Datasets:

ianiket23

/

podcast_llama_chat_format-5k

like 0

<s>[INST] you know, you've, uh, you've also added this, the science and have a paper on the musical accompaniment to the psychedelic experience is fascinating. [/INST] And we found basically that the about the same effect, even by a trend not significant, but a little bit better than effect, both in terms of um, subjective experience and long term, whether it helps people quit smoking. Just a little tiny non significant trend, even favoring the novel playlist with the tibetan singing bowls and, and the gongs and didgeridoo and all of that. And so, you were just saying, okay, we can deviate a little bit from this, like, what goes back to the 19 fifties of this method of using classical music as part of the psychedelic therapy, but they're listening to the music and they're not playing DJ in real time. You know, it's like, you know, they're just be the baby, you're not the decision maker for today. Go inward trust, let go be open. And pretty much the only interaction like that were, therefore, is to deal with any anxiety that comes up. So, guide is kind of a misnomer, in a sense, it's we're more of a safety net. And so, like tell us if you feel some butterflies that we can provide reassurance, ahold of their hand can be very powerful. I've had people tell me that, that was like the thing that really just grounded them. </s><s>[INST] Can you break apart trust? Let go be open. Uh what, uh, in a sense, how would you describe the experience, the intellectual and the emotional approach that people are supposed to take to really let go into the experience? [/INST] Yeah, so, trust is trust the context. Trust. The guides, trust the overall institutional context. I see it as layers of, like, safety, even though it's everything I told you about the relative bodily safety of cities have nonetheless, we're still getting blood pressure throughout the session, just in case we have a physician on hand who can respond just in case we're literally across the street from the emergency department just in case, you know, all of that, you know, </s><s>[INST] privacy is another thing you've talked about just trusting that you're and whatever happens is just between you and and the people in the study, [/INST] Right? And hopefully they've really gotten that by that point deep into the study that like they realize where do we take that seriously and everything else? You know? And so it's really kind of like a very special role you're playing as a as a researcher or guide and and hopefully they have your, your trust and so, you know, and trust that they can be as emotional, everything from laughter to tears. Like that's going to be welcomed. We're not judging them. It's like it's a therapeutic relationship where you know, this is a safe container. It's a safe space, a lot of baggage that term, but it truly is. It's a safe space for that for this type of experience and to like so trust, let's see, let go. So that relates to the emotional like you feel like crying cry, you feel like laughing your gas off laugh. You're a sof, you know, it's like all the things actually that sometimes it's more challenging with a recreation. Someone has a large recreational use. Sometimes it's harder for them because people in that context and understandably. So it's more about holding your shit, someone's had a bunch of mushrooms at a party, maybe they don't want to go into the back room and start crying about this, these thoughts about the relationship with their mother and they don't want to be the drama queen or king that bring their friends down because their friends are having experienced too. And so they want to like compose, you know, and also </s><s>[INST] just the appearance in social settings versus the so like prioritizing how you appear to others versus the prioritizing the depth of the experience and here in the study, you can prioritize the experience, [/INST] right? And it's all about like you're the astronaut and we're, there's only one astronaut were ground control and I use this often with um I have a photo of the space shuttle on a plaque in my in my office and I kind of use often use that as an example. It's like we're here for you, like we're a team but we have different roles. It's just like you don't have to like compose yourself, like you don't have to be concerned about our safety. Like we're playing these roles today and like yeah, your job is to go as deep as possible or as far out whatever your analogy is like as possible and we're keeping you you safe and so yeah, and you really the emotional side is a hard one, you know, because you really want people to like if they go into realms of subjectively of of despair and sorrow like yeah, like cry, you know like it's okay, you know? And especially if someone you know more macho and you know you want this to be the place where they can let go and and and again something that they wouldn't or shouldn't do if someone was to theoretically use it in a in a social setting. And like in also these other things like even that you get in those social settings of like yeah, you don't have to worry about your wallet for being taken advantage or for obsession for a woman sexually assaulted by some creep at a concert or something because they're you know, they're laying down </s><s>[INST] Being four million sources of anxiety, their external versus internal. So you can just focus on your own like the beautiful thing that's going on in your mind [/INST] and even the cops at that layer, even though it's extremely unlikely for most people, the cops would come in and bust them right with. Like even at that theoretical like that one in a billion chance, like that might be a real thing psychologically in this context we even got that covered this is that we've got d a approval like you are this is okay by every level of society that counts, you know, that has the authority. So it's so go deep trustee, you know, trust the setting, trust yourself um you know, let go and be open. So in the experience and this is all subjective and by analogy, but like if there's a door open it, go into it. If there's a stair well go down it or stairway, go up it. If there's a monster in the mind's eye, you know, don't run, approach it, look in the eye and say, you know, let's talk, yeah, what's up? What are you doing here? Let's talk turkey, You know? </s>

<s>[INST] but your your senses are Galaxies not teaming with life. [/INST] Yeah, our Galaxy, Our Milky Way Galaxy with several 100 billion stars and potentially habitable planets is not teeming with intelligent life. Intelligent. Yeah, I wouldn't well I'll get to the primitive life, the bacteria in a moment, but you know, we we may well be the only ones in our Milky Way Galaxy at most a handful I'd say, but I'd probably side with the school of thought that suggests we're the only ones in our own galaxy just because I don't see human intelligence as being a natural evolutionary path For life. Um I mean there's a there's a number of arguments. First of all, there's been more than 10 billion species of life on earth in its history. Uh nothing has approached our level of intelligence and mechanical ability and curiosity. You know, whales and dolphins appear to be reasonably intelligent, but there's no evidence that they can think abstract thoughts that they're curious about the world. They certainly can't build machines with which to study the world. Um So that's one argument, secondly, we came about as early hominids only four or five million years ago, and as homo sapiens only about a quarter of a million years ago. So for the vast majority of the history of life on earth, an intelligent alien zipping by earth would have said there is nothing particularly intelligent or mechanically able on earth. Okay. Thirdly, it's not clear that our intelligence is a long term evolutionary advantage. Now, it's clear that in the last 100 years, 200 years we've improved the lives of millions, hundreds of millions of people, but at the risk of potentially destroying ourselves, either intentionally or unintentionally or through neglect as we discussed before. </s><s>[INST] That's a really interesting point. Which is, it's possible that there huge amount of intelligent civilizations have been born even through our galaxy, but they live very briefly and they flash bulbs and they play, it's like [/INST] that brings me to the fourth, the fourth issue. And that is the, you know, the fermi paradox if they're comin where the hell are they? You know, notwithstanding the various Ufo reports in Roswell and all that. They just don't meet the bar. They don't clear the bar of scientific scientific evidence, in my opinion. Okay, so, you know, there's there's no clear evidence that they've ever visited us on earth here. So, and, you know, study has been Now the search for extraterrestrial intelligence has been scanning the skies and true, we've only looked a couple of 100 light years out and that's a tiny fraction of the whole galaxy, a tiny fraction of these 100 billion plus stars. Nevertheless, you know, if if the if the galaxy were teeming with life, especially intelligent life, you'd expect some of it to have been far more advanced than ours. Okay. There's no special, nothing special about when the industrial revolution started on earth. Right. The chemical evolution of our galaxy was such that billions of years ago, nuclear processing and stars had built up clouds of gas after their explosion that we're rich enough and heavy elements to have formed earth like planets, even billions of years ago. So there could be civilizations that are billions of years ahead of ours. And if you look at the exponential growth of technology among Homo sapiens in the last couple of 100 years and you just project that forward. I mean, there's no telling what they could have achieved even in 1000 or 10,000 years, let alone a million or 10 million or a billion years. And if they reach this capability of interstellar travel and colonization, then you can show that within 10 million years or certainly 100 million years you can populate the whole galaxy alright. And they, you know, so then you don't have to have try to detect them beyond 100 or 1000 light years, they would already be here, </s><s>[INST] do you think as a thought experiment, do you think it's possible that they are already here, but we humans are so human centric that we're just not like our conception of what intelligent life looks like is. Um We don't want to acknowledge it. Like what if trees? Right. Right. Like, Okay. I guess the in the form of a question, do you think we'll actually detect intelligent life if it came to visit [/INST] us? Yeah, I mean, it's like, you know, you're an ant crawling around on the sidewalk somewhere. And do you notice the humans wandering around Exactly and the empire state building and, you know, rocket ships flying to the moon and all that kind of stuff? Right. It's conceivable that we haven't detected it and that we're so primitive compared to them, that we're just not able to do? So </s><s>[INST] if you look at dark energy, maybe, [/INST] yeah, maybe we </s><s>[INST] call it as the field. [/INST] It's just that my own feeling is that in science now through observations and experiments. Yeah, we've measured so many things and Mhm. Basically we understand a lot of stuff. Okay, reality. Yeah. The fabric of reality. We understand quite well and there are a few little things like dark matter and dark energy that maybe some sign of some super intelligence, but I doubt it. Okay. You know, why would some super intelligence be holding clusters of Galaxies together? Why would they be responsible for accelerating the expansion of the universe. So the point is is that through science and applied science and engineering, we understand so much now that I'm not saying we know everything, but but we know a hell of a lot. Okay. And so there's, it's not like there are lots of mysteries flying around there that are completely outside our level of um, of, of exploration or understanding, </s>

