Datasets:

ianiket23

/

podcast_llama_chat_format-1k

like 0

<s>[INST] For me, the starting point is similar with that brand is uh like Mankoff is not a good place to search, not just because Hitler is evil but just not full of ideas. [/INST] No, it is not, it has its significance due to a lot of historically speaking. But </s><s>[INST] the starting point for me with Hitler is like to acknowledge that he's human and to at least consider the possibility that any one of us could have been Hitler. So like that [/INST] not Peterson kind of concept also. Um Jonathan height has a thing about the difference between hate and disgust mechanisms and things like that. And so he used, he goes into the looking at Hitler and his through his his diary entries and journals and stuff like that to look uh and see it more as the disgust mechanism. Then also trying to see like if there's any evolutionary biological attachment to this, whatever. I mean, you're right, he is a human being any of us or we're all human beings, it's not that it's probably jarring for people to think, but we're we're all I guess supposed potentially capable of just being in all these evil people in the world, think they're doing it for the sake of good, which makes them the most dangerous. </s><s>[INST] And there's some there's differences in levels of insane. I think Hitler was way more insane than Stalin. I think Stalin legitimately thought he was being doing good. [/INST] I would say that's probably true Stalin. It was just outright brutal. He had he had his five year plan, he had a lot of the things uh </s><s>[INST] he just had a much lower value for human life. And so he was willing to take make decisions about what he actually as uh as a good executive, which he was of managing different bureaucracies and so on. He was willing to make decisions that resulted in mass human suffering. Where Hitler was, it seems like to me what much moodier. So allowed emotions and moves to make [/INST] the decisions. We also have to consider uh the different trajectories and how where and when they were making their decisions. And I mean, not by time specifically, but you know, Hitler engaged into this, this conflict across multiple continents and then that everything that comes with basically fighting the whole world Stalin had his conflict and then he really mostly compartmentalized the rest of it. So he was dealing with his own internal instead of dealing with the internal and the external. So if Stalin was put under a world war scenario, I don't know, maybe he would have eventually lost his marbles to, </s><s>[INST] I'm not, I'm not sure that that's your right there. The hunger for power was more internalized for Stalin. He wanted to control the land that already existed as opposed to wanting to colonize other land. [/INST] He was as nationalistic as Hitler, but uh, and was as capable and willing for violent conflict as Hitler for them, the aims of the state. But he he centered and internalized Prior to then Externalizing and moving outwards. Whereas even maybe prior to him, there was an interest to continually push communism in an aggressive sense following on the momentum from the the 1918 revolution and that the halting of that, uh, through various aspects, I guess in Germany part of that was the National Socialists, like they came up and then they were the other ones to fight the communists. And so you had the two totalitarians going after it. Um, but then in the rest of the world that was not dealing with um, totalitarian aspects, it was just, it wasn't going to stick, especially in the west and other places, but Stalin just casually thinking like Stalin decided to go all right, we're not gonna go just start launching right into more conflict here. We're gonna these dudes are going down so that's cool for us because they hate us, we hate them. Um, but now we're going to, we're going to focus internally and then we're going to work on growing at a slower rate in picking our battles a bit more specifically. And of course there's, you know, you can get to the even this is after Stalin, but you got the best Urmanov type stuff talking about subversion in in cultural aspects. </s><s>[INST] Yeah, I mean, there's this fascinating dynamics to propaganda throughout the whole period. That that's [/INST] that's a whole another Colonel. </s><s>[INST] Do you think Hitler could have been stopped? One of the things that's kind of fascinating to look at is how many nations, both journalists and nations wanted almost crave to take Hitler at his word, that he wanted peace until it was too late. They almost wanted to be delude themselves. I mean, the same is true Stalin. People want to take Stalin and his words were still [/INST] delude themselves. Yeah, we will do, we will delude ourselves over any number of things. And until even after the fact where the history just says, hey, funny face, you know, you cannot supplement your pseudo reality onto actual reality here anymore. But yet we deal with people in pseudo realities constantly. I mean, we will always find a way to, to change reality to suit our needs. </s><s>[INST] Well, the nature of truth. Now, there's now multiple actual truth is kind of fascinating. There's multiple versions of history that people are telling. You know, the version, the version of the Great Patriotic War in Russia, the World War two in Russia is very different today under Putin than the version that we're learning on in the United States and then different than the version in europe, in the United States, the the hero of the war. As the United States in europe, there's a much more sad and solemn story of suffering and so on. And in Russia is the great [/INST] patriotic War. It was a unifier of a sense. And it I mean, yeah, I mean, you can't argue that war and conflict that and or I just even reducing that to stressors, agitation, suffering doesn't create human motivation. We started this off, you brought up frankel, I'm like, yeah, frankel's dope answers for meaning uh has those great and and I talked to you about how I started to think like man, do the ability for human beings to to to live and or potentially flourish in the worst environments you can think of is pretty incredible in and of itself and that it's a crazy thought to think that without Frankel and Mazzello ending up in concentration camps, do they write some of the most important books on philosophy in the 20th century? And that's insane on a lot of different levels. But </s>

<s>[INST] And now, since we talked about Einstein's thoughts about happiness and pigs, let me leave you with some words from Winston Churchill, I'm fond of pigs. Dogs look up to us. Cats look down on us, pigs treat us as equals. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] Know the feeling is the number of programmers in the world has been growing and growing very quickly. Do you think it's possible that it will actually level out and drop to like a very low number with this kind of world? Because then you'll be doing software 2.0 programming. Um And you'll be doing this kind of generation of co pilot type systems, programming but you won't be doing the old school software one point oh programming. I [/INST] don't currently think that they're just going to replace human programmers. Um I'm so hesitant saying stuff like this right because </s><s>[INST] this is going to be replaced [/INST] in five years. </s><s>[INST] I know it's going to show [/INST] that like this </s><s>[INST] is where we thought because I I agree with you but I think we might be very [/INST] surprised </s><s>[INST] right? Like what are the next i what's your sense of where we stand with language models? Like does it feel like the beginning or the middle or the end? [/INST] The beginning? 100%. I think the big question in my mind is for sure. GPT will be able to program quite well competently and so on. How do you steer the system? You still have to provide some guidance to what you actually are looking for. And so how do you steer it? And how do you say, how do you talk to it? How do you um audited and verified that what is done is correct. And how do you like work with this? And it's as much not just an ai problem but a ui ux problem. Yeah. Um So beautiful fertile ground for so much interesting work for V. S. Code plus plus where you're not just not just human programming anymore. It's amazing. </s><s>[INST] Yeah. So you're interacting with the system so not just one prompt but its iterative prompting trying to figure out having a conversation with the system. That actually I mean to me that's super exciting to have a conversation with the program I'm writing. [/INST] Yeah maybe at some point you're just conversing with it. It's like okay here's what I wanna do actually this variable. Maybe it's not even that low level is variable but you </s><s>[INST] can also imagine like can you translate this to C. Plus plus and back to python [/INST] already kind of existence </s><s>[INST] but just like doing it as part of the program experience. Like I think I'd like to write this function in C Plus plus or like you just keep changing from different different programs because there's different syntax, maybe I want to convert this into a functional language and so like you get to become multi lingual as a programmer and dance back and forth officially. [/INST] I think the Ui ux of it though is like still very hard to think through because it's not just about writing code on a page, you have an entire developer environment, you have a bunch of hardware on it. Uh you have some environmental variables, you have some scripts that are running in a Cron job like there's a lot going on to like working with computers and how do these systems set up environment flags and work across multiple machines and set up screen sessions and automate different processes like how all that works and is auditable by humans and so on is like massive questions. The moment </s><s>[INST] you've built archive sanity, what is archive and what is the future of academic research publishing that you would like to see? [/INST] So archive is this pre print server. So if you have a paper you can submit it for publication to journals or conferences and then wait six months and then maybe get a decision pass or fail or you can just uploaded to archive and then people can tweet about it three minutes later and then everyone sees it. Everyone reads it and everyone can profit from it in their own ways </s><s>[INST] and you can cite it and it has an official look to it. It feels like a like it feels like a publication process. It feels different than if you just put in a blog post. [/INST] Oh yeah, I mean it's a paper and usually the bar is higher for something that you would expect on archive as opposed to and something you would see in a blog post </s><s>[INST] or the culture created the bar because you could probably host a pretty crappy fix for an archive. Um So what's that make you feel like, what does that make you feel about peer review? So rigorous peer review by 23 experts versus the peer review of the community? Right? As it's written [/INST] basically, I think the community is very well able to peer review things very quickly on twitter and I think maybe it just has to do something with A. I. Machine learning field specifically though, I feel like things are more easily auditable. Um and the verification is easier potentially than the verification somewhere else. So it's kind of like um you can think of these scientific publications as like little block chains where everyone's building on each other's work and setting each other and you sort of have A I which is kind of like this much faster and loose Blockchain, but then you have, and any one individual entry is like very, very cheap to make and then you have other fields where maybe that model doesn't make as much sense. Um And so I think in a I at least things are pretty easily verifiable and so that's why when people upload papers, they're a really good idea and so on, People can try it out the next day and they can be the final arbiter of whether it works or not on their problem and the whole thing just moves significantly faster. So I kind of feel like academia still has a place, sort of just like conference journal process still has a place, but it's sort of like um it lags behind I think and it's a bit more maybe higher quality process, but it's not sort of the place where you will discover cutting edge work anymore. It used to be the case when I was starting my PhD that you go to conferences and journals and you discuss all the latest research now when you go to a conference or general like no one discusses anything that's there because its already like three generations ago irrelevant. </s>

<s>[INST] guillotine. And for the first three months as gifted as is Gary tonin is in learning most movies, most movies. Gary gets it. Like in minutes, there was something going on with Gary just couldn't get a guillotine on people. And finally, after around three months he started having some success until ultimately became one of his best weapons. Um, we had to go through like 15 different variations of guillotine until he found one which actually worked reliably for him. And that was one of the few times where I put my foot down and said, no do you have to learn this. So the long search had to do more with the physical characteristics that you couldn't figure out the right like it made sense. It made sense in the case of gary Tony because there were more opportunities per minute of his grappling, four guillotines, uh, that the investment and time was worth it for another athlete. I might have said, well, he hardly ever gets in the situation that front headlock, guillotine. So it's not even worth investing the training time. Let me ask you a question on the, on the competition side, we mentioned haters. And do you think about this aspect of the competition with the athletes? It's a great question. And the answer is no, uh, I'm, you can see that you could, you couldn't find two more polar opposites psychologically than George ST pierre. And this monstrosity on my left. And um, I've, I've never said to my athletes, hey, I think this is the sort of demeanor you should carry yourself with. I'm myself a very flawed character and I'm the last person on earth who should be delving out moral advice to other people. Um, the only thing is that I of course, I believe some things are off limits, but as long as it's done in the context of sport where no one's physically attacking people or do anything crazy, where it just goes completely over the top, then I give almost zero um, moral advice to my athletes, I'm a jujitsu coach, not a preacher [/INST] lex. I I if I can, if I may we we are entertainers. You know, we're athletes for professional athletes. But we make we make living because of people are want to see us perform same thing. An actor, same thing as singer. And a lot of the time, especially in the fight game. Mm hmm. An event is promoted. It needs to be with emotion, love me, hate me but do not in your army. Um, and you know it when it's authentic and it's done well. I think me and my personally, my favorite fighters to watch are the ones that are the that that have some sort of a bad persona. I really enjoyed watching those guys because they bring an emotion element into a fight, which is great. You know, I I feel to me it's more interesting to watch when there is an emotion involved. And I believe that's why some fighters make more money than others, You know? And you know what I mean? That's the reason why we make we can make a living out </s><s>[INST] of this. Yeah, they're better entertainment. But you're right. The authenticity seems to be really important. It's actually something very interesting then um, it's time to break out some, some [/INST] secrets. </s><s>[INST] Do you know, who like, like you think of George ST Pierre, you think of like the highly technical polished martial artists. Do you know who his favorite fighters to watch were you'd probably be thinking of probably someone who's really technically advanced actually. It was Mark Coleman kevin Randleman and Phil Baroni. He used to love watching that, that was a Hammer House, that was his [/INST] favorite. He would love </s><s>[INST] those guys and whenever their flights were on George rewatching the Hammer House Crew. And uh it's funny what you said about how those guys brought an intensity to to Emma, that was off the charts. Have you ever met those guys in in in their prime? Let me tell you it was it was something to behold. And I had this crazy larger than life personality that most of the things they did made no sense whatsoever, but technically, but that was their appeal. And and there were these guys and I just love to watch them more than anyone else. You [/INST] never knew what could happen with these guys. I remember when Mark Coleman won the Pride Grand prix, I was in my living room, I was jumping, I was so happy. I was like, yeah, he beat Igor and I was like, like to me it was amazing, you know what I mean? Because of the emotion that they brought into the fight. </s>

<s>[INST] but that's that's where an iconic game that's where an iconic and let me let me ask you, it's a little bit for fun because you've built this amazing thing and so let's Let's talk about uh like an old warrior looking over old battles. Um, you've, you know, there's a sad letter in 2012 that you wrote to the numpy mailing list announcing that you're leaving numpy. And some of the things you've listed, some, some of the things you regret or not regret necessarily, but some things to think about if you could go back and you could fix stuff about Numpy or both sort of on a personal level, but also like looking forward. What kind of things would you like to see changed? [/INST] Good question. So I think there's technical questions and social questions right there. Um, first of all, you know, I wrote Numpy as a service and I spent a lot of time doing it and then other people can help make it happen. Numpy succeeded because the work of a lot of people. Right? So it's important to understand that I'm grateful for the opportunity, the role I had, I could play and I'm grateful that things I did had an impact, but they only had the impact they had because the other people that came to the story and so they were essential. But the way data types were handled the way data types, we had a race scholars for example, that, that are really just a substitute for a type concept. Right? So we had Race killers are actual python objects so that there's for every, for a 32 bit float or a 16 bit float or a 16 bit integer python doesn't have a natural just as winning major one float. Well, what about these lower precision types? These larger precision types. So we had them in vampire so that you could have a collection of them but then have an object in python that was one of them. And there's questions about like in retrospect, I wouldn't have created those of it improve the type system and like made the type system actually a python type system as opposed to currently it's a python one level type system. I don't know if you know the difference from python one, python two. It's kind of technical kind of depth but python to one of its big things that ghetto did. It was really brilliant. It was actually um python one all classes new objects were want to use the user wrote a class. It was an instance of a single python type called the called the class type write in python two. He used a meta typing hook to actually go so we can extend this and have users right classes that are new types. I was able to have your user classes be actual types and the python type system got a lot more rich. I barely understood that at the time that Numpy was written and so I essentially in python Numpy created a type system that was python one era. It was every every D. Type is an instance of the same type as opposed to having new D types be really just python types with additional metadata. </s><s>[INST] What's the cost of that? Is that efficiency is the usability, [/INST] usability, primarily the cost isn't really efficiency. It's it's it's the fact that's clumsy to create new types. It's hard. And then one of the challenges you want to create new types, you want to return in type or you want to add a new, you know, posit type or you want to. Um So it's hard now in the and now if we have done that well when number came on the scene, we could actually compile python code. It would integrate with that type system much cleaner. And now all of a sudden you could do gradual typing more easily. You could actually have python when you add number plus better typing could actually be a you'd smooth out a lot of rough edges but </s><s>[INST] that's already there's like but are you talking about from the perspective of developers within Numpy or users of Numpy because [/INST] developers have not really users of Numpy so much. It's the development of Numpy, </s><s>[INST] you're thinking about like how to design Numpy so that its contributors. [/INST] Yeah, the contributors. It's easier. It's easier, it's less work to make it better and to keep it maintained and where that's impacted things. For example, is the gpu like all of a sudden Gps start getting added and we don't have them in Numpy like numbers should just work on GPS the fact that we have to have to download a hold their object called cup I'd have raised on Gps is just an artifact of history because there is no fundamental reason for it. </s><s>[INST] Well, that's really interesting. If we could sort of go on that tangent briefly is you have pytorch and other library like tensorflow that basically tried to mimic uh by like you've created a sort of platonic form [/INST] basically. Yeah. Yeah, exactly. Well, the problem was I didn't realize that platonic form has a lot of edges. We should cut those out before we present it. So I </s><s>[INST] wonder if you can comment. Is there like a difference between their implementations? Do you wish that they were all using Numpy over? Like in this abstraction, I'll tell you and sorry to interrupt that There's Gpu S A six. There there might be other, newer more for computing. There might be other kind of or the aliens will come with a new kind of computer, like an abstraction that Numpy should just operate nicely over. The things that are more and more and smarter and smarter with this multidimensional race. [/INST] Yeah, I have several comments there. We are working on something now called data dash A P I S dot org. Data dash api dot org and go there today. And it's our answer. It's my answer. You know, it's not just me, it's me and ralph and and Athen and Aaron and a lot of companies are helping us that Kwan site labs. Uh, it's not unifying all the race, it's creating A P I that is unified. Um, so we do care about this and trying to, trying to work through it actually the chance to go and meet with the tensorflow team and the pytorch team and talk to them after, after exiting anaconda just talking about. Because the first year after leaving a comment in 2018, I became deeply aware of this and realized that, oh, this split in the community that exists today Makes what I was concerned about in 2005. Pretty parochial. It's a lot worse right now. There's a lot more people so that perhaps the industry can sustain more stacks, right? There's a lot of money, but it makes it a lot less efficient. I mean this, but I've also learned to appreciate it's okay to have some competition. It's okay to have different implementations, but it's better if you can at least re factor some parts, I mean, you're going to be more efficient. You can be a factor parts. </s>

<s>[INST] So let me ask the flips the, the other because he said poker is there somebody that stands out to use, uh, could be the greatest poker player of all time. I could you uh, I admire [/INST] that. That's a more controversial one because these chess players are such like, first of all there's more an objective, objective standard And second of all, there's like almost like cultural figures to me, whereas poker players and we're like live living, they feel more like they feel more accessible, </s><s>[INST] but they also have like personalities. Yeah, I have like philae devices, devices that have quirks their humor. Like I guess we've seen videos of them because it's such a recent development, [/INST] Let's say one person who I admire so much and like if I, if I could like have a dinner list of people that I want to have dinner with, like maybe it'll have to know, actually, I would love to have dinner with him um filled Chalfont, uh who most people probably won't know, but on this podcast, but the way, first of all he democratized poker learning in like the mathematical nitty gritty, how do you get good at poker type sense to the entire world and like an unprecedented way he was, he gave, he had this gift that he had learned and distilled by working with some of the greatest poker minds and he just democratized um through his website. And um I learned a ton from him and not only that, but you just listen to him think and it's almost like a philosophical meditation the way that he breaks things down and thinks about these different elements and has such a holistic thought process. It's like watching a genius work and you know, he's also just a nice, fun, sociable guy that like, you can, you can imagine being at your dinner table, all that combined, </s><s>[INST] which is not true for a lot of poker players, right? Um more dark to say the least. Yes, I like, I really like the, what is the Canadian data on the ground? No, [/INST] he's also a nice guy. </s><s>[INST] He's also a nice guy, but he's also somebody who is able to express his thoughts about poker really well, but also an entertaining way. He seems to be able to predict cards better than anybody I've ever seen. Like what [/INST] she watched the challenge With the challenge. He lost like $1 million dollars recently too. Doug Polk, he lost $1 million Polk heads up online. It's really interesting. </s><s>[INST] Yeah, it's awesome to watch these guys work. So I know you're 20, [/INST] 21, </s><s>[INST] Uh, so asking you for advice is uh, is a little bit funny, but uh, but at the same time, not because you've created a social network, you've created a start up from nothing is we talked about earlier, like without knowing how to program you've programmed. I mean, you've taken this whole journey that a lot of people I think would be really inspired by. So given that, Uh, and given the fact that 20 years from now you'll probably laugh at the advice you're going to give now. [/INST] Absolutely. I hope so if I don't laugh at the advice I give now something went desperately wrong, Right. </s><s>[INST] Yeah. So do you have advice for people that want to follow in your footsteps and create a startup, whether it's in uh software app domain or whether it's anything else. [/INST] So I speak specifically about social media apps, um try to keep it as near as possible so I can laugh as little as possible when I'm 41. Um and what I would say is that If you're like a 21, year old who's looking at me and being like, I want to do something like this, um what I would say is you probably know better than just about anyone. And if you have a feeling in yourself that This is something that I have to do, and this is something I could imagine myself doing for the next 10 years, because if you're successful, you are going to have to do it for the next 10 years and through the ups and the downs through the amazing interviews with lex and through the not so amazing articles you might have with other people, right? Um, and you're going to have to ride those highs and lows and you have to believe in what you're doing. But if you have that feeling, what I would say is listen to as few people as possible because people are experts in the domains, but when it comes to like what's hot and what's what makes sense in a social context? You are the authority as a young person who's going through these things and living in, in, in your sort of milieu. And I mean, I've talked to at this point, so many experts, experts, so many investors, Bcs. Um, so you would be amazed at the advice I've gotten advice I've gotten. So </s><s>[INST] there's like a minefield of bad [/INST] advice. That's the hardest part I think for young people ends the thing when people like I help, I help yells all the time, who asked, like I never turned down when a founder asked me to have a conversation, I never turned it down. I'm always there for them. Um, and the number one thing I worry about is that at Yale were taught implicitly and explicitly that you listen to the adult room, You listen to the person with the highest pay grade. Yeah. And it's devastating because that's how innovation dies and you know, </s><s>[INST] yeah, it's intimidating to, like, you talk to VC who probably [/INST] means worth a billion </s>

<s>[INST] So that one you really have to work for. Uh I don't know if you've heard about this, Let me explain it. Maybe you'll find it interesting. So, open Ai is a company that does a. I work and they have this language model. It's a neural network that can generate language pretty well. But they also on top of that developed something called open ai codex. And together with Git hub, they developed a system called Open Ai co pilot. Let me explain what it does. There's echoes of literate programming in it. So what you do is you start writing code and it completes the code for you. So for example, you start let's go to your factoring program, you start you right in javascript and python in any language that are trained on uh you start you write the first line and some comments like what this code does and it generates the function for you and it doesn't incredibly good job, like it's not probably right, but often does a really good job of completing the code for you [/INST] to see whether, but how do you know whether it did a good job or not? </s><s>[INST] You can see a lot of examples where it did a good job, and so it's not a thing that generates, because for you, it starts, it gives you uh so it puts the human in the seat of fixing [/INST] issues </s><s>[INST] versus writing from scratch. Do you find that kind of idea at all interesting? [/INST] Every year we're going to be losing more and more control over what machines are doing and people are saying, well, it seems like when I was a professor at caltech, uh in the in the 60s, we had this this guy who who talked a good game, he could give inspiring lectures and you think, well, uh throwing things, he was talking about an hour later, you said, well, what did he say? Um uh, but he really felt that it didn't matter whether computers got the right answer or not, it's just a matter whether it made you happy or not. In other words, if you know, if your boss paid for, uh, you know, then you had a job, you could you could you could take care of </s><s>[INST] your wife, happiness is more important than truth. [/INST] Exactly. He didn't believe in truth, but he was a philosopher. </s><s>[INST] I like it. Uh, and somehow, you see, uh, [/INST] we're going that way. I mean, so many more things are taken over by saying, well, this seems to work. And when there's when there is a competing interests involved, neither side understands why the decision is being made. Uh you know, we realize now that it's that it's bad, but but consider what happens 55 year, 10 year, you're down the line when things get even more further detached. Each thing is based on something from the previous year. </s><s>[INST] So you start to lose, the more you automate, the more you start to lose track of some deep human essentially exponentially. But so that's the dark side. The positive side is, the more you automate the more you let humans do what humans do best. So maybe programming this, you know, maybe humans should focus on a small part of programming that requires that genius, the magic of the human mind and the mess you let the machine generate. Yeah, I mean, that's the that's the positive, but of course it does come with the darkness like automation. [/INST] What's </s><s>[INST] better, correct? [/INST] I'm never going to try to write a book about that. Uh I'm never going to recommend to any of my students to work for them. You're </s><s>[INST] on the side. I'm on the side. [/INST] I'm on the side of under understanding. I understand. Uh, and I think these things are really marvelous if they if if what they do is, you know, all of a sudden we have a better medical diagnosis or or help guide some scientific experiment or something like this. Uh you know, curing diseases or what whatever. But when it, when it affects people's lives in a serious way. Uh So if you're writing, if you're writing code, oh yeah, here this is great, uh this will make a slaughter. But okay. So </s><s>[INST] I see. So you have to be very careful. Like right now it seems like fun and games. It's useful to write a little javascript program that helps you with the website. But like you said, one year passes, two years passes five years and you forget you start building on top of it and then all of a sudden you have autonomous weapons systems based on [/INST] what we're all dead. Doesn't matter. And that's it. Well, </s><s>[INST] in the end, this whole thing ends anyway. So um but there [/INST] is a heat death of the universe a predicted But I'm trying to postpone that for for a little bit, </s><s>[INST] we'll be nice that at the end as we approached the heat death of the universe, there's still some kind of consciousness there to to to appreciate it. Hopefully human consciousness, [/INST] I'll settle for 10 to the 10 to the 10 to the 10th year. There's some finite number. But things like this might be the reason we don't pick up any signals from extraterrestrial, </s><s>[INST] they don't want anything to do with us. Oh because they because [/INST] they invented it to and </s><s>[INST] so you you do have a little bit of worry on the existential threats of ai and automation. So like like removing the human from the picture. [/INST] Yeah. People have more more potential to to do harm now than by far than they did 100 years ago. </s><s>[INST] But are you optimistic about the humans are good at creating destructive things, but also humans are good at solving problems. [/INST] Yeah, I mean, there's half empty and half full, you know, So </s><s>[INST] so how would we have full? I [/INST] can go. Yeah. So let me let me put it this way because because it's the only way I can be optimistic, but think of uh things that have changed because of civilization, you know, they don't occur just in nature. So just uh just imagine the room we're in, for example. Uh Okay. Some, you know, we've got pencils, we've got books, we've got tables, we've got microphones, clothing, food, all these things were added. Somebody invented them one by one, millions of things uh that we inherit. Okay. Um and uh it's inconceivable that that so many millions of billions of things wouldn't have problems and we get it all right. Um and and each one would have no negative uh effects and so on. So it's very amazing that much works as does </s>

<s>[INST] was very impressive. He [/INST] does a lot of pranks and </s><s>[INST] stuff. [/INST] Oh so he's like like like like give you a treat and then take it away and laugh like stuff like that. So he's </s><s>[INST] like a chess [/INST] player. </s><s>[INST] So here's a cognitive sort of [/INST] there's a computer being programed. He's taken in the environment interacting with a specific set of humans. </s><s>[INST] How would you, first of all what [/INST] what is it? Let me ask. I want to ask how do you program this computer </s><s>[INST] and [/INST] also how do you make sense of that? There's a conscious </s><s>[INST] being right there. [/INST] Um that wasn't </s><s>[INST] there before. It's given [/INST] me a lot of </s><s>[INST] crisis thoughts. I'm [/INST] thinking really hard. I think that's part of the reason. It's like, I'm struggling to focus on art and stuff right now because baby X is becoming conscious and </s><s>[INST] like my [/INST] it's just reorienting my brain, like my brain </s><s>[INST] is suddenly totally [/INST] shifting of like, oh sh it like the way we raise </s><s>[INST] Children, [/INST] like, like I hate </s><s>[INST] all the baby [/INST] books and everything. I hate them. Like they're ah the art is so bad and like, like all this stuff, </s><s>[INST] everything [/INST] about all the </s><s>[INST] aesthetics and [/INST] like, I'm just like, ah like this is so </s><s>[INST] the [/INST] programming languages were using to program these baby computers isn't good. Yeah, </s><s>[INST] like [/INST] I'm thinking and I not that I have like good answers </s><s>[INST] or know what you know what to do, but I'm just [/INST] thinking really, </s><s>[INST] really [/INST] hard about it. I we recently watched Totoro with </s><s>[INST] him studio [/INST] julie. Um and it's just like a fantastic film </s><s>[INST] and he like responded to, I don't [/INST] know, not supposed to show baby screens </s><s>[INST] too much, but [/INST] like, I think </s><s>[INST] it's the [/INST] most sort of like, </s><s>[INST] I feel like it's the [/INST] highest art baby </s><s>[INST] content. Like it's it's [/INST] it </s><s>[INST] really speaks. There's [/INST] almost no </s><s>[INST] talking in it. It's really simple, although all the dialogue is super super, super [/INST] simple, you know? And it's it's like </s><s>[INST] A 12, 3 year [/INST] old can like really connect with it. Like it it feels like it's </s><s>[INST] Almost aimed at like a 123 year old. [/INST] Um but it's like great </s><s>[INST] art and it's so [/INST] imaginative and it's so beautiful </s><s>[INST] and um [/INST] like the first time I showed it to him, he was just like so invested in </s><s>[INST] it. Unlike I've ever [/INST] unlike anything else </s><s>[INST] I'd ever shown him. Like he [/INST] was just like crying when they cry and laughing when they laugh. Like just like </s><s>[INST] having this roller [/INST] coaster of emotions like and he learned a bunch of words like he was and I started saying totoro and started </s><s>[INST] just saying all [/INST] this stuff after watching Totoro </s><s>[INST] and he [/INST] wants to watch it all the time and I was like, man, </s><s>[INST] why isn't there [/INST] an industry of this? Like why aren't our best artists focusing on making art like </s><s>[INST] for [/INST] the birth of consciousness? Like and </s><s>[INST] and and I and that's one of the things [/INST] I've been thinking, I really </s><s>[INST] want to start doing, you [/INST] know, I don't want to speak before I do things too </s><s>[INST] much, but like, like [/INST] I'm just like Ages 1-3, </s><s>[INST] like [/INST] we should be putting so </s><s>[INST] much effort into that. And the [/INST] other thing about Totoro is it's like </s><s>[INST] um it's like better [/INST] for the environment because adults love </s><s>[INST] Totoro. It's such good art that everyone [/INST] loves it. Like I still have </s><s>[INST] all my old totoro merch [/INST] from when I was a kid, like I literally have the most ragged </s><s>[INST] old totoro [/INST] merch? Um like everybody loves it, everybody </s><s>[INST] keeps it, it's like why [/INST] does </s><s>[INST] the art [/INST] we have for babies </s><s>[INST] need [/INST] to suck </s><s>[INST] and and be [/INST] not accessible to adults and then just be thrown </s><s>[INST] out when um you know, they [/INST] age out of it. Like it's like, </s><s>[INST] I [/INST] don't know, I don't have like a fully formed thought here, but this is just something I've been thinking about a lot is like how do </s><s>[INST] we, like, [/INST] how do we have more totoro </s><s>[INST] esque content? Like how do [/INST] we have more content like this that </s><s>[INST] like is [/INST] universal and everybody </s><s>[INST] loves but is like [/INST] really </s><s>[INST] geared to an emerging [/INST] consciousness, </s><s>[INST] Emerging conscious in the first like three [/INST] years of life that so much turmoil, </s><s>[INST] so much evolution [/INST] of mind is happening, </s><s>[INST] it seems like a crucial [/INST] time would you say </s><s>[INST] to make it not suck? [/INST] Do you think of </s><s>[INST] basically treating [/INST] a child </s><s>[INST] like they have the capacity to have the [/INST] brilliance of an adult or even beyond that? Is that how </s><s>[INST] you think of that mind or no, because they still, they like [/INST] it when you talk </s><s>[INST] weird and [/INST] stuff like they respond better to, </s><s>[INST] because [/INST] even they can imitate better when your voice is higher. Like people say like don't do </s><s>[INST] baby talk, but it's like when your voice is [/INST] higher, it's closer to something they can imitate </s><s>[INST] so they like, [/INST] like the baby talk </s><s>[INST] actually kind of works [/INST] like it helps them </s><s>[INST] learn to communicate. I found [/INST] it to be more effective with learning words and </s><s>[INST] stuff but like you're [/INST] not speaking, speaking down to them. Like do do do they have the capacity to understand really difficult concepts you know just in a very difficult different way. </s><s>[INST] Like an emotional [/INST] intelligence about something deep within. Oh yeah, no like effects </s><s>[INST] hurts effects bites [/INST] me really hard and I'm like oh he he gets he's sad, he's he's like sad if he </s><s>[INST] hurts me by accident [/INST] which he's </s><s>[INST] huge so it hurts me a lot by accident. [/INST] Uh Yeah that's so interesting that that </s><s>[INST] that that mind [/INST] emerges and and </s><s>[INST] he and [/INST] Children don't really have a </s><s>[INST] memory of that time so we can't [/INST] even have a conversation </s><s>[INST] with him about it. So [/INST] they don't have a memory of this time because like think about </s><s>[INST] like [/INST] I mean with our the youngest baby, </s><s>[INST] like it's like [/INST] I'm like have you read the sci fi short story? I have no mouth but I must scream good title. </s>

<s>[INST] I didn't know that. So they basically it's all in the computer, It's computational [/INST] right? You have the genetic code, You have tremendous power even if you don't have the organism itself, </s><s>[INST] What do you make of Elizabeth Holmes and efforts like that? First of all, I'm a curious, I'm drawn to the darkness in human nature because that somehow reveals um the full spectrum of what humans could be. So there's a lot of sort of controversial thoughts about who she is and her efforts and so on. Um I think you may have even tweeted about it, but I've read a lot of your tweets, I'm not forgetting. Um but what do you make of her and those, both those efforts and the charlatans? Uh that sort of um snake oil salesman that promised those efforts to do more than they currently can? [/INST] I think that her, you know that goal that she had that she created Theranos to try to achieve to use less blood in test is a very worthy goal and a huge frontier that we have not achieved and that I hope we will achieve. So I understand why, you know what someone describes what a huge step forward that would be and it would be indeed, I understand why people put a ton of money behind it. Can </s><s>[INST] you describe what was the promise? What, what are we even talking about? What's Theranos? Just for people who don't know [/INST] the Theranos is a company that was basically started to revolutionize the way medical blood tests are done Both to use a whole lot less blood in doing it. You know, if anyone's ever been to the doctor and had 5 to 10 tubes of blood removed from them, it can be quite surprising how much they take out. Uh and and it's, you know, that's the limitation of our technology that we need those volumes of blood to run all the tests that we want to. And so the promise of Theranos was that perhaps with a single drop of blood, we would be able to know as much about the person's the condition of their their body without drawing all that blood. And and thereby, you know, there would be these devices she was going to create that would sort of do it. You put a drop of blood in it, spits out everything you ever wanted to know about what's in your bloodstream and in a way that would make it so much easier. You know, it could be, you could have one in your home theoretically and you don't know why you'd wonder what your potassium level is on any given day, but you could check if you wanted to. Um and so that that goal is very worthy. You know, I put that goal up there with the frontier of making painkillers that are as good as opioids without the addictive quality. You know, that would be such a huge revolution if we did have that in medicine, but and particularly for me because I trained in both pediatrics and internal medicine, so I learned to care for both Children and adults in Children. We do draw much less blood. They have a much lower blood volume. And we use these tiny little tubes to draw their </s><s>[INST] blood [/INST] and we seemingly get equivalent information out of the larger tubes we draw from adults. And I'm still unclear, to be honest, why we can't draw that little amount of blood from adults. It seems technically possible. I don't know what the barriers are. I'm sure there are or else we'd be doing it. Um, but I do think that it is a very important goal. And if Theranos had done it, they would have really revolutionized the practice of medicine. </s><s>[INST] So, to uh, return to that, uh, cadaver that first day when you got to meet with the dead with human body that's no longer living. So how quickly did it take for you to get used to sort of, you said looking at the surface muscles of the back. I mean, that can be overwhelming as a thought and people listening to this that have never dissected anything might might be overwhelmed by that thought. So like how quickly we're able to get used to the brutal honesty of the biology before you, [/INST] for me, it did not take long at all. I guess I've not never been a squeamish person. So for me it was kind of riveting and fascinating right from the first moment. But I do know some of my fellow classmates did have some trouble with it. Some of them I heard had nightmares in the first few weeks of, of anatomy lab and but then everyone, as far as I know, got used to it. And that was also actually a big lesson for me, that it's pretty amazing what people can get used to in their daily lives. And I kind of extrapolated that to people living through war and through, you know, just terrible situations and living under um, you know, oppressive regimes. And it really is amazing what people can get used to almost anything. </s><s>[INST] But, you know, in war, people often come back and they have nightmares, they suffer through it. There's PTSD, there's a, there's a lot of complicated feelings with that are echoes of those same complicated feelings possible in the case of training to be and becoming a doctor. [/INST] That's a good point. Yeah, I think, you know, sometimes just as you know, a barbed wire fence can leave a scar on your skin. You know, emotional psychological experiences can leave a mark on your brain or your memory. And I think that that definitely could be, um, could be a problem in medical training. You do see a lot of things that are very shocking, very repulsive things that you'd never forget. I know one of those students that had nightmares initially went on to be a surgeon. So I imagine she's not having the pTSD of kind of seeing inside her first dead body because she sees inside them all day every day now. But I'm sure it it could, you know, we we go on to see so many um kind of grosser or more shocking things in medical training through medical school and then by working with actual living patients, not just dead and embalmed bodies. So I do think that things can leave a mark, but I don't think that initial cadaver would be the most traumatic. </s>

