goddammit, you're so ridiculous. But yeah, so but that is purely chemistry, like there's no rational, it doesn't fit with the rest of my life. I have all this ship, I'm always late to stuff, I'm always like there's all stuff, you know, I'm super self critical, like really self critical about everything I do almost. To the point I almost hate everything I do. But there's this engine of joy for life outside of all that and that has to be chemistry and the flip side of that is what depression probably is is the opposite of that feeling of like because I I bet you that feeling of the cup being amazing, it would save anybody in a state of depression like that that would be like fresh, you're in a desert and it's a, it's a drink of water Ah shit man, the brain is a, it would be nice to understand where that's coming from, to be able to, to understand how you hit those lows and those highs that have nothing to do with the actual reality. It has to do with some very specific aspects of how you maybe see the world. Maybe it could be just like basic habits you engage in and then how to walk along the line to find those experiences of joy. [/INST] And this goes back to the discussion we're having of human cognition is in volume the largest input of raw material into society. Yeah, and it's not quantified, we have no bearings on it. And so we just, you wonder we both articulated some of the challenges we have in our own mind and it's likely that others would say I have something similar and you wonder when you look at society, what how does that contribute to all the other compounded problems that we're experiencing? How does that blind us to the opportunities we could be looking at. And so it really it has this potential distortion effect on reality that just makes everything worse. And I hope if we can put some, if we can assign some numbers to these things just to get our bearings. So we're aware of what's going on, if we could find greater stabilization in how we conduct our lives and how we build society. It might be the thing that enables us to scaffold because we've really again we've done a human have done a fantastic job systematically scaffolding technology and science institutions. It's human these are our own selves which we have not been able to scaffold. It's it's we are the we are the one part of this intelligence infrastructure that remains unchanged. </s><s>[INST] Is there something you can say about coupling this brain data with not just the basic human experience but say an experience you mentioned sleep but the wildest experience which is psychedelics. Is there uh And there's been quite a few studies now that are being um approved and run which is exciting from a scientific perspective on psychedelics. Do you think? What do you think happens to the brain and psychedelics and how can data about this help us understand it? And uh when you're on D. M. T. D. C. L. S. And can we get can we convert into uh into data? Um [/INST] Can you add aliens in there? </s><s>[INST] Yeah aliens definitely. Do you actually meet aliens? And elves are elves aliens? I'm asking for uh for a few Austin friends yet that they are convinced that they've actually met the elves? [/INST] What it was like are they friendly? </s><s>[INST] Are they are they [/INST] like the smurfs are like they're like they're industrious and they have different skill sets and </s><s>[INST] the. Yeah I think they're very uh they're very critical as friends. It's the [/INST] trolls troll. </s><s>[INST] No but they care about you. So there's a bunch of different version of trolls. There's a loving trolls that are harsh on you but they want you to be better. And there's trolls that just enjoy the your destruction. And I think they're the ones that care for you. Like I I think their criticism from I. C. I'm talking I haven't met him directly. I'm it's like a friend of a friend [/INST] and I'm a telephone. </s><s>[INST] Yeah a bit of and and the whole point is that on psychedelics and certainly I D. M. T. Were this is where the brain data versus war data fails which is you know words can't convey the experience most people that you can be poetic and so on but it really does not convey the experience of what it actually means to meet the two meet the house. [/INST] I mean to me what baselines this conversation is imagine if you if we were interested in the health of your heart. And we started and said okay lex self introspect. Tell me how's the health of your heart and you sit there and you close your eyes and you think it feels all right like the same things feel okay. And then you went to the cardiologist and the cardiologist complex. You know tell me how you feel. Actually. What I really like you to do is do an E. K. G. And a blood panel and look at arterial plaques and let's look at my cholesterol and there's like 5-10 studies you would do. They give you this report and say here's the quantified health of your heart. Now with this data I'm going to prescribe the following regime of exercise and maybe I'll put you on a statin like uh etcetera. But the protocol is based upon this data. You would think the cardiologist is out of their mind if they just gave you a bottle of statins based upon you're like well I think something's kind of wrong and they're just just kind of experiment and see what happens. That's what we do with our mental health today. So you're it's it's kind of absurd. And so if you look at psychedelics uh to have begin to be able to measure the brain and get a baseline state and then to measure during a psychedelic experience and post the psychedelic experience and then do it longitudinal e you now have a quantification of what's going on. And so you could then pose questions what molecule is appropriate at what dosage is at what frequency in what contextual environment. What happens when I have this diet with this molecule of this experience, all the experimentation you do when you have good sleep data or HIV. And so that's what I think happens. What we could potentially do with psychedelics is we could add this level of sophistication that is not in the industry currently and it may improve the outcomes. People experience it may improve the safety and efficacy. And so that's why I hope we are able to achieve. And it would transform mental health because we would finally have numbers to work with the based on ourselves. And then if you think about it, we when we talk about things related to the mind, we talk about the modality. We use words like meditation or psychedelics or or something else because we can't talk about a marker in the brain. We can't use a word to say. We can talk about cholesterol, we don't talk about plaque in the arteries, we don't talk about HIV and so if we have numbers, then the solutions get mapped to numbers instead of the modalities being the thing we talked about meditation just does good things in a crude fashion. </s><s>[INST] So in your blog post, zero principle thinking good title, you partner. How do people come up with a truly original ideas? What what's your thoughts on this as a human and as a person who is measuring brain data. [/INST] zero Principles are building blocks. 1st principles. Our understanding of system laws. So if you take for example, I can Sherlock Holmes, he's a first principle stinker. So he says, once you've eliminated the impossible, anything that remains, however improbable, it's true. Mhm Whereas dirk gently the holistic detective by Douglas Adams says, I don't like eliminating the impossible. So when someone says from a first principles perspective and they they're trying to assume the fewest number of things within a given timeframe. And so when I after braintree Venmo, I set my mind to the question of what single thing can I do that would maximally increase the probability that the human race thrives beyond what we can even imagine. And I found that in my conversations with others in the books I read in my own deliberations, I had a missing piece of the puzzle because I didn't feel like over Yeah, I didn't feel like the future could be deduced from first Principles thinking. And that's when I read the book zero, a biography of a dangerous idea. And </s><s>[INST] I had a really good [/INST] book by the way, I think it's my favorite book I've ever read, </s><s>[INST] It's also a really interesting number zero [/INST] and I I wasn't aware that the numbers zero had to be discovered, I didn't realize that it caused a revolution in philosophy and and just tore up math and it tore up. I mean it builds modern society, but it it wrecked everything in its way. It was an unbelievable disruptor and it it was so difficult for society to get their heads around it. And so zero advocates of course the a representation of the zeroth principal thinking, which is, it's the caliber and consequential nature of an idea. And so when you talk about what kind of ideas have civilization transforming properties. Oftentimes they fall in the zeroth category. And so in thinking this through, I I was wanting to find a quantitative structure on how to think about the zero principles and so I came up with that to be a coupler with first principles thinking. And so now it's a staple is part of how I think about the world in the future. </s><s>[INST] So it emphasizes trying to identify the lands on that word impossible. Like what is impossible, essentially trying to identify what is impossible, what is possible and being as um how do you I mean this, this is the thing is most of society tells you the range of things they say is impossible is very wide. So you need to be shrinking that. I mean that's the whole process of of this kind of thinking is you need to be very rigorous in in uh trying to be trying to draw the lines of what is actually impossible because very few things are actually impossible. I don't know what is actually impossible. Huh? Like its joe Rogan is entirely possible. I like that approach to ah to science, to engineering to entrepreneurship. It's entirely possible, basically shrink the impossible to zero two very small set [/INST] your life constraints favor first principles thinking because it it enables faster action with higher probability of success pursuing zero of principle optionality is expensive and uncertain. And so in a society constrained by resources, time and money and a desire for social status, accomplishment, etcetera. It minimizes zero principle thinking about it. But the reason why I think zero principle thinking should be a staple of our shared cognitive infrastructure is If you look at the history of the past couple of 1000 years and let's just say we arbitrarily we subjectively try to assess what is a zero level zero level idea and we say how many have occurred on what time scales and what were the contractual settings for it. I would argue that if you look at Alpha go when it played, go from another dimension with the human go players, when it saw Alpha goes moves, it attributed to playing with an alien playing go with uh with Alphago beating from another dimension. And so if you say computational intelligence has an attribute of introducing zero like insights, then if you say what is going to be the occurrence of zeros in society going forward and you could recently say probably a lot more than have occurred and probably more at a faster pace. So then if you say what happens if you have this computational intelligence throughout society, that manufacturing design and distribution of intelligence is now going to heading towards zero. You have an increased number of zeros being produced with a tight connection between humans and computers. That's when I got to a point and said, we cannot predict the future with first principles thinking we can't that cannot be our imagination set, It can't be Our sole anchor in the situation that basically the future of our conscious existence, 2030, 40, 50 years is probably zero. </s><s>[INST] So just to clarify when you say zero, you're referring to basically truly revolutionary idea. [/INST] Yeah, it's something that is currently not a building block of our shared conscious existence either in the form of knowledge. Uh yeah, it's currently not manifest in what we've acknowledged. </s><s>[INST] zero principles, thinking is playing with ideas that are so revolutionary that we can't even clearly reason about the consequences once those ideas come to [/INST] be. Or for example, like Einstein, that was a zero, I would categorize it zeroes principal insight. </s><s>[INST] You mean general spacetime? Of course, yeah, [/INST] basically the building upon what Newton had done and said yes also, and it just changed the fabric of our understanding of reality. And so that was unexpected. It existed. We just it became became part of our awareness and the moves Alphago made existed, It just came into our awareness. And so it to your point, there's this question of what do we know and what don't we know? Do we think we know 99% of all things or do we think we know .001% of all things. And that goes back to no known unknowns and unknown unknowns and first principles and zero principle thinking gives us a quantitative framework to say there's no way for us to mathematically try to create probabilities for these things. Therefore it would be helpful if they were just part of our standard thought processes because it may encourage different behaviors and what we do individually collectively as a society, what we aspire to, what we talked about, the possibility sets we imagine. </s><s>[INST] Yeah, I've been engaged in that kind of thinking uh quite a bit and thinking about engineering of consciousness. I think it's feasible. I think it's possible in the language that we're using here. It's very difficult to reason about the world when inklings of consciousness can be engineered into uh artificial systems, not from a philosophical perspective, but from an engineering perspective, I believe a good step towards engineering consciousness is is creating engineering the illusion of consciousness. I'm captivated by our natural predisposition to anthropomorphize things. And I think that's what we Yeah, I don't want to hear from the philosophers, but I think that's what we kind of do to each other. [/INST] Okay, </s><s>[INST] that consciousness is created socially that like much of the power of consciousness is in the social interaction, I create your consciousness. No, I create my consciousness by having interacted with you. And that that's the display of consciousness. It's the same as like the display of emotion. Emotion is created through communication. Language is created through its use and then we somehow humans kind of, especially philosophers, you know, the hard problem of consciousness really want to believe that we possess this thing that's like there's a there's a there's a there's an elf sitting there with the hat or like name taxes consciousness and they're like feeding this subjective experience to us as opposed to like it actually being an illusion that would construct to make social communication more effective. And so I think if you focus on creating the illusion of consciousness, you can create some very fulfilling experiences in in software and so that to me is a compelling space of ideas to explore. [/INST] I agree with you and I think going back to our experience together with interfaces on you could imagine if we get to a certain level of maturity. So first let's take the university so you and I text back and forth and we're sending each other emojis that has a certain amount of information transfer rate as we communicate with each other. And so in our communication with people of the via email and text whatnot. We've taken the bandwidth of human interaction, the information transfer rate and we produced it. We have less social cues. We have less information to work with. There's a lot, a lot more opportunity for misunderstanding. So that is altering the conscious experience between two individuals. And if we add brainer faces to the equation, let's imagine now we amplify the dimensionality of our communications. That to me is what you're talking about which is consciousness engineering. Perhaps I understand you with dimensions. So maybe I understand your when you look at the cup and you experience that happiness, you can tell me you're happy and I then do theory of mind and say I can imagine what it might be like to be lex and feel happy about seeing this cup. But if the interface could then quantify and give me a 50 50 vector space model and say this is the version of happiness that lex is experiencing as you look at this cup, then it would allow me potentially to have much greater empathy for you and understand you as a human. And this is how you experience joy, which is entirely unique from how I experience joy even though we assumed ahead of time that we have, we're having some kind of similar experience. But I agree with you that the we do consciousness engineering today and everything we do when we talk to each other when we're building products and that we're entering into a a stage where it will be much more methodical and quantitative base in computational and how we go about doing it. Which to me I find encouraging because I think it creates better guard rails for to create uh ethical systems on versus right now. I feel like it's really wild Wild West on how these interactions are happening. </s><s>[INST] Yeah. And it's funny you focus on human to human but that this kind of data enables human to machine [/INST] Yes interaction </s><s>[INST] which is what we're kind of talking about when we say engineering consciousness [/INST] and that will happen. Of course let's flip that on its head. Let's right now we're putting humans as the central node. What if we gave gpt three a bunch of human brains said, Hey, GPT three learn some manners when you speak and run your algorithms on humans brains and see how they respond. So you can be polite and so that you can be friendly and so that you can be conversationally appropriate but to inverse it to give our machines a training set in real time with closed loop feedback so that our machines were better equipped to find their way through our society in polite and kind in appropriate ways. </s><s>[INST] I love the idea or better yet teach it some uh uh have it uh read the finding documents and have a visit austin in texas. And so that when you ask, when you tell it, why don't you learn some manners? DPT three learns to say no, it learns what it means to be free and the sovereign individual. So that it depends. So it depends what kind of a version of GPT three you want one that's free, one that behaves well with social revolution. You want, you want to like you want a socialist GPT three, You want an anarchist GPC three, you want a polite like you take it home with me to visit mom and dad. GPT three and you want like partying like Vegas to a strip club. GPT three, you want all flavors [/INST] and then you've got to have good alignment between all those. </s><s>[INST] Yeah, they don't want to manipulate each other for sure. Uh that's what I mean. You kind of spoke to ethics the one of the concerns that people have in this modern world, the digital data is that of privacy and security. But privacy, you know, they're concerned that when they share data it's the same thing we feel when we're trust other human beings uh in being fragile and revealing something that we're vulnerable, vulnerable about. There's a there's a leap of faith. There is a leap of trust that that's going to be just between us. There's a privacy to it. And then the challenge is when you're in the digital space and sharing your data with companies that use that data for advertisement, all those kinds of things. There's a hesitancy to share that much data to share a lot of deep personal data and if you look at brain data that feels a whole lot like it's richly deeply personal data. So how do you think about privacy with this kind of ocean of data. [/INST] I think we got off to a wrong start with the internet where the basic rules of play for the for the company that B was if your company you can go out and get as much information on a person as you can find without their approval and you can also do things to induce them to give you as much information and you don't need to tell them what you're doing with it. You can do anything on the back side, you can make money on it but the game is who can acquire the most information and devised the most clever schemes to do it. That was a bad starting place. And so we are in this period where we need to directly to correct for that and we need to say first of all, the individual always has control over their data. It's not a free for all. It's not like a game of hungry hippo but they can just go out and grab as much as they want. So for example when your brain data was recorded today, the first thing we did in the kernel app was you have control over your data. And so it's individual consent. It's individual control. And then you can build up on top of that but it has to be based upon some clear rules of play. If everyone knows what's being collected they know what's being done with it and the person has control over it. </s><s>[INST] The transparency and control. So everybody knows what does control look like. My ability to delete the data [/INST] if you want to delete it and to know who is being shared with under what you know what under what terms and conditions we haven't reached that level of sophistication with our products of if if you say for example hey Spotify please give me a customized playlist according to mine. you're um you know, you could say you can have access to this vector space model but only for this duration of time and uh and then you've got to delete it. We haven't gotten there at that level of sophistication, but these are ideas we need to start talking about of how do you, how would you actually structure permissions? And I think it creates a much more stable set for society to build where we understand the rules of play and people aren't vulnerable to being taken event. It's not fair for an individual to be taken advantage of without their awareness with some other practice that some companies doing for their sole benefit. And so hopefully we are going through a process now we're correcting for these things and that it can be an economy wide shift that because really these are these are fundamentals we need to have in place. </s><s>[INST] It's kind of fun to think about like in chrome when you install an extension or like install an app, it's ask you like what permissions you're willing to give and be cool if in the future it is like uh you can have access to my brain data. I [/INST] mean it's not unimaginable in the future. The big technology companies have built a business based upon acquiring data about you that they can then create a model of you and sell that predictability. And so it's not unimaginable that you will create with Colonel device for example, a more reliable predictor of you than they could and that they're asking you for permission to complete their objectives and you're the one that gets to negotiate that with them and say sure, but it's not unimaginable, that might be the case. </s><s>[INST] So there's a guy named Elon musk and he has a company in one of the many companies called neuralink that has uh that's also excited about the brain. So be interesting to hear your kind of opinions about a very different approach that's invasive that requires surgery implants a data collection device in the brain. How do you think about the difference in kernel and your link in the approaches of uh getting that stream of brain data. [/INST] Ellen and I spoke about this a lot early on we we met up, I had started Colonel and he had an interest in pre interfaces as well and we explored doing something together, him joining Colonel. And ultimately it wasn't the right move. And so he started, not only can I continue building Colonel, but it was interesting because we were both at this very early time where it wasn't certain what if there was a path to pursue if now was the right time to do something and then the technological choice of doing that. And so we were both our starting point was looking at invasive technologies and I was building to invasive technology at the time that's ultimately where he's gone ah a little less than a year after uh you and I were engaged, I shifted Colonel to do non invasive And we had this neuroscientists come to colonel, we were talking about he had been doing a neurosurgeon for 30 years, one of the most respected neuroscientists in the us. And we brought him to colonel to figure out the ins and outs of his profession. And at the very end of our three hour conversation, he said, you know, Every 15 or so years a new technology comes along. That changes everything. He said. It's probably already here. You just can't see it yet. And my jaw dropped. I thought because I I had spoken to bob Greenberg who had built uh second sight first on the optical nerve and then he did court up an array on the optical um cortex. And then I also became friendly with um no pace. Who does, who does the implants, first, seizure detection and remediation. And I saw in their eyes, What it was like to take something through an implantable device through for her for a 15 year run. They initially thought was seven years, Ended up being 15 years and they thought would be 100 million is, you know, 300, million. And I really didn't want to build invasive technology. It was the only thing that appeared to be possible. But then once I spun up an internal effort to start looking at non invasive options, we said, is there something here? Is there anything here that, again, has the characteristics of it has a high quality data, it could be low cost that could be accessible, couldn't make brain or faces mainstream. And so I did a bet the company move, we shifted from non invasive to invasive to non invasive. </s><s>[INST] So the answer is yes to that there's something there. It's possible. [/INST] The answers will see we've now built both technologies and they're now you experience one of them today. We or playing. We're now deploying it. So we're trying to figure out what values really there. But I'd say it's it's really too early to express confidence whether it's true. I think it's too early to assess which technological choice is The right one on what timescales, </s><s>[INST] timescales are really important. Very [/INST] important because if you look at the only invasive side, there's so much activity going on right now of less invasive techniques to get at The neuron firings, which would what neuralink is building. It's possible that in 10, 15 years when they're scaling the technology, other things have come along, you'd much rather do that. That thing starts the clock again. It may not be the case. It may be the case that neuralink has property, chosen the right technology and that that's exactly what they want to be totally possible. And it's also possible that the path we've chosen noninvasive fall short for a variety of reasons. It's just it's unknown. And so right now the two technologies we chose the analogy of Gift Give you to create a baseline of understanding is If you think of it like the Internet in the 90s, the internet became useful when people could do a dial up connection and then the paid and then as bandwidth increased. So did the utility of that connection and sort of ecosystem approved. And so if you say what Colonel Flow is going to give you a full screen on the picture of information but you're gonna be watching a movie but the image is going to be blurred and the audio is going to be muffled so it has a lower resolution of coverage. Colonel flux R M E G. Technology is going to give you the full movie and 10 80 P. And neuralink is going to give you a circle on the screen four K. Yeah. And so each one has their pros and cons and it's give and take. And so the decision I made. But Colonel was that these two technologies flux and Flow were basically the answer for the next seven years and that they would give rise to the ecosystem which would become much more valuable than the hardware itself and that we would just continue to improve on the hard way over time and you know, it's early days. So it's </s><s>[INST] kind of fascinating to think about that you don't it's very true that you don't know both paths are very problem are promising And it's like 50 years from now, we'll we will look back and maybe not even remember one of them and the other one might change the world. It's so cool how technology is. I mean, that's that's what entrepreneurship is, is like markets the zeroth principle is like you're marching ahead into the darkness, into the fog not knowing. [/INST] It's wonderful to have someone else out there with us doing this. Because if you if you look at Brainer faces, anything that's off the shelf right now is inadequate. It's had its run for a couple decades. It's still in hacker communities. It hasn't gone to the mainstream. The room size machines are on their own path, but there is no answer right now. We're bringing brainer faces mainstream. And so it both both they and us, we've both spent over $100 million dollars and that's kind of what it takes to have a go at this because you need to build full stack, I mean, Colonel, we are from the photon and the atom, through the machine learning. We have just under 100 people. I think it's something like 36 37 phds in these specialties, these areas that there's only a few people in the world who have these abilities and that's what it takes to build next generation have to make an attempt Breaking into brainer faces and so we'll see you in a couple years whether it's the right time or whether we were both too early or whether something else comes along in 7 to 10 years which is the right thing that brings it mainstream. </s><s>[INST] So you see Ellen as a kind of competitor or a fellow traveler along the path of uncertainty or both. [/INST] It's a fellow traveler it's like at the beginning of the internet is how many companies are going to be invited to this new ecosystem like an endless number because if you think that the hardware just starts the process and so okay back to your initial example if you take the Fitbit for example you say okay now I can get measurements on the body and what do we think the ultimate value this device is going to be? What is the information transfer rate? And they were in the market for a certain duration of time and google bought them for $2.5 billion. They didn't have ancillary value add. There weren't people building on top of the Fitbit device, they also didn't have increased insight with additional data streams. So he's really just the device. If you look for example at Apple and the device they sell you have value in the device that someone buys but also you have everyone who's building on top of it. You have this additional ecosystem value and then you have additional data streams that come in which increased the value of the product and so if you say if you look at the hardware as the Ingigator of value creation, you know over time what we've built may constitute five or 10% of the value of the overall ecosystem and that's what we really really care about. What we're trying to do is kick start the mainstream adoption of quantifying the brain and the hardware just opens the door to say what kind of ecosystem could exist. Mhm And that's why we're the examples are so relevant of the things you've outlined in your life. We hope, I hope those things the books, people write the experiences, people build the conversations, you have your relationship with your AI systems. I hope those all are feeding on the insights built upon this ecosystem, we've created to better your life and so that's the thinking behind it again with the drake equation being the underlying driver of value and the people that colonel have joined, not because we have certainty of success, but because we find it to be the most exhilarating opportunity we could ever pursue in this time to be alive, </s><s>[INST] You founded the payment system Braintree in 2007 That acquired Venmo in 2012 in that in that same year was acquired by paypal, which is now ebay, can you tell me the story of the vision and the challenge of building an online payment system and just building a large, successful business in general, [/INST] I discovered payments by accident As I was when I was 21. I I just returned from Ecuador living in extreme poverty for two years and I came back to the U. S. And I was shocked by the opulence and of the United States and I just thought this is, I couldn't believe it and I decided I wanted to try to spend my life helping others. Like that was the that was the life objective that I thought was worthwhile to pursue versus making money and whatever the case may be for its own right. And so I decided that moment that I was going to try to make Enough money by the age of 32, never have to work again. And then with some abundance of money, I could then choose to do things that might be beneficial to others but may not meet the criteria of being a standalone business. And so in that process I started a few companies, had some small successes, had some failures. In one of the endeavors, I was up to my eyeballs in debt. Things were not going well and I needed a part time job to pay my bills. And so I one day I saw in the paper in Utah where I was living the 50 richest people in Utah and I e mailed each one of the assistants and said, you know, I'm young, I'm resourceful, I'll do anything. I just want to, I'm entrepreneurial. I try to get a job that would be flexible and no one responded and then I interviewed at a few dozen places, nobody would even give the time of day like you wouldn't want to take me seriously. And so finally I it was a monster dot com that I saw this job posting for credit card sales, door to door commissioner, I did not know this story, This is great. I love the head drop. That's exactly right. So it was </s><s>[INST] the low points to which we go and [/INST] like so I I responded and you know the person made an attempt at suggesting that they had some kind of standards that they would consider hiring, but it's kind of like if you could fog a mirror, Like come and do this because 100% Commission. And so I started walking up and down the street in my community selling credit card processing. And so what you learn immediately and doing that is if you, you walk into a business first of all, the business owner is typically there and you walk in the door and they can tell by how your address or how you walk whatever their pattern recognition is and they just hate you immediately. It's like stop wasting my time. I really am trying to get stuff done. I don't want to do a sales pitch. So you have to overcome the initial get out and then once you engage when you say there were credit card processing, the person's like I already hate you because I have been taking advantage of dozens of times because you all are weasels. And so I had to figure out an algorithm to get past all those different conditions because I'm still working on my other startup for the majority of my time doing this part time. And so I figured out that the industry really was built on people uh on the seat basically people promising things that were not reality. And so I walk into a business and say look I will give you $100. I put $100 bill and say I'll give you $100 for three minutes of your time. If you don't say yes to what I'm saying, I'll give you $100. And then he usually crack a smile and say ok what you got for me son. And so I sit down, I just opened my book and I'd say here's the credit card industry, here's how it works. Here are the players, here's what they do here is how they deceive you. Here's what I am. I'm no different than anyone else. It's like you're going to process your credit card, you get the money in the account, you're just going to get a clean statement, you can have someone who answers the call when someone asked and you know just like the basic like you're okay and people started saying yes and then of course I went to next business and be like, you know joe and susie and whoever said yes to and so I built the social proof structure and I became the number one sales person out of 400 people nationwide doing this and I have worked half time still doing so their startup and </s><s>[INST] that's a brilliant strategy by the way, it's very well, very well strategized and executed. [/INST] He did it for nine months. And at the time my customer base was making was generating around I think was sick, if I remember correctly, $62,500 a month where the overall revenues, I thought, Wow, that's amazing. If I Built that as my own company, I would just make $62,000 a month of income passively with these merchants processing credit cards set up. And so uh, that's when I thought I'm going to create a company. And so then I started Braintree and the idea was the online world was broken because Paypal had had been acquired by Ebay around I think 19 2099 or 2000. And Ebay had not innovative much with Paypal. So it basically sat still for seven years as the software world moved along and then authorize dot net was also accompanied with relatively stagnant. So you basically had software engineers who wanted modern payment tools, but there were none available for them. And so they just dealt with software they didn't like. And so with Braintree, I thought the entry point is to build software that engineers will love. And if we can find the entry point via software, make it easy and beautiful and just a magical experience and then provide customer service on top of that. It was easy. That would be great. What was really going after for that was it was Paypal. They were the only company and payments making money because they, because they had the relationship with the bay early on, People created a Paypal account. They fund their account with their checking account versus their credit cards. And then when they use Paypal to pay a merchant, Paypal, how the cost of payment of zero versus if you have coming from a credit card, you have to pay the bank the fees. So Paypal's margins were 3% on a transaction versus a typical payments company, which may be a nickel or a penny or a dime or something like that. And so I, a new Paypal really was the model to replicate. But a bunch of companies had tried to do that. They tried to come in and build a two sided marketplace. So get consumers to fund the checking account, the merchants to accept it. But they all failed because building a two sided marketplaces very hard at the same time. So my plan was, I'm going to build a company and get the best merchants in the whole world to use our service Then in year five, I'm going to have, I'm going to acquire a consumer payments company and I'm going to bring the two together and </s><s>[INST] so focus on the merchant side. Exactly and then get the payments company, does the customer, the whatever the other side of [/INST] this is the planet presented when I was at University of Chicago. And weirdly it happened exactly like that. So for four years in our customer base included, Uber Airbnb, get hub 37 signals, not base camp. We had a fantastic collection of companies that represented the fastest growing, some of the fastest growing tech companies in the world. And then we met up with Venmo and they had done a remarkable job in building products then something very counterintuitive, which is make public your private financial transactions, which people previously thought were something that should be hidden from others. And we acquired Venmo and at that point we now had, we replicated the model because people could fund their Venmo account, but the checking account, keep money in the account and then you could just plug Venmo as a form of payment. And so I think people saw that, that we were getting the best merchants in the world. We had people using Venmo, they were both the up and coming millennials at the time who had so much influence online and so they came in and offered us uh an attractive number and my goal was not to build the biggest payments company in the world. It wasn't to try to climb the Forbes billionaire list. It was the objective was I want to earn enough money so that I can basically dedicate my attention to doing something that could potentially be useful on a society wide scale. And more importantly that could be considered to be valuable from the vantage point of 2050, 12,500. So thinking about on a a few 100 year time scale and there was a certain amount of money I needed to do that. So I didn't require the permission of anybody to do that. And so that what people offered was sufficient for me to get that amount of money to basically have a go. And that's when I set off to survey everything I could identify existence to say of anything in the entire world. I could do what one thing could I do that would actually have the highest value potential for the species. And so it took me a little while to arrive at Brainerd faces. But </s><s>[INST] you know, payments in themselves, our revolutionary technologies that can change the world. Like it's not, let's not sort of um let's not forget that too easily. I mean obviously, you know this, but there's uh quite a few lovely folks who are now fascinated with the space of Cryptocurrency and uh where payments are very much connected to this, but in general just money and many of the folks that I've spoken with, they also kind of connect that to not just purely financial discussions but philosophical and political discussions. And uh, they see Bitcoin as a way almost as activism, Almost as a way to resist the corruption of centralized the centers of power and sort of basically in the 21st century decentralizing control, whether that's Bitcoin or other cryptocurrencies, they see that's one possible way to give power to those that live in regimes that are corrupt or are not respectful of human rights and all those kinds of things. What's your sense? Just all your expertise with payments and seeing how that changed the world. What's your sense about the lay of the land for the future of Bitcoin or other cryptocurrencies in the positive impact you may have in the world? [/INST] Yeah, to be clear, my communication wasn't suggest wasn't meant to minimize payments or to denigrate in any way. It was a an attempted communication that when I was surveying the world, it was an algorithm of what could I individually do. So there's there are things that exist that have a lot of potential that can be done and then there's a filtering of how many people are qualified to do this given thing. And then there's a further characterization that can be done of, okay, given the number of qualified people will somebody be a unique out performer of that group to make something truly impossible to be something done that otherwise couldn't get done. So there's there's a process of assessing where can you add unique value in the world? </s><s>[INST] And some of that has to do with you being very uh very formal and calculated here. But some of that is just like what you sense. Like part of that equation is how much passion you sense within yourself to be able to drive that through, to discover the impossibility to make them possible. [/INST] That's right. And so we we were a braintree. I think we were the first company to integrate coin base into our uh, I think we're the first payments company to formally incorporate crypto if I'm not mistaken </s><s>[INST] for people who are not familiar, coin base is a place we can trade cryptocurrencies. [/INST] Yeah. Which was one of the only places you could. So we were early uh in doing that. And of course this was in the Air 2013. So an attorney to go in Cryptocurrency land, I concur with the the statement you made of the potential of the principles underlying cryptocurrencies and that many of the things that they're building in the name of money and end of of moving value is equally applicable to the brain and equally applicable to how the brain interacts with the rest of world and how we would imagine doing goal alignment with people. So it's to me it's a continuous spectrum of possibility. And we're talking your question is isolated on the money and I think it just is basically a scaffolding later for all of society. So you don't see </s><s>[INST] that this money is particularly distinct. I [/INST] don't it's I think we well colonel, we will benefit greatly from the progress being made in Cryptocurrency because it will be a similar technology stack we will want to use for many things we want to accomplish. And so I'm bullish on what's going on and I think it could greatly enhance brain our faces and the value of the brain face ecosystem. </s><s>[INST] I mean, is there something you can say about, first of all, bullish on Cryptocurrency versus fiat money? Do you have a sense that in 21st century Cryptocurrency will be embraced by governments and changed the the face of governments, the structural government. [/INST] It's the it's the same way I think about my diet where previously it was conscious brian looking at foods in certain biochemical states on my hungry. Am I irritated and depressed? And then I choose based upon those momentary windows do I eat at night when I'm fatigued and I have no willpower. Am I going to pig out on something? And the current monetary system is based upon human conscious decision making and politics and power and this whole mess of things. And what I like about the building blocks of cryptocurrencies, It's methodical, it's structured, it is accountable is transparent. So it introduces this scaffolding, which I think again it's the right starting point for how we think about building next generation institutions for society and that's why I think it's much broader and much broader than money. </s><s>[INST] So I guess what you're saying is Bitcoin is the demotion of the conscious mind as well. In the same way you were talking about diet, it's like giving less priority to the the ups and downs of any one particular human mind in this case your own and giving more power to the sort of data driven. [/INST] Yes. Yeah. I I think that is accurate. That Cryptocurrency is a version of what I would call my autonomous self that I'm trying to build. It is an introduction of an autonomous system of value, exchange and value and the process Yeah. Value creation in society. Yes, their similarities. </s><s>[INST] So I guess what you're saying is Bitcoin will somehow help me not pig out at night or the equivalent of speaking of diet if we could just linger on that topic a little bit. We already talked about your your blog post of I I fired myself. I fired brian the evening brian who's too willing to uh not not making good decisions for the long term well being and happiness of the entirety of the organism, basically you were like pigging out at night. And it was interesting because I do this, I do the same. In fact I often eat one meal a day and uh like I have been this this week actually, especially when I travel. And it's funny that uh it never occurred to me to just basically look at the fact that I'm able to be much smarter about my eating decisions in the morning and the afternoon than I am at night. So if I eat one meal a day, why not eat that one meal a day in the morning, Like I'm not, it never occurred to me this revolutionary until until you've uh you've outlined that. So maybe can you give some details and what this is just you? This is one person brian arrived at a particular thing that they do. But it's fascinating to kind of look at this one particular case study. So what works for you diet wise? What's your actual diet? What do you eat often do you eat? [/INST] My current protocol is basically the result of thousands of experiments and decision making. So I've I do this every 90 days. I do the tests, I do the cycle through that. I measure again and then I'm measuring all the time. And so what I I of course I'm optimizing for my biomarkers. I want perfect cholesterol and I brought perfect blood glucose levels and perfect DNA methylation. Uh you know, processes. Uh I also want perfect sleep. And so for example, recently, the past two weeks my resting heart rate Has been at 42 when I sleep and when my resting heart rate at 42, my HR V is at its highest. And I wake up in the morning filling More energized than any other configuration. And so I know from all these processes that eating roughly 8:30 AM, right after I work out on an empty stomach creates enough distance between that completed eating and bedtime where I have no almost no digestive processes going on in my body. Therefore my resting heart rate goes very low. And when my resting heart rate is very low, I sleep with high quality. And so basically I've been trying to optimize the entirety of what I eat to my sleep quality and sleep quality. Then of course feeds into my willpower, so creases virtuous cycle. So what at 8 30 what I do is I eat what I call super veggie, which is, it's a pudding of 250 g of broccoli, 150 g of cauliflower and hoping to other vegetables that I eat what I call nutty pudding, which is </s><s>[INST] make the putting yourself like, like like the what you call it, like a veggie mix, whatever thing that like a blender. [/INST] Yeah. How people can be made in a high speed blender. But basically the same thing every day veggie bowl as in the form of pudding, and then bowl in the form of nuts. And then I have </s><s>[INST] vegan vegan vegan. So that's fat and that's like uh that's fat and carbs and fats and protein and so on. But it tastes good. [/INST] I love it. I I love it so much I dream about it. </s><s>[INST] Yeah, that's awesome. This is uh [/INST] and then I have a third dish which is, it changes every day today, it was Callum spinach and sweet potato. And then I take about 20 supplements that hopefully make constitute a perfect nutritional profile. So what I'm trying to do is create the perfect diet for my body every single day we're </s><s>[INST] asleep as part of the optimization. You're like one of the things that really tracking me, Can you? Well I have a million questions but 20 supplements like what kind are like would you say are essential? Because I only take I only take uh athletic athletic greens dot com slash that's like the multivitamin essentially. That's like the lazy man, you know, like like if you don't actually want to think about ship, that's what you take and then uh fish oil and that's it, that's all I take [/INST] you. Alfred North Whitehead said advanced civilization advances as that extends the number of important operations that can do without thinking about them. And so my objective on this is I want an algorithm for perfect health that I never have to think about. And then I want that system to be scalable to anybody so that they don't even think about it. And right now it's expensive for me to do it. It's time consuming for me to do it and I have the infrastructure to do it. But the future of being human is not going to the grocery store and deciding what to eat. It's also not reading scientific papers trying to decide this thing or that thing, it's all end of one. So it's it's devices on the outside and inside your body assessing real time what your body needs and then creating closed loop systems for that to happen. </s><s>[INST] So right now you're doing the data collection and you're being the scientist, It would be much better if you're doing just that if you just did the data clock or it was being essentially done for you and you can outsource that to another scientist that's doing the N1 study of you. [/INST] That's right because every time I spend time thinking about this or executing spending time I'm spending less time thinking about building kernel or or future of being human and so it's we just all have these the budget of our capacity on on everyday basis and we will scaffold our way up out of this. And so yeah, hopefully what I'm doing is really it serves as a model that others can also build on why that's why I wrote about it is hopefully people can take and improve upon it. Uh I hold nothing sacred, I changed my diet almost every day based upon some new test results or science or something like that but </s><s>[INST] can you maybe elaborate on the sleep thing, why is sleep so important and why presumably like what does good sleep mean to you? [/INST] I think sleep is a contender for being the most powerful health intervention in existence. Yeah, it's a contender. I mean it's uh it's magical what it does if you're well rested and what your body can do. And I mean for example, I know when when I eat close to my bedtime and I've done a systematic study Four years looking at like 15 minute increments on time of day and where I eat my last meal, my willpower is directly correlated to my to the amount of deep sleep I get. So my ability to not binge eat at night when rascal brian's out about is based upon how much deep sleep I got the night </s><s>[INST] before. And so there's some, there's a lot to that. Yeah, [/INST] and so I just I've seen it manifest itself and so that I think the way it summarized this is in society, we've had this myth of we tell stories, for example, of entrepreneurship, where this person was so amazing, they stayed at the office for three days and slip into their desk and we say, wow, that's amazing, that's amazing. And now I think we're headed towards a state where we say that's primitive and really not a good idea if on every level. And so the new mythology is going to be the exact opposite. </s><s>[INST] Yeah, by the way, just sort of maybe push back a little bit on that idea. [/INST] Did you sleep under your desk collects </s><s>[INST] well? Yeah, I lied. I'm a big believer in that actually. I'm a big believer in, in chaos and not giving, giving into your passion and sometimes doing things that are out of the ordinary there, like not trying to optimize health for certain periods of time in, uh, in lieu of your passions is a signal to yourself that you're throwing everything away. So I think what you're referring to is how to have good performance for prolonged periods of time. I think there's, there's moments in life, we need to throw all that away, all the plans away, all the structure away. So the, I don't just, I'm not sure I have an eloquent way describe exactly what I'm talking about, but it all depends on different people on people, people are different, but there's a danger of over optimization to where you don't just give in to the madness of the way your brain flows. I mean, to push back on my pushback is like, it's nice to have like where the, where the foundations of your brain are not messed with. So you have a fixed foundation where the diet is fixed, where the sleep is fixed and that all that is optimal and the chaos happens in the space of ideas as opposed to the space of biology, but you know, I'm not sure if there's a, uh, that requires real discipline and forming habits. There's some aspect to which some of the best days and weeks of my life have been, yeah, sleeping under a desk kind of thing. And I don't, I'm not too willing to let go of things that empirically worked for things that work in theory. And so I'm again, I'm absolutely with you on sleep also, I'm with you on sleep conceptually, but I'm also very humbled to understand that for different people, good sleep means different things. I'm very hesitant to trust science on sleep. I think you should also be a scholar of your body. Again, the experiment of end of one. I'm not so sure that a full night's sleep is great for me. There is something about that power nap that I just have not fully studied yet. But that map is something special that I'm not sure. I found the optimal thing. Um, so like there's a lot to be explored to what is exactly optimal amount of sleep, optimal kind of sleep combined who died and all those cousins. I mean that all maps to sort of data leads the truth. Exactly. All referring to, [/INST] here's a data point for your consideration, the progress in biology over the past. It's a decade has been stunning. Yes. And it now appears as if we will be able to replace Our Organs. zero extra transplantation. And so we probably have a path to replace and regenerate every organ of your body except for your brain. You can you can lose your hand and your arm and leg. Get an official heart, you can't operate your brain. And so when you make that trade off decision of whether you're going to sleep under the desk or not and go all out for a four day marathon, right? There's a there's a cost benefit tradeoff of what's going on, What's happening to your brain in that situation, we don't know the consequences of modern day life on our brain. We don't, it's the most valuable organ in our existence and we don't know what's going on. If we and how we're treating it today with stress and with sleep and with dietary. And to me then, if you say that you're trying to you're trying to optimize life for whatever things you're trying to do. The game is soon with the progress in anti asian and biology. The game is very soon going to become different than what it is right now with Oregon rejuvenation, organ replacement. And I I would conjecture that we will value the health status of our brain above all things. </s><s>[INST] Yeah, absolutely everything you're saying is true. But uh, we die, we die pretty quickly. Life is short. And I'm one of those people that I would rather die in battle than uh than stay safe at home. It's like, yeah, you look at kind of, there's a lot of things that you can reasonably say this, this is the smart thing to do that can prevent you that becomes conservative that can prevent you from fully embracing life. I think ultimately you can be very intelligent and data driven and also embrace life. But I are on the side of embracing life. It's very, it takes a very skillful person to not sort of that hovering parent that says no, you know what? There's a three chance that if you go out, if you go out by yourself and play, you're going to die, get run over by a car, come to a slow or a sudden and and uh, I am more a supporter of just go out there if you die, you die. And that's a, it's a balance you have to strike. I think there's a balance to strike in the long term optimization and uh short term freedom for me, for programmer for programming mind, I tend to over optimize and I'm very cautious and afraid of that to not over optimize and thereby be overly cautious, sub optimally cautious about everything I do and that's the ultimate thing I'm trying to optimize for. It's funny you said like sleep and all those kinds of things. I tend to think, yeah, this is, you be more precise than I am, but I think I tend to want to minimize stress, which everything comes into that from you sleep and all those kinds of things. But I worry that whenever, I'm trying to be too strict with myself, then the stress goes up when I don't follow the strictness. And so you have to kinda it's a weird, it's uh there's so many variables in objective function as it's hard to get right. And sort of not giving a damn about sleep and not giving a damn about diet is a good thing to inject in there every once in a while for somebody who's trying to optimize everything. That's but that's me just trying to uh like it's exactly like you said, you're just a scientist. I'm a scientist of myself, your scientists of yourself. It'd be nice to somebody else is doing it and had much better data then because I don't trust my conscious mind. And I pigged out last night at some brisket in L. A. That I regret deeply [/INST] still uh </s><s>[INST] there's no point to anything I just said. [/INST] But what is the nature of your regret on the brisket? Is it do you wish you hadn't eaten it entirely? Is it that you wish you hadn't eat as much as you did? Is it that </s><s>[INST] I think uh well the most regret, I mean if you want to be specific, I drank way too much like dad's order my biggest regret is like having drinks so much diet soda. That's the thing that really was the problem, I had trouble sleeping because of that because I was like programming. And then I was editing so stipulated night and then I had to get up to go p a few times and it was just a mess. And it was, it's not really a mess, but like it's so many, it's like the little things I know if I just eat, I drink a little bit of water and that's it. And there's a certain all of us have perfect days that we know diet wise and so on, that's good to follow you feel good. I know what it takes for me to do that. I didn't fully do that and thereby because there's there's an avalanche effect where the other sources of stress, all the other to do items I have pile on my failure to execute on some basic things that don't make me feel good and all that combines to uh you know, to create to create a mess of a day. But some of that chaos, you know, you have to be okay with it. But some of it I wish it was was a little bit more optimal. And your ideas about eating in the morning are quite interesting as an experiment to try. Can you elaborate? Are you eating once a day? Yes, in the morning. And that's it. Can you maybe speak to how that you spoke? It's funny, he spoke about the metrics of sleep, but you're also, you know, you run a business, you're incredibly intelligent, you have to most of your happiness and success relies on you thinking clearly. So how does that affect your mind and your body in terms of performance. So not just sleep, but actually like mental performance [/INST] as you were explaining your objective function of for example, in the criteria you were including you like certain neurochemical states, like you like feeling like you're living life that life has enjoyment, that sometimes you want to disregard certain rules to have a moment of passion, of focus. There's this architecture of the way Lexus which makes you happy as a story you tell as something you kind of experience. Maybe the experience is a bit more complicated, but in this idea you have, this is a version of you and the reason why I maintain the schedule I do is I've chosen a game to say I would like to live a life where I care more about what intelligent yeah. What people who live in 2000 the year 2500 think of me than I do today, that's the game I'm trying to play. And so therefore the only thing I really care about on this optimization is trying to see past myself, past my limitations using zeroes principal thinking, Pull myself out of this contextual measured in right now and say what will matter 100 years from now, in 200 years from now, what are the big things really going on that are defining reality? And I find that if I were to hang out with diet soda lex and diet soda brian were to play along with that and my deep sleep were to get crushed As a result, My mind would not be on what matters in 100 years or 200 or 300 years, I would be irritable. I would be, you know, I've been a different state and so it's just gameplay selection. It's what you and I have chosen to think about. It's what we've chosen to. I'll work on. And this is what I'm saying that no generation of humans have ever been afforded the opportunity to look at their lifespan and contemplate that they will have the possibility of experiencing an evolved form of consciousness. That is unidentifiable that following a zero category of potential that to me is the most exciting thing in existence. And I would not trade any momentary neurochemical state right now in exchange for that, I would be willing to deprive myself of all momentary joy in the pursuit of that goal because that's what makes me happy. </s><s>[INST] Yeah, that's brilliant. But I'm I'm a bit I just looked it up with just looked up Braveheart speech and William Wallace, but he's in a fight and you may die run and you'll live at least awhile and dying in your beds many years from now, would you be willing to trade all the days from this day to that for one chance, just one chance picture of mel Gibson saying this to come back here and tell our enemies that they may take our lives with growing excitement, but they'll never take our freedom. I get excited every time I see that in the movie. But that's kind of how I approach life. And do [/INST] you think they were tracking their sleep? </s><s>[INST] I did. We're not tracking their sleep and they ate way too much brisket and they were fat, unhealthy, died early and uh were primitive. But there's some there's something in my eight brain that's attracted to that, even though most of my life is fully aligned with the way you see yours and part of it is for comedy of course, but part of it is like I'm almost afraid of over optimization [/INST] really. What you're saying though, if we're looking at this, let's say from a first principles perspective, when you read those words, they conjure up certain life experiences, but you're basically saying I experience a certain neurotransmitter state when these things are in action. That's all you're saying. So whether it's that or something else, you're just saying you have a selection for how your state for your body. And so if you as an engineer of consciousness, that should just be engineer a ble Yeah, and that's just triggering certain chemical reactions and so whether so it doesn't mean they have to be mutually exclusive. You can have that and experience that and also not sacrifice long term health and I think that's the potential of where we're going is we don't have we don't have to assume they are trade offs that must be had. </s><s>[INST] Absolutely. And so I guess from my particular brain is useful to have the outlier experiences that also come along with the illusion of free will, where I chose those experiences that make me feel like its freedom, listen, going to texas made me realize I spent so I was, I still am but I lived at Cambridge and M. I. T. And I never felt like home there. I felt like home in the space of ideas with the colleagues like when I was actually discussing ideas but there is something about the constraints, the how cautious people are, how much they valued also kind of uh material success, career success. When I showed up to texas, it felt like I belong, that was very interesting, but that's my neurochemistry, whatever the hell that is, whatever whatever maybe probably is routed to the fact that grew up in the soviet union, it was so such a constraint system that you'd really deeply value freedom and you've you always want to escape the the man in the control of centralized systems. I don't know what it is, but that's at the same time, I love strictness, I love the dogmatic authoritarianism of diet of like the same habit exactly the habit you have. I think that's actually when bodies perform ultimately my body performs ultimately. So balancing those two, I think if I have the data every once in a while party with some wild people, but most of the time he wants a day perhaps in the morning I'm gonna try. That might be very interesting, but I'd rather I'd rather not try it. I'd rather have the data that tells me to do it. But in general you're able to eating once a day. Think deeply about stuff like that's a concern that people have is like, you know, what does your energy wayne all those kinds of things? Do you find that it's especially because um it's unique. It's vegan as well. So you find that you're able to have a clear mind focus and just physically and mentally throughout. [/INST] Yeah, I find like my personal experience in thinking about hard things is often times I feel like I'm I'm looking through a telescope and I come aligning two or three telescopes so you kind of have to close one eye and move it back and forth a little bit and find just the right alignment. Then you find just a sneak peek at the thing you're trying to find. But it's fleeting. If you move just one little bit, it's gone and oftentimes what I feel like our the the ideas I value the most are like that. They're so fragile and fleeting and slippery and elusive and it requires a sensitivity to thinking and a sensitivity to maneuver through these things if I Concede to a world where I'm on my phone texting, I'm also on social media. I'm also doing 15 things at the same time because I'm running a company and I'm also feeling terrible from the last night. Um it all just comes crashing down and the quality of my thoughts goes to a zero. I'm just, I'm a functional person to respond to basic level things. But I don't feel like I I'm doing anything interesting. </s><s>[INST] I think that's a good word sensitivity because that's when you, that's, that's what thinking deeply feels like is you're sensitive to the fragile thoughts and you're right. All those other distractions kind of dull your ability to be sensitive to the fragile thoughts. It's a really good word out of all the things you've done. You've also climbed Mount Kilimanjaro. Is this true? [/INST] It's true. </s><s>[INST] Uh huh. What do you uh why and how and what do you take from that experience? [/INST] I guess the backstory is relevant because That in that moment it was the darkest time of my life. I was ending a 13 year marriage. I was leaving my religion. I sold Braintree and I was coming battling depression where I was just at the end and I got invited to go to Tanzania as part of a group that was raising money to build clean water wells. And I had made some money from braintree. And so I was able to donate $25,000 and it was the first time I had ever had money to donate outside of pain ties into my religion. It was such a phenomenal experience too. Two contribute something meaningful to someone else in that form. And as part of this process we were going to climb the mountain and so we went there and we saw the clean water wells were building, we spoke to the people there and it was very energizing and then we climbed Kilimanjaro and I came down with stomach flu on day three and I also had altitude sickness, but I became so sick that on day four, we are somebody on day five, I came into the camp base camp at 15,000 ft. Uh, just you know, going to the bathroom on myself and like falling all over. It was just, I was just a disaster. It was so sick </s><s>[INST] just flew and altitude sickness. [/INST] Yeah. And I just was destroyed from the situation And </s><s>[INST] plus one psychologically one of the lowest [/INST] points. Yeah. And I think that was probably a big contributor. I was, I was just smoked as a human. Just absolutely done. And I have three young Children and so I was trying to reconcile like this is not a weather, what whether I live or not is not my decision by itself. I'm now intertwined with these three little people and I have an obligation whether I like it or not, I need to be there and so it did. It felt like I was just stuck in a straitjacket and I had to decide whether I was going to summit the next day with the team and it was a difficult decision because once you start hiking there's no way to get off the mountain and midnight came and our guide came in and he said were you out? And I said I think I'm okay, I think I can try and so we went and so from midnight to I made it to the summit at five a.m. it was one of the most transformational moments of my existence and mhm the mountain became my problem, it became everything that I was struggling with and when I started hiking it was the pain got so ferocious that it was kind of like this uh it became so ferocious that um I turned my music to Eminem and it was you know Eminem was the he was the only person in existence that spoke to my soul and it was something about you know his anger and his vibrancy and his multi eventually he's the only person who I could turn on and I could just say like I feel some relief, I turned, I turned on Eminem and um I made it to the summit after five hours but just just 100 yards from the top I was with my guide ike and I started getting very dizzy and I was, I felt like I was gonna fall backwards off this cliff area we are on, I was like this is dangerous. And he said look brian I I know what you're at, this guy, I know where you're at and I can tell you you've got it in you, I want you to look up, take a step, take a breath and look up, take a breath and take a step. And I did and I made it and so I got there and I just I sat down with him at the top. I just cried like a baby </s><s>[INST] broke down, [/INST] just I just lost it. And So you know he let me do my thing and then we pulled out the pulse oximeter and measure my blood oxygen levels and it's like it was like 50 something percent and it was danger zone. So he so he looked at it and I think he was like really alarmed that I was in this situation. And so uh He said we can't get a helicopter here and we can't get you emergency evacuated, you've got to go down, you've got to hike down to 15,000 ft to get base camp. And so he we went on the mountain, I got back down to base camp and again that was pretty difficult and then they put me on a stretcher, This metal stretcher with this one will and a team of six people will be down the mountain and it was it was pretty tortuous, I'm very appreciative. They did also the trail was very bumpy. So they'd go for the big rocks and so my head would just slam against this metal thing for hours. And so I just felt awful. Plus I get my head slammed every couple seconds. So the whole experience was really a life changing moment and that's it. That was the demarcation of basically building your life, basically I said I'm going to reconstruct brian my my understanding of reality, my existential reality is what I want to go after and I try I mean as much as that's possible as a human, but that's when I set out to rebuild everything. </s><s>[INST] Was it the struggle of that? I mean there's also just like the romantic poetic, it's a freaking mountain, he's a he's a man in pain, psychological and physical, struggling up a mountain but its just struggle just in the in the face of just pushing through in the face of hardship or nature too. Something much bigger than you. Is that was that the thing that just clicked [/INST] for me, it felt like I was just locked in with reality and it was a death match. It was in that moment, one of us is going to die. </s><s>[INST] So you're pondering death, like not surviving [/INST] and and it was and that was the moment and it was the summit to me was I'm gonna come out on top and I can do this and giving in was it's like I'm just done. And so it did. I locked in and uh, that's why yeah, mountains are magical to me. I didn't expect that. I didn't design that. I didn't know that was gonna be the case. I not it would not have been something I would have anticipated. </s><s>[INST] But you are not the same man afterwards. Yeah. Is there advice you can give to a young people today that look at your story that's successful in many dimensions advice you can give to them about how to be successful in their career, successful in life, whatever path they choose. [/INST] Yes, I would say listen to advice and see it for what it is a mirror of that person and then map and know that your future Is going to be in a zero principle land. And so what you're hearing today is a representation of what may have been the right principles to build upon previously, but they're likely do appreciate him very fast. And so I am a strong proponent that people ask for advice, but they don't take advice. </s><s>[INST] So how do you take advice properly? [/INST] It's in the careful examination of the advice. It's it's actually you the person makes a statement about a given thing, somebody should follow, the value is not doing that. The value is understanding the assumption stack. They built the assumption of knowledge that they built around that that body of knowledge. That's the value is not doing what they say </s><s>[INST] considering the advice, but digging deeper to understand the assumption stack like the full person. It's I mean this is deep empathy essentially to understand the journey of the person that arrived at the advice and the advice is just the tip of the iceberg that ultimately is not the thing that gives you, it could it could be the right thing to do, It could be the complete wrong thing to do depending on the assumptions stack. So you need to investigate the whole thing. Is there some, are there been people in your start up in your business journey that's have served that role of advice giver has been helpful or do you feel like your journey felt like a lonely path? Or was it one that was of course we're all we're all they're born and die alone uh by uh do you fundamentally remember the experience is one where you leaned on people at a particular moment in time that changed everything? [/INST] Yeah. The most significant moments of my memory, for example, like on Kilimanjaro when I kick some person I had never met in Tanzania was able to in that moment apparently see my soul when I was in this death match with reality and he gave me the instructions look up step. And so there's magical people in my life that have done things like that. And I suspect they probably don't know, I probably should be better at identifying those things and but yeah, hopefully the, I suppose I can wisdom I would aspire to is to have the awareness and the empathy to be that for other people and not a a retail advertiser of advice of tricks and for life, but deeply meaningful and empathetic with a one on one context with people that it really can make a difference. </s><s>[INST] Yeah, I actually kind of experience, I think about that sometimes, you know, you have like an 18 year old kid come up to you. It's not always obvious. It's not always easy to really listen to them. Like not not the facts, but like see who that person is. I think people say that about being a parent is you know, you want to consider that you don't want to be the authority figure in a sense that you really want to consider that there is a special, unique human being there with a unique brain that may be um brilliant in ways that you are not understanding that you'll never be really tried to hear that. So when giving advice, there's something to that. It's a both sides should be deeply empathetic about the assumptions stack. I love that. The terminology. What do you think is the meaning of this whole thing of life? Why the hell are we here, brian johnson, We've been talking about brains and studying brains and you had this very eloquent way of describing life on earth as uh, as an optimization problem. Uh the cost of intelligence going to zero at first through the evolutionary process and then eventually through building uh through our technology building more and more intelligence systems, you ever ask yourself why is doing that? [/INST] Yeah, I think the answer to this question again, the information value is more in the mirror. It provides of that person which is a representation of the technological, social political context of the time. So if you asked this question 100 years ago, you would get a certain answer that reflects that time period, same thing would be to over 1000 years ago. It's rare. It's difficult for a person to pull themselves out of their contextual awareness and offer truly original response. And so knowing that I am contextually influenced by the situation that I am a mirror for our reality. I would say that in this moment, I think the real game going on is that in evolution built a system of scaffolding intelligence that produced us. We are now building intelligence systems that are scaffolding higher dimensional intelligence that's developing more robust systems of intelligence in doing in that process, with the cost going to zero, then the meaning of life becomes goal alignment which is the negotiation of our conscious and unconscious existence. And then I'd say the third thing is if we're thinking that we want to be explorers is our technological progress is getting to a point where we could aspirational, we say we want to figure out what is really going on really going on. Because does any of this really make sense Now, we may be 100 200 500,000 years away from being able to poke our way out of whatever is going on. But it's interesting that we could even stay in aspiration to say we want to poke at this question. But I'd say in this moment of time, the meaning of life is that we can build a future state of existence that is more fantastic than anything we could ever imagine. </s><s>[INST] The striving for something more amazing. [/INST] And that defies expectations that we would consider bewildering and all the things that that that and I guess the last thing, if there's millions of life, it would be infinite Games. You know? James Carse wrote the book finite games. Infinite Games. The only game to play right now is to keep playing the game. And so this goes back to the algorithm of the lexx algorithm of diet soda and brisket and pursuing the passion. I'm what I'm suggesting is there's a there's a moment here where we can contemplate playing infinite games. Therefore it may make sense to err on the side of making sure one is in a situation to be playing infinite games. If that opportunity arises. So just the landscape of possibilities changing very, very fast and therefore our old algorithms of how we might assess risk assessment of what things we might pursue and why those assumptions may fall away very quickly. </s><s>[INST] Well, I think I speak for a lot of people when I say that the game you mr brian johnson have been playing is quite incredible. Thank you so much for talking today. Thanks lex. Thanks for listening to this conversation with brian johnson and thank you too for stigmatic net suite Graham early and express VPN. Check them out in the description to support this podcast. And now let me leave you with the words from Diane Ackerman. Our brain is a crowded chemistry lab bustling with nonstop neural conversations. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] Uh Yeah and that requires the renegade ceo. Right? I'm with you. I'm with you. I still have a little bit faith in Waymo for for the renegade ceo to step forward but [/INST] it's not it's not john krafcik </s><s>[INST] Yeah it's uh you can't [/INST] it's not chris johnston and those people may be very good at certain things but they're not renegades </s><s>[INST] because these companies are fundamentally even though we're talking about billion dollars, all these crazy numbers, they're still like early stage startups. [/INST] I mean and I just if you are pre revenue and you've raised $10 billion, I have no idea like like this just doesn't work. You know, it's against everything. Silicon Valley, where's your minimum viable product, you know, where's your users with your growth numbers? This is traditional Silicon Valley. Why do you not apply it to what you think you're too big to fail already? Like oh </s><s>[INST] how do you think autonomous driving will change society? So the mission is for comma to solve self driving. Do you have like a vision of the world of how it will be different. Is it as simple as a to be transportation or is there like because these are robots, [/INST] it's not about autonomous driving in and of itself. It's what the technology enables it's I think it's the coolest applied ai problem. I like it because it has a clear path to monetary value. Um but as far as that being the thing that changes the world, I mean no, like like there's cute things we're doing in common like who you thought you could stick a phone on the windshield middle drive. Um but like really the product that you're building is not something that people were not capable of imagining 50 years ago. So no it doesn't change the world in that front. Could people have imagined the Internet 50 years ago? Only true junior genius visionaries. Everyone could have imagined autonomous cars 50 years ago so I could core but I don't drive it. </s><s>[INST] See I have this sense and I told you like I'm my long term dream is robots with which you have deep with whom you have deep connections, right? And there's different trajectories towards that. And I've been thinking so been thinking of launching a startup. I see autonomous vehicles as a potential trajectory to that. I'm that's not where the direction I would like to go. But I also see Tesla even call me, I like pivoting into into robotics broadly defined at some stage in the way like you're mentioning the internet didn't expect. [/INST] Let's solve you know when I say a calm about this, we can talk about this but let's all self driving cars first. You gotta stay focused on the mission. Don't don't, don't, you're not too big to fail for however much I think commas winning like no, no, no, no, no, you're winning when you solve level five self driving cars and until then you haven't win and one and you know, again, you want to be arrogant in the face of other people, great, you want to be arrogant in the face of nature, you're an idiot. </s><s>[INST] Stay, mission focused, brilliantly put uh like I mentioned thinking of launching a startup, I've been considering actually before, Covid, I've been thinking of moving to san Francisco, [/INST] Oh if I wouldn't go there, </s><s>[INST] so why is uh well, and now I'm thinking about potentially Austin um and we're in SAn Diego now, Diego, So why what? Um I mean you're, you're such an interesting human, you've launched so many successful things. What ah why san Diego? What do you recommend? Why not san Francisco? Have you thought so in your case SAN Diego with qualcomm and snapdragon. I mean that's an amazing combination, [/INST] but that wasn't really why </s><s>[INST] that wasn't the y [/INST] you know what I mean, Qualcomm was an afterthought qualcomm was, it was a nice thing to think about it, like you can have a tech company here, a good one, I mean, you know, I like to come, but yeah, no um what's </s><s>[INST] the white Sandy go better than what san Francisco suck. [/INST] Well, so okay, so first off we all kind of said like we want to stay in California, people like the ocean, you know, California for, for its flaws. It's like a lot of the flaws of California are not necessarily California as a whole and they're much more san Francisco specific. Um, san Francisco. So I think first tier cities in general have stopped wanting growth. Uh, well you have like in san Francisco, you know, the voting class always votes to not build more houses because they own all the houses and they're like, well, you know, once people have figured out how to vote themselves more money, they're going to do it. It is so insanely corrupt. Um, it is not balanced at all. Like political party wise, you know, it's, it's, it's a, it's a one party city. And </s><s>[INST] for all the discussion of diversity, it has, it stops lacking real diversity of thought of background of uh, approaches the strategies of ideas. It's kind of a strange place that it's the loudest people about diversity and the biggest lack of diversity. [/INST] I mean, that's, that's what they say, right? It's the projection </s><s>[INST] projection. Yeah, it's interesting and even people in Silicon Valley tell me that's uh, like high up people, but everybody is like, this is a terrible place. It doesn't make, I mean, and [/INST] coronavirus is really what killed it. San Francisco was the number one, uh, exodus during coronavirus, </s><s>[INST] but you still think san Diego is a is a good place to be. [/INST] Yeah, I mean we'll see, We'll see what happens with California a bit longer term like Austin and Austin is an interesting choice. I wouldn't, I wouldn't, I don't know really anything bad to say about Austin either except for the extreme heat in the summer. Um, which, but that's like very on the surface, right? I think as far as like an ecosystem goes, it's cool. I personally love colorado. Uh, I mean, you have these states that are, you know, like just play better run. Um, California is, you know, it's especially san Francisco, it's on its high horse. And like, </s>