<s>[INST] So, another fascinating place um in a paper title pushing the frontiers of density functional by solving the fractional electron problem. So, you're taking on modeling and simulating the quantum mechanical behavior of electrons. Can you explain this work and can ai model and simulate arbitrary quantum mechanical systems in the future? Yeah, [/INST] so this is another problem I've had my eye on for, you know, a decade or more, which is um sort of simulating the properties of electrons. If you can do that, you can basically describe how elements and materials and substances work. So it's kind of like fundamental if you wanna advance material science, um and, you know, we have Schrodinger's equation and then we have approximations to that density functional theory. These things are, you know, are famous and people try and write approximations to to these, to these functional and and kind of come up with descriptions of the electron clouds where they're gonna go, how they're gonna interact when you put two elements together and what we try to do is learn a simulation, learn a functional that will describe more chemistry types of chemistry. So, until now, you know, you can run expensive simulations, but then you can only simulate very small molecules, very simple molecules. We would like to simulate large materials. Um and so today there's no way of doing that. And we're building up towards building functional. Is that approximate schrodinger's equation. And then allow you to describe what the electrons are doing. Um And all materials sort of science and material properties are governed by the electrons and and how they interact. </s><s>[INST] So, have a good summarization of the simulation through the functional um but one that is still close to what the actual simulation would come out with. So what mm, how difficult that task. What's involved in that task is running those, those complicated simulations and learning the task of mapping from the initial conditions and the parameters of the simulation, learning what the functional would [/INST] be. So it's pretty tricky. And we've done it with you know the nice thing is we there are we can run a lot of the simulations. The molecular dynamics simulations on our compute clusters and so that generates a lot of data. So in this case the data is generated. So we like those sort of systems and that's why we use games Simulator generated data and we can kind of create as much of it as we want really. Um And just let's leave some you know if any computers are free in the cloud we just run we run some of these calculations right compute cluster calculations. </s><s>[INST] The free computer time is used up on quantum mechanics. [/INST] Quantum mechanics exactly simulations and protein simulations and other things. And so um and so you know when you're not searching on Youtube for video cat videos, we're using those computers usefully And Quantum chemistry the idea and putting them to good use and then Yeah. And then all of that computational data that's generated we can then try and learn the functional from that. Which of course are way more efficient. Once we learn the functional than running those simulations would be </s><s>[INST] do you think one day aI may allow us to do something like basically crack open physics so do something like travel faster than the speed of light. [/INST] My ultimate aim has always been with Ai is um the reason I am personally working on Ai for my whole life was to build a tool to help us understand stand the universe. So I wanted to and that means physics really and the nature of reality. So um I don't think we have systems that are capable of doing that yet, but when we get towards A G I I think that's one of the first things I think we should apply A G. I to. I would like to test the limits of physics and our knowledge of physics. There's so many things we don't know. There's one thing I find fascinating about science and you know, it's a huge proponent of the scientific method as being one of the greatest ideas humanity has ever had and allowed us to progress with our knowledge. I think as a true scientist, I think what you find is the more you find out the more you realize we don't know. And and I always think that it's surprising that more people don't aren't troubled, you know, every night. I think about all these things we interact with all the time that we have no idea how they work time, consciousness, gravity, life we can't I mean these are all the fundamental things of nature. </s><s>[INST] I think the way we [/INST] don't really know what they are </s><s>[INST] to live life. We pin certain assumptions on them and kind of treat our assumptions as if they're a fact that allows us to sort of [/INST] box them off somehow. </s><s>[INST] Box them off. But the reality is when you think of time, you should remind yourself, you should put it off, take it off the shelf and realize like no, we have a bunch of assumptions. There's still a lot of there's even not a lot of debate. There's a lot of uncertainty about exactly what is time. Uh is there an era of time? You know, there's there's a lot of fun about the questions that you can't just make assumptions about and maybe ai allows you to um not put anything on the shelf. Yeah, not make any hard assumptions and really open it up and see what [/INST] exactly. I think we should be truly open minded about that. And exactly that not be dogmatic to a particular theory. Um It'll also allow us to build better tools, experimental tools eventually, that can then test certain theories that may not be testable today about things about like what we spoke about the beginning about the computational nature of the universe. How one might if that was true. How one might go about testing that, right? And and how much, you know, there are people who have conjectured people like Scott Aaronson and others about, you know, how much information can a specific plank unit of space and time contain. Right? So one might be able to think about testing those ideas if you had um Ai helping you build some new, exquisite experimental tools. This is what I imagine that you know many decades from now we'll be able to do </s>