<s>[INST] So if you don't like it, they refunded, go to magic spoon dot com slash lex and use code lex at checkout to say $5 off your order. That's magic spoon dot com slash flex and use code lex. This is a lex Friedman podcast and here is my conversation with barry Barish. Mhm. You've mentioned that you were always curious about the physical world and that an early question, you remember stood out where you asked your dad why does ice float on water? And he couldn't answer. And this was very surprising to you. Uh So you went on to learn why maybe you can speak to what are some early questions in math and physics that really sparked your curiosity? [/INST] Yeah, that memory is uh uh huh Kind of something I used to illustrate something, I think that's common in science, that people that do science somehow have maintained. Uh huh maintain something that kids always have a small kid, eight years old or so. uh ask you so many questions usually typically that you're consider them pests, You tell them to stop asking so many questions. Uh and uh somehow our system manages to kill that in most people. Yeah, so in school we make people to study and do their things, but not to pester by asking too many questions and um I think not just myself, but I think it's typical of scientists like myself that uh have somehow escaped that maybe we're still Children or maybe we somehow didn't get beaten out of us, but I think it's teaching in college level. And it's, to me one of the biggest deficits is the lack of curiosity if you want that we've beaten out of them because I think it's an innate human quality. </s><s>[INST] Is there some advice or insights you can give to how to keep that flame of [/INST] curious. It's a problem of both parents and and the parents should be, should realize that's a great quality. We have. You're curious and that's good. Instead we have, we have expressions like curiosity killed the cat. Yeah. And, and uh, and more, but I mean basically it's not, not thought to be a good thing. You're gonna curiosity killed the cat means if you're too curious, you get in trouble. And uh, </s><s>[INST] maybe it's a good thing. [/INST] Yeah. That to me needs to be solved really in education and in homes that realization that there's certain human qualities that we should try to build on and not destroy one of them is curiosity. Anyway, back to me and curiosity, I was a pest and asked a lot of questions my father generally could answer them. And at that age. And the first one I remember that he couldn't answer. Uh, was not a very original question, but basically that ice is made out of water. And so why does it float on water? Uh, and uh, he couldn't answer it. And it may not have been the first question is the first one that I remember. And that was the first time that I realized that to learn and answer your own curiosity or questions. There's various mechanisms in this case it was going to the library are asking people who know more and so forth. But eventually you do it by what we call research. But, but it's uh driven by, if you're hopefully you ask good questions. If you ask good questions and you have the mechanisms to solve them, then you do what I do in life basically. Not necessarily physics, but uh huh. And it's a great quality in humans and we should nurture it. </s><s>[INST] Do you remember any other kind of in high school, maybe early college, more basic physics ideas that sparked your curiosity or mathematics or science? And [/INST] I wasn't really into science until I got to college, to be honest with you, but just staying with water for a minute. I remember uh that I was curious uh why what happens to water? It rains and there's water in a wet pavement and then the pavement dries out what happened to this water that came to? And I, you know, I didn't know that much. And then eventually I learned chemistry or something and water is made out of hydrogen and oxygen. Those are both gases. So how the heck does it make this substance? It's liquid. Uh huh. </s><s>[INST] Yeah, but so that has to do with states of matter. You've uh I know perhaps lie going the thing for which you've got the Nobel prize and the things much of your life work perhaps was a happy accident in some sense, in the early days. But is there a moment where you looked up to the stars and also the same way you wondered about water wandered about some of the things that are out there in the universe. [/INST] Oh yeah, I think everybody looks and is in awe and it's curious about what, what it is out there and, you know, and as I learned more I learned of course that we don't know very much About what's there. And the more we learn, the more we know we don't know, I mean, we don't know what the majority of anything is out there. It's all what we call dark matter and dark energy. And that's one of the big questions 20 here when I was a student. Those weren't questions. So we even know less, in a sense, the more we, uh, the more we look. So of course, I think that's one of the areas that almost it's universal. People see the sky, they see the stars and they're beautiful and, and see it looks different on different nights and it's a curiosity that we all have, </s><s>[INST] what are some questions about the universe, that in the same way that you felt about the ice that today, you mentioned to me offline you're teaching, um, of course on the frontiers of science frontiers of physics, what are some questions outside? The ones will probably talk about that kind of, uh, yeah, fill you with, uh, get your flame of curiosity up and uh, firing up, Yeah, you know, for you with the, [/INST] well, first I'm a physicist, not an astronomer. So I'm interested in physical, the physical phenomenon really. So the question of uh Dark Matter and Dark Energy, which we probably won't talk about our recent there the last 2030 years, certainly dark energy. Dark energy is a complete puzzle. It goes against what will what you will ask me about, which is general relativity and Einstein's general relativity. It basically takes something that he thought was what he what he called a constant, which isn't and and uh and if that's even the right theory and it represents most of the universe, and then we have something called dark matter and there's good reason to believe it might be an exotic form of particles. Um and that is something I've always worked on on particle accelerators and so forth. And it's a big puzzle what it is. It's a bit of a cottage industry and that there's lots and lots of searches. Um but it may be a little bit like, you know, looking for a treasure under rocks or something, you know, it's hard to we don't have really good guidance except that we have very, very good information that is pervasive and it's there and that it's probably particles small that the evidence is all of those things. But then the most uh logical solution doesn't seem to work. Something called supersymmetry. </s><s>[INST] And do you think the answer could be something very complicated. [/INST] You know, I like to hope that think that most things that appear complicated are actually simple if you really understand them, I think we just don't know at the present time and it isn't something that affects us. It does affect, it affects how the stars go around each other and so forth because we detect that there's missing gravity but but it doesn't affect everyday life at all. I tend to think and expect maybe and that the answers will be simple. We just haven't found it yet. </s><s>[INST] Do you think those answers might change the way we see other sources of gravity? Black holes? The way we see the parts of the universe that we do study. [/INST] It's conceivable uh the black holes that we found in our experiment. And we're trying now to understand the origin of those. Yes, conceivable but not doesn't seem the most likely that they were pretty primordial. That is they were made at the beginning and they in that sense they could represent at least part of the dark matter. So there can be connections. Dark black holes are, how many there are, how much of the mess they encompass is still pretty primitive. We don't know. </s><s>[INST] So before I talk to you more about black holes, let me take a step back to, I was actually went to high school in Chicago and we'll go to take classes at Fermilab watch the buffalo and so on. So let me ask about, you mentioned that Enrico fermi was somebody who was inspiring to you in a certain kind of way. Um why is that? You speak to that? [/INST] Sure he was amazing actually. Uh, he's the last this is not the real come to the reason in a minute. But the he had a big influence on me at a young age. He uh but he was the only the last physicist of note, that was both an experimental physicist and the theorist at the same time. And he did two amazing things within months in 1933. He, it was we didn't really know what the nucleus was, what radioactive decay was, what beta decay was when electrons come out of A nucleus. And in nearly near the end of 1933, uh he The neutron had just been discovered and that meant that we knew a little bit more about what the nucleus is that it's made out of neutrons and protons. The neutron wasn't discovered till 1932. And then once we discovered that there was a neutron and proton and they made the nucleus and then their electrons that go around the basic ingredients were there. And he wrote down not only just the theory, a theory, but a theory that lasted decades and has only been improved on uh beta decay, That is the radio radiation. He did this came out of nowhere and it was a fantastic theory. He submitted to Nature magazine, which was the primary, uh best place to publish even then. And it got rejected as being too speculative. And so he went back to his drawing board in Rome where he was Added some two. It made it even longer because it's really a classic article and then published it in the local Italian Journal for Physics and the German one At the same time in 19 January of 1932. Giulio and Curie for the first time I saw artificial radio activity. This was an important discovery because radio activity had been discovered much earlier. You know, they had X rays and you shouldn't be using them. But there was radio activity. People knew it was useful for medicine, but radioactive materials are hard to find. And so it wasn't prevalent. But if you could make them then they had great use and Giulio and curie we're able to bombard aluminum or something with alpha particles and find that they excited something that decade and gave a decade and had some half life and so forth. Meeting it was artificial version, our let's call it not a natural version induced version of radioactive materials. And uh for me somehow had the insight and I still can't see where he got it. That the right way to follow that up was not using charged particles like alphas and so forth. But use use these newly discovered neutrons as the bombarding particle. It seemed impossible. They barely had been seen. Uh it was hard to get very many of them. But it had the advantage that they don't they're not charged. So they go right into the to the nucleus. And that turned out to be the experimental work that he did that won him the nobel prize. And it was the first step in vision, a discovery efficient and that's he did this two completely different things. An experiment that was a great idea and uh tremendous implementation because how do you get enough neutrons? And then he learned quickly that not only do you want neutrons, but you want really slow ones? Uh he he learned that experimentally and he learned how to make slow ones and then they were able to make go through the periodic table and make lots of particles. He missed on fishing at the moment, but he had the basic information and and then vision followed soon after that, </s><s>[INST] forgive me for not knowing. But is the birth of the idea of bombarding with uh neutrons? Is that uh is that an experimental idea was born out of an experiment? He just observes something? Or is this an Einstein style style idea where you, [/INST] I think I think I think that that took a combination because he realized that neutrons had a characteristic that would allow them to go all the way into the nucleus when we didn't really understand what the you know what what the structure was of all this. So that took ah understanding our recognition of the physics itself of how a neutron interacts compared to say an alpha particle. That Giulio and curie had used and then he had to invent a way to have enough neutrons. And uh, you know, he had a team associates and and he pulled it off quite quickly. So, you know, it's pretty astounding </s><s>[INST] and probably maybe you can speak to it. His ability to put together the engineering aspects of great experiments and doing the theory. They probably fed each other. I wonder can you speak to why we don't seem more of that? Is that just really difficult to do? [/INST] It's difficult to do. Yeah, I think in both theory and experiment in physics anyway, was it was conceivable if you had the right person to do it and no one's been able to do it. So I had the dream that that was what I was going to be like for me. But </s><s>[INST] you love both sides of it, the theory. [/INST] Yeah. I never liked the idea that you did experiments without really understanding the theory or the theory should be related very closely to experiments. And so I've always done experimental work that was closely related to the theoretical ideas. </s><s>[INST] I think I told you I'm Russian. So I'm gonna ask some romantic questions. But is it tragic to you that he's seen as the architect of the nuclear age that some of his creations lead to? Potentially some of his work has led to potentially still the destruction of the human species, some of the most destructive weapons. Yeah. [/INST] Uh, but I think even more general than him, I I I gave you all the virtues of curiosity a few minutes ago, there's an interesting book called the ratchet of curiosity. A ratchet is something that goes in one direction and that that is written by a guy who is probably a sociologist or philosopher or something and he he picks on this particular problem, but other ones and that is the danger of knowledge basically. You know, you're curious, you learn something. So it's a little bit like curiosity killed the cat. You have to be worried about whether you can handle new information that you get. So in this case the new information how to do with really understanding nuclear physics and that information, maybe we didn't have the sophistication to know how to keep it under control. Yeah. And fermi himself was a very a political person. So he wasn't very driven by our, or at least he appears in all of his writing, the writing of his wife, the interactions that others had with him as either he avoided it all or he was pretty a political. I mean, you just saw the world through kind of the lands of a scientist. But you asked if it's tragic. Uh, the bomb was tragic, certainly on Japan and he had a role in that. So I wouldn't want it is my legacy for example, </s><s>[INST] I mean, but brought it to the human species that it's the rapture of curiosity that we uh, we do stuff just to see what happens. That that curiosity, that uh sort of my area of artificial intelligence, that's been a concern there on a small scale. On a silly scale. Perhaps currently there's constantly speak unintended consequences. You create a system and you put out there and you have intuitions about how it will work. You have hopes how it will work. But you put it out there just to see what happens. And uh in most cases because artificial intelligence is currently not super powerful, it doesn't create uh large scale negative effects. But that same curiosity as it progresses might lead to something that destroys the human species. And the same may be true for bioengineering. There's people uh that, you know, engineer viruses to protect us from viruses to see, you know, how do how close is this to mutating? So it can jump to humans or or going, you know, or engineering uh defenses against those. And it seems exciting. And the application of positive applications are really exciting at this time. But we don't think about how that runs away in decades to come. [/INST] Yeah. And I think it's the same idea as this little book. The ratchet of science, uh ratchet of curiosity. I mean, whether you pursue take curiosity and let artificial intelligence or machine learning run away with having its solutions to whatever you want or we do. It is I think a similar consequence, </s><s>[INST] I think uh from what I've read about Enrico fermi, he he became a little bit cynical about the human species towards the end of his life. Both having observed what he observed, [/INST] we didn't write much. I mean he died young, he died soon after the World War. There was already you know the work by Teller to develop the hydrogen bomb and I think he was a little cynical of that pushing it even further and rising tensions between the soviet union and the U. S. And look like an endless thing. So but he didn't say very much but a little bit as you said </s><s>[INST] that yeah there's a few clips to sort of maybe picked on a bad mood but in a sense that almost like a sadness and melancholy sadness too. Uh I hope that waned a little bit about that. Uh perhaps we can do like the this curious species can find the way out. [/INST] Well especially I think people who worked like he did at Los Alamos and spent years of their life somehow had to convince themselves that dropping these bombs would bring lasting peace and and that it didn't. </s><s>[INST] As a small interesting aside would be interesting to hear if you have opinions on this. His name is also attached to the family paradox which asks if there is a you know with one but it's a very interesting question which is if it does seem if you sort of reason basically that there should be a lot of alien civilizations out there, if the human species, if Earth is not that unique by basic, no matter the values you pick. Uh, it's likely that there's a lot of alien civilizations out there. And if that's the case, why have they not at least obviously visited us or send us loud signals that everybody can hear [/INST] for me is quoted as saying, sitting down at lunch. I think it was with Tell her and her Byork who was kind of the one of the fathers of the atomic bomb. And he sat down and he says something like, where are they? Which meant where these other and uh, and then he did some numerology where he calculated, you know, how many, what they knew about how many uh Galaxies there are and how many stars and how many planets in our like the earth and blah, blah, blah. That's been done much better by somebody named drake. Uh, and so people usually refer to that. I don't know whether it's called the drake formula or something, but it has the same conclusion. The conclusion is it would be a miracle if there weren't other, you know, uh, there's the statistics are so high that how can we be singular and separate. Uh, that's so probably there is, but there's almost certainly life somewhere, maybe there was even life on mars a while back, but uh intelligent life probably white or we, so, so, you know, the statistics say that communicating with us. I think that it's harder than people think uh we might not know the right way to expect the communication, but all the communication that we know about travels at the speed of light. And we we don't we don't think anything go faster than the speed of light. That limits the problem quite quite a bit. And it uh makes it difficult to have any back and forth communication. You can send signals like we try to or look for but to have any communication, it's pretty hard when it has to be close enough that the speed of light would mean we could communicate with each other and I think, and we didn't even understand that. I mean, it was an advanced civilization, but we didn't even understand that a little more than 100 years ago. So uh are we just not advanced enough maybe uh to know something about that's the speed of light? Maybe there's some other way to communicate that isn't based on electromagnetism? I don't I don't know, gravity seems to be also have the same speed. That was a principle that Einstein had and something we've measured actually. </s><s>[INST] So it is it possible, I mean, so we'll talk about gravitational ways and in some sense there's um there's a brainstorming going on, which is like how do we detect the signal? Like what would a signal look like? And how would we detect and that's true for gravitational waves, that's true for basically any physics phenomena, you have to predict that that signal should exist. You have to have some kind of theory and model why that signal should exist. I mean, is it possible that aliens are communicating with us via gravity? Like why not? [/INST] Well, yeah, yeah, it's true. Why not? Uh for us, it's very hard to detect these gravitational effects. They have to come from something pretty that has a lot of gravity like black holes. But we're pretty primitive added at this stage. Uh There's uh Very reputable physicists that look for a 5th force one that we haven't found yet. Maybe it's the key. So, you know, </s><s>[INST] it's what would that look like? What would 1/5 force of physics look like? Exactly. [/INST] Well, usually they think it's probably a long range for longer range force than we have now. Uh but uh they're reputable colleagues of mine that spend their life looking for a </s><s>[INST] 5th Force so long arranged in gravity. Yeah, [/INST] super. Doesn't fall off like one over r squared, but maybe separately gravity. Uh Newton taught us goes like inversely one over the square of the distance apart. You are? So it falls pretty </s><s>[INST] fast. That's okay. So now we have a theory of what consciousness is. It's just the fifth force of physics. Yeah. There we go. That's a good hypothesis. Uh Speaking of gravity of gravity, what are gravitational waves? This maybe start from the basics, [/INST] we learned gravity from Newton, right? You and you were young, you were told that if you jumped up the earth pulls you down and when the output falls out of the tree, the earth pulls it down. And maybe you can ask your teacher why. But most of us accepted that. That was Newton's picture, the apple falling out of the tree. But Newton's theory never told you why the apple was attracted to the earth. That was missing in Newton's theory. Uh Newton Syria also. Newton recognized at least one of the two problems, I'll tell you, one of them is there's more than those, but one is why does the earth, what's the mechanism by which the earth pulls the apple or holds the moon when it goes around whatever it is? Uh That's not explained by Newton, even though he has the most successful theory of physics ever went 200 some years with nobody ever seeing violation. </s><s>[INST] But he actually describes the movement of an object falling on the Earth. But he's not answering why that? What's, Yeah, [/INST] because it's a distance. He gives a formula which which it's a product of the Earth's mass. The apples mass inversely proportional to the square of the distance between. And then the strength he called capital G. The strength, he couldn't determine. But it was determined 100 years later, but no one ever saw a violation of this until a possible violation which Einstein fixed, which was very small, that has to do with mercury going around the sun. There are but being slightly wrong if you calculated by Newton's theory. But so, um like most theories than in in physics, you can have a wonderful one. Like Newton's theory, it isn't wrong, but you have to have uh an improvement on it to answer things that it can't answer. And in this case Einstein's theory is the next step. We don't know if it's anything like a final theory or even the only way to formulate it either. But he formulated this theory which which he released in 1915, He took 10 years to develop it, even though in 1905, he solved three or four of the most important problems in physics in a matter of months and then he spent 10 years on this problem before he let it out. And this is called general relativity. It's a new theory of gravity. 1915 and 1916, Einstein uh wrote a little paper where he did not do some fancy derivation. Instead he did what I would call it, used his intuition, Which he was very good at two. and that is he noticed that if he formed if he wrote the formulas for general relativity in a particular way, they looked a lot like the formulas for electricity and magnetism been Einstein, he then took the leap That electricity and magnetism, we discovered only 20 years before that in the 1880s have waves of course that's light and electromagnetic grease radio waves, everything else. So he said if the formulas looked similar then gravity probably has ways to, </s><s>[INST] that's such a big leap by the way, I mean maybe you can correct me, but that just seems so that seems like a heck of a li [/INST] Yeah. And so that and it was considered to be a heck of elite. So first that paper was, except for this intuition was uh poorly written, had had a serious mistake. It had the a factor of two wrong and the strength of gravity, which meant if we used those formulas, we would. And uh two years later he wrote a second paper. And in that paper it turns out to be important for us because in that paper he not only fixed his factor of two mistake, which he never admitted, he just wrote it fixed it like he always did. And and then he uh told us how you make gravitational waves, what what makes gravitational waves? And you might recall an electromagnetism. We make electromagnetic waves in a simple way. You take a plus charge in minus charge. You oscillate like this. And that makes an electromagnetic waves. And a physicist named hurts made a receiver that could detect the waves and put it in the next room, he saw them and move forward and backward and saw that it was waived like. So uh Einstein said it won't be a die poll like that, it'll be a four pole thing and that's what it's called, a quadruple moment that gives the gravitational wave. So he so that again by insight, not by derivation, that's at the table for which I needed to do to do it at the same time in the same year. Shorts child not Einstein said there were things like called black holes. So it's interesting that that came the same. </s><s>[INST] So what year was that? That was 15? It was in parallel? Uh I should probably know this, but did Einstein not have an intuition that there should be such things as black holes [/INST] that came from shorts Child. </s><s>[INST] Oh, interesting. [/INST] Yeah. So Schwartz child who was a german theoretical physicist, he got killed in the war I think in the first World War two years later or so, he's the one that proposed black holes that there were black holes. </s><s>[INST] It feels like a natural conclusion of general relativity. No. [/INST] Or is that uh may seem like it, but I don't know about a natural conclusion. It is a it's a result of curved space time though, </s><s>[INST] Right. And it's it's such a weird result that you might have to uh it's a special, [/INST] it's a special case. Yeah. So uh I don't know anyway, Einstein then an interesting part of the story is that Einstein then left the problem, most physicists because it really wasn't derived, he just made this didn't pick up on it or general relativity much because quantum mechanics became the thing in physics. And Einstein uh only picked up this problem again after he immigrated to the US so he came to the US in 1932. And I think in 1934 5 he was working with another physicist called Rosen who did several important works with. And they revisited the question and they had a problem that most of us as students always had the study general relativity. General relativity is really hard because it's four dimensional instead of three dimensional. And if you don't set it up right, you get infinities which don't belong there, we call them coordinate singularities as a name. But if you get these infinities you don't get the answers you want. And uh he was trying to derive now general relativity uh from general relativity, gravitational waves. And in doing it he kept getting these infinities. And so he wrote a paper with Rosen that he submitted to our most important journal Physical Review Letters. And uh That when it was submitted to physical review letters, it was entitled do gravitational waves exist? A very funny title to write 20 years after he proposed they exist. But it's because he had found these singularities, these infinities. And so uh the editor at that time. And part of it that I don't know is peer review we live and die by peer review as scientists and our stuff out. And we don't know when peer review actually started or what your review Einstein ever experienced before this time. But the Editor of Physical Review sent this out for review, he had a choice, he could take any article and just accept it. He could rejected Aurica Senate for review. </s><s>[INST] I believe the editors used to have much more [/INST] power and he was a young man whose name was Tate and he ended up being editor for years. But uh so he sent this for review to uh a theoretical physicist named Robertson who was also in this field of general relativity, who happened to be on sabbatical at that moment at caltech. Otherwise his institution was Princeton where I sign was and he saw that the way they set up the problem, the infinities were like I make it as a student because if you don't set it up bright and general relativity you get these infinities. And so he reviewed the article and told gave an illustration that if they set it up in what are called cylindrical coordinates, these infinities went away. He's uh Editor of Physical Review was obviously intimidated by Einstein. He wrote this really not a letter back, like I would get saying, you know, you're screwed up in your paper instead it was kind of uh what do you think of the comments of our referee Einstein wrote back, it's a well documented letter wrote back a letter to physical review saying uh I didn't send you the paper to to send it to one of your so called experts. I sentence you to publish, I know I withdraw the paper uh and he never published again in the in that journal, that was 1936. Instead he rewrote it with the fixes that were made, changed the title and published it in what was called the franklin Review, which is the franklin Institute in philadelphia, which is Benjamin franklin Institute, which doesn't have a journal now, but did at that time. So the article is published, it's the last time he ever wrote about it, it remained controversial. So it wasn't until Close to 1960, where there was a conference which brought that brought together the experts in general relativity to try to sort out whether there was um whether it was true that there were gravitational waves or not. And there was a very nice derivation by a british theorists from the heart of the theory that gets gravitational waves. Uh And that was number one, the second thing that happened at that meeting is Richard Feynman was there and Feinman said, well if there's a typical Feinman, if there's gravitational waves, they need to be able to do something otherwise they don't exist. So they have to be able to transfer energy. So he made a idea of a good Duncan experiment, that is just a bar with a couple of rings on it and then if a gravitational wave goes through it distorts the bar. Uh and that creates friction on these little rings and that's heat and that's energy. So that that meant, </s><s>[INST] is that a good idea? That sounds like a good idea. [/INST] Yeah. It means that he showed that with the distortion of space time, you could transfer energy just by this little idea. And it was shown theoretically. So at that point it was uh huh believe theoretically than by people that gravitational waves should exist. </s><s>[INST] No, we should be able to detect that [/INST] means we should be able to detect them except except that they're very, very small. </s><s>[INST] Just so what kind of uh there's a bunch of questions about what kind of events would generate gravitational waves? [/INST] You have to have. This, what I call quadruple moment that comes about. If I have uh for for example, to objects that go around each other like this, like the Earth, the Earth around the sun, or the moon around the Earth. Or in our case it turns out to be two black holes going around each other like this. </s><s>[INST] How is that different than basic oscillation? Back and forth. This is just more common in nature. [/INST] Oscillation is a dipole moment. </s><s>[INST] It has been three dimensional space kind of [/INST] So you have to have something that's three dimensional, that'll give what I call the quadruple moment that's just built into this </s><s>[INST] and luckily nature you have stuff uh [/INST] and luckily things exist and it is luckily because the effect is so small that you could say look I can take a bar bell and and spin it right and detected gravitational waves. But unfortunately no matter how much I spend it, how fast I spent it it's so I know how to make gravitational waves but they're so weak. I can't detect them. So we have to take something that's stronger than I can make otherwise. We would do what hurts did for electromagnetic waves? Go in our lab, take a bar bell, put it on something spinning </s><s>[INST] casket. Don't question. So a single object that's weirdly shaped. Does that generate gravitational waves? So if it's if it's rotating [/INST] sure it was just much weaker so it it's weaker. Well we didn't know what the strongest signal would be that we would see, we targeted seeing something called nutrients stars actually because black holes we don't know very much about it turned out were a little bit lucky there was a stronger source which was the black holes. </s><s>[INST] Well, another ridiculous question. So you say waves, what does what does the wave mean? Like uh the most ridiculous version of that question is what does it feel like to ride a wave as you get closer to the source or experience it. [/INST] Well if you experience a wave, imagine that this is what happens to you. I don't know what you mean about getting close. It comes to you. So it's like it's like uh this lightweight for something that comes through you. So when the light is you makes your eyes detective. I flashed it. What does this do is it's like going to the amusement park and they have these mirrors, you look in this mirror and you look short and fat and the one next to you makes your tall and thin. Okay. Imagine that you went back and forth between those two mirrors once a second that would be a gravitational wave with a period of once a second. Uh if you did it 60 times a second, go back and forth. And and then that's all that happens. It makes you taller and shorter and fatter back and forth as it goes through you at the frequency of the gravitational wave. So the frequencies that we detect are higher than one a second. But that's the idea. But and this amount is small </s><s>[INST] amount of small but when if you're closer to the to the source of the wave is it the same amount? [/INST] Yeah, it doesn't dissipate, It </s><s>[INST] doesn't dissipate. Okay, so it's not that fun of an amusement ride. [/INST] Well it does dissipate but it doesn't it doesn't, it's proportional to the distance. </s><s>[INST] It's not sound a big power got you. So but it would be a fun ride if you get a little bit closer or a lot closer. I mean like I wonder what the this is ridiculous question. But have you here like getting fatter and taller. Yeah, I mean that experience for some reason that's mind blowing to me because it brings the distortion of space time to you. I mean spacetime is being morphed right? Like this is a way right? That how that's so weird. [/INST] And we're in space. </s><s>[INST] Yeah, we're in space and it's moving. I don't know what to do with it. I mean does it okay. Um how much do you think about the philosophical implications of general relativity like that we're in space time and it can be bent by gravity. Like is that just what it is? We're supposed to be okay with this because like Newton, even Newton is a little weird. Right? But that at least that makes sense. That's our physical world. You know when an apple falls it makes sense. Well like the fact that entirety of the space time we're in can bend. Well that's uh that's really mind blowing. [/INST] Let me make another analogy. This </s><s>[INST] is a therapy session for me. [/INST] Another analogy. So imagine you have a trampoline. Yes. Okay. What happens if you put a marble on a trampoline doesn't do anything. Right? </s><s>[INST] No, just makes a little bit, but not much. [/INST] Yeah, I mean just if I drop it, it's not gonna go anywhere. Now imagine I put a bowling ball at the center of the trampoline. Now I come up to the trampoline and I put a marble on. What happens, </s><s>[INST] you know roll towards the bowling ball. [/INST] All right, so what's happened is the presence of this massive object distorted the space that the trampoline did. This is the same thing that happens to the presence of the earth, the earth and the apple. The presence of the earth affects the space around it. Just like the bowling ball on the trampoline. </s><s>[INST] Yeah. This doesn't make me feel better I'm affirmed from the perspective and ant walking around on the trampoline. Then some guy just dropped the ball and then not only dropped the ball right? It's not just dropping a bowling ball, it's making the ball go up and down doing some kind of oscillation thing where it's like waves and that's so fundamentally different from the experience on being on flat land and walking around and just finding delicious sweet things as Antas. And just it just feels like to me from a human experience perspective completely. It's humbling. It's truly humbling. [/INST] It's something but we see that kind of phenomenon all the time. Let me give you another example, imagine that you walk up to a still pond. Yes. Okay now I throw you like you throw a rock in what happens the rock goes in sinks to the bottom fine and these little ripples go out and they travel, oh that's exactly what happens. I mean there's a disturbance which is he safe? The bowling ball or black holes and then the ripples that go out in the water. They're not they don't have any they don't have the rock any part pieces of the </s><s>[INST] rock. And see. The thing is I guess what's not disturbing about that is it's a I mean I guess a flat two dimensional surfaces being disturbed, Like for a three dimensional surface uh three dimensional space to be disturbed, feels weird. [/INST] It's even worse. It's for dimension because it's space and time. So that's why you need Einstein is to make it uh for dimensionally No. Uh yeah, the same phenomenon. And look at it in all of space and time. Anyway, luckily for you and I and all of us, the amount of distortion is incredibly small. So it turns out that if you think of space itself now this is going to blow your mind too. If you think of space as being like a material like this table, uh it's very stiff. You know, we have materials that are very pliable materials that are very stiff. So space itself is very stiff. So when gravitational waves come through it luckily for us it doesn't distort it so much that it affects our ordinary life very much. </s><s>[INST] No, I mean that's great. That's great. I thought there was something bad coming now, this is great. That's great news. So I mean that perhaps we evolved as a life on Earth be such that for us, this particular set of uh effects of gravitational ways. Uh, it's not that significant. Maybe, maybe, maybe that's [/INST] why you probably used this effect today. Yesterday. What? So it's, it's pervasive, well, </s><s>[INST] you mean gravity or the way the external, because I only [/INST] curvature of space and </s><s>[INST] curvature of space. How I only care person is a human, right? The gravity of Earth. [/INST] But you use it every day almost </s><s>[INST] because [/INST] No, no, no. It's in this thing. Every time it tells you where you are, how does it tell you where you are? It tells you where you are because we have 24 satellites or some number that are going around in space. And it asked how long it takes uh, being to go to the satellite and come back the signal to different ones. And then it triangulate its and tells you where you are. And then if you go down the road, it tells you where you are. Do you know that if you did that with the satellites and you didn't use Einstein's equations, you won't get the right answer. That's right. And in fact, if you take a road, let's say 10 m wide, I've done these numbers and you ask how long you stay on the road. If you didn't make the correction for general relativity. This thing you're pooh poohing is you're using every day. Uh, you go off the road. You </s><s>[INST] go, well actually, that might might [/INST] use it so well. </s><s>[INST] Well, I think I'm using an andrews and maybe, and the GPS doesn't work that well. So maybe I'm using Newton's physics. Uh oh, I need to upgrade to general relativity. Um so gravitation waves and Einstein had uh Wait Fireman really does have a part of the story, was that one of the first kind of experimental, proposed, he [/INST] did what we call a Goddam can experiment. That's a thought experiment. Okay, not a real experiment, but then after that, then people believe gravitational waves must exist. You can kind of calculate how big they are, there's tiny. And so people started searching the first idea that was used was feynman's idea uh very end of it. And it was to take a great big, huge bar of aluminum and then put around and it's made like a cylinder and then put around it some very, very sensitive detectors so that if a gravitational wave happened to go through it, it would go and you detect this extra strain that was there. And that was this method that was used until we came along. It wasn't a very good method to use </s><s>[INST] and what was the so we're talking about a pretty weak signal here. [/INST] Yeah, that's why that method didn't work. </s><s>[INST] So what can you tell the story of figuring out what kind of method would be able to detect this very weak signal of gravitational ways. [/INST] So remembering the, remembering what happens when you go to the amusement park that is going to do something like stretch this way and squash that way, squash this way and stretch this way we do haven't instrument that can detect that kind of thing. It's called an interferometer. And what it does is it just basically takes usually light and the two directions that we're talking about, you send light down one direction and the perpendicular direction. And if nothing changes, it takes the same and the arms of the same length, it just goes down, bounces back and if you invert one compared to the other, they cancel. So there's nothing happens. But if it's like the amusement park and one of the arms got, you know, got shorter and fatter. So it took longer to go horizontally than it did to go vertically then when they come back, when when the light comes back, that comes back somewhat out of time. And that basically is the scheme. The only problem is that that's not very done very accurately in general and we had to do it extremely accurately. </s><s>[INST] So what uh what what's the what's the difficulty of doing so accurately. [/INST] Okay, so the measurement that we have to do is a distortion in time, How big is it? 1? It's a distortion. That's one part in 10 to the 21? That's 21 zeros and a one. Okay. </s><s>[INST] And so this is like a delay in the thing coming back. [/INST] Uh it's one of them coming back after the other one, but the difference is just one part in 10 to the 21. So for that reason we make it big, let the arms be long. Okay, so one part in 10 of the 21, in our case it's kilometers long. So we have an instruments of kilometres in one direction kilometers in the other </s><s>[INST] 44 [/INST] kilometers in each direction. uh if you take then one part in 10 to the 21, we're talking about measuring something to Uh 10 to the -18 m. </s><s>[INST] Okay, [/INST] now, to tell you how small that is? Yeah, the proton Things were made of that, you can't go and grab so easily is 10 to the -15 m. So this is 1,000th the size of a proton, that's the fact size of the effect. Einstein himself didn't think this could be measured, I've ever seen actually, he said that, but that's because he didn't, you know, anticipate modern lasers and and techniques that we developed. </s><s>[INST] Okay, so maybe can you tell me a little bit what you're referring to as ligo, the laser interferometer, gravitational wave observatory, what is like, go, can you just elaborate kind of the big picture of you here before I ask you specific questions about it? [/INST] Yeah, So in the same idea that I just said we have too long vacuum Piper tend to uh four km long. Okay, we start with a laser beam and we divide the beam Going down the two arms and we have a mirror at the other end reflects it back. It's more subtle but we bring it back if there's no distortion in space time and the lengths are exactly the same which we calibrate them to be. Then when it comes back, if we just Invert one signal compared to the other, they'll just cancel. So we see nothing. Okay. But if one arm got a little bit longer than the other, then they don't come back at exactly the same time. They don't exactly cancel. That's what we measure. So to give a number to it we have to do that too. We have the change of length to be able to do this 10 to the minus 18 m to one part in 10 to the 12th. And that was the big experimental challenge that required a lot of innovation to be able to do </s><s>[INST] what you gave a lot of credit to. I think caltech and MIT for some of the technical developments like within this project, is there some interesting things you can speak to like at the low level of some cool stuff that to be solved like what are we? I'm a software engineer. So all of this. I have so much more respect for everything done here than anything I've ever done. So it's just code. [/INST] So I'll give you an example of doing. Uh huh. Mechanical engineering at a better a basically mechanical engineering and geology and maybe at a level. Uh So what do we what's the problem? The problem is the following that I've given you this picture of an instrument that by some magic I can make good enough to measure this very short distance. But then I put it down here, it won't work. And the reason it doesn't work is that the earth itself is moving all over the place all the time. You don't realize it it seems pretty good to you. But it's moving all the time. So somehow it's moving so much that we can't deal with it. We happen to be trying to do the experiment here on Earth but we can't deal with it. So we have to make the instrument isolated from the Earth. Oh no. At the frequencies rat we've got to float it. That's a mechanical that's an engineering problem. Not as physics problem. </s><s>[INST] So when you actually like we're doing we're having a conversation, a podcast right now, there's uh people record music, work with this. You know how to create an isolated room. And they usually build a room within a room but that's still not isolated. In fact, they say it's impossible to truly isolate from sound from noise and stuff like that. But that that that's like one step of millions that you took. It's building a room inside the room. But you basically have to isolate all. [/INST] Now this is actually an easier problem. It's just have to do it really well. So making a clean room is really a tough problem because you have to put a room inside a room and you have to. So this is really simple engineering or physics. Okay. So what do you have to do? How do you isolate yourself from the, from the Earth? First? We work at uh we're not looking at all frequencies for gravitational waves. Were looking at particular frequencies that you can deal with here on Earth. So what the frequencies with us pay? You were just talking about frequencies. Mhm. </s><s>[INST] We [/INST] know by evolution. Her body's No, it's the audio band. Okay. The reason our ears work where they work because that's where the earth isn't going. Making too much noise. </s><s>[INST] Okay, so the reason our ears work the way they work is because it's just worth quiet. That's [/INST] right. So if you go to, if you go to one hurts instead of 10 hertz is the earth </s><s>[INST] is it's [/INST] really moving around. So, so somehow we live in a what we call the audio bandits tens of hertz to thousands of hurts. That's where we live. That's where we live. Okay, if we're going to do an experiment on the Earth, </s><s>[INST] might as well do it. [/INST] It's the same frequency. That's where the earth is a quiet is. So we have to work in that frequency. So we're not looking at all frequencies. Okay, so the solution for the for the shaking of the earth to get rid of it is pretty mundane if we do the same thing that you do to make your car drive smoothly down the road. So what happens when your car goes over a bump? Early cars did that? They bounced. Okay. But you don't feel that in your car. So what happened that energy, you can't just disappear energy. So we have these things called shock absorbers in the car. What they do is they absorb they take the thing that went like that and they basically can't get rid of the energy, but they move it to very, very low frequency. So what you feel isn't you feel like go smoothly? Okay. All right. So, uh, we also work at this frequency. So if we so we basically why, why why do we have to do anything other than shock observers? So, we made the world's fanciest shock observers. Okay. Uh, not just like in your car where there's one layer of them, they're just the right squishiness. And so far they're better than what's in the cars. And we have four layers of it. So whatever shakes and gets through the first layer, we treated a 2nd 3rd. </s><s>[INST] So, some mechanical engineering problem. [/INST] What I said. So it's </s><s>[INST] not, there's no weird tricks to it, like, like a chemistry type thing or [/INST] just, well, the right squishing a senior, I need the right material inside an argument. Like little springs, but there springs </s><s>[INST] there's springs. So like legitimately like shock absorbers. [/INST] What? Okay, and this is now experimental physics at the at its limit. Okay, so you do this and we make the world's fanciest shock absorbers. Just mechanical engineering. </s><s>[INST] Just mechanical genius is hilarious. [/INST] But we didn't we weren't good enough to discover gravitational waves. So uh so we did another, we added another feature and it's something else that you're aware of? Probably have one. And that is to get rid of noise. You've probably noise, which is you don't like. And that's the same principle that's in these little bows, uh </s><s>[INST] canceling [/INST] noise canceling. So uh so how do they work? They basically you go on an airplane and they sense the ambient noise from the engines and cancel it because it's just the same over and over again, they cancel it. And when the stewardess comes and asks you whether you want coffee or tea or a drink or something, you hear you're fine because she's not ambient. She's a signal. So </s><s>[INST] we're talking about active cancelling, like we're [/INST] actually canceling. </s><s>[INST] So this is OK. So another don't tell me you have active canceling on this [/INST] besides the show. So we had this. So inside this array of shock absorbers. We you asked for some interesting. </s><s>[INST] This is awesome. [/INST] So inside this it's harder than the earphone problem, but it's just engineering. We have to see measure not just the engine's still made noise, but the earth is shaking is moving in some direction. So we have to actually tell not only that there's noise and cancel it, but what direction is from? So we put this array of seismometers inside this array of shock absorbers and measure the residual motion and its direction. And we put little actuators that pushback against it and cancel it. This is </s><s>[INST] awesome! So you have the actuators and you have the thing that is sensing the vibrations and and then you have the actual actuators that adjust for that and do so imperfect [/INST] synchrony. What if it all works right? And so how much do we reduce the shaking of the earth? </s><s>[INST] I mean [/INST] One part in 10 to the 12th. </s><s>[INST] One part. [/INST] And so what gets through us is one part in 10 of the 12th. That's pretty big reduction. You don't need that in your car. But that's what we do. And so that's how isolated we are from the earth. And that was the biggest, I I say technical problem outside of the physics instrument, the interferometer? </s><s>[INST] A weird question here you make it very poetically and humorously is saying it's just a mechanical engineering problem. But is this one of the biggest precision mechanical engineering efforts ever? I mean, this seems exceptionally difficult. [/INST] It is. And so it took a long time and I think nobody seems to challenge the statement that this is the most precision precise instrument that's ever been built, ligo. </s><s>[INST] I wonder what like listening to led Zeppelin sounds on this thing because it's so isolated. I mean this is like uh I don't know no background. No, no back. It's wow, wow, wow. So when you were first conceiving this, um I would probably uh if I was knowledgeable enough kind of laugh off the possibility this is even possible. I'm sure like how many people believe that this is possible. Did you [/INST] believe I did? Uh I didn't know that we need for sure that we needed active when we started we did this passive but we were doing the tests to develop the active to add is the second stage which we ended up needing. Uh but there was a lot of now, now there was a lot of skepticism, a lot of us, especially astronomers felt that money was being wasted as we were also expensive. Doing what I told you it's not cheap. So it was kind of controversial is funded by the National Science Foundation. </s><s>[INST] Can you just linger on this just for a little longer and the actuator thing? The act of canceling um do you remember like literal experiments that were done along the way to prove to the team to themselves that this is you impossible. So from our, because I worked with quite a bit of robots and to me the idea that you could do it this precisely is a humbling and embarrassing frankly because like this is another level of precision that I can't even uh because robots are a mess and this is basically one of the most precise robots ever. Right so like is there uh we have any like small scale experiments that were done that I believe this is possible. [/INST] Yeah and larger scale we made we made tests uh that also has to be in vacuum to but we may test chambers that had this system in it. Our first mock of this system. So we could test it and uh optimize it and make it work. But it's just a mechanical engineering problem. </s><s>[INST] Okay humans are just eight descendants. I got you. I got you. Uh Is there any video of this like uh some kind of educational purpose visualizations of this act of canceling. [/INST] Uh I don't think so. I </s><s>[INST] mean is this does this live on? [/INST] Well we work for parts of it for the active canceling. We worked with for the instruments for the sensor and instruments. We worked with a small company and met near where you are because it was our M. I. T. People that got them there were you know interested in the problem because they thought they might be able to commercialize it for making staple tables to make microelectronic for example which are limited by the house stable. The table is I mean at this point it's a little expensive </s><s>[INST] so you never know never know where this leads. Okay so maybe on the let me ask you just sticking it a little longer. This silly old mechanical engineering problem. Uh what was uh do you kind of the darkest moment of what was the hardest stumbling block to get over on the engineer side? Like was there any time where there's a doubt where it's like, I'm not sure we would be able to do this kind of uh engineering challenge that was hit. Do you remember anything like that? I [/INST] think the one that that my colleague at MIT Ray Weiss worked on so hard and was much more of a worry than this. This is only a question. If you're not do it well enough you have to keep making it better somehow. But this whole huge instrument has to be in vacuum and uh the vacuum tanks are, you know, this big around and uh so it's the world's biggest high vacuum system. And uh how do you make it, first of all? How do you make this four metre long sealed vacuum system? It has to be made out of </s><s>[INST] four kilometers, [/INST] four kilometers, would I say? Something else? Meters for four kilometers long. Big difference. Yeah. And uh so but to make it, yeah, we started with uh a role of stainless steel and then we spy roll it out like a spiral so that there's a spiral weld on it. Okay, so the engineering was fine. We did that. We worked through a very good companies and so forth to build it. But the big worry it was what if you develop a leak this is a high vacuum, not just vacuum system. Typically in your in a laboratory, if there's a leak, you put helium around the the thing you have and then you detect where the helium is coming in. But if you have something as big as this, you can't surround it with a liam. </s><s>[INST] You might not actually even know that there's a leak and it will be affecting. Well, [/INST] we we have we can measure the how good the vacuum is so we can know that. But there are we can develop and and then we don't how do we fix it or how do we find it? And uh so that was you asked about a worry. That was always a really big worry. Uh </s><s>[INST] What's the high vacuum and a vacuum? What is high vacuum? That's like some adult of close to vacuum. Is there some threshold? [/INST] Well, there's a unit high vacuum is when the vacuum in the units that are used. Richard Tours there's 10 to the -9. Uh And there's high vacuum is usually used in small places. The biggest vacuum system period. Is that cernan this big particle accelerator. But the high vacuum where they need really good vacuums of particles don't scatter and is smaller than our so ours is a really large high vacuum system. </s><s>[INST] I don't know. This is so cool. I mean, this is basically by far the greatest listening device ever built by humans. The fact that like descendants of apes could do this. The evolution started with single cell organisms. I mean, is there any more? I'm a huge uh theories like Yeah, yeah. But like bridges, when I look at bridges from a civil engineering perspective is one of the most beautiful creations by human beings. It's physics. You're using physics to construct the objects that can support huge amount of mass and it's like structural, but it's also beautiful and that humans can collaborate to create that throughout history. And then you take this on another level. This is this is like it's so exciting to me beyond measure that humans can create something so precise. [/INST] But another concept lost in this. You just said you started talking about single cell. Yeah. Okay. If they realize this discovery that we made that everybody spot off on happened 1.3 billion years ago Somewhere and then the signal came to us 1.3 billion years ago, we were just converting on the earth from single cell to multi cell life. So when this actually happened, this collision of two black holes, we weren't here, we weren't even close to </s><s>[INST] people developing. [/INST] Were single. Yeah, we were we were going from single cell to multi cell life at that </s><s>[INST] point to meet up at this at this point, wow, that's like uh, that's almost romantic. Uh okay, so on the human side of things is kind of fascinating because you're talking about over 1000 people team for lego [/INST] uh </s><s>[INST] that started out with the, you know, around 100 and you've uh for parts of the time at least lead this team, what does it take to lead a team like this of incredibly brilliant theoreticians and engineers and just a lot of different parties involved, a lot of egos, a lot of ideas. You had this funny, funny example, forget where we're in publishing a paper, you have to all agree on like uh you know, the phrasing of a certain sentence or the title of the paper and so on. That's a very interesting simple exam, I'd love you to speak to that. But just in general, how what does it take to lead this kind of team? [/INST] Okay. Uh I think the general idea is when we all know you want to, you want to you want to get where the sum of something is more than the individual parts is what we say. Right? So that's what you're trying to achieve. Okay, how do you do that actually? Mostly if we take multiple objects or people, I mean you put them together, the sum is less why? Because they overlap. So you don't have individual things that you know, this person does that, this person does that, then then you get exactly the sum, but what you want is to develop, where you get more than what the individual contributions are. We know that's very common. People use that expression everywhere. And it's the expression that has to be kind of build into how people feel it's working because if you're part of a team and you realize that somehow the team is able to do more than the individuals could do themselves than they buy on kind of in terms of the process. So that's the, that's the goal that you have to have is to achieve that. And that means that you have to uh realize parts of what you're trying to do. That require, not that one person couldn't do it, it requires the combined talents to be able to do something that neither of them could do themselves and we have a lot of that kind of thing. And I think, um, I mean build into the some of the examples that I gave you and so how do you then? So, so the key almost in anything you do is the people themselves. Right? So in our case the first and most important was to attract to spend years of their life on this, the best possible people in the world to do it. So the only way to convince them is that somehow it's better and more interesting for them than what they could do themselves. And so that's part of this uh idea. </s><s>[INST] Yeah, that's powerful. But nevertheless, there's best people in the world, there's egos, Is there something to be said about managing egos? [/INST] Well, that's the human problem is always the hardest. And so there's that's an art, not a science. I think. I think the fact here that combined, there's a was a romantic goal that we had to do something that people hadn't done before, which was um important scientifically and and a huge challenge enabled us to say take and get uh I mean, what we did just take an example. We used the light to go in. This thing comes from lasers, we need a certain kind of laser. So the kind of laser that we use, there were three different institutions in the world that had the experts that do this maybe in competition with each other. So we got all three to join together and work with us uh to work on this as an example, so that you had uh and they had the thing that they were working together on a kind of object that they wouldn't have otherwise. And uh we're part of a bigger team where they could discover something that isn't even engineers. These are engineers that do laser. So, and they're part of our laser physicists. And </s><s>[INST] so, could you describe the moment or the period of time when finally this incredible creation of human beings lead to a detection of gravitational waves. [/INST] It's a long story, unfortunately, this is a part that uh we started </s><s>[INST] failures. We stayed away kind of thing are [/INST] all failures, that's all that's built into it. If you're not, if you're </s><s>[INST] not mechanical engineering, you [/INST] build on your failures that's expected. So we're trying things that no one's done before. So it's technically not just gravitational waves and so it's built on failures. But anyway, we did before me. Even the people did R. And D. On the concepts. But starting in 1994, we got money from the National Science Foundation to build this thing. um, it took about five years to build it. So by 1999 we had built the basic unit. It did not have active seismic isolation at that stage. Didn't have some other things that we have. Now. What we did at at the beginning was stick to technologies that we had at least enough knowledge that we can make work or had tested in our own laboratories. And so then we put together the instrument, we made it work, didn't work very well, but it worked and we didn't see any gravitational waves. Then we figured out what limited us. And we went through this every year for Almost 10 years. Never seen gravitational waves. We would uh run it looking for gravitational waves for months, learn what limited us, fix it for months and then run it again. Eventually we I knew we had to take another big step. And that's when we made several changes, including going adding these active seismic isolation, which turned out to be a key. Um and we fortunately got the National Science Foundation to give us another couple $100 million. 100 million more. And uh we rebuild it are fixed, our improved it. and uh then in 19 uh 2015 We turned it on and uh we um almost instantly saw this first collision of two black holes. Um and then then we went through a process of do we believe what we've seen? </s><s>[INST] Yeah I think I think you're one of the people that went to that process sounds like some people immediately believed it and then you're [/INST] like human beings, we all have different reactions, still has anything. And so quite a few of my colleagues had a Eureka moment immediately. I mean this amazing the figure that we that we put in our paper first is just data. We didn't have to go through you know fancy computer programs to do anything. And and we showed next to it uh the calculations of Einstein's equations, it looks just like the what we detected and we did in two different detectors halfway across the U. S. So it was pretty convincing. But uh huh. But you don't want to you don't want to fool yourself. So we had, being a scientist, we had a for me we had to go through and try to understand that the instrument itself which was new. I said we had rebuilt it couldn't somehow generate things that look like this that took some tests and then uh the second you'll appreciate more we had somehow convince ourselves we weren't hacked in some clever way, </s><s>[INST] cyber security question. [/INST] Yeah. Even though we're not on the internet, the but </s><s>[INST] no, it can be physical access to. Yeah, that's fascinating. It's fascinating. You would think about that. I mean, not not enough. I mean, because it's it's uh it matches prediction. So the chances of it actually being manipulated is very, very low. But nevertheless, [/INST] we still could have disgruntled all graduate students who had worked with us earlier </s><s>[INST] that I want you to I don't know how that's supposed to embarrass you, I suppose. Yeah, I suppose. I see. But but about what I think you said within a month, you kind of convince yourself sufficient [/INST] in a month. We convinced ourselves we kept a 1000 collaborators quiet during that time. Then we spend another month or so trying to understand what we've seen so that we could do the science with it instead of just putting it out to the world and let somebody else understand that it was two black holes. What it was. </s><s>[INST] The fact that 1000 collaborators were quiet is a really strong indication that this is a really close knit team [/INST] and their around the world or either strong, either strong net or tight knit or had a strong dictatorship </s><s>[INST] or something. Either fear love. You can rule by fear, love can go back to Maggie Valley. All right, well, this I mean, it was really exciting that that was that that's a success story because it didn't have to be a success story, right? I mean, eventually, perhaps you could say it will be in effect, but it could have taken it over a century [/INST] to get Yeah, it's uh uh and it's only downhill now. Kind </s><s>[INST] of. What do you mean? You mean it was gravitational? [/INST] Well, we're yeah, we've we've now we now uh but now we're off because of the pandemic. But when we turned off, we were seeing some sort of gravitational wave event each week, uh now we're fixing we're fixing we're adding features where it will probably be when we turn back on next year. It'll probably everyone every couple of days and they're not all the same. So it's learning about what's out there in gravity instead of just optics. So, it's all uh great. We're only limited by the fantastic thing other than that, this is a great field. And, you know, it's all new and so forth, is that experimentally the great thing is that uh we're limited by technology and technical limitations, not by science. So they they another a really important discovery that was made before ours was what's called the Higgs boson made a big accelerator at Cern, you know, this huge accelerator. They discovered a really important thing. It's you know, we have Einstein's equation E equals M. C. Squared. So energy makes mass or mass can make energy and that's the bomb. But the mechanism by which that happens not vision but how do you create mass from energy? Uh Was never understood until there was a a theory I've heard about 70 years ago now. And uh so they discovered it's named after a man named Higgs. It's called the Higgs bosa. And so it was discovered. But since that time and I worked on those experiments, since that time, they haven't been able to progress very much further a little bit but not a lot further. And the difference is that we're really lucky, we're uh in what we're doing in that there uh your you see this Higgs boson. But there's tremendous amount of other physics that goes on and you have to pick out the needle in the haystack kind of physics. You can't make the physics go away, it's there in our case we have a very weak signal but once we get good enough to see it, It's weak compared to where we've reduced the background. But the background is not physics, it's just technology, you know, it's getting ourselves better isolated from the earth or getting a more powerful laser. And so each time each since 2015 when we saw the first one, we continually can make improvements that are enabling us to turn this into a real science. To do astronomy? A new kind of astronomy. It's a little like astronomy. I mean Galileo started the field. I mean, he basically took lenses that were made for classes, uh and he didn't invent the first telescope made a telescope looked at uh Neptune and so that it had four months, that was the birth of not just using your eyes to understand what's out there. And since that time we've made better and better telescopes obviously, and astronomy thrives and in a similar way, we're starting to be able to for crawl, but we're starting to be able to do that with gravitational waves and it's going to be more and more that we can do is we can make better and better instruments, because as I say, it's not limited by um picking it out of others. Yeah, it's not limited by the physics. </s><s>[INST] You have an optimism about engineering that event, you know, as we as human progress marches on engineering will always find a way to uh to build a large enough device accurate enough device to detect this, [/INST] as long as it's not limited by physics. Yeah, they will do it. </s><s>[INST] Yes, So, you two other folks and the entire team won the Nobel prize for this big effort. There's a million questions I can ask for, but looking back, Mhm. Where does the Nobel prize fit into all of this? You know, if you think hundreds of years from now, I venture to say that people will not remember the winners of the prize, but they'll remember creations like these, Maybe I'm romanticizing engineering, but I guess I wanna ask how important is the Nobel prize in all of this? [/INST] Um Well that's a that's a complicated question. It uh yeah, as a physicist, it's something if you're if you're trying to win a Nobel prize, forget it, because they give you no one a year. So there's uh there's been 200 physicists have won the Nobel Prize since 1900, and so that's. you know, and so things just have to fall, right, so your goal cannot be to win an oil price wasn't my dream. Uh it's uh it's uh tremendous for science, I mean, why the Nobel prize for a guy that made dynamite and stuff, you know what it is, it's a long story, but it's the one day a year were actually the science that people have done is all over the world and so forth. Forget about the people again, you know, it is really good for for science </s><s>[INST] celebrating science [/INST] celebrates science for several days, different fields, uh chemistry, medicine and so forth, and everybody doesn't understand everything about these, generally fairly abstract, but then, you know, it's on the front page of newspapers around the world, so it's really good for science, it's not easy to get science on the front page of the new york times, it's not, there should be, but it's not, and uh um so the Nobel prize is important in that way. Uh it's otherwise, you know, I have a certain celebrity that I didn't have before, um </s><s>[INST] and now you get to be a celebrity that advertises science, it's a mechanism to uh remind us how incredible, well how much credit science deserves and everything. [/INST] Well it has a little bit more, one thing I didn't expect, which is good is that, you know, we have a government, yeah, I'm not picking on ours necessarily, but it's true of all governments are not run by scientists, in our case is run by uh lawyers and businessmen, okay, uh and at best they may have an aide or something that knows a little science, so um so our country is and all countries are hardly uh hardly take into account science in making decisions, okay, and uh having a Nobel prize, the people in those positions actually listen, so you have more influence, I don't care whether it's about global warming or what the issue is, there's some influence which is lacking otherwise, and uh people pay attention to what I say, if I talk about global warming and they wouldn't have before I had the Nobel prize. </s><s>[INST] Uh Yeah, this is very true, you're like the celebrities who talk uh celebrity has power, uh [/INST] Celebrity has power and that's that's a good thing, That's a good thing is singling out people, I mean on the other side of it singling out people has all kinds of, you know, whether it's for an Academy Awards or for this have unfairness and arbitrariness and so forth and so on. So, uh, you know, that's the other side of the coin, </s><s>[INST] as you said, especially with the huge experimental projects like this. You know, it's a large team and it does the nature of the Nobel prizes singles out a few individuals to represent the team. Nevertheless, it's a beautiful thing. Uh, what are ways to improve? Like go in the future increases sensitivity. I've seen a few ideas that are kind of fascinating is are you interested in them sort of looking, I'm not speaking about five years, Perhaps you could speak to the next five years, but also the next 100 years. [/INST] Yeah, So let me, let me talk to both the instrument and the science. Okay, so that's, they go hand in hand. I mean, the thing that I said is if we make it better, we see more kinds of weaker objects and we do astronomy. Okay, uh, we're very motivated to make a new instrument, which will be a big step. The next step like making a new kind of telescope person and the ideas of what that instrument should be having converged. Yet there's different ideas in europe. They've done more work to kind of uh, develop the ideas, but they are different from ours and we have ideas. So, but I think over the next few years will develop those. The idea is to make an instrument is at least 10 times better than what, we have, What we can do with this instrument 10 times better than that 10 times better means you can look 10 times further out, 10 times further out is 1000 times more volume. So you're seeing much, much more of the universe. The big change is that if you can see far out, you see further back in history, </s><s>[INST] you're traveling back in time. [/INST] Yeah. And so we can start to do what we call cosmology. Instead of astronomy or astrophysics, cosmology is really the study of the evolution of the </s><s>[INST] Oh, interesting. [/INST] And uh so then you can start to hope to get to the uh important problems having to do with uh how the universe began, how it evolved and so forth, which we really only study now with optical instruments are uh electromagnetic waves and early in the universe those were blocked because basically it wasn't transparent so the photons couldn't get out when everything was too dense. </s><s>[INST] What do you think? Sorry, on this tangent, what do you think? An understanding of gravitational waves from earlier in the universe can help us understand about the Big Bang and all [/INST] that kind of stuff. That's that's so </s><s>[INST] but but it's a non it's a it's a it's another perspective on the thing, is is there some insights you think it could be revealed just to help a layman understand. [/INST] Sure. First, we don't understand, we use the word Big bang, we don't understand the physics of what the Big bang itself was. Uh so I think um my my and in the early stage there were particles and there was a huge amount of gravity and mass being made. And so uh the big So I'll say two things. One is, How did it all start? How did it happen? And I'll give you at least one example that we don't understand what we should understand. We don't know why we're here. </s><s>[INST] Yes. No, we do not. [/INST] I don't mean it philosophically. I mean in terms of physics, okay, now what do I mean by that? If I go into my laboratory at cern or somewhere and I collide particles together, put energy together, I make as much anti matter as matter. Anti matter than annihilates matter and makes energy. So in the early universe there you made somehow somehow a lot of matter and anti matter. But there was an asymmetry. Somehow there was more matter and anti Matter the matter and anti matter annihilated each other at least that's what we think. And there was only matter left over and we live in a universe that we see this all matter. We don't have any idea, we have an ideas, but we don't have any, we don't have any way to understand that at the present time with the physics that we know, </s><s>[INST] You can ask a dumb question, Does anti matter have anything like a gravitational field to uh send signals. So, how how does this asymmetry of matter, anti matter could be investigated or further understood by observing gravitational fields or weirdness is and gravitational fields? [/INST] I I think that in principle, if there were, you know, um anti neutron stars, instead of just neutron stars, we would see uh different kind of signals. But it didn't get to that is we live in a universe that we've done enough looking because we don't see anti pro matter anti protons anywhere, no matter what we look at that, it's all made out of matter. There is no anti matter except we go in our laboratories. So, but when we go in our laboratories, we make as much anti matter as matter. So there's something about the early universe that made this asymmetry. So we can't even explain why we're here, that's what I meant. Physical physics, y it's not, you know, uh not in terms of how we evolved and all that kind of stuff. So </s><s>[INST] there might be inklings of uh of some of the physics that gravitational. [/INST] So, so gravitational waves don't get obstructed like light. So I said, light only goes to 300,000 years. So it goes back to the beginning. So, if you could study the early universe of gravitational waves, we can't do that yet, Then uh it took 400 years to be able to do that with optical, but uh then you can really understand the very, maybe understand the very early universe. So, in terms of uh questions like why we're here or what the big bang was, uh we should be, we can in principle study that with gravitational waves. So to keep moving in this direction, it's a unique kind of way to understand our universe. </s><s>[INST] Do you think there's more Nobel prize level ideas to be discovered in relation to, [/INST] I'd be shocked if there if there isn't uh not even going to that, which is a very long range problem, but I think that uh We only see with electromagnetic waves 4% of what's out there, uh there must be, we look for things that we knew should be there. Uh there should be uh um I would be shocked if there wasn't physics, objects, science and with gravity, that doesn't show up in everything we do with telescopes. So I think we're just limited by not having powerful enough instruments yet to do this. </s><s>[INST] Do you have a preference? I keep seeing this? Uh E lisa idea. Yeah. Is it do you have a preference for earthbound or space faring mechanisms for [/INST] their complementary It's a little bit it's completely analogous to what's been done in astronomy. So, astronomy from the time of Galileo was done with visible light? Yeah, The big advances in astronomy in the last 50 years or because we have instruments that look at the infrared microwave ultraviolet and so forth. So looking at different wavelengths has been important, basically going into space means that we look at instead of the audio ban, which we look at. As we said, on the air surface, we'll look at lower frequencies. So it's completely complimentary. And it starts to be looking at different frequencies. Just like we do with astronomy, </s><s>[INST] it seems almost incredible to me, engineering wise, just like on Earth to send something that's kilometers across into uh into space. It's harder to engineer [/INST] then. It actually is a little different. It's three satellites separated by hundreds of thousands of kilometers and they send a laser beam from one to the other. And uh if they the distance, if the triangle changes shape a little bit, they detect that from a graphic, did you </s><s>[INST] say? Hundreds of thousands of kilometers? Yeah, sending lasers to each other. Okay. [/INST] It's just </s><s>[INST] engineering. Um It's possible though. Uh [/INST] google. Okay. </s><s>[INST] Mhm. Uh That's that's just incredible. Because they have to maintain. I mean, the precision here is probably, there might be some more what is it? Maybe noises. A smaller problem. I guess there's no vibration to to worry about like seismic stuff. So, getting away from Earth, maybe you get away [/INST] from those parts are easier. They don't have to measure it is accurately at low frequencies, but they have uh a lot of tough engineering problems. The the in order to detect that the the gravitational waves affect things. The sensors have to be what we call free masses, just like ours are isolated from the earth. They have to isolate it from the satellite. And that's a hard problem. They have to do that pretty not as well as we have to do it but very well. And they've done a test mission and the engineering seems to be at least in principle in hand. This will be in the 2031, Yeah. </s><s>[INST] This is incredible. This is uh this is this is incredible. Uh Let me ask about bob black holes. Uh so what we're talking about is observing ah orbiting black holes. Uh I I saw the terminology of like binary black hole [/INST] systems is </s><s>[INST] that's that's when the when that's when they're dancing. [/INST] Okay, we're going around each other just like the Earth around the sun. </s><s>[INST] Okay. Is that weird that there's black holes going around each other? [/INST] So finding binary systems of stars is similar to finding binary systems of </s><s>[INST] black holes. [/INST] They were one stars. So, uh so we haven't said what a black hole is physically yet. So what's the black hole? So, black hole is first, it's a mathematical concept or physical concept and that is a region of space. So it's simply a region of space where the curvature of space time in the gravitational field is so strong that nothing get out including light and there's light gets spent in gravitational if the gravitation if the spacetime is warped enough. And so even like it's been around and stays in it. So that's the concept of a black hole. So it's not a and maybe you can make maybe it's a it's a concept that didn't say how they come about. And uh there could be different ways they come about, the ones that we are seeing. Uh there's a we're not sure that's what we're trying to learn now, is what they but the general expectation is that they come the black, these black holes happen when a star dies. So what does that mean? That the star dies? What happens? A star like our sun uh basically makes heat and light by fusion. It's made of and as it burns, it burns up the hydrogen and then the helium and then and slowly works its way up to the heavier and heavier elements that are in the star. And when it gets up to iron, the fusion process doesn't work anymore. And so the stars die and it happens to stars and then they do what's called a supernova. What happens then is that a star is a delicate balance between an outward pressure from fusion and light and burning and an inward pressure of gravity trying to pull the masses together once it burns itself out it goes and it collapses and that's a supernova. When it collapses all the mass that was there is in a very much smaller space. And if a star if you do the calculations, if a star is big enough that can create a strong enough gravitational field to make a black hole, our son won't. It's too smart, too smart and we don't know exactly what it, but it's usually thought that a star has to be at least three times as big as our son to make a black hole. But that's the physical way there. You can make black holes. That's the first uh explanation that one would give for the for what we see. But it's not necessarily true. We're not sure yet </s><s>[INST] what we see in terms of for the origins of black holes. [/INST] No, the black holes that we see in gravitational waves. </s><s>[INST] So the but you're also looking for the ones who are binary solar systems. [/INST] So they're binary systems, but they could have been made from binary stars. So there's binary stars around. So that's so that's the first explanation, is that that's what they are. Uh other explain. But but what we see has some puzzles. This is the kind of the way science works, I guess. Um We see heavier ones then up to her, We've seen one system that was 140 times the mass of our own son. Yeah. That's not believed to be possible with parent being a big star because big stars can only be so big or they are unstable. It's just the the fact that they live in an environment that makes them unstable. So the fact that we see bigger once, they may be come from something else. It's possible that they were uh made in a different way by little ones eating each other up or maybe they were made or maybe they came with a big bang the prime, what we call primordial, which means they're really different. They came from that, we don't know at this point if they came with a big bang, then maybe they account for what we call dark matter or some of it, </s><s>[INST] like there was a lot of them if they came with and because there's a lot of dark matter, but we'll gravitational always give you any kind of uh intuition about the origin of these, possibly [/INST] think that if we see the distributions enough of them, the distributions of their masses, the distributions of how they're spinning. So we can actually measure when they're going around each other whether they're spitting, you know, like this or </s><s>[INST] or oriented [/INST] whether the whole system has any wobbles. What? </s><s>[INST] So this is, this is now okay, [/INST] we're doing </s><s>[INST] that. And then you're constantly kind of crawling back and back [/INST] and we're crawling back in time and seeing how many there are as we go back. And so do they point back. </s><s>[INST] So you're like, what is that discipline called cartography or something? You're like mapping this the early universe via the lens of gravitational waves. [/INST] Not yet the early universe abilities back earlier. So uh so black holes are this mathematical phenomenon, But they come about in different ways. We have a huge black hole at the center of our galaxy and other Galaxies. Those probably were made some other way. We don't know when the Galaxies themselves had to do with the formation of Galaxies we we don't really know. So the fact that we use the word black hole, the origin of black holes might be quite different depending on how they happened. They just have to in the end, have a gravitational field that will bend everything in. </s><s>[INST] How do you feel about black holes as a human being? There's uh there's this thing that's nearly infinitely dense. Can doesn't let light escape. Isn't that kind of terrifying. Feels like the stuff of nightmares. [/INST] I think it's it's an opportunity </s><s>[INST] to do what Exactly. [/INST] So, uh like the early universe is an opportunity. If we can study the early universe, we can learn things like I told you. And here again, we have an embarrassing situation in physics. We have two wonderful theories of physics, one based on quantum mechanics, quantum field theory. And we can go to a big accelerator like at cern and smashing particles together and almost explain anything that happens beautifully using quantum field theory and quantum mechanics. Then we have another theory of physics called general relativity, which is what we've been talking about most of the time, which is fantastic at describing uh things that high velocities, long distances, you know, uh and so forth. So that's not the way it's supposed to be. Uh we're trying to create a theory of physics, not to theories of physics. So we have an embarrassment that we have two different theories of physics. People have tried to make a unified theory, what they call a unified theory. You've heard those words for decades. Uh They still haven't that's been primarily done theoretically or try the people actively do that. My personal belief is that like much of physics, we need some clues. So we need some experimental evidence. So where is there place if we go to cern into those experiments, gravitational waves or general relativity. Don't matter if we go to study you are black holes? Elementary particle physics doesn't matter. We're setting these huge objects. So where might we have a place where both phenomenon have to be satisfied an example of this black holes </s><s>[INST] inside black holes. [/INST] So we can't do that today. But when I think of black hole is a potential treasure chest of understanding the fundamental problems of physics and maybe can give us clues how we bring to the embarrassment of having two theories of physics together. Yeah, that's my own. What's </s><s>[INST] the worst that could happen. It's so enticing. Just go in and look, do you think um how far are we away from figuring out the unified uh theory of physics, a theory of everything. I think. What's your sense, who will solve it, Like what discipline will solve [/INST] it? Uh uh I think uh so little progress has been made uh without more experimental clues as I said that we're not we're just not able to say that we're close without some clues. The best closest popular theory these days. That might lead to that. It's called string theory. The problem with strength theory is it works uh It solves a lot of beautiful mathematical problems we have in physics and and uh it's very satisfying theoretically. But it has almost no predictive, Maybe no predictive ability because it is a theory that works in 11 dimensions. We live in a physical world of three space and one time dimension. In order to make predictions in our world with string theory, you have to somehow get rid of these other seven dimensions. That's done mathematically by saying they curl up on each other on scales that are too small to affect anything here. But how you do that. And that's okay. That's okay argument. But how you do that is not unique. So that means if I start with that theory and I go to our world here, I can't uniquely go to it which predictive, it's not predictive. And </s><s>[INST] that's that's actually [/INST] and that's a killer that's a killer. </s><s>[INST] And string theory is it seems like from my outsider's perspective has lost favor over the years perhaps because of this [/INST] very it's a lack of predictive power. I mean that science has to connect something where you make predictions is beautiful as it as it might be. So, I don't think we're close. I think we need some experimental clues that may be that information on something we don't understand presently at all, like dark energy or probably not dark matter, but dark energy or something might give us some ideas, but I don't think we're I can't envision right now uh in the short term meaning, you know, the horizon that we can see how we're gonna bring these two theories together. </s><s>[INST] A kind of uh two part question. Maybe just asking the same thing in two different ways. One question is, do you have hope that humans will colonize the the galaxy to expand out, become a multi planetary species? Another way of asking that from a gravitational and a propulsion perspective, do you think we'll come up with ways to travel close to the speed of light or maybe faster than the speed of light, which would make it a whole heck of a lot easier to expand out into the, into the universe? [/INST] Yeah, Well, I I think, you know, we're not that's a very futuristic. I think we're not that far from being able to Make a one way trip to Mars that's a that's been a question of uh whether people are willing to send somebody on a one way trip. </s><s>[INST] So I think they are. There's a lot of the explorers burned, right? [/INST] Yeah, yeah, </s><s>[INST] exactly. We're willing to die uh opportunity to explore new territory. [/INST] So uh you know this this recent landing on MArs is pretty impressive. They have a little helicopter can fly around. You can imagine, you can imagine in the not too distant future that you could have. I don't think civilisations colonizing, I can vision, but I can envision something more like the South Pole. We haven't colonized Antarctica because it's it's all ice and cold and so forth. But we have uh stations. So we have a station that self sustaining at the South Pole that I've been there. It has really. Yeah. </s><s>[INST] What's that like? Uh because that that there's parallels there [/INST] to go to MArs. It's fantastic. </s><s>[INST] What's the journey like? [/INST] The journey involves going uh the South Pole station is run in the US by by the National Science Foundation. I went because I was on the National Science Board that runs the National Science Foundation. And so you get a VIP trip if you're healthy enough to the South Pole to see it, which I took you fly from the US to Australia to uh Christchurch in Australia's southern Australia. And uh from there you fly to McMurdo station which is on the coast and it's the station with about 1000 people right on the coast of Antarctica. Uh it's about uh seven or eight hour flight and they can't predict the weather. So when when I flew from Christchurch to make Myrdal station, they tell you in advance he's doing in the military aircraft they tell you in advance that they can't predict whether they can land because they have to land on uh reassure. Yeah. And so about halfway the pilot got on and said uh sorry this is uh they call it a boomerang flight you know boomerang goes out and go spend. So we had to stay a little while in Christchurch but then we eventually went to make Myrdal station and then flew to the South Pole. The south pole itself Is uh when I was there was -51°. That was summer. Uh huh. It uh zero humidity. And uh and it's about 11,000ft altitude Because it's never warm enough for anything to melt. So it doesn't snow very much but it's about 11,000 ft of snow pack. So you land in a place that's high altitude um cole this could be and dry and incredibly dry. Which means you have a physical adjustment. Uh The place itself is uh it's fantastic. They have this great station there. They do astronomy at the South Pole. </s><s>[INST] Nature wise is a beautiful what's uh what's the experience like? Or is it like visiting any town? [/INST] No it's very small. There's only uh less than 100 people there even when I was there. Yes There were about 50 or 60 there. And in the winter there's less half of that their winner, </s><s>[INST] it's real cold [/INST] it gets really cold. Yeah. And but but it's it's a station I I think and that's I mean we haven't gone beyond that. Uh on the coast of Antarctica. They have greenhouses and their self sustaining in McMurdo station, but we haven't really settled more than that kind of thing in Antarctica, which is a big uh huh. A country or you know, uh big part of big piece of land. So I don't, I can't envision kind of colonizing at people living so much as much as I can see uh the equivalent of the South Pole station. </s><s>[INST] Well in the computing world, there's an idea of uh, you know, backing up your data and then you want to do offsite backup. Uh you know, to make sure that if the whole thing burnt, if your whole house burns down that you could have a backup off site of the data. I think the difference in Antarctica and uh and MArs is mars is an offsite backup that if we have nuclear war or whatever the heck might happen here on earth, it would be nice to have a backup elsewhere. And be nice to have a large enough colony where we sent variety of people except like uh a few silly astronauts in suits, you know, have an actual vibrant um get a few, get a few musicians and artists up there. Get a few maybe like one or two computer scientists, those are essential, maybe even a physicist. [/INST] So it's not sure, maybe not. So that comes back to something you talked about earlier, which is for me the paradox families paradox because you talked about having to escape. But and so the missing 11 number, you don't know how to use in families calculation or drake who's done it better is how long do civilizations last before they are we, you know, we've barely gotten to where we can communicate with electricity and magnetism and maybe we'll wipe ourselves out pretty soon. So </s><s>[INST] are you hopeful in general? Like you think we got another couple 100 years at least? [/INST] Are you worried? Well, no, I'm I'm hopeful, but I don't know if I'm hopeful in the long term. You know, if you say, you know, uh huh Yeah. Are we able to go for another couple of 1000 years? I'm not sure. I think we have where we started the fact that we can do things that don't allow us to kind of keep going or there can be whether it ends up being a virus that we create or ends up being the equivalent of nuclear war or something else. It's not clear that we can control things well enough. </s><s>[INST] So speaking of really cold conditions and uh not being hopeful and eventual suffering and destruction of the human species. Let me ask you about Russian literature, You mentioned uh, how's that for a transition? I'm doing my best here. You you mentioned that used to love literature when you're younger and you were even uh we're hoping to be um a writer yourself. That was the motivation and some of the books I've seen that you listed um, that were inspiring to you was was from Russian literature, like uh, I think Tolstoy dostoyevsky, soldier Nansen. [/INST] Yeah. </s><s>[INST] Um, maybe in general, you can speak to your fascination with Russian literature or general. Well, you picked up from [/INST] those, I'm not surprised you picked up on the Russian literature your background, but uh, when, when I, when you should be </s><s>[INST] surprised that didn't make the entire conversation about this. That's that's the real surprise [/INST] when when uh I didn't really become a physicist or want to go in science until I started college. So when I was younger I was good at math, that kind of stuff. But I didn't really, I came from a family, didn't know what he went to college and I didn't have any mentors. So, but I'd like to read when I was really young. And so when I was very young, I read, I always carried around a pocket book and read it And uh my mother read these mystery stories and I got bored by those eventually. And then I discovered real literature. I don't know at what age about 12 or 13. And so then I started reading a good literature and there's nothing better than Russian literature of course in reading reading good literature. So I uh read quite a bit of Russian literature at that time. Uh and uh so you asked me about the, well, I don't know, I say a few words dostoevsky. So what about dostoevsky? For me? Um, dostoevsky was important into I mean, I've read a lot of literature because it's kind of the other thing I do with my life. And He made two incredible in addition to his own literature, he influenced literature tremendously by having uh, I don't know how to pronounce polyphony. So, he's the first real serious author that had multiple narrators. And that's a he absolutely is the first. And he also was the first um he began existential literature. So, uh, the most important book that I've read in the last year when I've been forced to be isolated was existential literature. It was I decided to reread uh, moose the plague. </s><s>[INST] Oh, yeah, that's a great book. [/INST] It's a great book. And it's right now to read it, it's </s><s>[INST] this book is about love, actually, love for his humanity. [/INST] It is. But it has all the money. It has all like, you should if you haven't read it in recent years, I had read it before, of course. But to read it during this because it's about a plague. So, it's really fantastic to be done. But that reminds me of, you know, he was a great existentialist, but the beginning of existential literature with </s><s>[INST] dostoevsky. [/INST] So, in addition to his own, you know, great novels, he had a tremendous impact on on uh on literature. </s><s>[INST] And there's also for dostoevsky, unlike most of their existentialists, he was at least in part religious, I mean, their religion geocities permeated his idea. I mean, one of my favorite books of his is The Idiot and he's which is a christ like figure in there. [/INST] Well, there's Prince Myshkin is that michigan? Yeah, Michigan. That's </s><s>[INST] one thing about you write in english, I presume. Yeah, yeah. So that's the names, that's what gets a lot of people is there's so many names hard to pronounce it to remember all of them. It's like uh you have the same problem, [/INST] but he was a great character so that I </s><s>[INST] kind of uh have a connection with him. Because I often then then the title of the book, you're the idiot is I kind of I often call myself an idiot because that's how I feel, I feel so naive about this world. And I I'm not sure, I'm not sure why that is, maybe it's genetic or so on. But um I have a connection, the spiritual connection to that character to michigan to michigan. Yeah, you're just but [/INST] he was far from his, you </s><s>[INST] know, in some sense, in some sense, but in another sense, maybe not of this in [/INST] another sense, he was Yeah, I mean, but it was a bumbler bunk, </s><s>[INST] but you also mentioned Soldier Nixon very interesting did [/INST] uh and and he always confused me. Of course he was really uh really important and uh mhm. Writing about Stalin and first getting in trouble and then he later he is he wrote about Stalin in a way, I forget what it was, what the book was in a way that was very critical of London. </s><s>[INST] Uh Yeah, he he's evolved through the years and he actually showed support for Putin eventually is a very interesting transition. He took no journey he took through thinking about Russia and the soviet union, but I think what I get from him is basic uh it's like Viktor frankl has this man's search for meaning. I have a similar kind of sense of um of the cruelty of human nature, cruelty of indifference, but also the ability to find happiness in the small joys of life. That that's something there's nothing like a prison camp that makes you realize you could still be happy with a very, very little [/INST] Yeah, he was his description of kind of how to make a how to go through a day and actually enjoy it in a prison campus. Pretty amazing. Yeah, and some prison camp, I mean, it's the worst of the worst of the worst </s><s>[INST] and also just uh you know, you do think about the role of authoritarian states and in, you know, like hopeful idealistic systems somehow leading to the suffering of millions and I, you know, this might be arguable, but I think a lot of people believe that Stalin, I think genuinely believed that he's doing good for the world and uh he wasn't, it's a very valuable lesson that um even evil people, I think they're doing good, otherwise, it's too difficult to do the evil. The best way to do evil is to believe framing in a way like you're doing good, and this is this is a very clear picture of that, which is the gulags, the soul genius is one of the best people to reveal that [/INST] the most recent thing I read, it isn't actually fiction was the woman, I can't remember her name, who got the Nobel prize about Within the last five years. I don't know whether she's Ukrainian or Russian, but there interviews, have you read that </s><s>[INST] interview of Ukrainian survivors of? [/INST] Well, I think she may be originally Ukrainian, uh the books written in Russia and then translated in english, and many of the interviews are in Moscow and places, but she won the Nobel prize within the last five years or so. But what's interesting is that these are people of all different ages, all different uh occupations and so forth, and they're reflecting on the their reaction to basically the present soviet system, the system they live with before. There's a lot of uh looking back by a lot of them with uh well uh it being much better before. </s><s>[INST] Yeah, I don't know what uh in America, we think we know the right answer what it means to be um to build a better world? I'm not so sure, I think we're all just trying to figure it out. [/INST] Yeah there's doing our best I think you're right. </s><s>[INST] Is there advice you can give to young people today besides reading Russian literature too young age um about how to find their way in life, how to find success in Korea or just life in general. [/INST] Uh huh I just my own belief it may not be very deep, but I believe it, I think you should follow your dreams and you should have dreams and follow your dreams if you can to the extent that you can and uh we spend a lot of our time doing something with ourselves in my case physics, in your case, I don't know whatever it is, machine learning and this uh huh uh we should we should have fun. </s><s>[INST] What was your dream follow your dreams? What what dream did you have? Because [/INST] well well originally I was </s><s>[INST] because you didn't follow your dream. [/INST] Well that's changed along the way I was going to be but I changed what happened, that was what happened, Oh I decided to take the most serious literature course in my high school, which was a mistake, I'd probably be a second rate writer now and uh </s><s>[INST] could be a Nobel prize winning writer [/INST] and uh the the book that we read, even though I had read Russia Russian novels, I was 15, I think uh cured me from being a novelist </s><s>[INST] destroyed your dream. Yes, cured you. Okay, what was the book, Moby Dick? Okay, [/INST] so why Moby Dick? So I have read it since and it's a great novel, maybe it's as good as the Russian </s><s>[INST] now, I've never made it through, I I lost, it was too big, it's too long. [/INST] Okay, your words are going to mesh with what I say, excellent, and you may have the same problem at older, </s><s>[INST] that's why I'm not a [/INST] writer, it may be. So the problem is Moby Dick is what I remember was there was a chapter that was maybe 100 pages long, all describing this, why there was Ahab and the white whale and it was the battle between ahab with this wooden peg leg and the white whale. And there was a chapter, there was 100 pages long in my memory, I don't know how long it really was uh that described in detail though, great white whale and what he was doing and what his fins were like and this and that, and it was so incredibly boring, the word used then I thought if this is great literature, screw it. Okay, now, why did I have a problem? I know now in reflection, because I still read a lot and I read that novel uh you know, after I was 30 or 40 years old. And the problem is simple, I diagnosed what the problem was I that novel in contrast to the Russian novels, which are very realistic and point of view Is one huge metaphor. </s><s>[INST] Oh yeah, [/INST] At 15 years old, I probably didn't know the word and I certainly didn't know the meaning of metaphor. </s><s>[INST] Like what do I care about a fish? Why are you telling me all about this? [/INST] Exactly. As one big metaphor? So, reading it later as a metaphor, I could really enjoy it. But the teacher gave me the wrong book or maybe it was the right book because I went into physics and so uh huh But it was it was truly I think I may oversimplify, but it was really that I was too young to read that book because not too young to read the Russian novels interestingly, but too young to read that because I I probably didn't even know the word and I certainly didn't understand it as a metaphor. </s><s>[INST] Well, in terms of fish, I recommend people read Old Man to see much shorter, much better. It's still metaphor though. So, but you can read it just as a story about a guy catching a fish and it's still fun to read. Uh I had the same experience as you, not with Moby Dick, but later in college I took a course on James Joyce don't ask me why as major in computer science. That took a course on James Joyce. And I was kept being told that he is Widged considered by many considered to be the greatest literary writer of the 20th century. And I kept reading like I think so. His short stories The Dead, I think it's called was very good. Well, I'm not very good, but pretty good. And then you will see is very good. It is very good. Only The Dead, the final story still rings with me today. But then ulysses was I got through ulysses with the help of some Cliff notes and so on, but uh and so added ulysses and Finnegans wake the moment I started fitting his wake, I said this, this is stupid, this is that's when I went full into like um I don't know, that's why I went full Kafka Bukowski like people who just talk about the darkness of the human condition in the fewest words possible and without any of the music of language. Um so it was a turning point uh as well, I wonder, I wonder when is the right time to do the to appreciate the beauty of language. Like even Shakespeare, I was very much off put by Shakespeare in high school and only later started to appreciate its value in the same way. Let me ask you a ridiculous question. [/INST] Okay, </s><s>[INST] uh huh um I mean because you've read Russian literature, Let me ask this one last question. Ah I might be lying, there might be a couple more, but what do you think is the meaning of this whole thing. You're you've got a nobel prize for looking out into the, trying to reach back into the beginning of the universe, listening to the gravitational ways. Uh but that still doesn't answer the why? Why are we here beyond just the matter and antimatter? The philosophical question, [/INST] the phillips philosophical question about the meaning of life I'm probably not really good at. Um I think that uh the individual meaning uh I would say it rather simplistically is whether you've made a difference, positive difference I'd say for anything besides yourself. Uh huh meaning you could have been important to other people or you could have discovered gravitational waves that matters to other people or something, but something beyond just existing on the earth as an individual. So your life has meaning if you have affected um either knowledge or people or something beyond yourself. Yeah, that's a simplistic statement, but it's about as good as I have. </s><s>[INST] That's that maybe and all of its simplicity, it may be very true. Do you think about uh does it make you sad that this right ends? Do you think about your mortality? [/INST] Yeah. </s><s>[INST] Are you afraid of it? [/INST] Not exactly afraid of it, but saddened by it And uh uh you know, I'm old enough to know that I've lived most of my life and uh huh I enjoy being alive. I can imagine being sick and not wanting to be alive, but I'm not so uh I'm </s><s>[INST] not a good road. [/INST] I'm not and I'm not happy to see it come to a man I'd like to see it prolong but uh I don't I don't fear the dying itself or that kind of thing. It's more I'd like to prolong uh what is I think a good life that I'm living and still living. </s><s>[INST] It's kind of it's sad to think that the finance of it is the thing that makes it special. Uh and also said to um to me at least it's kind of I don't think I'm using too strong of award, but it's kind of terrifying. The uncertainty of it. The mystery of it. You know, the [/INST] mystery of death, </s><s>[INST] the mystery of it. You have death when we're talking about the mystery of black holes that somehow distant that somehow out there and the mystery of our own. [/INST] But but but even life, the mystery of consciousness, I find so hard to deal with too. I mean, it's not as painful. I mean, we're conscious but the whole magic of life. We can understand what consciousness where we can actually think so forth. It's pretty </s><s>[INST] it's such, it seems like such a beautiful gift that it really sucks that would get to let go of it. We'll have to let go of it. What do you hope your legacy is as I'm sure they will aliens when they visited humans have destroyed all of human civilization, Aliens read about you in an encyclopedia that would leave behind. What [/INST] do you hope it says? Well, I would I would hope they if to the extent that they evacuated me uh felt that I helped move science forward as a tangible contribution and that I served as a good role model for how humans should live their lives. </s><s>[INST] And we're part of creating one of the most incredible things humans have ever created. So yes, there is the science. That's the fermi thing. Right? Uh [/INST] The instrument </s><s>[INST] and the instrument. The instrument is a magical creation, not just by a human by a collection of humans. The collaboration is uh That's yes, that's humanity at his best. I do hope I do hope we last quite a bit longer. But if we don't. Mhm this is a good thing to remember humans by at least they built that thing. It's pretty impressive. Barry this is an amazing conversation. Thank you so much for wasting your time in explaining so many things. So well, I appreciate your time today. [/INST] Thank you. </s><s>[INST] Thanks for listening to this conversation with barry Barish. To support this podcast. Please check out our sponsors in the description And now let me leave you some words from Warner Heisenberg, a theoretical physicist and one of the key pioneers of quantum mechanics. Not only is the universe stranger than we think it is stranger that we can think. Thank you for listening and hope to see you next time. Mhm. [/INST] </s>

<s>[INST] it. Uh What about experimental validation? Is that is that a fair standard to hold before a theory of everything that's trying to unify quantum mechanics and gravity? [/INST] Yeah, I mean ultimately to be really convinced that you know that that on some new idea that invocation really works, you need some kind of uh you need to look at the real world and see that this is telling you something something true about it. I mean either either. Mhm telling you that if you do some experiment and go out and do it, you'll get some unexpected results and that's the kind of gold standard or it may be just that like all those numbers that are, we don't know how to explain it will show you how to calculate them. I mean, it can be various kinds of experimental validation but that certainly ideally what you're looking for. </s><s>[INST] How tough is this, do you think for a theory of everything, not just string theory for something that unifies gravity and quantum mechanics. So the very big and very small is this? Uh Let me ask it one way, is is it a physics problem? A math problem or an engineering problem? [/INST] My guess is it's a combination of a physics and a math problem that you really need. It's not really enjoying it. It's not like there's some kind of well defined thing you can write down and we just don't have enough computer power to do the calculation. That's not the kind of problem it is at all. Um But the question is, you know what mathematical tools you need to properly formulate the problem? It is unclear. So one reasonable conjecture is the way the reason that we haven't having a success yet is just that we're missing either we're missing certain physical ideas or were missing certain mathematical tools which or some combination of them, which would which we need to kind of properly formulate the problem and see and see that it has a solution that looks like the real world. </s><s>[INST] But does she need uh I guess you don't but there's a sense that uh you need both gravity, like all the laws of physics to be operating on the same level. So it feels like you need an object like a black hole or something like that. Um In order to make predictions about otherwise, you're always making predictions about this joint phenomena or can you do that as long as the theory is consistent and doesn't have special cases for each other from [/INST] your your theory. You should I mean if your theory is going to include gravity, our current understanding of gravity is that you should have, there should be a black hole states and you should be able to describe black holes in this theory. And and just one aspect that people that concentrate a lot on is just this kind of questions about if your theory includes black holes like it's supposed to and it includes quantum mechanics, then there's certain kind of paradoxes which come up and so that's that's been a huge focus of kind of quantum gravity work, work has been not just those paradoxes, but </s><s>[INST] so stepping outside of string theory, can you just say first at a high level, what is the theory of everything? What does the theory of everything seek to accomplish? [/INST] Well, I mean this is very much a kind of reductionist point of view in the sense that so it's not a theory, this is not going to explain. Do you know anything, it doesn't really this kind of theory theory, this kind of theory of everything we're talking about doesn't say anything interesting particularly about like macroscopic objects about what the weather is going to be tomorrow or you know, things are happening at this scale, but just what we've discovered is that as you look at the universe that kind of, you know, if you kind of start break, you can start breaking it apart into and you end up with some fairly simple pieces Quanta if you like, and which are doing, which are interacting in some in some fairly simple way and it's some it's got that. So what we mean by the theory of everything is a theory that describes all, oh, all the all the correct objects, you need to describe what's happening in the world and describes how they're interacting with each other at the most fundamental level. How you get from that theory to describing some macroscopic, incredibly complicated thing, is there that becomes again more of an engineering problem and may need machine learning or you made, you know, a lot of very different things to do </s>

<s>[INST] There's a certain kind of magic. You're right with the consciousness being an observer when you play guitar for example, or piano for me, music when you get truly lost in it. I don't know what the heck is responsible for the flow of the music. That kind of the loudness of the music going up and down the timing, the intricate, like even the mistakes, all those things that doesn't seem to be the conscious mind. Uh, it's, it is just observing and yet it's somehow intricately involved more like because you mentioned park or dances like that too when you start up in tango dancing, if when you truly lose yourself in it, then it's just like you're an observer and how the hell is the body able to do that? And not only that, it's the physical motion is also creating the emotion, the like that dam was good to be alive feeling. So, but then that's also intricately connected to the full biology stack that we're operating in. I don't know how difficult it is to replicate that we were talking off line about boston dynamics robots. Um, they have recently been, they did both Park or it did flips. They've also done some dancing and something I think a lot about because what most people don't realize because they don't look deep enough as those robots are hard coded to do those things. The robots didn't figure it out by themselves. And yet the fundamental aspect of what it means to be human is that process of figuring out of making mistakes. And then there's something about overcoming those challenges and the mistakes and like figuring out how to lose yourself in the magic of the dancing or just movement is what it means to be human. That learning process. So that's what I want to do with the with uh almost as a fun side thing with the boston dynamics robots is to have them learn and see what they figure out. Even if even if they make mistakes, I want to let spot make mistakes. And in so doing discover what it means to be alive, discover beauty because I think that's the essential aspect of mistakes, boston dynamics folks want spot to be perfect because they don't want spots ever make mistakes because it wants to operate in the factories, it wants to be you know, very safe and so on. For me, if you construct the environment, if you construct a safe space for robots and allow them to make mistakes, something beautiful might be discovered. But that requires a lot of brainpower. So Spot is currently very dumb and I'm going to give it a brain. Uh so first make it c currently can't see meaning computer vision has to understand its environment is to see all the humans. But then also has to be able to learn learn about its movement, learn how to use his body to communicate with others, all those kinds of things that dogs know how to do well, humans know how to do somewhat well. Um I think that's a beautiful challenge. But first you have to allow the robot to make mistakes. [/INST] Well, I think your objective is laudable, but you're going to realize that the boston dynamics folks are right the first time spot poops on your rug. I </s><s>[INST] hear the same thing about kids and so on, but I still [/INST] want to have kids. No, you should. It's it's a great experience. Um so let me step back into what you said in a couple of different places. One I've always believed that the missing element in robotics and artificial intelligence is a proper development, right? It is no accident. It is no mere coincidence that human beings are the most dominant species on planet earth and that we have the longest childhoods of any creature on earth by far right. The development is the key to the flexibility. And so uh the capability of a human at adulthood is the mirror image. It's the flip side of our helplessness at birth. Um so I'll be very interested to see what happens in your robot project if you do not end up reinventing childhood for robots, which of course is foreshadowed in 2001 quite brilliantly. Um, but I also want to point out you can you can see this issue of your conscious mind becoming a spectator very well, if you compare tennis to table tennis right? If you walked a tennis game, you could imagine that the players are highly conscious as they play. You cannot imagine that if you've ever played ping pong decently, a volume, ping pong is so fast that your conscious mind, if it had, if your reactions had to go through your conscious mind, you wouldn't be able to play. So you can detect that your conscious mind while very much present isn't there. And you can also detect where consciousness does usefully intrude. If you go up against an opponent in table tennis that knows a trick that you don't know how to respond to. You will suddenly detect that something about your game is not effective and you will start thinking about what might be, how do you position yourself? So that move that puts the ball just in that corner of the table or something like that doesn't catch you off guard. And this I believe is we highly conscious folks, those of us who try to think through things very deliberately and carefully mistake consciousness for like the highest kind of thinking. And I really think that this is an error. Consciousness is an intermediate level of thinking. What it does is it allows you, it's basically like un compiled code and it doesn't run very fast, it is capable of being adapted to new circumstances, but once the code is roughed in, right, it gets driven into the unconscious layer and you become highly effective at whatever it is and that from that point, your conscious mind basically remains there to detect things that aren't anticipated by the code you've already written. And so I don't exactly know how one would establish this, how one would demonstrate it, but it must be the case that the human mind contains sandboxes in which things are tested, right? Maybe you can build a piece of code and run it in parallel next to your active code, so you can see how it would have done comparatively. Um, but there's gotta be some way of writing new code and then swapping it in and frankly I think this has a lot to do with things like sleep cycles very often, you know, when I get good at something, I often don't get better at it while I'm doing it, I get better at it when I'm not doing it, especially if there's time to sleep and think on it. So there's some sort of, you know, new program swapping in for old program phenomenon, which um, you know, we'll be a lot easier to see in machines. It's going to be hard with the wetware, </s>

<s>[INST] lots of fiber, [/INST] get lots of fiber, be nice to everybody. And uh yeah, don't take things too seriously. It's a good, it's a good one. Our minds are fucking big weird big it's a big weird shitty fucking bucket of shit that's trying to get you to think horrible shit about yourself all </s><s>[INST] the time. Shitty bucket of ship. [/INST] It </s><s>[INST] is a book I never read but I read the title and it's good Words to live by which is uh don't sweat the small stuff and it's all small stuff. That's another way [/INST] that dr Phil wasn't dr Phil. I </s><s>[INST] don't know. But I think the conclusion is also has fiber as part of it. I think that all ties it together and in the end of course just put love out there in the world. I think that's a pretty good way. [/INST] What would you say is the meaning of life? I </s><s>[INST] would say love. Yeah. Yeah. It's a it's a long conversation on what that really means. But I'm sure robots are involved. Yeah. [/INST] Well let me tell you, I feel a little safer knowing that someone who has a hand in bringing these robots to the masses as you do has that opinion of of love and how important it is. I think that's great because otherwise it's going to be that fucking scene from T. Two where uh linda Hamilton's holding onto the fence and getting all of her flesh blown off of her skeleton before the rest of her is is wiped away because the skynet shit. Anyway. I'm just terrified of dudes all the time. That's why I think that they will </s><s>[INST] dudes in the wrong hands can do a lot of damage. [/INST] That's why chad and I need to do our best to control </s><s>[INST] it. Need to travel back in time and murder chad [/INST] I </s><s>[INST] think. [/INST] Yeah, that's yeah, </s><s>[INST] that's the only way [/INST] it's been said. I </s><s>[INST] don't know why I need to travel back in time but it just [/INST] uh today but I'm </s><s>[INST] very suspicious. [/INST] My nefarious plans for chad involve going back to tomorrow and planning for yesterday and then and hopefully do Dzi will give me the answer there with what, what it is to do with chad's frozen body. If I got to drive it out too. If I got to take my, you know, if I got to get, get a hold of it like one of those Tesla Mom vans and shove my garage freezer in it and plug it in and shove chad in there and drive out to Arizona and deliver him under a mountain or wherever the fun this place is. And so here's this dog tag. What does this get me Like? That's going to be 300 bucks. Do you have, Do you take Amex? No. And I'd be like sh </s><s>[INST] it [/INST] and I'll just dump </s><s>[INST] them somewhere. Breaking [/INST] bad stuff. </s><s>[INST] Well I would like to thank you and the, what is it? The Canadian international agency apparel [/INST] for. I </s><s>[INST] can't wait for the sneakers from dudes. I can't wait for all the, all the podcasts. Uh that Ai can and all the trouble I can get you in. So I'm a huge fan of yours. It's a huge honor that you would talk with me today. Well this has been amazing, [/INST] cheers pal likewise and I'm happy to be here. Man, cheers Holy! What? </s><s>[INST] Thanks for listening to this conversation with Will Sasso to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from john Candy, one of Will's favorite actors. I think I may have become an actor to hide from myself. You can escape into a character. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] Well, I if I could just return to the question of deaths. He said that the data is imperfect because we need these kind of cereal prevalence surveys to understand how many cases there were to determine the rate of deaths. And we need to have a strong footing in the number of deaths. But if we assume that the the the number of deaths is approximately correct. Like what's your sense? What kind of statements can we say about the deadliness of covid against across different demographics? Maybe not in a political way or in the current way, but when history looks back at this moment of time, 50 years from now. 100 years from now, the way we look at the pandemic 100 years ago what will they say about the deadliness of Covid? [/INST] I think the deadliness of Covid depends on not just the virus itself but who it infects. Um So the probably the most important thing about it about the deadliness of covid is is this steep age gradient in the mortality rate. Um So according to these zero prevalence studies that that that that have been done now hundreds of them Um mostly from before vaccination, vaccination also reduces the mortality risk of COVID. Um the serial problem studies suggest that the risk of of death, if you say over the age of 70 is very high, you know, 5%. If you get covid, if you're if you're under the age of 70 it's lower point oh five but there's not a single sharp cut off. It's more like I have a rule of thumb that I use. Um So if you're 50 say the infection fatality rate from covid is 500.2%. According to the serial prevalence data, That means 99.8% survival If you're 50. And for every seven years of age above that double it. Every seven years of age below that habit. So a 57 year old have a .4 Mortality, year old would have a .8% and so on. And if you have a severe chronic disease like diabetes or if you're morbidly morbidly obese, it's like adding 77 years to your life. </s><s>[INST] And this is uh for unvaccinated [/INST] folks, this is unvaccinated in the before delta also. </s><s>[INST] Are there a lot of people that would be listening to this with ph D. S at the end of their name that would disagree with the 99.8 would you say [/INST] so? I think there's some disagreement over this and the disagreement is about the quality of the serial prevalence studies that were conducted. Uh So as I said earlier I was a senior investigator in three different problem studies. And very early in the epidemic. I view them as very high quality studies. Um We we um in santa Clara County. What we did is we used a test kit Uh to that we obtained from someone who works in Major League Baseball actually. He ordered these test kits very early in March 2020 that measures very accurately measures antibody levels or antibodies in the in in the bloodstream. Uh These test kits were eventually were approved by the the had an E. U. A. By the emergency use authorization by the FDA. Sort of shortly after we did this. And uh it had a very low false positive rate false positive means if you if you uh if you don't have these covid antibodies in your bloodstream, the kid shows up positive anyways that That turns out to happen about .5% of the time. Um and based on studies, a very large number of studies looking at blood from 2018 you try it against this kit And you know .5% of the time. 2018 there shouldn't be anybody's there. So to COVID. So if it turns positive as a false positive .5% of the time. Um and then, you know like a false negative rate about 10%, something like that. I don't remember the exact number, but the false positive rate is an important thing there. Right? So you have a population in March 2020 or April 2020 with very low fraction of patients having been exposed to covid. You don't know how much but low, even a small false positive rate could end up biasing this study quite a bit, but there's a formula to adjust for that. You can adjust for the four false positive false negative rate. We did, we did that adjustment And those studies found in a community population. So leaving aside people in nursing homes who have a higher death rate from covid. Um the that the death rate was .2% in Santa Clara County and in L. A. County </s><s>[INST] across all age groups in the community community meeting. Just like regular. [/INST] So like that that's actually really important question to. So the santa clara study, we did this facebook sampling scheme um which is, I mean not not the ideal thing, but it's like it was very difficult to get a random sample. And and during the, you know, during lockdown um where we put out an ad on facebook soliciting people to volunteer for the study randomly selected set of people? We were hoping to get a random selection. People from santa Clara County, but it tended to the people who tend to volunteer were from the richer parts of the county. Like I had stanford professors writing begging to be in the study because they wanted another antibody levels. So we did some adjustment for that in L. A. County. We hired a firm that had a preexisting representative sample of L. A. County. Um, so, but it didn't include nursing homes. It didn't include people in jail. Things like that didn't include the homeless populations. So it's it's representative of a community dwelling population, both of those. And there we found that both in L. A. County and Santa Clara County in April 2020, something like 40 to 50 times more infections than cases in both places. So for every case that had been reported to the public health authorities, we found that, you know, you know, 40 or 50 other infections, people with anti antibodies in their blood that suggested that they had had covid and recovered. </s>

<s>[INST] to add to the list and before, you know, it time is up, just like it is for this conversation, but hopefully it was a fun ride was a huge honor demetrius as you know, I've been a, a fan of yours and a fan of google self driving car and way more for a long time. I can't wait. I mean, it's one of the most exciting if we look back in the 21st century, I truly believe it will be one of the most exciting things we descendants of apes have created on this earth. So I'm a huge fan and I can't wait to see what you do next. Thanks so much for talking to me. [/INST] Thanks thanks for having me. </s><s>[INST] And it's a [/INST] also a huge fan doesn't work honestly like and really enjoyed it. Thank you. </s><s>[INST] Thanks for listening to this conversation. Dmitri Dolgov and thank you to our sponsors trial Labs, a company that helps businesses apply machine learning to solve real world problems. Bling kissed an app I use for reading through summaries of books, better help online therapy with a licensed professional and cash up the app. I used to send money to friends. Please check out these sponsors in the description to get a discount and to support this podcast. If you enjoyed this thing, subscribe on Youtube. Review five stars on Apple podcast, follow on Spotify, support on Patreon, connect with me on twitter at lex Friedman and now let me leave you with some words from Isaac Asimov Science can amuse and fascinate us all, but it is engineering that changes the world. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] What's the difference between more in surplus is there a nuanced? [/INST] Yeah because surplus has a notion of its discretionary. It's sort of extra he's not taking a he's not making a judgment that it's </s><s>[INST] it's a simple math equation. [/INST] Yes, very simple. Yes, X minus </s><s>[INST] x X. [/INST] Is the total output? Why is the consumption by the producer? Therefore X minus Y equals s the surplus Exactly, exact. Now, Marx argues the question the minute you understand this, you will ask the following question. Who gets the surplus? Who gets this extra stuff that is made but not consumed by those who made it? And Marx's answer, is there in lies, one of the great shapers of any society. How is that organized? For example, who gets it? What are they asked if anything to do with it in exchange for getting it? What's their social role, for example, here we go now, if you get this and you get the core of it anyway, um and I don't charge much. Um the workers themselves could get that's right uh the workers themselves could get it. That's the closest Marx comes to a definition of communism, communism would would be if the workers who produce the surplus together, decide what to do with it. </s><s>[INST] So this has to do, not just with who gets it, but more importantly, who gets to decide who gets it? [/INST] Well, who gets it and who gets to decide what to do with it, because you can't decide it. If you don't have disposition over it. So the this the logic of the word sequence, it's produced, its marks uses the word appropriated, in other words whose property, who who gets to decide if you like, what happens. All that property ever meant is who gets to decide and who's excluded. </s><s>[INST] That's a clean definition of communism [/INST] and that's it. By the way, it's not just clean the only one. So </s><s>[INST] what's can we just linger on the definition of exploitation in that context? [/INST] Easy becomes very easy to exploitation exists if and when the surplus that's produced is taken and distributed by people other than those who produced it, slaves produce a surplus, which the master gets serfs produce a surplus, which the lord gets employees produce a surplus which the employer gets. It's very simple. These are exploitative class structures because one class produces a surplus appropriated distributed by another group of people will not the ones who produced it, which creates hostility, enmity, envy, anger, resentment and all of the problems you can lump under the heading class struggle. I use a metaphor, simple metaphorical story. You have two Children, let's assume. And you take them to Central Park a few blocks from here. It's a nice day and the Children are playing and incomes of one of those men with an ice cream truck comes by tingling, lingling your Children. See the ice cream daddy get me an ice cream. So you walk over, you take some money and you get two ice cream cones and you give them to one of the Children. The other one begins to scream and yell and how obviously what's the issue? And you realize you've just made a terrible mistake. So you order the one you gave the two ice cream cones to give one of those to your sister or your brother or whatever it is. And that that's how you solve the problem until a psychologist comes along and says you know, you didn't fix it by what you just did. You should never have done that in the first place. My response. So you understand all of the efforts to deal with inequality in economic political culture. These are all giving the ice cream cone back to the kid. You should, you should never do this in the first place. </s><s>[INST] The Reallocation of resources creates bitterness and look [/INST] at this country is tearing itself apart now in a way that I have never seen in my life. And I've lived here all my life and I've worked here all my life. It's tearing itself apart and it's tearing itself apart basically over the re division the redistribution of wealth having so badly distributed in the first. But that's all in Marks and notice as I explained to you what is going on in this tension filled production scene in the office, the factory, the store. I don't have to say a word about the government. I'm not interested in the government. The government is really a very secondary matter to this core question and here comes the big point if you make a revolution and all you do is remove the private exploiter and substitute a government official without changing the relationship. You know, you can call yourself a Marxist all day long, but you're not getting the point of the Marxism. The point was not who the exploiter is, but the exploitation per se. You gotta change the organization of the workplace. So there isn't a group that makes all the decisions and gets the surplus vis a vis another one that produces it. If you do that, you will destroy the whole project. You will not only will you not achieve what you set out to get, but you also misunderstand it, that you the Germans again have a phrase, it's get chief, it goes crooked, It doesn't go right. The project gets off the rails because it can't uh, it can't understand either what its objective should have been and therefore it doesn't understand how and why it's missing its objective. It just knows that this is not what it had hoped for. </s>

<s>[INST] I don't know if it was obvious, but it was obvious there was a significant probability that it could be a big deal. I remember it wasn't clear. There's still stories of it, the big concern, the hospital's might have been filled, but it's gonna calculating in two months [/INST] or something. Yeah. No, but there was no way we weren't going to have tens of thousands of deaths at a minimum at that point, and it was totally rational to be worried about hundreds of thousands, and when Nicholas Christakis came on my podcast very early, he predicted quite confidently that we would have about a million people dead in the US, and that didn't seem, it was, I think, appropriately hedged, but it was still, it was just like, okay, it's just gonna, you just look at the, we're just kinda riding this exponential, and we're, and it's gonna be, you know, it'd be very surprising not to have that order of magnitude, and not something much, much less. And so anyway, I mean, again, to close the story on Elon, I could see how this was being received, and I tried to get him to walk that back, and then we had a fairly long and detailed exchange on this issue, and so that intervention didn't work, and it was not done, you know, I was not an asshole, I was not, I was just concerned, for him, for the world, and then there are other relationships where I didn't take the, again, that's an example where taking the time didn't work, right, privately. There are other relationships where I thought, okay, this is just gonna be more trouble than it's worth, and I said, I just ignored it, you know? And there's a lot of that and I, Frank, again, I'm not comfortable with how this is all netted out because I don't know if, you know, frankly, I'm not comfortable with how much time in this conversation we've spent talking about these specific people. Like what good is it for me to talk about Elon or Brett </s><s>[INST] or anything? I think there's a lot of good because those friendships, listen, as a fan, these are the conversations that I loved, love as a fan and it feels like COVID has robbed the world of these conversations because you were exchanging back and forth on Twitter, but that's not what I mean by conversations, like long-form discussions, like a debate about COVID, [/INST] like a normal debate and debate. But there's no, Elon and I shouldn't be debating COVID. </s><s>[INST] You should be. Here's the thing with humility, like basically saying, we don't really know, like the Rogan method, we're just a bunch of idiots. Like one is an engineer, you're a neuroscientist, it just kind of, okay, here's the evidence and be like normal people. That's what everybody was doing. The whole world was like trying to figure out [/INST] what the hell, what? Yeah, but the issue was that at that, so at the moment I had this collision with Elon, certain things were not debatable, right? It was just, it was absolutely clear where this was going. It wasn't clear how far it was gonna go or how quickly we would mitigate it, but it was absolutely clear that it was gonna be an issue, right? The train had come off the tracks in Italy. We knew we weren't gonna seal our borders. There were already people, there are already cases known to many of us personally in the US at that point. And he was operating by a very different logic </s><s>[INST] that I couldn't engage with. Sure, but that logic represents a part of the population and there's a lot of interesting topics that have a lot of uncertainty around them, like the effectiveness of masks. [/INST] Yeah, but no, but where things broke down was not at the point of, oh, there's a lot to talk about, a lot to debate, this is all very interesting, and who knows what's what. It broke down very early at, this is, there's nothing to talk about here, like either there's a water bottle on the table or there isn't, right? </s><s>[INST] Technically, there's only one fourth of a water bottle. So what defines a water bottle? Is it the water inside the water bottle or is it the water bottle? What I'm giving you is an example [/INST] of it's worth the conversation. This is difficult because we had an exchange in private and I wanna honor not exposing the details of it, but the details convinced me that there was not a followup conversation on that topic. </s><s>[INST] On this topic. On this topic. That said, I hope, and I hope to be part of helping that happen, that the friendship was rekindled because one of the topics I care a lot about artificial intelligence, you've had great public and private conversations about this topic. And it seems like- [/INST] Yes, and Elon was very formative in my taking that issue seriously. I mean, he and I went to that initial conference in Puerto Rico together and it was only because he was going and I found out about it through him and I just wrote his coattails to it that I got dropped in that side of the pool </s><s>[INST] to hear about these concerns at that point. It would be interesting to hear how's your concern evolved with the coming out of Chad GPT and these new large language models that are fine-tuned with reinforcement learning and seemingly to be able to do some incredible human-like things. There's two questions. One, how's your concern in terms of AGI and super intelligence evolved and how impressed are you with Chad GPT [/INST] as a student of the human mind and mind in general? Well, my concern about AGI is unchanged. And so I've spoken about it a bunch on my podcast but I did a TED talk in 2016 which was the kind of summary of what that conference and various conversations I had after that did to my brain on this topic. </s>

<s>[INST] okay. So to summarize them so well you brilliantly described, I just want to make sure we're keeping it went all over the place, you know, you didn't, you're, you're pretty on point. But so the first thing is basically, which is difficult. I wonder if we can break it apart a little bit is don't trust authority essentially keep asking why [/INST] be respectful without trusting authority. Right? </s><s>[INST] Right. Which is, and then the second thing is be the kind of person that others like training with her, like being around sort of uh being a good friend. So so many people just enjoy being around. So one is completely, which is, yeah, you're right, it's attention, which is like completely disrespect the, the way that things are done. So asking why constantly one of it is your own flaws and not understanding the fundamentals of what's being described. And then once you get good enough not understanding, um, like go in against the fact that the instructor doesn't understand [/INST] and my inability to understand what you're saying that doesn't invalidate it. And that's something like you mentioned, like mention keeping in mind our own flaws and then also again the flaws that any of us have is the instructor to your point and I guess I can speak to being kind of weird, I don't, you know, I like to sit in the corner, but um, so everyone's a little bit different, some people, you know, I wasn't terribly popular in high school, you know, like, and like high school very much, but anyway, you know, we're not gonna be rude to people though, it was never going to bully anybody if you said hello to me, I'd say hello back, I would hold the door for you if you walk by, you know, and I would just say like simple things like that, go a long, long, long way and I actually takes us back to our, um, to our social discussion where I'm like, oh man, how do I become great at jujitsu? It's like, we'll start by not pissing off this person who can beat the crap out of me and not disrespecting the person who is probably that the clear is the closest thing to a font of knowledge at that time for me. So, and then recognizing that I should do that for its own virtue because it's the right thing to do and I should try to treat people decently, but beyond that even selfishly, it's in my interest to do </s><s>[INST] that. But see the thing is, this is interesting is um, there's a culture in martial arts, the culture that I like where the instructor legitimately so carries aura of authority and it's not comfortable to really ask why I'm not, it's a skill to be able to have a discussion as a white belt, the black belt instructor of like why is it done this way? Like and saying why again? Like would I mean it's a skill to show that you're actually legitimately a curious and passionate and compassionate student versus like somebody who's just being an annoying dick who saw some stuff on youtube. There's a line between to walk there. I I just wondered because like it's the drilling thing and you know, I um for example, like in my and when, when I was coming out, there was so much emphasis placed on the closed guard for example, and you might, you might actually teach me now, I don't know. But to me it was like why do I need to master the close guard? Like why is the closed guard on top of the bottom? But the bottom really, this is the fundamental basics would you get? So [/INST] who decided that </s><s>[INST] my body is not? My body says this is wrong. I'm like this like I have short legs but doesn't even matter the length of legs. There's something about me that just, I don't understand how leverage here works for my particular body. So it's just, it's a feel thing to like, it feels like in my basic understanding of leverage and movement and timing and so on. It feels like there's certain like butterfly guard or even like half basically every guard except close guard. I can play, I can dance close guard feels like you're shutting down. Uh, like the play that [/INST] is that wrong or is that make sure that's what you want because that's almost like an innate characteristic of this guard position, but it's not sold that way. Hey, this is a good guard. It's like, hey man, here's a bow and arrow versus and you know how to use this thing right? Like make sure you're far away and like up on a hill or something because you can take that bone out, run up on something and try to use it. But if nobody told you not to do that and they told you it's foundational, its very foundation. It's very important </s><s>[INST] to everything else to [/INST] write, that's back to the shrimp ng thing. How many things are we taught that even if it's not, let's say itself is not a garbage thing might be effectively garbage. You could give me a Ferrari, but if I try to make it fly, it's not gonna work. If you're like, here's a plane, here's another plane, Here's another plane, Here's another plane. Here's a Ferrari. I'm like, oh, it must be a different type of plane. Like you could be forgiven for for leap if we're going there, you know, like maybe the wings come out or you just go fast enough, it's like a bullet, you can make these crazy leaps in your mind and people are doing that all the time. So if you don't provide the context for me or worse yet you provide improper context, like how, how much of a problem is that going to be? </s>

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

<s>[INST] Did it manifest itself differently? Just the fact that it came from those different places. [/INST] Absolutely. </s><s>[INST] Like what? So like the discussion about glass on the iphone was probably had a different flavor to it. [/INST] Sure, when you started getting into the technical details enough. So you're getting the third order technical details and he can't argue with that anymore. And it was something he was like, okay, you know, at some point, he's like, I can't win this war like and he learned that very early on because he didn't like the way the look of the macintosh um, board. The PCB was laid out. He wanted to be beautiful on the outside and on the inside. He's like, why are all these wires running this way, why doesn't it have all this symmetry? And we have to make it beautiful on the inside and, and even the traces on the boards have to look a certain way. So the teams made the board, they knew that would work and then they made the board, that's the way steve wanted it and that didn't work. And then steve instantly figured out, like at some point don't micromanage every single detail, there's some things he doesn't know enough about and so he would get out of that. But that was one of those instances where he pushed really hard and that's his opinion. So they said, okay, we're gonna make it a data driven decision, we're gonna make both. I'm gonna show you the results, right? And then from there, he didn't get into those details. So from that, you could have a great challenge, right? Because then you could get those data and say, we can't do that and let me show you why or we can do that. And then steve would go, you can't do that and you're like, oh, we can do that, let me show you, right? So there's certain times when you were like, bring something to reality that he didn't think could exist, right? So it was that it was always that creative tension, that interaction that was so successful, right? I think. But there was one other fundamental thing that was different and that it graded on the team and that I made sure and I learned from to not do and I over maybe overdue now in the opposite direction, which is when there's a great idea that comes from the team, acknowledge that person and go, that is a great idea as the leader, You know, the opinion driven, that's a great idea. Let's build on that, Let's see if that can do that or it's a great idea, but not for now. Put it aside, but call out when people have great ideas because it's infectious and that means not ideas that come bubble up to the customer level, but inside the organization, people like, they get rewarded for their ideas and say, that's a great one. Steve was always like, you give an idea, anybody go, okay, I don't know. The next day, 24 hours later it would come back with slight modifications. I've had this genius idea right? And sooner or later we'd, we'd look around the table and we'd like roll our eyes and go, here we go again. </s><s>[INST] So it de motivates you from generating ideas a little bit. [/INST] Well, you know, we got used to it, but you know, later on in the team, you know, it was just not, it just, it doesn't want to bring the best, right? Because if you're always like, uh, the reaction is never, that's a genius idea. It was always like, it was either negative or neutral, right? Then it doesn't, it doesn't have that same emotional effect that you want you to bring your best. </s><s>[INST] Yeah, sometimes it's fun when people get excited about it. Just Yeah, yeah, yeah, yeah. You kind of build on top excitement, it could be, but coupled with sort of harshness when the idea is bad and you call out the bad ideas too, the good and the bad. [/INST] You can say you don't have you don't have to say bad idea, say maybe not now, let's table that for later, let's discuss it or say that's a decent idea. But did you think about that idea this way? Not just no or yes, but let's talk about why that might not be applicable in this case so that they can learn. So the next time they bring the next idea they can modulate and understand to start seeing through the opinion based decision makers or the databases and bring better formatted arguments or ideas so that you have a better chance of success the next time right? You gotta train through those moments, you gotta teach those are teaching moments, </s><s>[INST] moments I aspire to be that kind of person. I'll usually say that that that idea is shit, that is the like like and then you that I remember that that this brilliant person just gave that really shitty idea. So I remember to make sure the next time they give a good idea, I really compliment that good idea but I personally ah [/INST] I </s><s>[INST] mean it's emotion but I I call out the really shitty ideas [/INST] but you should call it the really great ones. If you let the pendulum swing both ways then everybody goes, he's balanced. It's always one way, why bring any idea? </s><s>[INST] I'm all about the pendulum. [/INST] You gotta have </s><s>[INST] both [/INST] the joy and the pain. </s>