<s>[INST] Yeah I just I only know I think the first letter is introverted. Extroverted. Right? Uh I've taken the test before. Just like a crude version of the test and that's the same problem you have with I. Q. Tests. There's the right thorough way of doing it and then there's like fun internet way. And um do you mind sharing what you're uh personality? Um [/INST] My my type index. I'm an E. N. T. P. That's an extrovert into iter perceive. Er uh Thinker E. N. T. Thinker P. Perceive. Er My wife is an I. S. F. J. Which is the polar opposite of me. E. I'm extroverted, she's introverted. I'm an intuit. Er She's a sensor. Uh I'm a thinker, she's a feeler, I'm a perceive er she's a judge. Er </s><s>[INST] Is there a good science on like [/INST] uh </s><s>[INST] Long term successful relationships in terms of the dynamics of that. The 16. I wonder if there's good data on that. [/INST] I don't I don't think there's a lot of good data in personalities writ large because there's not a lot of money to be made in personality testing but I would say that there's uh that with with experience with a good MBT. I. Test with a good paid test. 405 100 question test once you understand your own code and then you're you're taught how to assess the code of others with those two things kind of combined because then you have experience and learning uh it's it becomes very useful and you can have high confidence in this in the conclusions that you reach about people's professions, about people's relationships with family, about people's relationships professionally, people's capabilities to deal with stress how people will perform when pushed outside of their comfort zones. Really really powerful useful stuff in corporate world and in the espionage world. </s><s>[INST] So in terms of compressed representation of another human being um you can't do much better than those four letters. I [/INST] don't believe you can do much better in my experience. I have not seen anything better. </s><s>[INST] Yeah it is kind of it's difficult to realize that there is a core personality or the degree. That's true. It seems to be true. It's even more difficult to realize that there is a stable at least the science is so stable, consistent intelligence. Unfortunately. Uh you know the g factor that they call that if you do a barrage of I. Q. Test that's going to consistently represent that defect. And we're all born with that we can't fix it. That defines so much of who we are. It's sad. [/INST] I don't see it as sad because it's for me the faster you learn it, the faster you learn what your own sort of natural strengths and weaknesses are. The faster you get to stop wasting time on things that you're never going to be good at and you get to double down on the things that you're already naturally skilled or interested in. So there's a there's always a silver lining to a cloud. But I know now that I will never be a ballerina or a ballerina so I know that I'll never be an artist, I'll never be a musician, I'll never be any of those things and when I was 18 that might have made me sad. But now at 42 I'm like well shit awesome I can go be something else good always being bad. </s><s>[INST] You're not going to be a ballerina, you know [/INST] because I'm not graceful </s><s>[INST] and you've you've you've learned this years of experience. [/INST] Well </s><s>[INST] I don't know if there's an M. B. T. I. Equivalent for the for grace of movement. [/INST] I think it's called S sensor. </s><s>[INST] Oh [/INST] yeah because a sensor is someone who's able to interact with the world around them through their five senses very effectively. Like if you talk to dancers, dancers can actually feel the grace in all of their muscles. They know what position their fingers in. I don't have any idea, I don't know what position my </s><s>[INST] feet are in right now, I have to [/INST] look to make sure I actually feel the floor, right? </s><s>[INST] Yeah I definitely have. Oh that's good to know. So I don't you know I'm not a dancer but I do have that you're [/INST] a musician man like </s><s>[INST] the music I don't sure. Yeah that's true that that there is a physical component. But I think deeper because there's a technical aspect to that that's just like um it's less about feel. But I do know jiu jitsu, you know, and grappling. I've done all my life. I don't, you know, there's some people who are clumsy and they drop stuff all the time. They run into stuff. I don't I don't, first of all, I don't know how that happens. But to me I just have an awareness of stuff. Like if there's a [/INST] little orientation. </s><s>[INST] Yeah, like like I know that there's a small object I have to step over and I have a good sense of that. It's so it's so interesting. Yeah, you're just like born with that. [/INST] My wife is brilliant and she still walks into </s><s>[INST] doors. Yeah, [/INST] I mean she'll walk in a doorway. She'll Bang her knee on the same wall that's been there for the last 50 years. </s><s>[INST] It's it's for some reason really hilarious. That's good. Um, you've been asked I think on Reddit other big secrets that you know that could lend you and our country in terrible trouble if he came out to the public and you answered yes, I wish I could forget them. So let me ask you just about secrecy in general, are these secrets or just other secrets? Ones that the public will never know or will it come out in 10 2050 years I guess the the deeper question is what is the value of secrecy, transparency? [/INST] The, uh, the standard classification for all human intelligence operations is something called 2 to 5 x 2, 25 by two. So 50 years, 25 years times two years, times two rounds. So In essence, anything that I've seen has the first chance of becoming public domain declassified after 50 years unless there's some congressional requirement for it to be reviewed and assessed earlier. So by then, you know, I'll be 80 something years older or potentially dead. Which is either way that's when it's, it's, it can come out according to its typical classification. The, the value of secrets I I have seen is that secrets create space Secrets give opportunity for security. They give opportunity for thinking. They give space and space is an incredibly advantageous thing to have. If you know something, somebody else doesn't know, even if it's just 15 or 20 minutes different, you can direct, you can change the course of fate. So I, I find secrets to be extremely valuable, extremely useful. Uh, even at the place where secrets are being kept from a large mass part of what all americans need to understand is that one of the, one of the trade offs to building a system of government that allows us to be first world and wealthy and secure and successful. One of the trade offs is that we have given up a great deal of personal freedom and one of the personal freedoms that we give up is the freedom of knowing what we want to know, you get to know what the government tells you. You get to know what you need to know or what you've learned yourself. But you don't get to know secrets. People who do get to know secrets, know them for a reason. That's why it's called a need to know how </s>