<s>[INST] And speaking of politics, one of the great things about testing, maybe you can correct me, but for my sense, it's one of the only solutions to covid that has not yet been politicized. So masks and vaccines, whether you like it or not have been heavily politicized where there's literally a red blue split on the use of those or like proud use effective use of those tools. And uh, it seems like everybody I talked to about testing, everybody's on board rider blue. [/INST] They are, which is why I am particularly concerned about the vaccinate or test policy because all of a sudden we just politicized it. We just brought it with this thing that was fully bipartisan really by part. I mean I've talked to the fully the really right side of Congress and the super liberal side of Congress, the Senate, the same politicians governors everywhere in this country have asked me for support around these rapid tests because it's just you can have a reported or not. You can have it in the home in the privacy of your own home or not or you do it at school. These these tools are just so powerful to identify infectious people. They didn't have to be politicized. They still don't, I don't think that the action plan went so far that it's going to politicize them, but I do think already it's starting to conjure up emotion saying, well now I have to get tested. They have to part right and that is where we go wrong. It's I have to get tested or vaccinated, you know, screw that I am independent, you know, whatever. And and I do worry that this thing that was purely bipartisan that we could have just scaled up months ago, people would have, we could have delivered it to every household, didn't even have to ask people to request it. Just delivered packages to every home in America by now easily. If we were smart about it, you know, we could have done it. </s><s>[INST] The most unpleasant thing about covid is the uncertainty and that's what leads to fear on both the vaccine hesitant is the answer in juba the vaccine and people who are have taken the vaccine. The uncertainty around like in my endanger walking around. Can I go, can I walk down the hall like this, fear of the world around you and I think testing allows you to remove a lot of that uncertainty like you, you gain back confidence that you can operate in this world and not get infected and you become like a nicer person. I I find myself every time I get tested become a nicer person to others because I know I'm not putting in danger, I'm not putting people in danger. [/INST] It's a, it's a heavy burden to carry to worry. Am I infectious? Like I was out last night, but I do want to go see my mom today, you know, like my infectious I don't know and this has created massive anxiety and I can't, I completely agree that it is, it's a relieving feeling and and it's an amazing feeling to be in a room when and I did this in the middle of the pandemic when everyone was supposed to be wearing a mask indoors had everyone rapid tests, you know, and I said everyone should rapid test before you walk into this room and it was a wonderful experiment because everyone was just so relaxed. You know, the other, the alternative is everyone, nobody tests and everyone wears a mask, You have a mask that maybe gives you 20% maybe protection during if you're all in the same room together if that Or you have a rapid test program wherever in rapid tests before and that gives you like 95% to 100% protection. Not 100% but close and all of a sudden that allows everyone to take a big sigh and be like, wow, this is the first time I've seen people without masks indoors in a long time and I feel pretty good. And restaurants like restaurants were scary right now because you just don't know who might be infectious and nobody's masked and like wouldn't it be great to just go into a restaurant where you know that everyone just tested negative that day? Just really reduces anxiety. It makes individuals feel empowered. And I mean at the end of the day, Covid and our response to Covid is is it's truly an information problem. You know, why, why do we quarantine anyone? Why did we ever close anything down? We didn't close things down because everyone is positive. We close things down because we didn't know if anyone was positive. We quarantine a whole classroom of kids Not because they're all positive, but because we don't know if one of them are positive. And so we just quarantine everyone when there's a positive in the case in the in the classroom, like one day, well then ask the whole classroom not to come to school for 10 days. That's not a biological problem. That's an information problem. And the crazy thing is we have the tool to solve that information problem. It's literally our eyes on the virus. That's how we see this virus. And if everyone glowed green when they were infectious, we would have never had to close down anyone any society and we would have, I never had the outbreaks because we would have been able to stay away from the green people, you know, and </s><s>[INST] I like what you said the quarantine is an information problem. That's absolutely right. What is there something you can say to what people can do? Like listening to this individuals? Do you just complain loudly? Like why can't we do this? Can you speak with your money somehow? What what can people do to help [/INST] God, It's it's amazing to think you're asking me this question and this video will go out to the web and all the people that watch you and last year in july, maybe something like that june I forget exactly what it was. I was on twitter this week in virology. Um get </s>

<s>[INST] Yeah, I mean you I think offline yesterday mentioned josh Tenenbaum and he's very much he put his man, he's such an inspiration in in the child like way that he pulls you in on any topic. Doesn't even have to be about machine learning or the brain, he'll just pull you into a closest rideable surface, which is still you can find whiteboards and mighty everywhere and and just like like basically cancel all meetings and talk for a couple hours about some some aimless thing. And it it feels like the whole world, the time space continuum kind of warps and that becomes the most important thing. And then it's just it's definitely something worth missing in this, in this world where everything's remote. There's some magic to the physical [/INST] presence. Whenever I wonder myself whether it really is as great as I remember it. I just go talk to josh. </s><s>[INST] Yeah. You know that's funny. There's a few people in this world that carried the the best of what particular institutions stand for, right? And this [/INST] uh josh. I mean, I don't, my guess is he's unaware of this. That's the point </s><s>[INST] that the masters are not aware of their mastery. So I mean, yes, But but first attention know how did you meet me? So I'm not sure what you were thinking. But my when it started to dawn on me that maybe we had a longer term bond was after we all got laid off. And you had decided at that point that there were still paid were given an opportunity to like do job search and kind of make a transition. But it was clear that we were done and I would go to my office to work and you would go to my office to keep me from working. That was that was my recollection of it. You have decided that there was no really no point in working for the company because our relationship with the company was it was done. [/INST] Yeah, but remember I felt that way before him, it wasn't about the company, it was about the set of people, they're doing really cool things and it always, always been that way. But we were working on something together. Oh </s><s>[INST] yeah, yeah, that's right. So at the very end we all got laid off. But then our boss came to, our boss's boss came to us because our boss was Michael kearns and he had jumped ship brilliantly, like perfect timing, like things like right before the ship was about to sink, he was like got to go and and landed perfectly because Michael Cairns and the leaving the rest of us to go like this is fine. And then it was clear that wasn't fine. And we were all toast. So we had this sort of long period of time and but then our boss figured out, okay, wait, maybe we can save a couple of these people if we can have them do something really useful. And uh the useful thing was, we were going to make a basically an automated assistant that could help you with your calendar, you could like tell it things and it would respond appropriately. It would just kind of integrate across all sorts of your personal information. And so me and Charles and Peter Stone were this were set up as the crack team to actually solve this problem, other people, maybe we're too theoretical that they thought and, and, but we could actually get something done, so we sat down to get something done and there wasn't time and it wouldn't have saved us anyway. And so it all kind of went downhill. But the interesting, I think coda to that is that our boss's boss is a guy named Ron brockman and he, when he left 80 and because we were all laid off, he went to DARPA, started up a program there that became Kahlo, which is the program from which Siri sprung, which is a digital assistant that helps you with your calendar and a bunch of other things. Um, it really, you know, in some ways, got its start with me and Charles and Peter trying to implement this vision that Ron brockman had, that he ultimately got implemented through his role at DARPA. So when I'm trying to feel less bad about having been laid off from what is possibly the greatest job of all time. Um, I think about, well, we kind of helped birth Siri, that's something [/INST] and he did other things too, but the, we got to spend a lot of time in his office and talk about, </s>