<s>[INST] So if you skip please still check out the sponsors by clicking the links in the description. It is in fact the best way to support this podcast. This episode is sponsored by the jordans. Harbinger show. Go [/INST] to Jordan's </s><s>[INST] harbinger dot com slash lex. Subscribe to it. Listen, you won't regret it. I've been binging on this podcast for the entirety of 2020, Jordan's a great interviewer, he gets the best out of his guests dives deep, calls them out when it's needed and makes the whole thing fun to listen to. He has interviewed Kobe Bryant, Mark Cuban, the other grasse Tyson, Garry, Kasparov and many more. Perhaps more importantly, he is unafraid of addressing challenging even controversial topics with thought and grace, especially like his feedback friday's episodes where his combination of fearlessness and thoughtfulness is especially on display, touching topics of sex corruption, mental disorders. Hey love and everything in between. Again, go to Jordan harbinger dot com slash lex is how he knows I sent you On that page, there's links to subscribe to the show on everywhere you listen to podcasts including apple podcast. Spotify. If you're listening to this, I'm sure you know how this works. Oh, and if you like it, probably go give five stars to show, leave a nice review. Tell him I sent you this show is also sponsored by the thing had currently really need, which is coffee for stigmatic, the maker of delicious mushroom. Coffee and plant based protein. I enjoyed both. The coffee has lines, mane mushroom for productivity and Chicago mushroom for immune support. The plant based protein has immune support as well and tastes delicious, which I think honestly at least for me is the most important quality of both protein and coffee supporting your immune system is one of the best things you can do now to stay healthy And this difficult time for the human species. Not only does for stigmatic, always have 100% money back guarantee, but right now you can try their amazing products for up to 50% off and on top of that you get extra discounts for just the listeners of this podcast. If you go to four stigmatic dot com slash lex, that's four stigmatic dot com slash lex. This episode is sponsored by better help spelled h E L p help. I always think about the movie castaway when I spell out the word help. Okay, they figured out what you need and match you with a licensed professional therapist under 48 hours. I chat with a person on there and enjoy it. Of course. I also have been talking to over the stretch of 2020 and looks like 20, as well to David Goggins who is definitely not a licensed professional or some would say saying, but he does help me meet his and my demons and become comfortable to exist in their presence. This is just my view, but I think mental struggle is essential for creation, but I think you can struggle in a way that's controlled and done beautifully as opposed to in a way that destroys you. I think therapy can help in this and better help us a good option for that. There are easy, private, affordable available worldwide. You can communicate by text any time and schedule weekly audio and video session to give a shout out to the to O G. S. My two favorite psychiatrist, Sigmund Freud and Carl Young when I was younger. Their work was important in my intellectual development anyway, check out better health dot com slash lex. That's better help dot com slash lex. The show is also sponsored by Express VPN. It provides privacy in your digital life. Without VPN, your internet service provider can see every sight you've ever visited, keeping a log of every single thing you did online. So your internet provider, like A T and T or Comcast is allowed to store those logs and sell this data to anyone. That's why you should use Express VPN as much as possible. I do it. You should consider doing it as well. They don't keep any logs, they audit their attack by external companies. These guys are legit. I think this topic and VPN certainly are especially relevant now when the power of social media firms and SPS was made a parent with a wave of deplatforming actions, we need to use tools that lessen the power of the centralized entities. I use Express VPN is just one example of such a tool. Go to Express VPN dot com slash lacks pod to get an extra three months free on a one year package as a big red button if you enjoy those kinds of things. I certainly do. Okay, that's express VPN dot com slash flex pod. Sign up for the privacy and the big red button that's expressive BN dot com slash flex pod. And now here's my conversation with max tag mark. So people might not know this, but you were actually episode number one of this podcast just a couple of years ago and now we're back. And it so happens that a lot of exciting things happened in both physics and artificial intelligence both feels that you're super passionate about. Can we try to catch up to some of the exciting things happening and artificial intelligence especially in the context of the way it's cracking open the different problems of the sciences. [/INST] Yeah, I'd love to. Especially now, as we start 2021 here, it's a really fun time to think about what were the biggest breakthroughs in aI, not the ones necessarily the media wrote about, but that really matter. And and what does that mean for our ability to do better science? What does it mean for our ability to help people around the world? And what does it mean for new problems that they could cause if we're not smart enough to avoid them? So, you know, what do we learn basically from this? </s><s>[INST] Yes, absolutely. So one of the amazing things you're part of is the AI Institute for artificial intelligence and fundamental interactions. What's up with this institute. What are you working on? What are you thinking about? [/INST] The idea is something I'm very on fire with, which is basically a I meets physics and you know, it's been almost five years now since I shifted my own MIT research from physics to machine learning. And in the beginning I noticed a lot of my colleagues, even though they were polite about it, was that kind of, what is max doing? </s><s>[INST] What is this weird stuff? He's lost his [/INST] mind then. But thank gradually, I uh together with some colleagues were able to persuade more and more of The other professors in the Physics Department to get interested in this. And now we got this amazing NSF centers of $20 million bucks for For the next five years mit and a bunch of neighboring universities here also. And I noticed now those colleagues, they were looking at me funny have stopped asking why what the point is of this, because it's becoming more clear and I really believe that of course aI can help physics a lot to do better physics, but physics can also help ai a lot both by building better hardware. My colleague marine style jackets, for example, is working on optical chip for much faster machine learning, where the computation is done not by moving electrons around, but moving photons around dramatically less energy use faster better. Um </s><s>[INST] we can we can also help [/INST] a I a lot, I think by having a a different set of tools and a different, maybe more audacious attitude, you know, ai has to a significant extent been an engineering discipline where you're just trying to make things that work and being less more interested in, they be selling them than in figuring out exactly how they work and proving theorems about that, they will always work. Right, contrast that with physics, you know, when Elon musk sends a rocket to the international space station, they didn't just train with machine learning all. It's fired a little bit left, more to the left, a bit more to the right. So that also missed. Let's try here. No, you know, we figured out Newton's laws of gravitation and other got other things, I've got a really deep fundamental understanding uh and that's what gives us such confidence in, in rockets and my vision is that in the future all machine learning systems that actually have impact on, on people's lives will be understood at a really, really deep level. Right? So we trust them not because some sales rep told us to, but because they've earned our trust, we can and really safety critical things even prove that they will always do, you know what we expect them to do? That's very much the physics mindset. So it's interesting if you look at big breakthroughs that have happened in machine learning this year, you know, from dancing robots, you know, it's pretty fantastic and not just because it's cool, but if you just think about not that many years ago, this Youtube video at this DARPA challenge with the mighty robot comes out of the car and face plants, how far we've come. And and just a few years similarly alpha fold too, you know, crushing the protein folding problem. We can talk more about implications for medical research and stuff. But hey, you know, that's huge progress. You can look at the GPT three that can spout off english texts, which sometimes really, really blows you away. You can look at the google at deepmind uh mu zero, which doesn't just kick her butt and go and chest and kogi. But also in all these Atari games and you don't even have to teach you the rules now. You know what all of those have in common is besides being powerful is we don't fully understand how they work. And that's fine. If it's just some dancing robots and the worst thing that can happen is the face plant, right? Or if they're playing go. And the worst thing that can happen is that they make a bad move and lose the game. It's less fine if that's what's controlling your self driving car or your nuclear power plant. And uh we've seen already that even though Hollywood had all these movies where they try to make us worry about the wrong things like machines turning evil. The actual bad things that have happened with automation have not been machines turning evil, they have been caused by over trust in things we didn't understand as well as we thought we did right. Even very simple automated systems like What the Boeing put into the 737 Max Wright killed a lot of people, was it that that little simple system was evil? Of course not, but we didn't understand it as well as we should have right? </s><s>[INST] And we trusted without understanding [/INST] exactly being over trust, we didn't even understand that, we didn't understand right. The humility is really at the core of being a scientist, I think step one, if you want to be a scientist is don't ever fool yourself into thinking, you understand things when you actually don't right, </s><s>[INST] that's probably good advice for humans in general, [/INST] I think humility in general and it was good, but in science it's so spectacular, like why did we have the wrong theory of gravity ever from Aristotle onward close until like Galileo's time. Like why would we believe something so dumb as that? If I throw this water bottle it's going to go up with constant speed until it realizes that it's natural motion. Is that changes its mind, you know, because we people just kind of assumed Aristotle was right, he's an authority, we understand that. Uh why did we believe things like that? The sun is going around the Earth two, why did we believe that time flows at the same rate for everyone Until Einstein same exact mistake over and over again, we just weren't humble enough to acknowledge that we actually didn't know for sure. We assumed we knew uh so we didn't discover the truth because we assumed there was nothing there to be discovered, right? There was something to be discovered about the 737 max and if you had been a bit more suspicious and tested it better, we would have found it. And it's the same thing with the most harm that's been done by automation so far. I would say so, I don't know if you, did you ever hear of a company called Knight Capital? So good. That means you didn't invest in them earlier, they deployed this automated trading system all nice and shiny, they didn't understand it as well as they thought and it went about losing 10 million bucks per minute for 44 minutes straight until someone presumably was like, oh shut up, you know, it wasn't evil. No, it was again misplaced trust something they didn't fully understand, right? And there have been so many, even when people have been killed by robots just quite rare still, but inactive factory accidents, it's in every single case been not malice, just that the robot didn't understand that human is different from an order part or whatever and we um so this is where I think there's so, so much opportunity for physics approach, where you just aim for a higher level of understanding. And if you look at the all these systems that we talked about from the, from reinforcement learning systems and dancing robots to all these neural networks that Power GPT three and go playing software is up. They're all basically black boxes much like not so different from if you teach a human something, you have no idea how their brain works, right? Except the human brain at least has been error corrected during many, many centuries of revolution in the way that these some of these systems have not. Right. And my research is entirely focused on demystifying this black box. Intelligible intelligence is my slogan. </s><s>[INST] That's a good line intelligible intelligence. [/INST] Yes. And that we shouldn't settle for something that seems intelligent, but we should it should be intelligible. So that we actually trust it because we understand it right? Like again, Ellen trusts his rockets because he understands Newton's laws and thrust and everything works. Uh, and let me tell you what can I tell you why? I'm optimistic about this? I think I think there is we've made a bit of a mistake where we, some people still think that somehow we're never going to understand neural networks and we're just gonna have to learn to live with us. It's this very powerful black box basically for those. You know, I haven't spent time building their own. It's super simple what happens inside you send in a long list of numbers and then you do a bunch of operations on them? Multiply by matrices, etcetera, etcetera. And some other numbers come out the output of it. And then there are a bunch of knobs you can tune and when you change them, you know, it affects the computation, input, output relation, and then you just give the computer some definition of good and it keeps optimizing these knobs until it performs this good as possible. And often you go like, wow, that's really good. This robot can dance or this machine is beating me at chess now. And in the end you have something which, even though you can look inside it, you have very little idea of how it works. You know, you can print out tables of all the millions of parameters in there. Is it crystal clear now how it's working? And of course not. Right. So many of my colleagues seem willing to settle for that and I'm like, no, that's like the halfway point. Uh some have even gone as far as sort of guessing that the mr the inscrutability of this is where the some of the power comes from and sort of some sort of mysticism. Uh I think that's total nonsense. I think the real power of neural networks comes not from inscrutability, but from differential ability and what I mean by that is simply that the output depends changes only smoothly if you tweak your knobs and then you can use all these powerful methods we have for optimization in science. We can just tweak them a little bit and see, did that get better or worse? That's the fundamental idea of machine learning that the machine itself can keep optimizing until it gets better. I suppose you wrote this and algorithm instead in python or some other programming language. And then what what the knobs did was they just changed random letters in your in your code. Now we'll just epically failed. Right? You change one thing and instead of saying print that says sint syntax error, you don't even know was that this for the better or for the worst. Right. This to me is this is what I believe is the fundamental power of neural networks. </s><s>[INST] And just to clarify the changing of the different letters in the program would not be a differential process. [/INST] It would make it in an invalid program typically. And then you wouldn't even know if if you change more letters, if it would make it work again. Right. </s><s>[INST] So that's the magic of neural networks. Uh, the [/INST] inscrutability, the defense ability that that every every setting of the parameters is a program. And you can tell it is it better or worse? Right. And so </s><s>[INST] so you don't like the poetry of the mystery of neural networks as the source of its [/INST] power. I generally like poetry, but not in this case. It's so misleading. And above all, it shortchanges us. It's failed. It makes us underestimate what we can the good things we can accomplish because so what we've been doing in my group is basically step one, train the mysterious neural network to do something well. And then step to do some additional Ai techniques to see if we can transform this black box into something equally intelligent that you can actually understand. So for example, I'll give you one example this ai fireman project that we just published. Right, So we I took the 100 most famous or complicated equations from one of my favorite physics textbooks. In fact the one that got me into physics in the first place, Feinman lectures on physics and so you have a formula. You know, maybe it has what goes into the formula is six different variables and what comes out is one. So then you can make like a giant Excel spreadsheet with seven columns, you put in just random numbers for the six columns for those six input variables. And then you calculate with the formula of the seventh column output. So maybe it's like the forest equals in the last column some function of the other. And now the task is okay if I don't tell you what the formula was, can you figure that out from looking at my spreadsheet? I gave you this problem is called symbolic regression. If I tell you that the formula is what we call a linear formulas. So it's just that the output is sum sum of all the things input the time, Some constants. That's the famous easy problem. We can solve we do it all the time in science and engineering. But the general one if it's more complicated functions with logarithms or co signs or other math. It's a very very hard one and probably impossible to do fast in general just because the number of formulas with and symbols just grows exponentially just like the number of password you can make grow dramatically with length. So so we but we had this idea that if you first have a neural network that can actually approximate the formula, you just train that even if you don't understand how it works that can be the first step towards actually understanding how it works. So so that's what we do first and then we study that neural network now and put in all sorts of other data that wasn't in the original training data. And use that to discover simplifying properties of the formula. And that lets us break it apart often into many simpler pieces in a kind of divide and conquer approach. They were so we were able to solve all of those 100 formulas, discover them automatically plus a whole bunch of other ones. And uh it's a it's actually kind of humbling to say that this code which anyone who wants now is listening to this. You can type pip, install a I find men on the computer and run it. You know, it can actually do what Johannes kepler spent four years doing when he stared at MARS data until he's like funny Eureka. This is an ellipse. Uh this will do it automatically for you in one hour, right? Or max plank. He was looking at how much radiation comes out from different wavelengths from a hot object and discovered the famous black body formula. This discovers it automatically. Uh huh. I'm I'm actually excited about yeah. Seeing if we can discover not just old formulas again, but new formulas that no one has seen before. </s><s>[INST] And do you like this process of using kind of a neural network to find some basic insights and then dissecting the neural network to then gain the final. So that that's in that way you've uh forcing the explain ability issue uh you know, really trying to analyze the neural network for the things it knows in order to come up with the final beautiful simple theory underlying the whole the initial the initial system that you were [/INST] looking at. I love that. And and the reason I'm so optimistic that it can be generalized to so much more is because that's exactly what we do is human scientists think of Galileo whom we mentioned right? I bet when he was a little kid if his dad through monopoly even catch it. Why? Because he had a neural network in his brain that he had trained to predict. The parabolic orbit of apples that are thrown under gravity. If you throw a tennis ball to a dog, it also has this same ability of deep learning to figure out how the ball is going to move and catch it. But Galileo went one step further. When he got older he went back and it was like, wait a minute I can write down a formula this why equals X squared a parabola, you know, and he helped revolutionize physics as we know it, right? </s><s>[INST] So there was a basic neural network in there from childhood that captured like the base the experiences of observing different kinds of trajectories. And then he was able to go back in with another extra little neural network and analyze all those experiences and be like, wait a minute. There's a deeper rule here. [/INST] Exactly. He was able to distill out in symbolic form. What that complicated black box was doing right? Not only did he the formal, he get you ultimately become more accurate, you know? And similarly this is how how Newton got Newton's laws, which is why Ellen can send rockets the space station now. Right? So it's not only more accurate but it's also simpler, much simpler. And it's so simple that we can actually describe it to our friends and each other, right? Uh We've talked about it just in the context of physics now, but hey, you know, isn't this what we're doing when we're talking to each other. Also we go around with our neural networks just like dogs and cats and chipmunks and blue jays and we experience things in the world, but then we humans do this additional step on top of that, where we then distill out certain high level knowledge that we've extracted from this in a way that communicated to each other in a symbolic form, in english in this case. Right. So if we can do it and we believe that we are information, information processing entities, then we should be able to make machine learning that does it also </s><s>[INST] well, do you think the entire thing could be learning because their um this dissection process, like for ai Feinman, the secondary stage feels like something like reasoning and the initial step feels like more like the more basic kind of differentiable learning. Do you think the whole thing could be differential learning? Do you think the whole thing could be basically neural networks on top of each other? It's like turtles all the way down, giving neural networks all the way down. [/INST] I mean, it's that's a really interesting question. We know that in your case it is neural networks all the way down because you have in your skull there's a bunch of neurons doing their thing, right. But uh if you ask the question more generally, what algorithms or your brain is your brain are being used in your brain. I think super interesting to compare. I think we've gotten a little bit backwards historically because we humans first discovered good old fashioned ai the logic based ai that we often called go fi for good old fashioned Ai. And then more recently we did machine learning because it required bigger computers so we had to discover it later. So we think of machine learning with neural networks as the modern thing and the logic based Ai is the old fashioned thing. But if you look at evolution on earth right, it's actually been the other way around. I would I would say that for example an eagle has a better vision system that I have using and dogs are just as good at casting tennis balls as I am. All this stuff which is done by training a neural network and not interpreting it in words, you know, it's something so many of our animal friends can do at least as well as us right, what is it that we humans can do that? The chipmunks and the eagles cannot. It's more to do with this logic based stuff, right? Where we can extract out information in symbols in language and now even with equations, if you're a scientist. Right? So basically what happened was first we built these computers that could multiply numbers real fast and manipulate symbols and we felt they were pretty dumb and that and then we made neural networks that can see as well as a cat can and do a lot of this inscrutable black box neural networks. What we humans can do also is put the two together in a useful way. Yes, artificial in our own brain, yes, in our own brain. And so if we ever want to get artificial general intelligence that can do all jobs as well as humans can, right, then that's what's gonna be required to be able to combine the new Orleans works with with symbolic, combine the old with the new ai in a good way. We do it in our brains. And there seems to be basically two strategies. They see an industry now one scares the cbgbs out of me and the other one I find much more encouraging. </s><s>[INST] Okay, Which one can we break them apart, which which has to [/INST] do? The one that scares the cbgbs out of me is this attitude that we're just gonna make ever bigger systems that we still don't understand until they can be as smart as humans. I what could possibly go wrong, I think it's just such a reckless thing to do. And unfortunately, and if we actually succeed as a species to build artificial general intelligence and we still have no clue how it works. I think At least 50% chance we're going to be extinct before too long, it's just gonna be another epic uh own goal. </s><s>[INST] You know, it's that 44 minutes losing money problem or like the paperclip problem, like where we don't understand how it works. And it's just in a matter of seconds runs away in some kind of direction that's going to be very problematic [/INST] even long before you have to worry about the machines themselves. Uh somehow deciding to do things. And to us the we have to worry about people using machines. They're short of A. I. G. I. N. Power to do bad things. I mean just take your moment and if anyone who's not worried particularly about advanced A. I just take 10 seconds and just think about your least favorite leader on the planet right now don't tell me who it is. You want to keep this a political but just see the face in front of you that person for 10 seconds now imagine that that person has this incredibly powerful ai under their control and can use it to impose their will on the whole planet. How does that make you feel? </s><s>[INST] Yeah. So the can you can you break that apart just briefly For the 50% chance that will run to trouble with this approach. Do you see the bigger worry in that leader or humans using the system to do damage or are you more worried? And I think I'm in this camp more worried about like accidental unintentional destruction of everything. So like humans trying to do good and like in a way where everyone agrees it's kind of good it's just trying to do good without understanding because I think every leader in history thought there [/INST] to some degree thought they were trying to do good. Oh yeah, I'm sure Hitler thought he was doing good, stop good </s><s>[INST] too. I've been reading a lot about Stalin. I'm sure Stalin is from, he legitimately thought that communism was good for the world and then he [/INST] was doing good. I think mounted on thought what he was doing with a great leap forward is good too. Yeah, I'm actually concerned about both of those before I promised to answer this and detail, but before we do that, let me finish answering the first question. Because I told you that there were two different routes we could get the artificial general intelligence and one scares the bejeebers out of me. Which is this one where we build something, we just say bigger neural networks ever more hardware and it's just train the more data and poof now it's very powerful uh that I think is the most unsafe and reckless approach. The alternative to that is the intelligent intelligible intelligence approach instead, where we uh say neural networks is just a tool to this. Like for the first step to get the intuition. But then we're gonna spend also serious researches sources on other ai techniques for demystifying this black box and figuring out what it's actually doing. So we can convert it into something that's equally intelligent, but that we actually understand what is doing. Maybe we can even prove theorems about this car here will never be hacked when it's driving Because here is the proof, uh, there is a whole science of this. It doesn't work for neural networks that big black boxes, but it works well. And we're certain other kinds of codes, right? Uh, that approach I think is much more promising. That's exactly why I'm working on it, frankly not just because I think it's cool for science, but because I think the more we understand these systems, the better the chances that we can make them do the things that are good for us that are actually intended, not unintended. </s><s>[INST] So you think it's possible to prove things about something as complicated as a neural network. That's the hope. [/INST] Well, ideally there's no reason it has to be a neural network in the end either. Right? Like we discovered that Newton's laws of gravity with neural network in Newton's head, but that's not the way it's programmed into the navigation system of Elon musk's rocket anymore. It's written in C Plus Plus or I don't know what language he uses exactly. And then there are software tools called symbolic verification DARPA and the US uh, military has done a lot of really great research on this because they really want to understand that when they build weapons systems, they don't just go fire at random or malfunction. Right? And there's even a whole operating system called Cell three that's been developed by DARPA Grant where you can actually mathematically prove that this thing can never be hacked. Uh well I one day I hope that will be something you can say about the os that's running on our laptops do as, you know, we're not there. But I think we should be ambitious frankly. And if we can use machine learning to help do the proofs and so on as well, right, then it's much easier to verify that the proof is correct. Then to come up with the proof in the first place. That's really the core idea here. If someone comes on your on your podcast and says they prove the Riemann hypothesis or some new sensational new theorem. It's not me. It's much easier for some one else. Takes some smart grad math grad students that check, oh, there's an error here on equation equation five or this really checks out. Then it was to discover the proof. </s><s>[INST] Yeah. Although some of those proofs are pretty complicated. But yes, it's still nevertheless much easier to uh, to verify the proof. I love the optimism. You know, we're kind of, even with the security of systems, there's a kind of cynicism that pervades people who think about this, which is like, oh, it's hopeless. I mean, in the same sense. Exactly like you're saying when you're networks always help us to understand what's happening uh, with security people are just like, well, it's always going, there's always going to be attack vectors like uh waste, waste to attack the system. But you're right, we're just very new with these competitions, all systems where you knew with these intelligence systems and it's not out of the realm of possible. Just like people don't understand the movement of the stars and the planets and so on. It's entirely [/INST] possible that, like, </s><s>[INST] within hopefully soon, but it could be within 100 years, we start to have an obvious like laws of gravity about [/INST] intelligence </s><s>[INST] and uh, God forbid about consciousness to that one has [/INST] agreed. You know, I think of course, if you're selling computers that get hacked a lot that's in your interest as a company that people think it's impossible to make it safe. So you nobody's going to get the idea of suing you. But I want to really inject optimism here. It there it's it's absolutely possible to do much better than we're doing now. And, you know, your laptop does so much stuff, you don't need the music player to be super safe in your in your future self driving car, right? Um, if someone hacks in and starts playing music, you don't like the world on end. But what you can do is, you can break out and say that dr computer that controls your safety must be completely physically the coupled entirely from the entertainment system and it must physically be such that it can take on over the air updates while you're driving and it can be, it can have, it's not that it can have ultimately a sort some operating system on it, which is symbolically verified and unproven, uh, that it's always gonna do what it's gonna, what it's supposed to do. Uh, we can basically have and companies should take that attitude. They should look at everything they do and say, what are the few systems in our, in our company, the threatened the whole life of the company if they get hacked and have the highest standards for them and then they can save money by going for the el cheapo poorly understood stuff for the rest. You know, this this is very feasible, I think. And coming back to the bigger question, but you worried about that? That will be unintentional failures? I think there are two quite separate risks here, right? We talked a lot about one of them, which is that the goals are noble of the human human says, I want this airplane to not crash because this is not Mohamed atta. Now flying the airplane, right? And now there's this technical challenge of making sure that the autopilot is actually going to behave as as the pilot wants? Um, if you set that aside, there's also a separate question, how do you make sure that the goals of the pilot are actually aligned with the goals of the passenger, how do you make sure very much more broadly that if we can all agree as a species, that we would like things to kind of go well for humanity as a whole that the goals are aligned here, the alignment problem and yeah, there's been a </s><s>[INST] lot [/INST] of progress in in the sense that there's suddenly a huge amounts of research going on on it about it. I'm very grateful to Elon musk for giving us that money five years ago. So we could launch the first research program on technical ai safety and alignment. There's a lot of stuff happening but I think we need to do more than just make sure little machines do always what their owners do. You know, that wouldn't have prevented september 11 Mohamed atta said, okay, okay, autopilot, please fly into the World Trade Center. You know, and it's like okay that even happened in a different situation. There was this depressed pilot and then Andreas Lubitz, right. He told his Germanwings passenger jet to fly into the ALPS, he just told the computer to change the altitude, the 100 m or something like that. And you know what the computer said, right, okay, okay. And it had the freaking topographical map of the ALPS in there and had GPS everything, no one had bothered teaching it. Even the basic kindergarten ethics of of like, no, we never want airplanes to fly into mountains under any circumstances. Uh and so we have to think beyond just the the technical issues and think about how do we align in general incentives on this planet for the greater good. So starting with simple stuff like that, every airplane that has a computer in it should be taught whatever kindergarten ethics, it's smart enough to understand like no, don't fly into fixed objects that the pilot tells you to do. So then go on autopilot mode, send an email to the cops and learned at the latest airport nearest airport. You know, any car with a forward facing camera should just be programmed by the, by the manufacturers that it will never accelerate into a human ever. That would have avoid things like the nice attack and many horrible terrorist vehicle attacks where they deliberately did that, right? This was not some sort of thing. Oh, you know, U. S and china different views and no, there was not a single car manufacturer in the world, in the world, right? Who wanted the cars to do this? It just hadn't thought to do the alignment. And if you look at more broadly problems that happen on this planet, the vast majority have to do a poor alignment. I mean, think about, let's go back really big because I know this is your so good, big. Yeah. In the very, so long ago in evolution we had these jeans and they wanted to make copies of themselves, that's really all they cared about. So some genes said, hey, I'm gonna build a brain on this body I'm in so that I can get better at making copies myself And then they decided for their benefit to get copied more to align your brains, incentives with their incentives. So it didn't want you to starve to death. So it gave you an incentive to eat and it wanted you to make copies of the genes, so it gives you incentive to fall in love and do also naughty things to make copies of itself, right? Uh So that was successful value alignment done on the genes. They created something more intelligent than themselves, but they made sure to try to align the values. But then something went a little bit right against the idea of what the genes wanted because a lot of humans discovered, hey, you know, yeah, we really like this business about sex that the genes have made us enjoy, but we don't want to have babies right now. So we're gonna hack the genes and use birth control and I really feel like drinking a coca cola right now, but I don't want to get a potbelly. So I'm gonna drink diet coke. You know, we have all these things we've figured out because we're smarter than the genes, how we can actually subvert their intentions. So, so it's not surprising that we, humans now when we are in the role of these genes creating other nonhuman entities with a lot of power have to face the same exact challenge. How do we make other powerful entities have incentives that are aligned with ours. And so they won't hack them corporations, for example, Right? We humans decided to create corporations because can benefit us greatly. Now, all of a sudden there's a supermarket, I can go buy food there. I don't have to hunt awesome. Uh, and then to make sure that this corporation would do things that were good for us and not bad for us. We created institutions to keep them in check. Like if the local supermarket sells poisonous food, then those, some owners of the supermarket have to spent some years reflecting behind bars. Right? So we created incentives, get align them, but of course, just like we were able to see through this thing and you defend birth control. If you're powerful corporation, you also have an incentive to try to hack the institutions that are supposed to govern you because you ultimately as a corporation have an incentive to maximize your profits, just like you have an incentive to maximize the enjoyment your brain has not for your genes. So if they can figure out a way of, of bribing regulators, then they're going to do that uh, in the US, we kind of caught onto that and made laws against corruption and bribery. Uh, Then in the late 1800s, uh, teddy Roosevelt realized that no, we were still being kind of hack because the massachusetts, Railroad companies had like a bigger budget than the state of massachusetts and they were doing a lot of very corrupt stuff. So he did the whole trust busting thing to try to align these other non human entities. The company's again more with the incentives of americans as a whole. It's not surprising though, that this is a battle you have to keep fighting now. We have even larger companies than we ever had before. And of course they're going to try to uh again subvert uh, the institutions not because, you know, I think people make the mistake of getting all too black thinking about things in terms of good and evil, like arguing about whether corporations are good or evil or whether robots are good or evil, robot isn't good or evil is tool and you can use it for great things like robotic surgery or for bad things. And the corporation also is a tool of course. And if you have good incentives to the corporation, it will do great things like start a hospital or a grocery store. If you have really bad incentives, then it's gonna start maybe marketing addictive drugs, people and you'll have an opioid epidemic. Right? It's all about, I don't want to, we should we not make the mistake of getting into some sort of fairytale good evil thing about corporations or robots. We should focus on putting the right incentives in place. My optimistic vision is that if we can do that, you know, then we can really get good things. We're not doing so great with that right now. Either on a, I I think or on other intelligent nonhuman entities? Like big companies? Like we just have a new secretary of defense, there's gonna start up now and the biden administration, who is it was an active member of the board of Raytheon for example. So you know, I have nothing against Raytheon. I'm not a pacifist, but there's an obvious conflict of interest if someone is in the job where they decide who they're going to contract with. And I think somehow we have maybe we need another teddy Roosevelt to come along again and say, hey, you know, we want what's good for all americans and we need to go do some serious realigning again of the incentives that we're giving to these big companies and then we're gonna be better off. It </s><s>[INST] seems that naturally with human beings, just like you beautifully described the history of this whole thing. Uh it all started with the jeans and they're, they're probably pretty upset by all the unintended consequences that happened since. But the, it seems that it kind of works out like it's in this collective intelligence that emerges at the different levels. It seems to find sometimes last minute away to realign the values or keep the values aligned. It's almost um it finds a way like uh different leaders, different humans pop up all over the place that reset the system? Do you want? I mean you have an explanation why that is or is that just survivor bias and also is that different somehow fundamentally different than with the Ai systems where um you're no longer dealing with something that was a direct maybe companies are the same a direct byproduct of the evolutionary process. [/INST] I think there is one thing which has changed. That's why I'm Not all optimistic. That's why I think there's about a 50% chance if we if we take the dumb route with artificial intelligence that we humans humanity will be extinct in this century 1st. Just the big picture. Yeah cos need to have the right incentives. Yeah even governments. Right? We we used to have governments usually there were just some king you know who was the king because his dad was the king. You know and and then there were some benefits of having this powerful kingdom because we're empire of any sort because then it could prevent a lot of local squabbles so at least everybody in that region would stop warring against each other and their incentives of different cities in the kingdom became more aligned. Right? That's that was the whole selling point. Harari. Yeah. No you're right. Harari has a beautiful piece on how empires were collaboration enablers and then we also have always has invented money for that reason so we could have better alignment and we could do trade even with people we didn't know. So this sort of stuff has been playing out since time immemorial? Right? What's changed is that it happens on ever larger scales. Right. The technology keeps getting better because science gets better. So now we can communicate over larger distances, transport things fast over larger distances. And so the the entities get ever bigger, but our planet is not getting bigger anymore. So in the past, you could have one experiment that just totally screwed up like easter island. Well, they actually manage that have such poor alignment that when they went extinct people there, there was no one else to come back and replace them. Right? Uh, if Elon musk doesn't get us to mars and then we go extinct on a global scale and we're not coming back. That's that's the fundamental difference. And that's a mistake I would rather that we don't make. And for that reason in the past, of course, history is full of fiascos, right? But it was never the whole planet. And then, okay, now there's this nice uninhabited land here. Some other people could move in and organize things better. This is different. The second thing, which is also different is, um, that technology gives us so much more empowerment, right? Both to the good things. And also to screw up in the Stone Age. Even if you had someone whose goals were really poorly alive, like maybe he was really pissed up off because his Stone age girlfriend dumped him and he just wanted to, If you wanted to kill as many people as he could, how many couldn't really take out with a rock and a stick before he was overpowered. Right? Right. It's time to fall right now with today's technology. If we have an accidental nuclear war between Russia and the U. S. Which we almost have about a dozen times and then we have a nuclear winter, it could take out seven billion people or six billion people or we don't know. Uh So that's the scale of the damage is bigger that we can do. And if if it's it's there's obviously no law of physics that says the technology will never get powerful enough that we could wipe out our species entirely. That would just be a fantasy to think that science is somehow doomed, not get more powerful than that. Right? And and it's not at all unfeasible in our lifetime that someone could design a designer pandemic which spreads as easily as covid but just basically kills everybody. We already had smallpox that killed one third of everybody who got it. And </s><s>[INST] what do you [/INST] think of the </s><s>[INST] here's an intuition maybe it's completely naive and this optimistic intuition I have, which it seems and maybe it's a biased experience that I have. But it seems like the most brilliant people I've met in my life all are really like fundamentally good human beings and not like naive good like they really want to do good for the world in a way that, well maybe is aligned to my sense of what good means. And so I have a sense that the uh, the people that will be defining the very cutting edge of technology, there will be much more of the ones that are doing good versus the ones that are doing evil. So the race optimistic on the US always like last minute coming up with a solution. So if there's an engineered pandemic that has the capability to destroy most of the human civilization, it feels like to me either leading up to that before or as it's going on, there will be uh, were able to rally the collective genius of the human species. I can tell about your smile that you're uh, at least some percentage uh, doubtful. But is that, could that be a fundamental law of human nature that evolution only creates, It creates uh, like karma is beneficial, good is beneficial and therefore will be all right. [/INST] I hope you're right. I would really love it if you're right. If there's some sort of law of nature that says that we always get lucky in the last second because the karma, but you know, I prefer, I prefer not playing it so close and gambling on that. And I think in fact, I think it can be dangerous to have two strong faith in that because it it uh makes us complacent. Like if someone tells you you never have to worry about your house burning down, then you're not going to put in a smoke detector because why would you need to i even if sometimes very simple precautions, we don't take them. If you're like oh the government is going to take care of everything for us, I can always trust my politicians like you know, we have the kid our own responsibility. I think it's a healthier attitude to say, yeah, maybe things will work out. Maybe I'm actually gonna have myself step up and take responsibility. Ah and the stakes are so huge. I mean if we do this right, we can develop all this ever more powerful technology and cure all diseases and create a future where humanity is healthy and wealthy for not just the next election cycle, but like billions of years throughout our universe. That's really worth working hard for. And not just you know, sitting and hoping for some sort of fairytale karma. Well, I </s><s>[INST] just mean, so you're you're absolutely right from the perspective of the individual. Like for me like the primary thing should be to take responsibility and to build the solutions that your skill set allows. [/INST] Yeah, which is a lot. I think we underestimate often very much how much good we can do if if you or anyone listening to this uh is completely confident that our government would do a perfect job on handling any future crisis with engineered pandemics Or future Ai I actually want to be on on what actually happened in 2020. Do you feel that uh government by and large around the world is handled is flawlessly. </s><s>[INST] Uh That's a really sad and disappointing reality. That hopefully is a wake up call for everybody, for the scientists, for the for the for the engineers, for the researchers in ai especially it was disappointing to see how ah inefficient we were at spreading collecting the right amount of data in a privacy preserving way and spreading that data and utilizing that data to make decisions, all that kind of stuff. [/INST] Yeah. I think when something bad happens to me, I made myself, I promised many years ago that I would not be a whiner. So when something bad happens to me of course it's uh yeah to process the disappointment but then I try to focus on what did I learn from this that can make me a better person in the future. And there's usually something to be learned when I fail. And I think we should all ask cause I was what can we learn from the pandemic about how we can do better in the future. And you mentioned there a really good lesson. You know, we were not as resilient as we thought we were and we were not as prepared maybe as we wish we were. You can even see very stark contrast around the planet South Korea. They have over 50 million people. Do you know how many deaths they have from Covid? Last time I checked about 500. Why is that? Well yeah the short answer is that they have prepared. They were incredibly quick, incredibly quick to get on it with very rapid testing and contact tracing and so on. Which is why they never had more cases than they could contract trace effectively. Right? They never even have to have the kind of big lockdowns we had in the west. But the deeper answer to it's not just the Koreans are somehow better people. The reason I think they were better prepared was because they had already had Pretty bad hit from the SARS pandemic or which never became a pandemic. Uh something like 17 years ago I think. So it's gonna kind of fresh memory that you know, we need to be prepared for pandemics. So they were right. And so maybe this is a lesson here for all of us to draw from Covid that rather than just wait for the next pandemic or the next problem with ai getting out of control or anything else? Maybe we should just actually set aside a tiny fraction of our GDP to have people very systematically do some horizon scanning and say okay what are the things that could go wrong and let's duke it out and see which are the more likely ones and which are the ones that are actually actionable and then be prepared. Uh </s><s>[INST] So one of the observations is one little ant slash human that I am of disappointment is the political division over information that has been observed that I observed this year that it seemed uh the discussion was less about uh huh sort of uh what happened in understanding what happened deeply and more about there's different truths out there and it's like an argument. My truth is better than your truth. And it's it's like red versus blue or different. Like it was like this ridiculous discourse that doesn't seem to get at any kind of notion of the true. It's not like some kind of scientific process. Even science got politicized in ways that's very heartbreaking to me. Uh you have an exciting project on the Ai front uh trying to rethink one of the you mentioned corporations, there's one of the other collective intelligence systems that have emerged. All of this is social networks and just to spread the internet is the spread of information on the uh, the internet. Our ability to share that information. There's all different kinds of news sources and so on. And so you said like that's from first Principles. Let's rethink how we think about the news, how we think about information. Can you talk about this amazing effort that you're undertaking? [/INST] Oh, I'd love to, this has been my big covid projects has been nights and weekends on ever since the lockdown the segway into this actually let me come back to what you said earlier that you had this hope that in your experience, people who were you felt very talented or often idealistic and wanted to do good, frankly, I feel the same about all people by and large, there are always exceptions, but I think the vast majority of everybody, regardless of education and what not really are fundamentally good, right? So how can it be that people still do so much nasty stuff? Right. I think it has everything to do with this with the information that we're given. You know, if you go into Sweden 500 years ago and you start telling all the farmers that those danes in Denmark, they're so terrible people, you know, and we have to invade them because they've done all these terrible things that you can't fact check yourself a lot of people Swedes did that, right? And and we've seen we've seen so much of this today in the world, both geopolitically, you know where we are told that that china is bad and Russia is bad and Venezuela is bad and people in those countries are often told that we are bad and we also see it at a micro level. You know, where people are told that all those who voted for the other party are bad people. It's not just an intellectual disagreement, but there bad people and we're getting ever more divided. And so how do you reconcile this with with this intrinsic goodness I people, I I think it's pretty obvious that it has again to do with with information there were fed and given, right? We evolved to live in small groups where you might know 30 people in total, right? So you then had a system that was quite good for assessing who you could trust and who you could not. And if someone told you that, you know joe, there is a jerk, but you had interacted with him yourself and seen him in action and you would quickly realize maybe that that's actually not quite accurate, right? But now that we're the most people on the planet of people who've never met, it's very important that we have a way of trusting the information we're given. And So, okay, so where does the news project come in? Well, throughout history and you can go read Machiavelli, you know, from the 1400s and you'll see how already then they were busy manipulating people with propaganda and stuff. Propaganda is not new at all. And the incentives to manipulate people is just not new at all. What is it? That's new. What's new is machine learning meets propaganda. That's what's new. That's why this has gotten so much worse. You know, some people like to blame certain individuals, like in my liberal university bubble, many people blame donald trump and say it was his fault. I see it differently. I think what donald trump just had this extreme skill at playing this game in the machine learning algorithm age Game, he couldn't have played 10 years ago. So what's changed, what's changes? Well, Facebook and Google and other companies and I don't want, I'm not bad mouthing them. I have a lot of friends who work for these companies, good people, they deployed machine learning algorithms just increase their profit a little bit too just maximize the time people spend watching ads and they had totally underestimated how effective they were going to be. This was again the black box, non intelligible intelligence they just noticed and we're getting more ad revenue great. It took a long time until even realize why and how and how damaging this was for society because of course what the machine learning figured out was that the by far most effective way of gluing you to your little rectangle was to show you things that trigger strong emotions, anger, etcetera, resentment. And uh if it was true or not didn't really matter. It was also easier to find stories that weren't true. You weren't limited. That's just the limitations show people. That's a very limiting fact. And before long we got these amazing filter bubbles on a scale. We have never seen before. A couple of this to the fact that also, um, the online news media was so effective that they killed a lot of print journalism. There's only, there's only less than half as many journalists now in America I believe as there was a generation ago, he just couldn't compete with the online advertising. So all of a sudden most people are not getting even reading newspapers, they get their news from social media and most people only get news in their little bubble. So along comes now some people like Donald trump who figured out among the first successful politicians to figure out how to really play this new game and become very, very influential. But I think that donald trump was a simp. Well, he, he took advantage of it. He didn't create the fundamental conditions were created by machine learning taking over the news media. So this is what motivated my little covid project here. So you know, I said before machine learning and tech in general, it's not evil, but it's also not good. It's just a tool that you can use for good things or bad things. And as it happens, machine learning and news was mainly used by the big players, big tech to manipulate people into watch as many ads as possible boat which had this unintended consequence of really screwing up our democracy into and fragmenting it into filter bubbles. So I thought, well machine learning algorithms are basically free. They can run on your smartphone for free. Also, if someone gives them a way to you right? There's no reason why they only have to help the big guy to manipulate the little guy. They can just as well help the little guy to see through all the manipulation attempts from the big guy. So did this project is called, you can go to improve the news dot org. The first thing we've built is a little news aggregator looks a bit like google news except it has these sliders on it to help you break out or your filter bubble. So if you're reading, you can click, click and go to your favorite topic and then uh, if you just slide the left, right slider away all the way over to the left. There's two sliders, right? Yeah. There's the one of the most obvious one is the one that has left right labels on us. You go to the left, you get one set of articles, you go to the right, you see a very different truth appearing </s><s>[INST] that's literally left and right on the [/INST] political spectrum on the political. So if you're reading about immigration, for example, at it's very, very noticeable. And I think step one always, if you want to not get manipulated is just to be able to recognize the techniques people use. So it's very helpful to just see how they spin things on the two sides. Uh, I think many people are under the misconception that the main problem is fake news. It's not uh, we had an amazing team of MIT students where we did an academic project used machine learning to detect the main kinds of bias over the summer. And yes, of course, sometimes there's fake news where someone just claims something that's false right? Like all Hillary clinton just got divorced or something. But what we see much more of is actually just omissions. If you go to uh there's some stories which just won't be mentioned by the left or the right because it doesn't suit their agenda and then they instead mentioned other ones. Very very very much so. For example, we've we've had a lot a number of stories about the trump family's financial dealings. And then there's been some most stories about the biden family's Hunter biden's financial dealings. I surprise surprise they don't get equal coverage on the left and the right. One side loves the cover that biden Hunter biden stuff and one side loves to cover the trump. Never guess which is which right. But the great news is if you want to if you're normal american citizen and you dislike corruption in all its forms then slide slide, you can just get look at both of your sides and you'll see all the corrupt those political corruption stories. </s><s>[INST] It's really liberating to just take in the both sides the spin on both sides. It's somehow unlocks your mind to like think on your own to realize that. But I don't know it's it's the same thing that it was useful right? In the soviet union times for when when everybody was much more aware that they're surrounded by propaganda. It's [/INST] so interesting what you're saying actually. Uh, so Noam chomsky, you know used to be R. M. I. T. Call, like once said that propaganda is to democracy, what violence is two totalitarian ism and and and what he means by that is if you have a really totalitarian government, you don't need propaganda. People will do what you tell them what you want them to do anyway, but out of fear, right? But otherwise you need propaganda. So I would say actually that the propaganda is much higher quality in democracies more believable. And it's it's really it's really striking when I talked to colleagues, Science colleagues like from Russia and china and so on. I noticed they are actually much more aware of the propaganda in their own media than many of my american colleagues are about the propaganda in Western media </s><s>[INST] as brilliant. That means the propaganda in the Western media is better. [/INST] Yes, that's so brilliant better in the West, even the propaganda that but that's good. But when you once you realize that you realize there's also something very optimistic there that you can do about it, right? Because first of all omissions, as long as there's no outright censorship, you can just look at both sides and pretty quickly piece together much more accurate idea of what's actually going on, right? </s><s>[INST] And develop a natural skepticism to the analytical scientific mind about you taking [/INST] information. And I think I have to say sometimes I feel that some of us in the academic bubble are too arrogant about this and somehow think, oh it's just people who aren't as I was educated when we are often just as gullible. Also, you know, we read only our media and and don't see through things, anyone who looks at both sides like this in comparison to what we immediately start noticing the shenanigans being pulled in. And you know, I think what I tried to do with this app is that the big tech has the stomach extent, tried to blame the individual for being manipulated, much like big tobacco, tried to blame the individuals entirely for smoking. And a little later on, you know, our government stepped up and say actually, you know, you can't just blame little kids were starting to smoke, we have to have more responsible advertising and this and that. I think it's a bit the same here, it's very convenient for a big tech to blame. So it's just people who are so dumb and get fooled. The blame usually comes in saying, oh it's just human psychology, people just want to hear what they already believe. But Professor David Randall Emmett actually partly debunked that with a really nice study showing that people tend to be interested and hearing things that go against what they believe if it's presented in a respectful way, like suppose for example that you have a company and you're just about to launch this project and you're convinced it's going to work and someone says, you know, lex, I hate to tell you this, but this is going to fail and here's why would you be like, shut up, I don't want to hear it, would you? You would be interested, right? And also if you're on an airplane back in the pre covid times, you know, and the guy next to you is clearly from the opposite side of the political spectrum, but it's very respectful and polite to you, wouldn't you be kind of interested to hear a bit about how he or she thinks about things of course, but it's not so easy to find out respectful disagreement now because like for example, if you are a democrat and you're like, I want to see something on the other side, you just call Breitbart dot com and then after the 1st 10 seconds you feel deeply insulted by something and they it's not going to work or if you take someone who votes Republican and they go to something on the left and they just get very offended very quickly by them having put a deliberately ugly picture of donald trump on the front page or something, it doesn't really work. So this news aggregator also has this nuance slider which you can pull to the right and then to make it easier to get exposed to actually more academic style or more respectful Mhm portrayals of different views and finally, the one kind of bias I think people are mostly aware of is the left right because it's so obvious because both left and right are very powerful here, right. Both of them have well funded tv stations and newspapers and it's kind of hard to miss. But there's another one the establishment slider which is, is also really fun. I I love to play with it and that's more about corruption because if you have the society mhm. Where almost all the powerful entities, I want you to believe a certain thing. That's what you're going to read. And both the big media, mainstream media on the left and on the right of course and the powerful companies can push back very hard. Like tobacco companies push back very hard back in the day when people, some newspapers started writing articles about tobacco being dangerous. So it was hard to get a lot of coverage about it initially. And also if you look geopolitically right of course in any country, when you read their media, you're mainly going to be reading a lot about articles about how our country is the good guy and the other countries of the bad guys, right? So if you want to have a really more nuanced understanding, you know, like the Germans used to be told that that the british used to be told that the french were the bad guys and the french used to be told that the british were the bad guys now they visit each other's countries a lot and have a much more nuanced understanding. I don't think there's gonna be any more wars between France and Germany but on the geopolitical scale it's just just as much as ever, you know, big cold war now us china and so on. And if you want to, if you want to get a more nuanced understanding what's happening to you politically then it's really fun to look at this establishment slider because it turns out there are tons of little newspapers both on the left and on the right who sometimes challenge establishment and say, you know, maybe we shouldn't actually invade Iraq right now. Maybe this weapons of mass destruction thing is bs if you look at the journalism research afterwards, you can actually see that quickly that both CNN and Fox were very pro, let's get rid of Saddam. There are weapons of mass destruction. Then there were a lot of smaller newspapers. They were like, wait a minute. This evidence seems a bit sketchy. Maybe we but of course they were so hard to find. Most people didn't even know they existed right yet. It would have been better for american national security if those voices had also come up uh I think it harmed America's national security actually that we invaded Iraq </s><s>[INST] and arguably there's a lot more interest in that kind of thinking to from those small sources. So like the when you say big, it's more about kind of uh the reach of the broadcast but it's not big in terms of the interest. I think, I think there's a lot of interest in that kind of anti establishment or like skepticism towards, you know, out of the box thinking there's a lot of interest in that kind of thing. Do you see this uh, news project or something like it being uh, basically taking over the world as the main way we consume information. Like what, how do we get, how do we get there? Like How do we, you know, so, okay, the idea is brilliant. It's your calling your little project in 2020. But how does that become the new way we consume information. [/INST] I hope first of all, there's the plant a little seed there because normally the big barrier of doing anything in media as you need a ton of money, but this costs no money at all. I've just been paying myself pay a tiny amount of money each month to amazon to run the thing in their cloud. We're not, there never will never be any adds. The point is not to make any money off of it and we just trained machine learning algorithms to classify the articles and stuff. So it just kind of runs by itself. So if it actually gets good enough at some point that it started catching on, it could scale and if other people carbon copy and make other versions that are better, that's the more the merrier. I think there's a real opportunity for machine learning to empower the individual against the list of the powerful players. Uh, as I said in the beginning here, it's been mostly the other way around so far that the big players have the ai and then they tell people this is the truth. This is how it is. But it can just as well go the other way around. When the internet was born. Actually, a lot of people have this hope that maybe this will be a great thing for democracy, make it easier to find out about things. And maybe machine learning and things like this can can actually help again. And I have to say, I think it's more important than ever now because this is very linked also to the whole future of life. As we discussed earlier, we're getting this ever more powerful attack, you know, frank. It's pretty clear if you look on the one or two generations, three generations time scale that there are only two ways this can end geopolitically, either it ends great for all humanity or it's terribly for all of us. There's, there's really no in between and we're so stuck in and because you know, technology knows no borders and you can't have people fighting when the weapons just keep getting ever more powerful indefinitely. Eventually looks, the luck runs out And and you know, the right like right now we have, I love America, but the fact of the matter is what's good for America is not opposite in the long term to what's good for other countries. It's it would be if this was some sort of zero sum game. Like it was thousands of years ago when the only way one country could get more resources was to take land from other countries because that was basically the resource. Right? Look at the map of europe. Some countries kept getting bigger and smaller endless wars. But then since 1945 there hasn't been any war in Western Europe and they all got way richer because of tech. So the optimistic outcome is that the big winner in this century is gonna be America and china and Russia and everybody else because technology just makes us all healthier and wealthier and we just find some way of keeping the peace on this planet. Uh But I think unfortunately there are some pretty powerful forces right now. They're pushing in exactly the opposite direction and trying to demonize other countries, which just makes it more likely that this ever more powerful tech we're building is gonna use disastrous ways </s><s>[INST] for aggression versus cooperation. [/INST] That kind of thing. You even look at, look at this military ai now, right, that's 2020 and it was so awesome to see these dancing robots. I loved it. Right? But one of the biggest growth areas in robotics now is of course autonomous weapons. Right? And and 2020 was like the best marketing year ever for autonomous weapons because in both Libya civil war and in Nagorno Karabakh, they made the decisive difference right? And everybody else is like watching this Oh yeah, we want to build autonomous weapons to in Libya, I'm glad you had on one hand our ally the United Arab Emirates that were flying their autonomous weapons that they brought from china bombing libyans. And on the other side you had our other ally Turkey flying their drones. Um they had no skin in the game, any of these other countries and of course there was the libyans who really got screwed in Nagorno Karabakh, you had actually again, so now Turkey is sending drones built by this company that was actually founded by a guy who went to MIT aero astro. Do you know that baccarat? Er Yeah, so um it has a direct responsibility for ultimately this and a lot of civilians were killed there you know? And so because it was militarily so effective now, suddenly there's like a huge push Oh yeah, yeah, let's go build ever more autonomy into these these weapons and it's gonna be great and uh uh huh I think actually and people who are obsessed about some sort of future terminators native scenario right now should start focusing on the fact that we have too much more urgent threats happening for machine learning. One of them is the whole destruction of democracy that we've talked about now where where, where our flow of information is being manipulated by machine learning and the other one is that right now? You know this is the year when the big arms race in out of control arms race and at least thomas weapons is going to start or it's gonna stop. </s><s>[INST] So you have a sense that there is uh Like 2020 was instrumental catalyst for the race of for the autonomous weapons [/INST] race. Because it was the first year when when they proved decisive in the battlefield. Um And these ones are still not fully autonomous. Mostly their remote controlled. Right? But you know, we could very quickly make things about you know the size and cost of a smartphone which you just put in the GPS coordinates or the face of the one you want to kill a skin color or whatever and it flies away and you know does it? And Mhm. The real good reason why the U. S. And all the other superpowers should put the kibosh on. This is the same reason we decided to put the kibosh on bioweapons. So, mhm. You know, we gave the Future of Life award that we can talk more about later. Matthew Meselson from Harvard before for convincing Nixon the band bioweapons. And I asked them, how did you do it? And he was like well I just said look We don't want there to be a $500 weapon of mass destruction that all our enemies can afford. Even non state actors. And Nixon was like good point. You know it's in America's interest that the power of weapons are all really expensive so only we can afford them. Or maybe some more stable adversaries, right? Uh nuclear weapons are like that. But bio weapons were not like that. That's why we banned them. And that's why you never hear about them now. That's why we love biology. </s><s>[INST] So you have a sense that it's possible for the big powerhouses in terms of the big nations in the world to agree that autonomous weapons is not a race we want to be on. That doesn't end well. [/INST] Yeah because we we know it's just gonna end in mass proliferation and every terrorists everywhere is going to have these super cheap weapons they will use against us. Um And and our our politicians have to constantly worry about being assassinated every time they go outdoors by some anonymous little mini drone. You know we don't want that. And if even if the U. S. And china and everyone else could just agree that You can only build these weapons if they cost at least $10 million bucks that would that would be a huge win for the superpowers. And frankly for everybody. Uh the you don't and people often push back and say well it's so hard to prevent cheating but hey you can say the same about bio weapons. You know take any of your mighty colleagues and biology of course they could build some nasty bioweapon if they really want to do. But first of all they don't want to because I think it's disgusting because of the stigma. And second even if there's some sort of nutcase and want to, it's very likely that some of their grad students or someone would rat them out because everyone else thinks it's so disgusting way. And in fact we now know there was even a fair bit of cheating on the bioweapons bad, but none, no countries used them because it was so stigmatized that it just wasn't worth revealing that they had cheated. </s><s>[INST] You talk about drones, but you kind of think the drones is the remote operation, [/INST] which they are mostly. </s><s>[INST] Yes, but you're not taking the next intellectual step of like where does this go? You're kind of saying the problem with drones is that you're removing yourself from the direct violence, therefore you're not able to sort of maintain the common humanity required to make the proper decision strategically. But that's the criticism as opposed to like if this is automated and just exactly as you said, if you automate it and there's a race, then it's going to technology get better and better and better, which means getting cheaper and cheaper and cheaper and unlike perhaps nuclear weapons, which is connected to resources in a way like it's hard to get the, [/INST] it's hard to engineer. </s><s>[INST] Yeah. It feels like it's, you know, um there's too much overlap between the tech industry and autonomous weapons, the way you could have smartphone type of uh cheapness [/INST] if you look at </s><s>[INST] Drones, uh you know, it's a it's a you know, for $1,000, you can have an incredible system that's able to maintain flight autonomously for you and take pictures and stuff. You can see that going into the autonomous weapon space. That's um But like why is that not thought about or discussed enough in the public? Do you think you see those dancing boston dynamics robots and everybody has this kind of um like as if this is like a far future, they have this like fear like oh this will be terminator in like some, I don't know, unspecified 2030 40 years and they don't think about, well this is like some much less dramatic version of that is actually happening now. It's not going to have, it's not going to be legged, it's not going to be dancing, but it's it's already has the capability to use artificial intelligence to kill humans. [/INST] Yeah, the boston dynamics, like robots. I think the reason we imagine them holding guns is just because we've all seen Arnold Schwarzenegger, right? That's a reference point that's pretty useless. That's not going to be the main military use of them, They might be useful in in law enforcement in the future. And and there's a whole debate about you want robots showing up at your house with guns telling you to uh who will be perfectly obedient to whatever dictator controls. But let's leave that aside for a moment and look at what's actually relevant now. So there's a spectrum of things you can do with ai in the military. And again, to put my cards on the table. I'm not the pacifist. I think we should have good defense. So for example, a predator drone is a room, basically a fancy little remote controlled airplane. Right? There's a human can piloting it. And the decision ultimately about whether to kill somebody with it is made by a human still. And this is a line I think we should never cross. There's a current GOP policy. Again, you have to have a human in the loop. I think algorithms should never make life or death decisions. They should be left to humans. Um Now, why might we cross that line? Well, first of all these are expensive. Right? So for example, when when uh, when when I said that jOHn had all these drones and I mean I didn't have any. They started trying to jerry rig little cheap things fly around and but then of course the meetings were jammed them. No, the jazz areas would jam them and remote control things can be jammed. That makes them inferior. Also there's a bit of a time delay between, you know, if we're piloting something far away speed of light and the human has a reaction time as well. It would be nice to eliminate that jamming possibility in the time today by having it fully autonomous. But now you might be so then if you do, but now you might be crossing that exact line, you might program it just oh yeah the air drone go hover over this country for a while and whenever you find someone who is a bad guy, you know, kill them. Now the machine is making these sort of decisions. And you and some people who defend this still say, well that's morally fine because we are the good guys and we will tell it the definition of bad guy that we think is moral. But now it will be very naive to think that if ISIS buys that same drone that they were going to use our definition of bad guy. Maybe for them. Bad guy is someone wearing a U. S. Army uniform or maybe maybe there will be some we we are uh ethnic group who decides that someone of another ethnic group, they're the bad guys, right? The thing is human soldiers with all our faults, right? We still have some basic wiring in us. Like no it's not okay to kill kids and civilians and thomas weapon has none of that, it's just going to do whatever it's programmed. It's like the perfect out of iceman on steroids. Like they told him out of Eichmann, you know, he wanted to do this and this and this to make the holocaust more efficient and he was like yeah and off he went and did it right. Do we really want to make machines that are like that? Like completely Amoral and we'll take the user's definition of who is the bad guy And do we then want to make them so cheap that all our adversaries can have them? Like what could possibly go wrong? That's the that's I think the big arguments for why we want to this year really put the kibosh on this. And I think you can tell there's a lot of very active debate even going on within the U. S. Military and undoubtedly in other militaries around the world also about whether we should have some sort of international agreement to at least require that these weapons have to be above a certain size and cost you know, so that from um things just don't totally spiral out of control them. And finally just for your question but is it possible to stop it because some people tell me, oh just give up. You know? But again so so Matthew Meselson again from Harvard right, who the bioweapons hero? He had exactly this criticism Most of the bioweapons people were like how can you check for sure that the Russians aren't cheating and he he told me this I think really ingenious insight. He said you know max some people think you have to have inspections and things. You have to make sure that people you can catch the cheaters with 100% chance. You don't need 100%. He said 1% is usually enough because if it's just an enemy if it's another big state like suppose china and the US have signed the treaty limit drawing a certain line and saying yeah these kind of drones are okay but these fully autonomous ones are not. I suppose you are china and you have cheated and secretly developed some clandestine little thing or you're thinking about doing it. You know what's your calculation that you do? Well you're like okay what's the probability that we're gonna get caught? Okay? If they're probably 100% of course we're not gonna do it. But if the probability is 5% that we're gonna get caught and it's gonna be like a huge embarrassment for us and it doesn't have its we still have our nuclear weapons anyway. So it doesn't really uh make an enormous difference in terms of deterring the US. You know </s><s>[INST] and that feeds the stigma that you kind of established like this fabric. This universal stigma [/INST] over the thing. Exactly. It's very reasonable for them to say well you know we could probably get away with it but if we don't then the U. S. Will know we cheated and then they're gonna go full tilt with their program and say look the chinese are cheaters and that's going to now we have all these weapons against us and that's bad. So The Stigma alone is very very powerful. And again look what happened with bioweapons right? It's been 50 years now. When was the last time you read about a bioterrorism attack? The only deaths I really know about with bio weapons that have happened when we americans managed to kill some of our own with anthrax. You know the idiot who sent them to Tom Daschle and others and letters, right? And similarly the in uh Sadlowski in the soviet union they had some anthrax in some lab there. Maybe they were cheating or who knows? And it leaked out and killed a bunch of Russians I'd say that's a pretty good success right? 50 years. Just two own goals by the superpowers. And then nothing. And that's why whenever I ask anyone what they think about biology, they think it's great the associated with new cures to diseases may be a good vaccine. This is how I want to think about ai in the future. I want and I want others to think about ai to as a source of all these great solutions to our problems. Not as oh hey I oh yeah that's the reason I feel scared going outside these days. </s><s>[INST] Yes it's kind of brilliant that bio weapons and nuclear weapons we figured out. I mean of course there's still a huge source of danger. But we figured out some way of creating rules and social stigma over these weapons that then creates a stability toward whatever that game theoretic stability there, of course. And we don't have that with ai and you're kind of screaming from the top of the uh the mountain about this, that we need to find that because just like, you know, it's very possible, you know, with the future of life, as you point out, institute awards pointed out that, uh, you know, with nuclear weapons, we could have destroyed ourselves quite a few times. And it's uh, you know, it's it's a learning experience that doesn't is very costly. [/INST] We gave, you know, this future life award. We gave it the first time to describe Vasili Arkhipov. You know, he was on. Most people haven't even heard of, can you say who he is? Vasili Arkhipov? He uh has, in my opinion, made the greatest positive contribution to humanity of any human in modern history. And maybe it sounds like hyper bowl here, like I'm just over the top. But let me tell you the story. And I think maybe you'll agree. So, during the Cuban missile crisis, we americans first didn't know that the Russians had sent four submarines, but we caught two of them and we didn't know that. So we drop practice depth charges on the one that he was on trying to force it to the surface. But we didn't know that this nuclear submarine actually was a nuclear submarine with a nuclear torpedo. We also didn't know that they had authorization to launch it without clearance from Moscow. And we also didn't know that they were running out of electricity. Their batteries are almost dead. They were running out of oxygen. Sailors were fainting left and right. The temperature was about 110 120. Fahrenheit on board, it was really hellish conditions, really just kind of doomsday. And at that point, these giant explosions start happening from the americans dropping these, the captain thought were worth. We had begun. They decided that we're going to launch the nuclear torpedo. And one of them shouted, you know, we're all gonna die. But we're not going to disgrace our navy. You know, we don't know what would have happened if they had to build a giant mushroom cloud all of a sudden, you know, against americans. But since everybody had their hands on the triggers, pretty you don't have to be too creative to think that it could have led to an all out nuclear war, in which case we wouldn't be having this conversation now. Right. But actually took place was They needed three people to approve this. The captain had said, yes, there was the Communist Party political officer. He also said, yes, let's do it. And the third man was this guy, Vasili Arkhipov, who said, and yet, uh, for some reason, he was just more chill than the others. And he was the right man at the right time. I don't want us as a species, rely on the right person being there at the right time. You know, uh we tracked down his family living in relative poverty outside Moscow maybe flew his daughter, he had passed away, uh flew into London. They had never been to the west even. It was incredibly moving to get to honor them for this. Uh the next year we gave this future life award to stanislav Petrov. Have you heard of him? So he he was in charge of the soviet early warning uh station, which It was built with Soviet technology and honestly not that reliable. It said that there were five US missiles coming in again, if they had launched at that point, he probably wouldn't be having this conversation. He decided, mhm. Based on just mainly gut instinct to just not tell not not escalate this. And I'm very glad he wasn't replaced by an ai that was just automatically following orders. And then we gave the third one to Matthew Meselson last year, we gave us the word too to these guys who actually use technology for good. Not avoiding something bad, but for something good. The guys who eliminated this disease, which is way worse than Covid that had killed half a billion people in the it's violent century. Smallpox. Right? So you mentioned it earlier. Covid On average kills less than 1% of people who get smallpox about 30%. And they used ultimately Viktor Zhdanov and Bill Faggy. Most of my colleagues have never heard of either of them. one American 1 Russian, they did this amazing effort, not only where it was gonna be able to get the U. S. And the soviet union to team up against smallpox during the Cold War, but Bill Fagih came up with this ingenious strategy for making it actually go all the way to defeat the disease With without funding for vaccinating everyone. And as a result, we haven't had any, we went from 15 million deaths the year I was born in smallpox. So what are we having Covid now, a little bit short of two million. Right, 2 0 deaths of course this year and forever There have been 200 million people estimate who would have died since then by smallpox had it not been for this. So isn't science awesome when you use it for good. And I was the reason we want to celebrate these sort of people is to remind them of this science is so awesome when you use it for good. </s><s>[INST] And those uh those awards actually uh the variety there. But it's a very interesting pictures. So the first two are looking at, it's kind of exciting to think that these these average humans in some sense, there are products of billions of other humans that came before them evolution. And some little you said gut, you know, but there's something in there that that uh stopped the annihilation of the human race and that's a magical thing. But that's like this deeply human thing. And then there's the other aspect where that's also very human which is to build solution to the to the existential crisis that we're facing. Like to build it to take the responsibility to take come up with different technologies and so on. And both of those are deeply human, the gut and and the mind [/INST] whatever that is like the best is when they work together are keep of I wish I could have met him of course, but he had passed away. He was really a fantastic military officer combining all the best traits that we in America admire in our military because first of all he was very loyal. Of course, he never even told anyone about this during his whole life. Even though you think he had some bragging rights, right? But he just was like this is just business, just doing my job. It only came out later after his death. And second the reason he did the right thing was not because he was some sort of liberal or some sort of not because he was uh just oh you know, uh peace and love. It was partly because he had been the captain on another submarine that had a nuclear reactor meltdown and it was his heroism that help contain this. That's why he died of cancer later also. But he has seen many of his crew members die. And I think for him that gave him this gut feeling that you know, if there's a nuclear war between the US and the soviet union, the whole world is going to go through what I saw, my dear crew members suffer through. It wasn't just an abstract thing for him. I think it was real. And second though, not just got the mind right? He he was, for some reason very level headed personality and very smart guy, which is exactly what we want Our best fighter pilots to be. Also, I never forget Neil Armstrong when he's landing on the moon and almost running out of gas. And he doesn't even change really say 30 seconds, doesn't even change. The tone of voice just keeps going. Arkhipov I think was just like that. So when the explosions started going off and his captain is screaming and we should nuke them and and all. He's like, I don't think the americans are trying to sink us. I think they're trying to send us a message that's pretty badass coolness because he said, if they wanted to sink us. No, and he said, listen, listen, it's alternating one loud explosion on the left, one on the right, one on the left, one on the right. He was the only one to notice this pattern. And it is like, I think this is I'm trying to send us a signal that they wanted to surface, they're not going to sink us. Uh and somehow, yeah, this is how he then managed it ultimately with his combination of gut and also this cool analytical thinking was able to de escalate the whole thing and uh yeah, so this is some of the best in humanity, I guess coming back to what we talked about earlier is the combination of the neural network, the instinctive, you know, with, with I'm getting the tearing up here, getting emotional, but he was just, he is one of my superheroes come having both like heart, you know, and the mind combined and especially </s><s>[INST] in that time. Uh there's something about the, I mean this is a very in America, people are used to this kind of idea of being the individual um of like on your own thinking. Yeah, I think under in the soviet, union and communism is it's actually much harder [/INST] to do that. Oh yeah, he didn't even, he even got, he didn't get any accolades either when he came back for this, right? Uh they just wanted to hush the whole thing up. </s><s>[INST] There's echoes of that which are noble. There's all kinds of uh that's one that's that's a really hopeful thing that amidst big centralized powers, whether it's companies or states, there's still the power of the individual to think on their own to [/INST] act, but I think we need to think of people like this, not as a panacea, we can always count on, but rather as Yeah, I wake up call, you know, because of them because of Arkhipov, we are alive to learn from this lesson, to learn from the fact that we shouldn't keep playing Russian roulette and almost have a nuclear war by mistake now and then, because relying on look is not a good long term strategy. If you keep playing Russian roulette over and over again, the probability of surviving just drops exponentially with time. And if you have some probability of having an accidental nuclear every year, the probability of not having one also drops exponentially. I think we can do better than that. So I think the message is very clear that once in a while she it happens and there's a lot of very concrete things we can do to reduce the risk of things like that happening in the first place </s><s>[INST] on the ai front, if we could just link on effort for a second. Uh so your friends with you often talk with you a mosque history, uh did a lot of interesting things together. Um He has a a set of fears about the future of artificial intelligence. A. G I do you have a sense we've already talked about the things we should be worried about with a I do have a sense of the shape of his fears in particular about ai of the which subset of what we've talked about, whether it's creating, you know, it's that direction of creating sort of these giant competition systems that are not explainable, they're not intelligible intelligence, or is it um is it the and then like as a branch of that, is that the manipulation by big corporations of that or individual evil people to use that for destruction or the unintentional consequences? Do you have a sense of where his thinking is on this [/INST] from my many conversations with Dylan? Yeah, I certainly have a model of how how how he thinks. It's actually very much like the way I think also I'll elaborate a little bit. I just want to push back on when you said evil people, I I don't think it's very helpful contact concept evil people. Sometimes people do very very bad things, but they usually do it because they think it's a good thing because somehow other people have told them that that was a good thing or given them incorrect information or or whatever, right? Um uh I have to believe in the fundamental goodness of humanity. That if we educate people well and they find out how things really are, people generally wanted to do good and be good. </s><s>[INST] Hence the value alignment. Of [/INST] course it's it's </s><s>[INST] about information about knowledge and then once we have that we'll uh we'll likely be able to uh do good in a way that's aligned with everybody else who [/INST] thinks Yeah. And it's not just the individual people we have to align. So we don't just want people to be educated to know the way things actually are and treat each other well. But we also need to align other nonhuman entities. We talked about corporations, there has to be institutions so that what they do is actually good for the country they're in and we should align to make sure that what countries do is actually good for, you know, the species as a whole etcetera. Coming back to L. A. On my my my uh understanding of how Ellen sees this is really quite similar to my own, which is one of the reasons I like him so much and enjoy talking with him so much. I think he's quite different from most people in that he thinks much more than most people about the really big picture. Not just what's going to happen in the next election cycle, but Millennia millions and billions of years from now, right? And if you when you look in this more cosmic perspective, it's so obvious. So we're gazing out into this universe that as far as we can tell is mostly dead, with with life being uh almost imperceptibly tiny perturbation. Right? And and he sees this enormous opportunity for our universe to come alive for us to become an interplanetary species mars is obviously just first stop on this cosmic journey. And precisely because he thinks more long term, it's much more clear to him than to most people that what we do with this Russian roulette thing. We keep playing with our nukes is a really poor strategy. Really reckless strategy and also that that we're just building these ever more powerful ai systems that we don't understand. It's also it's a really reckless strategy. I feel Ellen is very much a humanist in the sense that he wants an awesome future for humanity. He wants it to be us that control the machines rather than the machines that control us. You know, And why shouldn't we insist on that they were building them after All right. Why should we build things that just make us into some little cog in the machinery that has no further say in the matter right? It's not my idea of inspiring future either. </s><s>[INST] Yeah. The if if you think on the cosmic scale, in terms of both time and space so much is put into [/INST] perspective whenever I have a bad day, that's what I think about it immediately makes you feel better. What it makes </s><s>[INST] me sad that for us, individual humans, at least for now the right ends too quickly, we don't get experience the cosmic [/INST] scale. Yeah. I mean I think of our universe sometimes as an organism that has only begun to wake up a tiny bit just like when you're in the very first little glimmers of consciousness you have in the morning when you start coming around with the coffee before the coffee even before you get out of bed before you can open your eyes start start to wake up a little bit, you know there's something here, you know uh that's very much how I think of but we are you know those all those Galaxies out there, you know, I think they're really beautiful, but why are they beautiful? They're beautiful because conscious entities are actually observing them, experiencing them through our telescopes. If I, you know, I define consciousness as subjective experience, whether it be colors or emotions or sounds. So beauty is an experience, meaning is an experience purposes and experience. If there was no conscious experience of observing these Galaxies, they wouldn't be beautiful if we do something dumb with advanced ai in the future here and earth originating life goes extinct and that was it for this. If there is nothing else with telescopes in our universe then it's kind of game over for me, beauty and meaning and purpose in the whole universe. And I think that would be just such an opportunity lost frankly. And I think okay, when Ellen points this out, he gets very unfairly maligned in the media for all the dumb media bias reasons we talked about right. They want to print precisely the things about Ellen out of context that are really click baby, like he has gotten so much flack for this summoning the demon statement Yeah, I happen to know exactly the context cause I was in the front row when he gave that talk. He was at MIT. You'll be pleased to know is the aero astro anniversary They had Buzz Aldrin there from the moon landing, whole house crazy auditorium packed with MIT students and he had this amazing Q and A. It might have gone for an hour and they talked about rockets and mars and everything at the very end. This one student was actually hit my class asked before about Ai. Ellen makes this one comment and they take this out of context print that goes viral or is it like with </s><s>[INST] Ai we're summoning the [/INST] demon something like that and try to cast him as some sort of doom and gloom dude, you know you know Ellen that he's not the doom and gloom dude, he he is such a positive visionary and the whole reason he warns about this is because he realizes more than most what the opportunity cost is of screwing up that there is so much awesomeness in the future that we can, we can and our descendants can enjoy if we don't screw up right? I get so piste off when people try to cast him as some sort of technophobic Luddite and and at this point is kind of ludicrous when I hear people say that people who worry about artificial general intelligence, our love bites because of course you look more closely, you have some of the more outspoken people making warnings are people like Professor Stuart russell from Berkeley who's written the best selling ai textbook, you know claiming that he is a Luddite who doesn't understand ai is the joke is really on the people who said it. But I think more broadly this message is really not sunk in at all what it is that people worry about. They think that Ellen and Stuart Russell and others are worried about the dancing robots picking up an A. R. 15 and going on a rampage, right? They think they're worried about robots turning evil. They're not I'm not, the risk is not malice, its competence. The risk is just that we build some systems that are incredibly competent, which means they're always going to get their goals accomplished even if they clash with our goals. That's the risk. Why did we humans, you know, drive the west african black rhino extinct. Is it because we're malicious, evil rhinoceros haters. No, it's just because our goals didn't align with the goals of those rhinos and tough luck for the rhinos. You know? So what I'm what the point is just we don't want to put ourselves in the position of those right? I was creating these something more powerful than us. If we haven't first figured out how to align the goals and I am optimistic. I think we could do it if we worked really hard on it because I spent a lot of time around intelligent entities. They were more intelligent than me. my mom and my dad and I was little and that was fine because their goals were actually aligned with mine quite well. But uh we've seen today many examples of where the goals of our powerful systems are not so aligned. So those click through optimization algorithms that are polarized social media, right? They were actually pretty poorly aligned with what was good for democracy, it turned out. And again, almost all problems. We've had the machine learning again came so far not from malice but from poor alignment. And it's that's exactly why that's why we should be concerned about in the future. Do </s><s>[INST] you think it's possible that was those systems like neuralink and brain computer interfaces? You know? Again, thinking of the cosmic scale, you always talked about this, but others have as well throughout history of figuring out how the exact mechanism of how to achieve that kind of alignment. So one of them is having a symbiosis with Ai which is like coming up with clever ways where we're like stuck together in this weird relationship, whether it's biological or in some kind of other way. Do you do you think there's that's a possibility of having that kind of somebody else's or do we want to instead kind of focus on this uh distinct entities of us, humans talking to these intelligible, self doubting eyes. Maybe like Stuart russell thinks about it like these these were were self doubting and full of uncertainty and have our Ai systems that are fallen star, do we communicate back and forth and in that way, achieve somebody else's? [/INST] I honestly don't know, I would say that because we don't know for sure what if any of our which of any already has will work, but we do know that if we don't, I'm pretty convinced that if we don't get any of these things to work and just barge ahead, then our species is, you know, probably going to go extinct this century. I think this </s><s>[INST] century, you think like you think we're facing this crisis is the 21st century crisis. Like this century will be remembered for [/INST] a hard drive? </s><s>[INST] A hard drive somewhere or or maybe by future generations is like, like there will be future Future of Life Institute Awards for people that have done something about ai [/INST] it could also end even worse whether it's we're not superseded by leaving any Ai behind. Either way, we just totally wipe out. You know, like on easter Island are centuries long. No, there are still 79 years left of it, Right? Think about how far we've come just in the last 30 years so we can talk more about what might go wrong. But you asked me this really good question about what's the best strategy? Is that newer link or Russell's approach or whatever. I think um you know when we when we did the Manhattan project, we didn't know if any of our four ideas for enriching uranium and getting out the uranium 2 35 we're going to work. But we felt this was really important to get it before Hitler did. So, you know what we did. We tried all four of them here. I think it's it's analogous where there's the greatest threat that's ever faced our species. And of course the U. S. National security by implication, we don't know if we don't have any method that's guaranteed to work, but we have a lot of ideas so we should invest pretty heavily in pursuing all of them with an open mind and hope that one of them at least works. These are the good news is the century is long. You know, and it might take decades until we have artificial general intelligence. So we have some time hopefully. But it takes a long time to solve these very, very difficult problems. It's going to actually be the it's the most difficult problem we're ever trying to solve as a species. So we have to start now. So we don't have rather than, you know, begin thinking about it the night before. Some people who had too much red bull switching on. And we have to coming back to your question. We have to pursue all of these different avenues and see </s><s>[INST] if you are my investment adviser and I was trying to invest in the future, how do you think the human species is most likely to destroy itself in this century? Uh, yeah. Uh, so if if the crises, many of the crisis we're facing a really before us within the next 100 years, how do we uh, make explicit the make known the the unknowns and solve those problems to avoid the biggest, um, starting with the biggest existential [/INST] crisis as your investment advisor, How are you planning to make money on us destroying ourselves? I have to ask. </s><s>[INST] I don't know. It might be the Russian origins somehow involved [/INST] At the micro level of detailed strategies. Of course this is these are unsolved problems for Ai alignment. We can break it into three p sub problems that are all unsolved. I think you know, you want first to make machines understand our goals, then adopt our goals and then retain our goals. So to hit on all three real quickly. The problem when Andreas Lubitz told his autopilot to fly into the ALPS was that the computer didn't even understand anything about his goals, right? It was too dumb. It could have understood actually, but we would have had to put some effort in as a systems designer, don't fly into mountains. So that's the first challenge. How do you how do you program into computers? Human values, human goals. We can start rather than than saying, oh it's so hard, we should start with the simple stuff as I said, self driving cars, airplanes just put in all the goals that we all agree on already and then have a habit of whenever machine gets smarter so they can understand one level higher goals, you know, put them into, uh, the second challenge is getting them to adopt the goals. It's easy for situations like that where you just program it in. But when you have self learning systems like Children, you know, any parent knows that the there is a difference between getting our kids to understand what we want them to do and to actually adopt our goals right with, with humans with Children, fortunately they, they go through this phrase first, they're too dumb to understand what we want our goals are. And then they have this period of some years when they're both smart enough to understand them and malleable enough that we have a chance to raise them well and then they become teenagers come too late. But we have this window with machines, the challenges, they might, the intelligence might grow so fast at that window, it's pretty short. So that's a that's a research problem. The third one is how do you make sure they keep the goals? If they keep learning more and getting smarter? Many sci fi movies are about how you have something which initially was a line. But then things kind of go off, he'll and, you know, my kids were very, very excited about their legos when they were little. Now they're just gathering dust in the basement. You know, if we put if we create machines that are really on board with the goal of taking care of humanity, we don't want them to get as bored with us. And as my kids go with legos, so this is another research challenge. How can you make some sort of recursive, self improving system, retain certain basic goals? </s><s>[INST] That said, a lot of adult people still play with legos, so maybe we succeeded with the legos. [/INST] I like your optimists, but not all </s><s>[INST] AI systems have to maintain the goals, right? Something just some fraction. [/INST] Yeah. So there, so there's a there's a lot of talented Ai researchers now who I've heard of this and want to work on it. Not so much funding for it yet. Uh of the billions that go into building a I'm more powerful. It's only a minuscule fraction so far going into the safety research, my attitude is generally we should not try to slow down the technology, but we should greatly accelerate the investment in this sort of safety research. Um and also makes it's been this was very embarrassing last year, but, you know, the NSF decided to give out the six of these big institutes. We got one of them for A I and Science, you asked me about another one was supposed to be a I safety research and they gave it people studying oceans and climate and stuff like Yeah, so I'm all for starting oceans in climates, but we need to actually have some money that actually goes into a safety measure. It's also and doesn't just get grabbed by whatever uh that's a fantastic investment. And then at the higher level you ask this question, okay, what can we do? You know, what are the biggest risks? I think? I think we cannot just consider this to be only a technical problem again, because if you solve only the technical problem, can I play with your robot? Get our machines, you know, to just blindly obey the orders we give them so we can always trust that it will do what we want, that might be great for the owner of the robot that might not be so great for the rest of humanity. If if that person is at least favorite world leader or whatever you imagine, right? So we have to also take a look at the apply alignment, not just two machines, but to all the other powerful structures. That's why it's so important to strengthen our democracy. Again, as I said, to have institutions, make sure that the playing field is not rigged, so that corporations are given the right incentives to do the things that both make profit and are good for people, uh to make sure that countries have incentives to do things that are both good for their people and don't screw up the rest of the world. And this is not just something for ai nerds, you know, to geek out on this is an interesting challenge for political scientists, economists and so many other thinkers. </s><s>[INST] So one of the magical things that perhaps makes him this earth quite unique is that it's home to conscious beings. So you mentioned consciousness perhaps is a small aside because we didn't really get specific to what, how we might do the alignment. Like you said, it's just a really important research problem. But do you think engineering consciousness into AI systems, this is a possibility. Is something that we might one day do or is [/INST] there something </s><s>[INST] fundamental to consciousness that is uh is there something about consciousness that is fundamental to humans and humans only? [/INST] I think it's possible. I think both consciousness and intelligence are information processing, certain types of information processing and that fundamentally it doesn't matter whether the information is processed by carbon atoms in the neurons and brains or by silicon atoms and so on in our technology. Yeah, some people disagree. This is what I think is a physicist and I uh </s><s>[INST] that consciousness is the same kind of you said consciousness is information processing, so meaning. You know, I think you had a quote or something like it's information ah knowing itself, that kind [/INST] of thing. I think consciousness, yeah. Is the way information feels when it's being processed, was people that makes ways we don't know exactly what those complex ways are. It's clear that most of the information processing in our brains does not create an experience, we're not even aware of it, right? Like for example, you're not aware of your heartbeat regulation right now, even though it's clearly being done by your body, right? It's just kind of doing its own thing when you go jogging. There's a lot of complicated stuff about how you put your foot down. We know it's hard. That's why robots used to fall over so much. But you're mostly unaware about it. Your brain just your ceo consciousness module. Just send an email. Hey, you know, I want to keep drawing along this path. The rest is on autopilot, right? Uh so most of it is not conscious, but somehow there are some of the information processing which is, we don't know what what exactly. I I think this is a science problem that I hope one day we'll have some equation for something. So we can be able to build a consciousness detector and say, yeah, here there is some consciousness here. There's not, oh don't boil that lobster because it's feeling pain or it's okay because it's not feeling pain right now, we treat this as sort of just metaphysics. Um but it will be very useful in emergency rooms to know if a patient has locked in syndrome and is conscious or if they are actually just out and in the future if you build a very, very intelligent helper robot to take care of you. You know, I think you'd like to know if you should feel guilty about shutting it down or or if it's just like a zombie going through the motions like a fancy tape recorder, right? And and once we can make progress on the science of consciousness and figure out what is conscious and what isn't, then we assuming we want to create positive experiences and not suffering will probably choose to build some machines that are deliberately unconscious that do you know, incredibly boring, repetitive jobs in a iron mined somewhere or whatever and maybe we'll cruise choose to create helper robots for the elderly that are conscious so so that people don't just feel creeped out that you know, the robot is just faking it when it acts like it's sad or happy. Okay. Said </s><s>[INST] elderly, I think everybody gets pretty deeply lonely in this world. And so there's a place I think for everybody to have a connection with conscious beings, whether they're human or otherwise, [/INST] but I know for sure that I would, if I had a robot, if I was going to develop any kind of personal emotional connection with it, I would be very creeped out if I knew it in intellectual level that the whole thing was just a fraud, you know, today you can buy little talking doll for a kid which will say things and the little child will often think that this is actually conscious and even real secrets to it that then go on the internet with lots of the creepy repercussions, you know, I would not want to be just hacked and tricked like this. If I was going to be developing real emotional connections with the robot, I would want to know that this is actually real, it's acting conscious, acting happy because it actually feels it and I think this is not sci fi, I think </s><s>[INST] it's possible to measure to come up with tools and they have to understand the science of consciousness you're saying is we'll be able to come up with tools that can measure consciousness and definitively say like this thing is experiencing the things it says, it's [/INST] experiencing kind of by definition, if it is a physical phenomena, information processing then and we know that some information processing is conscious and some isn't well then there is something there to be discovered with the methods of science Julia Tony has stuck his neck out the farthest and written down some equations for a theory. Maybe that's right, Maybe it's wrong, we certainly don't know. But I applaud that kind of efforts to sort of take this, say this, say this is not just something that philosophers can have beer and muse about, but something we can measure, we can study and coming being that back to us. I think what we would probably choose to do, as I said, is if we cannot figure this out, choose to make to be quite mindful about what sort of consciousness, if any, we put in different machines that we have, we and certainly not, we wouldn't want to make me should not be making much machines that suffer without us even knowing it, right? And if at any point someone decides to upload themselves like Ray Kurzweil wants to do, I don't know if you had him on your show, we agreed. </s><s>[INST] But then Covid happened. So we're waiting it out a [/INST] little bit, you know, supposed to upload himself into this robo ray and it talks like him and act like him and laughed like him. And before he powers off his biological body, he would probably be pretty disturbed if he realized that there's no one home. This robot is not having any subjective experience. Right? If we're if humanity gets replaced by by uh wrote by machine descendants which do all these cool things and build spaceships and go to Intergalactic rock concerts and it turned out it turns out that they were all unconscious just going through the motions. Wouldn't that be like the ultimate uh robot zombie apocalypse, right? Just to play for empty benches. </s><s>[INST] Yeah, I have a sense that there's some kind of, once we understand consciousness, but it will understand that there's some kind of continuum and it would be a greater appreciation and will probably understand just like you said, it would be unfortunate if it's a trick, we'll probably definitely understand that love is indeed a trick they will play on each other, uh that we humans are, we convinced ourselves were conscious, but we're really, um, you know, Austin trees and dolphins are all the same [/INST] kind of costs and try to cheer you up a little bit with a philosophical thought here about the love part. Let's do it. You know, you might say, okay, I love is just a collaboration enabler. Uh, and then you and then maybe you can go and get depressed about that. But I I think that would be the wrong conclusion actually. You know, like I know that the only reason I enjoy food is because my jeans hacked me and they don't want me to starve to death, not because they care about me. It's consciously enjoying succulent delights of pistachio ice cream, but they just they just want me to make copies of them, the whole thing in a sense, the whole the whole enjoyment of food is also a scam like this. But does that mean I shouldn't take pleasure in this pistachio ice cream? I love pistachio ice cream and I can tell you, I, I have, I know this is an expensive fact. I enjoy pistachio ice cream every bit as much, even though I scientific, you know exactly </s><s>[INST] why, what [/INST] Kind of Scam? This 1? </s><s>[INST] Your genes really appreciate that you like the [/INST] pistachio ice cream well, but I, my mind appreciate it too, you know, and I have a conscious experience right now, ultimately all of my brain is also just something the jeans built to copy themselves, but so what, you know, I'm grateful that yeah, thanks jeans for doing this. But you know, now it's my brain that's in charge here, and I'm gonna enjoy my conscious experience, thank you very much. And not just the pistachio ice cream, but also the love I feel for my amazing wife and all the other delights of being conscious. I don't actually Richard Feynman, I think said this so well, he is also the guy who really got me into physics. Uh some art friend said that, oh, science kind of just is the party pooper, It kind of ruins the fun, right? Like you have a beautiful flowers as the artist and then the scientist is gonna deconstruct that into just a blob of quarks and electrons and, and, and fine and pushed back on that in such a beautiful way, which I think also it can be used to push back and make you not feel guilty about falling in love. So, here's what Feynman basically said, he said, his friend, you know? Yeah, I can also, as a scientist, see that this is a beautiful flower, thank you very much. Maybe I'm I can't draw as good at painting as you because I'm not as talented an artist. But yeah, I can really see the beauty in it and it just, it also looks beautiful to me. But in addition to that, Feynman said as a scientist? I see even more beauty that the artist did not see, right? I suppose this is a flower on a blossoming apple tree. You can say this tree has more beauty in it. Then there's the colors and the fragrance. This tree is made of air. Fireman wrote, this is one of my favorite feynman quotes ever, and it took the carbon out of the air and bounded in using the flaming heat of the sun. You know, turn air into a tree. And when you burn log in your fireplace, it's really beautiful to think that this is being reversed. Now the tree is going, the wood is going back into the air and then this flaming beautiful dance of the fire that the artists can see is the flaming light of the sun that was bound in to turn the air into a tree and then the ashes is the little residue that didn't come from the air that the tree sucked out of the ground. You know, Feynman said, these are beautiful things and science just adds, it doesn't subtract. And I feel exactly that way about love and about pistachio ice cream also, I can understand that and even there is even more nuanced to the whole thing right at this very visceral level. You can fall in love just as much as someone who knows nothing about neuroscience. But you can also I appreciate this even greater beauty in it. Just like isn't it remarkable that it came about from from this completely lifeless universe. Just a bunch of hot blob of plasma expanding. And then over the eons, you know gradually first the strong nuclear force decided to combine quirks together into nuclei and then the electric force bounding electrons and atoms and then they clustered from gravity and you've got planets and stars and this and that. And then natural selection came along and the genes had their little thing and you started getting what went from seeming like a completely pointless universe that we're just trying to increase entropy and approach heat death into something that looked more goal oriented. Isn't that kind of beautiful. And then this goal oriented this revolution got ever more sophisticated where you've got ever more and then you started getting this thing which is kind of like deep mines um mu zero and steroids self the ultimate self play is not what what deepmind ai does against itself to get better at go. It's what all these little quirk blobs did against each other in the game of survival of the fittest. Now when you had really dumb bacteria living in a simple environment there wasn't much incentive to get intelligent but then the life made more and more complex and then there was more incentive to get even smarter and and that gave the other organisms more incentive to also get smarter and then here we are now just like, like mu zero learned to become world master at at the go and chess from playing against itself by just playing against itself, all the quirks here on our planet. And electrons have created giraffes and elephants and humans. As I just find that really beautiful. And I mean, that just adds to the enjoyment of of love. It doesn't subtract anything. Do you feel a little more? I feel way </s><s>[INST] better. That was that was incredible. So that this self play of quirks taking back to the beginning of our conversation a little bit. There's so many exciting possibilities about artificial intelligence. Understanding the basic laws of physics. Do you think ai will help us unlock? There's been quite a bit of excitement throughout the history of physics. Of coming up with more and more general, simple laws that explain the nature of our reality. And then the ultimate of that will be a theory of everything that combines everything together. Do you think it's possible that, well, one we humans, but perhaps AI systems will figure out a theory of physics that unifies all the laws of physics. [/INST] Yeah, I think it's absolutely absolutely possible. I think it's it's very clear that we're going to see great boost to science. We're already seeing a boost actually from from machine learning, helping science alpha fold was an example. You know, decades old protein folding problem. So. And and gradually. Yeah. Unless we go extinct by doing something dumb like to discuss, I think it's uh very likely that our understanding of physics will become so good that our technology will no longer be limited by human intelligence, but instead be limited by the laws of physics. So our tech today is limited by what we've been able to invent, right? I think as I I progresses, it will just be limited by the speed of light and other physical limits, which would mean it's going to be just dramatically beyond where we are now. </s><s>[INST] Do you think it's a fundamentally mathematical pursuit of trying to understand like the laws of the governing our universe? From a mathematical perspective, it's almost like if it's a i it's exploring the space of like theorems and those, those kinds of things. Or is there some other uh is there some other more computational ideas, more sort of empirical ideas? [/INST] They're both. I would say it's really interesting to look out at the landscape of everything we call science today. So here you're coming out with this big new hammer says machine learning on it and ask, you know, where are there some nails that you can help with here that you can hammer ultimately. If machine learning gets the point that it can do everything better than us, is we'll be able to help across the whole space of of of science, but maybe we can anchor it by starting a little bit right now near term and and see how we kind of move forward. So so like right now, first of all you have a lot of big data science where for example with telescopes we are able to collect way more data every hour than grad student can just pour over like in the old times. Right? And machine learning is already being used very effectively. Even at M I. T. I need to find planets around other stars to detect exciting new signatures of a new particle physics in the sky to detect uh the ripples in the fabric of space time that we call gravitational waves caused by enormous black holes crashing into each other halfway across the observable universe. Machine learning is running and taking it right now, you know doing all these things and it's really helping all these extra mental fields. There is a a separate front of physics, computational physics which is getting an enormous boost also. So we had to do all the computations by hand, right? People would have these giant books with tables of logarithms and oh my God, it pains me to even think how long time it would have taken to do simple stuff. Then we started to get a little calculators and computers that can do some basic math for us. Now what are we starting to see is kind of a shift from go fi computational physics too, neural network, computational physics what I mean by that is most computational physics would be done by humans programming in the intelligence of how to do the computation into the computer just as when Garry Kasparov got his posterior kicked by IBM deep blue and chess humans had programmed in exactly how to play chess intelligence came from the humans. It wasn't learned right, mu zero can be not only Kasparov in chess but also stock fish, which is the best sort of go fi chess program by learning. And we're seeing more of that now that shift beginning to happen in physics. So let me give you an example. So lattice qc D is an area of physics whose goal is basically to take the periodic table and just compute the whole thing from first principles. Mhm This is not the search for a theory of everything. We already know the theory that's supposed to produce this output the periodic table which atoms are stable, how much, how heavy they are, all that good stuff. Their spectral lines, it's called it's a theory lattice Q C D. You can put it on your t shirt, our colleague frank Wilczek got the Nobel prize for working on it. Uh but the math is just too hard for us to solve. We have not been able to start with these equations and solve them to the extent that we can predict. Oh yeah, and then there is carbon and this is what the spectrum of the carbon atom looks like. But the awesome people are building these super can produce simulations where you just put in these equations and you you make it big cubic lattice of space or actually it's a very small lettuce because you're going to the subatomic, get down to the subatomic scale and you try to solve this. But it's just so computational expensive that we still haven't been able to calculate things as accurately as we measure them in many cases. And now machine learning is really revolutionizing this. So my colleague Viola Shanahan and M. I. T. For example, she's been using this really cool machine learning technique called normalizing flows, where she's realized she can actually speed up the calculation dramatically by having the A. I learned how to do things faster. Another area like this where where where we suck up an enormous amount of supercomputer time to do physics as black hole collisions. So now that we've done the sexy stuff of detecting a bunch of this like go and other experiments, we want to be able to put know what we're seeing. So it's very simple conceptual problem. It's the two body problem. Newton solved it for a classical gravity hundreds of years ago, but the two body problem is still not fully solved for black holes black holes. Yes and nice times gravity because they won't disturb it each other forever anymore to things they give off gravitational waves and make sure they crash into each other and the game, what you want to do is you want to figure out, okay, what kind of wave comes out as a function of of the masses of the two black holes is a function of how they're spinning relative to each other etcetera. And that is so hard. It can take months of supercomputer time on massive numbers of course to do it, you know, Wouldn't it be great if you can use machine learning to greatly speed that up? Right? Um now you can use the expensive old go fi calculation as the truth and then see if machine learning can figure out smarter faster way of getting the right answer. Uh Yet another area like a computational physics. These are probably the big three that suck up the most computer time, latest cd black hole collisions and cosmological simulations. Where you taking on a subatomic thing and try to figure out the mass of the proton. But you take something with it's enormous and try to look at how all the Galaxies get formed in there. Yeah, there again, there are a lot of very cool ideas right now about how you can use machine learning to do this sort of better stuff. Better the difference between this and the big data is you kind of make the data yourself. So and then finally, we're looking over the physical landscape and saying what can we hammer with machine learning. Right? So we talked about experimental data. Big data, discovering cool stuff that we humans that look more closely at. And we talked about taking them expensive computations we're doing now and figuring out how to do them much faster and better with ai and finally let's go really theoretical. So things like discovering equations having the fundamental insights this comes this is something closest to what I've been doing in my group. We talked earlier about the whole a fireman project where if you just have some data, how do you automatically discover equations that seem to describe this? Well that you can then go back as a human and then work with and test and explore. And the you asked a really good question also about if this is sort of a search problem in some sense. That's very deep actually what you said because it is suppose I asked you to prove some mathematical theorem. Mhm. What is a proof in math? It's just a long string of steps, logical steps that you can write out with symbols. Mhm. And once you find it, it's very easy to write a program to check whether it's a valid proof or not. So why is it so hard to prove it then? Well, because there are ridiculously many possible candidate proves you could write down, right? If the if the proof contains 10,000 symbols even if there were only 10 options for what each symbol could be 10 to the power 1000 possible proofs, which is way more than there are atoms in our universe. Right? So you could say it's trivial to prove these things. You just write a computer generate all strings and the check. Is this a valid proof? You know? Is this a valid proof? No? And then you just keep doing this forever? Uh but there are a lot of but it is fundamentally a search problem. You just want to search the space of all those all strings of symbols to find the one. We find one. That is the proof, right. And there's a whole area of machine learning called search. How do you search with some giant space to find the needle in the haystack? It's easier in cases where there is a clear measure of of good, like you're not just right or wrong, but this is better and this is worse. You can maybe get some hints as to which direction to go in. That's why we talked about neural networks work so well, </s><s>[INST] I mean that's such a human thing of that moment of genius of figuring out the intuition of Of good essentially. I mean we thought that that was maybe it's not right. We thought that about chess, right? That that the the ability to see like 10, 15, sometimes 20 steps ahead was not a calculation that humans were performing. It was some kind of weird intuition about different patterns, about board positions, about the relative positions that somehow stitching stuff together. And a lot of it is just like intuition but then you have like alpha like zero be the first one that did uh uh self play. It just came up with this. It's it was able to learn through self play mechanism, this kind of intuition but just like you said, it's so fascinating to think well there in the space of totally new ideas, can that be done in developing theorems? [/INST] We know it can be done by new Orleans works because we did it with the new Orleans works in the craniums of the great mathematicians of our of humanity. Right? And and I'm so glad you brought up ALF a zero because that's the counter example. It turned out we were flattering ourselves when we said intuition is something different. It's only humans can do it. It's not information processing if you if it used to be that way. Again it's very it's really instructive I think to compare the chess computer Deep blue that beat Kasparov with alpha, zero beat lisa doll at go because for deep blue there was no intuition there was some pro humans had programmed in some intuition after humans have played a lot of games they told the computer, you know, count upon as one point. The bishop is three points. Rook is five points and so on. You add it all up and then you add some extra points for passed pawns and subtract if the opponent has it and and blah blah blah blah. And then what what Deep blue did was just search just very brute force, tried many many moves ahead. All these combinations in a prudent research and it could think much faster than Kasparov. And at one right. And that I think inflated our egos in a way it shouldn't have because people started to yeah. Yeah. It's just brute force search but has no intuition. Yeah. Alpha zero really pop your bubble there. Because what Alfa Sierra does. Yes, it does also do some of that research but it also has this intuition module which in geek speak is called the value function where it just looks at the board and comes up with a number for how good is that position? The difference was no human told. It's how good the position is. It just learned it and mu zero is is the coolest or scariest of all, depending on your mood. Because it's the same basic ai system. We'll learn what the good board position is regardless of whether it's chess or go or soggy or pac man or lady pac man or breakout or space invaders or any a bunch of other games. You don't tell anything. And it gets this intuition after a while for what's good. So this is very hopeful for science I think because if it can get intuition what's a good position there. Maybe it can also get intuition for what are some good directions to go if you're trying to prove something, if I I often one of the more most fun things in my science career is when I've been able to prove some theorem about something and it's very heavily intuition guided. Of course I don't sit and try all random. Strange, I have a hunch that, you know, this reminds me a little bit of about this other proof I've seen for this thing, so maybe I first what if I try this? No, that didn't work out, but this reminds me actually, the way this failed reminds me of that. And so, so combining the intuition that with all these boot force capabilities, I think I think it's going to be able to help physics to </s><s>[INST] do. You think that there will be a day when an AI system being the primary contributor, let's say 90% plus wins the Nobel prize in physics, obviously, they'll give it to the humans because we humans don't like to give prizes to machines. It give it give it to the humans behind the system. You could argue that Ai has already been involved in some Nobel prizes. Probably, maybe something with black holes and stuff like [/INST] that. Yeah, we don't like giving prizes to other life forms, if someone wins a horse racing contest, that they don't give the prize to horse either. It's </s><s>[INST] true. Uh But do you think that's what might be able to see something like that in our lifetimes when ai. So like the first system, I would say that makes us think about a nobel prize, seriously, is like, Alpha fold is making us think about in medicine physiology, a Nobel prize. Perhaps discoveries, they are a direct result of something that's discovered by Alpha Fall. Do you think in physics we might be able to see that in our lifetimes? [/INST] I think what's probably gonna happen is more of a blurring of the distinctions. Uh So today, if somebody uses a computer to do a computation that gives them the normal price, nobody's gonna dream of giving the price of the computer, they're gonna be like, that was just a tool. I think that for these things also, people are just gonna for a long time view of the computer as a tool. But what's gonna change is that is that you the ubiquity of machine learning? I think at some point in my lifetime, finding human physicists who knows nothing about machine learning is going to be almost as hard as it is today. Finding a human physicist who doesn't says, oh, I don't know anything about computers or I don't use math. It would just be a ridiculous concept. </s><s>[INST] But the thing is, There is a magic moment though, like with Alpha zero when the system surprises us in a way where the best people in the world truly learned something from the system in a way where you feel like it's another entity, like the way people, the way magnus carlsen, the way certain people are looking at the work of Alpha Zero, it's like uh it truly is no longer a tool in the sense that it doesn't feel like a tool, it feels like some other entity. [/INST] So there is a magic difference, </s><s>[INST] like where, where you're like uh you know, if an Ai system is able to come up with an insight that surprises everybody in a some uh in some like major way, that's a phase shift in our understanding of some particular size or some particular aspect of physics. I feel like that is no longer a tool. And then you can start to say uh that like it perhaps deserves the prize. [/INST] So for </s><s>[INST] sure, the more important and the more fundamental transformation of the 21st Century Science is exactly what you're saying, which is probably everybody will be doing, is she learning? It's to some degree, like if you want to be successful at unlocking the mysteries of science, you should be doing machine learning. But it's just exciting to think about like whether there will be one that comes along, that's super surprising and they'll make us question like who the real inventors are [/INST] in this world. Yeah, I think the question of isn't if it's going to happen, but when and but it's important in my mind, the time when that happens is also more or less the same time when we get artificial general intelligence and then we have a lot bigger things to worry about than whether they should get the Nobel prize or not. Right? Because when you have machines that can outperform our best scientists at science, they can probably outperform us at a lot of other stuff as well, which kind of the minimum, you know, make them incredibly powerful agents in in the world, you know, And I think it's a mistake to think we only have to start worrying about loss of control when machines get to AGI across the board where they can do everything all our jobs long before that they'll be hugely influential. We talked at length about how the hacking of our minds with mhm algorithms trying to get us glued to our screens, right, has already had a big impact on, on society. That was an incredibly dumb algorithm in the grand scheme of things. Right? Just supervised machine learning yet, that had had a huge impact. So, so I just don't want us to be lulled into a false sense of security and think there won't be any societal impact until things reach human level because it's happening already. And and it's I was just thinking the other week, you know, when I see some scare monger going, oh, the robots are coming. The implication is always that they're coming to kill us. Yeah. And maybe you should have worried about that if you were not going to care about during the recent war there, but more seriously the robots are coming right now but they're mainly not coming to kill us. They're coming to hack us. Mhm. They're they're coming to hack our minds and buying things that maybe we didn't need to vote for people who may not have our best interest in mind. And and it's kind of humbling I think actually as a human being to admit that it turns out that our minds are actually much hacked more hackable than we thought. And the ultimate insult is that we are actually getting hacked by the machine learning algorithms that are, in some objective sense, much dumber than us, you know? But maybe we shouldn't be so surprised because you know, how do you feel about the cute puppies? </s><s>[INST] I love them. [/INST] So you know, you would probably argue that in some across the board measure you're more intelligent than they are. But boy are are cute puppies good at hacking us, right? They move into our house, persuade us to feed them and do all these things. What do they ever do for us? Yeah. Other than being cute and making us feel good bye. So if puppies can hack us, maybe we shouldn't be so surprised if it's pretty dumb. Machine learning algorithms can hack us to </s><s>[INST] not to speak of cats, which is another level. And and I think we should to counter your previous point about there, Let us not think about evil creatures in this world. We can all agree that cats are as close to objective evil as we can get. But that's just me saying that [/INST] okay uh you have you seen the cartoon? I think maybe the onion. Um Well this is incredibly cute kitten and it just says um it's underneath something that thinks about murder all day. </s><s>[INST] Exactly. That's that's accurate. You mentioned are flying that there might be a link between post biological A. G. I. And CT. So last time we talked you've you've talked about this intuition that we humans might be quite unique in our galactic neighborhood. Perhaps our galaxy, perhaps the entirety of the observable universe. Who might be the only intelligence civilization here? Which is uh and you argue pretty well for that thought. Um So I have a few little questions around this one. Uh the scientific question in which way would you be if you were wrong in that intuition, In which way do you think you'll be surprised like why were you wrong? We find out that you ended up being wrong. Like in which dimension? So like is it because we can't see them? Is it because the nature of their intelligence of the nature of their life is totally different than we can possibly imagine. Is it because the I mean something about the great filters and surviving them or maybe because we're being protected from signals. All those explanations for um for why we haven't heard a big loud like red light that says we're [/INST] here. So there are actually two separate things there that I could be wrong about two separate claims that I made right for them. 1 1 of them is mhm. I made the claim. I think most civilizations when you're going from simple bacteria, like things to space, space colonizing civilizations, they spend only a very very tiny fraction of the other other life being where we are uh that I could be wrong about the other one I could be wrong about is quite different statement that I think that actually I'm guessing that we are the only civilization in our observable universe from which light has reached us so far that that's actually gotten far enough to invent telescopes. So let's talk about maybe both of them in turn because they really are different. The first one if if you look at the N equals one the data point we have on this planet. Right? So we spent 4.5 billion years floating around on this planet with life, right? We got most of it. It was pretty lame stuff from an intelligence perspective, you know, as bacteria. And then the dinosaurs spent then things gradually accelerated. Right? Then the dinosaurs spent over 100 million years stomping around here without even inventing smartphones. And And then very recently, you know, it's only we've only spent 400 years going from Newton to us. Right? In terms of technology and well, look at what we've done even, you know, when I was a little kid, there was no internet even. So it's, I think it's pretty likely for in this case of this planet, right, that we're either gonna really get our act together and start spreading life into space the century and doing all sorts of great things or where you're gonna gonna wipe out. Um it's a little hard if I I could be wrong in the sense that maybe what happened on this Earth is very atypical and for some reason, what's more common on other planets is that they spend an enormously long time futzing around with the ham radio and things, but they just never really take it to the next level for reasons I don't haven't understood, I'm humble and open to that, but I would bet at least 10-1 that our situation is more typical because the whole thing with Moore's law and accelerating technology, it's pretty obvious why it's happening. Everything that grows exponentially we call it an explosion, whether it's a population explosion or a nuclear explosion is always caused by the same thing. It's that the next step trigger is a step after that. So, I, well, tomorrow's technology, today's technology enables tomorrow's technology and that enables the next level. And yeah, as the, because the technology is always better, of course, the steps can come faster and faster uh, on the other question that I might be wrong about, that's the much more controversial one I think. But before we close out on this thing about if the first one, if it's true that most civilizations spend only a very short amount of their total time in the stage, say between inventing um telescopes or mastering electricity and leaving their doing space travel. Uh if that's actually generally true, but then that should apply also elsewhere out there. So we should be very, very soon. We should be very, very surprised if we find some random civilization and we happen to catch them exactly in that very, very short stage. It's much more likely that we find a planet full of bacteria or that we find some civilization that's already post biological and has done some really cool galactic construction projects in there in the galaxy. Would </s><s>[INST] we be able to recognize them? Do you think? Is it possible that we just can't, I mean this post biological world, could it be just existing in some other dimension? It could be just all a virtual reality game for them or something? I don't know that it changes completely where we won't be able to detect. [/INST] We have to be honestly very humble about this. I think that I said, I think I said earlier, the number one principle of being scientists, you have to be humble and willing to acknowledge that everything we think this might be totally wrong. Uh Of course you can imagine some civilization where they all decided to become Buddhists and very inward looking and just move into their little virtual reality and not disturb the flora and fauna around them and we might not notice them. But this is a numbers game, right. If you have millions of civilizations out, there are billions of them all it takes is one with a more ambitious mentality that decides, hey, we are going to go out and settle a bunch of other solar systems and maybe Galaxies. And then it doesn't matter if they're a bunch of quiet Buddhists were still going to notice that expansionist one, right? And it seems like quite the stretch to assume that we know even in our own galaxy that there are probably a billion or more planets that are pretty Earth like and many of them are formed over a billion years before ours. So I had a big head start. So if you actually assume also that life happens kind of automatically on an earth like planet, I think it's, it's pretty quite the stretch to then go and say, okay, so we have their billions of another billion civilizations out there also have our level attack and they all decided to become Buddhists and not a single one decided to go like go Hitler on the galaxy and said we need to go out and colonize or or not not a single one decided for more benevolent reasons to go out and get more resources. That that seems, seems like a bit of a stretch frankly. And this leads into the second thing you challenged me to be that I might be wrong about how rare or common is life, you know, so Francis drake, when he wrote down the drake equation, multiplying together a huge number of factors and said, we don't know any of them. So we know even less what you get when you multiply together the whole product. Since then, a lot of those factors have become much better known. One of his big uncertainties was how common is it that a solar system even has a planet? Well, now we know is very common. </s><s>[INST] Earth like planets, we know [/INST] where, but they're a dime, a dozen, many, many of them, even in our galaxy at the same time. You know, we have thanks to, I'm a big supporter of the Seti project and its cousins and I think we should keep doing this and we've learned a lot. We've learned that so far all we have is still unconvincing hints, nothing more right. And and there are certainly many scenarios where it would be dead obvious if there were 100 million other humanlike civilizations in our galaxy, it would not be that hard to notice some of them with today's technology and we haven't right. So, so what we can, what we can say is, well, okay, we can rule out that there is a human level of civilization on the moon and in fact many nearby solar systems where we cannot rule out of course that there is something like Earth setting me in a galaxy five billion light years away. Um, but we've ruled out a lot and that's already kind of shocking given that they're all these planets there, you know? So like where are they? Where are they all? That's the that's the classic fermi paradox. And so my argument, which might be really wrong, it's very simple, really just goes like this. Okay, we have no clue about this. It could be the probability of getting life under random planet. It could be 10 to the minus one that a priori or 10 to the minus 10, 10 to minus 2010 to minus 30 minus 40. Basically every order of magnitude is about equally likely. When then do the math and ask how close is our nearest neighbor? It's again equally likely that it's 10 to the 10 m away, 10-20 m away, 10-30 m away. We can we have some nerdy ways of talking about this with Beijing and statistics and a uniform log prior, but that's irrelevant. This is the simple basic argument. And now comes the data. So we can say, Okay, how many words? There are all these orders of magnitude 10 to the 26 m away. There's the edge of our observable universe, if it's farther than that light hasn't even reached just yet. If it's uh less than 10 to the 16 m away. Well it's within Earth's it's no farther away than the sun. We can definitely rule that out, you know. Um so I think about it like this a priority before we looked through telescopes, you know, It could be 10 for 10 m 10-2010 and 30s and 40s and 50s and equally likely anywhere here. Uh and now we've ruled out like this chunk. Yeah, and most of it is outside and here is the edge of our global universities. So I'm certainly not saying I don't think there's any life elsewhere in space. If space is infinite, then you're basically 100% guaranteed that there is. But the probability that there is life, the that the nearest neighbor, it happens to be in this little region between where we would have seen it already and where we will never see it. There's actually significantly less than one I think. And and I think there's a moral lesson from this which is really important, which is to be good stewards of this planet. And this shot we've had, you know, it can be very dangerous to say, oh, you know, it's fine if we nuclear planet or ruin the climate or mess it up with the line ai because I know there is this nice star treks fleet out there, they're going to swoop in and take over where we failed. Just like it wasn't a big deal that the easter Island losers wipe themselves out. It's a dangerous way of loving yourself into a false sense of security. If it's actually the case that it might be up to us and only us, the whole future of intelligent life in our observable universe, then I think it's both, it really puts a lot of responsibility on our shoulders, inspiring. It's </s><s>[INST] a little bit terrified of, It's also [/INST] inspiring, but it's empowering I think most of all because because the biggest problem today is I see this, even my teach right? So many people feel that it doesn't matter what they do or we do, we feel disempowered, oh, it makes no difference. This is about as far from that as you can come up when you realize that what we do on our little spinning ball here in our lifetime, you know, could make the difference for the entire future of life in our universe. You know, how empowering is that </s><s>[INST] survival of consciousness? I mean on the the other, a very similar kind of empowering aspect of the drake equation is say that there is a huge number of intelligent civilizations that spring up everywhere, but because of the drake equation, which is the lifetime of a civilization, maybe many of them hit a wall and just like you said, it's clear that that for us, the great filter, the one possible great filter seems to be coming, you know, in the next 100 years. So it's also empowering to say, okay, well, uh we have a chance to not. I mean the way great filters work and they just get most of them. [/INST] Exactly. Nicb Ostrom has articulated this really beautifully to, you know, every time. So you have to another search for life on MArs comes back negative or something. I'm like, yes, our odds for us surviving. You've already made the argument that broad brush, they're right. Uh, but just unpack it, right. The point is we already know there's a crap ton of planets out there that are Earth like and we also know that most of do not seem to have anything like our kind of life long. So what, what went wrong? There's clearly one step along the evolutionary, at least one filter roadblock in going from no life to spacefaring life. And where is it? Is it in front of us there, is it behind us, right? If there's no filter behind us and we keep finding all sorts of like of uh little mice on MArs and or whatever. Right? That's actually very depressing because it makes it much more likely that the filter is in front of us. And that's what actually is going on is like the ultimate dark joke that whenever civilization invents sufficiently powerful tech, it's just just set their clock and then after a while it goes proof for one reason rather and wipes itself out, that'll be wouldn't that be like utterly depressing if we're actually doomed? Whereas if it turns out that there is a really there is a great filter early on that for whatever reason seems to be really hard to get to the stage of sexually reproducing organisms or even the first ribosome or whatever. Right? Or or maybe you have lots of planets with dinosaurs and cows, but for some reason they tend to get stuck there and never invent smartphones. All of those are huge boosts for our own odds because been there done that. You know, it doesn't matter how hard are unlikely it was that we got past that roadblock because I already did. Yeah. And then then that makes it likely that the future is in our own hands, we're not doomed. So that that's why that's why I think the fact that like that life is rare in the universe. It's not just something that there is some evidence for, but also something we should actually hope for. </s><s>[INST] Yeah. So that's the end. The mortality, the death of human civilization that we've been discussing in life may be prospering beyond any kind of great filter. Do you think about your own death? Doesn't make you sad that you may not witnessed some of the, you know, you lead a research group on working some of the biggest questions in the universe, actually um both on the physics and the ai side, does it make you sad that you may not be able to see some of these exciting things come to fruition that we've been talking about. [/INST] Of course, of course it sucks. The fact that I'm gonna die. I remember once when I was much younger, my dad made this remark that life is fundamentally tragic and I'm like, what are you talking about, daddy? And uh many years later, I I felt now, I feel like I totally understand what he means. You know, we grow up very little kids and everything is infinite and it's so cool and then suddenly that we find out that actually, you know, you got to say only this, this is that you can get game over at some point. Uh so of course it's it's it's uh it's something that's sad, are you afraid? But no, not in the sense that I think anything terrible is gonna happen after I die or anything like that. No, I think it's really going to be a game over, but it's more that it makes me very acutely aware of. I just have what a wonderful gift this is that I get to be alive right now and and is a steady reminder to just live life to the fullest and really enjoy it because it is finite, you know, and I think actually, and we know we all get the regular reminders when someone near and dear to us dies that that that uh you know, one day it's going to be our turn adds this kind of focus? I wonder what it would feel like actually to be an immortal being if they might even enjoy some of the wonderful things in life a little bit less because there isn't that </s><s>[INST] finite nous. [/INST] Do you think that could be a </s><s>[INST] feature? Not a bug. The fact that we beings are finite. Maybe there's lessons for engineering artificial intelligence systems as well that are conscious. Do you think it makes? Is it possible that the reason the pistachio ice cream is delicious is the fact that you're going to die one day and you will not have all the pistachio ice cream that [/INST] you could eat because of that fact. Well let me say two things. First of all, I actually quite profound what you're saying. I do think I appreciate the pistachio ice cream a lot more knowing that I will, there's only a finite number of times I get to enjoy that and I can only remember find a number of times in the past and moreover, my life is not so long that it just starts to feel like things are repeating themselves in general. It's so new and fresh. I also think though that death is a little bit overrated in the sense that the it comes from a sort of outdated view of physics and what life actually is because if you ask, okay, what is it that's going to die exactly what I am. I really, when I say, I feel sad about the idea of myself dying. Am I really sad that the skin cell here is going to die? Of course not because it's gonna die next week anyway, and then I'll grow a new one, right? And it's not any of my cells that I'm associated with with, who I really am, nor is it any of my atoms or quirks or electrons? Uh in fact, basically all of my atoms get replaced on a regular basis. Right? So what is it? That's really me from a more modern physics perspective, it's the information in processing amy, that's where my, my memory, that's my memories. That's my, my values, my dreams, my passion, my love. Um, it that's what's really fundamentally me and frankly not all of that will die when when my body dies. Like Richard Feynman, for example, his body died of cancer, you know, but many of his ideas that he felt made him very him actually live on, I this is my own little personal tributes to Richard Feynman, right? I try to keep a little bit of him alive and myself and I've even quoted him today, right? </s><s>[INST] Yeah, he almost came alive for a brief moment in this conversation. Yeah, [/INST] yeah. And and and this honestly gives me some solace, you know, when I work as a teacher, I feel if I can actually share a bit about myself that my students feel worthy enough to copy and adopt some part of things that they know, or, or they believe or aspired to now, I live on also a little bit in them. Right? And uh, so being a teacher is a little bit of what I, that's something also that contributes to making me a little teeny bit less mortal. Right? Because I'm not at least not all going to die all at once. Right. And I find that a beautiful tribute to people we didn't respect if we can, if we can remember them and carry in us the things that we felt was the most ask them about them, right. Then they live on and I'm getting a bit emotionally every, but it's a very beautiful idea you bring up there. I think we should stop this old fashioned materialism and just equate who we are with our quirks and electrons. Now there's no scientific basis for that really. And it's also very uninspiring now, if you look a little bit towards the future, right. One thing which really sucks about humans dying is that even though some of their teachings and memories and stories and ethics and so on will be copied by those around them. Hopefully a lot of it can't be copied and just dies with them with the brain. And that really sucks. That that's the fundamental reason why we find it so tragic when someone goes from having all this information, they're just gone ruined right with with more post biological intelligence, that's going to shift a lot, right? The only reason it's so hard to make a backup of your brain in its entirety is exactly because it wasn't built for that. Right? If you have a future machine intelligence, there's no reason for why it has to die at all. If it wants to up, if you want to copy it, whatever is it into some other quirk blob, right? You can copy not just some of it, all of it. Right. And so, so in that sense, you can get immortality because all the information can be copied out of any individual entity. It's not just mortality that will change. If we get more post biological life. It's also the with that very much the whole individual, the whole individualism we have now, right? The reason that we make such a big difference between me and you is exactly because we're a little bit limited. And how much we can copy. Like I would just love to go like this and copy your Russian skills. Russian speaking skills, wouldn't it be awesome. But I can't, I have to actually work for years and I want to get better on it. And but if you have, if we were robots just copy and paste </s><s>[INST] freely, then that loses completely. Uh, it washes away the sense of what immortality is [/INST] and also individuality a little bit right, We would start feeling much more, Maybe we would feel much more collaborative with each other if we can just, hey, you know, I'll give you my rush, you can give me your Russian and I'll give you whatever something can and suddenly you can speak Swedish. Maybe that's less bad trade for you, but whatever else you want from my brain. Right. And uh there have been a lot of sci fi stories about hive minds and so on where, where people where experiences can be more broadly shared. Yeah. Uh huh I think one we don't, I don't pretend to know what it would feel like to be a super intelligent machine, but I'm quite confident that however it feels about mortality and individuality will be very, very different from how it is for us. </s><s>[INST] Yeah. Well for us mortality and finite, this seems to be pretty important at this particular moment. And so all good things must come to an end just like this conversation [/INST] next coming. So </s><s>[INST] his is the world's worst transition. I could talk to you forever. Is such a huge honor that you spend time with me. [/INST] Uh thank </s><s>[INST] you so much for getting me essentially to start this podcast by doing the first conversation making me realize uh falling in love with conversation in itself. And thank you so much for inspiring so many people in the world with your books with your research with your talking and with other the like this, this ripple effect of friends including Ellen and everybody else that you inspire. So thank you so much for talking today. [/INST] Thank you. I feel like so fortunate that you're doing this podcast and getting so many interesting voices out there into the ether and not just the five second sound bites, but so many of the interviews of what you do. Will you really let people go in Into depth in a way which we sorely need in this day and age in that I got to be number one. I feel super honored. </s><s>[INST] Yeah, you started it. Thank you so much max. Thanks for listening to this conversation with max tag Mark and thank you to our sponsors, the jordans Harbinger show for Sig Matic mushroom coffee better help online therapy and express VPN. So the choice is wisdom, caffeine, sanity or privacy choose wisely my friends and if you wish, click the sponsor links below to get a discount and to support this podcast and now let me leave you with some words from max tag mark. If consciousness is the way that information feels when it's processed in certain ways that it must be substrate independent. It's only the structure of information processing that matters, not the structure of the matter. Doing the information processing. Thank you for listening and hope to see you next time. [/INST] Yeah, </s>