<s>[INST] Well, thank you for allowing me for a brief moment to [/INST] try to channel your </s><s>[INST] uncle Mooney and [/INST] maybe Malcolm X in this </s><s>[INST] Conversation as we as we look forward to the 21st century, you mentioned [/INST] that in part </s><s>[INST] you're troubled by the term african american. So words are funny things until they're not. So let me ask you about [/INST] what </s><s>[INST] I think is one of the most powerful and controversial words in the english language? The N [/INST] word? Mm </s><s>[INST] hmm. So this [/INST] is the word that </s><s>[INST] I can't say that only certain people have the right to say. [/INST] Have </s><s>[INST] a friend, joe Rogan. Yeah, who [/INST] has </s><s>[INST] um, what would you say? There was [/INST] mass </s><s>[INST] push back or highlighting of the fact that he didn't just say n word but said the full word many times [/INST] throughout his </s><s>[INST] conversations when referring to um, [/INST] in a meta </s><s>[INST] way about [/INST] the power of </s><s>[INST] words, especially when related to certain comedians using those words. [/INST] Um, </s><s>[INST] yeah, [/INST] what do you think </s><s>[INST] about this word? [/INST] Is it empowering? </s><s>[INST] Is it destructive? What is it, what does it mean [/INST] for race </s><s>[INST] in America? Um, [/INST] what does it mean that people like joe </s><s>[INST] Rogan [/INST] were essentially </s><s>[INST] uh, there's an attack to cancel [/INST] him for using the </s><s>[INST] word just [/INST] as a, as a scholar of </s><s>[INST] human nature. What do you think about this whole thing? [/INST] And this is a phenomenon </s><s>[INST] that interests me. Okay [/INST] at the end </s><s>[INST] word ***, [/INST] I can say it because I'm black, but I mean I can also say it because I like hip hop and when I listen to hip </s><s>[INST] hop, I hear the word all the time. These *** ain't. Did [/INST] you know you have to watch </s><s>[INST] out for these, you know, [/INST] etcetera. I heard the word constantly as I was growing up </s><s>[INST] as a boy and a young man in [/INST] Chicago *** </s><s>[INST] ain't shit [/INST] that was said. That </s><s>[INST] was you know, [/INST] the and that could be a reflection of some kind </s><s>[INST] of pathology [/INST] within the african american community of self hatred </s><s>[INST] and so forth. It [/INST] could be or it could just </s><s>[INST] be a colloquial [/INST] linguistic way. I mean I assume other groups also have </s><s>[INST] their [/INST] various, I don't know how the irish talk about their </s><s>[INST] irish brothers [/INST] and you know, whatever and um I </s><s>[INST] don't know how the jews [/INST] talk about the jewish brothers </s><s>[INST] and whatever, [/INST] but black people when talking about other black people use the N word all the </s><s>[INST] time. [/INST] My </s><s>[INST] ***, N [/INST] I G G </s><s>[INST] A you [/INST] know my ***, uh </s><s>[INST] that is a term of [/INST] endearment. My friend Randall </s><s>[INST] Kennedy, the [/INST] law professor at Harvard </s><s>[INST] University has a [/INST] book called *** </s><s>[INST] and he [/INST] uses the word in the title of the book. The history of a Strange </s><s>[INST] history of a [/INST] of a provocative word is something that there's a subtitle. But the title of the book is N I G G E R colon and then he </s><s>[INST] has a subtitle. I [/INST] think of course the use of the word as a slur and an insult </s><s>[INST] which is a [/INST] part of the history of black people in the </s><s>[INST] United States. The [/INST] use of the word by the southern racist segregationist, We don't want no *** up in here, y'all, you know, ***, *** have no place in my restaurant in my store etcetera. That's meant to be an insult. It's an insult to people. That's a fighting word. It's a word that you say that to somebody. It's a it's a invitation for </s><s>[INST] conflict [/INST] that said, </s><s>[INST] what is it that about this particular word? And also the asymmetry of it. [/INST] That do you </s><s>[INST] think it's empowering to the black community? To own a word? My, [/INST] my honest answer to you is, I don't know, I don't fully understand it. It has become symbolic in a way and the policing of the use of the word. I can say it, but white people </s><s>[INST] can't say it, I [/INST] can say. And I'm not a racist, I'm not a self hating black, you know, I'm just speaking the </s><s>[INST] language [/INST] of colloquial english that has emerged amongst african americans in which that word plays a big role, but the prohibition on its use by others. And of course, in the joe Rogan case, it wasn't as if he was calling anybody </s><s>[INST] an [/INST] N. Word, he was simply pointing out that people had said stuff in which the n word was a part of what they said. Now he did make this statement about how did he put in the Planet of the apes that one of the offensive things that he said </s><s>[INST] had, you know, he walked into [/INST] a room, there's a bunch of black guys standing around, he says like Planet of the apes, he said, </s><s>[INST] it's like africa [/INST] Planet of the apes. Yeah, he should have and he should have been </s><s>[INST] more careful that [/INST] that was, that was an insult. That was, that was, </s><s>[INST] you know, [/INST] something that, uh, you know, if you say that and people are offended, they have a right to be offended. And if you didn't mean to offend them, you can apologize and he did apologize. I accept his apology, joe is okay with me as far as that goes. Um, in fact, McWhorter and I john McWhorter and I at the podcast that I do the glenn show, I had a conversation part of which touched on the joe Rogan phenomenon and we concluded he didn't really </s><s>[INST] do anything wrong. I mean, [/INST] I mean you can like caramel, you </s><s>[INST] can hate him or [/INST] whatever, but the idea that he's a racist, it's kind </s><s>[INST] of ridiculous. And frankly, I [/INST] mean enjoy, you know, </s><s>[INST] if that's your test of [/INST] what constitutes a racist, the utterance of the word, uh, then you know, it's kind of, it's kind of silly as far as I'm </s><s>[INST] concerned. What do you think about [/INST] the rigorous </s><s>[INST] testing of people to the degree that are racist or not? The accusation of [/INST] racism being </s>

<s>[INST] This show is brought to you by blinking my favorite app for learning new things. I'm sorry, I'm running around the mic. I just get really excited when I'm doing these ad reads Blankets. Takes the key ideas from thousands of nonfiction books and condenses them down into just 15 minutes that you can read or listen to. I can recommend a million books from sapiens to meditations by Marcus Aurelius. But what I should more specifically or more generally say that's a contradiction is that you can use it to both review the books you've already read or to select books that you're going to read and both are super useful. Go to blankets dot com slash lex to start your free seven day trial and get 25% off of a blinkers, premium membership that's blinking dot com slash lex spelled B L I N K I S T blankets dot com slash lex. This episode is also brought to you by magic spoon. Just saying that brings happiness to my heart. It's a low carb keto friendly cereal. It has zero g of sugar, 13 to 14 g of protein, only 49 g of carbs, 140 calories that needs serving. I just had a huge amount of barbecue Texas, barbecue yesterday. I made myself feel a lot better today to balance that out with the lightness and the health of also a keto friendly meal, which is magic spoon. You can build your own box or get a variety pack. But ladies and gentlemen, the best flavor is Coco. It is the flavor of champions. It reminds me of childhood and the happiness I felt when I was eating the sweet, sweet delicious cereal. But at the time those cereals were full of sugar and this cereal is not so it's also healthy for you. Magic spoon have a 100% happiness guarantee. So if you don't like it, they refunded, go to magic spoon dot com slash lex. And use code lex at checkout to save five bucks off your order. That's magic spoon dot com slash lex. And use code lex. This is a lex Friedman podcast and here is my conversation with carl zeiss Roth. You open your book called projections a story of human emotions with a few beautiful words to summarize all of humanity. The book draws insights about the human mind for modern psychiatry and neuroscience. So if it's okay, let me read a few sentences from the opening. You gotta give props to beautiful writing when I see it quote in the art of weaving warp threads are structural and strong and anchored at the origin, creating a frame for crossing fibers of the fabric is woven, projecting across the advancing edge into free space. Warp threads bridge deformed, passed to the ragged present to the yet featureless future, yet featureless future. Well done. Well done sir. The tapestry of the human story has its own warp threads rooted deep in the gorges of East africa connecting the shifting textures of human life over millions of years spanning pictographs backdrop by crevices, ice, by angular lated forestry by stone and steel and by glowing rare earths. The inner workings of the mind give form to these threads creating a framework within us upon which the story of each individual can come into being personal grain and color arise from the cross threads of our moments and experiences the fine weft of life embedding and obscuring the underlying scaffold with intricate and sometimes lovely detail. Here are stories of this fabric fraying in those who are ill in the minds of people for whom the warp is exposed and raw and revealing. What have you learned about human beings, human nature and the human mind, from those who suffer from psychiatric maladies, for those for whom this fabric is warped. [/INST] And one thing we learn as biologists is that when something breaks, you see what the original unbroken part was for and we see this in genetics, we see this in biochemistry. It's known that when you have a mutated gene, sometimes the gene is turned up in strength, there turned down in strength and that lets you see what it was originally for. You can infer true function from dysfunction. And this is a theme that I thought needed to be shared and needed to be made communicable to the lay public to everybody. People who, which is I think almost all of us who think and care about the inner workings of her mind, but who also care for those who have been suffering who have mental health disorders, who face challenges. But then more broadly, it's a very much larger story than the present. There's a a story to be told where the protagonist really is the human mind and that was one thing I wanted to share as well in projections, is that broader story, but still anchored in the moment of patients, of people of experiences at the moment. </s><s>[INST] Is there a clear line between dysfunction and function disorder in order? [/INST] This is always debated in psychiatry, probably more so than any other, you know, medical specialty. I'm a psychiatrist. I'm I treat patients still, I see acutely ill people who come to the emergency room where there is no doubt that this is not something that's working well where the manifestation of diseases so powerful, where the person is suffering so greatly where they cannot continue as they are. But of course it's a spectrum and there are people who are closer to the, to the realm of being able to work okay in their jobs but suffer from some small dysfunction and everywhere in between. In psychiatry were careful to say, we don't call it a disease or disorder unless there is a disruption in social or occupational functioning. But of course psychiatry has a long way to go in terms of developing quantitative tests. We don't have uh, blood draws, we don't have imaging studies that we can use to diagnose. And so that line ultimately, that you're asking about between order and disorder function and dysfunction. Its operational at the moment. How are things working? </s>