<s>[INST] the police because they are fed with this. Yeah. I mean, same thing was in the Soviet Union, it's funny, but then there's something inside you where that kind of opportunities come with a police officer where you realize you could just pay a little bit of money and get out of the thing. And then you realize you can pay a little bit of money or do a favor that get your kids in a bit of school or something like that. Yeah. But there comes opportunities where, if I do this little thing, I can get a huge promotion, or I can get a huge increase in my power, or I can get a lot of money. And something inside you says no, that's not right. And I wonder what that is. Cause like kids in a better school or something like that. Cause it feels different than the legal systems within which you operate. There's some kind of basic human integrity, human decency. I wonder if that's like constructed or it's always there. [/INST] If it's like, again, nature versus nurture. I think for me, it was looking at seeing that in somebody else that I kind of learned about it. There's a man that I consider a mentor figure. His name's Lieutenant Colonel Ezelda. He was a Lieutenant Colonel from the army that basically came over and took over the group that I used to work with. He was incorruptible. He was a, that was the essence or the aura that he projected. The first time he went off on patrol when he was placed in charge of us, I actually drove him around Tijuana. He was one of the lead from the front type of people. The amount of assassination attempts he got was basically a proof of how uncorruptible he was because they kept trying to pay him off. And when that didn't work, they tried to kill him several times. I think the last assassination attempt took the use of his legs. And that man is still a dangerous person in my mind. But for me, and people can gather a little bit about my background and where I'm from and some of the access I currently have to train the federal institutions here in the US as far as my background and if I was corrupted or not because there's a lot of that out there. The Catholic guilt that's kind of built into some of us is always kind of there, you know? El Cucui Viva Guelacama, the devil was under the bed. So I don't consider myself Catholic. Consider myself culturally Catholic, I think, is what I kind of say with that. I had a pretty good structure with my dad and my mom at the house and they never let me get away with things. And I think my mom was a pretty big moral compass for me. But Lieutenant Colonel kind of leading from example and seeing his work and how much profound change he caused in the people that work with him as far as we felt supported and we felt like we had a guiding figure during this Dejuana was the most dangerous city on the planet when I was working there </s><s>[INST] and he took charge, a figure. What does it take to be a man, the Lieutenant Colonel, who maintains integrity after assassination attempts? Is it possible for a normal human to do that [/INST] or again as a genetic? That's an interesting question, I'll say this. Seeing him, I mean, the last assassination attempt he had that took the use of his legs, he was with his kid. There was a recklessness to it, you know? I can see that now, like now that I have enough distance from it, I could see that there's a recklessness to being that way and also putting jeopardy people around you if you take that route. So I think there's a sacrifice to it, a very powerful and hard one to make for a lot of people. For me, it was, I wouldn't get picked to get on board with some of the operations groups that I wanted to work with because I was known for not taking money or not being trusted by certain older segments of the organization that I was with, with stuff because they knew that I wasn't on the, I wouldn't get money. So there's always a weird sacrifice to it and you're almost kind of masochistic in that way when you get approached with it, they're like, why are you being an idiot? Why are you driving around that beat up car? Look at the Hummer H2 that just drove in with the other guy that is doing exactly your same job. Society, there's a hole down there, doesn't reward it, or at least doesn't see it in the people that don't take that route in Mexico. For them, all cops are corrupt, all of them. And seeing it again from the outside, I'm not there anymore. There's almost like a, why didn't you, Ed? You know, that could have been easier maybe, or you could have been dead long ago because people that are on the takedown there are usually owned by one side or the other. And when that gets found out, if you have somebody that you're paying off that hints you off of drug operations in the area, </s><s>[INST] your rivals are pretty keen on killing you. Money aside, so like a Hummer aside, how much of a motivator's fear? [/INST] It's a big one. You know, I'll say, you know, for me, I didn't think I was gonna live to see 30. </s><s>[INST] You know, I was sure of it. Did that concept scare you, or was that just a principle of life [/INST] that you operated under? I lost my brother when I was 13 on it too. Like, you know, he was 19. He was like the VIP of the family, you know? You miss him? Oh, every day. He was a, you know, he was a, you know, skateboarded BMX motorcycle hunter, one of the best marksmen that I've ever seen shoot. So better than you had everything. Yeah, he was the best of us is what we would say. And when he died, there was a, there was, it's almost like a concert at this funeral. You know, I met three of his girlfriends that all introduced themselves like the one, you know? Yeah. To this day, every now and then I get pulled aside down when I go back home and they, you're Eric's brother, you know? Despite all the stuff that I've done, I'm still, you know, every now and then I get recognized. That made my mom and my dad go into a horrible depression and basically, you know, left me to my devices when I was a kid from 13 onwards. I had this self-destructive, you know, aspect to me after that, I think, you know, again, something that's come up in therapy, you know, after I've been gone through all that and had this notion that if I can only die good in some way, shape or form or for something that it would matter. And they would kind of, you know, look at me </s>

<s>[INST] You responded to a few things there, you spoke to the fact that, you know, there is a narrative of malevolence, like um you know, you're leaning into the making people angry just because it makes more money in the short term, that kind of thing. So you're you responded to that, but there's also kind of reality of human nature, just like you spoke about there's fights arguments we get in and we don't like ourselves afterwards, but we got into them anyway, so our long term growth [/INST] is </s><s>[INST] I I believe for most of us has to do with learning, challenging yourself, improving, being kind to each other, finding a community of people that, you know, you uh connect with on a real human level, all that kind of stuff. But it does seem when you look at social media that a lot of fights break out, a lot of arguments break out a lot of viral content ends up being sort of outraged in one direction or the other. And so it's easy from that to infer the narrative that social media companies are letting this outrage become viral, and so they're increasing the division in the world and perhaps you can comment on that or further, how can you be, how can you push back on this narrative? How can you be transparent about this battle? Because I think it's not just motivation or financials, it's a technical problem too, which is how do you improve long term well being of human beings, [/INST] I think that going through some of the design decisions would be a good conversation. But first I actually think, and I think you acknowledge that you know that narrative is somewhat anecdotal and I think it's worth grounding this conversation in the actual research that has been done on this, which by and large finds that social media is not a large driver of polarization, right? And um you know, I mean there's been a number of economists and social scientists and folks who have studied this. Um you know, a lot of polarization, it varies around the world if social media is basically in every country, facebook is in pretty much every country except for china and maybe north Korea and um and you see different trends in different places where you know, in a lot of countries, polarization is declining and some it's flat in the US it's it's risen sharply. So the question is, what are the unique phenomenon in the different places? And I think for the people who are trying to say, hey social media is the thing that's doing this. I think that that clearly doesn't hold up because social media is a phenomenon that is pretty much equivalent in all of these different countries and you have researchers like this economist at stanford Matthew gensco who's just written at length about this. Um and you know, it's a bunch of books by, you know, political scientists as recline and folks, we're why we're polarized basically goes through this decades long analysis in the U. S. Before I was born, basically talking about some of the forces and kind of partisan politics and Fox News and different things that predate the internet in a lot of ways that that I think are are likely larger contributors. So to the contrary on this, not only is it pretty clear that social media is not a major contributor, but most of the academic studies that I've seen actually show that social media use is correlated with lower polarization against the same person who just did the study that I that I cited about longitudinal polarization across different countries. Um You know, also did did a study that basically showed that If you looked after, you know, the 2016 election in the us, the voters who are the most polarized, um we're actually the ones who are not on the Internet. So, and there have been recent other studies, I think in europe and around the world, basically showing that as people stop using social media, they tend to get more polarized. Um then there's a deeper analysis around, Okay, well what polarization actually isn't even one thing, um because you know, having different opinions on something isn't I don't think that that's by itself bad. What what people who study this say is um most problematic is what they call affective polarization, which is basically are you do you have negative feelings towards people of another group? And the way that a lot of scholars study this is they basically ask a group um would you let your kids marry someone of group X, whatever the the groups are that you're that you're worried that someone might have negative feelings towards. And in general use of social media has corresponded to decreases in that kind of affective polarization. So I just want to I think we should talk to the design decisions and how we handle um the the kind of specific pieces of content. But overall I think it's just worth grounding that discussion in the research that's existed. That I think overwhelmingly shows that the mainstream narrative around this is just not right. </s><s>[INST] But the the narrative does take hold and it's compelling to a lot of people. There's another question I'd like to ask you on [/INST] this. I </s><s>[INST] was looking at various polls and saw that your one of the most disliked tech leaders today, 54%. Unfavorable rating. Elon Musk is 23% is basically everybody has a very high unfavorable rating that our tech leaders maybe you can help me understand that? Why do you think so many people dislike you? Some even hate [/INST] you? </s><s>[INST] And how do you regain their trust and support given everything you've just said? Why are you losing the battle in explaining to people what actual impact social media has in society? Yeah. [/INST] Well I'm curious if that's a U. S. Survey for world. </s>