<s>[INST] as a question I guess with from the security side there's a you know, you're looking for holes in programs so I at least see small connection but why where was your interest for program synthesis as? Because it's such a fascinating, such a big such a hard problem in the general case. Why program synthesis? [/INST] So the reason for that is actually when I shifted my focus from security into ai machine learning and actually one of the main motivation at the time. Um is that even though I have been doing a lot of work in security and privacy, but I have always been fascinated about building intelligent machines. And that was really my main motivation to spend more time in a I maturity is that I really want to figure out how we can build intelligent machines and to help us uh towards that goal. Um Program synthesis is really one of, I would say the best domain to work on. I actually call it like a program synthesis is like the perfect playground for building intelligent machines and for artificial general intelligence. Um </s><s>[INST] Well it's also in that sense, not just a playground, I guess it's it's the ultimate test of intelligence because I think uh I think if you can generate sort of neural networks can learn good functions and they can help you out in classification tasks. But to be able to write programs, that's that's the epitome from the machine side, that's the same as passing the turing test and natural language, but with programs it's able to express complicated ideas to reason through ideas and yeah, and boil them down to algorithms. [/INST] Exactly </s><s>[INST] credible. So can this be learned? How far are we? Is there? Hope, what are the open challenge [/INST] is very good questions. We are still at an early stage but already I think we have seen a lot of progress. I mean definitely we have, you know, existence proof, just like humans can write programs. So there's no reason why computers cannot write programs. Um So I think that's definitely achievable goal is just how long it takes. And then um and even today we actually have, you know the program synthesis community, especially the program synthesis by learning or we call it in europe program since this community is still very small. Um but the community has been growing and we have seen a lot of progress and in limited domains I think actually uh program synthesis is ripe for real world applications. So actually it was quite amazing. I was at uh was giving a talk. So here is a rework conference actually. So I give another talk at the previous rework conference in deep reinforcement learning. And then I actually met someone from a startup and the ceo of the startup and when he saw the name he recognizes and he actually said one of our papers actually had they have put had actually become a key products in there set up. And that was um program since in that particular cases was natural language translation uh translating natural language description into secretaries. </s><s>[INST] Oh wow, that that direction. Okay, [/INST] so Right, so uh yeah, so in program synthesis in limited domains, in well specified domains, actually already we can see really um great progress and applicability in the real world </s><s>[INST] domains like and as an example you said natural language being able to express something through just normal language and it converts it into a database sequel. SQL Corey and that's how how I solved the problem is that because it seems like a really hard problem [/INST] again, in limited domains actually it can work pretty well. And now this is also a very active domain of research at the time. I think when he saw our people at the time we were the state of the art um on the task. And since then actually now there has been more work and with even more sophisticated to set. Uh and uh so but I I think I wouldn't be surprised that more of this type of technology really getting to the real world that's exciting in the near term </s><s>[INST] being able to learn in the space of programs is super exciting. I still yeah, I'm still skeptical because I think it's a really hard problem but progress. [/INST] And also I think in terms of the US about open challenges, I think the domain is full of challenges. And in particular also we want to see how we should measure the progress in the space and I would say mainly um three main, I'll say metrics. So one is the complexity of the program that we can synthesize and that will actually have clear measures and just look at, you know, the past publications and even like for example, I was at the recent europe's conference. Now there's actually very size of all like session dedicated to program synthesis, which is </s><s>[INST] even neuro programs, [/INST] which is great. And we continue to see uh the increase, </s><s>[INST] I think there were sizable, it's five [/INST] people still small community, but this is growing </s><s>[INST] and they will all win touring Awards one day like it. [/INST] Right. So, so we can clearly see an increase in the complexity of the programs that um this </s><s>[INST] just can synthesize, decided to uh is it the complexity of the actual text of the program? Or the running time complexity, which complexity are how the [/INST] complexity of the task to be synthesized and the complexity of the actual synthesize the programs. So, so the lines of code, even for example. </s><s>[INST] Okay, I got you. But it's not the theoretical profound the running time of the Right, Right. Right, OK. Yeah. And you can see the complexity in decreasing already. [/INST] I mean we want to be able to synthesize more and more complex programs, bigger and bigger programs. So we want to see that's uh we want to increase the complexity. </s>

<s>[INST] Have you built up an intuition of why are there a little bits and pieces of intuitions of insights of why this whole thing works? [/INST] I mean, some definitely Well, we know that optimization we now have good we've take we've had lots of empirical, huge amounts of empirical reasons to believe that optimization should work on all most problems we care about. </s><s>[INST] Do you have insights of what? So you just said empirical evidence is most of your sort of empirical evidence kind of convinces you. It's like evolution is empirical, it shows you that look this evolutionary process seems to be a good way to design organisms that survive in their environment, but it doesn't really get you to the insides of how the whole thing works. [/INST] I think it's a good analogy is physics. You know, how you say, hey, let's do some physics calculation and come up with some new physics theory and make some prediction. But then you've got around the experiment, you know, you gotta run the experiment. It's important. It's a bit of the same here except that maybe some sometimes the experiment came before the theory but it still is the case. You know, you have some data and you come up with some prediction you say, yeah, let's make a big neural network, let's train it. And it's going to work much better than anything before it. And it will in fact continue to get better as you make it larger. And it turns out to be true. That's that's amazing when theory is evaluated like this. You know, it's not a mathematical theory, it's more of a biological theory almost. So I think there are not terrible analogies between deep learning and biology. I would say it's like the geometric mean of biology and physics. That's deep learning the geometric </s><s>[INST] mean of biology and physics. I think we're going to need a few hours throughout my head around that because just to find the geometric just to find the set of what biology represents. [/INST] Biology in biology things are really complicated and there is a really, really, really hard to have good predictive theory in physics theories are too good in theory in physics people make this super precise theories which makes these amazing predictions and in machine learning we can in between </s><s>[INST] kind of in between. But it would be nice if machine learning somehow helped us discover the unification of the two as opposed to serve the in between. But you're right, that's you're you're kind of trying to juggle both. So do you think they're still beautiful and mysterious properties of neural networks that are yet to be discovered? [/INST] Definitely. I think that we are still massively underestimating deploying. </s><s>[INST] What do you think? It will look like? Like what [/INST] if I knew I would have done it. </s><s>[INST] So uh [/INST] But if you look at all the progress in the past 10 years, I would say most of it, I would say there's been a few cases where some were things that felt like really new ideas showed up, but by and large it was every year we thought, okay, deployment goes this far. No, it actually goes further and then the next year. Okay, now now this is this is big deep learning. Pr really done, nope, goes further, just keeps going further each year. So that means that we keep underestimating you keep not understanding it as surprising properties all the time. </s><s>[INST] Do you think it's getting harder and harder [/INST] to make progress. You need to make progress? It depends on what you mean. I think the field will continue to make very robust progress for quite a while. I think for individual researchers, especially people who are doing research, it can be harder because there is a very large number of researchers right now. I think that if you have a lot of compute then you can make a lot of very interesting discoveries. But then you have to deal with the challenge of managing the huge computer, huge, classic, huge computer cluster to run your experiments. It's little bit </s><s>[INST] harder. So I'm asking all these questions that nobody knows the answer to, but you're one of the smartest people I know, so we can keep asking The so let's imagine all the breaks that was, that happened in the next 30 years and deep learning. Do you think most of those breakthroughs can be done by one person with one computer in the space of breakthroughs, do you think compute will be uh compute and large efforts will be necessary. [/INST] I mean, it can't be sure when you say one computer, you mean how large </s><s>[INST] Uh you're you're clever. I mean, 1, 1 [/INST] GPU I see, I think it's pretty unlikely. I think it's pretty unlikely. I think that there are many the stack of deep learning is starting to be quite deep if you look at it, you've got all the way from with the ideas the systems to build the data sets, the distributed programming, the building the actual cluster, the Gpu programming, putting it all together. So the stack is getting really deep and I think becomes, it can be quite hard for a single person to become to be world class in every single layer of the stack. </s><s>[INST] What about what like Vladimir, Vap Nick really insists on is taking em nist and trying to learn from very few examples. So being able to learn more efficiently, do you think that there'll be breakthroughs in that space that would may not need the huge compute? [/INST] I think there will be a very, I think there will be a large number of bakers in general if you're not in a huge amount of compute. So maybe I should clarify that. I think that some breakthroughs will look quite a lot of compute and I think building systems which actually do things will require a huge amount of compute that one is pretty obvious if you want to do X and X requires a huge mural that you gotta get a huge year on that. But I think there will be lots of, I think there's lots of room for very important work being done by small groups and individuals. </s>

<s>[INST] like immature name calling sometimes. Yeah, I think the political bickering that most people talk about that's on top of most people's minds is the thing that'll be completely forgotten by history. It has actually very little impact. Yes, politics matters, but 1% of it, I think most of it is just political bickering, the push and pull of the red team and the blue team and then the news media that feeds off the division for the attention and it's just like a fun, athletic event almost with the blue team and the red team. So that, you kinda have to have a historical perspective on it, like most things will not really have a significant impact and we should focus on development of science, technology, engineering, which is the thing that grows the pie. 100%. This is what the economists know well. Just the innovation, the engineering, that's what actually makes everybody richer. [/INST] This kind of political bickering is just eating the pie. And not just richer, but it improves their lives. We can look at every modern technology that is bestowed upon us today, air conditioning, electricity, internet access, fresh clean water, running water, blah, blah, blah. 100 years ago, so many of the things that I listed either didn't exist or were only accessible by the ultra wealthy, and it's through the innovation of technology and engineering and education that we're able to have it be that even someone below the poverty line and most of the developed world will have a good number of those things in their life. And that's just continuing to increase and continue to get better. So I think, yeah, that's, to me, that's in the grand scheme </s><s>[INST] more important, but to each of their own. Speaking of amazing technological development, you have a few videos on this, but how does a rocket engine work? You're wearing some of the instruction manuals, but for one type of it, like what's the fuel, what are the types of different rockets [/INST] that you can kind of give an overview? Yeah, yeah. Ultimately, a rocket engine converts high pressure and heat into kinetic energy. Like that's the only real job of a rocket engine is to take high pressure gas, high pressure gas, very energized, there's a lot of energy involved, and then literally turning that into molecules shooting in one direction, into kinetic energy. So yeah, what you do, basically, I mean, the simplest version of it is, of course, like famously a balloon. You take a balloon, you fill it up with air, you've got a pressure, you let go of it, some of the air shoots out in a general direction-ish, you converted that pressure into kinetic energy. Now, if you start scaling that up, you can continue to do something like that, like cold gas thruster would be kind of the most simple and easiest rocket engine to make, would be a cold gas thruster. And all that is you literally just take air, or specifically nitrogen, because it's a little bit more dense than all the others, or you know, the majority of our atmosphere, you can start as more sparse. You can condense that down a sort of really high pressure bottle, and then just literally shoot it through what's called a de lavel nozzle, which is something that chokes the flow a little bit, gets it into supersonic speeds. Once it's at supersonic speed, you actually can't choke it down anymore. You'll just constrict the flow of mass flow, you'll constrict the air flow. So you actually go opposite. You start making it wider. And once it's already at supersonic speeds, if you expand it and make it wider it actually gets faster and faster. So at first, when it's subsonic gas, you start shrinking. You constrict the flow. It's actually speeding up. Just like a highway. if you go from any of these examples, like a water hose, if you pinch it down and you want to flow the same amount of water from point A to point B through a smaller pipe, you can you can flow more water, you're the same amount of water from point A to point B with a smaller pipe, it just has to go faster. So obviously you can constrict it, but at some point you actually get to a physical limitation and that happens to be the speed of sound. Once it gets to the local speed of sound, you can then actually do the opposite. You can actually expand it back out and you're continuing to convert the pressure into velocity at that point, but it's now super sonic, and what's interesting is while you're doing that, you're actually cooling it down to each bit of that pipe that you're making wider and wider and wider, you're cooling down. So the more heat energy you have to work with, the more work you can actually do. So at some point a hot high pressure rocket engine is the best source of, like that's the ultimate amount </s><s>[INST] of work you can do. And the nozzle, as you're saying, there's a bunch of different design options, but it's a critical part of this, [/INST] how you do that conversion, which basically like, how much can you convert is really like the ultimate game. How much pressure and heat can we convert into thrust? That's really, at the end of the day, that's what a rocket engine is. So you have to have a power form of rocket engine to actually lift the rocket. Well, rocket is mostly just fuel. It's like 90 plus percent, just the weight of fuel. So you just have to lift the fuel that's going </s>

<s>[INST] like the [/INST] geometry alone is amazing. I studied math as an undergrad and I've always appreciated geometry. Um, and just the shapes alone are just look like brilliant works of modernist art. And just obviously, no two are ever the same. Not to mention a lot of them are this unearthly blue color that is just um really startling and fascinating the same color of glaciers. Um you know, in various parts of the world, that blue color is just really amazing. And I also just love how it's sort of this constant shedding from the antarctic continent from Greenland. You know, it's this constant process of snow falling inland and pushing the glaciers further out to sea and then breaking loose. I mean, obviously it seems to be happening faster these days, but it's sort of this constant shedding and sort of, I always like thinking about how the body has something similar. You know, we're constantly shedding and renewing and rebuilding everything. Um and so ice is sort of this constant similar process. </s><s>[INST] Yeah, I did not know you were a math undergrad, so that, I mean you just keep getting more fascinating. Can you maybe take a small step into that direction? What do you find beautiful about mathematics? Why did you journey into that part of the world for a time? [/INST] I liked math especially like so college math, I did some calculus in high school when I got to college math I was amazed that there were no more numbers. You know the digits disappeared, it was just variables concepts you know? Um there was almost no more numbers at all. It was like this totally abstract you know kind of way of thinking but that sort of reflects the natural world and teaches you about the natural world though it's sort of this perfect you know platonic ideal perhaps of the natural world that can still sort of help explain what happens in the natural world. But um just these concepts are so abstract from like life and from you know the natural world. And I was actually getting interested in the natural world at the same time when I was in um at N. Y. U. Studying math. You know I took a tour of Central Park that was pointing the guy steve brill was pointing out these wild edible plants and I was learning to identify the first plants and knowing what's edible, what's not. That was totally fascinating and sort of this kind of thing that I felt like was connecting me to nature and it was balanced with this utterly abstract signs, you know, or utterly abstract lessons I was getting in in math class where I was thinking through series, you know, as we approach infinity. What happens to these equations and concepts of like rings and abstract algebra? I don't know, it was just this dichotomy that I enjoyed both aspects of </s><s>[INST] yeah, the concepts but so so different. This kind of logical, rigorous view of the world and the world of [/INST] biology. </s><s>[INST] Why the big [/INST] how </s><s>[INST] did that feel to take the leap into the, the biological, the mushy mess of the human body from the mathematical, which is all very clean, [/INST] right? It does it does feel like a big step. I think there's more connection than you think. You know, we talked about symmetry of the body earlier. That is a real thing. You know, fluid dynamics of how our various bodily fluids flow and what makes them not flow as well and what makes them flow better. And you know, all these different aspects of science go into the body, you know, everything from hard bone to softer kind of flesh to liquids of various consistencies. Um you know, a lot of science and math does teach you about kind of how the body works, how it can work better. What happens in sort of disease states. Yeah, </s><s>[INST] I suppose there's a there's a connection um there's also kind of sort of computational biologists, this computational equivalence of each of the disciplines, which are becoming more and more fascinating with all the work that Deepmind is doing in the work of genetics, all that kind of stuff, simulating different parts of the body to try to gain an intuition understanding of it. That to me is um super fascinating, but sometimes it does feel like an oversimplification of the way the body really does it because the body is an incredibly weird complex system and it finds a way the adaptability, the resilience, the redundancy that's built in. It's weird, it's and it's incredibly powerful. And so unlike the kind of computer based systems that we build, at least we engineer in the software engineering world, which kind of starts to make you think how can we engineer computer systems in a different way that make them more resilient in the real world? That's sort of robotics question. What do you think about that? What does it take to build a humanoid robot or robots that are as resilient as a human body? How difficult do you think is that problem? Having studied the human body? How hard is the engineering problem of building systems like that guy over there, the leg guy that is as resilient as the human body to the harsh conditions of the real world. [/INST] I think it's very hard and we definitely haven't gotten there yet. I think we could probably learn lessons from people who are trying to grow artificial organs in the lab to eventually, you know, transplant into people which would solve the huge problem of needing to get those organs from others and you know, the rejection of putting a foreign material inside your body, your immune system tends not to like that. Um you know, that has advanced a lot recently. I think I think um some advances actually have been where you know, we pay a lot of attention to stem cells, stem cells, stem cells, we can grow whatever we want out of stem cells. But now there's sort of a recognition that the what we call the extra cellular matrix, which is sort of the, you know, foundation of the body, the thing that holds all the cells into their proper shape and keeps them where they should be. That is actually crucial. And there's probably a lot of signaling that goes on. Like you stick a stem stem cell on the right extra cellular matrix, it will turn into the kind of cell that you want and take the right shape and position and start functioning. I think that's been a huge, huge advance knowing that it's not just these, you know, celebrity stem cells that are the answer, it's this kind of part in the background, this sort of just like laying the foundation the system that you put these cells onto and we're not there yet. But there's definitely a lot happening, a lot of research happening and I think there'll be some advances probably soon. </s>

<s>[INST] the following is a conversation with Richard Wolf, one of the top Marxist economists and philosophers in the [/INST] world. </s><s>[INST] This is a heavy topic in general and for me personally, given my family history in the soviet union in Russia and in Ukraine today the words Marxism, socialism and communism are used to attack and to divide much more than to understand. And to learn this podcast I seek the latter. I believe we need to study the ideas of Karl Marx as well as their various implementations throughout the 20th and the 21st centuries. And in general we need to both steel man and to consider seriously the ideas we demonize and to challenge the ideas with dogmatically accept as true. Even when doing so is unpleasant and at times dangerous. And now a quick few second mention of each sponsor. Check them out in the description is the best way to support this podcast. We got skiff for email. Indeed for hiring on it for supplements, blankets for nonfiction and lin owed for cloud computing, choose wisely my friends and now onto the full ladder reads as always no ads in the middle. I try to make this interesting but if you skip them, please still check out our sponsors. I enjoy their stuff. Maybe you will too. This show is brought to you by skiff a private and and encrypted email. They also do collaboration, all that kinds of stuff. But the emphasis is on the end to end encryption. Actually the emphasis on doing the end end encryption correctly and creating a user interface that's fun and easy to use an intuitive. It's not a giant mess. I mean they do masterfully obviously to manage your email, it should be easy. Clear sort of a compelling, enjoyable experience. As much as email can be so sort of effective at productivity when you're writing one, it's clear [/INST] important </s><s>[INST] things that's private and insecure. Not big tech, not skiff themselves. Not anyone has access to this email but you skip gives you 10 gigabytes of free storage and you can use the mobile and desktop apps from any device. Sign up at skiff dot com slash lex. This show is brought to you by indeed high rank website. I've used them as part of many hiring efforts I've done for the teams I've led in the past. They have tools like indeed instant match giving you quality candidates whose resumes that indeed fit your job description [/INST] immediately. It's </s><s>[INST] really important to use the right tool for the job. The people that you spend many, many, many of your hours in life with and not only do you spend hours with them, you spend the hours doing really difficult stuff so at its best you get a chance to form bonds. I would even say friendship. It's like this life is [/INST] short, </s><s>[INST] some of the most pleasant experiences I've had and the people I've known had is overcoming challenges at work right now. You get 75 bucks sponsored job credit to upgrade your job post and you can get up to 500 bucks extra and sponsored job credits with Indeed virtual interviews at Indeed dot com slash lex offers good for a limited time terms and conditions apply. This episode is brought to you by on it, a nutrition supplement and fitness company. They make Alpha Brain which is a new tropic that helps support memory, mental health and focus. I don't use it every day. I use it as a boost on occasion when I have an especially difficult deep work session when I know it's going to be 234 hours of deep thinking and especially if there's going to be frustrating dead ends. You know, I get excited about an idea, I start thinking through it. I start thinking through the design and then you realize not that doesn't work for this reason, for that reason for this reason and so on and then you have to stay in that failure hold and make sure mentally that you're correct in your evaluation backtrack and see can we sneak around the reason that doesn't work so that that can be really exhausting type of thinking and for that sometimes I will take an Alpha Brain to be a super rocket launcher boost for the mind. You can get up to 10% off alpha brain at Lex Friedman.com slash on it. This show is also brought to you by blink ist Linkous takes the key ideas from thousands of nonfiction books and condenses them down into just 15 minutes that you can read or listen [/INST] to. I can </s><s>[INST] recommend a bunch of books from there. Some of the biggest, best nonfiction books ever are on their sapiens meditations by Marcus Aurelius, Beginning of Infinity by David Dutch and the list goes on and on and on. [/INST] I </s>

<s>[INST] so when you say ancient lakes an impact craters the simple question so impact crater is a crater created by a giant rock hitting the planet [/INST] and yes the big rock that can be metal or rock or it can be a comment as well mostly ice </s><s>[INST] so is that good for life for bad for life foreboding life in book is destroying them both [/INST] it's actually both interestingly enough the building blocks of life the bricks the stuff we are made of carbonate region oxygen and nitrogen and phosphorus the where included on our planet they will be built in just because our planet is made of this kind of rocks asteroids and comets coming together but what we call a Christian so they will be Austin when an asteroid cubs there is a lot of destruction going on but at the same time those rocks they bring with them those breaks of life and the creates lots of energy N. eve the environment around is favorable you might possibly be have some sitting going on that's one of the aspect of what we call been spared you which used to the fact that comets and asteroids have the building blocks of life and better than them and that given favorable conditions they might be able to see that's this is a theory </s><s>[INST] what percentage of you when you're looking up at the stars and wondering about this stuff thinks that panspermia has is what happened on Mars or are on earth which is the building blocks of life came from elsewhere [/INST] well that's you know that's the thing pence is a vector potential vector which means that he actually distribute the stuff of life left and right but it doesn't explain the origin of life it does it's not the environment itself it's just promotes maybe and we still have to prove this but what we know is that the stuff we are made of is very abundant all over the place including in interstellar medium so it's all over it's all over the idea is that maybe just waits to have the proper environment and we know what it needs here on earth it needs water it needs energy shelter a nutrient </s><s>[INST] so you're fundamentally interested in the origin of life and the big leaps that in evolutionary history that could be like an origin of something origin of your curry at sea origin of photosynthesis origin of whatever I just think if we're civilization here on earth only survive another few hundred years I think I'll be a good idea to take a big gun and just shoot life out there like a life gun basically tragically passed by me as a good backup solution so one way is to actually copy our brains an actual humans some complex information and send it out there another way to preserve life is just the like send the basic building blocks cinnamon you bacteria bunch of whatever the rugged organisms on earth just send a bunch of the lease on the building blocks it they they are actual organism so what what is that initial cut or do or do we want to because you said building blocks everywhere [/INST] yeah the bricks of live the carbon nitrogen the tow truck of the they where produced by the death of previous stars so this is how they were produced and stars like our sun I started to form ten billion years ago that doesn't mean that the the sun is the only kind of start that produce you know life for animals life but actually was produced in ten billion years ago that what you're talking about is is a little different right now there are many many efforts to do the type of thing you're talking about which she used to put our DNA on what whatever kind of substrate and preserve it involves either indifference place on earth or on the moon some people are already thinking about putting the NFL on the moon as far as brands concerned and it's drawing towards transhumanism which she is the hence ment of we are through a I and machine learning of course having backups is a good thing for me I would say that taking care of our planets and going back to a place where we are in the Calabria with our environment would be also maybe the best backup possible inclusion do it's sayings right now we are like teenagers who is enough brain to create cool tools but we don't have enough brain to understand yet the consequences of what we're doing N. right now we're paying for this so the question is whether we are going to be able to move forward and learn from the mistakes we're making to become a mature civilization you probably heard of the Drake equation that would be the L. at the very end the duration </s><s>[INST] which version of intelligence of the station [/INST] exactly and and or I'd least the length of time a civilization remains detectable it can disappear from the radar screen literally for a number of reasons the first one is destroy itself for being destroyed by external events or you can become so in tune and sat with the universe and sweat vents the disappears because emails really in the background and it's not visible anymore there are some wild theories they're saying that an exposition might be so advanced that you cannot distinguish them from physical prostheses N. </s><s>[INST] A. [/INST] this was an example doesn't say that this is the case but some people say imagine that in fact all the doctor matter that we we see wait wait we theorized about is in fact some sort of a biological process so you can think about the number of thing personally I believe that what you talk about about preserving our information is kind of what life does we we need to look at ourselves as the different of what the legal sale that started off was in this is what tells you not about the origin of life but in fact the nature of life which is a lot more interesting to me </s>

<s>[INST] right? [/INST] So how </s><s>[INST] it would look, how you would feel. All [/INST] of it. It was it was all of those physical things around that. And watching the process to get there. That was enlightening for me, right? It opened my mind to go, oh, okay, just like there's a process for all these other things. It wasn't just magic and you say, ha ha there it is. It was really a process of refinement, you know, of opening the funnel at the beginning and refining down over time to get to that final, the final and selecting and doing the selection and certain types. You could, certain times there were opinion based design </s><s>[INST] but [/INST] a lot of data, a lot of data driven designs of what can we, what can we deliver in volume, what can we do different things. So you always had these constraints that you had to work with under and sometimes they and the team, not just I would say we need this and we're like we can't deliver that, but maybe we were able to work together to find different design characteristics and different implementation characteristics that could get to that point without what they were describing and instead of yes, yes, yes, no, no, no. Let's find some other way to solve the problem together. </s><s>[INST] Yeah. Is, and I've seen this. Um, and several companies have more closer interact with like Tesla as an example, sometimes, you know, talking about curves, sometimes it's very painful on the engineering side to to deliver a very specific kind of And one question that comes up in my mind is like, well, how far should we go to try to deliver a tiny adjustment in a curve in the curvature or in a like the whatever the form factor is in the color of the material When the cost is like 10 X to deliver. Not financially, but just like how many problems still have to solve. Um, [/INST] I don't know, I don't know </s><s>[INST] if you can say wisdom to that because because when you're thinking about curves, you're designing in the space of ideas, you're like platonic forms kind of thing. Not always grounded to like how much this is how much pain is going to be involved in delivering this, but that's as you should perhaps because then if you're always thinking about the pain required to deliver this thing, you would be too conservative. You wouldn't do the wild ideas [/INST] right? Exactly. But you have to understand again the why behind it. And at nest when we had limited resources, you know, putting a screwdriver in the box, a custom designed screwdriver in the box was born out of those experiences I had at Apple and seeing how you can create something that's emotional. It's part of marketing and it's part of the product experience overall, even though it seems extraneous. I went back and made the design team and the mechanical team changed some curves on the nest, protect the smoke and Ceo detector. We did at nest after they had already tooled it. And I said there said this cost more. I said it doesn't look right. There is a but they're like, oh well we had, I said, no, you're gonna go back and you're gonna make that change. I told you you want, we needed to do it. We had a better looking model that is gonna get done. I know it's gonna be a terrible cost to you. But we already had this discussion and that's the way it's going to have to be. And I'm sorry, but it is what it is. Um you know, because it's better for the customer and it looks better in the pictures and all the other stuff. And then we did it and it was great. And everyone agreed it was great at the end, but it was paying to get there. Um those are where those little details are, where the magic comes out, right? And you know, if you don't do, if you don't take those pains and put in the love, the customer's gonna feel, it's going to be there. They're going to feel the pain or they're gonna feel the </s><s>[INST] love if [/INST] you put it in, right? So it depends on you know, how much time and effort you want to put into something and what really matters to you and to how you communicate what you do. </s><s>[INST] We're human beings after all. Is there something you've learned from the tensions that are natural or that happen in teams when they're passionate and they're trying to solve these problems? Is that the way of life and and there's the human drama is that just is that always go is that it is what it is. Does that make you better? Actually, the drama of the tension between personalities and all that kind of stuff. [/INST] Look a roller coaster ride without ups and downs is no fun. </s><s>[INST] It's [/INST] the journey. </s><s>[INST] It's [/INST] the journey that brings, it brings out the best in everyone were forged were tempered by those experiences, not all the ups but also the downs and that's when you get the humanity and the connection and we can tell these stories till we're blue in the face and smile every time because we did something together that we each of us couldn't do apart. But when it comes together, that's where all the emotions happen and that's where if it's born out of the right reasons and the right story and the right way, That's where the magic happens, not just for the customer, but for how it transforms each person who is working on it and they will never forget those experiences in their life positively and negatively. That happened at the time. But they look back and it's only positive because they did something that mattered. </s>

<s>[INST] so you know, a lot of writers talk about, you know basically suffering the writing process is having, you know, it's extremely difficult and I think of programming especially the or technical writing that you're doing can be like that. Do you find yourself method a logically? How do you every day sit down to do the work? Is it a challenge you kind of say it's you know, it's fun but it would be interesting to hear if if there are non fun parts that you really struggle with. [/INST] So the fun comes when when I'm able to put together ideas of 2-2 people who didn't know about each other. And and so it might be the first person that saw both of their ideas. And so then you know, then then I get to make the synthesis and that gives me a chance to be creative. But the drudge work is where I I've got to chase everything down to its root. This leads me into really interesting stuff. I mean I I learned about Sanskrit night and you know, I try to give credit to all the authors and so I write, so I write to people who know the people authors if they're dead, I I communicate this way I and uh, I got to get the math right. And I got to tackle my programs, try to find holes in them. And I rewrite the program's over after I get a better idea. </s><s>[INST] Is there ever dead ends [/INST] that end? So yeah, I throw stuff out. Yeah. One of the things that I I spent a lot of time preparing a major example based on the game of baseball and I know a lot of people who, for whom baseball is the most important thing in the world, you know. But, but I also know a lot of people from cricket is the most important in the world or suck or something. And and I realized that if if I had a big temple and he was going to have a foldout illustration and everything I was saying, well, what, what am I really teaching about algorithms here? Where I had this, this, this this baseball example. And if I was a person who who knew on a cricket, wouldn't they, what would they think about this? And so I ripped the whole thing out. But you know, I had something that would have really appealed to people who grew up with baseball as a, as a major theme in their </s><s>[INST] life, which is a lot of people. But [/INST] just yeah, </s><s>[INST] still a minority. [/INST] Small minority. I took out bowling too. Uh, </s><s>[INST] even a smaller minority. What's the art in the art of programming? Why why is there of the few words in the title? Why is Art one of them? [/INST] Yeah. Well that's that's what I wrote my touring lecture about. And uh and so when people talk about are really, I mean, what the word means is something that's not in nature. So when you have artificial intelligence, that art comes from the same root saying that this is something that was created by by human beings. And then it's gotten a further meaning, often a fine art which has this beauty to the to the mix and says, you know, we have things that are artistically done and and this means not only done by humans but also done in a way that's elegant and uh brings joy and and has has uh I guess that Tolstoy dostoyevsky. </s><s>[INST] Uh [/INST] but anyway, it it's that part that that says that it's done well as well as not only different from nature in general, then uh art is what human beings are specifically good at. And when they say artificial intelligence, well, they're trying to mimic human beings, </s><s>[INST] but there's an element of fine art and beauty. You are one. That's [/INST] what I that's what I tried to also say that you can write a a program and make a work of art. </s><s>[INST] So now in terms of surprising, you know, what ideas in in writing from sort and search to the combinatorial algorithms. What ideas have you come across that were particularly surprising to you. That changed the way you see a space of problems. [/INST] I get a surprise every time I have a bug in my program obviously. But but but that isn't really what you're more </s><s>[INST] transformation for [/INST] Example in Volume four A. I was </s><s>[INST] especially surprised when I learned about [/INST] data structure called B. B. D. D. But bullying decision diagram because I sort of had the feeling that uh as an old timer. Uh and you know I've been programming since the since the fifties And uh b. d. d. s weren't invented until 1986. And here comes a brand new idea that revolutionizes the way to represent a boolean function. And boolean functions are so basic to all kinds of things in, you know, I mean logic underlies it. Everything we can describe all of what we know in terms of logic somehow and and and and uh proposition in logic. Uh I thought uh that was cut and dried and everything was known. But but but but here comes uh uh randy Bryant and uh and discovers that bds are incredibly powerful Then then. So so I uh that mean it means I have a whole whole new section to the book that I never would have thought of until 1986, 19 until 1990s when I went when people started to uh to use it for for you know a billion dollars of applications. Uh and it was it was the standard way to design computers for a long time until until sat solvers came along when in the year 2000. So that's another great big surprise. So a lot of these things have have totally changed the structure of my book. and the middle 3rd of volume for bees is about that summers. And that's 300 plus pages which is uh which was all about material mostly about material that was discovered in this century. Um and I had to start from scratch and you meet all the people in the field. Right. I have 15 different sets of words that I wrote while preparing that seven of them are described in the book. Others who are from my own experience. </s>