<s>[INST] beautifully. I would say if there is from the machine learning from from the computer science computer vision perspective many of the researchers kind of ignore the way the human brain works, ignore even psychology or literature or studying the brain. I would hope josh Tenenbaum talks about bringing that in more and more and that's uh so you worked on some amazing stuff throughout your life. What's the thing that you're really excited about? What's the mystery that you would love to uncover in the near term beyond beyond. All the mysteries are already surrounded by. [/INST] Well. So there's a structure called the classroom. Okay, this is structures underneath our cortex. It's yea big. You have one on the left and right underneath this pipe underneath the insular, it's very thin, it's like one millimeter. It's embedded in in wiring in white matters. It's very difficult to image and it has it has connection to every cortical region and Francis crick. The last paper you ever vote, he dictated corrections the day he died in hospital on this paper. You know, we hypothesize well because it has this unique anatomy gets input from every cortical area and projects back to every every cortical area that the function of this structure is similar. It's just a metaphor to the role of a conductor in a symphony orchestra. You have all the different cortical players. You have some that do motion, some that do theory of mind, some that in for social interaction and color and hearing and all the different modules and cortex. But of course what consciousness is, consciousness puts it all together into one package, right, the binding problem, all of that. And this is really the function because it has a relatively few neurons compared to cortex. But it talks it receives input from all of them and it projects back to all of them. And so we're testing that right now we've got this beautiful neuronal reconstruction in the mouse called crown of thorn town of thor neurons that are in the classroom that have the most widespread connection of any new on I've ever seen. They're very they you have individual you want to sit in the clouds from tiny but then they have this single you don't have this huge external tree that cover both Itsy and continental cortex and and trying to turn using, you know, fancy tools like optogenetics, time to turn those neurons on or off and study it what happens in them in the mouth. </s><s>[INST] So this thing is perhaps where the parts become the whole into. [/INST] Perhaps it's one of the structures, a very good way of putting it where the individual parts turn into the whole of the whole of the conscious experience. </s><s>[INST] Well, with that, thank you very much for being here today. Thank you very much. [/INST] Thank you much </s>

<s>[INST] romantic question. But going back to the kid that dream to fly, what's it like to fly an airplane? What It looks incredible as a human like at the center of a pipe. I sit here on land and look up at you guys. It seems incredible that a human being can do that. [/INST] You know, people ask, you know, I'll be sitting around with my friends and they're like, how was I said, the greatest job on the planet. I said, you know, you, it's an office with a view because you're sitting in a glass of um, you, you can do uh, you know, it's like roller coasters. You go, it does all this cool stuff. So we take people flying, everyone's well and it's like, yeah, I like roller coaster, you know, take any roller coaster, coolest roller coaster I've ever been on And multiply it by 1000. I said it's an experience. Uh you know, to put your body under, you know, you know, the jets rated at 7.5, but it'll pull up to 8.1 before it over stresses depends on fuel weight. So I mean you routinely get up there towards eight Gs. Um, to be able to do that to you. But I mean it takes a toll. Like I can't really turn my head real good anymore and, and stuff like that. But uh, would I trade it? I mean it was a childhood dream and how many people get to do that, you know, professional. I want to be an NFL, you know, and you end up to the NFL, which is a very small percentage but well I want to fly jets and to fly, you know, at the time when I was flying the super hornets that we had in our squad and we're brand new, like literally right out of the factory had come off our first super hornet cruise. We had went to the Boeing factory in ST louis where they were building my new jets that I was going to get and actually signed the inside of one of the wings while they were putting it together. So I'm meeting the people that are putting the jet together that's going to get delivered to me in a couple of months that I'm going to fly. So, uh, just, I mean </s><s>[INST] it's [/INST] i, it's, I'll tell you what, when I left when I decided to walk away. </s><s>[INST] Yeah. Do you miss it? [/INST] I told myself I wouldn't, I promised myself That, you know, once you get through your 05 command, you're flying really starts to tag to come down. You know, even if you and your an air wing commander, which is, we call them cag carrier group commander. Um, you're not flying as much as like the normal pilots nor should you be. I mean there's young people that are coming up and it's training your relief because that's the next generation. So like currently I have friends of mine that we serve together. Their kids are flying super hornets. Right? So to me that's really neat because I watched them when they were little and now, you know, one of them who was good friends, uh, get his last name, but Joey uh, who lived down the street from us is the top was a top gun instructor and I'm like, hey Joey's joins the top gun, you know, and I'm like, that's cool because, you know, I went there and I knew him, he would come down to my house and now to see these kids that are because typically military breeds military, you know, because the kids grew up in it. I mean, and I, the only reason that my son is not doing it is he's color blind. So it disqualifies you for being a pilot, being a seal because he talked about doing that because he's an incredible swimmer and he likes doing that stuff and water polo player. But he's, you know, both my kids are, well, my daughter is a doctor and my sons in his third year, so, </s><s>[INST] but there's a, uh, I suppose, I mean from my perspective, a bittersweet handover of this incredible experience of flying to the younger generation. So you don't, you told yourself, you're not gonna miss it. You miss it. [/INST] Uh, there are days I do when I hear jets, like if I'm around a base or a jet flies over, but I have all the memories so I can look at it and go, it can't go on forever, you know, tom brady can't play football, there's gonna come a time where he has to stop. But you know, typically when you look at you go, I had the opportunity, uh, and I think his automation moves on especially with ai That you know, when will when will the last man fighter rebuilt? You know, and that's that big question. You know, we just did have 35, it's over budget at seven years late there's all kinds of issues and we try and do it and then you look at some of the new stuff that's coming out that the Air Force is working on with smaller cheaper a treatable platforms that you can go, oh we can because if you don't put a man in the box or a person because there's a lot of incredibly talented women that do this to um so I'll just say that his person </s><s>[INST] so we say man and he would mean both men and women because offline you've told me about a lot of incredible women that flowing. So [/INST] I had, I had three, three female but actually 41 of them didn't fly anymore. She actually lives right around here. She she ended up going into aircraft maintenance when she couldn't fly anymore. Uh One of the girls who everyone knows is incredibly, she's one of the most gifted people I've ever met in my life. She is the Vice President amazon Air, you can see her on tv or named Sarah incredible and then I had a page who ended up taking command. She got out of fighters and went into other platforms. Um and she was a commanding officer and then the other one is a teaches leadership and she is all three of them actually all four of the women that were direct, I'm home. Not forgetting, I don't think I'm forgetting someone uh incredibly incredibly talented. Uh and a great addition to the reading room. So anyone who gets into the, you know, women can't do it. That's all total horse crap. You know, we can talk about the original integration and stuff which was not done well by the military Northern Navy </s>

<s>[INST] That's a good question actually to ask for for a lot of things, not just machine learning. Um It's a good way to cut the, I forgot what the term we use but the fluff the blubber, whatever the uh the inefficiencies in life. What do you love about teaching, You seem to find yourself often in the like drawn to teaching. You're very good at it, but you're also [/INST] drawn to it. I mean I don't think I love teaching, I love happy humans </s><s>[INST] and [/INST] happy humans. Like when I teach, </s><s>[INST] I [/INST] wouldn't say I hate teaching, I tolerate teaching but it's not like the act of teaching that I like. It's it's that um You know I I have some I have something I'm actually okay at it. I'm okay at teaching and people appreciate a lot. And so I'm just happy to try to be helpful and teaching itself is not like the most. I mean it's really it's can be really annoying frustrating. I was working on a bunch of lectures just now. I was reminded back to my days of 231 and just how much work it is to create some of these materials and make them good. The amount of iteration and thought and you go down blind alleys and just how much you change it. So creating something good. Um in terms of educational value is really hard and it's not fun. It's </s><s>[INST] difficult. So people should definitely go watching new stuff you put out. There are lectures where you actually building the thing like from like you said the code is truth. So discussing back propagation by building it by looking through and just the whole thing. So how difficult that to prepare for. I think it's a really powerful way to teach. How did you have to prepare for that or are you just live thinking through it? [/INST] I will typically do like say three takes and then I take like the better take. So I do multiple takes and I take some of the better takes and then I just build out a lecture that way. Sometimes I have to delete 30 minutes of content because it just went down an alley that I didn't like too much. There's about a bunch of iteration and it probably takes me, you know, somewhere around 10 hours to create one hour of content </s><s>[INST] to give one hour. It's interesting. I mean, is it difficult to go back to the, like, the basics? Do you draw a lot of, like, wisdom from going back to the basics? [/INST] Yeah. Going back to back propagation loss functions where they come from. And one thing I like about teaching a lot, honestly is it definitely strengthens your understanding. So it's not a purely altruistic activity. It's a way to learn if you have to explain something to someone, uh you realize you have gaps in knowledge. Uh And so I even surprised myself in those lectures, like, also the result will obviously look at this and then the result doesn't look like it. And I'm like, okay, I thought I understood this, but that's why </s><s>[INST] it's really cool to literally code. You run it in the notebook and it gives you a result and you're like, oh wow, like actual numbers, actual input, you know, actual code, [/INST] it's not mathematical symbols, etcetera. The source of truth is the code. It's not slides, it's just like, let's build </s><s>[INST] it, It's beautiful, You're a rare human in that sense. What advice would you give to researchers trying to develop and published idea that have a big impact in the world of aI so maybe um undergrads, maybe early graduate students. [/INST] I mean, I would say like they definitely have to be a little bit more strategic than I had to be as a PhD student because of the way I is evolving. It's going the way of physics where, you know, in physics, you used to be able to do experiments on your bench top and everything was great and you can make progress and now you have to work in like LHC or like cern and and so ai is going in that direction as well. Um, so there's certain kinds of things that's just not possible to do on the bench top anymore. And uh, I think um that didn't used to be the case at the time. Do </s><s>[INST] you still think that there's like gan type papers to be written, were like, like very simple idea that requires just one computer to illustrate a simple example. [/INST] I mean, one example that's been very influential recently is diffusion models. The fusion models are amazing. The fusion models are six years old for the longest time. People are kind of ignoring them as far as I can tell and they're an amazing generative model, especially in images and so stable diffusion and so on. It's all diffusion based. The fusion is new, it was not there and came from, well, it came from google, but a researcher could have come up with it. In fact, some of the first actually, no, those came from google as well. But a researcher could come up with that in an academic institution. </s><s>[INST] Yeah. What do you find most fascinating about diffusion models? So from the societal impact of the technical architecture, [/INST] what I like about the fusion is it works so well. </s><s>[INST] Was that is that surprising to you? The amount of the variety almost the novelty of the synthetic data is generating? [/INST] Yes, So the stable diffusion images are incredible. It's the speed of improvement in generating images has been insane. Uh We went very quickly from generating like tiny digits to the tiny faces and it all looked messed up. And now you're stable diffusion. And that happened very quickly. There's a lot that academia can still contribute, you know, for example, um Flash attention is a very efficient colonel for running the attention operation inside the transformer that came from academic environment. It's a very clever way to structure the colonel. Uh that that's the calculation, so it doesn't materialize the attention matrix. Um and so there's I think there's still like lots of things to contribute, but you have to be just more strategic. Do </s>

<s>[INST] So what do you think? So, in in his case, in Tr's case he can get around, you know, getting permission from governments if we were to look at our us facing um outside of the store, us facing climate change. Where do you think the solution will come from governments working together or from bold billionaire Texans? [/INST] I'm pretty sure that this kind of intervention is never going to emerge from Western democracies. </s><s>[INST] Um, this kind of, sorry, government coordinate, uh which which option one of [/INST] solar geoengineering, </s><s>[INST] soldier engineering from a government from are like those are I want to sort of the distinction one is the idea of the technological idea you're talking about, but uh, two is like who comes up with the idea and agrees on governments or individuals. [/INST] If this were to happen, I think it would be either an individual or more likely just uh some government somewhere that just decides it's in their interests to to unilaterally do this and, you know, that's not me advocating it. It's just it's so it would be comparatively so cheap and easy to implement the solar geoengineering scheme that um, someone is probably going to do it once things get bad enough, but I don't think that the government will Western governments just because they're not um, well, we've seen what happened with with vaccines, right? So, um, you know, getting getting people to take vaccinations or wear masks, it's turned out to be incredibly hard, even though it might it might save those people's lives. </s><s>[INST] See I blame that's not Western. That's I blame failure of leadership there of leaders being not coming off as authentic, not being inspiring, uniting all those kinds of things. I think that's possible. I think it's it's just that we've gotten the leaders we have right now aren't the right people because we've lived through kind of a long stretch of relatively comfortable times. And it feels like unfortunate if you just look at history that hard times make great leaders and easy times make like bureaucrats that are egotistical and greedy and not very interesting and not very bold. [/INST] Yeah, no I think that's fair. So you know, we may be entering one of those interesting times, you know hardship in the chinese curse sense. Yeah. So um um so I could be wrong but I mean there have been some efforts to uh explore solar geoengineering. Uh There was a a plan to send up some balloons, high altitude balloons to take some measurements uh in Scandinavia that got um squashed by objections from people who lived up there uh who uh who were just opposed to the whole program on principle. Um So we'll see a lot more of that and it's gonna be a hard program to advocate for just because I think people don't quite understand how much carbon dioxide is in the atmosphere and how far we are from even slowing down the rate that we're adding more to say nothing of bringing that number down. We're a long way out from that, </s><s>[INST] do you see in terms of portfolio of solutions us becoming a multi planetary species as part of that? Is this also being a motivator for investing some percent of GDP into becoming a multi planetary species? And what percent should that be? You think, you [/INST] know, in an indirect way maybe? I mean, you know what people will say, which is the same argument that has been leveled against space exploration since the Apollo program, which is why we solve our problems here on earth before we uh spend money going into space. So, I've never been a believer in that, that argument. Um I think um there could be a sense in which the new perspective that could be obtained by uh you're thinking about like if we're thinking about terra forming mars, changing its atmosphere, making it more amenable to to life and survival, um you can see that may be changing people's opinions about terraforming the Earth. </s><s>[INST] Yeah, there are some dangerous consequences to this particular uh idea of blasting software of geoengineering, um what do you make of sort of big bold ideas that have uh that are double edged sword, are all ideas like this. All big ideas like this. They have uh they have the potential to have highly beneficial consequences in a potential to have highly destructive consequences. [/INST] I wouldn't say all I think, you know, going back to the What we were talking about earlier, you know how technology developed in the 50s and 60s there was a period of time there when um people maybe had unrealistic ideas about new technology and weren't sufficiently attentive to the possible downsides. So um so we got um and and there's a reason why, I mean the the there's you know in in the mid 20th century we saw you know antibiotics, we saw the polio vaccine, we saw uh just simple things like refrigerators in the home, you know? Um my grandmother to her dying day called the refrigerator the icebox. Because when she grew up it was a box with ice in it. So you see all that change and it's largely for the benefit of people. And so if somebody comes along and says hey we're going to build nuclear reactors to to make energy or um here's a new um chemical called D. D. T. That's going to kill mosquitoes then um it's easy to uh to just buy into that and not be alert to the possible downsides. And of course we know that um the the way that those early reactors were built and the way that the supply chain was built to create the fuel um and deal with the waste um was poorly thought out. And uh and we're still dealing with the resulting problems that places like Hanford in the state of Washington and we know that uh d d t although it did kill a lot of insects um also had terrible effects on bird populations. Um, so the kind of backlash that happened in the seventies, that is still kind of going on is to sort of assumed that everything is a double edged sword and always to look for. You know, we have to absolutely convince ourselves that the, the downside uh isn't gonna come back and bite us before we can adopt any new technology. And I think the people, people are overly sensitized to that now. </s>

<s>[INST] Well, there's still mysterious, difficult scientific questions of things like consciousness. So, what to you? Does the question of consciousness, how does it come into play into this debate? [/INST] So, I don't believe that consciousness is the sole criterion by which we judge the self interest in human life. So we are unconscious a good deal of our lives, right? That that does not, we will be conscious again, right? When, when you're unconscious, when you're asleep, for example, presumably your life is still worth living. If somebody came in and killed you, that would be a serious moral quandary at the very least. </s><s>[INST] But the birth of consciousness, the the lighting up of the flame, the initial lighting of the flame, that does seem to be something special about that. And it's a it's a mystery of when that happens. Well, [/INST] I mean, Peter Singer makes the case that basically self consciousness doesn't exist until you're 2.5. Right? So he says that even infanticide should be okay, and he's a bioethicist over Princeton. So, you get in some real dicey territory once you get into conscious Also, the truth is that consciousness is more of a spectrum than it is a it is a dividing line, meaning that there are people with various degrees of brain function. We don't actually know how conscious they are. And you get into eugenic territory pretty quickly when we start dividing between lives that are worth living based on levels of consciousness and lives are not worth living based on levels of consciousness. </s><s>[INST] Do you find it the the aspect of women's freedom, Do you feel the tension between that ability to choose the trajectory of your own life versus um the rights of the unborn child. [/INST] in one situation, 1 situation, no. If you've had sex with a person voluntarily and as a product of that, you are not pregnant? No, you've taken an action with a perfectly predictable result. Even if you took birth control, this is the way that human beings appropriated for literally all of human existence, and by the way, also how all mammals appropriate. So the idea that this was an entirely unforeseen consequence of your activity, I find I have less sympathy for you in that particular situation because you could have made decisions that would not lead you to this particular impact. In fact, this used to be the basis of marriage, right, was when when we were a apparently more terrible society. We used to say that people should wait until they get married to have sex. A position that I still hold. And the reason for that was because then if you have sex and you produce a child, then the child will grow up in a two parent family with stability. So, you know, the the not not a ton of sympathy there when it comes to rape and incest, obviously heavy, heavy sympathy. And so that's why I think you see statistically speaking, a huge percentage of americans, including many pro life americans. People who consider themselves pro life would consider exceptions for rape and incest. One of the sort of dishonest things that I think happens in abortion debates is arguing from the fringes. This tends to happen. A lot is pro choice activists will argue from rape and incest To the other 99.8% of abortions where you'll see people on the pro life side argue from partial birth abortion to all of abortion, that you actually have to take on sort of the mainstream case and then decide whether or not that's acceptable or not. </s><s>[INST] But do you the exception just ethically without generalizing it. Um, that is a valid ethically exception. [/INST] I don't hope that there should be a an exception for rape or incest because again, I hold by the bright line rule that once a human life with potential exists, then it has its own interest in life that cannot be curbed by your self interest. Um, the the only exception that I hold by is the same exception that literally all pro lifers hold by, which is the life of the mother is put in danger. </s><s>[INST] Such a tough, tough topic, because if you believe that that's the line, then we're committing mass murder [/INST] or at least mass killing. So I would say that murder typically requires a level of mens rhea that may be absent and in many cases of abortion rights, because the usual following question is we have to murder, why not prosecute the woman? And the answer is because the vast majority of people who are, who are having abortions don't actually believe that they're killing a person. They have a very different view of what is exactly happening. So, you know, I would say that there are all sorts of interesting hypotheticals that come in to play when it comes to abortion and you can play them any which way. Um, but levels, let's put this way, there are gradations of wrongs, I don't think that all abortions are equally blameworthy, even if I would, even if I would ban virtually all of them. I think that there are mitigating circumstances that makes well being wrong. Some abortions less morally blameworthy than others. I think that you know, there there is a I can admit a difference between between killing a two week old embryo in the womb and stabbing a seven year old in the face. Like I can I can recognize all that while still saying, I think that it would be wrong to terminate a pregnancy. </s><s>[INST] Do you think the question of one life begins? Which I think is a fascinating question. Um, is the question of science or a question of religion. [/INST] I mean, when life begins is a question of science, when when that life becomes valuable enough for people to want to protect it, uh, is gonna be a question that is beyond science. Science doesn't have moral judgments to make about the value of human life. This is one of the problems that Sam Harris and I have had this argument many times. And it's always kind of interesting because because Sam is of the opinion that you can get to ought from is right. That Science says is therefore we can learn also human flourishing is the goal of life. And I always say to him, I don't see where you get that from evolutionary biology. You can you can you can assume it just say you're assuming it, but don't don't pretend that that is a conclusion that you can draw straight from biological reality itself because obviously that doesn't exist in the animal world, for example, nobody assumes the innate value of every end. </s>

<s>[INST] It's still crazy that we can get a lot of information from that. [/INST] Crazy right? And it's crazy for a lot of other reasons because again you have to line up the sun and your target, you only have one telescope for target because every star is behind the sun in a different way. So it's a lot of complicated things. But what about the second the second one? It's called Star shot, you know Star shot means like big dreams and it's an initiative by the breakthrough foundation and star shot is the concept to send thousands of little tiny spacecraft which they now call star chip instead of starship. Starship and there's a little chip and the starship so like sending like thousands of little turtle spin born, they're not all going to make it because he used to send lots of them and each of these starships once they're launched into I guess low earth orbit, they will deploy a solar sail that's a few meters in diameter and they use it on Earth. We would have a bank of this one is still a bit on the other side of the line but we have a bank of telescopes with lasers, they'll be like a gigawatt power and these lasers would momentarily shine upwards and accelerate. They'd hit these sales, they'd be like a power source for the sale And would accelerate the sales to travel at about the 20th the speed of light </s><s>[INST] and that is that as crazy as [/INST] well like any good well like any good engineering project, it has to be broken down into the crazy parts and the breakthrough initiative like to their huge credit is sponsoring, You know, getting over these actually they've listed initially they listed 19 challenges. It's broken down to concrete things like one of them is well you have to buy the land and make sure the airspace is okay with you sending up that much power over head. Another one is you have to have material on the sale where the lasers won't just vaporize it and so there's a lot of, a lot of issues anyway, these sales will be accelerated to 20. The speed of light And their journey to the nearest star would now wouldn't would no longer be tens of thousands of years but could be 20 years. Okay, 20, so it's not not as bad as tens of thousands and this these thousands or whatever, however many make it, they'll go by the nearest star system and snap a few snaps some images and radio the information back to Earth because they're traveling so fast, they can't slow down but they'll zoom by, take some photos, send it back but see just what I want you to pause on for a second is that just by making that a real concept and the money given won't make it happen. But what it's done is it's planted the seed and it's shifted that line from what is crazy to what is a real project. It's shifted it just ever so slightly enough I think to plant the seed that we have to find a way to somehow find a way to get there. </s><s>[INST] That is again to stay on that that is so powerful. Take a big crazy idea and break it down into smaller crazy ideas ordered in a list and knock it out one of the time. Uh I don't know, I've never heard anything more inspiring from an engineering perspective because that's how you solve the impossible things. So you open your new book discussing rogue planet P. S. O. J. 3 18. I never said this out loud 180.5 22 so a rogue planet which it's just this poetic beautiful vision of a planet that um the as you write lurches across the galaxy like a rudderless ship wrapped in perpetual darkness, its surface swept by constant storms as black skies raining molten iron. Just like the vision of that, the scary the the darkness, the just how not pleasant it is for human life. Just the intensity of that metaphor. I don't know and the reason you use that is to paint and um a feeling of loneliness I think and despair and um why maybe on the planet side why does it feel maybe it's just me, why does it feel so profoundly lonely on that kind of planet? Like what I think [/INST] it's because we all want to be a part of something part of a family or part of a community or a part of something and so our solar system and by the way I only it's sort of like a like when you treat yourself to like eating an entire tub of ice cream like I sometimes treat myself to imagine things like this and not just be so cut and dried. But when you imagine that this plan is not because I don't wanna give emotions to planet per se but the planet is not part of anything, it's somehow problem. It's just all on its own. Just kind of out there without that warm energy from its sun? It's just all alone out there. </s><s>[INST] To me it was this little discovery that I actually feel pretty good being part of the solar system. It felt like we have a son, we have like a little family and it felt like it sucked for the rogue [/INST] planet </s><s>[INST] to just floating about not floating of flying rudderless by the way. How many rogue planets are there [/INST] in your son? You don't know totally. I mean there's some rogue planets that are just born on their own. I know that sounds really weird to be, How can you be born an orphan? But they just are because most planets are born out of a disk of gas and dust around a star. But some of these small planets are like totally failed stars there so failed. They're just small planets on their own. But we think that there's probably honestly there's another path to a rogue planet. That's one that's been kicked out of its star system by other planets. Like the game of billiard balls, something just gets kicked out. We actually think there's probably as many rogue planets and stars. </s>

<s>[INST] Okay, so zooming out a little bit on the physics uh apologize for the way too big of a question, but uh huh to you from either of us, you mentioned Exxon is, you know, more sort of an engineering endeavor, right? But from a perspective of physics in general, science in general or the side of engineering, what do you think is the most to you? Like, beautiful and captivating and inspiring idea in this space [/INST] in this space. And then I'm going to zoom out a little bit more but um in this space I keep budding up against material science questions. So I over the past 10 years, I feel like every problem or interesting thing I want to work on. If you dig deep enough, you end up in material science land, which I find kind of exciting and it makes me want to dig in more there. And um I was just, you know, even for our technology, when we have to move the propellant from the tank to the tip of the emitters, we rely a lot on capillary action and you're getting into wedding and surface energies </s><s>[INST] scale of [/INST] like, yeah, I mean you're if you look further it's quantum too, but it all is, </s><s>[INST] you know, the capillary action at the quantum level. [/INST] Yeah. So I would I come back to me to, you know, material sense, There's so much we don't understand these sizes. Um and I I find that um inspiring and exciting. Um and then more broadly, you know, I remember when I learned that the same equation that describes flow over an airfoil is used to price options, the black scholes equation and and it's just a partial differential equation. But that kind of connectedness of the universe. You know, I don't want to use options pricing and the universe and the same, but you know what I mean, this connectedness I find really magical. </s><s>[INST] Yeah, the patterns that mathematics reveals seems to echo in a bunch of different places. Yes. Yeah. There's just weirdness. It's like it really makes you think, I think through definitely living a simulation, like whoever [/INST] program like that's </s><s>[INST] your conclusion is using it using like shortcuts to program it. Like they didn't just copying basis and different parts. [/INST] Yeah. Think of something new or just paste from over there. </s><s>[INST] They won't notice [/INST] my conclusion from that was I'm going to go interview for finance jobs. So I had like a little detour. </s><s>[INST] That's the back, that's the backup option. So, in terms of using cold engines, what's, what's an interesting difference between a propulsion of a rocket from Earth when you're standing on the ground to orbit and then the kind of propulsion necessary for once you get out or better to like deep space to move around. [/INST] Yes. The reason you can't use an engine like mine to get off the ground is, you know, the thrust it generates is instantaneous thrust is very small. But if you, if you have the time and can accumulate that acceleration, you can still reach speeds that are very interesting for exploration and even for emissions with humans on them. Um, an interesting direction, I think we need to go as as humans exploring space is um, the power supplies for electric propulsion are, are limiting us in that, um, you know, solar panels are really inefficient and bulky and batteries. I don't know when anybody is ever going to um, improved battery technology and a lot of people that work on that. Um, and nuclear power we could have a lot more powerful electric propulsion system. So they would be extremely fuel efficient but more instantaneous thrust to do more interesting missions. Um if we could start launching more nuclear systems. </s><s>[INST] But something that's powered nuclear powered that's the right way to say it. But isn't a small enough container that could be launched. [/INST] Yeah. So um I mean as a world we do launch spacecraft with nuclear power systems on board. But size is one consideration. It hasn't been a big focus. So the reactors and the heaters and everything are bulky and so they're really only suitable for some of the much bigger interplanetary stuff. Um So that's one issue. But then it's a whole like rat's nest of political stuff as well. </s><s>[INST] I heard I think Elon described or somebody but I think I think it was Dylan described that E. V. Tall like electrical [/INST] vertical </s><s>[INST] takeoff and landing vehicles. So basically saying rockets obviously you always interested in electric vehicles right? But he said that rockets can't uh in the near term it doesn't make sense for them to be electrical. Uh what do you see a world was the rockets that we used to get into orbit are also electric based. [/INST] Uh it's possible you can produce the thrust levels you need but you need this a much bigger power supply. And I think that would be nuclear. And the only way people have been able to launch them at all is that they're in a, you know, 100 times redundancy safe mode while they're being launched and they're not turned on until they're farther off. So if you were to actually try to use it on launch, I think a lot of people would still have an issue with that. But someday </s>