<s>[INST] So great. So you, are, you joined the Bitcoin community in 2011? You said you began writing, so what's next, [/INST] started writing? Uh moved from high school to university halfway in between that and spent a year in university um then at the end of that year I dropped out to do a Bitcoin things full time and this was a combination of continuing the right Bitcoin magazine, but also increasingly work on software project and I traveled around the world for about six months and just going to different Bitcoin communities like I went to first in new Hampshire, then spain and other european voices, Israel and in san Francisco and along the way and I've met a lot of other people that are working on different Bitcoin project and when I was in Israel there were some kind of very smart teams there that were working on ideas that people were starting to kind of called Bitcoin two point oh, so one of these works covered coins, which is basically saying that hey let's not just use the Blockchain for Bitcoin but it's also a kind of issue other kinds of assets on it. And then there was a protocol called master coin that supported issuing assets but also supported many other things like financial contracts like domain name registration and a lot of different things together. And I um spent some time working with these teams and I quickly kind of realized that this master coin protocol could be improved by kind of generalizing it more. Right? So that the analogy I use is a domestic one protocol was like the swiss army knife. You have 25 different transaction types for 25 different applications. But what I realized is that you can replace a bunch of them with things that are more general purpose. So one of them was that you could replace like three transaction types for three types of financial contracts with a generic transaction type for a financial contract. Just watch you specify a mathematical formula for kind of how much money each side gets. </s><s>[INST] By the way it's a small pause what you say financial contract, just the terminology, what is the contract? What's a financial contract? [/INST] So this is just generally an agreement where kind of either one or two parties kind of put collateral kind of in um and then they depending on the kind of certain conditions like this could involve prices of assets that could involve different um the actions of the two parties could involve other things, They kind of get different amounts of uh of assets out that has just depend on things that happened. </s><s>[INST] So contract is really a financial contract is at the core, it's the core interactive element of the financial system. [/INST] Yeah, there's, there's many different kinds of financial contracts, like there's things like options where you kind of give someone the right to buy a thing that you have for some specific price for some period of time. There's a contracts for difference where you basically are kind of making a bet that says like For every dollar, this thing goes up, I'll give you $7 or for every dollar, the thing goes down. You give me $7 or something like that. Yeah, but the </s><s>[INST] main idea that these contracts have to be enforced and trusted [/INST] them. Yes, exactly. </s><s>[INST] You have to trust that they will work out in a system where nobody can be trusted. [/INST] Yes, this is </s><s>[INST] such a beautiful complicated system. Okay, so uh so you were seeking to kind of generalize this basic framework of contracts. So what does that entail? So what what technically are the steps to creating a theory? Um [/INST] Sure. So I guess just to kind of continue a bit with this master coin story. So started by and of giving ideas for how to generalize the thing and eventually this turned into a much more kind of fully fledged proposal that just says, hey, how about you scrap all your futures and instead you just put in this programming language and I gave this idea to them and their response was something like, hey, this is great, but this seems complicated and it seems like something that we're not going to be able to put onto a road map for a while. And my response to this was like, wait, do you not realize how evolutionary this is? We'll just go do it myself. And then I </s><s>[INST] was the name of the programming of which [/INST] I just called it ultimate scripting. Uh so then I go and I went through a couple more rounds of iteration and then the idea for a theory of itself started to form. Um and the idea here is that you just have a Blockchain where the core unit of the thing is what we call contracts as these and if accounts that can hold assets and they have their own internal memory but that are controlled by a piece of code. And so if I send some ether to a contract, the only thing that can determine where that kind of either the currency inside ethereum and it goes after that um is uh the code of that contract itself. And so basically kind of sending assets to computer programs becomes this kind of paradigm for creating the incentive agreement, self executing agreements, </s><s>[INST] self executing as so cool, the code is sort of part of this contract, so that that's what's meant by smart contracts. Yeah, so how hard was it to build this kind of thing, [/INST] harder than expected? Um And originally I actually thought that this would be a thing that I would kind of casually work on for a couple of months published and then go back to university, um Then I released it and a bunch of people, or I released a white paper, white paper that is the idea of the white paper, a whole bunch of people came in offering to help a huge number of people and have expressed interest and this was something that was totally not expecting. And then I kind of realized that this would be something in this kind of much bigger than I had ever thought that it would be. And then we started on this kind of much longer developments log of making something that lives up to this sort of much higher level of expectations. </s>

<s>[INST] chosen people of God never resonated with me too much. The graph of the Gertzel family, I mean, just the people I've encountered, just doing some research and just knowing your work through the decades, it's kind of fascinating. Just the number of PhDs. [/INST] Yeah, yeah. It's kind of fascinating. My dad is a sociology professor who recently retired from Rutgers University, but that clearly that gave me a head start in life. My grandfather gave me all this quantum mechanics books and I was like seven or eight years old and I remember going through them and it was all the old quantum mechanics, like Rutherford Adams and stuff. So I got to the part of wave functions, which I didn't understand, although I was a very bright kid and I realized he didn't quite understand it either, but at least like he pointed me to some professor he knew at UPenn nearby who understood these things, right? So that's an unusual opportunity for a kid to have, right? My dad, he was programming Fortran when I was 10 or 11 years old on like HP 3000 mainframes at Rutgers University, so I got to do linear regression in Fortran on punch cards when I was in middle school, right? Because he was doing, I guess, analysis of demographic and sociology data. So yes, certainly that gave me a head start and a push towards science beyond what would have been the case with many, many different situations. </s><s>[INST] When did you first fall in love with AI? Is it the programming side of Fortran? Is it maybe the sociology psychology that you picked up from your dad? [/INST] I fell in love with AI when I was probably three years old when I saw a robot on Star Trek. I was turning around in a circle going, error, error, error, error, because Spock and Kirk had tricked into a mechanical breakdown by presenting with a logical paradox. And I was just like, well, this makes no sense. This AI is very, very smart. It's been traveling all around the universe, but these people could trick it with a simple logical paradox. Like why, if the human brain can get beyond that paradox, why can't this AI? So I felt the screenwriters of Star Trek had misunderstood the nature of intelligence. I complained to my dad about it and he wasn't going to say anything one way or the other. Before I was born, when my dad was at Antioch College in the middle of the US, he led a protest movement called SLAM, Student League Against Mortality. They were protesting against death, wandering across the campus. So he was into some futuristic things even back then, but whether AI could confront logical paradoxes or not, he didn't know. But when I, 10 years after that or something, I discovered Douglas Hofstadter's book, Gortel Escherbach, and that was sort of to the same point of AI and paradox and logic, right? Because he was over and over with Gortel's incompleteness theorem and can an AI really fully model itself reflexively or does that lead you into some paradox? Can the human mind truly model itself reflexively or does that lead you into some paradox? So I think that book, Gortel Escherbach, which I think I read when it first came out, I would have been 12 years old or something. I remember it was like 16 hour day, I read it cover to cover and then reread it. I reread it after that because there was a lot of weird things with little formal systems in there that were hard for me at the time. But that was the first book I read that gave me a feeling for AI as like a practical academic or engineering discipline that people were working in. Because before I read Gortel Escherbach, I was into AI from the point of view of a science fiction fan. And I had the idea, well, it may be a long time before we can achieve immortality and superhuman AGI. So I should figure out how to build a spacecraft traveling close to the speed of light, go far away, then come back to the earth in a million years when technology is more advanced and we can build these things. Reading Gortel Escherbach, well, it didn't all ring true to me, a lot of it did. But I could see like there are smart people right now at various universities around me who are actually trying to work on building what I would now call AGI, although Hofstadter didn't call it that. So really, it was when I read that book, which would have been probably middle school, that then I started to think, well, this is something that I could practically work on. </s><s>[INST] Yeah, it's supposed to flying away and waiting it out, you can actually be one of the people that actually... Yeah, exactly. [/INST] Yeah, exactly. And if you think about, I mean, I was interested in what we'd now call nanotechnology and in the human immortality and time travel, all the same cool things as every other like science fiction loving kid. But AI seemed like if Hofstadter was right, you just figure out the right program, sit there and type it. Like you don't need to spin stars into weird configurations or get government approval to cut people up and fill with their DNA or something, right? It's just programming. And then of course, that can achieve anything else. There's another book from back then, which was by Gerald Feinbaum, who was a physicist at Princeton. And that was the Prometheus Project. And this book was written in the late 1960s, though I encountered it in the mid 70s. But what this book said is in the next few decades, humanity is going to create superhuman thinking machines, molecular nanotechnology, and human immortality. And then the challenge we'll have is what to do with it. Do we use it to expand human consciousness in a positive direction or do we use it just to further vapid consumerism? And what he proposed was that the UN should do a survey on this and the UN should send people out to every little village in remotest Africa or South America and explain to everyone what technology was going to bring the next few decades and the choice that we had about how to use it and let everyone on the whole planet vote about whether we should develop super AI, nanotechnology, and immortality for expanded consciousness or for rampant consumerism. And needless to say, that didn't quite happen. And I think this guy died in the mid 80s, so he didn't even see his ideas start to become more mainstream. But it's interesting, many of the themes I'm engaged with now from AGI and immortality, and to trying to democratize technology, as I've been pushing forward with singularity in my work in the blockchain world. Many of these themes were there in, you know, Fine Bomb's book in the late 60s even. And of course, Valentin Turchin, a Russian writer, and a great Russian physicist who I got to know when we both lived in New York in the late 90s and early aughts, I mean, he had a book in the late 60s in Russia, which was The Phenomenon of Science, which laid out all these same things as well. And Val died in, I don't remember, 2004 or 2005 or something of Parkinson'sism. So yeah, it's easy for people to lose track now of the fact that the futurist and singularitarian advanced technology ideas that are now almost mainstream, and they're on TV all the time. I mean, these are not that new, right? They're sort of new in the history of the human species, but I mean, these were all around in fairly mature form in the middle of the last century were written about quite articulately by fairly mainstream people who were professors at top universities. It's just until the enabling technologies got to a certain point, then you couldn't make it real. And even in the 70s, I was sort of seeing that and living through it, right? From Star Trek to Douglas Hofstadter, things were getting very, very practical from the late 60s to the late 70s. And the first computer I bought, you could only program with hexadecimal machine code and you had to solder it together. And then like a few years later, there's punch cards, and a few years later, you could get like Atari 400 and Commodore VIC-20, and you could type on the keyboard and program in higher level languages alongside the assembly language. So these ideas have been building up a while, and I guess my generation got to feel them build up, which is different than people coming into the field now for whom these things have just been part of the ambiance of culture for their whole career or even their whole </s>