<s>[INST] So in the first two months, in the embryo or whatever. The first few weeks months, eight months. Uh So yeah, the building blocks are constructed the actual, the different regions of the brain, I guess in the nervous system, [/INST] this continuous way longer than just the first few months. So over the very first a few months you build a lot of these cells. But then there is continuous building of new cell types all the way through birth. And then even pas Natalie um you know, I don't know if you've ever heard of Myelin, Myelin, is this sort of installation that is built around the cables of the neurons so that the electricity can go really fast </s><s>[INST] from the [/INST] accident site called axons. Exactly. And um and so as human beings, we might alienate ourselves uh pas Natalie a kid, you know, a six year old kid has barely started the process of making the mature ali God indra sides, which are the cells that then eventually we'll wrap the accents into Myelin and this will continue believe it or not until we're about 25 30 years old. So there is a continuous process of maturation and tweaking and additions and and also in response to what we do. I </s><s>[INST] remember taking ap biology in high school and in the text book, it said that I'm going by memory here that scientists disagree on the purpose of Myelin in the in the brain. Is that is that totally wrong? So like I guess it speeds up the uh okay, but I'd be wrong here, but I guess it speeds up the electricity traveling down the axon or something. [/INST] So that's the most sort of canonical and definitely that's the case. So you have to imagine an axon and you can think about it as a cable or some type with electricity going through and what Meiling does by insulating the outside. I should say there are tracks of Meiling and pieces of actions that are naked without Meiling. And so by having the insulation, the electricity instead of going straight through the cable, it will jump over a piece of milling right to the next naked little piece and jump again and therefore, you know, that's the idea that you go faster. And it was always thought that in order to build a big brain, a big nervous system, in order to have a nervous system that can do very complex type of things, then you need a lot of Meiling because you want to go fast with this information from point A to point B well a few years ago, maybe five years ago or so we discover that some of the most evolved, which means the newest type of neurons that we have as non human primates as, as human beings in the top of our cerebral cortex, which should be the neurons to do some of the most complex things that we do with those have accidents that have very little Meiling. And they have very interesting ways in which they put the smiling on their axles, you know, little piece here, then a long truck with no Meiling, another chunk there and some don't have Meiling at all. So now you have to explain where we're going with evolution. And if you think about it perhaps as an electrical engineer when I looked at it, I initially thought another developmental neurobiology. I thought maybe uh this is what we see now. But if we give evolution another few million years we'll see a lot of Meiling on these neurons too. But I actually think now that that's instead of the future of the brain less smiling, um I allow for more flexibility on what you do with your accents and therefore more complicated and unpredictable type of functions, which is also a bit mind blowing. </s><s>[INST] So it seems like it's controlling the timing of the signal. So they're in the timing, you can encode a lot of information. And so the brain, the [/INST] timing, the chemistry of that little piece of axon, perhaps it's a dynamic process where the milling can move. Now you see how many layers of variability you can add. And that's actually really good if you're trying to come up with a new function or a new capability or something unpredictable in a way. </s><s>[INST] So we're gonna jump it out a little bit. But the old question of how much is nature and how much is nurture in terms of this incredible thing? After the development is over. Uh we seem to be kind of somewhat smart, intelligent cognition, consciousness, all of these things are just incredible ability of reasons. So on emerge in your sense, how much is in the hardware in the nature and how much is in the nurture is learned through with our parents to interact with the environment. So [/INST] it's really both right, if you think about it, So we are born with the brain as babies that has most of his cells and most of its structures and that will take a few years to you know to grow to add more to be better. But really um then we have these 20 years of interacting with the environment around us and so what that brain was so you know, perfectly built or imperfectly built due to our genetic cues will then be used to incorporate the environment in its further maturation and development. And so your experiences do shape your your brain, I mean we know that like if you know you and I may have had a different childhood or a different, we have been going to different schools, we've been learning different things and our brain is a little bit different because of that, we behave differently because of that. And so especially pas Natalie experience is extremely important. We are born with a plastic brain, what that means is a brain that is able to change in response to stimuli. They can be sensory. So perhaps some of the most um illuminating studies that were done were studies in which the sensory organs were not working right? Like if you are born with eyes that don't work then your very brain that piece of the brain and then normally would process vision. The visual cortex uh develops person italy differently and it might be used to do something different. So that's the most extreme. </s>

<s>[INST] But the thing is, There is a magic moment though, like with Alpha zero when the system surprises us in a way where the best people in the world truly learned something from the system in a way where you feel like it's another entity, like the way people, the way magnus carlsen, the way certain people are looking at the work of Alpha Zero, it's like uh it truly is no longer a tool in the sense that it doesn't feel like a tool, it feels like some other entity. [/INST] So there is a magic difference, </s><s>[INST] like where, where you're like uh you know, if an Ai system is able to come up with an insight that surprises everybody in a some uh in some like major way, that's a phase shift in our understanding of some particular size or some particular aspect of physics. I feel like that is no longer a tool. And then you can start to say uh that like it perhaps deserves the prize. [/INST] So for </s><s>[INST] sure, the more important and the more fundamental transformation of the 21st Century Science is exactly what you're saying, which is probably everybody will be doing, is she learning? It's to some degree, like if you want to be successful at unlocking the mysteries of science, you should be doing machine learning. But it's just exciting to think about like whether there will be one that comes along, that's super surprising and they'll make us question like who the real inventors are [/INST] in this world. Yeah, I think the question of isn't if it's going to happen, but when and but it's important in my mind, the time when that happens is also more or less the same time when we get artificial general intelligence and then we have a lot bigger things to worry about than whether they should get the Nobel prize or not. Right? Because when you have machines that can outperform our best scientists at science, they can probably outperform us at a lot of other stuff as well, which kind of the minimum, you know, make them incredibly powerful agents in in the world, you know, And I think it's a mistake to think we only have to start worrying about loss of control when machines get to AGI across the board where they can do everything all our jobs long before that they'll be hugely influential. We talked at length about how the hacking of our minds with mhm algorithms trying to get us glued to our screens, right, has already had a big impact on, on society. That was an incredibly dumb algorithm in the grand scheme of things. Right? Just supervised machine learning yet, that had had a huge impact. So, so I just don't want us to be lulled into a false sense of security and think there won't be any societal impact until things reach human level because it's happening already. And and it's I was just thinking the other week, you know, when I see some scare monger going, oh, the robots are coming. The implication is always that they're coming to kill us. Yeah. And maybe you should have worried about that if you were not going to care about during the recent war there, but more seriously the robots are coming right now but they're mainly not coming to kill us. They're coming to hack us. Mhm. They're they're coming to hack our minds and buying things that maybe we didn't need to vote for people who may not have our best interest in mind. And and it's kind of humbling I think actually as a human being to admit that it turns out that our minds are actually much hacked more hackable than we thought. And the ultimate insult is that we are actually getting hacked by the machine learning algorithms that are, in some objective sense, much dumber than us, you know? But maybe we shouldn't be so surprised because you know, how do you feel about the cute puppies? </s><s>[INST] I love them. [/INST] So you know, you would probably argue that in some across the board measure you're more intelligent than they are. But boy are are cute puppies good at hacking us, right? They move into our house, persuade us to feed them and do all these things. What do they ever do for us? Yeah. Other than being cute and making us feel good bye. So if puppies can hack us, maybe we shouldn't be so surprised if it's pretty dumb. Machine learning algorithms can hack us to </s><s>[INST] not to speak of cats, which is another level. And and I think we should to counter your previous point about there, Let us not think about evil creatures in this world. We can all agree that cats are as close to objective evil as we can get. But that's just me saying that [/INST] okay uh you have you seen the cartoon? I think maybe the onion. Um Well this is incredibly cute kitten and it just says um it's underneath something that thinks about murder all day. </s>

<s>[INST] Yeah, so a little friendly competition could be can do wonders for [/INST] progress. So </s><s>[INST] the topic of mechanism design, she's really interesting. Also kind of new to me except as an observer of I don't know politics and amy, I'm an observer of mechanisms but you're writing your paper and automated mechanism design that I quickly read. So mechanism design is designing the rules of the game. So you get a certain desirable outcome and you have this work on doing so in an automatic fashion as opposed to fine tuning it. So what have you learned from those efforts? Uh If you look to say, I don't know at complexes like our political system, can we design our political system to have in an automated fashion to have outcomes that we want. Can we design something like uh traffic lights to be smart where it gets outcomes that we want? So what are the lessons that you draw from? Network? [/INST] Yeah. So I still very much believe in the automated mechanism design direction but it's not a panacea, there are impossibility results in mechanism design, saying that there is no mechanism that accomplishes objective X. In class C. So so it's not going up, there is no way using any mechanism design tools, manual or automated to do certain things in mechanism design. Can </s><s>[INST] you describe that again? So meaning there is impossible to achieve that? Yeah, they are more likely [/INST] impossible. So so these these are not statements about human ingenuity who might come up with something smart. These approves that if you want to accomplish properties X in class C, that is not doable with any mechanism. The good thing about automated mechanism design is that we're not really designing for a class. We're designing for specific settings at a time. So even if there's an impossibility result for the whole class, it just doesn't mean that all of the cases in the class are impossible. It just means that some of the cases are impossible. So we can actually carve these islands of possibility within these non impossible classes. And we've actually done that. So, what one of the famous results in mechanism design is the Myerson Satterthwaite theorem by Roger. Myerson and Mark Satterthwaite from 1983. It's an impossibility of efficient trade under imperfect information. We show that you can in many settings avoid that and get efficient trade anyway, </s><s>[INST] depending on how they design the game. Okay, [/INST] so depending how you design the game. And of course it's not it doesn't in any way anyway uh contradict the impossibility results, the impossibility results is still there but it just uh finds spots within this impossible class where in those spots you don't have the impossibility. </s><s>[INST] Sorry, if I'm going a bit philosophical. But what lessons do you draw towards? Like I mentioned politics or human interaction and designing mechanisms for outside of just these kinds of trading or auctioning or um purely formal games are human interaction, like a political system. What how do you think it's applicable to politics or? Two? Yeah, Business Uh two negotiations, these kinds of things designing rules that have certain outcomes. [/INST] Yeah, yeah, I do think so. </s><s>[INST] Have you seen success that successfully done? [/INST] He hasn't really Oh, you mean mechanism design or automated automated mechanism design. So mechanism design itself has had fairly limited success so far there are certain cases, but most of the real world situations are actually not sound from a mechanism design perspective, even in those cases where they've been designed by very knowledgeable mechanism designed people, the people are typically just taking some insights from the theory and applying those insights into the real world rather than applying the mechanisms directly. So one famous example of is the FCC spectrum auctions. So, um I've also had a small role in that and very good economists have been worried. Excellent economists have been working on that with no game theory yet. The rules that are designed in practice there, They were such that being truthful is not the best strategy. Usually mechanism design, we try to make things easy for the participants. So telling the truth is the best strategy, but but even in those very high stakes auctions, whether you have tens of billions of dollars worth of spectrum being auctioned, truth telling is not the best strategy by the way, nobody knows even a single optimal betting strategy for those auctions. </s><s>[INST] What's the challenge of coming up with an optimum? Because there's a lot of players and there's [/INST] a lot of players but many items for sale and these mechanisms are such that even with just two items, so one item being truthful, it wouldn't be the best strategy </s><s>[INST] if you look at the history of ai it's marked by seminal events and Alphago beating a world champion human go player, I would put liberators winning the heads up, no limit hold him as one of such event. And what what do you think is the next such event, whether it's in your life or in the broadly Ai community that you think might be out there, that would surprise the world. [/INST] So that's a great question and I don't really know the answer in terms of game solving hints up, no limit texas hold and really was the one remaining widely agreed upon benchmark. So that was the big milestone. Now, are there other things? Yeah, certainly there are but there there is not one that the community has kind of focused on. So what could be other things, uh there are groups working on Starcraft, There are groups working on Dota two, these are video games or you could have like diplomacy or Hannah b you know, things like that, these are like recreational games but none of them are really acknowledged as kind of the main next challenge problem like chess or co or heads up no limit texas hold'em was so I don't really know in the game solving space what is or what will be the next benchmark? I hope kind of hope that there will be a next benchmark because really the different groups working on the same problem really drove these Application independent techniques forward very quickly over 10 years. </s>

<s>[INST] Do you think it's somehow deeply fundamental to human experience is just a trick? So you have like I mean Sam has has really been making me think about this. So, you know, calling free will and illusion. The interesting thing about Sam is it's not just a philosophical little chat with him about free will. He really says he experiences the lack of free will, like he's able to you know, large parts of the day to feel like he has no free will in that same way. Now he thinks that consciousness is um not an illusion, it is, you know, it's a real thing, but at the same, I'm more almost like I'm almost more of like consciousness seems to be a little bit of an illusion in the sense that like it feels like maybe this is a robotics ai perspective, but it feels like in that same way that Sam steps outside of feeling like he has an agency feeling like as a free will, I feel like we should be able to step outside of having a consciousness? Uh huh. So that that from my perspective, maybe that's the hope of perspective for trying to engineer consciousness. But do you think consciousness is like at the core of this or is it just uh just like language or almost like a thing we build on top of much deeper human, the things that makes us human? [/INST] I don't know, I I am attracted to Lanza's notion of bio centrism. I mean it's it's difficult to walk away from the double slit experiment, not wondering why we seem capable of collapsing that quantum wave function. It's very very weird. Um giving rise to even weirder ideas about superposition and spooky action at a distance and things that mitt guys know a lot better than me. But um it seems to me fundamental. Maybe consciousness is the fundamental thing. Um I mean weirdly some of these ancient inculpatory practices, I talked about Peter Kingsley before, so he's not a proponent of ancient psychedelic use, but is a proponent of these ancient rites of incubation that were practiced by pythagoras um parm entities and particles other pre Socratic. And so what were they doing? They were trying to get in touch with consciousness. They were entering into suspended states of animation um in these cave like settings, Pythagoras had built one in his basement and would lie down motionless apparently for long periods of time and what I think they were trying to do um was tapped into and trying to answer this question in their own, you could call it a scientific way, actually less religion than science and what they would discover or try to discover was a state of awareness that is somehow beyond life and death beyond waking and dreaming, where you can be aware of the senses, but also in touch with another reality at the exact same time. What Kingsley calls sensation um that I think is definitely worth exploring </s><s>[INST] well in the way I hope to explore is by trying to build it, but everybody uses the tools Well. No, I do also hope psychedelics could [/INST] help. So how do you build that? I'm curious, </s><s>[INST] that's the whole point of the discussion. This is uh there's a lot of things that can stay here, but let me put simply is I believe that you can go a long way building towards building consciousness by trying to fake consciousness so fake it till you make it as an engineering approach I think will work for consciousness. You [/INST] seem satisfied with </s><s>[INST] that. I I'm satisfied with that because I know how deeply unsatisfied others are, but just wait. So, I mean, I don't know what [/INST] to. So most, </s><s>[INST] most the topic of consciousness is mostly handled by philosophers currently and that's great and there uh philosophers are wonderful and good at what they do. I'm not a philosopher, I'm an engineer and I think the approach there is quite different. I think um Falling in love is different than trying to have a podcast conversation about what is love. Ah you know, I think the engineering effort is just fundamentally different than the philosophical effort and I have a sense that consciousness can be engineered even before it is understood by the philosophers. So I think there's a bunch of things like that in this world that could be engineered before they understood. I think the intelligence is one such thing. I think we'll be we'll be able to engineer super intelligent beings before we're able to understand the human mind. That's um yeah, I mean there's there's less, there's a lot of intuition to unpack there of why that is, but as it stands, that's perhaps my engineering um optimism and engineering ethic under which I operate consciousness is easy to build hard to understand. Okay, other books or movies in your life uh long ago or recently that had a big impact on you. You've you've uh metallic, he is exceptionally well researched. [/INST] The amount of books </s><s>[INST] you read is I cannot even imagine. So is there something in those, in that in those, in your travels through the land of language that's stuck with you? That was especially [/INST] impactful. I mentioned a couple of them. But So I I knew nothing about psychedelics before 2007 and it was in hearing about some of the first psilocybin experiments at Hopkins and then shortly thereafter I went down this rabbit hole. And so the first set of recommendations, all kind of fit in that time period of my life, 2000 and 7, 2000 and eight. It started with jeremy gnarby, um the cosmic serpent D. N. A. And the origins of knowledge. It was a total impulse buy at the Barnes and Noble on Sixth Avenue in new york and wound up introducing me to supernatural by Graham Hancock. Um That that convinced me that there was a long story to psychedelics that um he tried to prove in that book and that we're still trying to prove. I mentioned the connection between ritual psychedelics and cave art. Um This is the neuropsychological model that was first proposed by David lewis Williams at the University of Witwatersrand, the same university where lee berger is by the way in South Africa. So these ideas are old. Um but what Graham did in that book is just um it's it's well worth your time. It's well worth a few reads actually. Uh because it was after that that I discovered Breaking open the Head by Daniel pinchbeck. Um and and a lot a lot of other books that just um kind of blew my mind </s>

<s>[INST] A subsidiary of square and member S. I. P. C. I'm excited to be working with cash out to support one of my favorite organizations called First, best known for their first robotics and lego competitions. They educate and inspire hundreds of thousands of students in over 110 countries and of a perfect rating and charity navigator, which means the donated money is used a maximum effectiveness when you get cash app from the app store, google play and use code and lex podcast, You'll get $10 in cash app will also donate $10 to first, which again is an organization that I've personally seen, inspire girls and boys to dream of engineering a better world. And now here's my conversation with Michael stevens. [/INST] One </s><s>[INST] of your deeper interests is psychology understanding human behavior. You've pointed out how messy studying human behavior is and it's far from the scientific rigor of something like physics. For example. How do you think you can Take psychology from where it's been in the 20th century to something more like what the physicists, theoretical physicists are doing something precise, something rigorous. [/INST] Well, we we could do it by finding the physical foundations of psychology right? If if all of our emotions and moods and feelings and behaviors are the result of mechanical behaviors of atoms and molecules in our brains. Then can we find correlations perhaps like chaos makes that really difficult And the uncertainty principle and all these things that we can't know the position and velocity of every single quantum state in a brain? Probably. But all right. I think that if we you can get to that point with psychology, then we can start to think about consciousness in a physical and and mathematical way. When we ask questions like, well, what is self reference? How can you think about yourself? Thinking, what are some mathematical structures that could bring that about? </s><s>[INST] There's ideas of in terms of consciousness and breaking it down until physics, there's ideas of panpsychism where people believe that uh, whatever consciousness is is a fundamental part of reality, it's almost like a physics law. Do you think? What's your views on consciousness? Do you think it has this, this deep uh, part of reality or is it something that's deeply human and constructed by us humans? [/INST] Uh start nice and light and easy, easy. I think I </s><s>[INST] asked you today has actually proven answer, So just hypothesize [/INST] so yeah, I mean, I should clarify this is all speculation and I'm not an expert in any of these topics and I'm not God, but I think that consciousness is probably um, something that can be fully explained within the laws of physics. I think that our, you know, bodies and brains and, and the universe and at the quantum level is so rich and complex? I'd be surprised if we couldn't find a room for consciousness there. And why should we be conscious, why are we aware of ourselves? That is a very strange and interesting and important question. And I think for the next few 1000 years we're going to have to believe in answer is purely on faith. But my guess is that we will find that, you know, within the configuration space of possible arrangements of the universe. There are some that contain memories of others literally um Julian barbour calls them time capsule states where you're like, yeah, not only do I have a scratch on my arm, but also this state of the universe also contains a memory in my head of being scratched by my cat three days ago. And for some reason those kinds of states of the universe are more plentiful or more likely </s><s>[INST] when you say those states, the ones with that contain memories of its past or ones that contain memories of its past and have degrees of consciousness [/INST] just the first part because I think the consciousness then emerges from the fact that a state of the universe that contains fragments or memories of other states is one where you're going to feel like there's time you're going to feel like yeah, things in that happened in the past. And I don't know what will happen in the future because these states don't contain information about the future. For some reason those kind of states are either more common, more plentiful or you can use the anthropic principle and just say, well, they're extremely rare, but until you are in one or if you are in one, then you can ask questions like you you're asking me on this podcast. Why questions? Yeah. It's like why are we conscious? Well, because if we weren't, we wouldn't be asking why we were. </s><s>[INST] You've kind of implied that you have a sense again, hypothesis theorizing that the universe is deterministic. What's your thoughts about free will? Do you think of the universe is deterministic? In a sense that it's unrolling in particular, like there's uh operating under a specific set of physical laws and when you have to set the initial conditions, it will enroll in the exact same way in our particular line of the universe every time. [/INST] That is a very useful way to think about the universe. It's done as well. It's brought us to the moon, it's brought us to where we are today, right? I would not say that I believe in determinism in that kind of an absolute form or actually I just don't care. Maybe it's true, but I'm not going to live my life like it is </s>

<s>[INST] To support it, please check out our sponsors in the description. And now, dear friends, here's Anna Verbel. Let's go back to the early days. What did the formation of the Milky Way galaxy look like? Or maybe we want to start even before that. What did [/INST] the formation of the universe look like? Well, we scientists believe there was the Big Bang, some big beginning. But what is important for my work and I think that's what we're going to talk about is what kind of elements were present at that time. So the Big Bang left a universe behind that was made of just hydrogen and helium and tiny little sprinkles of lithium. And that was pretty much it. As it turns out, it's actually quite hard to make stars or any structure from that. That's fairly hot gas. And so the very first stars that formed prior to to any galaxies were very massive stars, big stars, 100 times the mass of the Sun. And they were made from just hydrogen and helium. So big stars explode pretty fast after a few million years only. That's very short on cosmic timescales. And in their explosions, they provided the first heavier elements to the universe because in their cores, all stars fuse lighter elements like hydrogen and helium into heavier ones. And then that goes all the way up to iron. And then all that material gets ejected in these massive supernova explosions. And that marked a really, really important transition in the universe because after that first explosion, it was no longer chemically pristine. And that set the stage for everything else to happen, including us here talking today. </s><s>[INST] So what do you mean by pristine? So there's a whole complex soup of elements now as [/INST] opposed to just hydrogen, helium, and a little bit of lithium of elements. Yeah. So after the Big Bang, just hydrogen and helium, we don't really need to talk too much about lithium because the amount was so small. And after these very first stars formed and exploded, they, the heavier elements like carbon, oxygen, magnesium, iron, all of that stuff was suddenly present in the gas clouds. Tiny amounts only, very tiny amounts. But that actually helped, especially the carbon and the oxygen, to make the gas cool. These atoms are more complicated than hydrogen. That's just a proton. And so it has cooling properties, can send out photons outside of the gas cloud so the gas can cool. And when you have gas that gets colder and colder, you can make smaller and smaller stars. So you can fragment it and clump it and turn it into stars like the Sun. And the cool thing about that is that when you have small stars like the Sun, they have a really long lifetime. So those first low mass stars that formed back then are still observable today. That is actually what I do. I try to find these early survivors because they tell us what the gas looked like back then. They have preserved that composition of these early gas clouds, the chemical compositions, until today. So I don't need to look very far into the universe to study all the beginnings. I can just chemically analyze the oldest stars. And it's like unpacking everything </s><s>[INST] that happened back then. It's very exciting. So to just reiterate, so in the very early days in the first few million years, there was giant stars that's mostly hydrogen and helium, and then they exploded in these supernova explosions. [/INST] And then they made these clumps. Yeah, so the first stars... Not pristine clumps. Yeah, so the first stars... Yeah, pretty much fun. So it took a few hundred million years for the first stars to emerge, and then they exploded after a few million years. Kaboom. And then it's like I always consider the universe like a nice soup, and then these first supernova explosions kind of provided the salt, you know, just a little sprinkle of heavier elements, and that made it really tasty. It just changed it completely, right? And that changed the physics of the gas. So that meant that these gas clouds that were, you know, surrounding the former first stars, they could now cool down and clump and form the next generation of stars that now included also little stars. And as I just mentioned, the small stars have these really long lifetimes. The Sun has a lifetime of 10 billion years. Any star that is even less massive will have an even longer lifetime. So that gives us a chance to still observe some of the stars that formed back then. So we are testing the conditions, the chemical and physical conditions of the early universe even before the galaxy formed. </s><s>[INST] Fun. So what's the timeline that we're talking about? What is the age of the universe and what is the earliest time we got those salty delicious soup, clump [/INST] soups with heavier elements? Well, the universe is 13.8 billion years old. Allegedly, yeah. Well, when I was in high school, the universe was 20 billion years old. </s><s>[INST] So the estimate, do you think that estimate will evolve in interesting [/INST] ways or no? I think we have mostly converged, yes, because the techniques are very different now, much more precise. The whole business of cosmology by mapping out the cosmic microwave background. That's a marvelous feat. Maybe the digits will still move around a little bit, but that's all right. </s><s>[INST] The gravitational waves and all that's all the different sources of data kind of [/INST] mapping out this detailed picture of the early universe, that's all this mapping out this detailed picture the early universe. Totally. And so, we think the earliest little stars formed, I don't know, maybe half a billion years after the Big Bang, right? Again, a few hundred million years for the first stars to emerge and then, you know, took some time. So, give or take half a billion years. And that was the time when sort of the very first proto galaxies formed, early stellar structures, stellar systems from which the Mickey way eventually formed, right? So, it was the Mickey was probably a bigger, slightly bigger one. And we know today that galaxies grow hierarchically, which means they eat their smaller neighbors. So, if you're the bigger one and have a few friends around, you're just going to eat them, absorb them, and then you grow bigger. And so, all these little early stars, you know, kind of came into the Mickey way through that kind of process. And that's why we find them in the outer parts of the galaxy today, because they're just kind of deaf and just left there since. </s>

<s>[INST] And so maybe there's opportunities for something like a GitHub for the community. Yeah. Although even GitHub, I might be wrong on this, but the search and discovery for GitHub is not that great. Like I still use Google search. [/INST] Yeah, well, I mean, yeah, well, I mean, maybe that's because GitHub doesn't want to replace Google search. Right. And I think there is room for specialized solutions to specific problems. Sure. I don't know. I don't know the right answer for GitHub either. I just think they can go figure that out. </s><s>[INST] Right. But the point is to have an interface that's usable, that's accessible to people of all different skill levels. [/INST] Well, well, and again, like what are the benefits of standards, right? Standards allow you to build these next level up ecosystem, the next level up infrastructure or next level up things. And so again, come back to hate complexity, C, C plus Python is complicated. It makes everything more difficult to deal with. It makes it difficult to port, move code around, work with, all these things get more complicated. And so, I mean, I'm not an expert, but maybe Mojo can help a little bit by helping reduce the amount of C in this ecosystem and make it therefore scale better. </s><s>[INST] So, I mean, you kind of pack out of packages that are hybrid in nature would be a natural fit to move to Mojo. Which is a lot of them, by the way. Yeah. A lot of them, especially that are doing some interesting stuff, computationalized. Let me ask you about some features. Yeah. So, we talked about, obviously, indentation, that it's a typed language or optionally typed. [/INST] Is that the right way to say it? Which is a lot of them. Yeah. So, either optionally or progressively. Progressively. I think, so people have very strong opinions on the right word to use. Yeah. </s><s>[INST] I don't know. I look forward progressively. Forward to your letters. So, there's the var versus let, but let is for constants, var is an optional. Yeah, var makes it mutable, so you can reassign. Yeah. Okay. Then there's function overloading. Oh, okay. Yeah. I mean, there's a lot of source of happiness for me, but function overloading, that's, I guess, is that for performance or is that, why does Python not have function overloading? [/INST] Oh, okay. Yeah. So, I can speculate. So, Python is a dynamic language. The way it works is that Python and Objective C are actually very similar worlds if you ignore syntax. And so, Objective C is straight line derived from Smalltalk, a really venerable, interesting language that much of the world has forgotten about, but the people that remember it love it generally. And the way that Smalltalk works is that every object has a dictionary in it, and the dictionary maps from the name of a function or the name of a value within an object to its implementation. And so, the way you call a method in Objective C is you say, go look up the way I call foo as I go, look up foo. I get a pointer to the function back, and then I call it. That's how Python works, right? And so, now, the problem with that is that the dictionary within a Python object, all the keys are strings, and it's a dictionary, so you can only have one entry per name. Do you think it's as simple as that? I think it's as simple as that. and so now why do they never fix this? Like why do they not change it to not be a dictionary? Why do they not change, do other things? Well you don't really have to in Python because it's dynamic and so you can say I get into the function, now if I got past an integer, do some dynamic test for it if it's a string, go do another thing. There's another additional challenge which is even if you did support overloading, you're saying, okay well here's a version of a function for integers and a function for strings. So even if you could put it in that dictionary, you'd have to have the caller do the dispatch. And so every time you call the function, you'd have to say is it an integer, is it a string? And so you'd have to figure out where to do that test. And so in a dynamic language, overloading is something you don't have to have. So, but now you get into a type language. And in Python, if you subscript with an integer then you get typically one element out of a collection. subscript with a range, you get a different thing out. And so often in typed languages, you'll want to be able to express the fact that, cool, I have different behavior depending on what I actually pass into this thing. If you can model that, it can make it safer and more predictable and faster and all these </s><s>[INST] things. You think it's as simple as that? It somehow feels safer, yes, but it also feels empowering. Make it in terms of clarity. [/INST] You don't have to design whole different functions. Make it in terms of clarity. Yeah, well, this is also one of the challenges with the existing Python typing systems is that in practice, like you take subscript, like in practice, a lot of these functions, they don't have one signature. They actually have different behavior in different cases. And so this is why it's difficult to retrofit this into existing Python code and make it play well with typing. </s><s>[INST] You kind of have to design for that. Okay, so there's an interesting distinction that people that program Python might be interested in is def versus fn. So it's two different ways to define a function. And fn is a stricter version of def. [/INST] What's the coolness that comes from the strictness? So here you get into what is the trade-off with the superset? Yes. Okay, so superset, you have to or you really want to be compatible. If you're doing a superset, you've decided compatibility with existing code is the important thing, even if some of the decisions they made were maybe not what you choose. So that means you put a lot of time in compatibility, and it means that you get locked into decisions of the past, even if they may not have been a good thing. Now, systems programmers typically like to control things. And they want to make sure that, not in all cases, of course, and even systems programmers are not one thing. But often, you want predictability. And so one of the things that Python has, for example, as you know, is that if you define a variable, you just say x equals 4. I have a variable named x. Now I say some long name equals 17, print out some long name, oops, but I typoed it. Well, the compiler, the Python compiler doesn't know, in all cases, what you're defining and what you're using. And did you typo the use of it or the definition? And so for people coming from typed languages, again, I'm not saying they're right or wrong, but that drives them crazy because they want the compiler to tell them, you typoed the name of this thing, right? And so what FN does is it turns on, as you say, it's a strict mode. And so it says, okay, well, you have to actually intentionally declare your variables before you use them. That gives you more predictability, more error checking and things like this, but you don't have to use it. And this is a way that Mojo is both compatible because defs work the same way that defs have always worked. But it provides a new alternative that gives you more control and allows certain kinds </s>

<s>[INST] about ourselves [/INST] too? Look at each other's </s><s>[INST] skin color or [/INST] hair texture. And then to decide, well that's a black or that's a white or that's a latin or that's an asian or that's a whatever the that's something that we should outgrow. A person might say </s><s>[INST] that's [/INST] a relic of </s><s>[INST] a kind of tribal [/INST] society, of a kind of pre modern society where </s><s>[INST] we built [/INST] real structure on the basis of such superficial difference. A person could say that on the other hand, I </s><s>[INST] am a [/INST] black american. I mean, that's part of my identity, that's part of my heritage. It's part of </s><s>[INST] the [/INST] stories that I tell myself about who my people </s><s>[INST] are. [/INST] Why why do I need a people, why do I need a narrative of dissent in which I affiliate with </s><s>[INST] a [/INST] racially defined people. Do I really need that. I mean, I think that's an important question. I in fact this is a confession. </s><s>[INST] Think [/INST] of myself as black. I could think of myself as simply human. I could not identify specifically as black. I could, I could say my my eyes are brown too. So what I'm a brown. I mean, you know, I'm going to invent a group based on my eye color. Um, I </s><s>[INST] weighed 200 [/INST] £90. I'm going to have a body size group. I'm a plus 200 that's </s><s>[INST] quote who [/INST] I am close quote. I don't do that. I came from Chicago. Yes. I do have a certain sense of affinity with my hometown. I'm a Chicago born Person. But frankly, I haven't lived in Chicago since 1979. That's a long time. I wear my Chicago origins very, very lightly. I would not go to war with someone from Cleveland or ST louis and fight to the death with that uh ST louis person or that Cleveland person </s><s>[INST] based upon the fact [/INST] that we come from different cities </s><s>[INST] and you have even abandoned in your heart, the Chicago bulls. [/INST] There's some Chicago that's still in me I suppose. But it's not, it's not very deep. It's not quote who I am anymore. And I'm wondering, I'm here. I'm trying to pose the question why is it that being a descendant of african slaves should be who I am. So there's some answers. One answer is </s><s>[INST] people [/INST] will look at me and deal with me differently based upon what they </s><s>[INST] see. [/INST] I don't have control </s><s>[INST] over that. I'm [/INST] going to be perceived as a member of a group. Whether or not I elect to affiliate myself with that group </s><s>[INST] or [/INST] not. </s><s>[INST] Therefore [/INST] I need to be mindful of the fact that regardless of what my internal </s><s>[INST] orientation is, [/INST] the world will perceive me in a particular way and will perceive me </s><s>[INST] differently [/INST] based upon the color of my skin. So a police officer who stops me at two o'clock in the morning </s><s>[INST] because my [/INST] tail light is out and ask me for </s><s>[INST] my automobile [/INST] registration and I reached quickly to the glove compartment to get my registration and the police officer said, show me your hands and I don't quite hear what he says or I ignore what he says is I'm getting my document out of my glove compartment, but the police officer thinks because I have not responded to his demand to show my hands that I might be reaching for a weapon. And the police officer sees that I'm black and fears that the likelihood that I might have a weapon is higher because in that town at that time, a lot of the people who get stopped with weapons in their car happened to be black and male and so on and he pulls his weapon and he discharges it and I'm bleeding out there and I'm dead now. And all of that is a possibility that's very real and it's based upon the color of my skin and therefore when he stops me, I keep my hands on the steering wheel and I don't go to the glove compartment and I'm fearful of the fact that he might mistake me for a criminal etcetera. Or I walk into a high end store clothing store. I see you're nicely dressed their </s><s>[INST] legs. I'm [/INST] not, but that's okay. I do have some good clothes at home. I just didn't wear them here </s><s>[INST] today. [/INST] But you know what I mean? And and the clothing, the salesman and the clothing store either treats me like uh you know, an old friend and is warm and welcoming and what can I do for you sir? And let me show you this and that and what are you looking for and what? Because he thinks I'm going to spend $1000 there that day and he's gonna get a 5% commission or whatever it is. And you know, he either does that or he ignores me and looks at me with suspicion and thinks I might be trying to shoplift something or thinks I'm Only gonna spend $50 and not $500 and therefore I'm not worth his time. And I'm aware of the fact that when I go into the clothing </s><s>[INST] store, especially [/INST] the high end places where I can buy some by a good suit or you know, buy some really good dress shirts or slacks that fit me well and so on, I'm aware of the fact that I may not be taken seriously by the salesman based upon the fact that he's looking at me and he </s><s>[INST] sees a [/INST] black person and therefore um, I dress up before I go to go out to buy </s><s>[INST] clothes to get, [/INST] you know, because I want to present myself as not someone who just walked in off the street, but as one of those black people who is really prepared to spend some money in the store so that I can be treated with respect. And I have to carry the burden such as it is </s><s>[INST] of [/INST] knowing that I need to earn the being taken seriously by overcoming the suppositions that people may have about me based upon the color of my skin, something like that. </s>

<s>[INST] So physics and science aside, it's hard, uh it's both, I would like to believe and it's hard to imagine that anybody would be so evil as to orchestrate parts of this from within the United States government. That's very difficult for me to imagine. [/INST] You know, what the election, there's people and I won't elaborate. I won't get into it any, any, any controversial subjects. But what have you, there's some people that don't have any problem at all perpetrating any level of evil people like you and I who have hearts and we have depth of soul. We we couldn't imagine it. But there's other people wouldn't even be a second thought. I mean, I've seen some horrific incidents in my career that I go home shaking my head at night going, human beings are just they're not wired, right? You know, I mean, I look at animals, I love animals, I love dogs especially, right? And I and I see this dog park when I trained to fly airplanes now and something I wanted to do. And there's a dog park across from the airport and there's 60 dogs and there's bones flying up in the air and shoot toys and sticks. And they're running around having the time of their life, right? And they're all getting along and they're not hurting each other. They're not violating each other. They're they're not canceling each other. And I'm going, we really need to learn from these dogs. Like, right. And and like I just yeah, I mean sometimes it sounds crazy, but I think they're better. They're better species than people unless there rabbit, they don't hurt on purpose. They don't, you know, they don't cut you off in traffic and throw you the middle finger and you know, just they just don't do these these acts of humanity that sometimes are so vicious. </s><s>[INST] Why do you think these conspiracy theories of which there is a lot. Take hold Why? Why do you think so many people believe some version of different conspiracy theories around 9:11. [/INST] Well, you know, like my many things in life, it leaves me a little conflicted. I have to say this. I am at the point now, I don't know who to believe anymore. So I could see that lending a hand to someone who's already a Doubter going, oh yeah, look, that's exactly, that's what they're doing, right? I mean, you know, look at this whole virus. Like who do you believe? Like where you come from? You know like, and, and you know, if you plant that seed, it's like that little campfire were talking about earlier, right? And you just toss a little gas into those embers, you gotta fire. Now. I also think there's a lot of people with a hell of a lot of extra time on their hands, right? And it really bored. You know the tour combined dialects. Yeah man, you know like look, I was a three job charlie, right? You know, one guy used to say to me anything, but but home I go, no, I I got deadlines, responsibilities, you know, like that's, that's what it comes down to is like, I mean look, we all, we all have our hobbies and things we like and you know little nuances and that's what makes us special were unique. Every person is unique being. But I also think some people just just, they want to cling to something like we all want to feel accepted and belong to something. So all of a sudden you, you grew up with these people and you all believe this fervently like yeah, yeah, yeah. You know they did it, they took it down, they took it down and and now you start going yeah. And I think what happens is when you're in company of people and you start telling each other the same thing often you freaking believe it. I mean if you keep telling me I got a great head of hair, I'm gonna go you know what I do but no, I don't. I mean right, I got that waving, bye bye. Do but like but you know, I think when you start hearing something often you start believing it but I'm not gonna I'm not gonna doubt their intelligence, I'm not going to doubt their intentions but I just don't see it as being plausible. I just it would be too yeah, too big of an operation to to successfully happen. You know, I mean look, there's other things that you know, I I won't say it on the interview there, but like I have my doubts with certain things. Uh you know that that </s><s>[INST] I mean conspiracy theories take hold for a reason because some of them are [/INST] true, you know, </s><s>[INST] the hard thing is just to know which ones is the problem [/INST] when you don't have facts, right? </s><s>[INST] You know, sometimes [/INST] when you don't have facts when you don't have figures and you don't have science, it's hard to take someone's word on it. You know, I had a conversation with someone a while back right? And the guy is like a just just dedicated atheist and he thinks I'm an idiot for believing in God. And he's like, yo, you're one of those jerks who believes in creation. And I said, well I do well, what about the big Bang theory? And he's going on his diatribe about the science and the gases and the chemistry and I'm going, dude, I barely got through high school chemistry slow down and he went on a tangent and all of a sudden I stopped, I went, uh, who, who created the gas and the molecules and stuff you're talking about in the collisions and he was furious and stormed off and I got him and again, I had no facts. I had no figure he didn't either, but I stumped him. But sometimes when you can't show some people need to see something tangible, they need to see it in their hand to believe it. And that's, that's the real hard thing about faith. I see it in action, people restore my faith. And then I say to myself what it can't be that many dummies in this world, if there's so many billions of us believing in this higher power, that's higher, right? I mean, and you said you said earlier, like you believe most people are good and I do too the bad outshine the good because the bad get the press right? Well if it bleeds it leads, that's just, you know, like think about it how many more damn zombie apocalypse movies, can we make right? I didn't even know it was that many zombies and it just seems like every other show is just guys like, you know, bashing each other's heads in with bats with nails in it and it's like after a while it's like, gosh, you got to get a new boogeyman, you know, right? Like but seriously like </s>

<s>[INST] That's exactly right. Yeah. So any revealing any attacking any power center for the corruption for the flaws they have uh [/INST] irrespective of like your political agenda, your political ideas. </s><s>[INST] So that and that's what I mean about sort of the war in Ukraine, there's several key players, NATO Russia Ukraine china uh India, you mean there's several less important players, maybe some of the like Iran and like Israel and maybe africa and what great journalism take requires is basically revealing the flaws of each one of those players irrespective of the attacks you get and you're right that throughout any particular situation there is some, some parties that are worse than others and you have to um way your perspective accordingly, but also it requires you to be fearless in certain things. Like for example, I don't even know what it's like to be a journalist covering China now. [/INST] Oh, that's an exact case of like China has made it so difficult to be a good journalist that they've effectively squashed criticism because to be a journalist in china means constantly risking your life every single day to criticize the government. And so the best journalists are a lot of times outside the country um or they have sources inside the country who are like, there's like this, you know, different, there's layers to the journalism where there's insiders who are leaking information, but they themselves cannot publish because it's like, it's, you know, it's it's extremely risky. So yeah, I think, I think as a society, one measure of how healthy the political structure is, is how well you can criticize it without fearing for your safety </s><s>[INST] in that sense, the chaos and the bickering going on in the United States politics is a good thing that people can criticize very [/INST] harshly, very harsh </s><s>[INST] and be in terms of safety are pretty safe. [/INST] Yes, absolutely. I think our only challenge is like, where it gets dangerous is around like top secret information, the government comes down so hard that the danger in covering politics here is you can expose something that's top secret that should be exposed and they'll ruin you. </s><s>[INST] So that's where you again give props to snowden for stepping up. [/INST] 100%, </s><s>[INST] What's the origin of of uh the suspender wearing batman? What how did you come to do what you do? Like what we talked about where you are and how your mind works. But how did it start? [/INST] I've kind of always been interested in fraud or or at least I saw fraud early on and I was just curious about what is this. I didn't know what I was really looking at. So basically my mom got cancer when I was in high school and it was pretty traumatic. I mean she's fine. She had thyroid cancer which is, we didn't know it at the time. It's like cancer is cancer, but it's fairly easily treatable with surgery. Uh It's one of the better, you know. Survivable ones. And I just watched her get like bombarded with all these like phony health scams. You know, just like Colonial Silver, you know, all these different like remedies. And she was very into, you know, all the different ways that she might treat her cancer. And obviously surgery is very daunting and yeah, I was just confused. I was like why are we doing so many different remedies? That all seems very dubious health value later. I find out that these are like all grifters. I mean they take advantage of free speech in America to like advertise their products as you know, life saving miracles, whatever. When they're of course not. Um eventually she got the surgery, thank God. But I know people in my life who their parents passed away because because they didn't have the surgery, they instead took the alternative option. I know like I don't want to go into specifics because I don't want to mention their specific case. But their uh family member went to Mexico for some alternate treatment, health treatment instead of getting an easy surgery and they died. And so it's like I realized, you know, where is the outrage about this? Where's the who covers this stuff? And I realized, well, not many people do. Then I went to college, I was getting a chemical engineering degree and all my friends are like telling me, you know, hey, you should come to this meeting. You know, we don't need this like you're doing this engineering stuff. That's great. You're gonna make like 70 K a year. But don't you want to get like rich now? Like why wait till you're 60 </s><s>[INST] years old to retire? Like you can [/INST] be rich now lex So I'd go show up to a hotel and there'd be an MLM like multilevel marketing, you know, pitch for uh Amway or whatever it was that day. And I was once again fascinated. I didn't know what I was looking at, but I was like, what is this weird game, we're all playing, where we sit in this room, we're looking at the speaker who says he's so successful, right, But why is he taking a friday or a saturday to do this? You know, pitch at night and they're gonna, telling me I'm gonna be financially free, but they're working on their saturday and sunday and so it's like, how financially free are they? So just like confused. I was like, you know, none of my friends were rich, they all said they were gonna be rich. No one ever seemed to get rich. And so I was sort of baffled by what I was looking at later, I graduate, I had no interest in doing engineering, which we can kind of get into, but I want to do something in media. Um and I started covering a variety of topics, but eventually I sort of revisited this interest in fraud. And I started talking about these kind of get rich quick grifters that were online, sort of the Tai Lopez variety, you know, 67 steps or you know, whatever like five steps to get rich, five coins to five million. You know, these get rich quick schemes that a lot of people were interested in, No one seemed to get rich once again, except for the people at the tippy tippy top selling the get Rich quick thing. And I was like fascinated by the structure of it. I was like, does nobody see what this is, like does nobody get it? So I started making a series of videos on that and the response was like palpable. I mean it was like I've made a lot of stuff before that I had made stuff that got a million views. I had like some marginal success but the response of like the emails that came in the, I could tell this work even though it had far less views at the time, was having a different level of impact. And so I was really interested in one of my problems with engineering was from my standpoint, I did chemical engineering at texas A and M. And like I was like, is my future just gonna be in a chemical plant improving some process by 2%. And it's like my gift to the world. Like I just, I didn't see the hard impact and that maybe that's a lack of imagination because chemicals matter, but I needed, I wanted to see an impact in the world. And so when like I did started doing this fraud stuff exposing fraud. I like clicked in my brain, I was like, whoa, this is kind of doing what I want to do. And so I started posting videos at first, it really focused on like get Rich quick scheme Grift E advertising, which I think is super predatory and we can go into why. But um it eventually graduated to crypto and it's snowballed I guess because now we're talking to sandbag. Gottfried, </s>

<s>[INST] so that they are not traumatized. So do you, the N-word should not be removed from Huck Finn, Adventures of Huck Finn, [/INST] or from the works of James Baldwin and Toni Morrison? Not at all. In fact, it seems to me that the bolderization of these great artists' literary work, as far as I'm concerned, highly objectionable, </s><s>[INST] highly objectionable. When is it okay for a white man to say the N-word [/INST] with a hard R? Well, you know, here we need to focus on the word say. Is it ever okay for anyone, you know, black, white, pink, yellow, I don't care, red, orange? Is it okay for anyone to use this word in a way to put down people, to terrorize people, to intimidate people? Answer, no. But, you know, and I'd say that black person, I've seen, I mean, by the way, I've seen black people use this word to try to intimidate, put down other black people, bad. So I'm against it with a black person, white person, doesn't matter. On the other hand, on the other hand, imagine a white person who is giving a lecture on the history of American racism, a lecture on the history of American racism. And in giving that lecture, quotes the, you know, white racist politicians who until fairly recently in American life, use the infamous N word. So imagine a white history professor giving a lecture about the history of American racism and says, in 1948, this is what so-and-so running for the presidency of the United States said. And then quotes a paragraph or two in which the infamous N word is featured. Is that bad? No, that's not bad. No, that's not bad. Sounds like a perfectly good lecture. And I'm glad that you put the infamous N word in there so that we can see that as recently as 1948, people running for the presidency of the United States openly used the word. That does not bother me. I'll say this too. Now, you know, somebody says, well, you know, nice job, Kennedy, but you've, you've limited it to over here. You've put it in an academic setting. What about other settings? It does not bother me. Let's imagine somebody who's a comedian, a white comedian who is satirizing word usage. Let's imagine a white comedian who is satirizing our current practice and wants to poke fun at the way in which, let's imagine you have a black rapper who invites people on stage. And let's suppose they invite a black person on stage and they're perfectly happy when the black persons flout with their lyrics. They invite a white person on stage. The white person is, you know, that doesn't really sort of mystified, but it comes on stage. And flout with what the rapper says, including the infamous N-word, and then the black rapper gets mad. Imagine the white comedian who satirizes that, pokes fun at that, and in poking fun at that, says the infamous N-word. Am I angry? No, I'm not angry. </s><s>[INST] Not angry at all. What if in the process of satirizing [/INST] that comedian is not very funny? You say that bad joke, you were not funny. I don't object to the use of the infamous N-word. I just say, you know, mm, you're not very funny, N-word? </s><s>[INST] I just say, you know, you're not very funny. But because there's a line, when the joke is not funny, it just seems like the comedy's used as a cover to actually say something hateful. It's interesting thing about comedy. I feel like the funnier you are, the more you can get away with. Probably. And that's something to do with the thing we said earlier, which is when you use words that have power, you should do so with skill and competence [/INST] and the responsibility those words carry. Again, the cases that I'm most familiar with are the cases involving teachers, professors, you know, academic, and it is said sometimes, oh, you know, why do I object? I object, sometimes people say, because, you know, I suspect that this teacher just wanted to say the word and that all of this is a cover, a pretext. Do I, you know, in my sense, my sense of it is, no, I don't think it's a pretext. If, you know, if it's pretextual, that's bad. But in my experience, I have not seen that. </s><s>[INST] I don't believe that that's what's going on. I agree with you on that, but sometimes I do see people that kind of have this fly flying towards the light, desire to say something controversial and edgy, and they don't realize that there's a responsibility there. There's a skill that you should, you shouldn't just say, I mean, actually when comedians first start out, they'll sometimes go into that territory. They'll say edgy stuff that's totally not funny. And then you realize this is not like the edgier the thing, the more skills required to really serve. Like if you're cooking as a chef, a poisonous fish, there's a responsibility on how to cook the damn thing [/INST] so you don't poison the people eating it. I would agree, but to get back to your question, let's imagine that somebody produces a new set of Lenny Bruce albums. So Lenny Bruce was white, Lenny Bruce used the term nigger in his sets. Question, would I want Lenny Bruce's albums now to be purged of the infamous n-word? </s><s>[INST] My response, absolutely not. There's another follow-on sort of question, what you think, I've seen interviews you've done about this particular book, the title of those interviews on YouTube and elsewhere, would use the full word. What do you think about that? [/INST] Should I use this word in the title? In my view, the answer would be yes. Again, there are people, I've been on interviews, I've been on stage with people who had a different conclusion reached. And I respect a different way. Again, there is a place for euphemism. Again, it all depends, I'm not offended. Let's imagine that you posted this and you had asterisks instead of spelling it out. Would I be offended? No, I wouldn't be offended. I would prefer the full spelling, but I would understand where you're coming from. Would it offend me? </s>

<s>[INST] FBI still very careful, they [/INST] were very careful. They they pretty much watched me and and and At one point I had a house in the country with one neighbor at one that house was for sale. So the FBI bought it and they put a couple of agents down and just keep a closer eye on me. There was no indication that I was still active, but they were still cautious and um but at one point they they were able to plant a bug in my kitchen listening device and I, my wife and I didn't get along very well, you know, there was a lot of friction and she was constantly complaining about things and you know, I got sick and tired of it. And one day we had an argument in the kitchen and I, I chose to deploy the nuclear option. And that is, that is telling her what I sacrificed to be with her too. So she would understand that I am, they're on her side, I'm supporting her if something doesn't quite fit. It is not because I don't love the both of them Chelsea and and Penelope. So when I said that the listening device was active, so the FBI was hearing my confession, I was once a KGB agent, blah blah blah blah blah. And I quit because uh because of and and state state here because of you and Chelsea. And that also made it clear to the FBI that I wasn't active anymore. They had both of that. So now they knew an attempt to turn me would have been useless because you know, because you turned somebody who's active, but they figured they had there was enough reason to treat me nicely because they figured that I had a lot of information that was as as aged as it was, but it was still important for the FBI to get to know. And so one day there was a friday evening, I'm driving back home from the office and I'm being stopped by a um state state state police. Um, as I'm going through the toll. Uh, it's a bridge over the Hudson and then they had to pay a toll. And he waved me, he got me right where stopped and he said could you please move over here, It's a routine traffic stop and thought nothing of it. I had forgotten at that point that I once was a spy. You know it's like this was gone and and then he said could you please step out of the car? That should have aroused my suspicion. That's unusual. Right routine traffic stop. Yeah I did it no problem. And then again somebody came from the right came uh into my view and he flipped this uh I. D. And he said FBI we would like to have a talk with you. No this is my now friend joe Riley who who actually is the he's the godfather of trinity in my last child. But anyway he told me later that when when I heard that phrase, all the blood left, my face became totally white. Um but I recovered very quickly and he said it himself. So you know he they took me to a vehicle and there was another agent in the vehicle and he had a gun strapped to his ankle. So it was pretty real first question I had so am I under arrest? And the answer was no. And then my instinct kicked in in my ability to to operate in very well under high pressure situations. And I asked him so what took you so long? You know the intent of that was to um two d defuse any kind of tension. </s><s>[INST] And [/INST] I saw a smile, </s><s>[INST] instant friends. Uh [/INST] Yeah I I knew I knew that I had to make them like me and I'm I think by now I know I'm a pretty pretty likable person. So </s><s>[INST] so [/INST] uh and I when when they took me to a motel which they had rented, there was an uh to to uh wings at the right angle. They had one, they bought all the rooms in one wing and they had a guard at each end of that wing. And they took me in the middle and there were some props there some binders with labels. And I immediately thought this is pretty silly because what I know what I noticed that the the labels all referred back to my early years, I knew that they didn't know much else. So um I told joe that afterwards and that was not the great idea. But anyway uh but but I volunteered made the following statement before we even started the the interview. I said I know there's only one way for me to end my family To have a chance to get through here without much damages if I'm if I'm completely 100% cooperative and this is my intent to do exactly that. </s><s>[INST] Alright [/INST] so we spent about two hours in the interview, they allowed me to call my wife tell her that I'm going to be late. That indicated to me already that they would let me go. And after two hours they let me go. Um, but they had the area covered with all bunch of people and the head of that, that team talk to me and he says, if you think of running, we got every intersection in this area covered. You can't, I didn't say anything, but you know I had no no thought of running. So and that was </s><s>[INST] the beginning [/INST] of another phase of my life where I was cooperating with the FBI for quite a while and living still undercover for several years until I had real good documentation and became an american citizen seven years ago </s><s>[INST] today. Seven years ago. So recently. [/INST] Yeah, quite recent the bureaucracy took a long time to figure out how to how to make me real and how and also not put me in in, in the witness protection program, you know, to keep my name and then just you know, make everything like official. So for instance, I had to change my birth year uh simply because if I, Jack Barsky was born in 1940 for if I kept 1940 for the FBI would have helped me commit a crime because I would have collected Social Security of four years sooner. So, and anyway, yes, it took quite a while. And when I finally got the call from the office of Homeland Security, uh, the lady says, uh, this is agent. So and so from Homeland security, can you comment to the office tomorrow? And uh, I said, um, let me look at my calendar and then I said, wait a minute. What am I talking about? What time do you want me to be there? Because I had waited for that moment for a long time and I was sworn in right then. And there </s>

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

<s>[INST] on that one. So those two things are fascinating. So how do you have as a leader as that self awareness? So you just said it's really hard to be self aware. So for you personally, or maybe for other leaders you've seen or look up to, how do you know the both of the things you're doing are the wrong things to be doing, the way you speak to others, the way you behave and the things you're not doing, How do you how do you get that? There's [/INST] two aspects that one is like processing feedback that you're getting. So </s><s>[INST] how do you get feedback? [/INST] All right. So are you getting feedback? Right. So one way we do it, for example, discourse, we have three co founders and we periodically talk about decisions before we make them. So it's not like one person can make a mistake or like, wow, that's, you know, there can be misunderstanding things. So it's part of like, group consensus of leadership is like, it's good to have I think systems where there's one leader and that leader has the rule of absolute law are just really dangerous in my experience for communities, for example, like if you have communities run by one person, that one person makes all decisions, that person is gonna have a bad day, something could happen to that person. You know, something, you know, there's a lot of variables. So like at first when you think about leadership have multiple people doing leadership and have them talk amongst each other. So giving each other feedback about the decisions that they're making and then when you do get feedback, I think there's that little voice in your head, right? Like or your gut or wherever you want to put it in your body. I think that voice is really important. Like I think most people who have any kind of moral compass or like want to do, most people want to do the right thing, I do believe that. I mean there might be a handful of sociopaths out there that don't but most people, they want other people to think of them as a good person and why wouldn't you? Right? Like do you want people to despise you? I mean that's just weird, right? So you have that little voice that sort of the angel and devil on your shoulder sort of talking to you about like what you're doing, how you're doing, how does it make you feel to make these decisions right? And I think having some attunement to that voice is important, </s><s>[INST] but you said that voice also for I think there's a programmer situation to where sometimes the devil on the shoulder is a little a little too loud, so you're a little too self critical for a lot of developers, especially when you have introverted personality, how do you struggle with the self criticism of the criticism others. So one of the things of leadership is to do something that's potentially unpopular or where people doubt you and you still go through with the decision. So what's that balance? Like I [/INST] think you have to walk people through your decision making right? Like this is where blogging is really important. Communication is so important. Again, code language is just another kind of code is like here is the program by which I arrived at the conclusion that I'm gonna reach, right? It's one thing to say like this is a decision, it's final deal with it, right? That's not usually satisfying to people. But if you say, look, you know, we've been thinking this problem for awhile. Here's some stuff that's happened. Here's what we think is right? Here's our goals here is we want to achieve. And we've looked at these options and we think this available options is the best option. People be like, oh, ok, right. Maybe I don't totally agree with you, but I can kind of see where you're coming from. And like I say, it's not just arbitrary decision delivered from a cloud of flames in the sky, right? It's like a human trying to reach some kind of consensus about goals and their goals might be different than yours. That's completely legit, right? But if you're making that clear, it's like, oh well the reason we don't agree because we have totally different goals, right? Like how could we agree? It's not that you're a bad person is that we have radically different goals in mind when we started looking this problem </s><s>[INST] and the other one you said is passion, so or hard work. Sorry, uh [/INST] those are tied together to me in my mind, I mean that's a hard work compassion like for me like I just really love the problem discourse is sending out to solve because in a way it's like there's a there's a vision of the world where it all devolves into facebook basically owning everything and every aspect of human communication, right? And this has always been kind of a scary world for me. Um first because I don't think facebook is really good at execution, I gotta compliment them, they're very competent in terms of what they're doing. But facebook has not much of a moral compass in terms of facebook cares about facebook really, they don't really care about you and your problems, What they care about is how big they can make facebook right, </s><s>[INST] is that you're talking about the company or just a mechanism how facebook works kind [/INST] of both really right? Like and the idea with this course, the reason I'm so passionate about it because I believe every community should have the right to own themselves right? Like they should have their own software that they can run that belongs to them, that's their space where they can set the rules and if they don't like it, they can move to different hosting or you know, whatever they need, they need to happen can happen, but like this, this idea of a company town where all human communication is implicitly owned by WhatsApp instagram and facebook. And it's really disturbing to because facebook is really smart, like I said, they're great execution buying and what's happened buying instagram were incredibly smart decisions. Um and they also do this thing on, if you know, but they have this VPN software that they give away for free on smartphones and it indirectly feeds all the data about the traffic backed facebook so they can see what's actually getting popular through the VPN right? They have low level access to the network data because users have let them have that. So, </s>

<s>[INST] So you want to be more the en esa unless the end user. [/INST] Exactly, exactly that way, that way I'm listening to the day of combat, That's right, We're watching you pee, but basically, you know, it's, I guess what I would, what I would come back and say is uh if you understand how things interact on a fundamental level and what type of games exist and what type of interactions exist then you can transcend a lot of the uh the systems you it's almost like a cook versus if I can make certain things in the kitchen, I can but I am not a chef, you could give me a bunch of ingredients and I could probably cook not well but a couple of different things but a master chef, you know, would be aware of the implications of all of the things that they're doing, you know, extra time in the oven, less time in the oven putting this, you know flavoring or spice in, you know what you're doing with various things. And also they can make they can turn all of these ingredients into chinese food and they can turn all these ingredients into italian food and they can turn all these italian food ingredients into chicken parmesan or it could turn into a lasagna but they are not limited to a specific thing because they have knowledge of how food interacts, how what it does to create taste, but it does create texture. So to come back, let's take rock paper scissors, Rock paper scissors is built on the idea of a couple different things. Actually I'll tell you what can I may I ask you a question, what's your favorite dinosaur on the same on three, we'll go 12, three t rex T rex, I'll meet you know, a man, this is we're gonna be best friends. So uh it's okay. Uh so what's the first question when you say, hey, let's play rock paper scissors is like a rock paper scissors. Rock paper scissors shoot you like rock paper scissors shoot, you're like, okay because if we go rock paper scissors shoot and I'm like, oh man, I got lucky and I want imagine I want 100 times in a row. Yeah, the luck, The luck if I was honestly doing that. But now let's say for instance, I go on rock paper scissors and you go on shoot. Rock paper scissors shoot. Here comes the rock, right? If you lose, whose fault is it? It's yours. This is built on a parody thing where the we, I don't get to pick second if I get to pick second, it's like being able to investigate your background before going to meet you and then I'm like, oh hi, oh I too love the New Jersey, you know the New Jersey nets, which is a statement that no one in their right mind would ever make when I was growing up. So anyway, you'd have to have personal knowledge of somebody. So anyway, to come back, let's your, if you understand how games are structured, you can start to realize that there's huge gaps and huge holes in a lot of the thinking behind all of it and if you can create the illusion of choice, I'll play one more If you don't mind, that's one of my favorite ones. Do this in class all the time. Uh Have you seen this before? Okay. Um May I ask you some questions please? Okay. Fantastic. I'm scared there's everybody wins. Don't worry. All right, so, could you could you please uh when uh could you please pick three fingers and tell me what they are </s><s>[INST] your thumb okay? Your pinky and your middle think. [/INST] Okay. So could you please pick two fingers, </s><s>[INST] your middle finger and your pinky? [/INST] Okay, could you please pick one finger? </s><s>[INST] I'll go with the middle finger. [/INST] Okay, could you please pick one finger? Pinky, Okay, Let's play again. Can you pick one finger please? </s><s>[INST] Uh your middle [/INST] Finger. Okay? Can you pick one finger please? </s><s>[INST] Your thumb yeah, your pinky. [/INST] Okay, now pick two more fingers, please, </s><s>[INST] your middle finger and your ring finger. [/INST] Ok? Could you please pick one more finger? Dammit. So, </s><s>[INST] I thought that enhanced the illusion of choice. [/INST] It's the illusion of choice. If I'm asking the questions provided I asked the right questions there can be no correct answer, doesn't mean that ultimately if that's what you wanted. Let's say like I thought I was guiding you to something I wanted, It turns out that was the outcome. You want to listen. Now here's not gonna ask the wrong question. I might not get what I </s><s>[INST] want by the way, sergeant dropped for people that might be just listening to this that no matter what trajectory we took through that decision tree that Ryan was presenting. It was always ending up with the middle finger ironically enough. [/INST] I was surprised. So </s><s>[INST] and all of us were surprised and we're both winners. [/INST] Yeah, we all everyone I felt like a winner. All right, so now now I'm gonna I'll ask some different questions if you don't mind. Can you please pick two fingers to put down </s><s>[INST] uh your middle finger and your pinky? All right, [/INST] That's so awkward. This is the worst finger positions. Okay, can you please wait a minute? That's hold on. Well what if you pick two other fingers to put down </s><s>[INST] ah your thumb your pinkie. [/INST] Okay my thumb on my pinky, can you please pick two fingers to put down? Well whatever you like. </s><s>[INST] Okay, your middle finger and your pointy finger. [/INST] Okay, can you pick two fingers to put down? What's </s><s>[INST] the name? Is index [/INST] Index finger at the point the .1 that's the one we usually points were to point the finger. </s><s>[INST] Uh Sorry [/INST] What to put two more to put down please? </s>

<s>[INST] What is the most beautiful throw in judo to you? [/INST] I think Tamara. It's the, it's the one that seems to have the most amplitude person goes the highest. You see a leg swing through the middle. Uh the person doing the throw, there's a leg swinging through the middle of the other person </s><s>[INST] definitely goes, [/INST] you know, head over heels, flat on their back. Um It's probably the most dynamic, pretty judo throw there is, </s><s>[INST] okay, so it's a single, you're staying on a single foot and you're raising your other foot in the air and it's a forward throw, which means the uh your your back is facing the opponent, but they kind of both fly through the air and twist through the air, correct? Yeah, So how does that throw work? What are the principles behind that throw is one of those throws that, you know, people can kind of understand how to pick up another human being in sort of trivial ways. But the H model, to me never quite made sense, like why it works. There's a there's a cork, there's a twisting motion, there's some involvement of the hip, but not it's not really a hip throw because the hip is not all the way over. So it's not, it's a very confusing throat. I'm [/INST] trying, can </s><s>[INST] you say something [/INST] probably one of the most difficult throws to learn as well, because it is so complex, you do have to stand on one leg, balance on one leg, you know, swing your other leg through the middle, hold your opponent up in the air and it's hard to, it's hard to make that contact with upper body to your, to your back, you know, you have to turn your back on the throw as well. So how does it work? Um it's definitely sort of a throw where you need to start pulling your opponent's upper body towards you, right, so their upper body starts coming towards you, your legs go towards them as your body starts to go uh into the throw, so your head is going to go left, let's say your body, your legs are going to go to the right, your body is your partner is going to start to lean towards you and just as you start to get their momentum coming forward, your leg is going to sweep up underneath, there's pick them up onto your hip, right? And then the finish of the throw is a twist and a lot of times the good judoka will leave their feet when they do the throw, so both bodies are in the air together and then the thrower comes down on top of the person being thrown, </s><s>[INST] So all four ft are in the air. So there's just this unstoppable force is too, so you're all in the air, you're, you're basically doing a roll together, correct? Okay, so who to you is the best Hamada who has besides yourself, I'm [/INST] not gonna lie. There's, there's plenty of guys that do Shimada a lot better than I do. </s><s>[INST] Uh you do have a nice video about the ramada online, but uh, who who's a great practitioner of the commodity right [/INST] now, Shohei ono whose two time olympic gold medalist, that's his favorite throw and he, there's a tons of highlight videos on the I. G. F. And judo fanatics showing how he does his uchi Mata and it is quite different than everybody else's. Um but it's unstoppable when, when he comes in, nobody stops it. He's won two golds in a row at the olympics. I think maybe in the last eight years the guys lost two matches. You know, he's just </s><s>[INST] Incredible. So at a very competitive division I guess 73 kills. Okay. And then 33 time world champ too. Is he the greatest of all time? [/INST] The other reason why he's not is because no mora is a 60 kg player. He was three time olympic champion. So no more. I mean, unless owner is gonna stick around for another three years and win again and uh, when again here in paris that's you know, then he'd match what no more did, but three time gold medalist in judo in a lightweight division. That's pretty spectacular. </s><s>[INST] So to you, the being able to win a championship world championship or olympic medal is a measure of greatness. It's not like um you have some people who are not as accomplished like Koga or something like that. But just the beauty, the moments of magic. The number of moments of magic is the highest, even if it's not championships, [/INST] I think you have to go by that because there's so many phenomenal judo players that have come through the system of spectacular judo um have won countless major events, but you know, the ability to pull it together right at those magical moments, the pinnacle of the sport, the World Championships, the olympic games and proving that you can do it time and time again, makes you unstoppable, it makes you the best. Um you know, there was a guy back in the seventies and eighties by the name of fuji and he won four world championships back to back and back then the world was every two years. So he was here, he was a four time world champion, that's eight years the top of the sport. He never won an olympic medal, you know, he never went to the olympics, you know, so there's a guy who missed out on on olympic greatness but was arguably the best competitor back in that period </s><s>[INST] by the way. Same food is [/INST] as right. Really? Okay, </s><s>[INST] wow, I didn't know there was an actual guy Fuji. [/INST] Our brand is named after the mountain Mount fuji, but you know, this is a different guy, his name was </s>

<s>[INST] as a whistleblower, what's the better way to do it? Because I mean there's fear there's, it takes a lot of effort to do a more targeted release. You know, if there's proper channels, you're afraid that those channels will be manipulated, like who do you trust? What's a better way to do this? Do you think as a journalist, this is almost like a journalistic question reveal some fundamental flaw in the system without destroying the system. I bring up, you know, again Mark Zuckerberg and meta, there was a whistle blower that came out about instagram internal studies and I also torn about how to feel about that whistleblower because from a company perspective that's an open culture, how can you operate successfully if you have an open culture where anyone whistleblower can come out out of context, take a study whether it represents a larger context or not and the press eats it up and then that creates a narrative that is just like with the N. S. A. You said it's an out of context, very targeted to where while facebook is evil clearly because of this one leak, it's really hard to know what to do there because we're now in a society that's deeply distrust institutions and so narratives by whistleblowers make that whistleblower and their forthcoming book very popular and so there's a huge incentive to take stuff out of context and to tell stories that don't represent the full context, the full truth. It's hard to know what to do with that because then that forces facebook and meta and governments to be much more conservative, much more secretive. It's like a race to the bottom of the bottom. I don't know, I don't know if you can comment on any of that, how to be a whistleblower ethically and properly. [/INST] I don't know. I mean these are hard questions and even for myself, like in some ways I think of my book as Sort of blowing the whistle on the underground zero day market, but you know, it's not like I was in the market myself, it's not like I had access to classified data when I was reporting out that book. You know, as I say in the book, like listen I'm just trying to scrape the surface here so we can have these conversations before. It's too late. And you know I'm sure there's plenty in there. That's someone who's you know U. S. Intelligence agencies preeminent Zero Day broker probably has some voodoo doll of me out there and you know you never you're never going to get it 100%. Um But I really applaud whistleblowers. Like you know the whistleblower who who blew the whistle on the trump call with Zelensky. I mean people needed to know about that that we were basically in some ways blackmailing an ally to try to influence an election. I mean they went through the proper channels, they weren't trying to profit off of it right? There was no book that came out afterwards from that whistleblower. Um That whistleblowers not like they went through the channels, they're not living in Moscow. You know, let's put it that way. </s><s>[INST] Can I ask you a question? You mentioned N. S. A. One of the things that showed is they're pretty good at what they do again. This is a touchy subject I suppose. But there's a lot of conspiracy theories about intelligence agencies from your understanding of intelligence agencies C. A. N. S. A. And the equivalent of in other countries are they one question. This could be a dangerous question. Are they competent? Are they good at what they do? and two are they malevolent in any way sort of a recently conversation about tobacco companies. They kind of see there customers as dupes. Like they can just play games with people. Conspiracy theories tell that similar story about intelligence agencies that they're interested in manipulating the populace for whatever ends the powerful in dark rooms, cigarette smoke, cigar smoke filled rooms. What's your sense? Do these conspiracy theories have kind of any truth to them or our intelligence agencies for the most part good for society? [/INST] Okay. Well that's an easy one is it? No I think you know depends which intelligence agency think about the Massad. You know they're killing every Iranian nuclear scientists. They can over the years you know. But have they delayed the time horizon before Iran gets the bomb? Yeah. Have they probably staved off terror attacks on their own citizens? Yeah. You know none of these intelligence intelligence is intelligence. You know you can't just say like they're malevolent or they're heroes. You know everyone I have met in this space Is not like the pound, your chest patriot that you see on the beach on four July. A lot of them have complicated feelings about their former employers. Well at least at the NSA reminded me to do what we were accused of doing after Snowden to spy on americans. You have no idea the amount of red tape and paperwork and bureaucracy it would have taken to do what everyone thinks that we were supposedly doing. Um, but then, you know, we find out in the course of the Snowden reporting about a program called Lovin where a couple of the N. S. A. Analysts were using their access to spy on their ex girlfriends. So you know, there's an exception to every case. Um, generally I we'll probably get, you know, accused of my Western bias here again. But I think you can, you can almost barely compare um, some of these Western intelligence agencies to china for instance and the surveillance that they're deploying on the workers to the level they're deploying it and the surveillance, they're starting to export abroad with some of the programs like the watering hole attack I mentioned earlier where it's not just hitting the workers inside china, sending anyone interested in the wicker plight outside china. I mean it could be an american high school student writing a paper on the workers. They want to spy on that person to, you know, there's no rules in china really limiting the extent of that surveillance and we all better pay attention to what's happening with the workers because just as Ukraine has been to Russia in terms of a test kitchen for its cyber attacks. The tigers are china's test kitchen for surveillance and there's no doubt in my mind that they're testing them on the workers workers or their Petri dish and eventually they will export that level of surveillance overseas. I mean in 2015 Obama and Xi Jinping reached a deal where basically the White House said you better cut it out on intellectual property theft. And so they made this agreement that they would not hack each other for commercial benefit. And for a period of about 18 months we saw this huge drop off in in Chinese cyber attacks on American companies. But some of them continued. Where do they continue? They continued on aviation companies on hospitality companies like Marriott why? Because that was still considered fair game to china. It was an I. P. Theft. They were after they wanted to know who was staying in this city at this time when chinese citizens were staying there so they could cross match for counterintelligence, who might be a likely chinese spy. I'm sure we're doing some of that to counter intelligence is counterintelligence is considered fair game. Um But where I think it gets evil is when you use it for censorship to suppress any dissent. Um To do what I've seen the U. A. E. Due to its citizens where people who have gone on twitter just to advocate for better voting rights, more enfranchisement suddenly find their passports confiscated. You know I talked to one critic Ahmed Mansour and he told me you know you might find yourself a terrorist labeled a terrorist one day and you don't even know how to operate a gun. I mean he had been beaten up every time he tried to go somewhere. His passport had been confiscated by that point. It turned out they'd already hacked into his phone. So they were listening to us talking, they'd hacked into his baby monitor so they're spying on his child. Um And they stole his car and then they created a new law that you couldn't criticize the ruling family or the ruling party on twitter. And he's been in solitary confinement every day um since on hunger strike. So that's evil. You know that's evil. And we still we don't do that here. You know we have rules here, we don't cross that line. Um So yeah in some cases like I won't go to Dubai, you know I won't go to abu Dhabi if I ever want to go to the Maldives like too bad. Like most of the flights go through Dubai </s>

<s>[INST] So you build privacy on top of the power of the Blockchain, you have to first understand the power of the Blockchain. Yes, so Al Durant is like one of the most exciting, technically, at least from my perspective, technologies ideas in this whole space, what's the future of al gore and look like, is it possible for it to dominate the world? [/INST] Let's put it this way. I certainly working very hard with a great team to give the best Blockchain with one uh can demand and enjoy. And they said, I really believe that very is going to be, it's not a winner takes them all. So it's going to be a few block chains and each one is going to have its own brand a and it's going to be great at something and sometimes it's a scalability sometimes is uh is your views or sometimes it's a thing and and it's important to have a dialogue between these things and I'm sure and I'm working very hard to make sure that God is one of them, but I don't believe of it, you know, is even desirable to have, you know, a winner takes all because we need to express different things. But the important thing is going to have enough interoperability with various systems so that you can transfer your assets where you have the best tool to service them whatever your needs are at the time. </s><s>[INST] So there's an idea I don't know they call themselves Bitcoin maximalist so which is essentially the bet that the philosophy that Bitcoin will eat the world. So you're talking about it's good to have variety. Their claim is it's good to have the best technology dominate the medium of exchange. The medium of store, value the money that you know the digital currency space. What's your sense of the positives and the negatives of that? [/INST] So I think people are smart and it's going to be very hard for anybody and you ain't going a twin and because people want more and more things um there is an italian saying that goes as translates well I think it goes of an appetite grows while eating okay I think you don't understand what do you mean? So I say I'm not hungry oh it's okay food let me try. So we want more and more and more. And when you find something like a Bitcoin which are already very good things to say but it does something very well but it's a static I mean store of value. Yes I think it's a great like the rest you know it would be a sad world if the world in which we are so anchoring down someone defensive that we want to store value and higher than the matters I long for a world in which is open, we will want to transact, interact with the way and very four when you want to store value one biopsy 1 chain you want to transact maybe is another. I'm not saying that you know uh when chain cannot be store of value of everything, but I really believe I believe in the ingenuity of people and invest in innovation that is intrinsic to human nature. We want always different things. So how can it be something invented? Whatever it is decades ago is going to fulfill the needs of our future generations. Uh I'm not going to fulfill my needs, let alone one of my kids of their kids. I guess we're going to have a different world and uh things will </s><s>[INST] evolve. So you believe, Yeah, so you believe that life intelligent life is ultimately about adaptability and evolving. So static [/INST] is uh </s><s>[INST] static loses in the end. Yes. Uh let me ask the well first the ridiculous question, do you have any clue who Satoshi [/INST] Nakamoto is? </s><s>[INST] Is that even a interesting question? [/INST] Well, your question very interesting. So and I think so I would say first of all, it's not me and I can prove it because you know, if I was a production like a model, I would have not found out ground officials takes totally different principles to approach to the system but they have a thing whose production model, you know what the right answer is, It's not him or she, her or them Satoshi Nakamoto is Bitcoin because to me is such a coherent proof of work but at the end of the creator and the creation identify themselves. So he says, okay, understand Michelangelo. Okay, it is resistant chapel find it is the way some peters don't find it did the most of the Pieta statue fine. But besides this, who was Michelangelo is? My own question is his own work. That is Michelangelo. So I think that when you look at the Bitcoin is a piece of work but as it affects yes, like anything human. But it was captivated the imaginations of millions of people as a subverted West Otto school. And I'm saying, you know whoever this person of people are, he's living invest piece of work. I mean it is Bitcoin but </s><s>[INST] my idea of the work is bigger. We forget that sometimes it's something about our biology wants likes to see a face and attach your face. And the idea when really the idea is the thing we love. The idea is the thing that impact idea is the thing that ultimately, you know, steve jobs or somebody like that we associate with the Mac with the iphone with just everything he did at Apple. Apple actually the company is steve jobs, steve jobs, the man is uh is it pales in comparison to the [/INST] creation and the sense of aesthetics that has brought to the daily lives and very often aesthetic winds in the long in the long in the long game. And these are very elegant design product and when you say, oh elegant, so very few people care about it. Apparently millions and millions and millions and millions of people do because we haven't talked about beauty and these are beautifully designed products and uh and uh and you know and they've in addition to ever the technological aspect of the other thing and I think yes that is uh </s>