<s>[INST] in this aspect, in other aspects you have a deep interest in Cryptocurrency and distributed leisure tech in general. I talked to um metallic Budarin yesterday on this podcast. He says hi by the way, is a brilliant, brilliant person, talked a lot about Bitcoin and ethereum of course. So can you maybe linger on this point? What what do you find Appealing about Bitcoin about digital currency? Where do you see it going in the next 10, 20 years? And what are some of the challenges with respect to square, but also just bigger for our for our globally for our world, for the way we uh we think about money, [/INST] I think the most beautiful thing about it is there's no one person setting the direction um and there's no one person on the other side that can stop it. So we have something that is um pretty organic in nature and very principled in its original design. Um and uh I you know, I think the Bitcoin White paper is one of the most seminal works of computer science in the last 2030 years. Um it's poetry, I mean that's pretty cool </s><s>[INST] technology. I mean that's not often talked about sort of uh there's so much sort of hype around digital currency about the financial impact of it, but the actual technology is quite beautiful from a computer science perspective. [/INST] Yeah, and the and the underlying principles behind it that went into it even to the point of releasing it under a pseudonym. I think that's a very, very powerful statement, the timing of when it was released as powerful, it was, it was a total activist move. I mean it's it's moving the world forward and in a way that um I think is extremely noble and honorable and Enables everyone to be part of the story um which is also really cool. So you ask the question around 10 years and 20 years, I mean, I think the amazing thing is no one knows uh and it can emerge and every person that comes into the ecosystem. whether they be a developer or someone who uses it, can change its direction in small and large ways. Um and that's what I think it should be because that's what the internet has shown is possible. Now, there's complications with that of course, and um there's, you know, certainly companies that own large parts of the internet and contracted more than others and uh there's not equal access to every single person in the world just yet, but all those problems are visible enough to speak about them and to me that gives confidence that they're they're solvable in a relatively short time frame. I think the world changes a lot as we get these satellites um uh projecting the internet down on earth um because it just removes a bunch of the former constraints um and uh and really levels the playing field, but a global currency, which a native currency for the internet is a proxy for is a very powerful concept and I don't think any one person on this planet truly understands the ramifications of that. I think there's a lot of positives to it. There's some negatives as well. </s><s>[INST] I think it's possible. Sorry to interrupt you think it's possible that this kind of digital currency would redefine the nature of money to become the main currency of the world as opposed to being tied to fiat currency of different nations and sort of really push the decentralization of control of money, [/INST] definitely, but I think the bigger ramification is how it affects how society works and I think there were there there are many positive ramifications. Money outside of just money. Money money is a foundational layer that enables so much more. I was meeting with an entrepreneur in Ethiopia and um payments is probably the number one problem to solve across the continent, um both in terms of moving money across borders between nations on the continent or um the amount of corruption within the current system. Um but the lack of easy ways to pay people makes starting anything really difficult. I met an entrepreneur who started the lift slash Uber of Ethiopia and one of the biggest problems she has is that it's not easy for her writers to pay the company and it's not easy for her to pay the drivers. Um and that definitely has stunted her growth and made everything more challenging. So the fact that she's, she even has to think about payments instead of thinking about the best writer experience and the best driver experience uh is pretty telling. Um so I think as we get a more durable resilient and global standard, um we see a lot more innovation everywhere and I think there's no better case study for this than the various countries within within africa and their entrepreneurs who are trying to start things within health or sustainability or transportation or a lot of the companies that we've seen that we've seen here. So the majority of companies I met uh in november when I spent a month on the continent were payments oriented. </s><s>[INST] You mentioned there's a small tangent, you mentioned the anonymous launch of Bitcoin is a sort of profound philosophical statement, [/INST] pseudonymous </s><s>[INST] what that even means. There's a student [/INST] first as an idea, there's an identity tied to it. It's not just anonymous Nakamoto. Um so Nakamoto might represent one person or multiple people, but let me </s><s>[INST] ask, are you Satoshi Nakamoto? Just checking [/INST] if I wear what I tell you, but you slip a pseudonym is is constructed identity. Anonymity is just kind of this, you know, random, like drop something off leave. Um there's no intention to build an identity around it and well, the identity being built was a short time window. It was meant to stick around I think, and to be known and it's being honored in um you know how the community thinks about building it. Like the concept of Satoshi Satoshi is for instance, um is one such example, but I think it was smart not to do it anonymous not to do it as a real identity, but to do it as soon because I think it builds tange ability and a little bit of empathy that this was a human or a set of humans behind it. And there's there's this natural identity that I can imagine, </s>

<s>[INST] He's 16 months old. There you are watching an [/INST] off in an environment environment, he'd never seen before mechanism. How did he do that? Yes, that's a good question. How did he do that? That's why it's </s><s>[INST] like okay like you can see the the leap of genius from using one hand to perform a task to combining doing. I mean first of all manipulation, that's really difficult. It's like two hands both necessary to complete the action [/INST] and completely different and had never seen a window open for but in third somehow handle open something. Yeah. </s><s>[INST] There may have been a lot of uh slightly different failure cases that you didn't see. Yeah. Not with the window but with other objects of turning and twisting and handles. [/INST] You know, there's a there's a great counter to um you know, reinforced reinforcement learning will just give you know the robot, I give the robot plenty of time to try everything. Actually. Can I tell a little side story here? So I'm in the deepmind in London uh is just 34 years ago where um you know there's a big google building and then you go inside and you go through this more security and then you get to deepmind with the other google employees can't go and I'm in a I'm in a conference room bear conference room with some of the people and they tell me about the reinforcement learning experiment with robots. Um which um are just trying stuff out and then my robots, they're they're Sawyer's that we sold them. Uh they really like him because Sawyer's compliant and consents forces so they don't break when there's bashing into walls, they stop and they do all the stuff and you know, so you just let the robot do stop and eventually figure stuff out </s><s>[INST] by the way. So we're talking about robot manipulation, so robot arms and so on. [/INST] So it's a it's a robot just </s><s>[INST] to go what Sawyer. [/INST] So there's a robot arm that my company rethink robotics built. </s><s>[INST] Thank you for the context. Yes. Sorry. Okay of course there were indeed mine. [/INST] And you know it's in the next room. These robots are just bashing around to try and use reinforcement learning to learn how to act and what can I go see them. Oh no they're secret. All my robots that secret. </s><s>[INST] That's hilarious. [/INST] Anyway, the point is, you know this idea that you just let reinforcement learning figure everything out is so counted at how a kid does stuff. So Again story about my grandson, I gave him this this uh box that had lots of different lock mechanisms, he didn't random, you know, and he was 18 months old. He didn't randomly try to touch every surface or push everything. He found he could see what where the mechanism was. And he started exploring the mechanism for each of these different lock mechanisms. And there was reinforcement no doubt of some sort going on there. But he applied a pre filter which cut down the search space dramatically. I </s><s>[INST] wonder to what level we're able to introspect what's going on because it's also possible is you have something like reinforcement learning going on in the mind in the space of imagination. So like you have a good model of the world you're predicting and you may be running those tens of thousands of like loops, but you're like as a human, you're just looking at yourself trying to tell a story of what happened and it might seem simple, but maybe there's a lot of computation going on, [/INST] whatever it is, but there's also a mechanism that's being built happens, not just random search mechanism prunes it dramatically. Yeah, </s><s>[INST] the pruning that putting step, but it doesn't it's possible that that's so you don't think that's akin to a neural network inside of reinforcement learning algorithm, is it possible? [/INST] It's yeah. Until it's possible. I but you know, um I will be incredibly surprised if that happens. I'll also be incredibly surprised that, you know, after all the decades that I've been doing this where every every few years someone thinks now we've got it now we've got, you know, four or five years ago, I was saying, I don't think we've got it yet and everyone was saying, no you don't understand how powerful A I had people tell me you don't understand how powerful it is. Um you know, I sort of had a track record of what the world has done to think. Well this is no different from before we have bigger computers, we have bigger computers in the 90s and we could do more stuff. Yeah, </s><s>[INST] but okay, so let me, let me let me push back cause I'm, I'm generally sort of optimistic and try to find the beauty and things. Um I think there's a lot of uh surprising and beautiful things that neural networks, this new generation of deep learning revolution has revealed to me has continually been very surprising the kind of things that's able to do now generalizing that over saying like this, we've solved intelligence. That's another big leap. But is there something surprising and beautiful to you about, you know, networks that were actually, you sat back and said I did not expect this. [/INST] Oh, I think I think their performance, their performance on Image Net was </s><s>[INST] shocking. The computer vision in those early days, it was just very like, wow, okay. [/INST] That doesn't mean that they're solving everything in computer vision we need to solve or in vision for robots. What </s><s>[INST] about alpha zero and self play mechanisms and reinforcement learning. Isn't that [/INST] That was all in Donald Mickey's 1961 paper. Everything there was there which introduced reinforcement learning? Um </s>

<s>[INST] Check it out and get special holiday savings of up to $400 when you go to eight sleep dot com slash lex. This episode is also brought to you by fun dries spelled F U N D R I S E. It's a platform that allows you to invest in private real estate as you know, looking at different markets and investment opportunities and all the crazy financial stuff that's going out there in the world. I think it's a good idea to diversify and uh, that's why private real estate is an interesting place to diversify in. And of course when you do that kind of diversification, you should be using the services that make it super easy. You don't need to be uh an expert in what it's required in this kind of investment. You don't need to go to super complicated paperwork and so on. They vet everything for you. They figure out what are good real estate projects to invest in and make it super easy for you to do So. Over 150,000 investors use it, Check it out. It takes just a few minutes to get started at fun dries dot com slash lex [/INST] The </s><s>[INST] show is also brought to you by Inside Tracker a service. I used to track biological data that comes from my body is fed in as the raw signal into machine learning algorithms, the DNA data, fitness tracker data, blood data, all that kind of stuff goes into the machine learning algorithm and gives a prediction a recommendation about what I should do with my diet and lifestyle changes. This is obviously the early steps in uh what will make the 21st century incredible. Which is the personalization, the depersonalization, both medicine, lifestyle, diet, everything, career choices, mentorship, everything should be coming from rich, raw signal coming from your body. Maybe one day coming from your brain. If you have B. C. I. S brain, computer interfaces like neuralink operating. This is such an exciting future. So I'm a huge supporter of this kind of future. If it's done right, if it's done in a way that respects people's privacy and people's rights. This is really, really a great way to help individuals optimize their life and get special savings for a limited time. When you go to Inside Tracker dot com slash lex. This show is also brought to you by athletic greens and it's a G one drink which is an all in one daily drink to support better health and peak performance. It's my zen temple that I returned to twice a day after a cup of coffee. It's the first thing I drink every day. I also drink it after a long run and it gives me a certainty that I have all my nutritional bases covered. So all the crazy kind of diet stuff I'm doing if I'm fasting, if I'm doing one meal a day, if I'm doing carnivore, just a little carb, all that kind of stuff. Or if I'm fasting for multiple days or if I'm doing crazy stretches of work or exercise. So both the mental and physical fatigue that everything I'm doing to my body in terms of challenging it. I know I have that bases covered and so it's, it's like, it's like a multivitamin but amazing multivitamin. I highly, highly recommended and plus it also tastes good. They'll give you one month supply of fish oil when you sign up at athletic greens dot com slash lex. This is the lex Friedman podcast to support it, please check out our sponsors in the description and now dear friends, Here's guido, python 3.11 is coming out very soon in it. C python claimed to be 10 to 60% faster. How'd you pull that off? And what C python? [/INST] See, Python is the last Python implementation standing also the first one that was ever created. The original Python implementation that I started over 30 years ago. </s><s>[INST] So what does it mean that python, the programming languages implemented in another programming language called C. [/INST] What kind of audience do you have in mind here? People who know programming </s><s>[INST] know there's somebody on a boat that's into fishing and they've never heard about programming, but also some world class programmers, you're gonna have to speak to both. Imagine a boat with two people. One of them has not heard about programming is really into fishing. And the other one is like an incredible Silicon Valley programmer that's programmed in everything. C C plus plus python, rust, java. Who knows the entire history of programming languages. So you're gonna have to speak to both. I [/INST] imagine that boat in the middle of the ocean. I'm gonna please the guy who knows how to fish first. Yes, </s><s>[INST] please. He seems like the most useful in the middle of the ocean. You got you got to make him mad. [/INST] I'm sure he has a cell phone. So he's probably very suspicious about what goes on in that cell phone. But he must have heard that inside his cell phone is a tiny computer and a programming language is computer code that tells the computer what to do. It's </s><s>[INST] a very low level language. It's zeros and ones and then there's assembly. [/INST] Oh yeah, we don't talk about these really low levels because those just confuse people. I mean when we're talking about human language, we're not usually talking about vocal tracks and how you position your tongue. I was talking yesterday about how when you have a chinese person and they speak english, this is this is a bit of a stereotype. They often don't know or they can't can't seem to make the difference. Well between an L. And an R. And I have a theory about that and I've never checked this with linguists uh that it probably has to do with the fact that in chinese there is not really a difference. And it could be that there are regional variations in how china native chinese speakers pronounce that one sound. That Sounds to L. to some like L. two. Some of them like hard to others. So </s>

<s>[INST] then the work is been talked about like you take a really high dose, you take a journey and then the breakthroughs come from when you return from the journey and like integrate quote unquote that experience. [/INST] I think that's where all the and again we're babies at this point. But my gut tells me yeah that that it's the it's the so called integration, the aftermath. We know that there's some form different forms of neural plasticity that are unfolding in the days following a psychedelics at least in animals, probably going on humans. We don't know if that's related to the therapeutic effects. My gut tells me it is although it's it's only part of the story. But we need big studies where we compare people like let's get 100 people like that. Scientists that are working on a problem and then randomize them to and then I think you need a um even more incredible, you know, active controls are active placebo conditions to kind of tease this out. Um and then also in conjunction with that and you can do this in the same study, you want to combine that with more rigorous sort of um experimental models where we actually get their problem solving tasks that we know, for example, that you tend to do better on after you've gotten a good night's sleep versus not. And my sense is there's a relationship there, you know, people go back to first Principles, you know, questioning those first principles they're operating under and um you know, getting away from their prior is in terms of creative problem solving and so, you know, I think wrap those things and you can speak a little more rigorously about those because ultimately, if everyone's bringing their own problem, that's that's I think that's more in the face of valid side. But you can't dig in as much and get as much experimental power and speak to the mechanisms as you can with having everyone do the same sort of, you know, can, you know, problem solving tasks. </s><s>[INST] So we've been speaking about psychedelics generally, is there one you find from the scientific perspective or maybe even philosophical perspective most fascinating to study [/INST] therapeutically. I'm most interested in psilocybin and LSD and I think we need to do a lot more with LSD because it's mainly been psilocybin in the modern era. I've recently gotten a grant from the hefter research institute to do an LSD studies so I haven't started it yet but I'm going through the paperwork and everything and </s><s>[INST] therapeutic meaning there's some issue and you're trying to treat that issue right right. [/INST] In terms of just like what's the most fascinating, you know understanding the nature of these experiences if you really want to like wrap your head around what's going on when someone has an a completely altered sense of reality and sense of self. They are. I think you're you're talking about the the the high dose either smoked vaporized or intravenous injection which all kind of they're very similar pharmacologically of D. M. T. And five meth oxy D. M. T. This is like when people this is what you know if you're familiar with Terence McKenna, he would talk a lot about smoking D. M. T. Joe Rogan has has talked a lot about that. People will say that and there's a close relative called five meth Oxy gMT. Most people who know the terrain will say that's that's an order of magnitude or orders of magnitude beyond. I mean anything one could get from even a high dose of psilocybin or LSD. Um I think it's a question about whether you know how therapeutic I think there is a therapeutic potential there, but it's probably not as sure of a bet because one goes so far out. It's almost like you're not contemplating their relationship and their direction in life. They are like reality is ripping apart at the seams and the very nature of the of the self and of the sense of reality. And the amazing thing about these compounds seem to a lesser degree with the you know with oral sell Simon and LSD is that unlike some some other drugs that that really throw you far out there um you know anesthetics and and even even alcohol like it as reality starts to become different at higher and higher doses. There's there's this numbing, there's this sort of there's this ability for the sense of being the center, having a conscious experience that's memorable that is maintained throughout these classic psychedelic experiences. Like one can go as far so far out while still being aware of the experience and remembering the experience </s><s>[INST] interesting. So being able to carry something back? Right can you dig in a little deeper, like what is uh D. M. T. How long is the trip usually like how much do we understand about it? Is there something interesting to say about just the nature of the experience and what we understand about it? [/INST] One of the common methods for people to use it is to is to smoke it or vaporize it and it usually takes this is a pretty good kind of description of what it might feel like on the ground. Um The caveat is it's it's it's a completely insufficient description and someone is going to be listening, it was done. It's like nothing you could say it's going to come close, but it will take about three big hits inhalations in order to have what people call a breakthrough dose. Um and there's no great definition of that, but basically meaning moving away from, you know, not just having the typical psilocybin or LSD experience where like things are radically different, but you're still basically a person in this reality to go in somewhere else. And so that will typically take like three hits and this stuff comes on like a freight train. So one takes a hit and around the time of the first exhalation. So we're talking about a few seconds in or maybe just, you know, sometime between the first and the second hit, like it will start to come on and they're already up to that say um You know what they might get from a 30 mg or or 300 microgram LSD trip. A big trip, They were already there when at the second hit, but they're going their consciousnesses gear, this is like acceleration, not speed to speak of physics, okay, It's like you just those receptors are getting filled like that and they're going from 0 to 60 and like, you know Tesla time and at the second hit again there at this maybe the strongest psychedelic experience I've ever had. And then if they can take that third hit and some people can't, they're I mean they're they're propelled into this other reality and the nature of that other reality, it will will will differ depending on who you ask. But you know, folks will talk often talk about and and we've done some survey research on this entities of different types. Elves tend to pop up all the caveat is I I strongly presume all of this is culturally influenced, you know? But thinking more about the psychology and neuroscience, there is probably something fundamental, you know, like for someone that might be colored as elves, others it might be colored as um Terence McKenna called himself dribbling basketballs for someone else that it might be little animals or someone else, it might be aliens. Um I think that probably is dependent on who they are and what they've been exposed to. But just the fact that one has the sense that they're surrounded by autonomous entities, </s>

<s>[INST] So for a package, port it to Mojo, and then create a Python interface. So how do you just link on these packages, NumPy, PyTorch, TensorFlow? How do they play nicely together? So is Mojo supposed to be? Let's talk about the machine learning ones. Is Mojo kind of vision to replace PyTorch and TensorFlow to incorporate it? [/INST] What's the relationship in this? All right, so take a step back. So I wear many hats. So you're angling it on the Mojo side. Mojo's a programming language, and so it </s><s>[INST] can help solve the C, C++, Python view that's happening. The FireMojo got me. I'm sorry. We should be talking in modular. [/INST] Yes, yes, yes. OK, so the FireMojo is amazing. I love it. It's a big deal. The other side of this is the FireMojo is in service of solving some big AI problems. And so the big AI problems are, again, this fragmentation, this hardware nightmare, this explosion of new potential, but it's not getting felt by the industry. And so when you look at how does the modular engine help TensorFlow and PyTorch, it's not replacing them. In fact, when I talk to people, again, they don't like to rewrite all their code, you have people that are using a bunch of PyTorch a bunch of TensorFlow. They have models that they've been building over the course of many years. And when I talk to them, there's a few exceptions, but, generally, they don't want to rewrite all their code. And so what we're doing is we're saying, OK, well, you don't have to rewrite all your code. What happens is, the modular engine goes in there and goes underneath TensorFlow and PyTorch. It's fully compatible and just provides better performance, better predictability, better tooling. It's a better experience that helps lift TensorFlow and PyTorch and make them even better. I love Python, I love TensorFlow, I love PyTorch, right? This is about making the world better </s><s>[INST] because we need AI to go further. But if I have a process that trains a model and I have a process that performs inference on that model and I have the model itself, what should I do with that in the long arc of history in terms of if I use PyTorch to train it, should I rewrite stuff in Mojo? [/INST] Would that, if I care about performance? Oh, so I mean, again, it depends. So if you care about performance, then writing in a Mojo is gonna be way better than writing in Python. But if you look at LLM companies, for example, you look at OpenAI rumored and you look at many of the other folks that are working on many of these, many of these LLMs and other like innovative machine learning models, on the one hand, they're innovating in the data collection and the model billions of parameters and the model architecture and the RLEHF and the like all the cool things that people are talking about. But on the other hand, they're spending a lot of time writing CUDA kernels. And so you say, wait a second, how much faster could all this progress go if they were not having to hand write all these CUDA kernels? And so there are a few technologies that are out there and people have been working on this problem for a while and they're trying to solve subsets to the problem, again, kind of fragmenting the space. And so what Mojo provides for these kinds of companies is the ability to say, cool, I can have a unifying theory. Right, and again, better together, the unifying theory, the two-world problem or the three-world problem or the n-world problem, like this is the thing that is slowing people down. And so as we help solve this problem, I think it will be very helpful </s><s>[INST] for making this whole cycle go faster. So obviously we've talked about the transition from Objective-C to Swift, have designed this programming language. And you've also talked quite a bit about the use of Swift for machine learning context. Why have you decided to move away from maybe an intense focus on Swift for the machine learning context versus sort of designing a new programming language [/INST] that happens to be a super-service? You're saying this is an irrational set of life choices I make, or what? </s><s>[INST] Did you go to the desert and did you meditate on it? Okay, all right. No, it was bold and needed. And I think, I mean, it's just bold. And sometimes to take those leaps [/INST] is a difficult leap to take. Yeah, well, so, okay. I mean, I think there's a couple of different things. So, actually I left Apple back in 2017, like January of 2017. So it's been a number of years that I left Apple. And the reason I left Apple was to do AI. Okay, so, and again, I won't comment on Apple and AI, but at the time, right, I wanted to get into and understand and understand the technology, understand the applications, the workloads, and so I was like, okay, I'm gonna go dive deep into applied AI and then the technology underneath it, right? </s><s>[INST] I found myself at Google. [/INST] And that was like when TPUs were waking up. Exactly, and so I found myself at Google and Jeff Dean, who's a rock star, as you know, right? And in 2017, TensorFlow is like really taking off and doing incredible things. And I was attracted to Google to help them with the TPUs, right, and TPUs are an innovative hardware accelerator platform, have now, I mean, I think proven massive scale and like done incredible things, right? And so one of the things that this led into is a bunch of different projects, which I'll skip over, right? One of which was this Swift for TensorFlow project, right? And so that project was a research project. And so the idea of that is say, okay, well, let's look at innovative new programming models where we can get a fast programming language, we can get automatic differentiation into language, let's push the boundaries of these things in a research setting, right? Now that project, I think lasted two, three years. There's some really cool outcomes of that. So one of the things that's really interesting is, I published a talk at an LLVM conference in 2018. Again, this seems like so long ago about graph program abstraction, which is basically the thing that's in PyTorch 2. And so PyTorch 2, with all this Dynamo real thing, it's all about this graph program abstraction thing from Python bytecodes. And so a lot of the research that was done ended up pursuing and going out through the industry and influencing things. And I think it's super exciting and awesome to see that. But the Swift for TensorFlow project itself did not work out super well. And so there's a couple of different problems with that. One of which is that you may have noticed Swift is not Python. There's a few people that write Python code. Yes. And so it turns out that all of ML </s>