<s>[INST] care of the sea to flip the table on you, then wearing a tie is communicating the nice guy image. So it actually gives you the freedom for more elements of surprise by wearing the tie. If you take it off, that's more you're limiting your options because nobody's going to expect the guy in the tie to do anything. [/INST] I'm a big believer that sometimes it's not only materialism, it's what you project. Like I had troubles in a bar and I was able to deflect. The guy was looking for trouble talking to me and I was able to deflect is all aggressive. Itty by saying like, hey man, that's a nice shirt, where did you get it? Like saying like something or stupid like this, then it kind of break, break the momentum and he, you know, but the guy was looking for trouble. I don't want to fight you. I don't want to fight you, but I'm not going to wait until you pull you make the first move because the first, the minute you you touch me, you push me or you touch me, you declare war and the war is unleashed, my friend and I'm I'm taking you out of order with the necessary force. Of course, you know, I mean, that's the thing with martial art. If you use the necessary force to take care of the problem, it's okay. But if you, you know, you you take advantage of it. That's when it's not all right because it's a weapon. So if someone comes up to me, that's my position and now I'm I'm assessing the situation, you know, that's that's how they teach in self defense here never put your hands down always end there because I'm bound or boom, like what this is, this is very important and you never, you always your center line on the side. Yeah, like this, if someone knows martial aren't it will recognize that pattern. But if you go, like if someone talked to you and you go like this, that's mean you're telling the guy that you want to fight, you don't want to do that, you don't want to. Yeah, that's it, that's it. You know, that's that's the position because you're an R here, you know, whatever you can do your here, </s><s>[INST] we'll also, your ear tells the story. [/INST] It's not everybody that knows that however it, some people might think that it's, my mom grabbed me by the hair and pulled me because I didn't listen to her, you know, a real fight in the street and the fight in the, in the mixed martial art is a different ball game. </s><s>[INST] What do you think is the best martial art to prepare you for street fighting? You know, people often kind of have this discussion of jujitsu, maybe boxing and the wrestling. Do you think we talked about a young person studying martial arts to prepare themselves [/INST] for a street fight, it's often much different than a mixed martial arts fight and I know there's a lot of Bs in the world of martial arts like self defense stuff that like, but I believe self defense is very important in a way to understand the situation, to understand those, those situations that might accurate how to deal with it because not necessarily the we talk about the technicality, we talk about the practicality, the tactics, you know, like when I'm talking to you about the element of surprise is important. This is not technique, technique is a punch or or techniques that I physically will use to unable my opponent. My aggressor tactic is the tactic I'm telling you about is in a street fight. If someone is looking for trouble and I feel the heat rising as the conversation goes, that's the position I'm going to take, and I have to be first, I cannot let him go first, so I have to strike first or do something. This is the first thing that generally, and I have to two to agree on, um after that, of course there's the knowledge if you're a professional fighter, you have a a huge advantage once the fight started the war is declared, now it's everything goes. But generally speaking, the person that will intervened physics that will have the first blower, the first, you know, the first punch, we'll have a huge decision, used advantage, it's like doing 100 m race and having a head start, </s><s>[INST] you know, and and that you don't you can't prepare for with any martial [/INST] art. Yeah, and and if I'm a smart guy, I know how to fight, if a guy like uh an every weight champion comes to me or like, like, like a, you know, I know I know what to do to this, this napoleon like boom or hair and, and or the, the neck, you know like, and if you, if you're blind them what we're gonna do, you know what I mean? So, so, or or a bottle, you know what I mean? So so the element of surprise is, it's everything. So that's why it's always always good to be the nice guy and not looking for trouble because if you're not looking for trouble, you have the head start, you have the option of having a head start. </s><s>[INST] So what you're saying is being a nice guy is the best form of self defense, Maybe a little humor. [/INST] Uh you know, I have learned that I've learned that when I </s><s>[INST] was a kid, [/INST] I was about Maybe 7, 6, 6 years old, we used to play in, in my child is a lot of snow. We used to play king of the mountain. That's the first combat lesson that I've learned in my life. And I managed somehow, it was a lot of kids, I managed to get on the top of the mountain and another guy can come in on the top of the mountain and he was angry that before I was there before him and when you play king of the mountain, the mountain, it was a mountain of snow, you don't strike each other. We just wrestle and push and I managed to be first. And when he came he says to me say, okay you want to you want to fight. And I said, yeah, I don't know what I mean. Like I want to fight, you want to wrestle. He said, I say yes, he punched me right in the face boom. And then I and then I fall on the bottom of the mountain. But then I when I fall down, I remember that vision in mali because it's I really remember that for the rest of my life, I'm about to stand up and I see the blood coming out of my nose. I see the snow is red because my nose is bleeding. Now I I remember the limit of surprises, everything. My first street fight, I lost it. I didn't get knocked out, but I got I got dropped on the bottom of the mountain and I was like, you got me because I was not expecting my hand, I was not expecting a punch. So from there when I felt the heat of an inn during an argument or something was not right. I always stroke first. I didn't win all my fights because sometimes there were more than one guy's on me, you know, but I think it's important. Do not be the aggressor. So you have the element of surprise and I always use that in </s>