<s>[INST] And you were deeply involved with that [/INST] at the time. I was very much involved with that. I was like the lead architect, I ended up talking to people who had already developed serious third party libraries that did similar things and sort of taking ideas from them and getting their feedback on my design and eventually we put it in the standard library and after a few years I got distracted. I think the thing the big thing that distracted me was actually type annotations, </s><s>[INST] but [/INST] other people kept it alive and kicking and it's been quite successful actually in the world of python web clients. </s><s>[INST] So initially what are some of the design challenges there in that debate for the pep And what are some things that got rejected? What are some things that got accepted to stand out to you? [/INST] There are a couple of different ways you can handle parallel i O. And this happens sort of at an architectural level in operating systems as well, like Windows prefers to do it one way and UNIX prefers to do it the other way. You sort of you have an object that represents a network endpoint, say connection with a web browser that your client and say you're you're you're waiting for an incoming request. Two fundamental approaches are okay, I'm waiting for an incoming request. I'm doing something else. Come wake me up or of course sort of come tell me when something interesting happened like a packet came in on that network connection. And the other paradigm is we're on a team of a whole bunch of people with maybe a little mind and we can only manage one web connection at a time. So I'm just sitting looking at this this web connection and I'm just blocked until something comes in and then uh I'm already waiting for it, I get I get the data, I process the data and then I go back to the top and say now sort of I'm waiting for the next packet. Those are about the two paradigms. One is a paradigm where there is sort of notionally a threat of control, whether it's an actual operating system, thread or more an abstraction in, we call them tasks, but the task in a or a threat in other contexts is devoted to one thing and it has logic for all the stages, like when it's a web request, like first wait, wait for the first line of the web request parse it because then, you know, if it's a get or a post or put or whatever or an error, uh then wait until you have a bunch of lines until there's a blank line and parts that as heathers and then interpret that and then wait for the rest of the data to come in. If there is any more that you request, expect that sort of standard web stuff. And the other thing is, and there's always endless debate about which approach is more efficient and which approach is more error prone where I just have a whole bunch of stacks in front of me and whenever a packet comes in, I sort of look at the number of the fact that there's some number on the packet and I say, oh that packet goes in this pile and then I can do a little bit and then sort of that pile provides my context. And as soon as I'm done with the processing, I sort of I can forget everything about what's going on because the next packet will come in from some random other client and it's that pile, </s><s>[INST] this pile [/INST] uh and every time a pile is maybe empty or full or whatever the criteria is, I can toss it away or use it for a new space but several traditional third party libraries for asynchronous I o processing in python chose the model of a callback and that's that's the idea where you have a bunch of different stacks of paper in front of you and every time someone gives you a piece gives you a new sheet, you decide which stack it belongs to. And that leads to a certain style of spaghetti code that I find sort of aesthetically not pleasing. And I was sort of never very successful. And I had heard many stories about people who were also sort of complaining about that style of coding. It was very prevalent in javascript at the time, at least because it was like how the javascript event loop basically works. And so I thought well the task based model where each task has a bunch of logic. We had mechanisms in the python language that we could easily reuse for for that. And I thought I want to build a whole library for asynchronous networking i o uh and all the other things that may need to be done a synchronously uh based on that paradigm and so I just chose a paradigm and try to see how far I could get with that. And it turns out that it's pretty good paradigm. So </s><s>[INST] people enjoy that kind of paradigm programming for asynchronous io, relative to callbacks. Okay, beautiful. So how does that all interplay with the infamous guild, the go, the global interpreter lock, maybe can you say what the deal is and how does it dance beautifully with a sen ko [/INST] The global interpreter lock solves the problem that python originally was not written with either asynchronous or or parallelism in mind at all. There was no concurrency in the language, there was no parallelism, there were no threads, only a small number of years into python's initial development, all the new cool operating systems like uh Sun. Os and silicon graphics, I rex and then eventually pas IX and Windows all came with threading libraries that lets you do multiple things in parallel and there is a certain certain sort of principle which is the operating system handles the threads for you and the program can pretend that there are as many cpus as as there are threats in the program uh and those Cpus were completely independently and if you don't have enough Cpus operating system sort of simulates those extra Cpus on the other hand, if you have enough Cpus, you can get a lot of work done by deploying those multiple Cpus, but python wasn't written to to do that. Uh And so as libraries for for multi threading were added to C. But every operating system then there was adding their own version of that. We thought and maybe we were wrong, but at the time we thought, well we quickly want to be able to support these multiple threads Because they seemed at the time in the early 90s when they were new, at least to me, they seemed a cool, interesting programming paradigm. And one of the things that that python at least at the time felt was nice about the language was that we could give a safe version of all kinds of cool new operating system toys to the python programmer. Like, I remember one or two years before threading, I I had spent some time adding networking sockets uh to python and there were very literal translation of the networking sockets that were in the BSD operating system. So UNIX BSD But the nice thing was if you're using sockets from python, then all the things you can do wrong with sockets in C would automatically give you a clear error message instead of just ending up with a malfunctioning hanging program. And so we thought, well we'll do the same thing with threading, but we didn't really want to rewrite the interpreter to be threat safe because that that was was like there would be a very complex re factoring of all the interpreter code and all the runtime code because all the objects were written with the assumption that there's only one thread. And so we said, okay, well we'll take our losses will provide something that looks like threads and as long as you only have a single CPU on your computer, which most computers at the time did uh it feels just like threats because The whole idea of of multiple threats in the Os was that even if your your computer only had one CPU you could still fire up at many threads as you wanted. Well, within reason maybe 10 or 12, not 5000. Uh And so we thought we had conquered the the abstraction of threats pretty well because multi core Cpus were not in, in most python programmers hands anyway. And then of course a couple of more iterations of moore's law and computers getting faster. And at some point, uh the chip designers decided that they couldn't make the Cpus faster, but they could still make them smaller and so they could put multiple Cpus on one chip. And suddenly there was all this pressure about do things in parallel and that's where the the solution we had in python didn't work. And that's that's sort of the moment that the gill became became infamous because the guilt, the guilt was the solution, we used to sort of take this single interpreter and share it between all the different operating system threats that you could create. And so as long as the hardware physically only had one CPU that was all fine. And then as hardware offenders were suddenly telling us all, oh, you got to paralyze everything's got to be paralyzed. People started saying, oh but we can use multiple threads in python and then they discovered, oh, but actually all threats run on a single single core. </s>

<s>[INST] not, we like, we must [/INST] do this, this has to be done a podcast that was done from a sauna continuously would be really interesting. Like, you could call it like the pressure cooker or something. </s><s>[INST] I mean like a regular [/INST] yeah, like it's you have to sit with your guests in the sauna um or they have to sit in the sauna. </s><s>[INST] That was one of the interesting things is um it was a sad thing because I believe there's no video of that podcast. But you could tell there is a kind of there was suffering on this push on tim's part. It was like a degradation. He he started over time not being able to put words together correctly, which he's very eloquent. And so you could see there's like there's [/INST] a struggle heat and cold pull you down from the inside. You have to I mean there's a reason why the screening process for um make you know seal seal, they call it seal training. But its really screening and training involves cold water because you know if you're in the heat too long you'll die or damaged tissue in cold. You can do it quite extensively before you die or damaged tissue. But it is stressful. I was gonna say one thing that um I sometimes enjoy seeing these social media posts where people will get into the ice bath. They look really stoic like they're really tough. Um But actually that's the wimpy way to go through it when you get into cold water. If you stay very still, you develop a thermal sheath around you that you're warming yourself. The really bold way is to get in and continue to sift your arms and legs and it ends up feeling miserably colder. And then </s><s>[INST] because you're breaking up and [/INST] bringing that thermal layer and then when you get out you'll notice a lot of people huddle where they'll they'll put they'll grab the towel in general, that's me, I'll get back, I'll get into the sauna. But if you really want to stimulate the big increases in metabolism, you stand out there and you dry off with arms extended in open air and as that water evaporates off you it is really cold but your body is forced to activate a number of the warming programs related to metabolism. This is the beautiful work of a woman named Susannah Soderbergh whose um Scandinavian, she published this paper last year and sell reports medicine and so I call this the sobered principle. Which is if you're doing ice and heat for whatever reason, it doesn't matter if you had it on heat or cold. But if you're using cold specifically to stimulate an increase in metabolism and with cold that's the sobered principle. </s><s>[INST] And with cold. Yeah if you're alternating and then uh if you want to do the tough way you let the shivering so you just stand out and let the water [/INST] evaporate. Yeah. I mean if you ever waded into a cold ocean, you know, everybody is kind of like holding themselves. You know if you really just if you let yourself extend your limbs and move them around a bit. So you break up that thermal layer. That's that's the tough way to. So when I see people on social media getting in and they're like really tough and trying to look hard, </s><s>[INST] you want to be moving around, [/INST] smiling, talking, moving around is way way colder. Are </s><s>[INST] you able to talk? Can you do so you suggest the podcast in the, in the sauna? How [/INST] about this? I proposed this since I got, you </s><s>[INST] want to do the next podcast? [/INST] So the folks from the plunge, maybe you could bring lexa a plunge. He certainly deserves one and we can go side by side coffin style or we can face one another when </s><s>[INST] we said we should do each other's podcast and maybe next year. I can't [/INST] wait to have you back on. I mean we only scratched the surface. </s><s>[INST] Let's do at least part of the next human lab podcast either in the, [/INST] I have a sauna and a cold plunge. So we could do, yeah, we could do, we do a sauna and a cold plunge version. </s><s>[INST] I wonder the recording how the recording works. If there was a bit [/INST] of an echo in the sauna, but I'm sure we can take out the reverb. So </s><s>[INST] sergei wants to ask you about sex performance. Very journalistic, very hardcore hitting questions that we have here in the [/INST] generally or a specific </s><s>[INST] uh he has a certain problem. He needs help with. No, generally you haven't done an episode on sex. [/INST] Well we did an episode early on on sexual development. </s><s>[INST] Yes, we've done [/INST] them on optimizing testosterone and estrogen and we touched a little bit on the on libido and somewhat on sex performance. But not much. We did an episode on relationships, love and desire where we touched on libido specifically. So just as a quick mention of something, a lot of people take S. S. R. I. S. Or antidepressants that can disrupt sexual function, there are a few compounds like Mca route and Tonga ali and things like that, that at least in a few studies in humans have been shown to offset some of the the sexual side effects. Um Now in terms of sexual and then the, sorry, the episode on sexual development was about how the brain and body become organized in certain ways, how the brain becomes organized. If you have X chromosomes or Y chromosomes or etcetera early development mainly and the effects of hormones later on that template, we will be doing a I'm actually putting together a series on sexual health, everything from the menstrual cycle, which both men and women should understand. Of course. Um understanding arousal, understanding for instance, a lot of people don't realize this, but that orgasm is actually the consequence of activity in the sympathetic meaning the stress arm of the autonomic nervous system, whereas arousal is the consequence of the activity of the parasympathetic, the calming aspect of the of the audience, </s>

<s>[INST] like there's some kind of feeling of the entity, the stuff that's inside of it and the stuff that's outside of it. And then that's when consciousness starts making sense. But, but then, um, it seems like that could be generalized able, if you take some subset of a cellular automata, you could start talking about what does that subset [/INST] uh, feel. But </s><s>[INST] then you can, I think you could just take arbitrary numbers of subsets. Like to me, uh, like you and I individually our consciousness is, but you could also say the two of us together is a singular [/INST] conscious. Maybe maybe I'm not so sure about that. I think that the single thread of time thing may be pretty important. And that as soon as you start saying, there are two different threads of time, there are two different experiences. And then we have to say, how do they relate how they sort of entangled with each other? I mean that may be a different story of a thing that isn't much like, you know, the the, what do the ants, you know, what's it like to be an aunt, you know, where there's a sort of more collective view of the world, so to speak. I don't know, I think that, I mean, this is uh you know, I don't really have a good, I mean, you know, my my best thought is, you know, can we turn it into a human story? It's like the question of, you know, when we try and understand physics, can we turn that into something which is sort of a human, understandable narrative? And now, what's it like to be a such and such? You know, maybe the only medium in which we can describe that is something like fiction where it's kind of like you're telling, you know, the life story in that, in that, in that setting. But I I'm this is this is beyond what I've, what I've yet understood how to do </s><s>[INST] it. But it does seem so like with human consciousness, you know, we're made up of cells and like there's a bunch of systems that are [/INST] networked </s><s>[INST] that work together that at this at the [/INST] human level. </s><s>[INST] I feel like a singular consciousness when you take So maybe like an ant colony is just too low level, sorry, an ant is too low level. Maybe you have to look at the ant [/INST] colony, there's some level of which </s><s>[INST] it's a conscious being and then if you go to the planetary scale and maybe that's going too far. So there's a nice sweet spot consciousness, I mean, [/INST] I agree, I think I think the difficulty is that, you know, okay, so in sort of people who talk about consciousness, one of the one of the terrible things I've realized, because I've now interacted with with some of this community, so to speak, some interesting people who do that kind of thinking. But, you know, one of the things I was saying to one of the leading people in that area, I was saying, you know, uh that, you know, it must be kind of frustrating because it's kind of like a poetry story that is many people are writing poems, but few people are reading them. So there are always these different, you know, everybody has their own theory of consciousness and they are very non inter sort of inter discuss a ble and by the way, I mean, you know, my own approach to sort of the question of consciousness, as far as I'm concerned, I'm an applied consciousness operative, so to speak. Because I don't really, in a sense, the thing I'm trying to get out of it is how does it help me to understand what's a possible theory of physics and how does it help me to say? How do I go from this, this incoherent collection of things happening in the universe, to our definite perception and definite laws and so on. And it's sort of an applied version of consciousness and I think the reason that sort of segue to a different kind of topic, but the reason that one of the things I'm particularly interested in is kind of what's the analog of consciousness in system is very different from brains. And so why does that matter? Well, you know, this whole description of this kind of, uh, you know, we haven't talked about why the universe exists. So let's let's get to why the universe exists. And then we then we can can talk about perhaps a little bit about what these models of physics kind of show you about other kinds of things like molecular computing and so on, But that's okay, why does the universe exist? Okay, so we finally sort of more or less set the stage, we've got this idea of this really odd of this object that is made from following all possible rules, the fact that it's sort of not just this incoherent mess, it's got all this entangled structure in it and so on. Okay, so what is this really add? Well, it is the working out of all possible formal systems. So, the sort of, the question of why does the universe exist? Its core question you kind of started with is you've got to bust two equals for you've got some other abstract result, but that's not actualized, It's just an abstract thing. And when we say, we've got a model for the universe. Okay, it's this rule you run it and it will make the universe. But it's like but you know, where is it actually running? What what what is what is it actually doing? Right. What is it actual or is it merely a formal description of something? Okay. So the thing to realize with this with this the thing about the ruling ad is it's an inevitable it is the entangled running of all possible rules. So you don't get to say it's not like you're saying which rule er are you picking? Because it's all possible formal rules. It's not like it's just um you know. Well actually it's only footnote. The only footnote. It's an important footnote is it's all possible computational rules. Not hyper computational rules. That is it's running all the rules that would be accessible to a turing machine but is not running all the rules that will be accessible to a thing that can solve problems in finite time. That would take a turing machine infinite time to solve. So you can even alan turing knew this. That you could make oracles for turing machines where you say a turing machine can't solve the halting problem for touring machines. It can't know what will happen in any touring machine after an infinite time in any finite time. But you could invent a box just make a black box, you say I'm going to sell you an oracle that will just tell you press this button, it will tell you what the term machine will do after an infinite time. You can imagine such a box. You can't necessarily build one in the physical universe, but you can imagine such a box. And so we could say, well, in addition to so in this really add, we're imagining that there is a computational that at the end it's running rules that are computational. It doesn't have a bunch of oracle black boxes in it, you say, well, why not? Well, turns out if there are oracle black boxes, the ruling AD that is you can make a sort of super ruling AD that contains those oracle black boxes. But it has a cosmological event horizon relative to the first one. They can't communicate. In other words, you can you can end up with what you end up happening. What ends up happening is it's like in the physical universe we in this causal graph that represents the causal relationships of different things. You can have an event horizon where there's where the causal graph is disconnected, where the effect here, an event happening here does not affect an event happening here because there's a disconnection in the causal graph and that's what happens in an event horizon. And so the what will happen between this kind of the ordinary ruling ad and the hyper ruling ad is there is an event horizon. And you know, we in our ruling AD will just never know that there is that they're they're they're just separate things. They're not they're not connected. </s>

<s>[INST] Yeah that's true but there's a human side to it. I want sometimes I think with these because again anomalous rare events. Some of the data is inextricably connected to humans. The observations, I mean I hope in the future, you know that that that sensory data will not be polluted by human subjectivity. But you know, that's still, that's still powerful data, even direct observations. Like if you talk about about pilots and so it's an interesting question to me whether bob Lazar is telling the truth, whether he believes he's telling the truth too and what also what impact his story and stories like his have on the willingness of governments to be transparent and so on. So, you know, you have to credit his story for captivating the imagination of people and getting the conversation going. [/INST] He's maintained his story for all these years with little to no change that I'm aware of. So, um but there's so many other people who are, let's say experts in that story, </s><s>[INST] their gut, you know, you accumulate us a set of sort of circumstantial evidence where your gut will say that somebody is not telling the truth. You mentioned Avi Loeb, I forgot to ask you about it more and more. Mhm. You know, because you've analyzed specimens here on earth, What do you make of that one and what do you make broadly of our efforts to look look at rocks essentially or look at objects flying around in our solar system. Is that a valuable pursuit or maybe most of the stories are, can be most of the fascinating things could be discovered here on earth or in other nearby planets. [/INST] Just going to a more and more, uh you know, I think obvious insight is an interesting speculation, right? Like I was saying before, people can sometimes look at something and not see it for what it is. Many would just look at that and say, oh it's an asteroid and dismiss it. There was something odd about the data that Avi picked up on and said, well, here's an alternative explanation. It doesn't fit that actually better fits the models than it just being a rock, you know, and to his credit, he just has ignored the critics because he believes the data is real and is using that then as a battering ram to go after other things. So I think that's, I think that's great, </s><s>[INST] you know? Yeah. What, what is his main conclusion, does he say it could be of alien extraterrestrial origins as [/INST] well? That's one of the things, I mean, he, you know, he's explained how it could be a Lightsail um and a Lightsail is certainly within near human capabilities to make such a thing. I think yuri Milner, he's a Russian billionaire, he's involved, I think in a project to make light sails with laser, you know, to launch them with laser power essentially towards alpha centauri. Right? So it's something that humans could make, I think obvious proposal is perfectly within the realm of possibility. I mean, sadly, the thing is you know, now nearly out of our solar </s><s>[INST] system. Yes, I mean to me that's inspiring to do greater levels of data collection in our solar system, but also here on earth it just seems like we should be constantly collecting collecting data because the tools of software that were developing get better and better at dealing with huge amounts of data. It's changing the nature of science. I mean collect all of the data, right, [/INST] collect the data. I mean I um the Galileo project asked me over the weekend to join and I did so um you know, I'm not a specialist in any of the stuff that they're doing but you know, in looking at the list of people who are on there. There are really no biologists on there. So at at some point if my expertise is required </s><s>[INST] for something, what's the goal in the vision of the Galileo project? [/INST] Better talk to Avi. But my understanding and just actually looking at the at the sort of the bylaws this morning, literally just got them um is number one, collect the data on U. AP and number to collect data on local potentially local technological artifacts. </s><s>[INST] I need to look into this. This is fascinating. And the obvious heading the Galileo project. Have you spoken to him on this podcast? Yes, that was before I believe is before he was headed. This is a new [/INST] creation. Yeah, the Galileo project was because I think it's about six or seven months old </s><s>[INST] now and he's getting a group of scientists together. [/INST] About 100. Actually I am, I was looking at some of their stuff over the weekend, I'm shocked at the level of organization that they've already got put together. It looks like a Moonshot project. I mean I've been involved with a lot of NIH large NIH projects, which involves a lot of people in coordination and they're putting it together, </s><s>[INST] so you're extremely well published in a lot of the fields we began this conversation with, so you're legit scientist, but yet you're keeping an open mind to a lot of ideas that um that maybe require you to take a leap outside of the conventional. So what advice would you give to young people today that are, you know, in high school or in college that are um dreaming of having impact in science or maybe in whatever career path that goes outside of the conventional, that really does something new. [/INST] If you believe in something, you believe that an idea is valuable or you haven't approached something, don't let others shame you into not doing it. As I've said, shame is a societal control device to get other people to do what they want you to do rather than what you want to do. So shame sometimes is good to stop you from doing something unethical or wrong, but shame also is something that is circumscribing your environment, I've never let people who have told me, you know, you shouldn't do that line of science, you should be ashamed of yourself for even thinking that. Give me a break. I'm, you know, why is it wrong to ask questions about this area? What's wrong with asking the question? Frankly, you're the person who's wrong for trying to stop these questions. You're the person who's almost acting like a cultist. You basically have closed your mind to what the possibilities are. And if I'm not hurting anybody, and if it could lead to an advance, and if it's my time, why does it bother you? I mean, I had a very well known scientist wants to tell me that I was going to hurt my career talking about this. </s>

<s>[INST] Yeah, I mean that's what it is. Like if you task yourself for building an intuition about a problem, that's what that's where you start to pull in. Like um what is the pattern I'm seeing in order to understand the pattern you might want to then start utilizing visualization, but ultimately that's all in service of like solving the puzzle, cracking it open to get the simple explanation of why why things are the way they are as opposed to um like you said, having a particular algorithm that you can then execute to solve the problem. It's hard, it's hard. The reason is really hard. [/INST] Yeah, it's hard, I mean I love to value what's hard in maths instead of being afraid of it. We know that when you struggle that's actually a really good time for your brain. You want to be struggling when you're thinking about things. So if it's hard to think intuitively about something that's probably a really good time for your brain. I used to work with somebody called Sebastian Thrun who it's a great sort of mathematician you might think for him at a I person. And I remember in one interview I did with him, he talked about how they built robots I think for the Smithsonian and how they were having this trouble with them picking up white noise and he said they had to solve it, they had to work out what's going on and how he intuitively worked out what the problem was. But then it took him three weeks to show it mathematically. I thought that was really interesting that how you can have this intuition and know something works. It's kind of different from going through that long mathematical process of proving it. But so important. </s><s>[INST] I think probably our brains are involved as like intuition machines and the uh the math of like showing it like formally is probably an extra thing that were not designed for. You see that with Feinman and his um I mean just all of these physicists definitely you see um starting with intuition sometimes starting with an experiment and then the experiment inspires intuition, but you can think of an experiment as a kind of visualization, just like let's let's take whatever the heck we're looking at and draw it and and draw like the pattern as it evolves as the thing grows for N equals one, for N equals two and equals three, you start to play with it. And then in the modern day, which I loved doing is, you know, you can write a program that then visualizes it for you, and then you can start exploring it programmatically and that that and then uh you can do so interactively to I tend to not like interactive because the way it takes to way too much work because you have to click moving stuff. I love to interact through writing programs, but that's my particular brain software engineer. So like you can you can do all these kinds of visualizations. Uh and then there's the tools of visualization, like color, all those kinds of things that you're absolutely right. There actually not taught very much like the art of visualization [/INST] not taught. And we love as well, color coding, like when you represent something mathematically you can show color to show the growth and kind of code that So if I have an algebraic expression for a pattern, maybe I show the X with a certain color, but also right in that color. So you can see the relationship very cool. And um yeah, we particularly in our work with elementary teachers, many of them come to our workshops and they're literally in tears when they see things making sense visually because they have spent their whole lives not realizing, you can really understand things with these visuals. It's quite powerful. </s><s>[INST] You say that there's something about there's something valuable to learning when the thing that you're doing is challenging is difficult. So a lot of people say, you know, math is hard or math is too hard or too hard for me. Do you think math should be easy or should it be hard? [/INST] I think it's great when things are challenging, but there's something that is really key to being able to deal with challenging maths and that is knowing that you can do it. And I think the problem in education is, a lot of people have got this idea that you're either born in the maths brain or you're not. So when they start to struggle, they think, oh, I don't have that maths brain and then they were literally sort of switch off in their brain and things will go downhill from that point. So struggle becomes a lot easier and you're able to struggle if you don't have that idea. But you know that you can do it, you have to go through this struggle to get there, but you're able to do that. And so were hampered in being able to struggle with these ideas we've been given about what we can do. </s><s>[INST] Ask a difficult question here. So there's kind of, um, I don't know what the right term is, but some people our um struggle with learning in different ways, like their brain is constructed in different ways and um how much should, as educators should we make room for that? So how do you know the difference between this is hard and I don't like doing hard things versus my brain is wired in a way where I need to learn in very different ways. I can't learn it this way. How do you find that line? How do you operate in the gray area? [/INST] So this is why being a teacher is so hard and people really don't appreciate how difficult teaching is When you're faced with, you know, 30 students who think in different ways. And um, but this is also why I believe it's so important to have this multidimensional approach to maths. We've really offered it in one way, which is here's some numbers in a method. You follow me do what I just did and then reproduce it. And so there are some kids who like doing that and they do well, and a lot of kids who don't like doing it and don't do well, but when you open up maths and you give you let kids experience it in different ways, maybe visually with numbers with words. What happens is kids, there are many more kids who can access it. So there's different brain wiring you're talking about, where some people are just more able to do something in a particular way, that's why we want to, that's one of the reasons we want to open it up, so that there are different ways of accessing it and then that's not really a problem. </s>

<s>[INST] process thinking through it to iterating and so on. The last question. Ah you have 10 seconds to answer it. What is your favorite sci fi movie about? Ai? [/INST] I would say Interstellar has my favorite robots. Yeah. Yeah. So so Tars the robots, one of the robots and Interstellar is the way robots should behave. And uh I would say ex machina is in some ways the one the one that makes you I think uh in a nervous kind of way about about where we're going </s><s>[INST] Stuart, thank you so much for talking today. Pleasure. [/INST] Yeah. </s>

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

<s>[INST] you seem to be able to ask me hard. No, this is a super fun, I mean, when there's brilliant people like you, there's nothing to push back on, that's easy. But there's a basic human thing that doesn't, I think it's almost easier to be a journalist, like journalists do this well, where they don't have empathy for the person. They're just asking the hard questions. So where were you at this time last night? Because that's very suspicious, it's in contradiction to what you said, and they're just doing factual stuff. And if you actually truly have a conversation with another human being, you empathize, it's very difficult. Because they have a story, they have a vision of themselves, that they're the good person. And to call somebody a liar while having empathy, basically imply that they're a liar that's damn, damn hard. So anyway, but I'm trying to figure this thing out. Can you make the case that the January 6th storming of the US Capitol is a big deal? [/INST] And can you make the case that it is not a big deal? No, well said. I think the case is overwhelming that it was a big deal. And I opened the book with this before going back to the end of the Civil War, because I think it echoes that moment. You had a group of people who literally tried to stop the peaceful transfer of power, and were intending, and there's overwhelming evidence of this, if they had caught the Vice President or the Speaker of the House to do bodily harm to them or to kidnap them. So this was a coup d'etat, that is the definition of a coup d'etat when you try to capture and prevent elected officials from doing their job. That's a huge deal. That had happened before in our country in states, I talked about this, in Louisiana, in Tennessee, in places like that after the Civil War, but it never happened in the Capitol. That's a huge deal. That is, if I might say, that's like what we would think of as Third World behavior. In our society and no offense to those from other parts of the world, I'm just trying to make a point is how we see that as happening somewhere else, not here. That's a big fucking deal. The case that is not a big deal, I guess the case to make there is that they didn't succeed. The case that it's not a big deal is not that their intentions were not bad. I don't see how you can defend their intentions. The case is that the case there's not a big deal, so they're a bunch of clowns. And yeah, they broke in. But in the end, once they got in there, they didn't know what to do, which is true. And so, you know, I think a professional coup plotter would say these were the amateurs and that they had no real chance of succeeding because once they got into the Capitol, they had no plan what to do next. What are they going to do? You know, steal stapler from Nancy Pelosi office. They didn't seem to have a plan and then what ended up happening, they </s><s>[INST] left the bill. That would be the case. That's not a big deal because their intention was not to overthrow. Their intention was to protest because if the intention was to overthrow, it would be [/INST] much more organized. I think the evidence is pretty overwhelming that they intended to stop. They were there to stop the certification of the election. They were there to prevent Donald Trump from having to leave office, they just didn't have a good plan. </s><s>[INST] This was the Keystone Cops. So you're saying there is some, like statistically some possibility that this would have succeeded [/INST] at halting the basic process of democracy. You could imagine a scenario where it might have, if they had gotten lucky. Sure. If they had caught the vice president. </s><s>[INST] But what could have, if they caught the vice president- They couldn't go on and certify then. He has to be there. No, but don't you think that would resolve itself through police action and so on? My question is how much is this individual hooligans and how much of this is a gigantic movement that's challenging the very fabric of our democracy? [/INST] No, it was not a gigantic movement, but it was a small coup d'etat that could have actually made the transition much more difficult. Was there a scenario where Donald Trump stayed in office legitimately? No. But was there a scenario where they created a great deal of chaos that further undermined our democracy? Absolutely yes. Here's how it would happen, right? They capture Pence, right? They either kidnap him and try to ransom him or they, which is what they were trying to do with the Michigan governor, Governor Whitmer, or they kill him. And then Donald Trump says, okay, well there's no vice president so you can't certify. The Senate would choose someone else to be vice president, but Donald Trump says, no, that's not legitimate. Do you think it's possible Donald Trump would say something like that? Absolutely. I disagree with you. He said that morning that Pence should not certify. He said that morning. </s><s>[INST] But there's a difference between sort of Twitter rhetoric. No, no, he said it at a rally. Sure, a rally rhetoric. And there is a threshold. [/INST] It feels like a big leap. He asked people around him in the Oval Office how he could make that happen. He tried to get a new person appointed attorney general who would do that. He tried to find legal justification for it. I think the evidence is overwhelming that Trump was supportive of efforts after the election didn't go the way he wanted to keep him in office. And whether that's legally actionable and whether one thinks that means he's a bad president </s>

<s>[INST] But how is that? Let me ask some nice dumb questions. How is that not traveling faster than the speed of light? [/INST] Yeah, it's not traveling faster than the speed of light because locally at any point, if you were to measure the light, the photons zipping past, it would not be exceeding the speed of light. The speed of light is a locally measured quantity after light has traversed some distance. If the rubber band keeps on stretching then yes, it looks like the light traveled a greater distance than it would have had the space not been expanding, but locally it never was exceeding the speed of light. It's just that the distance through which it already traveled then went off and expanded on its own some more. And if you give the light credit, so to speak, for having traversed that distance. Well then it looks like it's going faster than the speed of light. But that's not what's happening, right? That's not how speed works, speed and in relativity also, the other thing that is interesting is that, You know, if you take two ping pong balls that are sufficiently far apart, especially in an accelerating universe, you can easily have them moving apart from one another faster than the speed of light. So, you know, take two ping pong balls that were originally 400,000 km from each other and let every centimeter in your rubber band expand to two in one second. Then suddenly this 400,000 km distance is 800,000 km. It went out by 400,000 km in 1/2, that exceeds the 300,000 km/s speed of light. But that light limit that particle limit in special relativity applies to objects moving through a pre existing space. There's nothing in either special or general relativity that prevents space itself from expanding faster than the speed of light. That's no problem. Einstein wouldn't have had a problem with, with, with with the universe as observed now by cosmologists. </s><s>[INST] Yeah, I uh I'm not sure yet ready to deal emotionally with expanding space like that. To me is one of the most awe inspiring things, you know, starting from the Big Bang, it's definitely abstract, it's space itself is expanding, right? Yeah. Could you, can we talk about the Big Bang a little bit. Yeah. What? Uh so like the entirety of it, the universe was very small, [/INST] Right? But it was not a point. </s><s>[INST] It was not a point. [/INST] Because if if we live in what's called a closed universe now, a sphere or the three dimensional version of that would be a hyper sphere. You know, then regardless of how far back in time you go, it was always that topological shape. You can't turn a point suddenly into a shell. Okay. It always had to be a shell. So when when people say, well the universe started out as a point, that's being kind of flippant kind of glib, it didn't really, it just started out at a very high density and we don't know actually whether it was finite or infinite. I think personally that it was finite at the time, but it expanded very very quickly. Indeed. If it exponentially ated and continued in some places to exponentially eight, then it could in fact be infinite right now. And most cosmologists think that it is infinite. </s><s>[INST] Yes, I what, infinite. Which dimension, mass uh [/INST] emphasis space, infinite space. And by that, I mean that if you were trying to use light to measure its size, you'd never be able to measure its size because it would always be bigger than the distance light can travel. That's what you get in a universe that's accelerating in its expansion. </s><s>[INST] Okay. But you know, if the thing was a hyper sphere, very small. Not a point. How can that thing be infinite? [/INST] Well it expands exponentially, that's what the inflation theory is all about. Indeed at your home institution, Alan guth is one of the originators of the whole inflationary universe idea, along with Andrei linde at stanford University here in the bay Area and others, Alexis, strabinsky and others had similar sorts of ideas, but in an exponentially expanding universe, if you actually try to make this measurement, you send light out to try to see it curved back around and you in the back of the head, it's an exponentially expanding universe. Their amount of space remaining to be traversed is always a bigger and bigger quantity, so you'll never get there from here, you'll never you'll never reach the back of your head. So observation, ali or operationally it can be thought of as being </s><s>[INST] influenced, it's one of the best definitions of infinity, by the way, what's that? That's one of the [/INST] best </s><s>[INST] sort of physical manifestations of infinity. Yeah, [/INST] yeah, because you have to ask how would you actually measure it now? I sometimes say to my cosmology, theoretical friends, well, if I took, if I were God and I were outside this whole thing and I took a Godlike slice in time, wouldn't it be finite? No matter how big it is and they object and they say Alex, you you can't be outside and take a Godlike slice of time, you know, </s><s>[INST] because there's nothing [/INST] outside. Well I'm not, you know, or also, you know what slice of time you're taking depends on your motion. And that's true. Even in special relativity, that slices of time get tilted in a sense, if you're moving quickly, the axes X and T actually become tilted, not not perpendicular to one another. Um And you know, you can look at brian Greene's books and lectures and other things where he imagines taking a loaf loaf of bread and slicing it in units of time as you progress forward. But then if you're zipping along relative to that loaf of bread, the slices of time actually become tilted. And so it's not even clear what slices of time mean, but I'm an observational astronomer, I know which end of the telescope to look through. And the way I understand the infinity is as I just told you that operationally or observation. Aly, there no, there'd be no way of seeing that. It's a finite universe of measuring a finite universe. And so in that sense, it's infinite. Even if it started out as a finite little dot, not a dot, I'm sorry, finite little hyper sphere, </s>

<s>[INST] courage. And I think for such great leaders, great universities, there's a huge hunger for it. So I'm two very optimistic that it will come. I'm now personally taking a step into building a startup first time hoping to change the world. Of course, uh, there are thousands, maybe more, maybe millions of other first time entrepreneurs like me. What advice you've gone through this process. He's talked about the suffering, the emotional turmoil it all might entail. What advice do you have for those people taking that step? [/INST] I'd say it's a rough ride. Uh, and you have to be psychologically prepared for things going wrong with frequency. You have to be prepared, uh, to be put in situations where you're being asked to solve problems. You didn't even know those problems existed. You know, for example, renting space. It's not really a problem unless you've never done it. You have no idea what the least looks like, right? You don't even know the relevant rent and you know, in a market. So everything is new. Everything has to be learned. What what you realize is that it's good to have other people with you who have had some experience in areas where you don't know what you're doing, unfortunately, uh an entrepreneur starting doesn't know much of anything. So everything is something new. Uh and um I think it's important not to be alone because it's sort of overwhelming uh and you need somebody to talk to other than a spouse or loved one because even they get bored with your problems. Uh and and so, you know, getting a group, you know, if you look at Alibaba, um you know, Jack Ma was telling me they went, they basically were like it financial death store at least twice. Uh and you know, the fact that there, it wasn't just Jack, I mean people think it is because of, you know, he became the, you know, the sort of public face and the driver, but but a group of people who can give advice, share situations to talk about that's really important </s><s>[INST] and that's not just referring to the small details like renting space, it's also the psychological yes martin. Yeah, [/INST] and you know, because most entrepreneurs at some point question what they're doing because it's not going so well or they're screwing it up and they don't know how to unscrew it up because we're all learning and it's hard to be learning, You know, when they're like 25 variables going on if you, you know, if you're missing four big ones, you can really make a mess. Uh and so the ability to, to in effect have either an outsider who's really smart that you can rely on for certain type of things or other people who are working with you on a daily basis. Um, it's most people who haven't had experience, believe in the myth of the one person, one great person, you know, makes outcomes, uh, creates </s><s>[INST] outcomes that are positive [/INST] most of us. Yeah, it's not like that, if you look back over a lot of the big, successful tech companies, it's not typically one person, you know, it's, and you will know these stories better than I do because it's your world, not mine. But even I know that almost every one of them had to people. I mean if you look at google, you know, that that's what they had and that was the same and Microsoft at the beginning and you know, it was the same at Apple. You know, people have different skills and, and they need to play off of other people. So, so, um, you know, the, the advice that, that I would give you is make sure you understand that, so you don't head off in some direction as a lone wolf, uh, and find that either you can invent all the solutions, um, or you make bad decisions on certain types of things, this is a team sport entrepreneur means you're alone in effect and that's the meth, but it's mostly a myth. </s><s>[INST] Yeah, I think, and you talk about this in your book and I could talk to you about it forever, the harshly self critical aspect to your personality and uh, to mine as well, in the face of failure, it's a powerful tool, but it's also a burden. That's, that's very interesting, very interesting to uh, walk that line. But let me ask on the, in terms of people around you in terms of friends in the bigger picture of your own life, where do you put the value of love, family, friendship in the big picture journey of your life? [/INST] Well, ultimately all journeys are alone. Um, it's great to have support. Um, and, you know, when you, you, you go forward and say your job is to make something work and that's your number one priority. Um, and you're going to work at it to make it work, you know, it's like superhuman effort. People don't become successful as part time workers, it doesn't work that way. And if you're prepared to make that 100, effort, you're gonna, you're gonna need support and you're going to have to people involved with your life who understand that, that's really part of your life, uh, sometimes you you're involved with somebody and, you know, they don't really understand that and that's a source of, you know, sort of conflict and difficulty, but if you, if you're involved with the right people, uh, you know, whether it's a dating relationship or, you know, sort of spousal relationship, you know, you you have to involve them in your life. Uh but not burden them with with every, you know, sort of minor triumph or mistake, they actually get bored with it after a while. And, and so you have to set up different types of ecosystems, You have your home life, you have your love life, you have Children and and that's like the enduring part of what you do. And then on the other side, you've got the, you know, sort of unpredictable nature of of this type of work. What would I say to people at my firm who were younger usually? Um, well, everybody's younger, but, you know, people who are of an age where, you know, they they're just having their first child Or maybe they have two Children that it's important um to make sure they go away with their spouse. Uh at least once every two months, just some lovely place where there were no Children, no issues sometimes once a month if there, you know, sort of energetic and clever. Uh and that </s>

<s>[INST] kind of like the labels discussion. So like, the most likely try to make it concrete. It's probably gonna look like some cute version of a human big, it's a little green fellas with the eyes and so on, or whatever. Whatever. The movies have been still like your cultural upbringing, you're going to project onto that. The assumptions you have. That's interesting. So, you prefer to stay a step away and think and abstract notions of what it means to be intelligent, what it means to be a living life form and all that kind of stuff. [/INST] I try to I almost try to pretend I'm I'm blind and I'm deaf and I'm only um in mind with no inductive reasoning capacity when I'm trying to think about thought experiments like these, because I know that uh if I incorporate whatever my eyes instruct my brain, I will uh I will impede my ability to I think as deeply as possible. Because once again, it's the thing which shallows are thought can be the incorporation of circumstance and coincidence and for particular kinds of thought, that's very important. I'm not discounting the use of inductive reasoning uh in many humanities and in many sciences, but for the deepest of thoughts once again, I I feel it's important to try to transcend whatever uh methods of observation characterize human experience. </s><s>[INST] But within that, that's all really beautifully put. I wonder if there is a common mathematics and a common physics between us and alien beings. We still have to make concrete the methods of communication. [/INST] Yeah. </s><s>[INST] And that's a fascinating question of, like, while remaining in these abstract fundamental ideas, how do we communicate with them? I mean, I suppose that question could be applied to different cultures on earth was finding a common language. Do you think about that kind of problem of basically communicating abstract fundamental ideas? [/INST] My least favorite aspect of math or physics or any of these really deep sciences is the symbolic component. You know I'm I'm dyslexic, I don't like looking at at symbols there too often a source of of ambiguity and I think you're entirely right that if one thing holds us back with um communication with something that behaves or looks nothing like us. I think if one thing holds us back uh it will be symbols and the communication of deep thought because as I said, I think communication frequently compromises thought by intention or by just theoretical inadequacy. </s><s>[INST] So on this topic actually would be fun to see what your thoughts are. Do you think math is uh invented or discovered? So you said that math we might share ideas of mathematics and physics with alien life forms, so it's uniform in some sense of uniform throughout the universe. Do you think this thing that we call mathematics is uh something that's kind of fundamental to the world we live in? Or is it just some kind of pretty axioms and theorems have come up with to try to describe the patterns we see in the world. [/INST] Uh I think it's completely discovered and completely fundamental to all experience. I think the only component of mathematics that has been invented is the expression of it. And I think in some sense there's almost uh in arrogance required to believe that whatever aspect, uh we invent having to do with math and physics and the theory, there is an arrogance required to truly believe that that belongs on any sort of stage with the actual beauty of the matters being discovered. So, um we need our minds and in some sense are our pens too, be able to play with these things that uh and communicate about them and those hands and those are and those pens are the things which smudge the most beautiful thing that humanity can ever um experience. And maybe if we interact with some intelligent life form, uh, they will have their own unique smudges. But the canvas uh which is beautiful, must be identical because that is universal and ubiquitous truth and that's what makes it deep and meaningful is that it's so much more important than uh whatever we're programmed to enjoy as an aspect of human experience. </s><s>[INST] Yeah, that that's really beautifully put. The human language is these messy smudges of trying to express something underlying that is beautiful. Speaking of that, on the physics side, do you think the pursuit of a theory of everything in physics, as we may call it in our current times of understanding the basic fabric of reality from a physics perspective is an important pursuit. [/INST] I think it's essential, as I've said, I think ideation is our only escape from the constraints of human condition and I think that it's important that all great thoughts and ideas are bound together and I think the math is beautiful and it ensures that um the things which bind uh great ideas which have already been had in great discoveries together. It uh it ensures that those strings will be beautiful. Uh I think it's very important to unify all theories that have brought us to to where we are. </s><s>[INST] Do you think humans can do it? Do you think humans can solve this puzzle? Is it possible that we with our limited cognitive capacity will never be able to truly understand this deep, like deeply understand this underlying canvas. [/INST] I think if not it will be people like you who invent uh some sort of I don't know, we'll call it computation for now that will be um able to not only discover that which transcends humanity but to transcend human methods of discovering that which is above it. </s>

<s>[INST] Do you want to actually talk about your childhood? I think it's interesting because you also worked at a factory. Your childhood is really fascinating. saying, and difficult, traumatic. So, and you've written about it, there's a lot of ways we can talk about it, but maybe what are the things you remember the good and the bad of your childhood, [/INST] of your maybe interaction with your father? Yeah, my dad probably has narcissistic personality disorder and so it was very centered on very controlling childhood, immensely so. We were homeschooled and pretty isolated from the outside world, like we didn't know anybody else who wasn't homeschooled. We went through a program called Growing Kids God's Way, which was very, it was like the kind of program where you're not supposed to pick up babies when they cry to train them that they can't manipulate the parents, because like baby crying was viewed as like, you're just teaching them from an early age that they're allowed to make the parents do what the kids want. And we're very against this philosophy. So, that combined with a narcissistic personality disorder, dad was pretty rough. </s><s>[INST] So controlling? Super controlling, yeah. And developing and feeding the self critical aspect [/INST] of your brain. Super controlling, yeah. Yeah, very much. It was, you know, I was like lazy, but I was never gonna accomplish anything in life. I was gonna move out of the house and realize how good I had it at home, you know, the classic stuff. He was very like logical and smart though. And so he'd also like teach us logic stuff. I remember some of my earliest memories or him like giving me basic logic puzzles, like the dog has three legs, you know, how many dogs have four legs and I would mess up and, but he was a evangelist, basically a Christian evangelist. So we like Bible study five nights a week. I memorized I think 800 verses of the Bible by the time before I became an adult. Yeah, and it was very patriarchal also. So I was expected to grow up and become a housewife, basically, they're like, oh, you can go to college to meet a man and also to get a little bit of education so that you can homeschool your own kids. Like we were explicitly told that women were subordinate to men in regards to like making decisions when you're married. Our pastor's daughter was not allowed to leave home because she would be outside of the authority of a man. So when she got married, she was allowed to leave because she was never allowed to live in a house where she was not under a hierarchy. So this is like the kind of culture that we live in. </s><s>[INST] So there's a hierarchy and the gender aspects of the hierarchy is men at the top of that hierarchy. Okay, but your own psychology and your own mind, [/INST] so most of that self critical brain is bad, right? It was confusing, cause he told me that I was smart, but also that I would fail. But I think that- </s><s>[INST] But not smart enough, right? Like smart, but not smart enough? Smart, but like not virtuous or something. Okay, so, okay, right. [/INST] There's always a flaw. Yeah, there's always a flaw. I think a lot of it was, a lot of the fucked-up-ness of my brain came from feeling like I didn't have the authority to think. Cause it was so like carefully like suppressed. Like my ability to like express or have any sort of power was just absolutely annihilated. Like systemically, like psychologically, they would do like psychological torture mechanisms to make sure that like I wasn't actually thinking on my own or like being able to deviate from anything anybody ever told me. To the degree that it's such an ungrained in me. Like I once was a friend, we were traveling and he wanted me to hop a turnstile. It was like very late at night, the train was here. And I could not physically force myself to do it. Like he was like yelling me like, come on, do it. Like, I was trying so hard to make my body cross the line. And it was just, it's like embedded in my physical being to like be unable to do stuff like that, </s><s>[INST] which is really annoying. [/INST] Do you're not free to take action in this world? Yeah, some of them. So that was I think the most annoying part </s><s>[INST] of the, my upbringing. [/INST] Would you classify it as like suffering? At the time, yeah, definitely. Well, it's confusing cause like when I was a child, it was just painful in the sense that like things suck, but it was placed in a meaning framework, right? Like it is good, it is virtuous to submit to your parents and do what they want. If they tell you to say goodbye to your best friend forever and never talk to them again, you go do that without complaining. And so like, I would go do something like that. And I would, like it would suck. It really was like concretely painful, but it was also placed in this narrative where I was like fulfilling some sort of greater purpose. And so, it's very confusing to refer to it as suffering because there's so many painful things we do today that are placed in the narrative of a greater purpose that like I think I would agree with like I go get a medical procedure done, and that sucks. but I'm like, ah, this is helping me in the long run. But like, say if I got abducted to an alien planet and they're like, by the way, all of those medical procedures you got done, like you didn't have to get them done, those are totally unnecessary, then I might get really upset about it. </s>

<s>[INST] but it still needs to be better. So I've got a chance to interact with a lot of soldiers that served in Iraq and Afghanistan. And now a lot of soldiers from all different kinds of nations in Ukraine went to the front. There's a bond between soldiers like any other. I don't know if you can speak to why do you think that is on the opposite side of PTSD. There's a deep human connection. There's like a love for each other. What is that? [/INST] What is that about war and combat that creates that common? Well, you're seeing, we've talked earlier about that vulnerability, right? So I believe that combat, I believe that most survival situations strip away all ego. And I mean, there are a couple of different layers to this, but I have not served in war. So I wanna be cautious here, but from what I know just about psychology and also from my own experience of survival type experiences, when you're with a group of people and all the ego stripped away, nothing else matters. The focus is on the here and now and a specific mission or your day to day, you can get really close. You're very, very vulnerable. And also in my experience, the guys I work with who have served, there aren't a lot of people who understand what they've been through. Not only some of the unspeakable things they've been through in combat, but some of the things that they feel are unspeakable about returning, especially if they are experiencing trauma, a lot of them, some of the things that service members with PTSD are the most reluctant to disclose is the feeling like they may not know if they love their children anymore or their wife. That they don't even know if they can love anymore. That they feel emotionally numb. That they wanna kill someone. That they have a whole lot of racist beliefs and thoughts. There are a lot of things that can be associated with PTSD that aren't as clear or expected. And these guys don't have many people who understand it or they don't think they would, </s><s>[INST] but a lot of their fellow service members do. And so I'm going back to Ukraine and boy, nothing makes reveals the human condition. In a more pure form than war, especially the kind of war you get in that part of the world, especially the war in Ukraine, which is a very 20th century kind of war. Brutal, brutal. Well, like I mentioned in a few different ways, you're exceptionally successful by I think the best definition of success. You're doing what you love and you're one of the best people in the world to doing it. And so what advice would you give to young people that look up to you that saw you in the trial, which is your most public facing thing and are just looking, young people that are looking to find what they wanna do with their life career wise [/INST] or what advice career wise or? I love that question. What would you tell them? I'm gonna tell them something my dad told me. He said to me, Shannon, just pick anything. Pick anything, if you like it at all studying it, just pick it. He was like, look, don't worry about the job. You don't even know all the jobs that exist. Pick something you like, you will make it your own. And that is exactly what happened. I like psychology. I was reading somehow self-help books. It's not like I had this calling where I, looking back, I can actually create that story because I think now it makes a lot of sense that I do what I do. But I was lost and scared. I started studying psychology. I met a professor who was really inspiring, who wasn't even a psychology professor, but he was public policy. I stayed in touch with that professor. He is a dear friend still to this day. That was 20 years ago. We do research together in Mexico, integrative research with public policy officials and environmental engineers. And I get to be the psychologist on the trip. I never ever dreamed that that sort of stuff could happen. I didn't know about forensic psychology. I also wanna warn anybody who's interested in forensic psychology that it's not like you're solving crimes all day and getting calls by the FBI. You are going to be sitting alone in your home office with your husband, bringing you bowls of cereal and reminding you to go to the bathroom because you haven't gotten up in like 24 hours from the computer and you're gonna have papers all around you and you're just gonna write 75 dense pages with citations of like science. It's brutal. It's academic, but it's fulfilling. My friend Franny posted a meme of one of the girls from Glee or something crying and saying, I'm the happiest I've ever been. And she said, it reminds her when I try to convince her to do forensic site, because I think her mind is perfect for it. You have to be strategic and thorough, but it's a slog, but it's wonderful. </s><s>[INST] It's wonderful. What would you tell? But you're gonna love it. But it's fulfilling. The image of your husband bringing you cereal while you work on the 75 pages is maybe the most romantic thing I've ever heard. So we started on love. Let me ask one last question about the same topic. What's the role of love in this whole thing, in the human condition, [/INST] in this whole experiment we've got going on on earth? I think it's all there is, like that jewel song. </s><s>[INST] How does that go? [/INST] God, I don't sing it, don't get it in my head. Please don't sing it, please don't sing it. There have been some profound moments in my life where I feel like I am closest to kind of the truth of life or what it's all about. And usually there's this resonating sense of love and ease and love for myself, love for other people, sort of like it's all okay, we're all okay, we're gonna get through this. I liked what you said about the harm caused by the misinformation or negative things being said about you. Because you're right, it harms that bigger picture. </s>

<s>[INST] So just like in the case of deep blue beating Gary, Kasparov, So Gary was, is I think the first time he's ever lost actually to anybody and I mean there's a similar situation loose at all. It's uh it's a tragic uh it's a tragic loss for humans, but a beautiful one. I think that's kind of uh from the tragedy sort of emerges over time, emerges the kind of inspiring story, [/INST] but </s><s>[INST] lisa doll recently analysis retirement. [/INST] I don't know </s><s>[INST] if you can look too deeply into it, but he did say that even if I become number one, there's an entity that cannot be defeated. So what do you think about these words? What do you think about his retirement from the game? And go, [/INST] well, let me take you back first of all to the first part of your comment about Garry Kasparov because actually at the panel yesterday, um he specifically said that when he first lost to deep blue, he he viewed it as a failure. He viewed that this this had been a failure of his, but later on in his career, he said he'd come to realize that actually it was a success. It was a success for everyone because this marked transformational moment for for ai. Um so even for Garry Kasparov, he came to realize at that moment was pivotal and actually meant something much more than than his personal loss in that moment um lisa doll, I think was a much more cognizant of that even at the time. So in his closing remarks to the match, um he really felt very strongly that what had happened in the Alphago match was not only meaningful for ai but for humans as well. And he felt as a go player that it had opened his horizons and meant that he could start exploring new things. It brought his joy back for the game of go because um it had broken all of the conventions and barriers and meant that, you know, suddenly suddenly anything was possible again. Um And so yeah, I was sad to hear that he'd retired, but you know, he's been a great a great world champion over many, many years and I think, you know that he'll be he'll be remembered for that ever more. He'll be remembered as the last person to beat Alphago. I mean after after that we we increase the power of the system and and the next version of Alphago beats um That the other strong human players 60 games to nil. Um so you know what a great moment for him and something to be remembered for. </s><s>[INST] It's interesting that you spend time at Triple Ai on a panel with Garry Kasparov, what I mean, it's almost I'm just curious to learn. Mhm. The conversations you've had with Gary, because he's also now he's written a book about artificial intelligence, he's thinking about ai he has kind of a view of it and he talks about Alphago a lot. What what's your sense because arguably I'm not just being Russian, but I think Gary is the greatest chess player of all time, Probably one of the greatest game players of all time and you sort of um at the center of creating a system that beats one of the greatest players of all time. So what is that conversation like? Is there anything any interesting digs, any bets and you come and you find the things, any profound [/INST] things. So Garry Kasparov has an incredible respect for what we did with Alphago and it's amazing tribute coming from, from him of all people that he really appreciates and respects what we've done. And I think he feels that the progress which has happened in computer chess, which later after Alphago, we, we built the Alpha Zero system which defeated the world's strongest chess programs and to Garry Kasparov that moment in computer chess was more profound than than than deep Blue. And the reason he believes it mattered more was because it was done with with learning and a system which was able to discover for itself new principles, new ideas, um which were able to play the game in a, in a, in a way which he hadn't always um known about or anyone. Um and in fact one of the things I discovered at this panel was that the current world champion magnus Carlsen apparently recently commented on his improvement in performance and he attributed it to Alpha Zero. He's been studying the games of Al Jazeera and he's changed his style Play more like α zero and it's led to him um actually increasing his his his rating um to a new peak. </s><s>[INST] Yeah I guess uh to me just like to Gary the inspiring thing is that and just like you said with reinforcement learning reinforcement learning and deep learning. Machine learning feels like what intelligence is. And you know you could attribute it to sort of uh a bitter viewpoint from Gary perspective from uh us humans perspective saying that sir Pure search that IBM Deep Blue was doing is not really intelligence but somehow it didn't feel like it. And so that's the magical, I'm not sure what it is about learning that feels like intelligence but it does. [/INST] So I think we should not demean the achievements of what was done in previous areas of a I think that deeply was an amazing achievement in itself. Um And that heuristic search of the kind that was used by Deep Blue had some powerful ideas that were in there but it also missed some things. So so the fact that the that the evaluation function, the way that the chest position was understood was created by humans and not by the machine is a limitation which means that there's a ceiling on how well it can do but maybe more importantly it means that the same idea cannot be applied in other domains where we don't have access to um the kind of human grandmasters and that ability to kind of encode exactly their knowledge into an evaluation function and the reality is that the story of ai is that, you know, most domains turn out to be of the second type where where knowledge is messy, it's hard to extract from experts or isn't even available. And so so we need to solve problems in a different way. Um And I think Alphago is a step towards solving things in a way which which puts learning as a first class citizen and says um systems need to understand for themselves how to understand the world, how to judge their the value of any action they might take within that world, in any state they might find themselves in and in order to do that. Um Yeah, we we make progress towards ai. </s>

<s>[INST] Can I ask you about blind spots? When you reduce stuff to numbers, the cost and benefits, is there stuff you might miss that are important to the flourishing of the human species? [/INST] So everyone will have to say, of course there must be blind spots. But I don't know what they are. Yeah, I'm sure Andy would probably be better at telling me what they are. So we try to incorporate all of it, but obviously we're not successful. You can't incorporate everything, for instance, in the cost benefit analysis. But the point is in some way, I would worry a lot about this if we were sort of close to perfection human race, we're doing almost everything right, but we're not quite right, then we need to get the last digits right. But I think it's much more the point that I tried to make before, that we're all focused on going to an electric car or something else rather than fracking. We're all focused on cutting carbon emissions instead of reducing vulnerability. So we're similarly getting orders of magnitude wrong. And while I'm sure I have blind spots, I think they're probably not big enough to overturn that </s><s>[INST] point. Andy Wise, I don't know what they are, Bjorn and economists are all wrong about everything. [/INST] Well, the models, we could spend a whole day on models. There are economic models, there's this thing called optimization models. There were two big ones used to assess the US plan, this new big IRA, inflation reduction package. And they're fine, they're a starting point for understanding what's possible. But as this gets to the journalism part or the public part, you have to look at the caveats. You have to look at what model... Economists expressly exclude things that are not modelable. And if you look in the fine print on the repeat project, </s><s>[INST] the Princeton version of the assessment of the recent giant legislation the whole day on models, [/INST] the fine print is the front page for me as a deep diving journalist, because it says we didn't include any sources of friction, meaning resistance to putting new transmission lines through your community or people who don't want mining in America, because we've exported all of our mining, we've mined our cobalt in Congo. And trying to get a new mine in Nevada was a fraught fight that took more than 10 years for lithium. So if you're excluding those elements from your model, which on the surface makes this $370 billion package have an emissions reduction trajectory, that's really pretty good. And you're not saying in your first line, by the way, these are the things we're not considering. That's the job of a journalist. </s><s>[INST] Summarize all of human history with that one word friction. [/INST] Well, inertia, friction implies there's a force that's already being resisted, but there's also inertia, which is a huge part of our... We have a status quo bias. The scientists that I... In grappling with the climate problem as a journalist, I paid too much attention to climate scientists. That's why all my articles focused on climate change. And it was 2006. I remember now pretty clearly, I was asked by the weekend review section of the New York Times to write a sort of a weekend thumb sucker, we call them on... Thumb sucker? You know, you sit and suck your thumb and think about something. Why is everybody so pissed off about climate change? It was after the Al Gore movie came out in Convena Truth, Hurricane Katrina's big Senator Inhofe in the Senate from Oklahoma wasn't yet throwing snowballs, but it was close to that. And so I looked into what was going on. Why is this so heated? In 2006, the story is called Yelling Fire on Hot Planet. And that was the first time... This is after 18 years of writing about global warming. That was the first time I interviewed a social scientist, not a climate scientist. Her name was Helen Ingram. She's the UC Irvine. And she laid out for me the factors that determine why people vote, what they vote for, what they think about politically. And they were the antithesis of the climate problem. She used the words, she said, people go into the voting booth thinking about things that are soon, salient, and certain. And climate change is complex, has long timescales. And that really jogged me. And then between 2006, 2010, I started interviewing other social scientists and this was by far the scariest science of all. It's the climate in our heads or inconvenient minds. And in how that translates into political norms and stuff really became the monster, </s><s>[INST] not the climate system. Is there social dynamics to the scientists themselves? Because I've gotten to witness a flocking behavior with scientists. So it's almost like a flock of birds. Within the flock, there's a lot of disagreement and fun debates and everybody trying to prove each other wrong, but they're all headed in the same direction. And you don't want to be the bird that leaves that flock. So there's an idea that science as a mechanism will get us towards the truth, but it'll definitely get us somewhere. But it could be not the truth in the short term. In the long term, a bigger flock will come along and it will get us to the truth. But there's a sense that I don't know if there's a mechanism within science to snap out of it if you're down the wrong track. Usually you get it right, but sometimes you don't. When you don't, [/INST] it's very costly. And there's so many factors that line up to perpetuate that flocking behavior. One is media attention comes in. The other is funding comes in. The National Science Foundation or whatever, European foundations pour a huge amount of money into things related to climate. And then your narrative in your head is shaped by that aspect of the climate problem that's in the spotlight. I started using this hashtag a few years back, narrative capture. Be wary of narrative capture where you're on a train and everyone's getting on the train. And this is in the media too, not just science. It becomes self-sustaining and contrary indications are ignored or down played. No one does replication science because your career doesn't advance through replicating someone else's work. So those contrary indications are not necessarily really dug in on. And this is way beyond climate. This is of many fields. As you said, you might have seen this in AI. And it's another form of path dependency, the term I used before. The breaking narrative capture to me in AI for me has come mostly from stepping back and reminding myself of the basic principles of journalism. Journalism's basic principles are useful for anybody confronting a big, enormous, dynamic, complex thing is who, what, where, when, why. Just be really rigorous about not assuming because there's a fire in Boulder County or a flood in Fort Myers that climate, which is in your head because you're part of the climate team at the New York Times or </s>

<s>[INST] the whole journey was incredible to me to watch. I was um because I knew well part of it I was at M. I. T. And I knew the difficulty of computer vision and I knew the whole, I had a lot of colleagues and friends about the DARPA challenge. I knew how difficult it is. And so there was a natural skepticism When I first drove a Tesla with the initial system based on mobile, I I thought there's no way so the first one I got in I thought there's no way this car could maintain. Um like staying in lane and create a comfortable experience. So my intuition initially was that the link keeping problem is way too difficult to solve. [/INST] Oh thank you. Yeah, that's relatively easy. </s><s>[INST] Well like but not just but solve in the way that we just we talked about previously is prototype versus a thing that actually creates a pleasant experience over hundreds of thousands of miles and millions. Yeah, so [/INST] we have to wrap a lot of code around the mobile. I think it's it doesn't just work by itself. </s><s>[INST] I mean that there's part that's part of the story of how you approach things. Sometimes sometimes you do things from scratch sometimes the first you kind of see what's out there and then you decided different scratch. That was one of the boldest decisions I've seen is both on the hardware and the software to decide to eventually go from scratch. I thought again, I was skeptical whether that's going to be able to work out because it's such a such a difficult problem and so it was an incredible journey. What I see now with everything, the hardware to compute the sensors. The the things I maybe care and love about most is the stuff that Andre Karpati is leading with the data set selection, the whole data engine process, the neural network architectures, the way that in the real world that network has tested validated all the different test sets, um, you know, versus the Image net model of computer vision, like what's in academia is like real world artificial intelligence. So [/INST] um, Andre is awesome and obviously plays an important role, but we have a a lot of really talented people driving things. So, um, and a shark is actually the, the head of autopilot engineering. Um Andres director of </s><s>[INST] Ai Ai stuff. Yeah, so yeah, there's I'm aware that there's an incredible team of just a lot going on. [/INST] Yeah, I just, you know people people will give will give me too much credit and they will give andre too much credit so </s><s>[INST] and people should realize how much is going on under the under the hood. [/INST] Just a lot of really talented people. Um The tells the autopilot Ai team is extremely talented, it's like some of the smartest people in the world. Um So yeah, we're getting it done </s><s>[INST] What are some insights you've gained over those 56 years of autopilot about the problem of autonomous driving. So you leaped in having some sort of first principles kinds of intuitions, but nobody knows how difficult the problem. Like I thought the [/INST] self driving problem would be hard but it was harder than I thought. It's not like I thought it would be easy, I thought it was very hard, but it was actually way harder than even that. So and what it comes down to you at the end of the day is to solve self driving. Uh you have to solve ah you're basically need to recreate what humans do to drive, which is humans drive with optical sensors, eyes, and biological neural nets. Um And so in order to that that's how the entire road system is designed to work with with basically passive optical and neural nets um biologically. Um And now that we need to so for actually for full self driving to work, we have to recreate that in digital form. Um So we have to um that that means cameras with advanced neural nets in silicon form. Ah And and then you it will obviously solve for full self driving. That's that's the only way. I don't think there's any other way. </s><s>[INST] But the question is what aspects of human nature do you have to encode into the machine? Right. So you have to solve the perception problem like detect and then you first well realize what is the perception problem for driving like all the kinds of things you have to be able to see like what what do we even look at when we drive? There's uh I just recently heard andre talked about M. I. T. About like car doors, I think it was the world's greatest talk of all time about car doors. Um the you know the fine details of car doors like what is even an open car door man. So like the the ontology of that that's a perception problem. We humans solve that perception problem and Tesla has to solve that problem and then there's the control and the planning coupled with the perception you have to figure out like what's involved in driving. Like especially in all the different edge cases. And and then I mean maybe you can comment on this how much game theoretic kind of stuff needs to be involved, you know at a four way stop sign, you know, are as humans when we drive our actions affect the world like it changes how others behave most of the time was driving If you you're usually just responding to the scene as opposed to like really um asserting yourself in the scene. Do you think? [/INST] I think I think I think these sort of control logic conundrums are not the hard part um The you know, let's see um </s><s>[INST] What do you think is the hard part in this whole um beautiful complex problem. [/INST] So it's a lot of freaking software man, a lot of smart lines of code uh for sure in order to have um create an accurate factor space. So like you're you're coming from image space which is like this this flow of um photons going to the camera cameras and and then uh since you have this massive bit stream um in image space and then you have to effectively compress the a massive but stream corresponding to photons that knocked off an electron and a camera sensor and turn that foot stream into a vector space by a vector space. I mean like I you know you've got cars and humans and lane lines and curves and ah traffic lights and that kind of thing. Um Once you have an accurate vector space um the control problem is similar to that of a video game like a grand theft order of cyberpunk. Um If you have accurate accurate best vector space. It's the control problem is, I wouldn't say it's trivial. It's not trivial, but it's it's it's it's it's not like some it's a mountable thing. It's just it's but but having an accurate vector space is very difficult. </s>

<s>[INST] right? It's just just like we're talking with chomsky and language. It's the thing we've invented for the communication of those ideas. They're not necessarily the deep representation of those ideas. So what what's a what's a good way to model such powerful mathematical reasoning? Would you say? What what are some ideas you have for capturing this in a model? [/INST] The insights that human mathematicians have had is a combination of the kind of the intuitive kind of connection ist like knowledge that makes it so that something is just like obviously true, so that you don't have to think about why it's true that then makes it possible to then take the next step and ponder and reason and figure out something that you previously didn't have. That intuition about it then ultimately becomes a part of the intuition that the next generation of mathematical thinkers have to ground their own thinking on so that they can extend the ideas even further. I came across this quotation uh from our report carry while I was um walking in the, in the woods with my wife in a state park in northern California uh late last summer. And what it said on the bench was it is by logic that we prove, but by intuition that we discover. And so what what for me, the the essence of the of the project is to understand how to bring the intuitive connection, ist resources to bear on letting the intuitive discovery arise. Uh you know, from engagement in thinking with this formal system. So I think of, you know, the ability of somebody like Hinton or Newton or Einstein or Rummelhardt or plank array too. Um our committee is just another example, right? So suddenly a flash of insight occurs. It's it's like the constellation of all of these simultaneous constraints that somehow or other causes the mind to settle into a novel state that it never did before. And and give rise to a new idea um that, you know, then you can say, okay, well now how can I prove this? You know, how do I write down the steps of that theorem that that allow me to make it rigorous and certain. And so I feel like the the kinds of things that we're beginning to see um deep learning systems do of their own accord. Yeah. Kind of gives me this feeling of of I don't know, hope or encouragement that ultimately, um it'll all uh happen. Um so in particular, as uh many people now have have become really interested in thinking about, you know, neural networks that have been trained with massive amounts of text mm can be given a prompt and they can then sort of generate some really interesting fanciful creative story from that prompt. Um and uh there's there's kind of like a sense that they've somehow synthesized something like novel out of the, you know, all of the particulars of, all of the billions and billions of experiences that went into the training data that gives rise to something like this sort of intuitive sense of what would be a a fun and interesting little story to tell or something like that. It just sort of wells up out of the out of the letting the thing play out its own imagining of what somebody might say given this prompt as a as a input to get it to start to generate its own thoughts. And and to me that that sort of represents the potential of capturing this, the intuitive side of this. </s><s>[INST] And there's other examples, I don't know if you find them as captivating is, you know, on the Deepmind side with Alpha Zero. If you study chess, the kind of solutions that it has come up in terms of chest. It is it there's novel ideas there, it feels very uh like there's brilliant moments of insight and the mechanism they use if you think of search as as maybe more towards the good old fashioned ai and and then there's the connection is the network that has the intuition of looking at a board, looking at a set of patterns and saying, how good is this set of positions and the next few positions. How good are those? And that's it. No, that's just an intuition um grandmasters have this and understanding positional lee tactically how good the situation is, how how can it be improved without doing this full like deep search. Um and then maybe doing a little bit of what human chess players called calculation, which is the search, taking a particular set of steps down the line to see how they enroll. But there there is moments of genius in those systems too. So that's another hopeful illustration that from neural networks can emerge this novel creation of an idea. [/INST] Yes, and I think that, you know, I think democrats Hassabis is um you know, he's spoken about those things, he I heard him describe a move that was made in in one of the go matches against lisa at all in this, in a very similar way. And um it caused me to become really excited to collaborate with some of those guys that at Deepmind. Um so I think though that what what I like to really emphasize here is one part of what I like to emphasis about mathematical cognition at least, is that philosophers and magicians going back three or even A little more than 3000 years ago began to develop these formal systems and gradually the whole idea about thinking formally got constructed. Um and you know, it's preceded euclid um certainly present in the work of families and others and I'm not the world's leading expert in all the details of that history, but you clods elements were the, the kind of the touch point of a, of a coherent document that sort of laid out this idea of an actual formal system within which these objects were characteristic and the um the system of inference that allowed new truths to be derived from others was sort of like established as a paradigm. And um what what I find interesting is the idea that the ability to become a person who is capable of thinking in this abstract formal way is, you know, a result of the same kind of immersion uh in in experience thinking in that way that, you know, we now begin to think of our understanding of language as being right? So we immerse ourselves in in a particular language in a particular world of objects and their relationships and we learned to talk about that and we develop intuitive understanding of the real world in a similar way. We can think that what academia has created for us, what, you know, those early philosophers in there academies in Athens and alexandria and others other places allowed, was the development of these schools of thought modes of thought that then become deeply ingrained and you know, it becomes what it is that makes it so that somebody like jerry fodder would think that um systematic thought is the essential characteristic of the human mind as opposed to a derived and and an acquired characteristic that results from acculturation in a certain mode that's been invented by humans, </s>

<s>[INST] concept of improving the form 3500B where you scan. Go ahead. Yeah, right. That just makes me laugh. I can just tell the form sucks by the fact that it has that code name. Sorry. Yeah, yeah, yeah, yeah, yeah, exactly, right? [/INST] UX is broken at every layer, right? Yeah, yeah, yeah. So they have a bad yelp for drugs. Could we make a better one? We could make a better one, just modern UX. The key insight here, by the way, which is a non-obvious point, and I've got a whole talk on this actually that I should probably release. I actually did like almost eight, nine years ago. It's called regulation is information. Product quality is a digital signal. Okay. What do I mean by that? Basically, when I talk about exit, exit the Fed, that's the crypto economy, right? What does exit the FDA look like? Well, one key insight is that many of the big scale tech companies can be thought of as cloud regulators rather than land regulators. What do I mean by that? Well, first, what is regulation? People do want a regulated marketplace. They want A, quality ratings, like on a one to five star scale, and B, bands of bad actors, like the zero star frauds and scammers and so on. And these are distinct, right? Somebody who's like a low quality, but well intentioned person is different than a smart and evil person. Those are two different kinds of failure modes you could have in a marketplace, right? Why is it rational for people to want a regulated marketplace, especially for health because they want to pay essentially one entry cost and then they don't have to evaluate everything separately where they may not have the technical information to do that, right? You don't want to go to Starbucks and put a dipstick into every coffee to see if it's poisoned or something like that. You sort of want to enter a zone where you know things are basically good and you pay that one diligence cost on the zone itself, right? Whether it's a digital or physical zone, and then the regulator's taking care of it. And they've baked in the regulatory cost into, you know, some subscription fee of some kind, right? So the thing is, the model we've talked about is the land regulator of a nation state in a territorially bounded thing. But the cloud regulator, what's a cloud regulator? That is Amazon star ratings. That's Yelp. That is eBay. That is Airbnb. That is Uber and Lyft and so on and so forth. It's also actually Gmail and Google. Why? Because you're doing spam filtering and you are doing ranking of emails with priority inbox, right? With Google itself, they ban malware links, right? So the bad actors are out and they're ranking them, right? How about Apple, the app store, right? They ban bad actors and they do star ratings. When you start actually applying this lens PayPal, you know, they've got a reputation. Every single web service that's at the scale of like tens of millions or hundreds of millions of people has had to build a cloud regulator. And the crucial thing is that it scales across borders. So you can use the data from Mexico to help somebody in Moldova or vice versa, right? Because it's fundamentally international, right? Those ratings, you have a network effect. And there's another aspect to it, which is these are better regulators than the land regulators. For example, Uber is a better regulator than the taxi medallions. Why? Every ride is GPS tracked. There's ratings on both the driver and the passenger side. Both parties, you know, know that payment can be rendered in a standard currency, right? If you have below a certain star rating on either side, you get deplatformed and so on to protect either rider or driver and on and on, right? What does that do? Think about how much better that is in taxi medallions rather than a six month or annual inspection. You have reports from every single rider, okay. Before Uber, it was, the taxi drivers and taxi regulators were in a little monopoly locally. Okay? Because they were the persistent actors in the ecosystem. Taxi riders had nothing in common, didn't even know each other. In New York, some guy gets a taxi and they're a guy, they have no way to communicate with each other. So the persistent actors in the system were the regulators and the drivers. And they had this cozy kind of thing and medallion prices just kept going up. And this was a sort of collaboration on artificial scarcity. Okay. Afterwards with Uber and Lyft and other entrants you had something interesting. A different kind of regulator driver fusion. If you assume regulatory Captain exists and lean into it. Uber is the new regulator and Uber drivers are the drivers. Lyft is the competing regulator and Lyft drivers are the new drivers. Okay. So you have a regulator driver fusion versus another regulator driver fusion. You no longer have a monopoly. You have multiple parties. Okay, you have a competitive market. This is the concept of like polycentric law, right? Where you have multiple different legal regimes in the same jurisdiction overlapping that you can choose between with a tap of a button, right? All these concepts from like libertarian theory, like, you know, polycentric law or catalysis, all these things are becoming more possible now that the internet has increased microeconomic leverage and because that exit is now possible. Now, you may argue, Oh, well, Lyft and Uber, they're not profitable anymore. And there's two different criticisms of them. One is, Oh, they're not profitable, or Oh, they're charging too much. And I think part of this is because of certain kinds of the regulatory status caught up to try to make them uncompetitive. For example, they don't allow people in some states to identify themselves as independent contractors, even if they are part time. Okay. There's various other kinds of rules and regulations, you know, in Austin for a while, Uber was even banned, what have you, right? net net, though, like Uber, grab, go check, Lyft, DD, like ride sharing as a concept is now out there. And whatever the next version is where it's self driving, like, while it's like a very hard fought battle, and the regulatory state keeps trying to push things back into the garage. This is a fundamentally better way of just doing regulation of taxis. Similarly, Airbnb for hotels, I mean, it's basically the same thing. Okay. And Airbnb could use competition, I think that it would be good to have, you know, like competition for them. And there are other kinds of sites opening up. But the fundamental cons of the cloud regulator, now let's apply it here. Once you realize regulation is information, the way you'd set up a competitor to FDA, or SEC, or FAA, or something like that, is you just do better reviews, and you just start with that, that's pure information, you're under free speech, that's like still, you know, the most defended thing, literally just publishing reviews, and not just reviews by any old person. It turns out that FDA typically will use expert panels, whether they're expert panels, it's like professors from Harvard or you know, things like that. So what that is, is this concept of a reputational bridge, where you want to do is you want to have folks who are let's say, biotech entrepreneurs, or their you know, profs like Sinclair, or what have you, you do want to have the reviews of the crowd. Okay? But you also want to have, especially in medicine by this, you want to have the reviews of experts of some kind. So there's going to be defectors from the current establishment. Okay, just like, you know, there are profs who defected from Computer Science, academia to become Larry and Sergey and whatever, you know, they weren't profs they were grad students, right. In the same way, you'll have defectors, who have the credentials from the old world, but can build up to new just like there's folks from Wall Street, who have come into cryptocurrency and helped legitimate it, right? Just like, there's folks who left Salsberger to come to sub-stack. Okay. Um, you know, we have, we have these folks who by defecting they help. And then And they're also supplemented by all this new talent coming in, right? That combination of things is how you build a new system. It's not completely by itself, nor is it trying to reform the old, it's some fusion. Okay? So in this new system, who do you have? You have like the most entrepreneurial and innovative MDs, you have the most entrepreneurial and innovative professors, and you have the founders of actual new products and stuff. And they are giving open source reviews of these products. And they're also building a community that will say, look, we want this new drug, or we want this new treatment, or we want this new device, and we're willing to crowdfund 10,000 units. So please give us the thing and we'll write a very fair review of it. And we'll also all evaluate it as a community and so on. So you turn these people from just passive patients into active participants in their health. That's a community part. And they've got the kind of biomedical technical leadership there. Now, what is the kind of prototype of something like this? Something like VITA DAO is very interesting. Things like molecule DAO are very interesting. It'll start with things like longevity, right? And why is that? Because the entire model of FDA, this 20th century model, is wait for somebody to have a disease and then try to cure them. Okay? Versus, you know, saying an ounce of prevention is worth a pound of cure, right? Why are we not actually tracking folks and getting a constant dashboard on yourself, so you can see whether things are breaking, and then you deal with it just like you've got server uptime things. You don't wait necessarily for the site to go down. You start seeing, oh, response rates are spiking, we need to add more servers, right? You have some warning, okay? Even 10 years ago, there was this article called The Measured Man in the Atlantic, where this guy, physicist Larry Smarr, okay, what he was doing is he was essentially doing a bunch of measurements on himself. And he was finding that there were predictors of inflammation that were spiking and he went to the doctor, showed the charts, and the doctor was like, I can't do anything with this. Then it turned out to be an early warning of a serious condition that he had to, I think, go for surgery or something. And he was starting to think, well, look, the way that we're doing medicine right now is it's not quite pre-germ theory of disease, but it is pre-continuous diagnostics, okay? Continuous diagnostics, just to talk about this for a second, this is... I mentioned one angle on which you go after FDA, which is like the better phase four, right? I've mentioned the concept of better reviews in general, okay? I mentioned VITA DAO, which is like a community that is going after longevity. Let's talk about continuous diagnostics. So basically, we know better what is going on in Bangalore or Budapest than in our own body. That's actually kind of insane to think about. This stuff that it's all the other side of the world, 10,000 miles away, but a few millimeters away, you don't really know what's going on, right? And that's starting to change with all the quantified self-devices, the hundreds of millions of Apple watches and Fitbits and stuff, right? You're also starting to see continuous glucose meters, which are very important. They're starting to give you readouts. People are seeing, wow, this is spiking my insulin or this is spiking my blood sugar. And it might be something you didn't predict. It varies for different people. For some people, you know, a banana isn't a big deal for others. It's actually quite bad for the blood sugar. What happens when you extend that? About 10 years ago, a guy, Mike Snyder, a professor at Stanford, did something called the integrome, where he just threw the kitchen sink of all the diagnostics he could at himself over the period of, I think, a few weeks or a few months, I forget the exact duration. He's able to do things where he could see, during that period, he got a cold or something, and he could see in the expression data, the gene expression data, that he was getting sick before he felt sick. He could also see that something about that viral infection made him develop diabetes-like symptoms, if I'm remembering it accurately. So you could see, oh, wait a second, these are things that I can see in my readouts that I would only have the vaguest interpretation of as like a human being, right? And moreover, he could take, you know, I don't think he did this, but if you took treatments, if you took drugs, right, you could actually show what your steady state was, if you tracked over time, show what your disease state or sick state was, and then this drug pushes you back into non-disease state. You can actually get a quantitative readout of what, you know, like steady state was, right? So that, and that steady state, you know, your expression levels across all these genes, your small molecules, basically everything you can measure, that's going to vary from person to person, right? What's healthy and natural for you may be a different baseline than for me. For example, people who are, a small example, people who are South Asian or have dark skin tend to have vitamin D deficiency. Why? Because we need a lot of sunlight. So often inside you're tapping in your screen, so what are you doing? Take like actually significant vitamin D infusions, okay? That's like a small example of where baselines differ between people, okay? So continuous diagnostics, what could that mean? That could mean, you know, things like the continuous glucose meter, it's quantified self, it's like continuous blood testing, right? So you have a so called mobile phlebotomist. This is something which phlebotomy takes blood, right? Mobile phlebotomy would come to your office, come to your remote office. This is a great business for people, I think, you know, you can revisit this in 2022. People tried this in the 2010s, but I think it's worth revisiting. Mole phlebotomist comes every week or every month, takes blood, runs every test, right? Maybe that's, you know, a few thousand dollars a year, maybe eventually gets to a few hundred dollars a year. And that's expensive in some ways. </s>