<s>[INST] you see yourself being able to be relaxed through that kind of storm. Well, I guess I [/INST] remember being, being, being savagely beaten is very well at the </s><s>[INST] time, the timing of that answer was like, okay, that's a dumb question, that's ultimately the goal of jujitsu is to be relaxed to the fire [/INST] for sure. And remember, like every UFC fighter I win all hypothetical matchups. Yeah, </s><s>[INST] that's true, uh since uh I wanted to ask ridiculous questions and we've been talking about sci fi and all that kind of stuff. Let me ask the kind of big question that everybody disagrees about. Certainly with me is who are the top five greatest m m a fighters of all time? And uh, why is fate or number one? [/INST] Okay, well, first off Fedor is number one. I really agree right there with you. Really? Yeah. Talk about people that just get completely underappreciated, even </s><s>[INST] though he's never been like, he's never succeeded in the UFC. [/INST] It's not his fault. It came along after him at the time that at the time that Fedor was at his height, the UFC was not where it was at for heavyweight fighting. I mean, not that there weren't good heavyweights there, but Fedor Federal is unbelievable, you know, I mean, remember I mean, Ministering O'Gara, I was a massive fan of him. I still remember watching uh what is it Pride 2004 when, when Nogueira fought Cro cop and got blasted with that left kick and dropped with like seconds left in the first round. Pride was great. Set a 10 minute first round in that five minutes second, which again materially alters alters the fight big time. And, you know, the texture of the fight because it's totally it's borderline of different sports, you know, Then then getting a five a pause in the five. But anyway, uh similar sports, like one of those swimming things, they have nine gold medals for different types of swimming, right? But still swimming. But anyway, uh </s><s>[INST] Uh yeah, that they would disagree. Yeah, I mean, I'm not saying that it's totally true. 10 minutes is different than, [/INST] I'm sorry, I don't, don't, don't drown me swimmers. I don't swim very well. It's easy to downplay it. But anyway, uh uh yeah, and then better </s><s>[INST] than Jon jones, like the modern era. [/INST] Well, I mean, I guess it's, it's tough to computer to compare across eras. It would be like going and saying like, oh man, how how would such and such great grappler from today fare against someone from 1995 I'm like, well, probably pretty well for them depending upon who they are, what's going on. You know, there's some people that with their skill sets, my transition across eras, but a lot of times not, but that's not fair. We get that. They'll be like comparing Spartans to modern day, you know, like army guys, like, well, who's gonna win? Like we'll do modern day army guys get modern day weapons. Well, yeah, but who's the toughest rugged ist group of people at the very least. So I guess it's tough to say. But at least in my mind, the people that I think about for great fighters, their their quality of opposition, um, their level of like lasting like success, the level of lasting innovation, like the courage that they have to demonstrate because again, it's like being a big fish in a small pond takes? No courage doesn't mean that there's nothing there, but it just requires something a little bit different because usually Sakurada is one of my guys too. Hi, B J Penn also, I mean, BJ penn fault Liotta Makita, that's insane. You know, it's, that was the time, it was a different sport. It was a different time in the sport where, you know, there were some guys were bouncing around doing different things, but let's, so I guess the gracie family, I mean, they never had in like, obviously hoist was there. Um, but they never, and that was definitely a different sport weight classes being open, things like that, but you have to say the horses up there. Oh no question. One of the greatest ever. I think so too. And, and again, I wouldn't be sitting here talking to you, um, if it weren't for him. So the gracie family as a whole, but I mean, who's the better? I mean, I think the horse would tell you himself probably that Nixon would have handled business back then, but they didn't put him in. So, again, he's the greatest fighter, the greatest fighter of the greatest fighter that we saw do his business. So hoist up there for sure. </s><s>[INST] What about, so this is like, nobody seems to agree with me on this, but like this connects to soccer again and messy. It seems that people value, like how long you've been a champion? How many like defenses of the championship that you've had successfully? To me, I highly value singular moments of genius. So like, like I don't, like if you look at Connor McGregor, he hasn't, I guess held been a champion very long, very much. He [/INST] didn't defend either title, right? He </s><s>[INST] didn't defend any of that either the titles. But like if you're in the same with messy, if you look at uh Leonel messi, there's just moments of brilliance unlike any other in history for both. Connor and messy and people don't seem to give credit like, well how many world cups have you on, but to me like why is it about this arbitrary world cup thing or championship thing? [/INST] I think it's easier for people to wrap their head around, right? It's like the NFL combine. When was, I mean tom Yeah, numbers, it's something, well again, if I go and if I pick tom brady in the first round, you know, and it works out, they call me a genius if I picked tom brady in the first round after his combine and it doesn't work out, I get fired and I never hired again, I have to work work somewhere else, but it's like I'm insulating myself from criticism. I think almost if I go by the numbers, well he had more bench presses, it's like, how many times have the guys that are like the super studs in the, in the NFL combine ever been on the greatest players in the NFL history, in NFL history, like zero or close to zero. And even if even if there's some, it's certainly not a 1 to 1 correlation. So it's so funny though. I think it's just like, how many, how long, how many days did you hold? The title of your title reign was x times longer, that means nothing. So if we wanted to find greatest fighter ever, like you said, I think individual moments of like, like that was transcended, that was different. That was something else because people can win or lose for any number of different reasons and that it's an interesting thing. Again, I don't blame Argentina not winning the World Cup on messy, you know, that's not fair. You know, how many times as you know, I mean, uh you remember when Trent Dilfer was the quarterback for the Baltimore Ravens and they had such a strong defense. I'm not trying to pick on Trent Dilfer, but it's like they had such a strong defense that that they were to make it, that was the Ray Lewis, you know, chris Mcalister era, you know, and they won, they won the Super Bowl. I don't think anyone is going to say that Trent Dilfer is a better quarterback than, you know, or put him in the same category as dan Marino, but he got the w he's got the he's got the super ring, how many times? Let's use March Madness or super. I love it like that. That guy always makes the finals, but he just never gets it done. So let me get this straight, get to the finals nine times doesn't count because you didn't win the end game. I'm not saying it wouldn't be better, but that guy won the game once he got over the hump. How many other times in the finals? zero. </s>

<s>[INST] So there's gonna be a bunch of applications that pop up around autonomous vehicles, some, some of which may be many of which we don't expect at all. So if you look at optimus ride, what do you think, You know the viral application that the one that really works for people in mobility? What do you think optimist ride will connect with in the near future? First? [/INST] I think that the first places that I like to target honestly is like these places where transportation is required within an environment, like people typically call a geo fence. So you can imagine like a roughly two miles by two miles could be bigger, could be smaller type of environment and there's a lot of these kinds of environments are typically transportation deprived, the Brooklyn Navy yard that, you know, we're in today, we're in a few different places, but that's, that was the one that was last publicized. That's a good example. So there's not a lot of transportation there. Um and you wouldn't expect like, I don't know, um I think maybe operating an Uber there ends up being sort of a little too expensive or when you compare it with operating Uber elsewhere, um that becomes the elsewhere becomes the priority and these people's place has become totally transportation deprived. And then what happens is that, you know, people drive into these places and to go from point A to point B inside this place within that day, they use their cars and so we end up building more parking for them to for example, take their cars and go to lunch place. And I think that one of the things that can be done is that you can put in efficient, Safe, Sustainable Transportation Systems into these types of places 1st and I think that you could deliver mobility in an affordable way, affordable, accessible sustainable way. But I think what also enables is that this kind of effort money area land that we spend on parking, you could reclaim some of that and that is on the order of like even for a small environment like two miles by two miles, it doesn't have to be smack in the middle of new york. I mean anywhere else. You're talking tens of millions of dollars if you're smack in the middle of new york, you're looking at billions of dollars of savings just by doing that and that's the economic part of it. And there's a societal part, right? I mean, just look around, I mean, um the places that we live are built for cars, it didn't look like this just like 100 years ago, like today, no one walks in the middle of the street, it's four cars. We no one tells you that growing up, but you grow into that reality. And so sometimes they close the road, it happens here, you know, like the celebration, they closed the road. Still people don't work in the middle of the road, like just walk in and people don't, but I think it has so much impact the, the car in the space that we have. And, and I think we talked about sustainability livability. I mean, ultimately these kinds of places that parking spots at the very least could change into something more useful or maybe just like park areas, recreational. And so I think that's the first thing that, that we're targeting. And I think that we're getting like a really good response, both from an economic societal point of view, especially places that are a little bit forward looking and like for example, Brooklyn Navy Yard, they have tenants. Um there's distinct miracle, like new lab. It's kind of like an innovation center, there's a bunch of startups there. And so, you know, you get those kinds of people and you know, they're, they're really interested in um sort of making the environment more livable and these kinds of solutions that optimist right, provides almost kind of comes in and becomes that and many of these places that are transportation deprived, you know, they have, um they actually ran shuttles and so, you know, um you can ask anybody, the shuttle experience is like terrible people hate shuttles. Um and I can tell you why it's because you know, like the driver is very expensive in a shuttle business. So what makes sense is to attach, 2030 seats to a driver and a lot of people have this misconception, they think that shuttle should be big. Sometimes we get that are optimists, right? We tell them we're going to give you like four cedar, six cedars and we get asked like how about like 20 cedars? Like, you know, you don't need 20 cedars, You want to split up those seats so that they can travel faster and the transportation delays would go down. That's what you want. If you make it big, not only you will get delays in transportation, but you won't have an agile vehicle, it will take a long time to speed up, slow down and so on. You need to climb up to the thing, so it's kind of like really hard to interact with </s><s>[INST] and scheduling to perhaps when you have more smaller vehicles, it becomes closer to Uber where you can actually get a personal, I mean just the logistics of getting the vehicle to you, it becomes easier when you have a giant shuttle, there's fewer of them and it probably goes on a route, a specific route that is supposed to hit [/INST] and when you go on a specific route and all seats travel together um versus you know, you have a whole bunch of them, you can imagine the route you can still have, but you can imagine you split up the seats and instead of, you know them traveling like I don't know a mile apart, they could be like, you know, half a mile apart if you split them into two, that basically would mean that your delays when you go out, you won't wait for them for a long time and that's one of the main reasons or you don't have to climb up. The other things that I think if you split them up in a nice way and if you can actually know where people are going to be somehow, you don't even need the app. A lot of people ask us the app, we say, why don't you just walk into the vehicle? How about you? Just walk into the vehicle, it recognizes who you are and it gives you a bunch of options of places that you go and you just kind of go there. I mean people kind of also internalize the apps, everybody needs an app. It's like you don't need an app, you just walk into </s>

<s>[INST] Do you think you'll be surprised to see what the 20 like if we were to travel in time 100 years into the future. Do you think you'll be able to like if I gave you a month to like talk to people? No like let's say a week, would you be, would you be able to understand what the hell is going on? [/INST] I mean if I was there for a </s><s>[INST] week, Yeah, if you over there for a [/INST] week, 100 years in the future. Yeah. </s><s>[INST] So like, so I'll give you one thought experiment is like, isn't it possible that we're all living in virtual reality by then? [/INST] Yeah, no, I think that's very possible. You know, I've played around with some of those VR headsets and they're not great, but I mean, the average person spends many waking hours staring at screens right now, You know, they're kind of low Rez compared to what they could be in 30 or 50 years. Um but certainly games and why not? Uh any other interactions could be done with VR and it would be a pretty different world. And we'd all, you know, in some ways be as rich as we wanted, You know, we could have castles and could be traveling anywhere we want. Um and it could obviously be multi sensory. So that would be, it would be possible. And, you know, there's people, you know, uh you've had Elon musk and others, you know, there are people Nicb Ostrom, you know, makes the simulation argument that maybe we're already there already there. </s><s>[INST] So, but in general, or do you not even think about this kind of way? You're self critically thinking, how good are you, as an economist at predicting what the future looks like [/INST] It starts getting. I mean, I feel reasonably comfortable next, you know, 5, 10, 20 years in terms of um that path when you start getting truly superhuman artificial intelligence um Kind of by definition be able to think of a lot of things that I couldn't have thought of and create a world that I couldn't even imagine. And uh so I'm not sure I can I can predict what that world is going to be like. One thing that ai researchers, safety researchers worry about is what's called the alignment problem. When an Ai is that powerful then um they can do all sorts of things. We really hope that their values are aligned with our values. And it's even tricky to finding what our values are. I mean first off we all have different values and secondly maybe if we were smarter we would have better values. Like You know I like to think that we have better values than he did in 1860. Um and or in you know the year 200 BC on a lot of dimensions, things that we consider barbaric today and it may be that if I thought about it more deeply I would also be morally evolved. Maybe I'd be a vegetarian or or do other things that right now whether my future self would consider kind of immoral. So um that's a tricky problem getting the A I to do what we want, assuming it's even a friendly ai I mean I should probably mention there's a nontrivial other branch where we destroy ourselves right? I mean there's a lot of exponentially improving technologies that could be ferociously destructive. Um whether it's in nanotechnology or biotech and weaponized viruses, ai and other things that nuclear weapons, nuclear weapons of </s><s>[INST] course, the old school [/INST] technology, good old good old nuclear weapons that could uh could be devastating or even existential um new things yet to be invented. So that's a branch that, you know, I I think it is pretty significant. And there are those who think that one of the reasons we haven't been contacted by other civilizations, right. Is that is that once you get to a certain level of complexity and technology, there's just too many ways to go wrong. There's a lot of ways to blow yourself up and people or I should say species end up falling into one of those traps. The great filter, </s><s>[INST] the great filter. I mean, there's an optimistic view of that. If there is literally no intelligent life out there in the universe, or at least in our galaxy, that means that we've passed at least one of the great filters or some of the great filters that we survived. [/INST] Yeah, I think I think Robin Hanson has a good way of maybe others have a good way of thinking about this, that If there are no other intelligence creatures out there and that we have to be able to detect one possibility is that there's a filter ahead of us and when you get a little more advanced, maybe in 100 or 1000 or 10,000 years, things just get destroyed for some reason. The other one is the great filters behind us that will be good is that most planets don't even evolve life, or if they don't evolve life, they don't involve intelligent life. Maybe we've gotten past that. And so now maybe we're on the good side of the of the great filter. </s><s>[INST] So, uh, if we sort of rewind back and look at the thing where we could say something a little bit more comfortably at five years and 10 years out, you've written about jobs and uh, the impact on sort of our economy and the jobs in terms of artificial intelligence that might it might have. It's a fascinating question. What kind of jobs are safe? What kind of jobs are not? He may be. Speak to your intuition about how we should think about ai changing the landscape of work. [/INST] Sure, Absolutely. Well, this is a really important question because I think we're very far from artificial general intelligence, which is a i that can just do the full breadth of what humans can do. But we do have human level or superhuman level, narrow intelligence, narrow artificial intelligence. Um, and, you know, obviously my calculator can do math a lot better than I can. And there's a lot of other things that machines can do better than I can. So, which is which we actually set out to address that question with tom Mitchell. I wrote a paper called what can machine learning do that was in science. And we went and interviewed a whole bunch of ai experts and kind of synthesized what they thought machine learning was good at and wasn't good at. And uh we came up with we called a rubric basically a set of questions you can ask about any task that will tell you whether it's likely to score high or low on suitability for machine learning. And then we've applied that to a bunch of tasks in the economy. Um In fact there's a data set of all the tax in the U. S. Economy believe not it's called a net. Um The U. S. Government put it together probably Bureau of Labor Statistics. They divide the economy into about 970 occupations like bus driver, economist, primary school teacher radiologist. And then for each one of them they described which tasks need to be done. Like for radiologists there are 27 distinct tasks. So we went through all those tasks to see whether or not a machine could do them. And what we found interestingly was </s>

<s>[INST] The unique elements of the three companies perhaps. [/INST] Yeah, I think Apple represents while the user please the user and um the essence of design and brand and it's the one company and perhaps the only tech company that draws people with a strong serious desire for the product and the need and the willingness to pay a premium because of the halo effect of the brand which came from the attention to detail and great respect for user needs. Microsoft represents a platform approach that builds giant products that become very strong modes that others can't do because it's well architected at the bottom level and the work is efficiently delegated to individuals and then the whole product is built by adding small parts that some together so it's probably the most effective high tech assembly line that builds a very difficult product that and the whole process of doing that is kind of a um differentiation and something competitors can't easily repeat. </s><s>[INST] Are there elements of the chinese approach in the way Microsoft went about assembling those little pieces and dominating, essentially dominating the market for a long time? Or do you see this is distinct? [/INST] I think there are elements that are the same. I think the three American companies that had or have Chinese characteristics and obviously as well as American characteristics are Microsoft, Facebook and Amazon. </s><s>[INST] Yes, that's right, amazon [/INST] because these are companies that will uh tenaciously go after adjacent markets, build up strong um product offering and and find ways to extract greater value from a sphere that's ever increasing and they understand the value of the platforms so that's the similarity and then with google, I think it's a uh genuinely value oriented company that does have a Heart and Soul and that wants to do great things for the world by connecting information and that has um also very strong technology jeans and wants to use technology and has found uh out of the box ways to use technology to deliver incredible value to the end user </s><s>[INST] who can look at google for example, you mentioned Heart and Soul ah there seems to be an element where google [/INST] is </s><s>[INST] after making the world better. There's a more positive view. I mean they used to have the slogan don't be evil and facebook a little bit more has a negative into it at least in the perception of privacy and so on. Do you have a sense of uh how these different companies can achieve? Because you've talked about how much we can make the world better in all these kinds of ways with a I what is it about a company that can make, give it a heart and soul gain the trust of the public and just actually just not be evil and do good for the world. [/INST] It's really hard and I think google has struggled with that. Um first they don't do evil mantra is very dangerous because every employee's definition of evil is different and that has led to some difficult employee situations for them. So I don't necessarily think that's a good value statement, but just watching the kinds of things google or its parent company alphabet does, uh, in new areas like health care, like, you know, eradicating mosquitoes, things that are really not in the business of a internet tech company. I think that shows that there's a heart and soul and desire to do good and willingness to put in the resources to do something when they see it's good, they will pursue it. Um, that doesn't necessarily mean it has all the trust of the users. I realized while most people would view facebook as the primary target of their recent unhappiness about Silicon Valley companies, many would put google in that category. And some have named google's business practices as um, predatory also. So it's kind of difficult to have the two parts of the body, the brain wants to do what it's supposed to do for shareholder maximize profit, and then the heart and soul wants to do good things that may run against what the grain wants to do. So in this </s><s>[INST] complex balancing that these companies have to do, you've mentioned that you're concerned about a future where too few companies like google facebook amazon are controlling our data are controlling too much of our digital lives. Can you elaborate on this concern? And perhaps do you have a better way forward? [/INST] I think I'm hardly the most vocal complainer of this. Speak. There are a lot louder complainers out there. I do observe that um having a lot of data thus perpetuate their strength and um limit competition in many spaces. But I also believe ai is much broader than the internet space. So the entrepreneurial opportunity still exists in using ai to empower um financial, retail, manufacturing, education applications. So I don't think it's quite a case of um full monopolistic dominance. That makes that totally uh stifles innovation, but I do believe in their areas of strength is hard to dislodge them. I don't know if I have a good solution, Probably the best solution is let the entrepreneurial VC ecosystem work well and find all the places that can create the next google the next facebook, so there will always be increasing number of challengers in some sense that has happened a little bit, you see Uber Airbnb having emerged despite the strength of the big three. Um, and um, and I think china is an environment maybe more interesting for the emergence because if you look at companies between, let's say 50 to $300 billion china has emerged more of such companies than the U. S. In the in the last 3 to 4 years because of the larger marketplace, because of the more fearless nature of the entrepreneurs. Um that and and the chinese giants are just as powerful as american ones. Tencent alibaba very strong. But Bytedance has emerged worth 75 billion uh and financial, while it's alibaba affiliated, it's nevertheless independent and worth 150 billion. And so I I do think if we start to extend to traditional businesses, we will see value very valuable companies. So it's probably not the case that in Uh five or 10 years we'll still see the whole world with these five companies having such dominance. </s>

<s>[INST] as we know it today. And much of the troubles of the world, including wars in different parts of the world like Ukraine is energy based. And yeah, it's just sitting right there to be solved. That said, I mean, to me personally, I think it's clear that if AGI were to be achieved, that would change the course of human history. [/INST] So AGI wise, I was, you know, I was making this decision about what do I want to focus on after VR. And I'm still working on VR regularly. I spend a day a week kind of consulting with meta and I, you know, Boz styles me the consulting CTO is kind of like the Sherlock Holmes that comes in and consults on some of the specific tough issues. And I'm still pretty passionate about all of that. But I have been figuring out how to compartmentalize and force that into a smaller box to work on some other things. And I did come down to this decision between working on an economical nuclear fission or artificial general intelligence. And the fission side of things, I've got a bunch of interesting things going that way. But it would take, that would be a fairly big project thing to do. I don't think it needs to be as big as people expect. I do think something original SpaceX sized, you build it, power your building off of it. And then the government, I think, will come around to what you need to. Everybody loves an existence proof. I think it's possible. Somebody should be doing this, but it's going to involve some politics. It's going to involve decent sized teams and a bunch of this cross-functional stuff that I don't love. While the artificial general intelligence side of things, it seems to me like this is the highest leverage moment for potentially a single individual, potentially in the history of the world, where the things that we know about the brain, about what we can do with artificial intelligence, nobody can say absolutely on any of these things. But I am not a madman for saying that it is likely that the code for artificial general intelligence is going to be tens of thousands of lines of code, not millions of lines of code. This is code that conceivably one individual could write, unlike writing a new web browser operating system. And based on the progress that AI has, machine learning has made in the recent decade, it's likely that the important things that we don't know are relatively simple. There's probably a handful of things. And my bet is that I think there's less than six key insights that need to be made. Each one of them can probably be written on the back of an envelope. We don't know what they are. But when they're put together in concert with GPUs at scale, add the data that we all have access to, that we can make something that behaves like a human being or like a living creature. And that can then be educated in whatever ways that we need to get to the point where we can have universal remote workers, where anything that somebody does mediated by a computer and doesn't require physical interaction, that an AGI will be able to do. We can already simulate the equivalent of the Zoom meetings with avatars and synthetic deep fakes and whatnot. We can definitely do that. We have superhuman capabilities on any narrow thing that we can formalize and make a loss function for. But there's things we don't know how to do now, but I don't think they are unapproachably hard. Now that's incredibly hubristic to say that it's like, but I think that what I said a couple of years ago is a 50% chance that somewhere there will be signs of life of AGI in 2030. And I've probably increased that slightly. I may be at 55, 60% now because I do think there's a little sense of acceleration there. </s><s>[INST] So I wonder what the, and by the way, you also written that I bet with hindsight, we will find that clear antecedents of all the critical remaining steps for AGI are already buried somewhere in the vast literature of today. So the ideas are already there. [/INST] I think that's likely the case. One of the things that appeals to so many people, including me, about the promise of AGI is we know that we're only drinking from a straw from the fire hose of all the information out there. I mean, you look at just in a very narrowly bounded field, like machine learning, like you can't read all the papers that come out all the time. You can't go back and read all the clever things that people did in the 90s or earlier that people have forgotten about because they didn't pan out at the time when they were trying to do them with 12 neurons. So that this idea that, yeah, I think there are gems buried in some of the older literature that was not the path taken by everything. You can see a kind of herd mentality on the things that happen right now. It's almost funny to see. It's like, oh, Google does something and open AI does something, meta does something. They're the same people that all talk to each other and they're all one upping each other and they're all capable of implementing each other's work given a month or two after somebody has an announcement of that. But there's a whole world of possible approaches to machine learning. And I think that we probably will in hindsight go back and see it's like, yeah, that was kind of clearly predicted by this early paper here. And this turns out that if you do this and this and take this result from animal training and this thing from neuroscience over here and put it together and set up this curriculum for them to learn in, that that's kind of what it took. You don't have too many people now that are still saying it's not possible or it's going to take hundreds of years. And 10 years ago, you would get a collection of experts and you would have a decent chunk on the margin that either say not possible or a couple of hundred years, might be centuries. And the median estimate would be like 50, 70 years. And it's been coming down. And I know with me saying eight years for something that still puts me on the optimistic side, but it's not crazy out in the fringes and just being able to look at that at a meta level about the trend of the predictions going down there, the idea that something could be happening relatively soon. Now, I do not believe in fast takeoffs. That's one of the safety issues that people say it's like, oh, it's going to go foom and the AI is going to take over the world. There's a lot of reasons. I don't think that's a credible position. And I think that we will go from a point where we start seeing things that credibly look like animals' behaviors and have a human voice box wired into them. It's like I tried to get Elon to say, it's like your pig in Neuralink, give it a human voice box and let it start learning human words. I think animal intelligence is closer to human intelligence than a lot of people like to think. And I think that culture and modalities of IO make the Gulf seem a lot bigger than it actually is. There's just that smooth spectrum of how the brain developed and cortexes and scaling of different things going </s>

<s>[INST] That's why there's a lot of value in a channel like number file where they basically trap a really smart person and force them to explain stuff. Brown sheet of paper. So but of course that's not scalable. It's a single channel. If they if there's anything beautiful that it could be done as people take it in their own hands, educators, [/INST] which is again circling back. I do think the pandemic will serve to force a lot of people's hands. You're going to be making online content anyway. It's happening right? Just hit that publish button and see how it goes. </s><s>[INST] Yeah, see how it goes. The cool thing about YouTube is it might not go for a while, but like 10 years later. Right? Yeah. It'll be like this is the thing, that's what people don't understand with you to at least for now, at least that's my hope with it is uh it's a leg, it's uh it's literally better than publishing a book in terms of the legacy. It will live for a long, long time. Of course, it's uh one of the things I mentioned, Joe Rogan before, it's kinda, there's a sad thing because I'm a fan, He's moving to Spotify. [/INST] Yeah, yeah, 9-digit numbers will do that to you, </s><s>[INST] but he doesn't realize that he's one person that doesn't actually care that much about money. Like having talked to him, he, it wasn't because of money, it's because he legitimately thinks that they're going to do like a better job. So there, so from his perspective, Youtube, you have to understand where they're coming from. Youtube has been cracking down on people who they, you know, Joe Rogan talks to Alex jones and conspiracy theories and Youtube is really like, careful, that kind of stuff and that's not a good feeling like, and joe didn't, doesn't feel like Youtube is on his side. Um you know, he's often has videos that they don't put in trending that like are obviously should be in trending because they're nervous about, like, you know, if this concept is this is this content going to, you know, upset people that all that kind of stuff have misinformation and that's not a good place for a person to be in and Spotify is giving them. Uh, we're never going to censor, you were never going to do that. But the reason I bring that up, whatever you think about that, I personally think that's bullshit because podcast things should be free and not constrained to a platform. It's pirate radio. What the hell? You can't as much as I love Spotify, you can't just, you can't put fences around it. But anyway, the reason I bring that up is joe is going to remove his entire library from Youtube. [/INST] Whoa. Really? That's going to </s><s>[INST] his full length, the clips are going to stay, but the full length videos are all, I mean made private or deleted. That's part of the deal. And like that's the first time where I was like, oh Youtube videos might not live forever. Like things you find like, okay, [/INST] this is why you need, uh, I PFS or something where it's like, if there's a content link are familiar with this system at all. Like right now, if you have a U. R. L. It points to a server, there's like a system where the address points to content and then it's like distributed. So you, you can't actually delete what's at an address because it's, it's content address and as long as there's someone on the network who hosts it, it's always accessible at the address that it once was. Um, </s><s>[INST] but I mean that raises a question, I'm not gonna Put you on the spot. But like somebody like the sauce, right? Spotify comes along and gives him let's say $100 billion. Okay let's say some crazy number and then removes it from YouTube. Right? It's made me I don't know for some reason, I thought youtube is forever. [/INST] I don't think it will be. I mean, you know, another variant that this might take is like uh that you know um you fast forward 50 years and uh you know, google or alphabet isn't the company that it once was and it's kind of struggling to make ends meet and you know, it's been supplanted by the whoever wins on the A. R. Game or whatever it might be. And then they're like, you know, All of these videos that we're hosting our pretty costly. So we're just we're going to start deleting the ones that aren't watched that much and tell people to like try to back them up on their own or whatever it is. Um or even if it does exist in some form forever. It's like if people are not habituated to watching YouTube in 50 years there watching something else, which seems pretty likely. Like it would be shocking if youtube remains as popular as it is now indefinitely into the future. So uh it won't be forever. </s><s>[INST] It makes me sad still. But because it's such a nice, it's just like you said of the canonical videos, [/INST] sorry to interrupt, you usually get juan benet on the thing and then talk to him about permanence. I think you would have a good conversation. Who's that? So he's the one that founded this thing called PFS that I'm talking about. And if you have him talk about basically what you're describing, like, oh, it's sad that this isn't forever, then you'll get some articulate pontification around it. It's been pretty well thought through. </s>