<s>[INST] And now here's my conversation with Stephen Wolfram, you and your son Christopher helped create the alien language in the movie arrival. So let me ask maybe a bit of a crazy question, but if aliens were to visit us on earth, do you think we would be able to find a common language. [/INST] Well, by the time we're saying aliens are visiting us, we've already prejudiced the whole story because the, you know, the concept of an alien actually visiting, so to speak, we already know they're kind of uh things that make sense to talk about visiting. So we already know they exist in the same kind of physical setup that we do. They're not, you know, it's not just radio signals, it's an actual thing that shows up and so on. Um So I think in terms of, you know, can one find ways to communicate? Well, the best example we have of this right now is a I mean that's our first sort of example of alien intelligence. And the question is how well do we communicate with Ai you know, if you were to say if you were in the middle of a neural net and you open it up and it's like what are you thinking? Can you discuss things with it? It's not easy, but it's not absolutely impossible. So I think I think by the time but given the setup of your question, aliens visiting, I think the answer is yes. One will be able to find some form of communication. Whatever communication means? Communication requires notions of purpose and things like this. It's a kind of philosophical quagmire. So </s><s>[INST] if ai is a kind of alien life form, what do you think visiting looks like? So if you look at aliens visiting and we'll get to discuss computation and the world of computation. But if you were to imagine you said you already prejudiced something by saying you visit. But what how would aliens visit [/INST] by visit? There's kind of an implication. And here we're using the imprecision of human language, you know, in a world of the future. And if that's represented in computational language, we might be able to take the concept visit and go look in the documentation basically and find out exactly what does that mean? What properties does it have and so on. But by visit in ordinary human language, I'm kind of taking it to be, there's, you know, something a physical embodiment that shows up in a spacecraft. Since we kind of know that that's necessary. We're not imagining. It's just, you know, photons showing up in a radio signal that uh, you know, a photons in some very elaborate pattern we're imagining. It's it's physical things made of atoms and so on that that show up. </s><s>[INST] Can it be photons in a pattern? [/INST] Well, that's good question. I mean, whether there is the possibility, you know, what counts as intelligence? Good question. I mean, it's, you know, and I used to think there was sort of a, oh, there will be, you know, it'll be clear what it means to find extraterrestrial intelligence, etcetera, etcetera, etcetera. I've I've increasingly realized as a result of science that I've done that there really isn't a bright line between the intelligent and the merely computational so to speak. So, you know, in our kind of everyday sort of discussion will say things like, you know, the weather has a mind of its own Well, well let's unpack that question. You know, we realize that there are computational processes that go on that determine the fluid dynamics of this and that and the atmosphere etcetera etcetera etcetera. How do we distinguish, distinguish that from the processes that go on in our brains of, you know, the physical processes that go on in our brains? How do we how do we how do we separate those? How do we say the physical processes going on that represents sophisticated computations in the weather? Oh, that's not the same as the physical processes that go on that represents sophisticated computations in our brains. The answer is I don't think there is a fundamental distinction. I think the distinction for us is that there's kind of a thread of history and so on that connects kind of what happens in different brains to each other, so to speak. And it's a you know, what happens in the weather is something which is not connected by sort of a thread of of uh civilisational history, so to speak, to what we're used to in </s><s>[INST] our story in the stories that the human brain's told us, but maybe the weather has its own stories. Absolutely, [/INST] Absolutely. And that's and that's where we run into trouble thinking about traditional intelligence because, you know, it's like that pulsar magnetosphere, that's generating these very elaborate radio signals, you know, is that something that we should think of as being this whole civilization that's developed over the last however long, you know, millions of years of of processes going on in the in the neutron star or whatever versus what, you know, what we're used to in human intelligence. I mean, I think it's a I think in the end, you know, when people talk about extraterrestrial intelligence and where is it? And the whole, you know, fermi paradox of how come there's no other for signs of intelligence in the universe. My guess is that we've got sort of two uh alien forms of intelligence that we're dealing with artificial intelligence and sort of physical or extraterrestrial intelligence. And my guess is people will sort of get comfortable with the fact that both of these have been achieved around the same time. And in other words, people will say, well, yes, we're used to computers, things we've created digital things we've created, being sort of intelligent, like we are. And they'll sell we're kind of also used to the idea that there are things around the universe that are kind of intelligent, like we are, except they don't share the sort of civilizational history that we have. And so we don't, you know, there there are different branch. I mean, it's similar to when you talk about life for instance, I mean, you you you kind of said life form, I think almost synonymous lee with intelligence, which I don't think is is um you know, the the A. I. S. Would be upset to hear you uh equate those </s>

<s>[INST] So maybe a difficult question. Maybe you'll push back on this. But you're widely seen politically as a conservative Coover institution is politically conservative. What is the role of politics at the University of Austin? Because some of the ideas, people listening to this when they hear the ideas you're expressing, they may think there's a lean to these ideas. There is a conservative lean to these ideas. Is there such a lean? [/INST] There will certainly be people who say that because the standard mode of trying to discredit any new initiative is to say, oh, this is a sinister conservative plot. But one of our uh co founders heather. Hying is definitely not a conservative. Uh she's as committed to the idea of academic freedom as I am. But I think on political issues we probably agree on almost nothing and at least I would guess. But but politics max Faber made this point a long time ago, the politics really should stop at the threshold of the classroom of the lecture hall and in my career, I've always tried to make sure that when I'm teaching, it's not clear where I stand politically though. Of course undergraduates and insatiably curiously want to know. But it shouldn't be clear from what I say, because indoctrination on a political basis is an abuse of the power of the professor as Veber rightly said. So I think one of the key principles of the University of Austin will be that barbarian principle, that politics is not an appropriate uh subject for the lecture hall for the classroom. And we should pursue truth and enshrine liberty of thought. If that's a political issue, then I can't help you. If you're against freedom of thought, then we don't really have much of a discussion to have. And clearly there are some people who politically seem quite hostile to it. But my sense is that there are plenty of people on the left in academia. I think of that interesting partnership between Cornell West and Robbie George which has been institutionalized in the Academic Freedom Alliance. It's bipartisan this issue. It really, really is. After all, 50 years ago, it was the left that was in favor of free speech. The right still has an anti free speech element to it. Look how quickly they're out to ban Critical Race theory. Critical Race theory won't be banned at the University of texas workers and won't be banned. Everything will be up for discussion, but the rules of engagement will be clear Chicago principles, those will be enforced. And if you have to give a lecture on Well, let's just take a recent example, the Dorian Abbot case, if you're giving a lecture on astrophysics, but it turns out that in some different venue, you express skepticism about affirmative action? Well, it doesn't matter, it's irrelevant. We want to know what your thoughts are on astrophysics because that's what you're supposed to be doing. A lecture on that used to be understood. I mean, at the Oxford of the 1980s, there were communists and there were ultra tories at Cambridge. There were people who were so reactionary that they celebrated Franco's birthday, but they were also out and out communists down the road at King's College. The understanding was that that kind of intellectual diversity was part and parcel of university life. And frankly, for undergraduate was great fun to cross the road and go from, you know, outright conservatism, ultra tourism to communism. One learns a lot that way. But the issue is when you're promoting or hiring or tenure in people, their politics is not relevant. It really isn't. And when it started to become relevant. And I remember this coming up at the Harvard history department. Later in my time there, I felt deeply, deeply uneasy that we were having conversations that amounted to, well, we can't heart X person despite their obvious academic qualifications because of some political issue, that that's not what should happen at a healthy university. </s><s>[INST] Some practical questions will University of Austin be a physical and personal university or virtual university. What are some uh in that aspect, where the [/INST] classroom is, it will be a real space institution, There may be an online dimension to it because there are clearly are a lot of things that you can do uh, via the Internet, but the core activity of, of teaching and learning, I think requires real space. And I've thought about this a long time debated Sebastian Thrun about this many, many years ago when he was a complete believer in, let's call it the metaverse city to go with the metaverse. I mean the metaverse city was going to happen, wasn't it? But I never really believed in the metaverse city. I didn't do my books because I just didn't think you'd a be able to retain the attention, be, be able to cope with the scale scaled grading that was involved. I think there's a reason universities have been around and their form for about a millennium, you kind of need to all be in the same place. So I think the answer to that question, definitely a campus in the Austin area, that's where we'll start and if we can allow some of our content to be available online? Great. We'll certainly do that. </s><s>[INST] Another question is, what kind of courses in programming will it offer? Is that something you can speak to? What's your vision here? [/INST] We think that we need to begin more like a startup than Like a full service university from day one. So our vision is that we start with a summer school which will offer provocatively the forbidden courses we want, I think, to begin by giving a platform to the professors who have been most subject to council culture and also to give an opportunity to students who want to hear them to come. So we'll start with the summer school that will be somewhat in the tradition of uh of those institutions in the interwar period that were havens for refugees. So we're we're dealing here with the internal refugees of the work era. We'll start there. Uh it will be an opportunity to test out some uh some content, see what students will come uh and spend time in Austin to hear. So that's part a that's the sort of uh if you like the launch product and then we go straight to a master's program. I don't think you can go to undergraduate education right away because the established brands in undergraduate education are offering something it's impossible to compete with initially because they have uh the brand Harvard Yale stanford and they offer also this peer network uh which is part of the reason people want so badly to go to those places, not really the professors, it's the classmates, so we don't want to compete there initially, where there is, I think room for new entrance is in a master's program and the first one will be in entrepreneurship and leadership because I think there's a huge hunger amongst people who want to get into, particularly the technology world to learn about those things and they know they're not really going to learn about them at business schools, the people who are not going to teach them leadership and entrepreneurship are professors. So we want to create something that will be a little like the very successful Schwartzman program in china, which was come and spend a year in china and find out about china. We'll be doing the same essentially saying come and spend a year and and find out about technology and there'll be a mix of academic content. We want people to understand some of the first principles of what they're studying there are first principles of entrepreneurship and leadership, but we also want them to spend time with people like one of our co founders, joe Lansdale, who has been a hugely access a successful venture capitalist and and learned directly from people like him. So that's the kind of initial offering. I think there are other masters programs that we will look to roll out quite quickly. I have a particular passion for a master's in applied history or politics and applied history. I'm a historian driven crazy by the tendency of, of academic historians to drift away from what seemed to me the important questions and certainly to drift away from addressing policy relevant questions. So I would love to be involved in in a master's in applied history and we'll build some programs like that before we get the full liberal arts experience that we envisage for an undergraduate program and the undergraduate program is an exciting one because I think we can be innovative there too. I would say two years would be spent doing some very classical and difficult classical things, bridging those old divides between arts and sciences, but then there would also be in the second in the second half, and the junior and senior years, something somewhat more of an apprenticeship where we'll have centers including a sensor for uh technology, engineering, mathematics, that will be designed to help people make that transition from the theoretical to the practical. So that's the vision. Uh and I think like any like any early stage uh idea will doubtless tweak it as we go along, we'll find things that work and things that don't work. But I have a very clear sense in my own mind of how this should look five years from now, and I don't know about you. I mean, I'm unusual as an academic cause I quite like starting new institutions and I've done a bit of it in my career. You've got to kind of know what it should look like after the first four or five years to get out of bed in the morning and put up with all the kind of hassles of doing it, not not least the inevitable flack that were bound to take from the educational establishment. </s>