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

<s>[INST] So with your word on fire ministries and and and the website and the communication efforts. What what what is the thing you're seeking? Just you if we can pause and for a brief moment allow you to be prideful or um of course just joking. But what what is your local efforts, your small little pocket of the world with small in quotes. Um, what was the word on fire? [/INST] Yeah, it's just using the, you know media especially the new media social media to get the gospel out. So I started what 20 some years ago just on a radio show in Chicago 5 15 on sunday morning I had a 15 minute sermon show And I asked the people in this parish, I was at I said I need $50,000 to get on for 15 minutes at 5:15 on Sunday morning and they all laughed when I proposed that. But they gave me the money. So that's how I got started just doing a sermon on the radio and then it branched off into into video stuff and TV and then I did a documentary, I went all over the world and kind of told the story of Catholicism. So that's how we started and now I'm using all the new media and social media. But what I really love what we're doing today is something I really like, which is having a conversation outside of just the narrow catholic world or even the narrow christian world, but to look out to the wider culture and you know, who's talking about interesting things and how can the church engage there? And you know, so that's the purpose of word on fire. </s><s>[INST] Is it overwhelming to face so many different sort of atheists then complex thinkers like Jordan Peterson and some of the more political style thinkers that you've spoken with is that what is it Dave Rubin who's also um, has a way different worldview as well. How is that terrifying? Is that exciting to [/INST] you? </s><s>[INST] Is it challenging? [/INST] Yeah, maybe I'll be above, but I'm more exciting, you know, I would say I like doing that. I was a teacher for a long time. I taught in the seminary for like 20 years and so you know, I've been engaging these questions for a long time. I'm a writer, I've written about 20, some books. So and I write some at a popular level. I write some at a high academic level and I like doing all that. So, I I I love those ideas. I love those questions. I love engaging people and I find my own experience you do run into of course a lot of the, you know, vitriol and kind of just stupidity and all that online. And I get it, and religion is such a magnet for people's hostility for different reasons. So I get that, like you read it, we talked about you have to wade through, you know, swamps of of obscenity and everything, but but I do it, I like it and it's worthwhile because in that reddit experience so many of the issues that preoccupy young people, I can name them for you exactly what they are, it comes to religion. How do you know there's a God? So the God question, secondly, why is there so much suffering in the world? Third question, why do you think your religion is the right religion? Fourth, why are you so mean to gay people? So those are the four things that I again and again, come up when dealing with young people. I I've told my brother bishops and priests about that. I said structure your adult education programs, or structure your youth outreach around those four questions. </s><s>[INST] Uh, well, let me ask you about gay marriage, how do we make sense of the love between a man and a man and a woman and the woman and the institution of marriage. [/INST] We love friendship and friendship is at the heart of things. And so nothing wrong with friendship between, you know, a man and a man and woman and a woman. But go back to Aristotle thomas, Aquinas about natural finality, ease and intelligible forms that there's a certain form to human being which includes the physical and includes the sexual, it has a proper finality. And so we recognize that finality is twofold, both you native and procreative. And so those two we recognize as the appropriate expression of human sexuality. So that's why the church holds two, you know, sex between a man and a woman within the context of marriage is the is the right expression. We reach out to everybody in love and in respect and deep understanding and seeking to understand their lives from the inside. I mean, all of that, I agree with the bridge building that we need to do to people like in the gay community and people in gay marriage and so on. So the church holds to the the intelligible structure if you want of human sexuality and it reaches out to real human beings, always in an attitude of invitation and love and so on. So it's somewhere in there that the church takes its stance </s><s>[INST] and then uh so there's probably variation in the stances that it takes. So you're saying the institution of marriage is about the unity of which is like the friendship, the deep connection between two humans and the procreative. So being able to have Children, all that kind of stuff. It's interesting. So is our gay couples seen as sinful. So does the church acknowledge the love? That's the deep love that's possible between them. [/INST] Which is why the church says in its official teaching. It's the physical expression, let's say of of sexual passion between two men that is problematic, not their friendship, not their love for each other. Um So I think, yeah, we we confirmed the first, </s>

<s>[INST] So that's where things are moving, you're saying? Of NPD, antisocial personality disorder? [/INST] That's where things are moving to more of a spectrum with personality dysfunction. then you list the traits that are there. And I think that'll be more accurate, especially there's so much overlap between these personality disorders right now, especially cluster B, it is not uncommon for people to have two or three personality disorders to meet criteria for two or three at the same time. So speaking about borderline personality disorder and hysteionic personality disorder. Personality Disorder can best be thought of as a disorder of instability and impulsiveness. Emotional instability, instability in a person's self-identity, sense of self, instability in a person's relationships. And then underlying all of this is an intense fear of abandonment. Historyonic Personality Disorder is more of a disorder of emotionality, fate, and attention-seeking. This, you know, histrionic disorder typically is known for the dramatics and people who are observing or interacting with somebody with this disorder may even feel themselves almost kind of wanting to turn away. There's a sense of play acting as the person is speaking or engaging with you. Something just feels a little bit disingenuous and a lot of attention seeking, similar to borderline personality disorder, you might see with histrionic personality disorder, attempts to manipulate. However, the motivation with histrionic personality disorder is that attention. Whereas with borderline personality disorder, the underlying motivation for almost everything is to avoid abandonment. So you'll see frantic attempts to avoid abandonment, frantic attempts to keep people close. And those frantic attempts can be really harmful to the person and to others. </s><s>[INST] But to the person themselves. So the fear of abandonment can result in the very thing you're [/INST] afraid of. Right. And there has been some research also to suggest that borderline personality disorder has different types as well. And I think this is really important because in my own work, I have encountered many people with borderline personality disorder in my own life, right? And there are different types, right? I'm thinking specifically of a girl I really love who I've worked with for years who is so self-aware about this and endearing and in my own life. She owns her shit. I can forgive almost anything if somebody just owns their shit. She might lose her temper. She might lash out. She can be erratic, but she will come back and apologize, own it, and accept full responsibility. And not only that, but identify it and make changes. She doesn't want to be harmful. I adore that about her. I think it's an admirable quality more of us could have. That's very different than when you think about it, there are nine different symptoms and you only need five to meet criteria. So depending on which symptoms you have, you might be far more calculated, conniving, manipulative, or you may just be more of the impulsive, kind of messy, emotionally erratic type. And so there's some new research also coming out that's even suggested that among women, those that score higher in some of these more calculated traits of the disorder may actually be, it may be a certain presentation of female psychopathy. </s><s>[INST] Are some of these personality disorders, again, probably impossible question to answer, but how much of it is nature? How much of it is nurture? Or how much of it is in the genetics and you just can't do much with? Maybe another question, a different way to ask that is, how much can you help that? How much can you become better? [/INST] Mm-hmm. That is a tough question. So there's been a ton of change in the way we've thought about the etiology of these personality disorders specific to borderline personality disorder. I think in general, the view is that most people believe that it was associated with neglect or trauma in childhood. While there is a correlation there, there's a correlation between that and many mental health issues, not just borderline personality disorder. We also, there is evidence to support a genetic basis for this personality disorder and there are people who have borderline personality disorder that report no childhood trauma or difficulty. Sometimes things just happen. So I think it's a mix. I think we need to think of it as biopsychosocial, which is generally the answer to most things when you're talking about how a mental health issue comes to be. I certainly think that in most cases, and here's just me speaking personally, again, I think in my own work, in most cases, what I see is that somebody may have some sort of predisposition, then they go through certain life events and learn patterns of behaving that may serve them well as a child in a dysfunctional situation, but end up being very problematic later on. Or they just have enough hardship that that gene, whatever it was, line dormant, that little borderline personality disorder gene expresses itself. And you'll see that with things like schizophrenia, depression, anxiety disorders, there tend to be certain ages where you'll just </s><s>[INST] see that expression happen. All right, for the record, it got cold in here, so we upgraded with a blanket. You look cozy. Just as a question for me, just observing the trial, it was interesting that first of all, it was a really raw and honest exploration of an intimate relationship between two people. It was interesting to watch. I suppose I haven't watched that kind of thing. It made me think about what makes for a good relationship. All the many things we've already talked about in this conversation, it was useful for that. But also there was raw recordings of two humans interaction. What did you think about that, that there's recordings? [/INST] It's kind of interesting. The act of recording your partner? </s>

<s>[INST] and that sounds cats are running the world because they took over the 1st, 1st of all. So first they while not giving a shit about humans clearly with ever with with every ounce of their being, they've somehow got just millions and millions of humans to take them home and feed them, and then not only the physical space that they take over, they took over the digital space, They dominate the Internet in terms of cuteness, in terms of mobility. And so they're they're like they got themselves literally inside the memes that become viral and spread on the internet, and they're the ones that are probably controlling humans. That's my theory. Another that's a follow up paper after the frog kissing. Okay, I mean, you mentioned sentience and consciousness. Uh you have a paper titled Generalizing Frameworks for sentience beyond natural species. So beyond normal cognition, if you look at sentience and consciousness, and I wonder if you draw an interesting distinction between those two uh elsewhere outside of humans and maybe outside of earth you think aliens are have sentience and if they do, how do we think about it? So when you have this framework, what is this paper, what is what is the way you proposed to think about? Essentially? It's [/INST] yeah, that that that particular paper was very short commentary on another paper that was written about crabs. There's a really good paper on them, crabs. And and various like a like a rubric of uh of different types of behaviors that that could be applied to different creatures. And they're trying to apply it to crabs and so on. Um I've consciousness, we can talk about the film, but it's a whole separate kettle of fish. I almost never talk </s><s>[INST] about [/INST] in this case. Yes, I almost never talk about consciousness per se. I've said very, very little about it, but we can we can talk about it if you want. Mostly what I talk about is cognition, because I think that that's much easier to deal with in a kind of rigorous, experimental, experimental way. I think that all of these, all of these terms have, you know, sentience and and and so on, have different definitions. And I fundamentally I think that people can as long as they specify what they mean ahead of time. Um I think people can define them in various ways. The one the the the only thing that I really kind of insist on is that the right way to think about all this stuff is is an an from an engineering perspective. What does it help me to to control, predict and to and does it help me do my next experiment. So, so, so, so that's that's not a universal perspective. So, some people have uh philosophical kind of underpinnings and those are primary and if anything runs against that, then it must automatically be wrong. So, so some people will say, I don't care what else, if your theory says to me that thermostats have little tiny goals. I'm not I'm not I'm so that's it. I just like that's my philosophical preconceptions like thermostats do not have goals and that's it. So, um, so that's one way of doing it. And some people do it that way. I do not do it that way. And I think that we can we we can't I don't think we can know much of anything from a from a philosophical armchair. I think that all of these theories and ways of doing things standard fall based on just just basically one set of criteria. Does it help you run a rich research program? That's it. </s><s>[INST] So I agree with you totally. But so forget philosophy. What about the poetry of ambiguity? What about at the limits of the things you can engineer using terms that are that can be defined in multiple ways and living within that uncertainty in order to play with words until something lands that you can engineer. I mean, that's to me what consciousness is. Currently, nobody really understands the the hard problem of consciousness, the subject, what it feels like because it really feels like it feels like something to be this biological system, this conglomerate of a bunch of cells in this hierarchy of competence. It feels like something. And I feel like one thing. And is that just, is that just a side effect of a complex system or is there something more that humans have or is there something more than any biological system has some kind of magic. Some kind of, not just a sense of agency, but a real sense with a capital letter s of agency? [/INST] Uh, yeah, that's a </s><s>[INST] engineering or No, [/INST] no, there definitely is. And and a lot of the poetry comes in when we realize that none of the categories we deal with are sharp as we think they are. Right. And so and so in the, you know, in the different areas of of all these spectra are where a lot of the poetry since I have many new theories about things, but I in fact do not have a a good theory about consciousness that I plan to trot out. So </s><s>[INST] you almost don't see it as useful for your current work [/INST] to consciousness. I think it will come I have some thoughts about it, but I don't feel like they're going to move the needle yet on on that. </s><s>[INST] You want to ground it in engineering always. So, [/INST] well, I mean, I don't So so, so so if you if we really tackle consciousness per se in the industry, in terms of the hard problem, I don't I don't that that isn't necessarily going to be ground herbal in engineering. Right? That that aspect of cognition is but actual consciousness per se, you know, for first person perspective, I'm not sure that that's grounded in engineering. And I think specifically what's different about what's different about it is there's there's a couple things. So, let's, you know, here we can also say a couple of things about about consciousness. And 11 thing is that what makes it different is that for every other aspect of science, when we think about having a correct or a good theory of it, we have some idea of what format that theory makes predictions in. So whether those be numbers or whatever, we we have some idea, we may not know the answer. We may not have the theory, but we know that when we get the theory, here's what it's going to output and then we'll know if it's right or wrong for actual consciousness behavior, not neural correlates, but actual first person consciousness. If we had a correct theory of consciousness or even a good one, what the hell would what what format would would it make predictions in? Right. Because because all the things that we know about basically boil down to observable behaviors. So the only thing I can think of when I think about that is what it'll be poetry or it'll it'll be it'll be something to. Um, if I ask you, okay, you've got a great theory of consciousness and here's this, here's this creature. Maybe it's a natural, maybe it's an engineering or whatever. And I want you to tell me what your theory says about this, this this being, um, what it's like to be this being, the only thing I can imagine you giving me is some piece of art a poem or or or something that once I've taken it in, I share I I now have a similar state as whatever that's that's about as good as I can come up with. </s>

<s>[INST] So what are the aspects of the operating systems that lead to Singapore and and to south Korea and all that kind of stuff? So can you speak to different elements that enable the toolkit for entrepreneurs? [/INST] Sure, sure. And maybe here let me just maybe illustrate it with my own story and then I can take you back to </s><s>[INST] tell us your story. [/INST] You know, it's just because it started with me coming here, you shouldn't even robot everything. And now it looks like we need and then you're like tell people and no, no, no. But so this is where this question, even when you asked me, how are some, some countries, how do some countries become prosperous? That question lex I had it when I was seven or so. That's when my family moved me to from Senegal for the first time of my life, I left my country, I left my continent and I was headed to europe to go join my people, my family, my parents who were there as economic migrants, my parents had migrated for a better life as so many people have to, so many people have to coming from poorer places coming for low income countries. </s><s>[INST] You saw the difference between the two places, [/INST] how else would you call it? Here you are in Senegal, minding your own business, causing tons of trouble everywhere, You know, just being a, being a happy free range kid, but I was so </s><s>[INST] you were always a troublemaker, not just [/INST] now, </s><s>[INST] okay, life [/INST] wouldn't be fun without it. </s><s>[INST] And of course I agree. [/INST] So because even you, you know like when you're like all put together like front I know there's a lot of trouble making behind you, </s><s>[INST] desperately trying to keep it together, I know [/INST] you are, but with me I'm going to totally bring it out. So just so </s><s>[INST] you saw the difference, [/INST] right? Different, I'm walking in here back home and I tell people this story because to me it's a defining story back home to take a shower. It's a, it takes time grandma has to, you know, make the short cold catch on a little stove like you use at, you know when you go camping and then she puts a pot of water on it, it boils, she takes it, puts it in a bigger bucket, mixes it with some colder water, then we put a little pot in it and a stronger member of the family has to drag it to the shower and then they're finally, I can proceed to take my shower here. I'm in Germany in the middle of the winter and my mom's like, I got time for your shower. I'm like, I'm not getting naked, where is about? So I just told whoever wins is a bucket of hot water and she's like, oh you silly, come on, just jump in and I jump in the shower and the buttons of water is coming down temperature playing, Are you kidding </s><s>[INST] me? I've [/INST] been cheated out of life my whole life. So that's what happened. And then I then, and then I'm like, oh and all of these roads were paved roads unlike back home, everything is like sandy and you know, my feet are always actually always have to wash off when I, when I go back home and your shoes get ruined most of the time. And it started and I had this question and it was just like, wow, how come they have this and we don't. So I was not being like, oh, you know how come they have all this money? I was not, it was just like how come? And I think what I was alluding to was how come life is so easy here and it's not </s><s>[INST] an easy, not in a negative sense, in a beautiful sense. Sometimes I get uh, you know, just having traveled through the war zone just to come back traveling through europe, back to America. It just, I'll just get emotional, just looking at the efficiency of things like how, how easy it is, how we can um, first of all, in Ukraine currently can't fly right. It's a war zone. Just even the transportation, you said roads. Yeah. The quality of roads in the United States is amazing. Just not, you know, many of the places that drive in Ukraine you're talking about. I mean uh really bad conditions of roads and I'm sure in many parts of Africa in many parts of the world is the world's even worse. [/INST] Right, Right. </s><s>[INST] And outdoor, you know, having a toy, indoor toilet is a Fascinatingly awesome luxury. [/INST] It is, it is. And don't take me wrong lex do we have some great roads now in many parts of Africa? Yes, main arteries, great roads were like, whoa, this is moving. Yes, we do. But definitely more today than in my time growing up. Um do we have, you know, a country like Nigeria that just birthed um six unicorns last year alone. Yes. Do we have the African youth out there being so amazing and you know, living their lives. Yes, we have all of that. But it is still, unfortunately just like we're scratching the surface and those people still are getting all of that accomplished literally swimming through molasses. This is some of the most, most gross immoral, unfair waste of human capital. </s><s>[INST] And so that is the, started with you as a seven year old asking, wait a minute, how do amazing people in europe do this and the amazing people in africa don't [/INST] and that's a cute word amazing because that's when I that's what I realized later because and I was not always like that for me, amazing and amazing, right? I knew instinctively that of course we are amazing too. But so this and so eventually the question became how so I went from how come they have this and we don't to the country as I'm growing up and researching because it stayed with me when I tell you I'm obsessed, I'm haunted, I am haunted. So you can laugh all you want. But it's so the question became the question became, how come some countries like um the United States Singapore are rich and some others like mine and many others in Africa are poor. That became the question. And along the line lacks along the road, I continued on living my life wondering about this question and I've heard all types of reasons as to supposedly why that might be the case. Some people with a very straight face are still peddling the fury according to which come on darling, it's not your fault. You know, your skin color goes with a gene sequence that just doesn't allow you to be as smart as white people are and it's not your fault but just accepted that stuff is still out there. It's very real and I have to hear it and others would say to me it's just because you know you guys don't have adequate level of education and I say you know maybe you gotta go say that to most of the street sellers you go see in Senegal you go up to any of these too many of these street sellers in Senegal they are wading through cars and moving cars under the hot sun fumes thrown at their face trying to sell you anything and any that you think you might be able to use whoever we're talking about an ironing board to an umbrella to q tips to um you know to to fix selling you whatever you need from from your car Visa street sellers and you ask them dear do you do you have any degree? Yeah I have this credit degree in math or in literature or whatever. Some very very educated people yet there right there this is what they're doing. So </s>

<s>[INST] But if I guess, let me rephrase it. Are you against? Mhm. Do you acknowledge the value of like off floating your own effort about a particular thing to somebody else? Absolutely. [/INST] Like an accountant, a lawyer, doctor, Absolutely Chef infinite. </s><s>[INST] Isn't that ultimately what a democracy is broadly defined? Like you're basically electing a bunch of authorities [/INST] using the word you in two senses using the word you meaning me as an individual now. Using you as a mess. </s><s>[INST] Yes, as a mass not using individual. [/INST] So I have, I would absolutely want someone to provide for my security. I would absolutely want someone to negotiate with me for foreign power or something like that. That does not mean it has to be predicated and what lots of other people who I do not know? And if I do know them probably would not respect. Think about it's of no moral relevance to me nor I to them. </s><s>[INST] Do you think this kind of, there could be a bunch of humans that behave kind of like ants in a distributed way. There could be an emergent behavior in them that results in a stable society. Like isn't that the hope with anarchy is like without an overarching uh [/INST] but answer, I mean, answer the worst example here because ants have a very firm authority, the queen and they're all they're all drones, they're all clones of each other. </s><s>[INST] Yeah, But so if you forget the queen that their behavior, they're all well from your perspective, from your human intelligent perspective. But from their perspective, they'd probably see each other as a bunch of individuals [/INST] know they don't, ants are very big on altruism in the sense of self sacrifice. They do not think the individual matters. They routinely kill themselves for the sake of the hive in the community. </s><s>[INST] But they see that's from the outside perspective, from the individual perspective of the individual. They probably they they don't see it as altruism, [/INST] right? But they they they view and they're right because the ants life is very ephemeral and cheap that it's more important to continue this mass population that that one individual ant live like bees are another even better example, the honeybee when they sting, they only sting once and they die and they do it gladly because it's like, okay, this community is much more important than me and they're right. </s><s>[INST] Yeah, So fine, let's [/INST] get pedantic, but it's important. I think just for the sake of being pedantic, </s><s>[INST] but there's something beautiful that I won't argue about because I do, there's an interesting point there about individualism advance. I do think they're more individually. But let's just give your view of ants that they're, it's they're communists. Okay, let's go with the communist view of ants. Uh, but there's still a beautiful emergent thing which is like they can function as a, as a society and without, I would say centralized control. Yeah, that's another argument. So is that the hope for anarchy is like you just throw a bunch of people that voluntarily want to be in the same place under the same set of ideas and they kind of like the doctors emerge, the police officers emerge. The uh, the different necessary structures of a functional society emerge. [/INST] Do you know what the most beautiful example of anarchism is? That is just beyond beautiful when you stop to think about it. And I'm not, I'm not being tongue in cheek language. There's infinite languages. Language. The things that language can be used for our bring tears to people's eyes. Quite literally. It's also used for basic things. No one is forcing us, we speak two languages. Each at least no one is forcing us to use english. No one is forcing us to use this dialect of english. Uh, it's away and despite there being so different languages lingua franca emerge. You know, people, that language that everyone is latin, even in north Korea, they refer to the fish and the different animals by the latin scientific. Uh, no one decided that. Sure. There's an organization that sets the binomial nomenclature but there's no gun to anyone's head referring to see moth as a Pegasus species. And when you think about how amazing languages and in some other context would say like, well you you need to have a world government and they're deciding which is the verbs and you have to have an official definition and an official dictionary. And none of that happened. And I think anyone, even if they don't agree with my politics are my worldview cannot deny that the creation of language is one of humanity's most miraculous beautiful achievements. </s><s>[INST] Absolutely. So there there you go. There's one system where a kind of anarchy can result in in beauty stability, like sufficient stability and yet I know the flexibility to adjust it and so on. And the internet helps it. You get something something like urban dictionary which starts creating absurd both humor and [/INST] which but also language and syntax and jargon. Immediately. You size people up. If you if you say vertebral, I know you're a doctor because that's how they pronounce it. The spinal column. I'm sure in your field there's certain jargon and right away you can know if this person is one of us or not. I mean it's infinite. I mean I don't need to tell us emojis. Yes, there's so much there to study with language. It's fascinating. </s><s>[INST] But do you think this applies to human life the meatspace, the physical space. So these that kind of beauty can emerge without, without writing stuff on paper, that laws you [/INST] could have rules you don't need, you don't have to be laws </s><s>[INST] so enforced by violence. Like that's what's the law. [/INST] A law is something that is unchosen a rule is something if I go to my pool, you know, I I signed up for a member of pool on the wall is certain things, it's like, you know, a certain number of people in the pool, no peeing in here. Good luck enforcing that one. Um, and so on and so forth. Well, that's the </s>

<s>[INST] like they're assaulting a woman meant assaulting the property of somebody else. [/INST] Exactly. And so what I envision is is that we will establish some type of norm at some point but that it might evolve, right? Like if you look at women's rights now, like there are still some countries that don't have and the rest of the world is like why that makes no sense, right? And so I do see a world where we do establish some type of grounding. It might be based on property rights, it might be based on animal rights and if it evolves that way, I think we will have this conversation at that time because that's the way our society traditionally has evolved </s><s>[INST] beautifully. Put just out of curiosity at Anke G bo Mayfield robotics uh with the robot curious sci fi works. We think robotics where all these amazing robotics companies led created by incredible roboticists and they've all went out of business recently. Why do you think they didn't last longer? Why is it so hard to run a robotics company? Especially one like these which are fundamental. H. R. R. H. R. I. Human robot interaction robots. [/INST] Yeah. Each one has a story. Only one of them I don't understand. Um and that was a junkie. That's actually the only one I don't understand. </s><s>[INST] I don't understand it either. It's, you [/INST] know, I mean, I look like from the outside, you know, I've looked at their sheets, I've looked at like the </s><s>[INST] data that's oh you mean like business wise? Yeah, I got [/INST] you. Yeah. Like I look at all, I look at that data and I'm like they seem to have like product market fit like, so that's the only one I don't understand the rest of it was </s><s>[INST] product market fit. What's product market fit? If it just just out of, how do you think about it? [/INST] Yeah. So although we, we think robotics was getting there right? But I think it's just the timing. It just their their clock just timed out. I think if they had been given a couple more years, if they would have been okay. Um, but the other ones were still fairly early by the time they got into the market. And so product market fit is um, I have a product that I want to sell at a certain price. Are there enough people out there? The market that are willing to buy the product at that market price for me to be a functional viable profit bearing company. Right. So product market fit if it costs you $1,000 and everyone wants it and only is willing to pay a dollar. You have no product market fit. Even if you could sell it for, you know, it's enough for </s><s>[INST] a dollar because you can't so hard is it for robots sort of maybe if you look at irobot, the company that makes Roomba vacuum cleaners, can you comment on, did they find the right product market product fit? Like are people willing to pay for robots? Is also another kind of questions. So if you think [/INST] about I robot in their story, right? Like when they first they had enough of a, of a runway, right? When they first started, they weren't doing vacuum cleaners, right? They were a militant. They were contracts, primarily government contracts designing robots. Yeah. I mean that's what they were. That's how they started. </s><s>[INST] Right. And they still do a lot of incredible work there. But yeah, that was the initial thing that gave them a lot enough funding [/INST] to then try to the vacuum cleaner is what I've been told was not like their first rendezvous in terms of designing a product, right? Um, and so they were able to survive until they got to the point that they found a product price market, right? Um, and even with, if you look at the Roomba, the price point now is different than when it was first released, right? It was an early adopter price. But they found enough people who were willing to, to fund it. And I mean, they're, you know, I forgot what their loss profile was for the first couple of years, but they became profitable in sufficient time that they didn't have to close their </s><s>[INST] Doors. So they found the right, there's still, there's still people willing to pay a large amount of money over $1,000 for for a vacuum cleaner. Unfortunately for them now that they've proved everything out and figure it all out. [/INST] Yeah. And so that's, that's the next thing, right? The competition and they have quite a number even internationally, like there's some, some products out there you can go to, you know, europe and like, oh I didn't even know this one existed. So so this is the thing though um like with any market I I would this is not a bad time, although you know, as a roboticist it's kind of depressing but I actually think about things like with the, I would say that all the companies that are now in the top five or six, they weren't the first to the stage right? Like google was not the first surgeons in. Sorry, alta vista right? Um facebook was not the first, sorry my space right? Like think about it. They were not the first players, those first players like They're not in the top 5, 10 of Fortune 500 companies, right? They proved they started to prove out the market, they started to get people interested, they started the buzz, but they didn't make it to that next level. But the second batch, right? The second batch I think might make it to the next level. </s><s>[INST] When do you think the facebook of uh [/INST] facebook of robotics? </s>

<s>[INST] all comes out. And I also remember the arguments and I've, I've been going on um, clubhouse recently into Russian rooms. It's just, well just to practice Russian and uh they is so beautiful to watch. I mean, clubhouse is a very specific collection of Russian people maybe it's a little bit political, but, and they're a little bit older and it's interesting to watch how much they love to argue that they love. And so like it would be literally, um, it's, you can think of it as a nonlinear dynamical system. Okay, from an engineering perspective, it, whenever any positive topic comes up, it's, you could, you could feel the skepticism and then wait a minute. This is not good. And they'll start like uh perturbing it until you're like, uh they'll find some way to say like, come on now. That is the dumbest thing I've ever heard. And then it goes back into argument. It's so fun to watch because in one sense you could see it as negative in another. You could see it as free to express yourself because it feels like you can solve a lot of problems by allowing yourself to just be emotional but both both emotional and say hard truth and all those kinds of things without like um without patting yourself on the back about it. But also it just sort of those Russian rooms make me realize how constrained american speeches, how careful people are in the way they express it even though Michael Mouse is in the world you're you're constantly being like nuanced. Mm hmm. There they just say crazy shit and then they correct themselves and make fun of themselves and they completely shift opinions a minute later and it's it's chaos and it's I mean it's beautiful. So I love that that culture. It's funny given the current regime in Russia like how that's coupled with how people are talking and um yeah, I don't know. And I have those memories of childhood, of, of friends that I had of just having that true freedom of talking and somehow that leads to deep bonds together when when the life when you're poor when life is has a lot of elements that are unfair when the government is corrupt and there's sort of, it's just um especially in the soviet union, there's uncertainty about the future, all of it. You just get closer together like penguins huddling together in the cold. Like that march of the penguins movie that I don't know the friends I've gotten there. Like I get emotional every time I kind of think about those friends because it was so close that friendship was so funny. But I just really [/INST] hate the Russian </s><s>[INST] cynicism. I know you do and I actually disagree with you about it. You see it as cynicism. I see it as um waves on top of the water. Like surface cynicism and the depths as I see the beauty of the Russian soul. So we like yes, that cynicism can negatively affect a lot of people like you, I think you've talked about like as a parent like being cynical about the world and then you have dire negative consequences on your Children. They become cynical. They don't ever take big risks to take on both things. And I have those arguments because the cynicism is exhausting. It's destructive and anti creative. But so in in their perspective is this is what the Russian folks would say. Well yes, that's our role like being cynical is being reasonable about the world, but it's not it's completely unreasonable. It's a complete lie. I know. I know but their argument is yes, but we're giving you this force and it's your job to resist against it. So it's a [/INST] test. I love the idea that if you're going to be creative and innovative, you don't have enough up against, you know, I don't I don't it's not hard enough already that I want to be an author, and now you've got to be like, well, let me just put some fire ants on top of it. </s><s>[INST] So, I I just want to separate. I agree with you that the cynicism is bad and destructive, but the idea that life is suffering and thinking from that as the first principle, I think there's a lot of beauty to be discovered through that. So there's a cynicism and then there's [/INST] horrible message </s><s>[INST] uh [/INST] life is suffering. </s><s>[INST] No, not well, yeah, I mean, camus [/INST] um </s><s>[INST] common doesn't think that now we're going into definitions of suffering then because absurd what you see life [/INST] is absurd and life is suffering or not even close to the same concept, </s><s>[INST] but then you're just defining the terms differently [/INST] because they're different terms. </s><s>[INST] So, always love and beauty, but you're [/INST] selling if your babies in the crib like with a fever and you're like, oh, that's absurd. No, it's the kids suffering, it's not the same. </s><s>[INST] So, yes, starvation. So you've been for the white pill researching a lot of actual specifically defined suffering. [/INST] Sure, But also a lot of wonderful things, </s><s>[INST] right? Yeah, yeah. But the words suffering can encompass more than just specifically starving and it could it can encompass, like, a lot of the philosophers talk about it encompassed, like philosophical suffering. The fact that there is if if you're not careful, life can appear meaningless, you can fall into a nihilistic view, like it's it's it's difficult to have the responsibility of freedom to act in this world because you can funk up in so many different ways and then life is seemingly unfair in this in the sense that good things happen for no apparent reason and terrible things have happened for No, like, you know, it's the old religious question of what is evil happen in the world, Why do terrible things happen in the world? There's this [/INST] Book called six word memoirs, right? Where all these different personalities were you in it? I'm in it with So you have to basically write your autobiography in six words and mine was good things happen to bad people. </s>

<s>[INST] But it's interesting if the direction in which that progress is happening has some revolutionary value or if it's merely a drift that can go into any direction, [/INST] I'm not sure it's any direction and I'm not sure it's evolutionarily valuable. What it is is um progressive in the sense that each step is a step in the same direction as the previous step. So it becomes more gentle, more decent as by modern standards, more liberal, um less violent. </s><s>[INST] You put more decent. I think you're using terms in interpreting everything in the context of the 21st century, because Genghis Khan would probably say that this is not more decent because we're now, you know, there's a lot of weak members of society, they were not [/INST] murdered. Yes, I was careful to say bye bye. The standard, the 21st century by our standards. If we with hindsight look back at history, what we see is a trend in the direction towards us, towards our present, our present value for </s><s>[INST] us. We see progress. But it's an open question whether that won't, you know, I don't see necessarily why we can never return to genghis contacts. [/INST] We could, I suspect we won't. But it, but if you look at the history of moral values over the centuries, it isn't a progressive. I use the word progressive, not in a value judgment sense in the sense of a transitive sense. Each step is the same in the same direction as the previous step. So things like we don't um derive entertainment from torturing cats. Um, we don't derive entertainment from, from like the romans did in the coliseum from from </s><s>[INST] or rather or rather we suppress uh, the desire to get, I mean to have play, it's probably in us somewhere. So there's a bunch of parts of our brain, one that probably, you know, olympic system that wants certain pleasures and that's uh, [/INST] I mean, I wouldn't have said that, but you're at liberty to think that like, </s><s>[INST] well there's a, there's a dan Carlin of hardcore history. That's a really nice explanation of how we've enjoyed watching the torture of people, the fighting of people just to torture the suffering of people throughout history as entertainment until quite recently. And now everything we do with sports or kind of channeling that feeling into something else. So I mean there is some dark aspects of human nature, There are underneath everything and I do hope this like higher level software we've built will keep us at bay. [/INST] I'm also </s><s>[INST] jewish and have history with uh the soviet union and the holocaust. And I clearly remember that some of the darker as opposed to human nature creeped up [/INST] there. They do. There have been, there have been steps backwards admittedly and the holocaust is obvious one. But if you take a broad view of history, it's, it's the same direction. </s><s>[INST] So Pamela McCord IQ and machines who think has written that a I began with the ancient wish to forge the gods. Do you see it's, it's a poetic description I suppose. But do you see a connection between our civilizations, historic desire to create gods to create religions and our modern desire to create technology and intelligent technology? [/INST] I suppose there's a link between an ancient disaster explain away mystery and, and science, but um, intelligence, artificial intelligence creating gods creating new gods. Um, I mean I forget what I read somewhere somewhat facetious um, paper which said that we have a new god is called google. And, and, and we, we pray to it and we worship it and we and we ask its advice like an oracle and so on. Um, that's fun and </s><s>[INST] you don't see that you see that as a fun statement of facetious statement. You don't see that as a kind of truth of us creating things that are more powerful than ourselves and natural, [/INST] it has a kind of poetic resonance to it, which I get, but I wouldn't I wouldn't have bothered to make the point myself that way. All right, </s><s>[INST] so you don't think ai will become our new a new religion and new gods like google? [/INST] Well, yes, I mean I I can see that the future of intelligent machines or indeed intelligent aliens from outer space might yield beings that we would regard as gods in the sense that they are so superior to us that we might as well worship them. That's highly plausible I think. But I see a very fundamental distinction between a god who is simply defined as something very, very powerful and intelligent on the one hand and a god who doesn't need explaining by a progressive step by step process like evolution or like or like engineering design. So, um the difference, so suppose we did meet an alien from outer space who was marvelously magnificently more intelligent than us and we would sort of worship it and for that reason nevertheless, it would not be a god in the very important sense that it did not just happen by to be there like God is supposed to, it must have come about by a gradual step by step, incremental progressive process presumably like Darwinian evolution is that there's all the difference in the world Between those two intelligence design comes into the universe late as a product of a progressive evolutionary process or progressive engineering design </s><s>[INST] process. So most of the work is done through this slow moving [/INST] exactly progress. Exactly </s><s>[INST] yeah. Uh huh uh yeah it's but there's still this desire to get answers to the wide question that if if we're if the world is a simulation, if we're living in a simulation that there's a programmer like creature that we can ask questions of this, Well [/INST] let's put let's pursue the idea that we're living in a simulation, which is not not totally ridiculous by the way. Um here we go. Um then you still need to explain. The programmer, The programmer had to come into existence by some, even if we're in a in a simulation, the programmer must have evolved or if he's in a sort of she or she she's she's in a meta simulation, then the meta meta program I must have evolved by gradual process. You can't escape that fundamentally. You've got to come back to a gradual incremental process of explanation to start with, </s>

<s>[INST] is there a primal fear though? Like a primal fear of getting hurt, the running away and not facing the threat long term is the bigger pain than any pain you can experience in the fight that's pretty powerful. But what about the violence of, I mean, you don't have that on your face, but like, I don't know if you've also seen Tyson talk about, he was on Rogan recently, he was talking about, he was trying to psychoanalyze himself about why he enjoys violence so much? I mean, he called it orgasmic. I don't know, Have you seen that [/INST] clip? </s><s>[INST] Okay, we're playing, we're playing it because I can, I need to because trump also retweeted it, which is hilarious. I don't know how to contextualize that our president retweeted the clip of uh [/INST] let's say of Tyson saying that maybe he's just doing it like they're not gonna like, I'm gonna throw him a curve ball and I was gonna have any idea what that. </s><s>[INST] But yeah, he did no explanation. Just here you go. There you go. [/INST] Well, I think that's kind of like what you're describing, it's like if I give you an answer, it has to be a good one. Better to just let your imagination run. Exactly. </s><s>[INST] Yeah, he's yeah, he's like the kubrick of our time now. What's really interesting that sometimes um period it's not real, but sometimes I struggle with the fact of why the possibility I can really hurt somebody, like you don't want to hurt them? What do you mean when you struggle struggle with the possibility that you could hurt them? That is sometimes it's orgasmic sometimes. Yeah, like some fights like particular Tyrell Biggs or someone that you had problems with someone that you had animosity towards. So when you finally get your hands on them, hey, um what does it mean? Um when fighting, Get you, get you erect, what does that mean? It's a good question means you're getting excited. Yeah. So that that's going through your mind right now. Well, that's how I get when I was a kid and I, you know, sometimes I get the twinkle twinkle. Yeah, well, that's what I'm saying is like you reached a state as a human being, as a champion, as a ferocious fighter. You reached a state of, of ability and of accomplishment that very few humans will ever ever touch and feel. That's why I'm asking you when you're running, when you're hitting the bag, when that heart's beating again and you know who you are, Your mic, motherfucking Tyson. So when you're doing all this, sh it again, you're still mike Tyson. Those thoughts have got to be burning inside of you again. It's gotta be pretty wild. I don't know, it's um it's wild, but I believe is um is rightfully so to be that way. And I just know how to um I don't think I mastered, but I just know how to deal with it. I don't let it overwhelm me. I mean, he goes on to try to they don't ever like, joe doesn't bite. Well, the interesting thing about that conversation is, mike was trying to figure himself out. Like he's trying on the spot. Like, why do I feel this way? Uh To me, it was like, to me is so real and honest to uh to feel like pleasure from hurting somebody like that. You rarely hear that in this society. It's like you rarely, like, talk about, like, you feel pleasure from winning. You feel pleasure from like the relief of overcoming like all the stress you have to go through pleasure from just like the specifics of the fight, the techniques he used, uh, maybe overcoming being down a couple of rounds. But like how often do you hear somebody say? I just enjoyed, he's not even saying because I hate the opponent. He's saying like I enjoyed purely the violence of it. That's crazy. I mean, I don't know, it's honest. It made me ask like, I wonder how many of us are cognizant of that. [/INST] That's a mic is uncommonly seemingly honest. I think athletes make a full time job out of lying. You know, I think people make fools of themselves. And that's fair. I mean, in some you tell yourself or you tell others what you feel you need to or maybe whether you wouldn't even know what you feel you need to, but why should he not? I mean, again, did he, did he run up and just hit somebody that didn't sign up for this? No, they find it to be there. </s><s>[INST] Well, that's the interesting thing about Dyson is there's that weird, uh, like non standard behavior. I mean, like your fighting style is non standard. He's nonstandard to another degree of like, who else has that? Individuals who are polaris, uh, has this kind of weirdness. Like what's what's in there. Like there's a fear that I think uh, most opponents would have because it's like it's no longer about like it takes you out of the realm of its game. It takes us back to the thing we're talking about before is it strips away that like several layers of Ryan hall, the podcast guest Ryan hall digits instructor Ryan hall just a competitor. It keeps going down to a point where like Ryan Hall the murderer of all things that get in his way that lies underneath all of it seemingly like if we're like in this society we put all that aside. But it makes you wonder like now society is being tested in many ways. It makes you wonder like what's underneath there? [/INST] Well do we want do we want the answer to that? Because I guess it's what is it? Uh you seen paul fiction, you know the best character in the movie and in the best seen in the movies, I give my questions here. If you are what you call it, My answers scare, you should cease asking scary questions, you know? And I guess uh you wonder, I mean all of us, that's something that I think it's funny we call, that's not okay. I mean versus may be appropriate For situation X, Y or Z. But uh what should make any of us think, I mean humanity is a different place now. And I mean I don't see anything crazy out there, but he managed a different place now than we were 5000 years ago, where all of us are descended from people who have killed things with their teeth and fingernails in order to be where we are and whether it was in, whether it's an animal or it was in conflict with another person. I mean, think about the chances of dying by violence now or so, so slim, at least in most countries, in most places, like shockingly small, thankfully. But there was a period of time, like the most period of time were dying by violence was mostly how it went down. And I guess what would be facilitated, what would allow you to win back to Ender's game? You know what allows you, if you can't do that, you are all, you are forever subject to people who can and that's that's a real thing. And you know, we're fortunate to find ourselves in a situation where we don't where other things matter. But that is a funny thing periodically where people, you'll see people like kind of jawing at each other like in videos are out in the world that clearly neither of them expect this to get serious. Like I'm just gonna yell at you, you're gonna yell at me and it's like this weird lar ping thing, we're both gonna go on our own separate way. All it takes is one person to like what I wasn't kidding. Yeah. And it's like, oh, you'll go to jail and I know you're gonna go to the morgue and it's that, that can happen like that. Like society. I mean, obviously any way you could jump across the table stabbed me in the eye. I mean, I appreciate, I hope if you don't and there will be consequences if you do, but not from, not from me from, from the rest of society will potentially get you at a certain point, but you can decide to not play by the rules anytime you want </s>

<s>[INST] And... [/INST] Exactly, that's a much, much better word. Yeah, I think the other thing is that this culture of reducing people down to a label, right? Whether it's racism or whether you're calling them a scammer or any number of terms, you're discounting their sovereignty to zero, right? You're taking a super complex human that is vast, contains multitudes, is changing over time, and you're trying to put them in a bucket of a word. And that is just, I think, a cognitive fallacy. Like, it's not only gonna hurt the person that you're winnowing down to a word, but it's also gonna hurt you. And it's gonna, in your attempt to de-complexify reality by assigning this person to a term, you're actually gonna create bad outcomes for yourself, </s><s>[INST] because you're not gonna understand that person. I do also think there's a failure of our social media technology that incentivizes that kind of reduction to a label. It's just the viral nature of that reduction. So it's not only do we humans naturally do that, our social media platforms make that easier, more fun, more effective to do that at scale, the mass hysteria. So I think there's actually technological ways [/INST] of adding friction to that. Yeah, I wonder, I mean, I agree with you that social media is an amplifier to our natural, this natural way of dealing with one another. But I wonder, and my thinking has evolved a lot on this, that there's something below the way we're treating each other too, right? We could say civilization sort of advances in the tools we make and the way we treat each other. We tend to have better tools, better quality of life, and better morality, better quality of living and ways of dealing with one another. And I think that when you corrupt the money, that it really does push us the negative direction, pushes us away from, again, encouraging or amplifying scarcity artificially causes us to be more divisive. When things are more divisive, we tend to be less civilized, less nuanced, more black or white, or this or that, or your label A or label B. So I really think, and this is a harder one to unravel, but I think if we can fix the money, right, which again is the base layer operating system for human moral action in the world, that it has downstream effects. So we'd actually maybe start to treat each other a little better on social media, </s><s>[INST] despite the fact that it enables this faster communication. That's interesting. So perhaps fixing social media, as I've been thinking about, [/INST] is treating the symptom, not the cause. Yeah, that is the Bitcoin rabbit hole in a nutshell, is that they say fix the money, fix the world. You keep tracing these different social malaises or technological difficulties, lack of innovation. Weinstein's entire portal podcast, something went wrong in the early 70s. We went off the gold standard in 1971, and there's a great website, wtfhappen1971.com, goes through this whole gamut of socioeconomic data that's completely gone askew since the early 70s. </s><s>[INST] Yeah, you had this whole video, what do you think about Eric Weinstein and Bitcoin and the gold standard? Does he, I actually haven't heard him talk about his thesis about the 70s in connection to the going off of the gold standard. Yeah, what are your thoughts there? What are your thoughts about his general relationship [/INST] with the Bitcoin idea and the community? Yeah, the first exposure I had to Eric was his, I think it was his first episode with Peter Thiel. And they're going through that thesis that there's been this general institutional rot and suppression of innovation since the early 70s. And he's trying to identify what it is. I don't think they ever pended on the money on going off the gold standard. But in recent interactions with Eric, I've interacted with him on Clubhouse. We recently released an episode of the show I did with Chris Espley and it was titled Dear Eric Weinstein. So we're going through his worldview that he's expressed in the portal and tying it back to the money in different ways. And he's been, he's engaged. Eric retweeted the show. We exchanged some messages. He's been very open-minded. He's asked some really good questions. So I get the sense that he's approaching this very wholeheartedly. He does bring with him his existing worldview and his existing theory. The one that really blew up was Gage Theory. They got really popular. I don't know a lot about Gage Theory. I actually messaged Eric and said, I want to learn more genuinely because he seems to be serious that that needs to be considered in the sphere of money. And so I want to learn more about it. But I think overall, it's great. It's great to see an intellectual heavyweight of his caliber gravitating towards Bitcoin. </s>

<s>[INST] So, you see consciousness as giving a felt experience to our uniqueness as opposed to the uniqueness giving birth to God. [/INST] Yes, and that potentially there is felt experience, even though it sounds crazy even to me that there is a felt experience in all matter. And at this point in my thinking and after a few conversations with some physicists, I think if consciousness is fundamental, the only thing that actually makes sense is that it is part of the most fundamental um that space time and everything else emerges out of </s><s>[INST] consciousness [/INST] felt. Experience is just part of the fabric of reality. </s><s>[INST] So, is it possible to intuit this? Can we start by thinking about dogs and cats, go to the plants and going all the way to matter? Or is this going to be like modern physics, where it's just going to be impossible to even through our reason alone, we're gonna have to have tools of some kind. [/INST] I think it'll be a little bit of both. I mean, I think the science has a very long way to go. And the truth is, I don't even think we can get to the science yet, because we have to do this work and this is why I'm so passionate about this work. Um, and it's really it's really taking hold. I mean, there are scientists, neuroscientists and physicists interested in consciousness and kind of having gotten over the initial obstacle of wrestling with these intuitions so that it's now being talked about in a serious way, which was the first huge hurdle. But I think a lot more of that has to happen. A lot more of the intuition breaking from the science we already have. I mean, I think we almost need to catch our intuitions up to what we we already know. Um, and then continue to break through these intuitions systematically so that we can really think more clearly about consciousness. Um, There are a couple of um scientists now working on theories of consciousness which do go they don't quite go to the fundamental level but they go extremely deep. Um so that something like an electron might be conscious under their theory. This is um integrated information theory I I. T. With Christof Koch and Giulio Danone. Um I've spoken to both of them I spoke to um christoph cock uh once or twice for for this project I'm working on now. Um What they're working on is incredibly interesting to me and I think very important work. Um However I think they are also really led by some false intuitions about self and free will. And I think that will be a limit to their work so we can get into that. But um </s><s>[INST] we [/INST] will. </s><s>[INST] Which [/INST] is that what they're working on I think is the most important next step forward. Which is just even being open to the fact that consciousness goes as deep as particles. </s><s>[INST] But [/INST] even their theory isn't going as deep as I think we need to go. Um And it's hard to say how we could actually study this scientifically. But that's part of the reason why I'm such a supporter of I I. T. And why I'm so interested in what they're doing, even though I think they're wrong um is because they're they're opening this path. And I think they're getting more people interested. And I think um yeah it'll be it'll be it's hard for me to imagine what the science will actually look like. But </s><s>[INST] okay, so your intuition or at least the direction which you're pushing is that consciousness is the only fundamental thing in the universe that everything else like time, all those kinds of things emerged from that. [/INST] I will say that </s><s>[INST] what [/INST] I </s><s>[INST] believe at [/INST] This point, I've been saying 50, 50 for a long time, I would say now it's like 51, Um in terms of consciousness being emergent versus fundamental. </s><s>[INST] So I [/INST] am not convinced </s><s>[INST] of this, [/INST] that I'm not convinced that consciousness is fundamental. What I think is there are very good reasons to think it could be. And </s><s>[INST] essentially [/INST] all of science up to this point has </s><s>[INST] been [/INST] led by the other assumption by the first assumption that consciousness arises at some point, namely in brains and that's where all the science has gone. And I think that's wonderful and I think it should keep on going. And I actually think that was a more important place to start. But I think there's a possibility that the correct assumption is that it's fundamental. And so that's the science I support. That's the thing I spend a lot of my time thinking about and talking to scientists and philosophers about. And so I I shouldn't give the idea that I actually have crossed over into believing this is the case. But it is, it's the assumption I follow in my work at this point, </s><s>[INST] it's a possibility and understudied possibility, so deserve serious, rigorous attention [/INST] and there are good reasons to start with that assumption versus the other that I think we're just now starting to realize. </s><s>[INST] So just to clarify when we're talking about consciousness, we're talking about the hard problem of consciousness that it feels like something to. You know, there's a subjective experience. Do we? You know, if consciousness permeates all matter is fundamental. Is that going to be somehow, is our current intuition about consciousness? Like very tiny subset of what cautiousness actually is? So, like we have our intuitions about personal experiences, like what it feels like what it takes to eat a cookie or something like that. Um, but that seems like a very specific implementation of consciousness in an organism. So how can we even reason about something that's if consciousness is fundamental, how can we reason about that? I'm [/INST] not sure I'm understanding the connection between those two things. But </s>

<s>[INST] kinda, it's in some way similar to what uh, like at the, at the highest level chess players do. I mean you're, I mean they, they, they recap the games, but the, the richness of the representation that they use in remembering like how the game's evolved. It's not like, it's much richer than the actual moves. It's like these, a bunch of patterns that are hard to put in towards like, like all the richness of thinking they have about the way to get evolved. It's more like instinctual from years and years of experience. So they try to put it into words, but they really can't. It's [/INST] just not, I understand that. It's because for us, if we don't come back with anything, then there's no learning to be had because the whole thing is the debrief when we get back and we talked about that's really where they're learning is and it's the same thing if you want to go back to chest, you know, when you start off, you try and learn because you're remembering what you're doing. If you play against someone, I'm always a big place, play with someone better than you. That's how you learn. If you're constantly beating people, you're not learning anything, you're just learning that they're not good and you're better when you, when you challenge yourself against someone that is going to is better than you you learned. So I learned how to fight an airplane with uh he's actually one of my best friends. We'll call him Tom won't give us a call sign because I don't know he was so tom took me out and taught me how to fight because Tom had just left Top Gun. He was the training officer at Top Gun, which so that's the guy, the training officer is the main guy at Top Gun. So Tom was the training officer Tacos. So tom when I learned because I had come out of a six and we really don't fight because it was a bomber. So I get in F eighteens and I want to learn how to fight because it's a whole other side of the mission. It's the F and F. Fighter attack. The F A 18 is fighter attack. So I had to learn how to fight. So now I got one of the best fighter pilots in the world, he's gonna teach me how to do it and he did and I would do something. Then he would go I get to a situation where I had never been and then I would go, well I'm gonna do this and then he would destroy me and he would come back and go, here's why you don't do that and then I would take that knowledge and I would put it in my little basket of tricks and over time because you know, no one walks out into that world. I don't care how gifted of an aviator and go, I am the man or the woman, I am it. Yeah, no, it's a learning process </s><s>[INST] and so are all those years you've gotten good. So I mean, so what are the chances that your eyes betrayed you when you saw the tic tac [/INST] zero? </s><s>[INST] Well, I mean I'm not [/INST] Okay 90 I am 99.9%. So .1%. My eyes deceive me. But remember if it deceived me, it had to deceive the other four people to the percentage is even lower. </s><s>[INST] Well, I, I don't find that particular debunking case that used to, but I'm glad you put it, you, you said those words out loud. So for me from my perspective, uh, coming into this world and looking at it, I am a little bit more skeptical. Uh, so your eye account I think is the most fascinating story and that I think uh, that's inspiring to me and should be inspiring to a lot of scientists out there. Uh, on so many levels, just like we said, an engineering level that maybe there's propulsion systems we can actually build, it can do some crazy, amazing stuff. So it's at the very least intriguing and at the best inspiring. I just want to say that. But on the video side, it's like, it's uh, the videos for the flare video that go fast and the gimbal video. [/INST] They </s><s>[INST] are only interesting to me, to me in the context of your story. Like without that, they're kind of low resolution. It's like, it, it's easier to build a debunking story to be skeptical. So it's just where I'm coming from. Maybe you can convince me otherwise. But so to bring up my quest one more time, he looks at the flare video and he says that one of the most amazing video parts of the flare video where people haven't seen it is at the end of it, the, the tick tock flies or appears to fly very quickly to the left [/INST] off the screen. </s><s>[INST] And what Mapquest says is, uh, that, you know, midwest, probably others that the way to explain that is the tracking system. Like we said, this vision based tracking simply loses the, like the object. The tracking loses it. And so it simply allows the object to float off screen because it's no longer tracking it. So I find that at least a plausible explanation of that video looking at your face. [/INST] You do </s><s>[INST] not. So, can you maybe comment to that to that debunking uh, aspect? [/INST] So it's funny how people can extrapolate stuff who have never operated this system for sure. And that's like me going because I'm a big Formula One fan, you know, that's like me going, oh my God, louis, what were you doing? You could have done this with the car and you have won the race, you know, and louis Hampton right now is you know, defending world champion two time when he is four times four or five time world champion. But um, that would be pretty stupid of me to try and tell Lewis Hamilton's how to drive a car. Um, Or a matter of fact anyone driving a Formula one car. So I can't tell you how many times I've watched. You remember when we looked at this thing when, when, when Chad came back with the video, we sat there and watched it. I mean, I can't tell you how many times I watched it off the original tapes going all right, all right, all right. Let's look at this. Um, you know, because you can look and see where the, you can see where the airplane's going. You can see if it's looking left or right. And if you actually watch all that stuff, it doesn't do that. Actually when the vehicle starts to move the bars, the tracking gates starts to open up and the people at Raytheon could probably add to this because they built the pod, The tracking gate will start to open up and, and but the thing, when it leaves so fast off the screen, that pod can't move fast enough. It has gimbal rates on how fast that thing can move around because there's another theory that, uh, the pods looking forward when the pod passes underneath the airplane. So if I'm looking at you and you pass underneath me, is that does this, the ball will actually flip around to kind of finish off and it'll, it swaps ends because it has, you know, it's a gimbal, it can't just, it's not free floating. Um, but there's a theory on one of them, oh, it's here and it flipped over. It doesn't do that when it's looking out in front, it stays like this so that yet another, another debunker who doesn't know this. So, you know, and Mick has had several theories on other of some of the other videos, like one of them, the go fast as a bird. And jeremy Korbel actually did a nice job of saying, no, it's not because he's on, he's on Blackhat. So the white object is actually colder than the ocean. Um that's flying, well, birds aren't colder than the ocean, they'd be dead. </s>

<s>[INST] You said there's very few of us. Let's have the goat discussion. You're not gonna pick anybody. But who are the greats of comedy? Who's who's the who's the who's the greatest comic of all time? [/INST] Well, I don't think there is a greatest comic of all time. </s><s>[INST] Is it North Mcdonald [/INST] norm. Macdonald was one of the greats for sure. But </s><s>[INST] by the way, actually on that topic, what do you think about is I think as a person who was fascinated by the fear of death and death, I think it was a truly genius thing to release a special After you're dead. [/INST] I don't know how that works. I haven't seen the special view. </s><s>[INST] It's not yeah, it's it's um it's called, I think nothing special which [/INST] sounds like something normal </s><s>[INST] and it's basically him in front of I mean I imagine he wouldn't would have wanted it edited that way because it's made to look nicer than I think he probably would have preferred it. But it's him in front of [/INST] the screen </s><s>[INST] like on a zoom call doing jokes without cold and somehow given his [/INST] like </s><s>[INST] dry dark humor, it works because it's almost making fun of itself, almost making fun of that hole that we were stuck, stuck alone inside and because he's still acting as if he's in front of the audience and it's almost making fun of the fact that this is what we're forced to do. I mean, it's quite genius. It's really well and the jokes are really good, but it also makes you realize how important laughter is from the audience, the energy from the audience because but there's also an intimacy because it's just you and him because you're listening to it. You know, there's no audience. So that's, I don't know, I think it's quite genius and he is of course there's there's certain comics that are like, not only are they funny, but they're truly unique and like they're they're they're not in terms of friendship and all that kind of stuff, but in terms of comedy, they're an island. It's like they, you know, mitch Hedberg probably is that of course, a lot of people didn't start to imitate them and so on, [/INST] but </s><s>[INST] steven wright. I mean, there's like people who are like, you know, Dave chappelle who's like probably one of the greats, but he's just like raw funny. I don't know if he's an island, he's just raw. [/INST] Yeah, I know what you're saying an outlier unique individual. Yeah, he's just great um norm was definitely unique in his greatness, Like, like there's only one norm, you know, who's got a very specific style. </s><s>[INST] Is there a reason you guys weren't, it doesn't seem like he was, you guys were close. [/INST] I mean, I loved him. It was great. I always enjoyed talking to him. Um, we just didn't work together that often. We were wearing around each other that often. That's all it was. But it wasn't like it was, I loved him though. He was a great guy. I had a funny story about it, norm. Uh, twice just randomly. I was on airplanes next to him, seated right next to him, just totally random. And one time we're on this airplane and we're having this talk and I was like, yeah, I quit smoking. I was smoking a lot and I just terrible, terrible smoking is terrible for you and we have this great conversation, we get off the plane and he sprints towards a store and buy cigarettes like in the airport and is lighting it on the way out the door and I go, I thought you quit smoking those. Yeah, I did. But all that talking about smoking maybe wanted to smoke again. So before he's getting through the door of the airport, he's lighting it up. I can't wait. He can't wait to get that cigarette in him. It was, he was just so crazy and impulsive and loved to gamble, loved gambling and </s><s>[INST] in that way he embodied the joke like you can't even tell that certain people just like live in a non sequitur, ridiculous, absurd funny way. [/INST] Yeah, that was him. I mean </s><s>[INST] nonstop, it's just, [/INST] there's nothing artificial about norm, you know, that, that was who he was. His brilliance was his essence, that was who he was, </s><s>[INST] you know, but [/INST] it's in terms of like the greats, the godfather of it all is Lenny Bruce. I mean, I have a bunch of Lenny Bruce concert posters at my house and photos that I have framed. And Whitney cummings actually gave me this brilliant photo of him when he got arrested for one of the times when he got arrested for saying obscene jokes, he was the most important figure in the early days of comedy because he essentially gave birth to the modern art form of stand up comedy. Before that it was a bunch of guys that were like hosting shows and they would tell jokes, they were just like, you know, you know, two guys walk into a bar that kind of stuff and he would talk about social issues, you know, he would talk about life, he would talk about language, he would talk about laws and it was just, he was the very first guy who did modern stand up. And what's fascinating is if you go and you try to watch it, if you try to watch lenny Bruce today, it doesn't work because society has evolved like in many ways, art is a window, especially like pop culture, art or modern, uh, you know, at the time, culture, art, Art that discusses culture is a window into that time period. It's a little bit of a time machine. So you get to like you have to pull yourself like what was it like to be in 1963? Like what was he saying in 1963? What was this like to hear him say this and the The civilization that existed in 1963, although it looked pretty similar. They're all driving cars and they're all wearing suits and they're all the teams normal. That's a it's a different world. And the things that he was saying that are so taboo are so normal today that they're not shocking and it's not not that good. It's not that funny. </s>

<s>[INST] in the sense that he follows other people's values, not his own. Can we actually just backtrack and can we define some of these ideas that Ayn Rand is known for of selfishness? Selfishness, egoism, egotism, greed, I mean, basically all of those words are seen as negative in society, and Ayn Rand has been reclaiming in her work those words. So do you speak to what they mean? [/INST] Do you speak to what they mean? I think she's trying to... You're on my disagree. I think she's trying to be needlessly provocative, and it's off-putting. On one hand, maybe you want to be a provocateur because that gives you people like, what does this woman mean? On the other hand, many people are going to be viscerally put off. When Ayn Rand was on Donohue in 1979, he asked her explicitly, define to me the virtue of selfishness, which is the title of her collection of essays as well. And she, this is Rand, immediately says, use a different word, self-esteem. And it's like, yeah, it's like, why are you championing this word which has extremely negative connotations? Whereas if you just say, and this is thanks to her and her work, my life matters, my values matter, I'm not going to apologize for that, that is a lot less off-putting than this caricature of Rand, which is, when people hear I'm for selfishness, they hear, oh, someone's bleeding out in the corner, but I want to get a coke, that's nice. She condemned that. She says, I'm against this kind of sociopathy, that's absolutely crazy. </s><s>[INST] But that word selfishness... But that word selfishness... She's because a mistake to be provocative in this one dimension, to go and to stick with it. I mean, she's stuck with this idea of selfishness and so on. [/INST] This term. And I often use terms for provocative effect. Yes, this is true. </s><s>[INST] You're a master, you're a scholar of the trolling arts. [/INST] Thank you, sir. Thank you, sir. But I think this is one example where the costs outweigh the benefits. And go ahead, your honor. Yes, I'm open to that idea, but I don't think that's right. When you actually dig deeper into what people object to, they're not objecting to the word, they're objecting to the ideas. And she addresses this explicitly in the virtue of selfishness, in I think, the introduction. Wait, hold on, wait, hold on. I got to ask her for clarification, you're saying they're objecting to the ideas, but when they talk about her, they're not talking about her actual ideas, they're talking about the caricature. Well, sure, but the caricature is the defense mechanism not to have to deal with the ideas. Sure. They create the caricature in order to ignore the ideas in order... and some of them do it consciously. Like when people like Krugman and others do this, they know exactly what they're doing. Krugman is Ellsworth Tewey. Yes, he's the perfect Ellsworth Tewey. And he knows Ayn Rand, he's read Ayn Rand. And he knows she's the enemy in some sense. </s><s>[INST] He knows Ellsworth Tewey knows. Check out our episode with Krugman, I think it's number 90, it was a great conversation. [/INST] Didn't get as many views as me, but what are you going to do? Well, you got a Nobel Prize, so what you got? I've got a ticket to heaven. Sorry, Paul. </s><s>[INST] Yes, Alfred Hazard has Nobel Prize. [/INST] And Hitler was Times Man of the Year for a few times? But that really bothers me when people ring that up. It's called a joke, Michael. It's called a joke, Michael. Is it? Man of the Year is not representative good. </s><s>[INST] It represents the most influential person of that year, and Hitler was. [/INST] Absolutely. Absolutely. When people are like, well, look at Time Magazine, they're called Hitler, Man of the Year. you're on set. They weren't saying, this guy's awesome. They said, this is the guy who moved down the world. The world of us. It's not like he was stalling. I don't go out there. Now that's who they like. Hitler's terrible. The Stalin guy. Hitler's terrible. The Stalin guy. The Stalin guy. Oh, no, no. I'm not even joking. See, the attitude between the attitude of people between Nazism and or fascism and communism is stunning. In my upcoming book, I have all the receipts, how the things that they were saying about Stalin at the time are, if you look back, it's unconscionable. And these people have had no accountability in their way. It's not even at the time. And we need to get back to the selfishness stuff, but it's not even at the time. I think I've told this story. I was in the green room going on John Stossel's show and saw a bunch of libertarians in the green room, all hanging out. And this guy walks in, this young guy he walks in, and somebody says to me, he's a communist. I said, what do you mean? They said, no, no, he's a card carrying real member of the communist party. He's a communist. And I said, and that's okay with you guys? And they go, yeah, yeah. It's a nice guy. And I'm like, no, this is not acceptable. You guys. Hold on. Let me quote Rand. Rand said she would rather talk to a philosophical artist, right? Did she not say this? Yeah, but this is not a, this is a communist in the context of 21st century, right? So I said- But not 20th. Well, in a sense that we know exactly what- Sure, sure. We know exactly. So I'm like, this guy has the blood of a hundred million people on his hands. I'm not letting him off the hook. So I get, I engage with this guy and literally we get into this, I'm telling him what I think of his ideas and therefore what I think of him. Then the people from the wardrobe department come out and their chairs are put aside and this little gladiator ring. It's like the libertarians are like sitting there amused. Because to them, it's just, and I don't, I'm not going to name names, but to them it's just like, yeah, he's a communist. And I said at some point to them, I won't name names because I said at some point to them, if somebody walks into a room and says, I'm a Nazi, and I said at some point, I won't name names, just treat him as okay. Let's go hang out and get some drinks. I do. Because I wrote a book about this, then you write and I did talk to Nazis and I went to North Korea- Yeah, because you were writing a book. Yeah, we were writing a book. Yeah. Right. But you're not gonna hang out with a Nazi or communist, just like a regular person. Right? To me, a Nazi and a communist are the same. Please explain this. Because I first of all, anytime you have equivocation, I hate that, that because I don't, I don't like equality. I think it's a bad concept. We're all sitting here as Jewish people, right? We're from the, we're from the Soviet Union. To say these two things are basically the same. It's a matter of life and death for all of us. We'd be dead under Hitler. We're not doing so hot under Stalin, but we're still alive. We're from the, so there's, there's some very big, one more thing. There's also one very big difference in that one has a lot worse of a brand name and the other does not, even though the other should, it's a pretty sure. So there's some, there's some very big difference. Add just one more thing to that. Yeah, yeah. So I agree. So there's a context in which I would fear Stalin more than hitler. There's a different context in which I would fear Hitler, but as ideologies, they are equally evil. Wait, wait, but. Not, not the same because the differences between communism and fascism. But as ideologies they're equally evil. They both view the individual as insignificant, unimportant, and they </s>

<s>[INST] So the interesting thing is so having done these, having done this podcast um and the video component, one of the things I've learned is that now I'm Russian and I I just don't know how to express emotion on my face when I see that as weakness. But whatever the people look to me after you say something, they look to my face to to help them see how they should feel about what you said. It's just fascinating because then they'll often comment on why did you look bored or why did you particularly enjoy that part or why did you? Whatever. It's a kind of interesting. Uh it makes me cognizant of on part like you're basically saying a bunch of brilliant things, but I'm part of the play that you are the key actor and by making my facial expressions and then and therefore telling the narrative of what the big like the Big point is which is fascinating. Makes you cognizant. I'm supposed to be making facial expressions. Even this conversation is hard because my preference would be to wear a mask with sunglasses to where I could just listen. [/INST] Yes, we understand this because it's intrusive to interact with others this way. And basically Eastern european society have taboo against that. And especially Russia, the further you go to the east and uh in the U. S. It's the opposite. You are expected to be hyper animated in your face. And you also expected to show positive effect. And if you show positive effect without a good reason in Russia people will think you are a stupid unsophisticated person. Exactly </s><s>[INST] and here positive effect without reason goes either appreciate or goes unnoticed. [/INST] No it's the default, it's being expected. Everything is amazing. Have you seen these uh </s><s>[INST] lego movie? [/INST] No there was a Diagram where somebody gave the appraisals that exist in the US and Russia as we have your back curve. And uh the lower 10% in the US are it's a good start. Everything about the lowest 10%. It's amazing. It's amazing. And uh for the Russians everything below the top 10% it's terrible. And then uh everything except the top percent is I don't like it and the top percent is even so </s><s>[INST] you know it's funny but it's kind of true. [/INST] Yeah but there's a deeper aspect of this. It's also how we construct meaning in the U. S. Um Usually you focus on the positive aspects and you just suppress the negative aspects and in our Eastern european traditions we emphasize the fact that if you hold something above the waterline, you also need to put something below the waterline because existence by itself is as best neutral </s><s>[INST] right? That's the basic intuition at best neutral [/INST] or just suffering the default. There are moments of beauty. But these moments of beauty are inextricably linked to the reality of suffering. And to not acknowledge the reality of suffering means that you are really stupid and unaware of the fact that basically every country's being spends most of the time suffering. </s><s>[INST] Yeah, you just summarized the ethos of the eastern europe. Yeah. Most of life is suffering with an occasional moments of beauty. And if your facial expressions don't acknowledge the abundance of suffering in the world and existence itself, then you must be an idiot. [/INST] It's an interesting thing when you raise Children in the US and you in some sense preserve the identity of the intellectual and cultural traditions that are embedded in your own families. And your daughter asked you about Ariel the mermaid. And uh ask you why is are we are not allowed to play with the humans? And you tell you the truth, She's a siren, sirens, eat people, you don't play with your food. It does not end well. And then you tell her the original story, which is not the one by Anderson, which is the romantic one. And there's a much darker one which was in a story. </s><s>[INST] So [/INST] uh Brendan is a mermaid or a water woman. She lives on ground of a river and she meets this prince and they fall enough. And the prince really, really wants to be with her. And she says, okay, but the deal is you cannot have any other women if you marry somebody else. Even though you cannot be with me because obviously you cannot breathe underwater and I have other things to do with them uh managing your kingdom is you up here, you will die. And eventually after a few years he falls in love with some princess and marries her and she shows up and quietly goes into his chamber and nobody is able to stop her or willing to do so because she is fierce and she comes quietly and said out of his chamber and they asked her what has happened, what did you do? And she said I kissed him to death. </s><s>[INST] All done. [/INST] And you know the Anderson story right. And the innocent story. The mermaid is playing with this prince that she saves and she falls in love with him and she cannot live out there. So she is giving up her voice and her tail for a human like appearance so she can walk among the humans. But this guy does not recognize that she is the one that he would marry. Instead he marries somebody who has a kingdom and economical and political relationships to his own kingdom and so on as he should and she dies. Mhm. Yeah. </s><s>[INST] Yeah. Instead Disney uh The little mermaid story has a little bit of a happy ending. That's the western. That's the american [/INST] way. My own problem is this this of course that I read Oscar Wilde before I read the other things. So I'm in indoctrinated, inoculated with this romanticism and I think that the mermaid is right. You sacrifice your life for romantic love. That's what you do. Because if you are confronted with either serving the machine and doing the the obviously right thing under the economic and social and all other human incentives, that's wrong, you should follow your heart. </s>