<s>[INST] exactly. And and then you can throw that person even anonymous into a pool of discourse and they would be better. [/INST] I think you're absolutely right. It's a very very very elegant way of stating it. </s><s>[INST] But like you said the A. G. I might be a few years away, so that's a huge investment. Like my concern, my gut feeling is this a thing we're calling A G. I. Is actually not that difficult to build technically, but it requires a certain culture and it requires a certain certain risks to be taken. [/INST] I think you could reductive lee boil down the human intellect into cognition and emotion and you know depending on who you are and depending on the moment they're weighted very differently. Obviously um cognition is so easily done by computers that we should assume that that's a solved problem. So our differentiation is the reasoning part, it's the emotional overlay. It's that it's the empathy, it's the ability to steal man the opposite person's case and and feel why that person, you know, you can forgive them without excusing what they did as an example. Um That is a very difficult thing I think, to capture in software, but I think it's a matter of when not if </s><s>[INST] if done crudely, it takes a form of censorship just banning people off the platform. Let me ask you some tricky questions. Uh do you think trump should have been removed from twitter? What's the what's the pro case? Can you, I'm having fun here, You steal man, each side, [/INST] let's steal man, get him off the platform. Here, we have a guy who um is virulent in always he promotes confrontation. Um he lacks decorum, he incites the fervent believers of his cause to act up and push the boundaries bordering on and potentially even including breaking the law, he does not observe the social norms of a society that keep us well functioning, including an orderly transition of power. If he is left in a moment where he feels trapped and cornered, he could behave in ways that will confuse the people that believe in him to act in ways that they so regret that um it could bring our democracy to an end or create so much damage or create a wound that's so deep, it will take years of conflict and years of confrontation to heal it, we need to remove him and we need to do it now. It's been too long. We've let it go on too long. The other side of the argument would be he was a duly elected person whose views had been run over for way too long and he uses the ability to say extreme things in order to showcase how corrupt these systems have become and how insular these organizations are in protecting their own class. And so if you really want to prevent class warfare and if you really want to keep the american dream alive for everybody, we need to show that the First Amendment, the constitution, the second Amendment, all of this infrastructure is actually bigger than any partisan view no matter how bad it is and that people will make their own decisions. And there are a lot of people that can see past the words he uses and focus on the substance of what he's trying to get across and more generally agree than disagree. And so when you silence that voice, what you're effectively saying is this is a rigged game and all of those things that we told, we were told were not true are actually true. </s><s>[INST] If you were to look at the crude algorithms of twitter, of course I don't have any insider knowledge, but I could imagine that they saw the let's say there's a metric that measures how negative the experiences of the platform and they probably saw uh in several ways you can look at this, but the presence of Donald trump on the platform was consistently increasing how shitty people are feeling short term and long term because they're probably yelling at each other having worse and worse and worse experience. If you even do a survey of how do you feel about using this platform over the last week, they would say horrible relative to maybe a year ago when Donald trump was not actively tweeting and so on. So here you're sitting at twitter and saying, okay, I I know everyone's talking about speech and all that kind of stuff, but I kind of want to build a platform where the users happy and they're becoming more and more unhappy, how do I solve this? Happiness problem? Well let's [/INST] ban, </s><s>[INST] let's let's uh yeah let's ban the sources of the unhappiness. Now, we can't just say you're a source of unhappiness will ban you. Let's wait until that source, say something that we can claim uh breaks our rules like incites violence or so on. [/INST] That would work if you could measure your construct of happiness properly. The problem is I think what twitter looked at were active commenters and got it confused for overall system happiness because for every piece of content that's created on the internet, of the 100 people that consume it. Maybe one or two people comment on it. And so by over amplifying that signal and assuming that it was the plurality of people, that's where they actually made a huge blunder because there was no scientific method I think to get to the answer of deplatforming him and it did expose this idea that it's a bit of a rigged game and that there are these deep biases um that some of these organizations have two opinions that are counter to theirs and to their orthodox view of the world. </s><s>[INST] So in general you lean towards keeping um first of all presidents on the platform but also controversial voices [/INST] all the time. I think it's really important to keep them there. </s>

<s>[INST] So from the perspective of computer science, you've got a chance to work the application to cancer into medicine in general from a perspective engineer and computer scientist, how far along are we from understanding the human body biology of being able to manipulate it in a way we can cure some of the melodies some of the diseases. [/INST] So this is very interesting question. And if you're thinking as a computer scientist about this problem, I think one of the reasons that we succeeded in the areas where as a computer scientist succeeded is because we don't have, we're not trying to understand in some ways, like if you're thinking about like e commerce amazon amazon doesn't really understand you and that's why it recommends you certain books or certain products correct and uh you know traditionally when people were thinking about marketing, you know, they divided the population, two different kind of subgroups, identify the features of the subgroup and come up with a strategy which is specific to that subgroup. If you're looking about recommendation systems are not claiming that their understanding, somebody there just managing to from the patterns of your behavior to recommend your product. Now, if you look at the traditional biology, obviously I wouldn't say that I uh at any way, you know, educated in this field, but you know what they see that it's really a lot of emphasis on mechanistic understanding. And it was very surprising to me coming from computer science how much emphasis is on this understanding and given the complexity of the system, maybe the deterministic full understanding of this process is is, you know, beyond our capacity. And the same way as in computer science when we're doing recognition when the recommendation and many other areas, it's just probabilistic matching process. And in some way maybe uh in certain cases we shouldn't even attempt to understand and we can attempt to understand, but in parallel we can actually do this kind of matching that would help us to find a cure or to do early diagnostics and so on. And I know that in these communities it's really important to understand, but I'm sometimes wondering what exactly does it mean to understand here? </s><s>[INST] Well, there's stuff that works and but that can be like you said separate from this deep human desire to uncover the mysteries of the universe, of of science, of the way the body works, the way the mind works. It's the dream of symbolic i of being able to reduce human knowledge into into logic and be able to play with that logic in a way that's very explainable and understandable for us humans. I mean that's a beautiful dream. So I I understand it, but it seems that what seems to work today and we'll talk about it more is as much as possible to reduce stuff into data, reduce whatever problem you're interested in to data and try to apply statistical methods, apply machine learning to that. And on a personal note, You were diagnosed with breast cancer in 2014. What it facing your mortality make you think about how did it change you? [/INST] This is a great question. And I think that I was interviewed many times and nobody actually asked me this question. I think I was 43 at a time and it's the first time I realized in my life that I may die. And I never thought about it before. And there was a long time since you diagnosed until you actually know what you have and have CV is your disease for me. It was like maybe 2 1/2 months. And I didn't know where I am during this time because I was getting different tests and one would say it's bad and I was you know, it is not. So until I knew where am I really was thinking about all these different possible outcomes. </s><s>[INST] Are you imagining the worst or were you trying to be optimistic or [/INST] it would be really I don't remember what was my thinking. It was really a mixture with many components at the time. Speaking, you know, in our terms. And one thing that I remember and you know, every test comes and you're saying, oh, it could be there. So it might not be this and you're hopeful and then you're desperate. So it's like there is a whole you know, slow of emotions that goes through. But what I remember that when I came back to MIT I was kind of going the whole time to the treatment to Emmett but his brain was not really there. But when I came back really finished my treatment and I was here teaching and everything. You know, I look back at what my group was doing, what other groups was doing. And I saw these trivialities. It's like people are building their careers on improving some parts around two or 3% or whatever. I was like, seriously, I didn't work on how to decide for eukaryotic, like a language nobody speak and whatever, like what is significant. When I was suddenly, you know, I walked out of MIT which is you know, when people really do care. You know what happened to you a clear paper, you know, what is your next publication uh to a cl to the world where people, you know, people you see a lot of suffering that I'm kind of totally shielded on it on daily basis. And it's like the first time I've seen like real life and real suffering. And I was thinking why we're trying to improve the parcel or deal with some trivialities when we have capacity to really make change. And it was really challenging to me because on one hand, you know, I have my graduate students really want to do their papers and their work and they want to continue to do what they were doing, which was great. And then it was me who really kind of reevaluated what is the importance. And also at that point, because I had to take some break. I uh Look back into like my years in science and I was thinking, you know, like 10 years ago, this was the biggest thing, I don't know, topic models that we have like millions of papers on topic models and variation topics. Models. And I was really like irrelevant. And you start looking at this, you know, what do you perceive as important, a different point of time and how, you know, it's fades over time. And uh since we have a limited time of us have limited time on us. It's really important to prioritize things that really matter to you maybe matter to you at that particular point, but it's important to take some time and understand what matters to you, which may not necessarily be the same as what matters to the rest of your scientific community and pursue that vision. </s>

<s>[INST] I see you're holding the cords on the screen. So you're doing the multi-touch sensing there. That's incredible. [/INST] I honestly cannot believe that I pulled it off because I think I was, I was, ignorance was definitely bliss because that was like, yeah, the first hardware project I'd ever built, the first iPhone app I'd ever programmed. And now, if somebody was like, hey, I want this to be my first project, I would probably be like, oh, that's a lot. </s><s>[INST] But hold it off. Because that's such an interesting thing for people to hear because it's your first project. And a lot of people stop because of the difficulty of their first project. They never truly discover their own genius because they stop at the first, and you didn't stop. So it'd be interesting to kind of psychoanalyze you on the couch of why you didn't stop. Because you have to build an app to figure out how to, did you know how to program much? Or no? [/INST] Yeah, I mean, a little bit, but I never program, </s><s>[INST] or done any iOS apps. So you have to figure out how to get forget like what the app does just get the app running and working. And then you have to figure out how to get the sensors in like real time, the finger touching. And you have to connect how to get the capacitors touch working with the might have controllers. Do you know anything about the capacitor [/INST] touch sensors at that time jet time? I mean it's pretty easy. </s><s>[INST] Now it's basically now. It's basically, everything's easy. [/INST] You know rock hits they're pretty easy. You sound like my grandma because I have and Italian grandma, and I always trying to get her, we're like trying to get her to tell her recipes, and every recipe starts with, it's very simple. </s><s>[INST] And then there's like 45 minutes of her explaining it. It's like with gymnastics at the Olympics, they make it look easy. The best people in the world always make [/INST] the impossible seem easy. I pride myself with making buildings look really hard, </s><s>[INST] because I feel like I'm always struggling so much, and struggling so much. You make the easy seem impossible. No. So how many strings was it? [/INST] Was it just possible? No. </s><s>[INST] Gosh, I mean, this is such a long time, but no, it was six. Oh, six strings, and you could touch it and then there's, [/INST] wow, and then the phone itself makes a sound? And I still think it's such a cool concept to have this like, I'm not even a guitar player. I don't know. I mean, I got the idea because I was kind of strumming </s><s>[INST] on my charge cord of my phone. [/INST] Oh, like an air guitar, but on a cord? Yeah, but I've been thinking about it, because I'm like, oh man, it would be really fun to go back to that project with what I know now. But the problem with it is that when you're producing the tension in your string just with your arm, like you can't make it taut enough to actually play. Like it kind of becomes playing these like saggy strings. So it's you're not really getting that experience. And I think that's why, I mean, I, yeah, I haven't really pursued it. </s><s>[INST] I wonder if there's a way to generate the tightness from the case itself, the device that unfolds [/INST] and then with some kind of tightening mechanisms, tightness. Yeah, but then it kind of becomes this whole thing in a guitar that it just becomes a really shitty guitar. Which this is a really shitty guitar, but it's also... Guitar, yeah. </s><s>[INST] It's not a guitar. [/INST] But it's so shitty, it's awesome. Yeah, I don't know. </s><s>[INST] But it's cool that you have an interface between a device that's capable of incredible computational power and an actual hardware thing. Is there something that you can psychoanalyze that made you finish that others could hear in their own struggle to do their first project like that? Because you were in a non-engineering person, technically. And you did a pretty cool renegade out there, [/INST] wild, no-instructions engineering project. No, it definitely was an off-road build, where it's like if you're building a Lego kit, it's very much on the road and you're following instructions and this is like, you have no idea if you're headed for a cliff or a dead end or you're gonna get stuck. I think it had a natural pressure to it because it was a school project. So it did have deadlines built into it and stuff like that. So that definitely helped. But I think also it was just so incredibly motivating when I realized that I might be able to pull it off. Like that was, I felt like a bloodhound, you know? Just like, oh my God, I can actually make this happen. And I think if I hadn't seen that, the horizon, </s><s>[INST] it would have been harder to stick through. [/INST] Were you able to see the end of the tunnel pretty early on? No, not really. </s><s>[INST] So there's something to just suffering for a while. [/INST] I don't know how your brain works, but it's like if I have a problem, I can't stop thinking about it. Like it's so fun to think about it. Like I spent two and a half years designing a coat hanger and I just can't stop thinking about it. </s><s>[INST] Like I get so into it because I think it's so much fun. Take me to this two year journey of the coat hanger. [/INST] How did it begin, what, how did it begin? How did it begin? It began with a corner in my home where I couldn't fit a coat rack. The thing is I shouldn't have brought this up because I'm gonna release it as a product </s>

<s>[INST] So first of all there's uh you have a really nice informative website rapid test dot org information on this. I still can't believe this is not more popular. It's ridiculous. Okay. But are are one of the F. A. Q. S. You have is a rapid test too expensive. So can can cost be brought down. Like I pay I take a weekly pcr test and I think I paid 100 and 60 170 bucks a week. [/INST] No I mean it's criminal. Absolutely. We can get cost this this thing right here cost less than a dollar to make with everything combined. Plus the swabs. You know maybe it costs a dollar 50 could be sold for Frankly it could be sold for $3 and still make a profit if they want to sell it for five. This one here uh This is a slightly more complicated one but you can see it's just got the exact same paper strip inside. This is really it doesn't look like much but it's kind of the cream of the crop in terms of these rapid tests. This is the one that the U. S. Government thought and it is doing An amazing job. It has a 99.9% sensitivity and specificity. So it's really it's really good. And so essentially the way it works is you just use a swab you put the ones you kind of use the swab in yourself. You put the swab into these little holes here, You put some buffer on and you close it And uh and a line will show up if it's positive and and the line won't show up if it's negative it takes 5:10 minutes. This whole thing the this this can be made so cheap that the U. S. Government was able to buy them By 150 million of them from Abbott for $5 apiece. You know, so anyone who says that these are expensive, we have the proof is right here this one at its, you know, it was Abbott did not lose money on this deal. You know, they got $750 million 150 million of these at $5 apiece. Um all of these tests can do the same. So anyone who says that this should be, you know, unfortunately what's happening though is the FDA is only authorizing all of these tests as medical devices. So what happens when you, if I'm a medical company? If I'm if I'm a test production company and I want to make this test and I go through and the FDA at the end of my authorization, the FDA says, okay, you know, you now have a medical device, not a public health tool but a medical device and that affords you the ability to charge insurance companies for it. Why would I ever as a, you know, in our capitalistic economy and and and sort of infrastructure, why would I ever not sell this for $30 when insurance will pay for it? Or $100 you know might only cost me 50 cents to make. But but by pushing all of these tests through a medical pathway at the FDA they what what extruded out. The other side is an expensive medical device that's erroneously expensive. It doesn't need to be inflated and costs. But the companies say well I'd rather make fewer of them And just sell them off for $30 apiece. Then make tens of millions of them which I could do and sell them at at a dollar uh marginal uh profit. You know. And so It's a problem with our with our whole medical industry that we see tests only as medical devices and uh you know what I would like to see is for the government in the same way that they bought 150 million of these from Abbott. They should be buying You know all of these tests that they should be buying 20 million a day and getting them out to people's homes. This virus has cost trillions of dollars to the American people. It's closed down restaurants and stores and obviously the main streets across America have shut have shuttered. It's killing people. It's killing our economy that's killing lifestyles and and it </s><s>[INST] was an obvious solution to me, this is exciting. This is like this is a solution I wish uh like in april or something like that uh to launch like the larger scale manufacturing deployment of tests. It doesn't matter what tests they are. It's obviously the capitalist system would create cheaper and cheaper tests that would be hopefully driving down to $1. So what are we talking about? America? There's, I don't know, 300 plus million people. So that means you want to be testing regularly. [/INST] Right, </s><s>[INST] So how many do you think it's possible to manufacture will be the ultimate goal to manufacture per month. [/INST] So if we want to slow this virus and actually stop it from transmitting, achieve what I call her defects like vaccine herd immunity. Heard effects are when you get that our value below one Through preventing onward transmission. If we want to do that with these tests, we need about 20 million to 40 million of them every day. Which is not a lot in the United States, in the United States. So we could do it. There's other ways you can have two people in the household uh swab each other, you know, swab themselves rather. And then mix, you know, put the swabs into the same tube and onto one test. So you can pull so you can get a two or three X gain in efficiency through pooling in the household. I could do that in schools or offices to wherever and just use a swab of a there's two people like I mean even if it's just standing in line at a public testing site or something you know you can just say okay these two are the last people to test or swab themselves. They go into one one thing and if it comes back positive then you just do each person and you know it's rapid. So you can just say to the people one of you is positive let's test you again. Um So there's ways to get the efficiency gains much better. But let's say I think that the that the optimal number right now that matches sort of what we can produce more or less today if we wanted is 20 million a day. Right now one company that I don't have their test here but one company is already producing five million tests themselves and shipping them overseas. It's an american company based in California called the nova. And they are Giving five million tests in the UK Every day. Not to the you know and this is just because there's no the the federal government hasn't authorized these tests without the </s>

<s>[INST] him. Conversation like any other. Yeah. Between two friends. [/INST] He hugs me. Yeah. Before I go, I have something to warm up. I can't remember what. And he says, hey, in my ear, I know what you do for a living. It's not a safe place for you to be. And I walk off. A few moments later, the army showed up, and you could feel the amount of rounds going off from two blocks away. We came back with our guys, and it was over. So he didn't survive that? I looked through the bodies, and the cars that were left, you know, there was bodies all over the place. </s><s>[INST] People left there, the bodies. [/INST] It was a mess that spent, like, an hour looking for him. The only way I could recognize him was his hair. I stayed with his body all night. There's a bridge in Tijuana that goes over the river in a place called La Mesa, and that's where the forensic offices were. His body was taken there, and I stayed with his body until it was released. I told his family about it because I knew them, and that aspect of, you know, us versus them, or they're the enemy, and you're like that, and my mom told me those words, nobody's against you. They're just for themselves, so don't make the mistake of dehumanizing anybody. And those roles could have been easily reversed. I could have been shot in the face there. That aspect of conflict brings where the bad guys, good guys, you know, heroes, villains, you know, there's an innocence to that that goes away. Is your mom still with us? No. Almost three weeks before I decided to quit, she passed away. Did that have a role to play? A major one. After I got done on the protection detail with the governor, like everything down there, again, the whole cycle, you know, he got his turn. So when he went away, you know, politics change, and down there, basically, if you're a gubernatorial candidate, you have either a friend, a friend of a friend or a family member be the head bodyguard guy, and the guy that won the elections had his head bodyguard guy already there. So all of us were sent back to whatever we came from. So I went back to work on the streets. I was back on the operations group. I was working with the sub director directly with him, basically, back on the ground doing the stuff that I was doing before that job. We were moving away from the successes that had been had by people like Lazola when they were in charge of that whole process to people that I used to work with. Some of the only successes in that counter push against cartels in Mexico, and you can kind of like, it's documented, you can read about it out there, a bunch of people wrote papers on it. Some of the only successes were had by Lazola and the places where he had leadership. He not only pacified Tijuana, he also did the same in Juarez. He was sent to be the police chief in Juarez too. But politics change and, you know, heroes become villains. A lot of people started calling him a villain because of his unorthodox approach and human rights violations and all of this type of stuff kind of come through the forefront. And people forgot, you know, people forgot what it took to get Tijuana off the most dangerous city list on the planet. And people were vilified, people like him. And the police force that I was a part of started getting compromised. A lot of the things that were put forth to try and keep us honest. There was a program, they had these centers called C3s. They would go there every year, you would get your financials checked, you would get a physical, psychological evaluation, you would get a polygraph exam done on you, all of the works. They'd try and see if you were somebody doing something wrong. And all of that was canceled because it violated your human rights if you get fired from a job because of a failed polygraph exam, because that was not an actual admissible way of firing somebody. So all of a sudden you had people that were known cartel compromised people that were fired five, six years ago, showing back up to work with their back paid and everything. So this started happening and I quickly realized that it was going to be hard to stay there. I was driving home from work and I got a call from my brother that my mom had been going through some health issues that had turned into psychiatric issues. So we were basically taking turns trying to take care of her, locking the door so she wouldn't wander off and stuff like that. So not only was I dealing with the job on the street, but I was dealing with that. And also I had a two-year-old and a marriage that was difficult at that time. So I was trying to figure all these things out. I made it more difficult by your job. It's not a financially secure job, you know, and the pressures that it has and the odd hours and all that made it really hard. And then all of a sudden my brother calls me and tells me that let's go to the hospital with my mom. Something happened to my mom. It wasn't my turn to watch her, so I felt pretty shitty about that. I got to the hospital and the doctors, you know, came out and told us that she was gone. It was a massive heart attack. She had a pacemaker by then, so she was gone. She was in her sixties, so, you know, we kind of expected something, but not, you know, that was like hard for me. She was my center. She was going to be the one that I would ask for advice as far as work, you know, as fast as she leaves or not. The ground was removed from underneath. There was nobody, there was, yeah, there's nothing underneath me. I get three days off work. That's what they gave me. And I'm trying to grieve as I go back to work. Dark shit crosses my mind as I'm going through that process of trying to figure things out. </s>

<s>[INST] because these mechanisms of publishing that make it easier on twitter? I mean we're evolving as a species and the internet is a very fresh thing. And so it's kind of interesting. I think that as opposed to twitter, this is what Jack also complains about, it is twitter is not innovating fast enough. And so it's almost like the people are innovating and thinking about their productive life faster than the platforms on which they operate can catch up. And so that the point the gap grows sufficiently, they'll jump a few people fumigated folks will just create an alternative and perhaps distributed perhaps just many little silos and then people jump and then we'll just continue this [/INST] kind of way. See I think like substack for example what they're going to pull out of twitter among other things is the audience that was let's say like slightly left of center. but um slightly off center don't like trump uncomfortable with like, postmodern critical theories made into political action, right? And they're like, yeah, twitter, there was people on there talking about this and it made me feel sort of heard because I was feeling a little bit like a nerd about. But honestly, I'd probably rather subscribe to four subs, you know, I'm gonna have like berries and Andrew Sullivan. I have like a jesse signals, like I have a few sub stacks I can subscribe to. And honestly, that's I'm a knowledge worker who's 32 anyways, probably that's an email all day. And so like, there's an innovation that's going to that group, you know, it's gonna suck him off, which </s><s>[INST] is actually a very large group. [/INST] Yeah, that's a lot of that's a lot of energy and then once trump's gone, I guess that's probably going to drive that drove a lot of uh more like trump people off twitter, like this stuff is fragile. So </s><s>[INST] I but the fascinating thing to me because I've hung out on parler for a short amount enough to to know that the interface matters is so fascinating. Like that, that it's not just about ideas, it's about creating like substack too, creating a pleasant experience addicting [/INST] experience, You're right, you're right about that and it's hard and that's why the interest is one of the conclusions from that India's social media article is it's just the ugliness matters and I don't mean even just aesthetically, but just the clunkiness of the interface is the um, and I don't know, it's to some degree that social media companies have spent a lot of money on this and to some degree, it's a survivorship bias, right? Like twitter, every time I hear Jack talks about this, it seems like he's as surprised as anyone else the way twitter is being used and it's basically the way, you know, they had it uh years ago and then, you know, it's great to be status is right, this is what I'm doing, you know, and my friends can follow me and see it and without really changing anything, it just happened to hit everything right </s><s>[INST] to support this other type of interaction. Well, there's also the Javascript model which Brendan Eich talked about, he's just implemented javascript uh like the crappy version of javascript in 10 days throughout there and just ah changed it really quickly, involved it really quickly and now it's become, according to stock exchange, the most popular programming language in the world that drives like most of the internet and even the back end and now mobile and so that that's an argument for the kind of thing you're talking about where like, like the bike club people could literally create the thing that would, you know, run most of the internet 10 years from now. Yeah, so there's something to that, like, as opposed to trying to get lucky or trying to think through stuff is just to, uh, to solve a particular problem, [/INST] do stuff and then do stuff, do something, keep tinkering til you love it. </s><s>[INST] Yeah. And then, uh, and of course the sad thing is timing and luck matter and that you can't really control the problem, but [/INST] You can't go back to 2007. Yeah, that's like the number one thing you could do to have a lot of success with the new platform is go back in time, 14 years. </s><s>[INST] So the thing you have to kind of think about is what is the, like, what's the totally new thing that, uh, 10 years from now, it would seem obvious. I mean, some people saying clubhouses that there's been a lot of stuff like clubhouse before, but it, it hit the right kind of thing. It's similar to Tesla, actually, what clubhouse did is it got a lot of relatively famous people on there quickly. And um, and then the other effect is like, it's invite only. So like, oh, all those, like famous people are on there, I wonder what's, it's the fomo like, fear that you're missing something really profound exciting happening there. So those social effects and then once you actually show up, I'm a huge fan of this, it's the javascript model is like, clubhouse is so dumb, like, so simple in its interface, like, you literally can't do anything except mute mute as a mute button and there's a leave quietly button and that's it. It's [/INST] kind of, I love single use technology that, </s><s>[INST] yeah, there's no, like, there's no, it's just like trivial and uh, you know, twitter kind of started like that facebook started like that, but they've evolved quickly to add all these features and so on and you know, I do hope clubhouse stays that way. [/INST] Be interesting or there, there's alternatives. I mean, I mean, even with clubhouse though, the, so one of the issues with a lot of these platforms, I think is, uh, bits are cheap enough now that we don't really need a unicorn investor model. I mean, the, the investors need that model, there's really not really an imperative of, we need something that can scale 200 million plus a year revenue. So because it was gonna require this much seed and angel investment and, and you're not going to get this much seed Angel investments, you can have a potential exit this way because you have to be part of a portfolio that depends on one out of 10 exiting here. If you don't actually need that and you don't need to satisfy that investor model, which I think is basically the case. I mean bits are so cheap, everything is so cheap. You don't know. So even like with clubhouse, it's investor back, right? This notion of like, this needs to be a major platform. Um, but the bike club doesn't necessarily need a major flat. So that's where I'm interested. I mean, I don't know, there's so much money. That's the only problem that bets against me is that you can concentrate a lot of capital if you do these things, right? So facebook was like a fantastic capital concentration machine. It's crazy how much where it even found that capital in the world, that it could concentrate and ossified in the stock price at a very small number of people have, you know, access to, Right? That's, that's incredibly powerful. So when there, when there is a possibility to, to, to consolidate and gather a huge amount of capital, that's a huge imperative. That's very hard for the bike club to go up again. So, </s>