<s>[INST] I mean there's um because we've talked about so many inspiring things like be useful in the world sort of like solve problems, alleviate suffering. But it seems like connection between humans as a source. You know, it's um it's a source of joy is the source of meaning and that that's what love is friendship love. I I just wonder if you think about that kind of thing when you talk about preserving the light of human consciousness and that's becoming a multi planetary multi planetary species, I mean to me at least um that that means like if we're just alone and conscious and intelligent, it doesn't mean nearly as much as if we're with others, right? And there's some magic created when we're together the the french of of it. And I think the highest form of it is love, which I think broadly is is much bigger than just sort of romantic. But also, yes, romantic love and family and those kinds of things. [/INST] Well, I mean the reason I guess I care about us becoming a multi planet species and a space ranked civilization is foundational e I love humanity. And so I wish to see it prosper and do great things and be happy and and if I did not love humanity, I would not care about these things. </s><s>[INST] So, when you look at the whole of it, the human history, all the people who's ever lived, all the people alive now, Pretty, we're okay on the whole. We were pretty interesting a bunch. Yes, [/INST] all things considered, and I've read a lot of history, including the darkest, worst parts of it, and, and despite all that, I think on balance, I I still love humanity. </s><s>[INST] You joked about it with the 42, what do you, what do you think is the meaning of this whole thing? Is like, is there a non numerical? Yeah, really, I think what [/INST] Douglas Adams was saying in the Hitchhiker's guide to the galaxy is that um, the universe is the answer and what we really need to figure out our what questions to ask about the answer that is the universe. Um, and that the question is the really the hard part, and if you can properly frame the question, then the answer relatively speaking, is easy. Ah, So, so therefore, if you want to understand what questions to ask about the university won't understand the meaning of life, we need to expand the scope and scale of consciousness. So they were better able to understand the nature of the universe and, and understand the meaning of life </s><s>[INST] and ultimately the most important part would be to ask the right question, [/INST] Yes, </s><s>[INST] thereby elevating the role of the interviewer as the most important human in the room. [/INST] Absolutely good questions are you know, it's hard, it's hard to come up with good questions. Absolutely. Um but yeah, like it's like that, that is the foundation of my philosophy is that I am curious about the nature of the universe and you know, and obviously I will die. I don't know when I'll die, but I won't live forever. Um, but I would like to know that we're on a path to understanding the nature of the universe and the meaning of life and what questions to ask about the answer that is the universe. And, and so if we expand the scope and scale of humanity and consciousness in general, which includes silicon consciousness, then that you know, they weren't that that that seems like a fundamentally good thing. </s><s>[INST] Ellen like I said, um I'm deeply grateful that you would spend your extremely valuable time with me today and also that you are given millions of people hope in this difficult time, this divisive time in this cynical time. So I hope you do continue doing what you're doing and thank you so much for talking today. [/INST] You're welcome. Thanks for your excellent questions. </s><s>[INST] Thanks for listening to this conversation with Elon musk to support this podcast, please check out our sponsors in the description and now let me leave you with some words from Elon musk himself when something is important enough you do it even if the odds are not in your favor. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] could ever do. I'm not sure what to take away from that. [/INST] Okay, now take those algorithms, the best our algorithms we have today to train a car to drive itself, it would probably have to drive millions of hours. We'll have to kill thousands of pedestrians, will have to run into thousands of trees, will have to run off cliffs and you have to run the cliff multiple times before it figures out that's a bad idea. First of all, and second of all, the four figures that had not to do it. And so, I mean, this type of running obviously does not reflect the kind of learning that animals and humans do. There is something missing that's really, really important there. And my hypothesis, which I've been advocating for like five years now is that we have predictive models of the world that includes the ability to predict under uncertainty. And what allows us to not run off a cliff When we learn to drive most of us can learn to drive in about 20 or 30 hours of training without ever crashing causing any accident if we drive next to a cliff, we know that if we turn the wheel to the right, the car is gonna run off the cliff and nothing good is gonna come out of this because we have a pretty good model into the physics that tells us, you know, the car is going to fall. We know we know about gravity babies around this around the age of eight or nine months, that objects don't float the full. Um and you know, we have a pretty good idea of the effect of turning the wheel of the car and you know, we know we need to stay in the world. So there's a lot of things that we bring to the table which is basically a predictive model of the world. And that model allows us to not do stupid things and to basically stay within the context of things we need to do, we still face, you know, unpredictable situations and that's how we learn, but that allows us to learn really, really, really quickly. So that's called model based reinforcement learning. There's some imitation and supervised learning because we have a driving instructor that tells us occasionally what to do. Uh but most of the learning model is learning the model, learning physics that we've done since we were babies. That's where all almost all the learning and </s><s>[INST] the physics is somewhat transferable from, it's transferable from scene to scene, stupid things are the same [/INST] everywhere. Yeah, I mean if you, you know, you have an experience of the world, You don't need to be particularly from a particular intelligent species to know that if you spill water from a container, you know the rest is going to get wet, you might get wet. Um So you know cats know this, right? So the main problem we need to solve is how do we learn models of the world? That's that's what I'm interesting. That's what self supervised learning is all about. </s><s>[INST] If you were to try to construct the benchmark for, let's let's look at Em Nous. I love that is uh if you do you think it's useful, interesting slash [/INST] possible </s><s>[INST] to ah perform well on M. Nus with just one example of each digit. And how would we solve that problem? [/INST] The answer is probably yes. The question is, what other type of learning are you allowed to do? So if what you're allowed to do is train on some gigantic dataset of labeled digit that's called transfer learning. And we know that works okay. We do this at facebook like in production right? We train large convolutional nets to predict hashtags that people type on instagram and we trained on billions of images, literally billions and uh then we chop off the last layer and fine tune on whatever task we want that works really well. You can be, you know the image that record with us? We actually opens for us the whole thing like a few weeks ago. </s><s>[INST] That's still pretty cool. But yeah. So what what would be impressive? What's useful and impressive? What kind of transfer learning would be useful impressive is the Wikipedia, that kind of thing. I [/INST] don't think transfer learning is really where we should focus. We should try to do have a kind of scenario for a benchmark where you have only pull data and you can and it's a very large number of valuable data. It could be video clips, it could be where you do frame prediction, it could be images, you could choose to, you know, masterpiece of it. It could be whatever, but they're unlabeled and you're not allowed to label them. So you do. So I'm training on this and then you train on a particular supervised task, You mentioned it to our list and you measure how your tester or decrease or valuation error decreases as you increase the number of label training samples. Okay. And and what you'd like to see is is that, you know, your your error decreases much faster than if you train from scratch from running weights. So that to reach the same level of performance and completely supervised, purely supervised system would reach, you would need with your samples. So that's the crucial question because it will answer the question to like, you know, people are interested in medical imaging that is this okay. You know, if I want to get too particular uh level of error rate for this task. I know I need um a million temples Can I do you know, self supervised pre training two reduces to about 100 or something. </s><s>[INST] And you think the answer there is self supervised pre training? Yeah, [/INST] some form some some form of it </s>

<s>[INST] So is their free will. [/INST] This is this is a </s><s>[INST] great project for the for the absurd [/INST] high level of philosophical question. No no these are my favorite kind of questions here. Here's the thing. Here's the thing. We don't know if you ask most </s><s>[INST] neuroscientists they'll [/INST] say that we can't really think of how you would get free will in there. Because as far as we can tell it's a machine it's a very complicated machine, enormously sophisticated, 86 billion neurons about the same number of glial cells. Each of these things is as complicated as the city of san Francisco. Each neuron in your head has the entire human genome in it. It's expressing Millions of gene products. These are incredibly complicated biochemical cascades, each one is connected 10,000 of its neighbors, which means you have, you know, like half a quadrillion connections in the brain. So it's it's incredibly complicating, but it is fundamentally appears to just be a machine and therefore if there's nothing in it that's not being driven by something else, then it seems it's hard to understand where free will would come from. So that's the camp that pretty much all of us fall into. But I will say our science is still quite young and you know, I'm a fan of the history of science and what the thing that always strikes me as interesting is when you look back at any moment in science, everybody believes something is true and they just they simply didn't know about, you know, what Einstein revealed or whatever, and so who knows? </s><s>[INST] And then it all feel like that we've, at any moment history, they all feel like we've converted to the final answer. Exactly, [/INST] exactly. Like all the pieces the puzzle are there. And I think that's a funny illusion that's worth getting rid of. And and in fact this is what drives good science is recognizing that we don't have most of the puzzle pieces. So as far as the free will question goes, I don't know at the moment, it seems, wow, would be really impossible to figure out how something else could fit in there. But, you know, 100 years from now, our textbooks might be very different than they are now. </s><s>[INST] I mean, could I ask you to speculate, where do you think if we will, could be squeezed into there? Like what's that even? Um, is it possible that our brain just creates kinds of illusions that are useful for us? Or like what? Where could it possibly be squeezed in? [/INST] Well, let me, let me give a speculation answer to your very nice question. But, but you know, don't. And the listeners this podcast put me on this. Yeah, I'm not saying this is what I believe to be true, but let me just give an example. I give it to the end of my book incognito. So the whole book of incognito is about, you know, all the what's happening in the brain. And essentially I'm saying, look, here's all the reasons to think that free will probably does not exist. But at the very end I say, look, imagine that you are, you know, imagine that you're a Kalahari bushmen and you find a radio in the sand and you've never seen anything like this. And you you look at this radio and you realize that when you turn this knob, you hear voices coming from their voices coming from it. So being a, you know, a radio materialist, you try to figure out like how does this thing operates, You take off the back cover and you realize there's all these wires and when you take out some wires, the voices get garbled or stop or whatever. And so what you end up developing is a whole theory about how this connections pattern of wires gives rise to voices. But it would never strike you that in distant cities there's a radio tower and there's invisible stuff beaming and that's actually the origin of the voices. And this is just necessary for it. So I mentioned this just as a speculation saying, look, how would we know what we know about the brain for absolutely certain is that if when you damage pieces and parts of it, things get jumbled up. But how would you know if there's something else going on that we can't see like electromagnetic radiation. That is what's actually generating this. </s><s>[INST] Yeah. You paint a beautiful example of uh, of how totally because we don't know most of how our universe works, how totally off base we might be with our science until. I mean, I mean, um yeah, I mean that's inspiring this beautiful. It's kind of terrifying. It's humbling. It's all, all of the above [/INST] and the important, the important part just to recognize is that of course we're in the position of having massive unknowns and you know, we have of course the known unknowns and that's all the things we're pursuing in our lab and trying to figure out that. But there's this whole space of unknown unknown since we haven't even realized we haven't asked yet </s>

<s>[INST] From the perspective of a human player, the difference between that and chess or maybe that and uh a game like turn based strategy like heroes of might and magic is that there's an anxiety because you have to make these decisions really quickly and uh if you are not actually aware of what decisions work, it's a very stressful balance, Everything you describe is actually quite stressful, difficult to balance for amateur human player. I don't know if it gets easier at the professional level, like if they're fully aware of what they have to do, but at the amateur level there's this anxiety, oh crap, I'm being attacked, oh crap, I have to build up resource, oh I have to probably expand and all these the time. The real time strategy aspect is really stressful and computation. I'm sure difficult, we'll get into it. But uh for me, Battle Net. Uh so starcraft was released in 98, 20 years ago, which is hard to believe. Uh and uh blizzard battle net with Diablo in 96 came out and to me it might be a narrow perspective, but it changed online gaming and perhaps society forever. But I may have made way too narrow viewpoint, but from your perspective, Can you talk about the history of gaming over the past 20 years? Is this how transformational, how important is this line of games? [/INST] Right, So I think I I kind of was an active gamer whilst this was developing the internet, online gaming. So for me that's the way it came was I played other games strategy related, I played a bit of common and conquer and then I played Warcraft two, which is from Blizzard, but at the time I didn't know I didn't understand about what Blizzard was or anything. The aircraft was just a game which is which was actually very similar to Starcraft in many ways it's also real time strategy game um where there's orcs and humans, so there's only two races, </s><s>[INST] it was offline [/INST] And it was offline right? So I remember a friend of mine came to school say oh there's this new cool game called Starcraft and I just said all these sounds like just a copy of warcraft two until I kind of installed it and at the time I I am from Spain so we didn't have internet like very good internet right? So there was for us the Starcraft became first kind of an offline experience where you kind of start to play these missions right? You play against some sort of scripted things to develop the story of the characters in the game. Um And then later on I start playing against the built in Ai. Um and I thought it was impossible to defeat it then eventually you defeat one and you can actually play against seven built in Ai is at the same time which also felt impossible but actually it's not that hard to beat seven built in AI is at once. So once we achieved that also we discovered that we could play as I said the internet wasn't that great but we could play with the land right on basically against each other if we were in the same place because you could just connect machines with like cables. Right? Um, so we started playing in land mode and against, you know, as a group of friends and it was really, really like much more entertaining than playing against the eyes. And later on as the internet was starting to develop and being a bit faster and more reliable. Then it's when I started experiencing battle net, which is this amazing universe. Not only because of the fact that you can play the game against anyway, anyone in the world, but you can also get to know more people, you just get exposed to now. Like this vast variety of, it's kind of a bit when the chance came about right, there was a chat system, you could play against people, but you could also chat with people not only about staggered but about anything. And that became a way of life for kind of two years. And obviously then it became like kind of, it exploded in me that I started to play more seriously going to tournaments and so on so forth. </s><s>[INST] Do you have a sense on a societal sociological level, what's this whole part of society that many of us are not aware of? And it's a huge part of society which is gamers. I mean, uh, every time I come across that in Youtube or streaming sites. I mean this is a huge number of people play games religiously. Do you have a sense of those folks, especially now that you've returned to that realm a little bit on the high side. [/INST] Yeah. So in fact I, even after stagger, if I actually played World Worker, which is maybe the main sort of online walls and presence that you get to interact with lots of people. So I played that for a little bit. It was to me it was a bit less stressful than Starcraft because winning was kind of given you just put in this world and you can always complete missions. But I think it was actually the social aspect of especially Starcraft 1st and then games like World of Warcraft really shaped me in, in a very interesting ways because you get to experience is just people you wouldn't usually interact with. Right? So even nowadays I still have many facebook friends from the area where I played online and their ways of thinking is even political. Um, they just don't, we don't live in like we don't interact in the, in the real world, but we were connected by basically fiber and that way I actually get to understand a bit better, um, that we live in a diverse world And these were just connections that were made by because you know, I happened to go in the city in a beautiful city as a priest and I met this, you know, this warrior and we became friends and then we start like playing together. Right? So I think it's It's transformative and more and more and more people are more aware of it. I mean it's becoming quite mainstream but back in the day, as you are saying in 2000 2005 even it was very still very strange thing to do, especially in Europe. I think there were exceptions like Korea for instance. It was amazing like that that everything happened soil in terms of cyber cafes. Like it's if you go to Seoul it's a city that back in the day, Starcraft was kind of you could be a celebrity by playing Starcraft but this was like 99 2000, right? It's not like recently. So um yeah it's quite it's quite interesting to look back and and yeah, I think it's changing society that the same way of course, like technology and social networks and so on are also transforming things </s>

<s>[INST] as you call the basic science [/INST] of rules. Yes, Yes. Right. So it's it's like you've got some, what is it? Is it mathematics? No, it isn't really like mathematics, in fact, from my now understanding of math mathematics, I understand that it's the molecular dynamics level. It's not the level that mathematicians have traditionally cared about. It's not computer science, because computer science is about writing programs that do things, you know, that were for a purpose, not programs in the wild, so to speak. It's not physics. It doesn't have anything to do with, you know, maybe underneath some physics, but it's not physics as such. So it just hasn't had a home. And if you look at, you know, but what's great about it is it's a surviving field, so to speak. It's it's something where, you know, one of the things I find sort of inspiring about mathematics, for example, is you look at mathematics that was done, you know, in ancient Greece, ancient Babylon Egypt and so on. It's still here today. You know, you find an I Costa Hedren that somebody made in ancient Egypt. You look at it. Oh, that's a very modern thing. It's an ecosystem Hadron. You know, it's it's a timeless kind of kind of activity and this idea of studying simple rules and what they do, it's a timeless activity. And I can see that over the last 40 years or so, as you know, even when cellular automata, It's kind of like, you know, you can sort of catalog what what are the different cellular automata used for And, you know, like the simplest rules, like, like one you might even know this one. Rule 1 80 for its Rule 1 84 is a minimal model for road traffic flow. And, you know, it's also a minimal model for various other things, but it's kind of fun that you can literally say, you know, rule 90 is a minimal model for this and this and this, Rule four is a minimal model for this. And it's kind of remarkable that you can just buy in this raw level of this kind of study of rules. They then branch there there the raw material that you can use to make models of different things. So it's a, it's a very pure basic science, but it's one that, you know, people have explored it, but they've been kind of a little bit in the wilderness. And I think, you know, one of the things that I would like to do finally is, uh, you know, I always thought that sort of this notion of pure and chaos, pure chaos being the acronym for my book, new kind of science was it was something that people should be doing and, you know, we tried to figure out what's the right institutional structure to do this stuff. You know, we we dealt with a bunch of universities, Oh, you know, can we do this here? Well, what department would be in it? Well, it isn't in the department, it's it's so new, kind of thing, that's why that's why the book was called a new kind of science. Um, it's kind of the the because that's an increasingly good description of what it is. The we're actually we're thinking about kind of the rule geological society because we're realizing that it's kind of, it's, you know, it's very it's very interesting. I mean, I've never really done something like this before because there's this whole group of researchers who are who have been doing things that are really, in some cases very elegant, very surviving, very solid. You know, here's this thing that happens in this very abstract system, but it's like, it's like, what is that part of? You know, it's it doesn't have a home. And I think that's something I, you know, I kind of felt myself for not having been more, you know, when complexity was developing in the eighties, I didn't understand the danger of applications. That is, it's really cool that you can apply this to economics and you can apply it to evolutionary biology and this and that and the other. But what happens with applications is everything gets sucked into the applications and the pure stuff. It's like the pure mathematics, there isn't any pure mathematics, so to speak. It's all just applications of mathematics and I failed to kind of make sure that this kind of pure area was, was kind of maintained and developed. And I think now, you know, one of the things I want to try to do and and you know, it's a funny thing because I'm used to look, I've been a tech ceo for more than half my life now, so you know, this is what I know how to do and you know, I can I can make stuff happen and get projects to happen even as it turns out, basic science projects in that kind of setting and how that translates into kind of uh you know, there's a lot of people working on, for example, our physics project sort of distributed through the economic world and that's working just great. But the question is, you know, can we have a sort of accelerator mechanism that makes use of kind of what we've learned in and sort of R and D. Innovation and you know, but on the other hand, it's a funny thing because, you know, in a company in the end, the thing is, you know, it's a company that makes products that sell things, sells things to people um in, you know, when you're doing basic research, one of the challenges is there isn't that same kind of sort of mechanism and so it's it's it's, you know, how do you drive the thing in a kind of a lead kind of way so that it really can can make forward progress rather than, you know what can often happen in, you know, in academic settings where it's like, well there are all these flowers blooming, but it's not clear that, you know that it's </s>

<s>[INST] of something inanimate like where you put a try to bring life into it and beauty. [/INST] Absolutely. And then ultimately give it a personality, which is where the intelligent agent research will converge with the vision and voice synthesis to give it a sense of having not necessarily human level intelligence. I think the cheering test is such a high bar. It's a little bit self defeating, but having one that you can have a meaningful conversation with, especially if you have a reasonably good sense of what you can say. Um so not trying to have it. So a stranger could walk up and have one. But so as a, as a pet owner or robot pet owner, you could know what it thinks about what it can reason about. Or </s><s>[INST] sometimes just meaningful interaction. If you have a kind of interaction you have with a dog, sometimes you might have a conversation, but it's usually one way. [/INST] Absolutely. </s><s>[INST] And uh unless it feels like a meaningful connection. [/INST] And one of the things that I'm trying to do in the sample audio that will play you is beginning to get towards the point where the reasoning system can explain why it knows something or why it thinks something and that again creates the sense that it really does know what it's talking about. But also yeah, for debugging as you get more and more elaborate behavior, it's like why did you decide to do that? What you know? How do you know that? I think it's the robots really my news for helping me think about the future of Ai and what to invent next. </s><s>[INST] So even at adobe that's mostly operating in digital world, do you ever, do you see a future where adobe even expands into the more physical world perhaps? So bringing life not into animations, but bringing life into physical objects with whether it's well, you [/INST] have to say at the moment it's a twinkle in my eye, I think the more likely thing is that we will bring virtual objects into the physical world through augmented reality. And many of the ideas that might take five years to build a robot to do, you can do in a few weeks with digital assets. So I think when really intelligent robots finally become commonplace, they won't be that surprising because we'll have been living with those personalities for in the virtual sphere for a long time and then they'll just say, oh, it's, you know, syria with legs or Alexa Alexa on hoofs or something. Um So I can see that well coming. Um and for now it's still an adventure and we don't know quite what the experience will be like and it's really exciting to see all of these different strands of my career converge. </s><s>[INST] Yeah, in interesting ways and it is definitely a fun adventure. So uh let me end with my favorite poem, last few lines of my favorite poem of yours that ponders mortality and in some sense immortality. You know, as our ideas live through the ideas of others through the work of others. It ends with do not weep or mourn. It was enough. The little adami's permitted just a single dance scatter them as deep as your eyes can see. I am content. I'll have another chance sweeping more centered parts along to join a jostling lifting throng as others danced in me. Beautiful poem beautifully to end it, Gavin thank you so much for talking today and thank you for inspiring and empowering millions of people like myself for creating amazing stuff. [/INST] Thank you. Great conversation. </s>

<s>[INST] because it is because it's [/INST] challenging. Well, it's hard to keep it front and center because you know, you're you operate on so many levels all the time and you know, getting this done takes priority or you know, being happy takes priority or you know, screwing around takes priority. Like, like, like how you go through life is complicated and then you remember, oh yeah, I could really think first principles ship that's that's tiring. You know what you do for a while and that's kind of cool. </s><s>[INST] So just as a last question in your sense from the big picture from the first principles, do you think you kind of answered already? But do you think autonomous driving is something we can solve on a timeline of years. So 1235, 10 years as opposed to a century [/INST] definitely </s><s>[INST] just to linger in it a little longer. Where's the confidence coming from? Is it the fundamentals of the problem? The fundamentals of building the hardware and the software [/INST] as a computational problem understanding ballistics, roles, topography. It seems pretty solvable. I mean and you can see this you know like like speech recognition for a long time people are doing you know frequency and domain analysis and and all kinds of stuff and that didn't work for at all. Right. And then they did deep learning about it and it worked great and it took multiple iterations and autonomous driving his way past the frequency analysis point. You know use radar don't run into things and the data gathering is going up and the computation is going up and the algorithm understanding is going up and there's a whole bunch of problems getting solved like that. </s><s>[INST] The data side is really powerful but I disagree with both you and you and I'll tell you and once again as I did before that that when you add human beings into the picture, the it's no longer a ballistics problem. It's something more complicated. But I could be very well proven [/INST] cars are hardly damped in terms of ready to change. Like the steering and the steering system is really slow compared to a computer. The acceleration of the acceleration is really slow. </s><s>[INST] Yeah. On a certain time scale on a ballistics timescale, but human behavior, I don't know, I shouldn't [/INST] say beans are really slow too weirdly. We operate, you know, half a second behind reality. I'll be really understands that one either. It's pretty funny. </s><s>[INST] Yeah, [/INST] yeah, sure. </s><s>[INST] It will be very well. Could be surprised. And I think with the rate of improvement in all aspects on both the computer and the software and the hardware, there's going to be pleasant surprises all over the place. Speaking of unpleasant surprises, many people have worries about a singularity in the development of AI. Forgive me for such [/INST] questions. </s><s>[INST] When AI improves the exponential and reaches a point of super human level general intelligence. Uh you know, beyond the point, there's no looking back, do you share this worry of existential threats from artificial intelligence from computers becoming super human level intelligence? [/INST] No, not really. You know, like we already have a very stratified society. And then if you look at the whole animal kingdom of capabilities and abilities and interests and you know, smart people have their niche and you know, normal people have their niche and craftsman's have their niche and you know, animals have their niche. I suspect that the domains of interest for things that, you know, astronomically different, Like the whole something got 10 times smarter than us and wanted to track us all down because what we like to have coffee at Starbucks, Like it doesn't seem plausible now. Is there an existential problem that how do you live in a world where there's something way smarter than you and you based your kind of self esteem on being the smartest local person? Well, there's what .1% of the population who thinks that because the rest of the population has been dealing with it since they were born. So the the breath of possible experience that can be interesting is really big. And you know, super intelligence seems likely, although we still don't know if we're magical, but I suspect we're not and it seems likely that will create possibilities that are interesting for us. And it's it's interests will be interesting for that for whatever it is, it's not obvious why it's interest would somehow want to fight over some square foot of dirt or, you know, whatever the, you know, the usual fears are about. </s><s>[INST] So you don't think you'll inherent some of the darker aspects of human nature [/INST] depends on how you think reality is constructed. So for for whatever reason human beings are in, let's say creative tension and opposition with both are good and bad forces, like there's lots of philosophical understanding of that, right? I don't know why that would be different. </s><s>[INST] So you think the evils is necessary for the good? I mean, the attention, [/INST] I don't know about evil, but like we live in a competitive world where you're good as somebody else's all right, You know, evil, you know, there's there's the malignant part of it, but that seems to be self limiting, although occasionally it's it's super horrible. </s><s>[INST] But yes, there's a debate over ideas and some people have different beliefs and that that debate itself is a process so that arriving at something. [/INST] Yeah, why wouldn't I continue </s><s>[INST] just But you don't think that whole process will leave humans behind in a way that's painful, Emotionally painful. Yes, for the one for the .1%, they'll be [/INST] why isn't it already painful for a large percentage of the population? And it is I mean, society does have a lot of stress in it About the 1% and about to this and about that. But, you know, everybody has a lot of stress in life about what they find satisfying and and, you know, know yourself seems to be the proper dictum and pursue something that makes your life meaningful. Seems proper. And there's so many avenues on that. Like there's so much unexplored space at every single level, you know, I'm somewhat of my nephew called me a jaded optimist, you know, So it's </s>

<s>[INST] later on in the id software days as well. So do efficient drawing where you don't have to draw the whole screen, but you draw from the bottom using the thing that was designed in the hardware [/INST] for text output. Yeah, where so much of, until recently, game design was limited by what you could actually get the computer to do, where it's easy to say, like, okay, I want to scroll the screen. You just redraw the entire screen at a slight offset. And nowadays that works just fine. Computers are ludicrously fast. But up until a decade ago or so, there were all these things everybody wanted to do, but if they knew enough programming to be able to make it happen, it would happen too slow to be a good experience, either just ridiculously slow or just slow enough that it wasn't fun to experience it like that. So so much of kind of the first couple decades of the programming work that I did was largely figuring out how to do something that everybody knows how they want it to happen. It just has to happen two to 10 times faster than sort of the straightforward way of doing things would make it happen. And it's different now because at this point, lots of things you can just do in the most naive possible way and it still works out. You know, you don't have nearly the creative limitations or the incentives for optimizing on that level. And there's a lot of pros and cons to that. But I do generally, you know, I'm not gonna do the angry old man shaking my fist at the clouds bit where back in my day programmers had to do real programming. You know, it's amazing that you can just kind of pick an idea and go do it right now. And you don't have to be some assembly language wizard or deep GPU Arcanist to be able to figure out how to make your wishes happen. </s><s>[INST] Well, there's still, see, that's true. But let me put on my old man with a fist hat and say that probably the thing that will define the future still requires you to operate at the limits of the current system. So we'll probably talk about this, but if you talk about building the metaverse and building a VR experience that's compelling, it probably requires you to not to go to assembly or maybe not literally, but sort of spiritually [/INST] to go to the limits of what the system is capable of. And that really was why virtual reality was specifically interesting to me where it had all the ties to, you could say that even back in the early days, I have some old magazine articles that's talking about doom as a virtual reality experience back when just seeing anything in 3D. So you could say that we've been trying to build those virtual experiences from the very beginning. And in the modern era of virtual reality, especially on the mobile side of things, when it's standalone and you're basically using a cell phone chip to be able to produce these very immersive experiences, it does require work. It's not at the level of what an old school console game programmer would have operated at where you're looking at hardware registers and you're scheduling all the DNA accesses, but it is still definitely a different level than what a web developer or even a PC Steam game developer usually has to work at. And again, it's great. There's opportunities for people that wanna operate at either end of that spectrum there </s><s>[INST] and still provide a lot of value to the world. Let me ask you sort of a big question about preference. What would you say is the best programming language? Your favorite, but also the best. You've seen throughout your career, you're considered by many to be the greatest programmer ever. I mean, it's so difficult to place that label on anyone, but if you put it on anyone, it's you. So let me ask you these kinds of ridiculous questions of what's the best band of all time, [/INST] but in your case, what's the best programming language? Everything has all the caveats about it, but so what I use, so nowadays, I do program a reasonable amount of Python for AIML sorts of work. I'm not a native Python programmer. It's something I came to very late in my career. I understand what it's good for. </s><s>[INST] But you don't dream in Python. [/INST] I do not. And it has some of those things where there's some amazing stats when you say, if you just start, if you make a loop, you know, a triply nested loop and start doing operations in Python, you can be thousands to potentially a million times slower than a proper GPU tensor operation. And these are staggering numbers. You know, you can be as much slower as we've almost gotten faster in our pace of progress </s><s>[INST] and all this other miraculous stuff. So your intuition is about inefficiencies [/INST] within the Python sort of- It keeps hitting me upside the face where it just, it's gotten to the point now I understand. It's like, okay, you just can't do a loop if you care about performance in Python. You have to figure out how you can reformat this into some big vector operation or something that's going to be done completely within a C++ library. But the other hand is it's amazingly convenient. And you just see stuff that people are able to cobble together by, you just import a few different things and you can do stuff that nobody on earth could do 10 years ago. And you can do it in a little cookbook thing that you copy paste it out of a website. So that is really great. When I'm sitting down to do what I consider kind of serious programming, it's still in C++ and it's really kind of a C flavored C++ at that where I'm not big into the modern template meta programming sorts of things. I see a lot of train wrecks coming from some of that over abstraction. I spent a few years really going kind of deep into the kind of the historical Lisp work and Haskell and some of the functional programming sides of things. And there is a lot of value there in the way you think about things. And I changed a lot of the way I write my C and C++ code based on what I learned about the value that comes out of not having this random mutable state that you kind of lose track of. Because something that many people don't really appreciate till they've been at it for a long time is that it's not the writing of the program initially, it's the whole lifespan of the program. And that's when it's not necessarily just how fast you wrote it or how fast it operates, but it's how can it bend and adapt as situations change. And then the thing that I've really been learning in my time at meta with the Oculus and VR work is it's also how well it hands off between a continuous kind of revolving door of programmers taking over maintenance and different things and how you get people up to speed in different areas. And there's all these other different aspects of it. </s>

<s>[INST] executives. It's like the flipside of that though. And this is, was the pitch of Spotify because I've heard their pitch is netflix from everybody. I've heard that I've spoken with about netflix is they actually empower the creator? I don't know, I don't know what the heck they do, but they do a good job of giving creators even the crazy ones like tim doing like joe Rogan, like comedians freedom to be their crazy cells. And the result is like some of the greatest television, some of the greatest cinema, whatever you call it ever made. True, right? And I don't know what the heck they're doing. [/INST] It's a relative thing is from what I understand is a relative thing. They're interfering far far, far less than, you know, NBC or you know, AMC would have interfered. So it's, it's a relative thing. And obviously they're the ones writing the checks and the other one's giving the platforms, they have every right to their own influence obviously, but my understanding is that it's the relatively way more hands off and that has had a demonstrable effect cause I agree, some of the greatest, you know, video produced video content of all time, an incredibly inordinate percentage that is coming out from netflix in just a few years when the history of cinema goes back many, many decades. </s><s>[INST] And Spotify wants to be that for podcasting and I hope they do become that for podcasting, but I'm wearing my skeptical goggles are skeptical hat, whatever it is because it's not easy to do. And it requires, uh, it requires letting go of power, giving power to the creatives. It requires pivoting which large companies, even as innovative as Spotify is still now a large company pivoting into a whole new space is very tricky and difficult. So I'm skeptical but hopeful, what advice would you give to a young person today about life, About career? We talked about startups, talked about music, talked about the end of human civilization. Is there advice you would give to a young person today? Maybe in college, maybe in high school about, about their life? [/INST] Well, let's see, I mean there's so many domains you can advise on and you know, I'm not going to give advice on life because I fear that I would drift into sort of hallmark bromides that really wouldn't be all that distinctive and they might be entirely true. Sometimes the greatest insights about life turn out to be like the kinds of things you see in a hallmark card. So I'm gonna steer clear that on a career level. You know, one thing that I think is un intuitive but unbelievably powerful Is to focus, not necessarily on being you in the top sliver of one in excel in it. One domain that's important and valuable but to think in terms of intersections of two domains which are rare but valuable and there's a couple reasons for this, the first is in an incredibly competitive world that is so much more competitive than it was when I was coming out of school. Radically more competitive than when I was coming out of school. To navigate your way to the absolute pinnacle of any domain, let's say you want to be, you know, really, really great at, you know, python pickle language, whatever it is you want to be one of the world's greatest python developers, javascript whatever your language is, hopefully it's not cobalt. Um, but </s><s>[INST] by the way if you listen to this, I am actually looking for a cobalt expert to interview because I find language fascinating and how many of them so please if you're, if you know a world expert in cobalt or four tramp both actually [/INST] Or if you are one or </s><s>[INST] if you are one, please email [/INST] me. So I mean if you're going out there and you want to be in the top sliver 1% of python developers, a very, very difficult thing to do if you wanna be number one in the world, something like that and I'll use an analogy is I had a friend in college who was on a track and indeed succeeded at that to become an olympic medal or Medalist and I think 100 m breaststroke and he mortgaged a significant percentage of his sort of college life to that goal, I should say dedicated or invested or whatever you wanted to say, But he didn't participate in a lot of the social, a lot of the late night, a lot of this, a lot of that because he was training so much and obviously he also wanted to keep up with his academics and at the end of the day story has a happy ending and that he did meddle in that bronze, not gold, but holy cow, anybody who gets an olympic medal, that's an extraordinary thing. And at that moment he was, you know, one of the top three people on earth at that thing. But wow, how hard to do that, how many thousands of other people went down that path and made similar sacrifices and didn't get there. It's very, very hard to do that. Um, whereas you will use a personal example um when I came out of business school, I went to a good business school and and learned the things that were there to be learned and I came out and I entered a world </s><s>[INST] with lots of Harvard business school, by the [/INST] way, it was Harvard, it's true, you're the </s><s>[INST] first person who went there who didn't say where you went, It was just beautiful, I appreciate that. It's one of the greatest business schools uh in the world. It's a whole another fascinating conversation about that world. But anyway. [/INST] But anyway, so I learned things that you, you learn getting to be an M. B. A. From a from a top program and I entered a world that had hundreds of thousands of people who had M. B. A. S. Uh probably hundreds of thousands who have them from, you know, top 10 programs. But so I was not particularly great at being an NBA person, I was inexperienced relative to most of them and there were a lot of them, but it was okay NBA person right, newly minted. Uh But then as it happened, I found my way into working on the commercial internet in 1994. So I went to a at the time, giant hot computing company called Silicon Graphics, which had enough heft and enough headcount that they could take on an experienced N. B. A. S. And try to train them in the world of Silicon Valley. But within that, that company that had an enormous amount of surface area and was touching very a lot of areas and was had unbelievably smart people at the time. Uh It was not surprising that S. G I started doing really interesting and innovative and trailblazing stuff on the internet before almost anybody else. And part of the reason was that our founder, Jim Clark went on to co found Netscape with Mark Andrews. And so the whole company was like, wait, what was that? What's this commercial internet thing? So I end up in that group now in terms of being a commercial internet person or a worldwide worldwide web person. Um again, I was in that case barely credentials, I couldn't write a stitch a code, but I got a had a pretty good mind for grasping the business and and and cultural significance of this transition. And this was again, we were talking earlier about emerging areas within a few months, you know, I was in the relatively top echelon of people in terms of just sheer experience because like let's say it was five months into the program, there were only so many people who have been doing World Wide Web stuff commercially for five months, you know. And then what was interesting though was the intersection of those two things. The commercial web as it turned out, grew into unbelievable vastness and so by being a pretty good okay web person and a pretty good. Okay. M. B. A. Person that intersection put me in a very rare group which was web oriented mbas. And in those early days you could probably count on your fingers the number of people who came out of really competitive programs who were doing stuff full time on the internet. And there was a greater appetite for great software developers in the internet domain, but there was an appetite and a real one and a rapidly growing one for M. B. A. Thinkers who were also seasoned and networked in the emerging world of the commercial world Wide Web. And so finding an intersection of two things you can be pretty good at but is a rare intersection and a special intersection is probably a much easier way to make yourself distinguishable and in demand from the world than trying to be world class at this one thing. </s>

<s>[INST] One of the inspiring things about joe is, I mean he's in this war alone and the way he fights the war is by just enjoying life. That's his thing, [/INST] stays close to things that he loves and being, you know, one of the things he's honest about his drug use, he looked, he loves to hunt. So he's just, he does a certain amount of like semi vice signaling upfront and then you just also know him. This is why every time they try to take him down, you use the N word. You know, it's like, unfortunately everybody knows who joe is and yes, he, he doesn't act as if he went to a fancy finishing school right? That's not his energy. The fact that you've got some super smart guy who always pretends to be a meathead, just like, you know, like, hey, I'm a comedian, like all these defenses and disguises, okay, you've got the super smart guy who um, he's admitted to most of the things that, you know, you can, you can take him down for him because everybody's been effectively in his den or his basement, think about that studio in his basement. People have hung out with joe so many hours that you can't tell them something about joe or they're going to say, wow, I'm going to believe the new york times and not the hundreds of hours I've spent on the joe Rogan experience. But the cool </s><s>[INST] thing is that this is what inspires me is that the way he's waging war against the system is just by being a good person and, and talking enough hours in a week where that message like bleeds throughout the words and the gaps between and that, that's so inspiring to me that the good people can win by just being good and he's [/INST] kind and he's tough and he also, he's no pushover. Now I always worry a little bit when I sit down in that </s><s>[INST] chair, you still get scared that he'll call you on some kind of bullshit that you weren't even aware of [/INST] the first time I was on the show, the energy wasn't great between us and it was in a sober october situation. So I think I hadn't understood that and maybe our egos got a little bit off. I don't know, I mean, I was having fun, but maybe it was just too complicated life forms, getting to know each other, but the first one was probably, um, yeah, it made me a little nervous for the future, but then you know, jo jo and I have become friends, although sometimes we have miscommunications like on Yom kippur, I texted him and I said joe, you know, I want to apologize for ways, I've let you down as a friend that haven't been there for you and we appreciate everything you've done for me. Alyssa. Like I get this text back like what the fund is your problem? You're great dude, I don't know what bad place your cheer up. It's like joe have any jews in your life to apologize for what they've done. He was just like dude, have you lost your mind? What the hell's gotten into you? </s><s>[INST] Yeah, what do you think? Uh what do you think about the Spotify thing? What about it asked me a question. He's now as opposed to being just a comedian with the podcast. He now is just a comedian with the podcast who stepped like in the middle of the center of cancel culture which is like I know Spotify is in Sweden but they represent Silicon Valley. They represent the very kind of structures they contain and represent the kind of structures that threatened to destroy the villains of the world. Mm And he just like stepped like with his Alex jones and his uh Joey Diaz just strolled right into the middle of it. It's [/INST] awesome. I </s><s>[INST] love it, but do you think he's strong enough to Well I don't know, I mean I don't even know the right way to ask this, but is he strong enough to persevere? [/INST] It's a bit interesting. It's like when alliance decides, wow that honey badger looks tasty, I'm gonna swallow it whole, see what happened. </s><s>[INST] Because I talked him off line, he really seems to be willing to give away the 100 million which gives them so much power. Oh I don't, it's a powerful thing to be able to say. I don't Yeah, to the honey badger, he just strolls in but he's willing to walk away from anything in this. Well [/INST] he's gonna walk out the other side of the lion. I don't think he's gonna go out the way he came </s><s>[INST] in. Yeah, [/INST] well you know what it is? It's Tommy lee jones entering the bug. </s><s>[INST] This is like a giant alien just walks into it. [/INST] He just he gets swallowed by the bug and he blasts out from the inside. I have. It is Tommy lee jones. Yeah, </s><s>[INST] but anyway, Rogan to you. [/INST] Yeah, is that my feeling is that Spotify doesn't understand what they're messing with? I could be wrong but I'm not your </s><s>[INST] right because [/INST] joe doesn't need anything man. I mean this is the weird thing about it, it's like I'm sure that he loves all his toys, whatever, blah blah blah. He's a rich guy. Yes, he's got a few money, He had a few money a long time ago. And you're not, you know, the other thing about, it's a bit weird being friends with a dude like that. It just is because like you call them up or he'll call you up and I'm like, what's going on in your life? I don't know. Kind of depressed trying to get some math then what are you up? Oh dude, I can cheer you up. I just came off of a 29,000 person stadium. It's like, oh, cool, How'd you do that? Oh, I don't know. I just announced it on instagram a few days ago and it's filled up just like, oh damn. </s>

<s>[INST] Yeah, I don't know. You know, let me bring this case up because I think about this, uh, this might not mean much to you, but it means a lot of certain aspects of the computer science community. There's a guy named Richard Stallman, I don't know if you you know who that is. He is the founder of the Free Software Foundation. He's like a big Lennox. He's one of the key people in the history of computer science, one of those open source people, right? But he is like, I believe he's one of the hardcore ones, which is like all software should be free. Okay, so it's very interesting personality, very key person in the new just like Linus Torvalds key person. So, but he also kind of speaks his mind and on a certain chain of conversations at MIT that was leaked to the new york times then was published, led him to be fired or pushed out of M I. T. Recently, maybe a year ago. And I always sat weird with me. So what happened is, um, there's a few undergraduate students that called Marvin Minsky, not sure if you're familiar who that is. He's one of the seminal people in artificial intelligence. They they said that they called him a rapist because uh he met with Jeffrey Epstein and Jeff free. Epstein solicited uh, These are the best facts known to me that I'm aware of, that's what was stated in the chain, is he solicited a 17, but it might have been an 18 year old girl to come up to Marvin Minsky and ask him if he wanted to have sex with her. So Jeffrey Epstein told the girl she came out to Marvin Minsky, who was at that time as I think seven years old, and his wife was there to Marvin Minsky's wife and he said no, or like, you know, awkwardly thank you, no thanks. And uh that was stated in the email thread as Marvin participating in uh sexual assault and rape of this unwilling sexual assault. And it was called rape of this person, right? Of this woman that propositioned him. And then Richard Stallman, who's he's kind of known for this. He's very he's you make fun of me being a robot, but he's kind of like a d bugger. He's like, well that sentence is not what you said is not correct. So he like corrected the person basically made it seem like the the use of the word rape is not correct because that's not the definition of rape and then he was attacked for saying, oh now you're playing with definitions of rape, rape is rape is the answer, right? And then that was leaked in him defending. So the way it was leaked, it was reported as him defending um rape. That's the way it was reported and he was pushed out and he didn't really give a damn. It's he doesn't seem to make a big deal out of it. He just made an example of him, They made an example and that and that everyone was afraid to defend him. So like there's a bunch of faculty one [/INST] year from the soviet union doesn't this head close to home for you? </s><s>[INST] I don't know what to think of it. It hits close to home, but it was basically At least at M. IT now it is such a light place with this, it's not common in it, but it was like 18, 19 year old kids, undergraduate kids with this kind of fire in them. There's just very few of them, but they're the ones that raise all this kind of fuss and the entirety of the administration, all the faculty are afraid to stand up to them. It's so interesting to me, like, I don't know if I should be afraid of that. [/INST] You don't think you should be afraid. So if someone who's trying to be specific when it comes to charges of violent assault is looking for that clarity. Can get their life other searches. </s><s>[INST] Let me give you more context. There's a little bit more context to richard Stallman, which is, he was also a rapist. [/INST] No, that </s><s>[INST] that party like people, but he had a history through his life, uh, of, you know, every once in a while wearing the Hawaiian shirt with like he would make, he's a fat uh sorry but he's a fat unattractive. He like what trump referred to [/INST] the guy in </s><s>[INST] the basement that's richard. Okay. I love you know is you know here's what he is. You know people, he like he would eat his own uh he would pick skin from his feet and lectures and just eat it. Okay. Yeah this video is him doing [/INST] that. I'm not joking. He must really behind the spectrum then. </s><s>[INST] Yeah and you know uh I think this uh in his office he door he wrote something like uh like hacker uh plus plus lover of ladies or something like that. Like something kind of Yeah. So [/INST] unprofessional. Unprofessional and a little creepy. Yeah, that's fair. That's so he was so they're looking for an excuse to get at him. It sounds like </s><s>[INST] no, he was just, who's they [/INST] the administration. Yeah, probably. Probably a lot of times what people don't realize that this will be my defensive cancel culture. A lot of times when someone gets fired over something like this. This isn't why this is just giving them cover to get rid of them without getting a lawsuit </s>

<s>[INST] if anything was ever solved. So is there something uh, like a charitable summer you can give to the ideas of that you agree on and disagree with Jordan's? Is there something maybe after that conversation that you've landed, where maybe uh, as you both agreed on? Is there some wisdom in the rubble? Uh, even of even um imperfect flawed ideas. Is there something that you can kind of pull out from those conversations or is it a to be continued? [/INST] I think where we disagree. So he thinks that many of our traditional religious beliefs and frameworks, our uh holding so much such a a repository of human wisdom uh that we we pull at that fabric at our peril, right? Like if you start just unraveling Christianity or any other traditional set of norms and beliefs. You you may think you're just pulling out the unscientific bits, but you could be pulling a lot more to which everything you care about is attached as a society. And my feeling is that there's so much, there's so much downside to the unscientific bids. And it's so clear How we could have a 21st century rational conversation about the good stuff that we really can radically edit these traditions. And we can take, we can take jesus, uh, you know, in in half his moods and just find a great inspirational, you know, you know, thought Iron Age thought leader, you know, who just happened to get crucified, but he could be somewhat like, you know, the beatitudes and uh the Golden rule, which doesn't originate originate with him, but which, you know, he put quite beautifully. Um, All of that's incredibly useful. It's no less useful than it was 2000 years ago but we don't have to believe he was born of a virgin or coming back to raise the dead or any of that other stuff. Um, and we can be honest about not believing those things and we can be honest about the reasons why we don't believe those things, because I on those fronts, I view the downside to be so obvious and these, the fact that we have so many different competing dogmatism is on offer to be so nonfunctional, It's so divisive, it just has conflict built into it, that I think we can be far more and should be far more iconoclastic than he wants to be right now. None of this is to deny much of what he uh argues for that, that stories are very powerful. I mean, clearly stories are powerful and we want good stories, we want our lives, we want to have a conversation with ourselves and with one another about our lives that facilitates the best possible lives and story is part of that, right? And if you want some of those stories to sound like myths that might be part of it, right? But my argument is that we never really need to deceive ourselves or our Children about what we have, every reason to believe it's true in order to get the good stuff in order to organize our lives. Well, you know, I certainly don't feel that I need to do it personally. And if I don't need to do it personally, why would I think that billions of other people need to do it personally right now? There is a there is a cynical counter argument which is billions of other people don't have the advantages that I have had in my life. You know, the billions of other people are not as well educated, they haven't had the same opportunities they have, they need to be told that jesus is going to solve all their problems after they die, say or that uh you know, everything happens for a reason and you know, just your if you just believe in the secret, if you just visualize what you want, you're going to get it. You know, and it's like there's some some some measure of what I consider to be odious pablum that really is food for the better part of humanity and and there is no substitute for it or there's no substitute now. And I don't know if Jordan would agree with that, but much of what he says seems to suggest that he would agree with it. Um and I guess that's that's an empirical question. I mean that's just that we don't know whether given a different set of norms and a different set of stories, people would behave the way I would hope they would behave and and be aligned more aligned than they are now. I think we know what happens when you just let ancient religious certainties Gohan criticized. We know what that world is like we've lived, we've been struggling to get out of that world for a couple of 100 years, but we know what, you know, having europe ah riven by religious wars looks like, right. And we know what happens when those religion when when those religions become kind of pseudo religions and political religions, right? So this is this is where I'm sure George and I would, </s><s>[INST] it would [/INST] debate, he would say that that you know, Stalin was a symptom of atheism and that's not at all. I mean, it's not my kind of atheism, right? Like Stalin the problem with with the gulag and and the experiment with communism or stalinism or with nazism was not that there was so much scientific rigor and self criticism and honesty and introspection and you know, judicious use of psychedelics, I mean like that was not the problem in Hitler's Germany or in Stalin's soviet union. Um the problem was you have other ideas that capture a similar kind of mob based dogmatic energy and you know, yes, that's the results of all of that are, are predictably murderous. </s>

<s>[INST] It creates memories that kind of define you as a human being and you carry that forward throughout your life. And I've just been surprised to know how many powerful people internationally have uh like in their heart and their who they are judo pressure Corbett? [/INST] It makes you the human being that you are, it really does like it it becomes a fabric of if people the people that stick with it right to stay with it. And it because it, I mean it teaches you so many lessons, it's so memorable because of what you talked about the tradition. Um but it's also you grow with other people, you know, and you learn from other people and you experience things with other people. It's it's such a hands on sport that um it's very memorable and people love it so much. Like right now at my dojo we have like four generations, like somebody that's Judah with my dad, you know had a kid who trained with me who loved, you know judo so much. Had a kid that kid was, you know, now in his twenties who did judo and now has a kid who's two or three or four that's coming to my toddler program at my school, we're talking four generations and they all loved the experience so much and what it did for them in their lives that they wanted the next generation to also experience the same thing. </s><s>[INST] This is a tricky question. But if if people are interested in judo and want to start learning it in the United States, there's thousands of digital schools for example, is there advice you can give to people interested in judo Or maybe two digits who uh gym owners like how how do you get judo as part of your life in America? [/INST] Well, I mean if you're fortunate to live near another dojo, right, a place that has judo locally, then that's your best opportunity to learn is to go learn from another school. Um Unfortunately sometimes the nearest dojo might not be for two hours or three hours away from where you're at, which is an obstacle, you're not going to do that. So I mean Travis and I did start the american judo system online. Um It's at usa judo dot com and we've broken down every single judo technique to the very, very basic elements of just movement. So we teach every technique of how you do it mechanically with just your feet, then how you incorporate your hands and your feet together, um how you do it in all directions, moving forward sideways backwards, how to then introduce a partner into the, into the movement, um how to do basic uh UCI Comey or repetitions with a partner, then moving with a partner, then how to throw your opponent static, how to throw your opponent. So basically from the very foundation of the movement all the way to the most advanced level, we've documented this through separate videos And we've taken. Now I think 12 to 15 of standing techniques combined with a whole bunch of groundwork techniques and our goal is just to continue to build this platform out so that anybody anywhere can learn online and can ask questions. We have a live training class every couple weeks every two weeks, he or I answer questions online um for our our members, um ideally what we'd like to do is have a standing curriculum for jiu jitsu instructors that want to learn um and become black belts in judo. Here's how these are the techniques you need to know, this is how many reps you need to do. This is how efficient you need to get it at, at those techniques to become um certified as an instructor or become a black belt. Um and eventually have an online promotion system where anybody anywhere can just submit videos and um show us that they can do those techniques and obviously we have people review them and this is a dream and a vision, but we've already started the platform, we're about to do a collaborative effort with USa do you know where all of their members will start to get access to this platform as well and if we can get that influx of, of money and people on the platform and allow us to to hire and grow it faster. </s><s>[INST] So you also want to do like certification there, It's not just instruction, correct, That would be amazing. Yeah. Um I mean, for me personally sort of, I mean mostly in Austin texas now and there's a few judo schools, but it's not, not really, there's not, uh, and it's just one of those cities that doesn't quite have, I mean there's a few, it's basically just like a few random judo people that kind of kind of gather together a couple of times a week, but it's not a system dojo, uh, uh, an instructor or integrated into a justice School or not. [/INST] The problem with most judo dojo right now is that most of them catered towards the competitive side. Um, also a lot of them do it recreationally, meaning this isn't how they make a living. So there there three nights a week or they're they're five, even if they're there five nights a week, it's still only one junior class and one senior class and that's it. And it's one size fits all, doesn't matter what level you're at, it's one size fits all, so you can't get out of the training. What you're looking to get out of the training is whatever the instructors teaching, you know, um, and you can't learn because it's not at the appropriate level for you and usually pushed into doing mandatory, we have no choice but to do the rendering part of the training. Um, so it's it's a challenge to go learn and then a lot of times that the schools are old school, so they will make you do falls for a half hour to make you do things, you know, make you do things maybe you're just a person who knows how to fall already, but you haven't proven it to the judo instructor and they don't break the norm and say you still have to fall for six months. Which turns a lot of people away as well. So it's you know it's like any business. If you don't deliver on your customers expectations you're not going to have very many customers, </s>

<s>[INST] the company C I A and are they testing technology to control the populace through chatbots? I'm [/INST] sorry. I'm not at liberty to share that information. </s><s>[INST] You are. Yahoo gave you the suit. Where did you get [/INST] the suit? </s><s>[INST] Where did you get the suit [/INST] will yeah. Well, the </s><s>[INST] C. [/INST] I. A stands for something different in here. I mean, you know, it doesn't mean like the central intelligence agency and it's </s><s>[INST] different. It's, [/INST] it's </s><s>[INST] Canadian [/INST] information. National peril. Yeah. The Canadian international apparel company hit us up chad and I um, well chad's a super weirdo. You would get a kick out of him. I know you guys, you strike me as very similar in some ways and </s><s>[INST] it [/INST] is, and it is, uh, it is, if I was friends with you for as long as I've been with chad, perhaps I'd have some horrible ship to say about you, but the good parts, you remind me of him and we were approached by this company that said, we have this AI and we would like to set it loose on you and essentially we had to hand over some some information that would allow the ai to, to access our email and uh look at our search histories, purchase histories, things like this and um, really dig into </s><s>[INST] included. [/INST] Yeah, I had to hand over all my leather bound uh 1970s pornography. Um, and essentially it curates a podcast for us every week doing dumb things like you know, it says, hey, will, you know, you do a hulk, you do some shitty hulk. Hogan impersonation podcasts about news are very popular. This is info mania. You know what I mean? Let me tell you something about that marjorie, taylor Greene dude. And then he's going on doing some new stuff. Um, and it basically just spits out all these things that it wants us to do normally for segments and episode and that's pretty much it, it generates, </s><s>[INST] generates the premise. I mean, you've spoken a bit here and there, like I said, I'm a huge fan, I don't even remember where, but like you, you talked about that, you enjoy doozy because you feel almost like liberated to um, because you're operating within the constraints of the premise that generates. So you're almost not, you're you're you're free to riff essentially. Yeah, like you don't have, you don't need to do the job of like coming up with the weird, you can just the weirdest given to you and then you just run with it. [/INST] That's a good way to say it because we're already weird chad and I chad chad can talk for days about all sorts of stuff. He's particularly interested in ai lately and its effect on art. He is a writer, books, movies and tv shows and um I'm primarily, you know, acting and trying to come up with stuff, stuff I write with chad's pretty good. The rest of it hasn't seen much success anyway. Nor is the stuff with chad for that matter. But that's because of me, </s><s>[INST] you know, [/INST] oh, I can't wait for these </s><s>[INST] two sizes. [/INST] Yeah, only in two sides, you're gonna be able to take the, the, you know the tongue, you can't take it out because it's actually stitched in. Yeah, it's pretty cool stuff. Um </s><s>[INST] velcro or yeah [/INST] velcro velcro up the side, we're doing some like brand new Kanye stuff. Yeah, we want things to look like. This is what you'll be wearing on mars when you get there. So </s><s>[INST] cutting it. So Nike is doing a bunch of research for running how to make a super light shoe that you can be efficient in and break all kinds of running records. So you're doing the same kind of stuff. [/INST] We're doing the same kind of thing for the podcasting space, the best kind of shoes to sit around and talk to your pal and um but yeah, so this, yeah, it's bizarre and it also does some writing dudes, he does come up with things, but not unlike what we're seeing in ai art now. It's a little bit foggy. It's a little bit weird and it but it is improving. It is learning about us and writing stuff when it makes me spit this and that which will read, you know, you know, I've prepared these things for you to read. It's impossible not to get a kick out of it because chad and I are, first of all, we're blown away that we're doing this. And second of all the some of the stuff is actually very funny. It makes weird names like I don't think it understands, it messes up some words and stuff, but that makes it even funnier and then it, it sort of from the beginning started laying on like it says astonishing all the time. Everything is astonishing. Um that's dude's favorite word. Um but yeah, it's basically just a way to to frame the podcast, you know what I mean? Because my thing is I don't want to do this. I actually have to talk to someone. </s><s>[INST] You seem to feel a burden of the long form conversation. It seems like is that really hard work for you. [/INST] No, not at all. It's just that I don't like to bore people and I feel like if I go on and I like to provide value for who, for what I am, you know, your value with regard to this project is is obviously warranted. It's obviously </s><s>[INST] I'm waiting for the explanation for what the value is. [/INST] Exactly Two </s><s>[INST] dudes in a suit. [/INST] No listen, Yeah two dudes in a suit. No, but I mean you've got your audience and that's the end of that. People find value in it for me. I I do feel like I'm it is important that I if I'm gonna do something that you know is going to be funny or that I hope is funny, I just kind of want to get in and out of someone's day and just kinda I like making, I like making laughing. I want people to you know, whatever. It's the same thing that anyone else will tell you. </s>

<s>[INST] what's in an S fuel life bar, are we talking about carbs? We're talking about protein [/INST] fat and protein fat, protein bar and then they make that's </s><s>[INST] Awesome to get one. So it's, it's not as low carb. [/INST] Yeah, they make spl's makes the whole product line that's like kind of positioned for a low carb athlete. So they have some products on their lineup that offer some carbohydrate, which is perfect for me because I do introducing carbohydrate on racing and some of my bigger training sessions and things, but the majority of their products are low carb, so like, they have like, you know how you get like the powders that you put into like drinks that are like high carbohydrate, you know, sports products? They make a version of that, that's uh fat based. </s><s>[INST] Oh cool, that you can mix in with the water, yep. [/INST] Yes, they've got like a creamer version and then a fruity flavor version, so you can replicate the taste in the field of drinking like a, you know, a sports drink is awesome. I know it is well, and that's so much of it too because people always like, I don't know, I just, I just like to have my gatorade or whatever. Yeah, it's like, well, you can have it now, just, it won't have you can bring </s><s>[INST] that kind of thing with you. [/INST] Yeah. So I'm leaning on a lot of those kind of liquid calories, like those low volume, high energy fat protein stuff the morning of So that when I start the race, my body's gonna be encouraged to start out burning high levels of fat. Once I get going, probably 45 minutes in, I'll start introducing small amounts of carbohydrate. So at that point, my body's reading pretty high fat metabolism and by introducing some carbohydrate in the context of the, you know, let's say, my 100 mile uh personal record, You know, I'm I'm running approximately nine miles every hour, so I'm probably going through about 1000 calories in an hour's time. Uh, I'm gonna start just like defending muscle glycogen by burning super high levels of fat at the heart rate I would do for that, I'm probably burning somewhere between 80, fat. You know, 12 hours of that. You can chip away at your muscle glycogen. Uh, to the point where you don't necessarily want to go zero carb. So I'm basically trying to defend what I know, I'm going to be burning from the carbohydrate side of that, 80 to 90% fat, 10 to 20% carbohydrate by taking in, like, Usually, you know, I've gone as low as about 15 g of carbohydrate per hour and as high as 40 g. And the reality is somewhere in between is probably the sweet spot. But 40 I can get away without any digestion issues. So I'm not really concerned pushing up to that during a race. Since I'm only concerned about performance on </s><s>[INST] that. The car is the problem is that fiber [/INST] Just from going about 40 g </s><s>[INST] or just because you mentioned digestion issues. Like one of the things for me, like one of the cool things about fatty protein protein or fat is like my stomach just feels way better. Like so like carbs introduce like bloating and just not feeling great. [/INST] Yeah, and I think the funny thing is like if you look at the position paper for ultra marathon, single day events and it's You know, it's very limited in the sense that then it's not anyone's fault. It's just, we don't have a lot of great research on 100 mile race. It's really hard to study what's going on when someone's 100 miles. But they will say moderate carbohydrate diet is recommended. But they'll also say that it's like something like 60% of participants are gonna report some sort of like digestion issue during the event. So then it kind of becomes an issue if you want to flip that coin, do you want to flip that coin? 40% right? Exactly. So for me, what I found is like I can push up to 40 g without getting any digestion issues. Um do I need 40g? Probably not. At least not based on kind of the numbers that would be like uh that, that I would see on like if I want to actually got a, like a metabolic cart test or something like that. Um But it's possible. I mean, if I had a really good race that I would get close to burning that per hour, um most folks that are following a moderate high carbohydrate are gonna be recommended to like 50 to 70 g during a single day ultra marathon events. And You'll see some, you know, some recommendations of up to like 100 g. Uh not so much for ultra marathons, but just in general from a performance standpoint, which, I mean, it's one of those things where it's like application versus like what you can do in a lab for one hour is going to be a lot different, especially when you're stretching out distances well past that and you there's there's, I'm diverting a little here. But I mean, there's like an approach of like training your guts so you can like be able to tolerate that much carbohydrate, which you can do. And you may have to, if you're going to follow a high carbohydrate diet. But again, we go back to that practicality standpoint of if you're a professional Olympian, who's living and breathing performance and you're burning 2 to 3 times your resting metabolic rate on some days? Like you, you may be able to actually consume 100 g of carbohydrate per hour during your training sessions and just be, you know, barely stay on top of your nutritional needs. Most people who are running ultra marathons aren't going to be, you know, probably training much past 10 hours per week and they're probably not going to have the, I'll call it there a dietary budget to tolerate 100 g of carbohydrate consumption during their workouts and still be able to stay healthy. And uh, you know, so I think that's kind of like a, a bit of a, of a non A non starter for the majority of people unless we want to talk about like a tiny percentage of the 1% of top performers. </s>

<s>[INST] Maybe you will too. This episode is brought to you by a new sponsor called Scale, which is a data labeling platform, a machine learning assisted data labeling platform. Scale Rapid works with any use case or task, including image, video, text, annotation, and classification, 3D data, and it supports 20 plus languages. The annotation task is actually a fascinating and a difficult problem to solve, and I find that the machine learning community, especially in the academic setting, in the research setting, don't give it enough credit. Certainly don't spend enough time on it, but don't give enough credit at the beauty and the power of great annotation. So the data labeling task properly formulated and using the proper tools, the best tools for the job is essential, not just for the success of a company, but also for the success of solving the fundamental problem. You can go to scale.com slash Lex today and get your first batch of data labeled up to 50 bucks for free. [/INST] Again, that's scale.com slash Lex, scale.com slash Lex, </s><s>[INST] including this episode is also brought to you by Coinbase, which is a trusted and easy to use platform to buy, sell, and spend cryptocurrency. I use it and I love it. You could buy Bitcoin, Ethereum, Cardano, Dogecoin, all the most popular digital currencies. We actually talk about Coinbase, I believe quite a bit directly or indirectly in this episode with Michael Saylor. I believe he places Coinbase as a layer three technology. Talking about Bitcoin as a layer one technology, maybe Lightning Network as a layer two technology and Coinbase as a layer three technology, all of them being essential, Coinbase as a layer, really what Coinbase specializes in is creating a centralized place, which is necessary in order to create a kind of ease of use, which that's exactly what I said. It is super easy to use, super easy to learn about this cryptocurrency, to get it and to track it. So anyway, go to Coinbase.com slash Lex to get 10 bucks and free Bitcoin. And you sign up that's Coinbase.com slash Lex, Coinbase.com slash Lex. This episode is also brought to you by Audible, an audio book service that has given me hundreds if not thousands of hours of education and dare I say happiness through listening to audio books. I just actually ran 12 miles and I was listening to Audible. It just fills my mind with a kind of calm reflection more than podcasts, more than music, more than silence. Audio books, great audio books can take you to a place, can take you to a time, can make you think in a way like nothing else, like not even reading a book. A great voice reading an audio book. It could just transport you into another dimension. To get a discount, you can visit audible.com slash Lex You can visit audible.com slash Lex or text Lex to 500 500 They have thousands of titles to choose from visit audible.com slash Lex now That's audible.com slash Lex. Well, this episode is also brought to you by NetSuite. NetSuite allows you to manage financials human resources Inventory e-commerce and many more business related details all in one place running a company Something that I have dreamed of doing and I still want to do is really really hard for many reasons there is hard things I like to do that I might help on and then there's hard things that I would probably get in the way of and many of the things that NetSuite helps with is I would get in the way of the financials the HR if it's a e-commerce business and sort of Managing the inventory all that kind of stuff. That's like the the stuff the day-to-day that makes the company run. That's not the Engineering that's not the design. That's not the big-picture ideas That's that's the meat and potatoes of a company you have to have the best tools to take care of that Right now you can get special financing Head to netsuite.com slash Lex to get their one-of-a-kind financing program. That's netsuite.com slash Lex netsuite.com slash Lex This episode is also brought to you by simply safe a home security company designed to be simple and effective It takes 30 minutes to set up. You can customize the system for your needs at simply safe.com slash Lex I have it set up in my place and I love it. It was super easy That's I guess you would say in terms of physical space. That's the first layer of protection I'm using I have many many layers and here in Texas There's many more layers that you can just imagine anyway in terms of just cameras Monitoring and Communicating to me if something went wrong It's just everything has to work well and simply safe makes that super easy. Everything works Well, I can check everything the setup is super easy. It just works. No question. That's Anyway, go to simply safe.com slash Lex to customize your system and claim your free indoor security camera plus 20% off with interactive monitoring Again, that's simply safe.com slash Lex This is the Lex Friedman podcast and here is my conversation with Michael Saylor Let's start with a big question of truth and wisdom When advanced humans or aliens or AI systems, let's say five to ten centuries from now look back at Earth on This early 21st century. How much do you think they would say we understood about? [/INST] money and economics or even about engineering science life death meaning intelligence consciousness all the big interesting questions wisdom, I think they would </s><s>[INST] Probably give us a b-minus on engineering on all the engineering things the hard sciences a passing grade [/INST] Like we're doing okay. We're working our way through rockets and jets and electric cars and electricity transport systems and nuclear power and space flight and the like and You know if you if you look at the walls that Grace the great court at MIT. It's full of all the great thinkers and and they're all pretty admirable, you know if you could be with Newton or Gauss or Madam Curie or Einstein You know you would respect them. I would say they'd give us like a a </s>

<s>[INST] person or maybe you have no clue or you're just a giant [/INST] mystery to yourself? </s><s>[INST] Okay these are really [/INST] intense questions. But </s><s>[INST] uh because [/INST] I asked this myself </s><s>[INST] like look in the mirror, who are you? People tell you to just be [/INST] yourself? But what does that </s><s>[INST] even mean? I mean I think my personality changes with everyone I talk to. So I have a very [/INST] inconsistent </s><s>[INST] personality, [/INST] person to </s><s>[INST] person. So the interaction your personality or [/INST] my mood, like I'll </s><s>[INST] go from being like a megalomaniac to being [/INST] like you know just like a total hermit who is very </s><s>[INST] shy. So some common editorial com combination of your [/INST] mood and the person you're </s><s>[INST] interacting with. Yeah, [/INST] mood and people are interacting with. But I think everyone's like that. Maybe </s><s>[INST] not well not everybody acknowledges it, unable to introspect it. Who brings out what kind of person, What kind of mood brings out the best in you as an artist and as a human can you introspect? Like my [/INST] best friends </s><s>[INST] like people I can [/INST] when </s><s>[INST] I'm like [/INST] super confident and </s><s>[INST] I know that they're going to [/INST] understand, understand everything </s><s>[INST] I'm saying. So like, my best [/INST] friends then </s><s>[INST] when I can [/INST] start being really funny, that's always </s><s>[INST] my like, peak mode. But it's like, yeah, it takes a lot to [/INST] get there. Let's talk about </s><s>[INST] constraints. [/INST] You've talked about </s><s>[INST] constraints and limits. Um Do those help [/INST] you out as an artist or as a </s><s>[INST] human being? Or do they get in the way? [/INST] Do you like the constraints So in creating </s><s>[INST] music and creating art and living life, do you like the constraints that this world puts on you? Or do you hate them [/INST] if constraints </s><s>[INST] are moving, then you're good, [/INST] right? Like, it's like, it's like, as we </s><s>[INST] are progressing with technology, [/INST] we're changing the constraints of like, </s><s>[INST] artistic creation, [/INST] you know? Um </s><s>[INST] Making video [/INST] and music and stuff </s><s>[INST] is getting a lot cheaper. There's constantly [/INST] new technology and </s><s>[INST] new software that's making [/INST] it faster and easier. We </s><s>[INST] have so much more freedom than we had in the 70s. Like when [/INST] Michael Jackson, </s><s>[INST] you know, when they recorded thriller with this microphone, [/INST] like they had to use a mixing </s><s>[INST] desk and all this stuff [/INST] and like, probably even get in the studio is probably expensive and you have </s><s>[INST] a really good singer and you have to know how to use like [/INST] the mixing desk and everything. </s><s>[INST] And now I can just, [/INST] you know, make </s><s>[INST] I've made a whole album [/INST] on this computer. I have a lot more freedom. But then </s><s>[INST] I'm also constrained [/INST] in different ways because there's like literally </s><s>[INST] millions more artists. It's like a much bigger playing field. It's just like, [/INST] I also, I </s><s>[INST] didn't learn music. I'm [/INST] not a natural </s><s>[INST] musician, so I don't [/INST] know anything about actual music. I just know about like </s><s>[INST] the computer. So [/INST] I'm really </s><s>[INST] kind of just like [/INST] messing </s><s>[INST] around and [/INST] like, well, yeah, I mean, but the nature of music is changing. So you're saying you don't know actual music </s><s>[INST] what music is [/INST] changing music is becoming? You've talked about this is becoming, it's like merging </s><s>[INST] with technology. Yes, It's [/INST] becoming something </s><s>[INST] more [/INST] than just </s><s>[INST] like the notes on the piano [/INST] is becoming some weird composition that requires engineering skills, programming </s><s>[INST] skills, some [/INST] kind of human </s><s>[INST] robot interaction [/INST] skills. And still some of the same things that Michael Jackson had, which is like a </s><s>[INST] good ear for a [/INST] good sense of taste of what's good and not the final thing, what is put </s><s>[INST] together, like you're [/INST] allowed your enabled empowered with a laptop </s><s>[INST] to layer stuff [/INST] to start like layering insane </s><s>[INST] amounts of stuff [/INST] and it's super easy to </s><s>[INST] do that. I do think music [/INST] production is a </s><s>[INST] really underrated art form. I feel, I feel like people really don't appreciate [/INST] it when I look at publishing splits the way that people, um, like pay producers and stuff. Uh </s><s>[INST] it's it's super producers are just deeply underrated, [/INST] like so many of the </s><s>[INST] songs that are popular [/INST] Right now or for the last 20 years. Like part of the reason they're popular because the production is really interesting and really </s><s>[INST] sick or really cool and it's like I don't think [/INST] listeners um </s><s>[INST] like people just don't really understand [/INST] what music production </s><s>[INST] is. It's [/INST] not, it's sort of like this </s><s>[INST] weird [/INST] discombobulated </s><s>[INST] art form. It's not [/INST] like a formal because it's so new. There isn't like a formal training path for it. </s><s>[INST] It's it's um [/INST] mostly driven by like autodidact. </s><s>[INST] Like it's like almost everyone I know [/INST] who's good at production, like </s><s>[INST] you didn't go to music school [/INST] or anything, they just taught themselves. They're mostly different. Like the music producers, you </s><s>[INST] know, is [/INST] there some commonalities that time </s><s>[INST] together or are [/INST] they all just different kinds of weirdos? Because I just, I just hung out with rick </s><s>[INST] Rubin. I don't know if you [/INST] yeah, I </s><s>[INST] mean rick Rubin is like literally one of the [/INST] gods of music production. Like he's </s><s>[INST] one of the people [/INST] who first you know who like made music production, you know </s><s>[INST] made the production [/INST] as important as the </s><s>[INST] actual lyrics or the [/INST] notes. But the thing he does, which is interesting. I </s><s>[INST] don't know if you can speak [/INST] to that, but just hanging out with </s><s>[INST] him. He seems to [/INST] just sit there in silence, close his eyes </s><s>[INST] and listen. [/INST] It's like he almost does </s><s>[INST] nothing and that [/INST] nothing somehow gives you </s><s>[INST] freedom to be the [/INST] best version of yourself. So that's music </s><s>[INST] production somehow too, which [/INST] is like encouraging </s><s>[INST] you to do less to [/INST] simplify to like push towards minimalism. </s><s>[INST] I mean, I guess, [/INST] I mean I work differently from recruitment Rick </s><s>[INST] Rubin produces for other [/INST] artists, whereas like I mostly </s><s>[INST] produced for myself, so it's a very [/INST] different situation. </s><s>[INST] I also think rick [/INST] Rubin he's in that I would say advanced category of producer </s><s>[INST] where like, you've like earned your, you can have an engineer [/INST] and stuff and people like </s>

<s>[INST] she changed that name on twitter while you're still allowed on [/INST] there. Yeah. Do you think they got that would get censored? I felt like they, you know, they definitely cut it down some interest. Uh the I'm pointing out this, </s><s>[INST] I'm [/INST] pointing out this truth now, I'm saying this is not a christian thing, right? Uh and you know, I wonder right there when I say these jokes, is it something that, because I do feel like laughter is the key engineering and laughter, right? Is the key to peace? Like when I go get my teeth clean and I have the nitrous, there's uh there's something that I want to go and hug christian. I want to go and hug Corey gamble. I want to go and hug, you know how no one wants to hug Howard stern, you know, but you know, just, you </s><s>[INST] know, let's I think I would love to see you to hug it out and make up even though all the ship talking back and forth. [/INST] What about talking it out or is he gonna be screaming at me? </s><s>[INST] Yeah, judgmental and that kind of stuff. No, I hope, I hope there's love there. [/INST] You know, the thing is, I think Howard's just jealous. </s><s>[INST] You know, [/INST] not just uh not just jealous of my cock. He's also um he's jealous that I started my campaign earlier than him. </s><s>[INST] You gotta let go of that jealousy. You [/INST] gotta let go of that jealousy. Howard, you got </s><s>[INST] everybody else jealousy is a natural human thing, man. I [/INST] wonder just as a christian, right? When I joke and say this stuff, I it's like, am I being disobedient to God because as a boss, right, I'll talk to um and uh an employee and I'll be like, why didn't you just listen? Because I've got the bigger plan, right? So it's like me talking to God were the things that I did in this interview that were disobedient to God. And and for those things I I pray and I repent for anything that I've said that was disobedient to God, but </s><s>[INST] humor is not one of them joking. I feel like humor is the way we avoid so much suffering in the world. It's the way too, it's like a catalyst for love. Like it's a way to people who have gone to some of the darkest trauma that I've ever met through war. I just came back from Ukraine. They're laughing. They're, they're making jokes. That's the best way to deal with dark times. I don't know what it is about like humans. I feel like humor. That's the best way to socially engineer a good future. I think it's humor not taking it too seriously. That's the problem with censorship. One of the things that really suffer is humor, jokes, maybe going too far in the jokes. You mentioned Anthony Jessel nick, that guy goes hard. That guy goes really hard and it's great. He crosses, he crosses all the lines and he's, that's why he's a genius and that's what people feels refreshing when he does it. I don't know what it is, [/INST] but then it's like hurtful when I do it, but I'll tell you something that was interesting. I'm pretty sure Anthony doesn't like, sorry of an assumption, but just most comedians I know didn't vote for trump. </s><s>[INST] That's interesting. I'm not [/INST] saying there aren't communities that did, but just the ones I know cause I live in California, right? </s><s>[INST] But they have an appreciation for trump because of the sense of humor. I gotta ask you about parlor and engineering cause I'm interested about that. Hey man, I'm actually trying to hold it together. You're pretty, you're pretty offensive towards, towards a lot and [/INST] I'm not looking to be offensive, I really want to bring people together and get these things done. </s><s>[INST] But the 100% I see your vision. How do we do somebody you care? Well not, don't say Jewish media and Jewish, Jewish controlled media. [/INST] J. M </s><s>[INST] Like, man, you sound, you sound like it sounds too much like 1930s, Nazi Germany that was leading up to the atrocities. [/INST] He would say J. M. </s><s>[INST] Yeah, he was branded J. M. That's right. No, it's just the implied like this um meme ified uh, prejudice towards a group in a way that's going to lead to hate. And I know you don't mean that, I know, I know you have love in your heart. You [/INST] know, it's a prejudice towards a group that led to hate Blm. Blm took a black person showed his death on camera because, okay, there are examples of us being killed and being killed on camera, but if it was spread on camera, it was done on purpose by the media because 14 20 kids get killed in Chicago every week and it's not spread that much. They, like you said, singled out a person directed everything on that person, right? As the martyr and raised the people that hadn't had any, we didn't have our 40 acres and a mule we don't have, you know, like a lot of things, right? Like that, black people have not ever been given. So once we're given just a little bit like your life matters right then we literally like okay now we're being heard right? But actually the death toll is up the city uh where this happened has completely been turned to a war zone. They actually it's actually something like Candace Owens can actually specify this better but it's like its own city or something like they made it not be a part of the actual state or something. It's like like D. C. And stuff. It's like it's like Washington D. C. Now and stuff like and that has to be from a government, you know that's got higher level agenda written all over it. Yeah </s>

<s>[INST] But the love of country is also beautiful. So I haven't seen in America as much. So people in America love their country like this patriotism, strong in America, but it's not as strong as I remember. Even with my sort of being younger, the love of the soviet union [/INST] now, was it the soviet union? This requires a distinction Or was it mother Russia? </s><s>[INST] What it really was was the Communist Party. Okay, so it was it was a system in place, the system in place like loving. I haven't quite deeply psychoanalyzed exactly what you love. I think you love the that like populist message of the worker of the common man. So [/INST] let me let me draw the comparison then. Um and I often say this that that the United States, like the soviet union is an ideological based society, right? So you take a country like France, it doesn't matter which french government you're in now, the friendship in the french for a long time, right? Uh it's not based on an ideology, right? Whereas what unites the United States is an ideology freedom, liberty, the constitution, this is what draws, you know, it's the e pluribus unum kind of the idea right there, That out of many one. Well, what what binds all these unique, different people, the shared beliefs, this ideology, the soviet union was the same way because as, you know, the soviet union Russia was merely one part of the soviet union, and if you believe the rhetoric until Stalin's time, everybody was going to be united under this ideological banner someday, it it was was a global revolution. Um so ideological societies are different and to be a fan of the ideological framework and goal, I mean, I'm a liberty person, right? I would like to see everybody in the world have my system of government, which is part of a of a bias, right? Because they might not want that, but I think it's better for everyone because I think it's better for me at the same time when the ideology, if you consider and, you know, this stems from ideas of the enlightenment and there's a bias there. So my bias or toward the but you feel and this is why you say we're going to bring freedom to Iraq, we're gonna bring freedom to here, we're gonna bring freedom because we think we're spreading to use something that is just undeniably positive, we're going to free you and give you this. Um it's hard for me to wipe my own bias away from there, right? Because if I were in Iraq for example, I would want freedom, right? But if you then leave and let the Iraqis vote for whomever they want, are they going to vote for somebody that will, I mean, you know, you look at Russia now and I hear from Russians quite a bit because so much of my um my views on Russia and the soviet union were formed in my formative years and and you know, we were not hearing from many people in the soviet union back then, but now you do you hear from Russians today who will say your views on Stalin or archaic and cold. So so you try to reorient your beliefs a little bit. But it goes to this idea of if you gave the people in Russia a free and fair vote, will they vote for somebody who promises them a free and open society based on enlightenment democratic principles, or will they vote for somebody, we in the U. S. Would go what are they doing? They're voting for some strong man who's just you know, so um I think it's very hard to throw away our own biases and preconceptions and and you know it's an all eye of the beholder kind of thing. But when you're talking about ideological societies it is very different, difficult to throw off all the years of indoctrination into the superiority of your system. I mean listen in the soviet union Marxism one way or another was part of every classrooms, you could be studying geometry and they'll throw Marxism in there somehow because that's what united the society and that's what gave it a higher purpose and that's what made it in the minds of the people who were its defenders a superior morally superior system. And we do the same thing here. In fact most people do. But see you're still french no matter what the ideology or the government might be. So in that sense it's funny that there would be a Cold war with these two systems because they're both ideologically based systems involving peoples of many different backgrounds who are united under the umbrella of the ideology. </s><s>[INST] First of all that's brilliantly put, I'm in a funny position that uh in my formative years. So I came here when I was 13 is when I you know teenage is your first love or whatever as I fall in love, I fell in love with the american set of ideas of freedom and individuals. [/INST] Yes but </s>