<s>[INST] A sleep currently ships within the U. S. A. Canada and the United Kingdom. They told me to tell you this, that's a sleep dot com slash lex. This is the lex Friedman podcast And here is my conversation with Gary Nolan. You are a professor stanford studying the biology of the human organism at the level of individual cells. So let me ask first the big ridiculous philosophical question, what is the most beautiful or fascinating aspect of human biology at the level of the sell to you, [/INST] the micro machines and the nanomachines that proteins make and become, that to me is the most interesting. The fact that you have this basically dynamic computer within every cell that's constantly processing its environment. And at the heart of it is D. N. A. Which is a dynamic machine, a dynamic computation process. People think of the D. N. A. As a linear code. It's codes within codes within codes and it is the actually the epigenetic state that's doing this amazing processing. I mean if you ever wanted to believe in God, </s><s>[INST] just look inside the cell, the DNA is both information and computer. Exactly. How did that computer come about? A big continuing the philosophical question that it's this both scientific and philosophical, how did life originate on earth do you think? How did this guy at every level. So the very first step and the fascinating complex computer that is D. N. A. That is multicellular organism. And then maybe the fascinating uh complex computer that is the human mind. [/INST] Well, I think you have to take just one more step back to the complex computer that is the universe, right? All of the the so called particles or the waves that people think the universe is made of and appears to me at least to be a computational process and embedded in that is biology. Right? So all the atoms of a protein etcetera sit in that computational matrix. From my point of view, it's computing something. It's computing towards something it was created in some ways. If you want to believe in God and I don't know that I do. But if you want to believe in something the universe was created or at least enabled to allow for life to form. And so the D. N. A. If you ask where does DNA come from and you can go all the way back to Richard Dawkins and the selfish gene hypotheses. The way I look at D. N. A. Though is it is not a moment in time. It assumes the context of the body and the environment in which it's going to live. And so if you if you want to ask a question of where and how does information get stored? D. N. A. Although it's only three billion base pairs long contains more information, then I think the entire computational memory resources of our current technology because who and what you are is both what you were as an egg all the way through to the day you die. And it embodies all the different cell types and organs in your body. And so it's a computational reservoir of information and expectation that you will become. So actually I would sort of turn it around a different way and say if you wanted to create the best memory storage system possible, you could reverse engineer what a human is and create a D. N. A. Memory system. That is not just the linear version but is also </s><s>[INST] everything that it could become when we're talking about DNA, we're talking about Earth and the environment creating DNA. So this you're talking about trying to come up with an optimal computer for this particular environment. Um So if you were to reverse engineer that computer, what do you mean by considering all the possible things that could become? [/INST] So who you are today? Right. So three billion bits of information does not explain. Lex Friedman doesn't explain me right. But the D. N. A embodies the expectation of the environment in which you will live and grow and become. So all the information that is you, right, is actually not only embedded in the D. N. A. But it's embedded in the context of the world in which you grow into and develop. Right. But so all that information though is is packed in the expectation of what the DNA expects to see. </s><s>[INST] Interesting. So like some of the information is that accurate to say is stored outside the body. Exactly [/INST] the information is stored outside because there's a context of expectation. Isn't that interesting? </s><s>[INST] Yeah, it's fascinating. I mean, to linger on this point, if we were to run Earth over again, a million times, how many different versions of this type of computer would we get? [/INST] I think it would be different each time. I mean if you assume there's no such thing as fate. Right. And it's not all pre programmed, you know, and that there is some sort of, let's say variation or randomness at the beginning, you would get as many different versions of life as you could imagine. And I don't think it would all be unless there's something built into the, you know, into the substrate of the universe. It wouldn't always be left handed proteins. Right. </s><s>[INST] But I wonder what the flap of a butterfly wing, what uh effects it has because it's possible that this system is really good at finding the efficient answer. And maybe the efficient answer is there is there is only a small, finite set of them for this particular environment. Exactly. [/INST] Exactly. That's the kind of in a way the anthropomorphic universe of the multiverse expectations. Right. That, you know, there's probably a zillion other kinds of universes out there. If you believe in a multiverse theory, we only live in the ones where the rules are such that life like ours can exist. </s>

<s>[INST] suffering you know behind these things they're marveling about. Speaking of which I think you mentioned in the context of a social democracy that freedom of speech and freedom of the press or basically the freedom of people to have a voice is an important component which I think is something that caught my ear a little bit because if you think about the Soviet Union one of the ways that the authoritarian regime was able to control it's almost part of the central planning is you have to control the message and you have to limit the freedom of the press so there's a kind of notion especially in like ideas or maybe caricatures of the ideas of cultural Marxism sometimes caricatured even further as wokeism that you want to be careful with speech you want the sense of speech because some speech hurts people so in some sense you want to respect the value the equality of human beings by being careful the words [/INST] you say so what is there a tension there for you? I think there's no tension and part I think that it is very condescending or patronizing for to assume that people can't take debate that people can't either a society or individuals visually be engaged in the exchange of ideas without even very vigorous debate without you know being broken by it it's just not the case I'm basically a free speech absolutist I mean I would draw the line at obviously direct incitements of violence or certain other speech like that but in general you think a lot of people would be surprised to hear that no I mean not not people who know my work I mean more generally I think a lot of people on the right even in the center I think might have the idea that a lot of the Far Left wants to censor them I think some of the center left watch censor them but I think a lot on the Far Left on the the Marxist Socialist Left I think that you </s><s>[INST] know free speech is more or less the norm yeah yeah Where is the imperative, the censor coming from? Is this just some small subset of the left on Twitter? Is there some philosophical idea behind certain groups that like, if we're to steel man the case and which group actually has the interest of humanity [/INST] in mind in wanting to censor speech? I think we might need to just take it case by case for an example, by example, because honestly, I would have to think about a particular case, but let's just say generally that a lot of American liberalism rightly sees the revolution around the civil rights and later the extension of this rights revolution for gay rights and so on as being a very positive achievement in the last half century and I completely agree. Now for me, now that we've won those rights, a lot of our battle for change needs to go beyond the representational realm and needs to really reground itself in the material bread and butter struggles of ordinary people trying to survive, the battle for good healthcare for all Americans and so on, these are my immediate demands. I think there's a segment of American liberalism that doesn't want to go in that confrontational economic direction and wants to skirt away from battles over things like universal healthcare and so on and really are just still caught at this battle over rights and representation and it's devolved in such a way that they feel like they need to make change. The way they make change is only through interventions and culture, because they don't really have the same sense of class and class struggle that agree or disagree with it, it's a very material plane. So instead, they look at comedians who said the wrong thing or they look at all sorts of other ways to make change, it's not really making a change, it's just making them look bad and making our culture worse and I think that's where a lot of it comes from but I think that a lot of the left, even the left that's much more into battles over race and lots of other stuff like real serious anti-racist and the left, of course I'm an anti-racist but a lot of my work is focused on the primacy of class but even these people are very concerned about material struggles and issues and they don't really care about these issues, </s><s>[INST] they think are ephemeral kind of issues. So when you focus exclusively on language that somehow leads you astray, like on being concerned about language without like deeper economic inequalities and so on, you just become an asshole. That's on Twitter pointing out how everything, how racist everyone is. [/INST] So the anti-racism becomes a caricature of anti-racism. Exactly, because anti-racism was really about the struggle of people for equal rights and voting, it was about the struggle for people who were trapped into bad neighborhoods because they couldn't get decent jobs and their neighborhoods were redlined or whatever else. It was really like a struggle for survival. And what was the main demands, like the language of this one? It was the march for jobs and freedom. It was the slogan, I am a man, asserting the kind of universal dignity of people. This is what the civil rights movement was about and it wasn't a surprise, there was a lot of self-described socialists, people like Bayard Rustin, A. Philip Randolph, Martin Luther King Jr. I mean, these were people who were, Ella Baker, they were socialists, you know? And I think a lot of Americans agree with them with their immediate demands, even though they weren't themselves socialist, but it was a very materialistic struggle. And I think a lot of this has been co-opted into just some sort of vague and disconcerting complaints </s>

<s>[INST] Since you're italian Sicilian. I also heard rumors that you are a connoisseur of food. Uh, what you know, if I said today is the last day you get to be alive, I'm rushing, you shouldn't have trusted me. You never know what the Russian whether you're gonna make it out or not. If you had one last meal, you can travel somewhere in the world. Either you make it or somebody else makes it, What's that gonna look like? [/INST] All right. This is one last meal I must say, you know in this area, Covid, I've not been able to see my mom and uh and uh it was my mama was a fantastic chef. Okay. And had this very traditional food. As you know, the very traditional foods are great for a reason because they survived hundreds of years of culinary innovation. So, and there is one very laborious thing which is uh and you had the name which is this uh parmigiana but to do it is a piece of art so many hours. But only my mom could do it if everyone last meal, I want to tell me john what </s><s>[INST] is uh what's, what's the laborious process is is that the ingredients, is it uh the actual process, is it the, the atmosphere and the humans involved [/INST] val ladder. Uh the ingredient like in any other in the italian cuisine believes in very few ingredients. If you take a quintessential italian recipe where everybody knows spaghetti pesto. Okay, pesto is olive oil. Very good. Extra virgin olive oil, um, basil, pine nuts, paper, clover galley. Not too much otherwise you, you know the power everything and then yet to, through in two schools of fourth parmesan or pecorino or or a mix of the two, I mentioned six ingredients that is typical italian that is, I understand that there are other cuisines for instance of french cuisine which is extremely sophisticated and extremely combinatorial or some chinese cuisine which has a lot of many more ingredients and invest and yet the artist to put them together a lot of things in Italy is really describing for simplicity yet to find a few ingredients but the right ingredients to create something so impacted Jonah. The ingredients are egg ones. We are tomatoes were basil but how to put them together and the process is he's an actor or love, Okay, Labor and love is that uh, you can spend uh entire day when I'm exaggerating but the entire morning for sure to do it properly. </s><s>[INST] Yeah. It's a japanese cuisine to, there's a mastery to the simplicity with the sushi. I don't know if you've seen George dreams of sushi, but there's a mastery to that that's propagated through the generations. It's fascinating. You know, people love it. Uh, when I ask about books, I don't know if if books, whether fiction, nonfiction, technical or completely nontechnical had an impact in your life throughout. If there's anything you would recommend or even just mentioned is something they give you an insight or moved you in some way. [/INST] So okay, so I don't know if I can command because in some sense that you almost, it could be italian or to be such a scholar but being italian one thing with a really Impressed me tremendously is the divine comedy, it is a media evil poem, the very long poem divided in three parts hell purgatory and paradise. Okay. And the vet is the non trivial story of a middle man, man gets into a crisis, personal crisis and then out of this crisis he purifies makes a catharsis, it purifies himself more than more than more until has become capable of actually meeting God. Okay. And it is actually a complex story. So you have to get some very sophisticated language maybe Latin at that point that we're talking about 1200 italy right uh in Florence and this guy instead they chose his own dialect, not spoken outside his own immediate circle. Right, A florentine dialect. It actually don't, I really made italian italian. So how can you express such a sophisticated things in some ways? And then the point is that these words of that nobody actually knew because they were essentially dialect and plus a bunch of very intricate the rhymes in which I had to rhyme for things and turns out a bit by getting meaning from things with the crime, you essentially guess what the world means and you invent uh italian and you communicate by almost osmosis, what you want is a miracle of communication in a dialect of very poor language, very unsophisticated to express, very sophisticated situation, I love it, people who love it and italian and not italian, but, but what what I got to it is that, you know, very often limitations our strength because if you limit yourself at a very poor language somehow you get out of it and you achieve even better form of communication. If you're using a hyper sophisticated, a literary language of lots of restaurants from the private books so that you can actually instantaneously quote, you couldn't quote anything because nothing was written down before him. So I really felt better limitations are our strength. And I think that rather than complaining about the limitations we should embrace them because if you embrace our limitation limited as we are, we find very creative solutions that people with less limitation we have, we would not even think about </s>

<s>[INST] perhaps and how much it costs, [/INST] How much it costs? Now that can go either way because if you say Humira costs $72,000 And it's no more effective as a first line drug than methotrexate, which costs $480. People might say I want the expensive drug because I can get it for $25 copay. Um so you'd have to uh temper that a little bit. </s><s>[INST] Oh you mean people are so they don't care, [/INST] They don't care, their insurance is gonna cover it. And then and it's a $25 copay, but we could figure out how to deal with that. The main point is that if we assume that advertisements are going to keep going and they are, we could require that there be outside evaluation of the message that reasonable, unbiased viewers take away from the ads and the ads would have to tell the truth about the drug </s><s>[INST] and the truth should have like sub truth guardrails meaning like the cost that we talked about the effects compared to things that actually, you know, lifestyle changes. Um just these details, very strict guardrails of what actually has to be specified. [/INST] And I would make it against the law to have family picnics or dogs catching Frisbees in the ads. </s><s>[INST] So [/INST] you </s><s>[INST] Mean 95% of the ads? Yes. Um [/INST] I mean there's something </s><s>[INST] dark and authentic about those advertisements but they see, I mean, I'm sure they're being done because they work for the target audience and then the doctors too, Can you really buy a doctor's opinion? Why does it have such an effect on doctors um advertisement to doctors like you as a physician. Again, like from everything I've seen, people love you and I've just, people should definitely look you off from, there's a bunch of videos of you giving talks on youtube and it's just just, it's so refreshing to hear just the clarity of thought about health policy about healthcare just the way you think throughout the years. So like it's easy to think about like maybe you're criticizing Big Farmer. That's part of one part of the message that you're talking about. But you know that's not like your brilliance actually shines in the positive and the solutions and hard to do it. So as a doctor, what affects your mind [/INST] and how does big pharma </s><s>[INST] affect your mind? [/INST] Number one, the information that comes through legitimate sources that doctors have been taught to rely on evidence based medicine. The articles in peer reviewed journals, the guidelines that are issued. Now those are problematic because when an article is peer reviewed and published in a respected journal people and doctors obviously assume that the peer reviewers have had access to the data and they've independently analyzed the data and they corroborate the findings in the manuscript that was submitted or they give feedback to the authors and say we disagree with you on this point. And would you please check our analysis and if you agree with us making, that's what they assume the peer review processes. But it's not the peer reviewers don't have the data. The peer reviewers have the manuscript that's been submitted by the usually in conjunction with or by the drug company that manufactures the drug. So peer reviewers. All right, unable to perform the job that doctors think they're performing to vet the data to assure that it's accurate and reasonably complete, they can't do it. And then we have the clinical practice guidelines which are increasingly more important as um the information, the flow of information keeps getting brisker and brisker and docs need to get to the bottom line quickly. Clinical practice guidelines become much more important. And we assume that the authors of those clinical practice guidelines have independently analyzed the data from the clinical trials and make their recommendations that set the standards of care based on their analysis. That's not what happens. The experts who write the clinical trials rely almost entirely on the publications presenting the results of the clinical trials which are peer reviewed. But the peer reviewers haven't had access to the data. So we've got a system of the highest level of evidence that doctors have been trained over and over again to rely on to practice evidence based medicine to be good doctors that has not been verified. </s><s>[INST] Do you think that data that's coming from the farmer companies? Do you think there what level of manipulation is going on with that data is at the at the study design level is it that literally there's some data that you just keep off, you know, keep out of the charts, keep out of the the aggregate analysis then you then published or is it the worst case which is just change some of the numbers. [/INST] It happened all three happened. I can't I don't know what the denominator is but I spent about 10 years in litigation and for example, in vieques, uh which was withdrawn from the market in 2004 in the biggest drug recall in American history. The problem was that um, it got recalled when a study that Merc sponsored showed that Vioxx doubled the risk more than doubled the risk of heart attacks, strokes, and blood clots, serious blood clots. It got pulled then. But there was a study that a bigger study that had been published in 2000 in the New England Journal of Medicine that showed that Vioxx was a better drug for arthritis and pain, not because it was more effective, it's no more effective than a leave or Advil. Um, but because it was less likely to cause serious gi complications bleeds and perforations in the gut. Um, now in that study that was published in the new England Journal, that was never corrected. It was a little bit modified 15 months after the drug was taken off the market but never corrected. Mark left 3 3 heart attacks. And the FDA knew that Mark left out three heart attacks and the FDA is analysis of the of the data from that study said that they weren't going to the FDA wasn't going to do the analysis without the three heart attacks in it. And the important part of this story is that there were 12 authors listed on that study in the New England Journal, two were Merck employees. They knew about the three heart attacks. That had been omitted. The other 10 authors? The academic authors didn't know about it. They hadn't seen that data. So Mark just They had an excuse, it's complicated and the FDA didn't accept it, so there's no reason to go into it. Um but mark just left out the three heart attacks and the three heart attacks, it may seem 300 tax and a 10,000 person study may seem like nothing except they completely changed the statistics. So that had the three heart attacks been included, the only conclusion that Mark could have made was that Vioxx significantly increased the risk of heart attack and they abbreviated their endpoint from heart attacks, strokes and blood clots to just heart attacks. </s>

<s>[INST] And that's something we should, you know, talk about. And that's a really complicated human question. It does seem that the rhetoric, the populism of workers unite. We've been fucked over for way too long. Let's stand together. Somehow that message allows flawed or evil people to take power. It seems like the rhetoric, the idea is so good, maybe the utopian nature of the idea is so good that it allows a great speaker to take power. It's almost like if the mission, like come with me friends, beyond the horizon, a great land is waiting for us, that encourages sort of, yeah, dictators, authoritarians to take power. Is there something within the ideology that allows for that, for the sort of, for lying to people, essentially? [/INST] Well, I might surprise you with my answer because I would say, yes, maybe. But I think that it's not just socialism, any sort of ideology that appeals to the collective and appeals to our long-term destiny, either as a species or as a nation or as a class or whatever else, can lend itself to authoritarianism. So you can see this in many of the nationalisms of the 20th century. Now some of these nationalisms use incredibly lofty collective rhetoric, like in Sweden, the rhetoric of we're going to create the people's home. We're going to make this a country with dignity for all Swedes. We're going to make this a country that's more developed, more free, and so on. And they managed to build a pretty excellent society in my estimation from that. In countries like fascist Germany and Italy, they managed to do horrendous things in Japan and horrendous things with that. In the US, with national popular appeals, FDR was able to unite a nation to elevate ordinary working class people into a position where they felt like they had a real stake in the country, and I think did great things with the New Deal. In Russia, of course, this language was used to trample upon individual rights and to justify hardship and abuses of ordinary individual people in the name of a collective destiny. A destiny, of course, was just decided by the party in power and during the 30s and 40s by just Stalin himself, really. Now I think that that's really the case for making sure that we have a bedrock of civil rights and democracy, and then on top of that, we could debate. We could debate different national destinies. We could debate different appeals, different visions of the world, but as long as people have a say in what sacrifices they're being asked to do, and as long as those sacrifices </s><s>[INST] don't take away what's fundamentally ours, which is our life, which is our basic rights. And voice, our voice. So this complicated picture, because, help me understand, you mentioned that social democracy is trying to have social policies within a capitalist system in part, but your vision, your hope for a social democracy is one that goes beyond that. How do you give everybody a voice while not becoming the Soviet Union, while not becoming where basically people are silenced either directly through violence or through the implied [/INST] threat of violence and therefore fear? So I think you need to limit the scope of where the state is and what the state can do and how the state functions, first of all. Now for me, social democracy was like the equivalent of, I'll give a football analogy, it was the equivalent of getting to the red zone and then kicking a field goal. You'll take the three points, but you would have rather got a touchdown, and for me, socialism would be the touchdown. </s><s>[INST] It's not a separate, different playing field. [/INST] Some people would say socialism would be an interception. Sure, sure. </s><s>[INST] No, and they would have the right to, again, to say that and to say we shouldn't go further. And most coaches would take the safer route, right? So you're going against the decision. Anyway, I'll just take it too far. But I understand, I understand. [/INST] So for you, the goal is full socialism. But I'll take the three points. It's part of, I just want to march down the field. I want to get within scoring position. The reason why we should really move from this analogy, but the reason why I call myself a socialist is looking through history and these examples of social democracy, you saw that they were able to give working class people lots of rights and income and power in their society. But at the end of the day, capitalists still have the ultimate power, which is the ability to withhold investment. So they could say in the late 1960s and early 70s, listen, I was fine with this arrangement 10 years ago, but now I feel like I'm going to, you know, take my money and I'm going to go move to a different country or I'm just going to not invest because my workers are paid too much. I'm still making money, but I feel like I could be making more. I need more of an upper hand, right? So their economic power is then challenging the democratic mandate of Swedish workers that were voting for the Social Democratic Party and were behind this, this advance. So to me, what socialism is in part is taking the means of production, right, where this capitalist power is coming from and making it socially owned so that ordinary workers can control their workplaces, can make investment decisions and so on. Now does that mean total state ownership of everything or a planned economy? I don't think that makes any sense. You know, I think that we should live in a society in which markets are harnessed and regulated and so on. My main problem is capitalist ownership, in part on normative grounds, just because I think that it doesn't make sense that we celebrate democracy and all these other spheres, but we have workplaces that are just treated like tyrannies. And in part because I think that ordinary workers would much prefer a system in which over time they, you know, accrued shares in ownership where they got, in addition to base kind of ways, they got dividends from their firm being successful and that they figured out how to, you know, large firms, they're not going to be making day-to-day decisions by democratic vote, right, but maybe you would elect representatives, elected management once every year or two, depending on your operating agreement and so on. That's kind of my vision of a socialist society and this sounds, I hope, like agree or disagree, like it would not be a crazy leap into year zero, right? This could be maybe a way in which we could take a lot of what's existing in society but then just add this on top, but what it would mean is a society without a capitalist class. This class hasn't been, you know, individually, these people, you know, haven't been taken to re-education camps or whatever else, but they're just no longer in this position. And they're now part of the economy in other ways, like they'll probably be the first set of highly competent technocrats and managers and so on, they'll probably be very well compensated for their time and expertise and whatever else. But to me, both the practical end of things, like taking away this ability to withhold investment and increasing our ability to democratically shape investment priorities and to continue down the road of social democracy and on normative grounds, my egalitarian belief that ordinary people should have more stake in their lives in the workplace leads me beyond social democracy to socialism. </s>

<s>[INST] What are some interesting ways that this force data matter is different than gas? [/INST] Let's go to how a gas works, right? So the reason a gas, and it goes back to Feynman's brilliance in saying that this is the most important concept. The reason actually solid, liquid and gas phases work is because the nature of the interaction between the atoms changes. And so in a gas, you can think of this as being this room and the things, although you can't see them, is that the molecules are flying around, but then with some frequency, they basically bounce into each other. And when they bounce into each other, they exchange momentum and energy around on this. And so it turns out that the probability and the distances and the scattering of those of what they do, it's those interactions that set the, about how a gas behaves. So what do you mean by this? So for example, if I take an imaginary test particle of some kind, like I spray something into the air, there's got a particular color. In fact, you can do it in liquids as well too. Like how it gradually will disperse away from you. This is fundamentally set because of the way that those particles are bouncing into each other. The probabilities of those, the particle bouncing. The rate that they go at and the distance that they go at and so forth. So this was figured out by Einstein and others at the beginning of the Brownian motion, all these kinds of things. These were set up at the beginning of the last century and it was really like this great revelation. Wow, this is why matter behaves the way that it does. Like, wow. So, but it's really like, and also in liquids and in solids, like what really matters is how you're interacting with your nearest neighbor. So you think about that one, the gas particles are basically going around until they, until they actually hit into each other, though, they don't really exchange information. And it's the same in a liquid. You're kind of beside each other, but you can kind of move around. And in a solid, you're literally like stuck beside your neighbor. You can't move like, plasmas are, are weird in the sense is that it's not like that. So it's because the particles have electric charge. This means that they can push against each other without actually being in close proximity to each other. It's not, that's not an infinitely true statement, which goes get it. It's a little bit more technical, but basically this means that you can start having action or exchange of information at a distance. And that's in fact, the definition of a plasma is that it says these have a technical name is called a Coulomb collision. It just means that it's dictated by this force, which is being pushed between the charged particles is that the definition of a plasma is a, is a medium in which the collective behavior is dominated by these collisions at a distance. So you can imagine, then this starts to give you some strange behaviors, which I could, I could quickly talk about, like, for example, one of the most counterintuitive ones is as plasmas get more hot, because they get higher in temperature, then the collisions happen less frequently. </s><s>[INST] Yeah. [/INST] Like what? That doesn't make any sense. When particles go faster, you think they would collide more often, but because the particles are interacting through interacting through their electric field, when they're going faster, they actually spend less time in the influential field of each other. And so they talk to each other less in an energy and momentum exchange point of view. Interesting. Just one of the count, one of the counterintuitive aspects of plasmas. </s><s>[INST] Which is probably very relevant for nuclear fusion. Yes, exactly. So if I can try to summarize what a nuclear fusion reactor is supposed to do. So you have, [/INST] what, a couple of elements? What are usually the elements? Yes, exactly. It's usually deuterium </s><s>[INST] and tritium, which are the heavy forms of hydrogen. You have those and you start heating it. And then as you start heating it, I forgot the temperature you said. About a 100 billion. No, first it becomes today. [/INST] Oh, first it becomes plasma, so about a 100 billion. Oh, first it becomes plasma. So it's a gas and then it turns into a plasma at about 10,000 degrees. </s><s>[INST] And then, so you have a bunch of electrons and ions flying around, and then you keep heating the thing. I guess as you heat the thing, the ions hit each other rarer and rarer. Yes. around and then you keep heating the thing and I guess as you heat the thing the ions hit each other rarer and rarer? Yes. So man that's not fun so you have to keep heating it such that you have to keep hitting into the probability of them colliding becomes reasonably high and so also on top of that and sorry to interrupt, you have to prevent them from hitting the walls of the reactor somehow. [/INST] Rare, high. And so you asked about the definitions of the requirements for fusion. So the most famous one or some sense, the most intuitive one is the temperature. And the reason for that is that you can make many, many kinds of plasmas that have zero fusion going on in them. And the reason for this is that the average so you can make a plasma at around 10,000. In fact, if you come by the way, you're welcome to come to our laboratory at the PSFC, I can show you a demonstration of a plasma that you can see with your eyes and this at about 10,000 degrees. And you can put your hand up beside it and all this, and it's like a nothing, there's zero fusion going on. </s>