<s>[INST] it becomes, uh, for lack of a better word, viral positivity does. And I mean I believe that ultimately that that wins out because I think there's much more power to be gained. So I think most people want to do good and if you want to wield power, you want to, uh, channel people's desire to do good. And I think over time, that's, that's exactly what people, uh, we'll do. But yeah, this, I mean, both on the natural side, the pandemic, you know, there's still biology of play. There's still viruses out there kind of goes, there's accidents, uh, there's nuclear weapons, there's unintended consequences of tools with this. And then nanotechnology side or the artificial intelligence side. Then there's the natural things like Meteors and all that kind of stuff and the climate change, all of that. But I tend to think we humans are clever bunch when there's a deadline, a real deadline or real threat before us, we kind of step up. I don't know, but maybe you have to believe that until the very end. [/INST] Yeah, that's right. I mean, we'll have to see, I guess, you know neither. Well, ideally we won't be alive to see that. Well, no, </s><s>[INST] Michael, I'm glad we talk again because this has been such a difficult time that feels like there's no solutions. And it's so refreshing to hear that there is a solution to Covid and there's an engineering solution on the individual level. Something people can do on the government level is something people can do on the global level, something people can do. We should be doing rapid testing at scale. It's obvious. It's amazing that you still our, um, you know, telling that story, pushing that message bravely boldly. I really, really appreciate the work you're doing. And, and I, I I will do in my small way, uh, the same to try to help out and everybody else should too, until we get hundreds of millions of tests in people's hands. Uh, it's obvious solution. We should have had a long time ago and I like solutions, not problems. And this is obviously a solution. So thank you for presenting it to the world and thank you for talking about it. [/INST] It's it's something that I can't not do if it saves one person's life, then it was worth the two years of lobbying for this, you know, And uh, so let's hope we see a change. </s><s>[INST] Thanks for talking today. [/INST] Absolutely. </s><s>[INST] Thanks for listening to this conversation with Michael Mina to support this podcast, please check out our sponsors in the description. And now let me leave you with some words from Lord Byron. Always laugh when you can. It is cheap medicine. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] So you said a few really interesting things there. So because you are kind of an insider war for time and insider meaning you were able to build up an intuition about the good, the bad and ugly of these institutions specifically the good. A lot of people don't have a good sense of the good, they know the bad and the ugly or can infer the bad and the ugly. You mentioned that the one little key little thing there at the end saying the N. S. A. Doesn't care about whether you hate the president or not. Now that's what people really worry about is [/INST] they </s><s>[INST] they're not sure they can trust the government to not going to full dictatorial mode and and based on your political preference, your oppositions. You're basically one of the essential powers. Uh uh the freedom of speech in the United States is ability to criticize your government and that they they worry while can't the government get ahold of the N. S. A. And start to ask the basic question. Well, can you give me a list of people that are criticizing the government? [/INST] Think about. So let's just walk through that exact example, right? Because this is it's a preponderance. It's a it's a preponderance fear. It's a ridiculous fear because you would have to tap on multiple elements of government for anything to happen. So, for example, let's just say that somebody goes to the N. S. A. And says, hey, can you give us a read out on all the people who are tweeting terrible things about the president? Okay, cool. Here's your 100 million people, whatever it is, right? Here's all the people saying negative things about the government. So now they have a list. What do they do next? Well, let's just make it simple. They stay with N. S. A. And they say surveil them even more, tap their phones, tapped their computers. I want to know even more. So then they get this preponderance of evidence. What do you do with evidence? You take it to a court? Well, guess what? No court is going to support anything that goes against the freedom of speech. So the court is not going to support what the executive is asking them to do. Even before you take somebody to court, you have to involve law enforcement, essentially, you have to send some sort of police force to go apprehend the individual who's in question. Well, guess what doesn't meet criteria for any police force anywhere in the United States arresting people who have, who have to say negative things about the president? Now, if somebody poses a threat to the life of a public figure, the threat to life of a politician, that's a completely different case, which means the standards of evidence are much higher for them to arrest that person. So unless you create a secret police force, then your actual public police force is never going to take action. So all these people who are afraid of this, this exact situation that you're outlining, they need the creation of a secret police force, the creation of a secret court that operates outside the judicial system. The creation of a secret intelligence service that operates outside of foreign intelligence collection. Also that a handful of people who don't like the president, get what whisked away assassinated, put in prison, who knows what think about the resources that would be the amount of money and time, and how hard would it be to keep that secret to have all of those things in motion? The reason it worked in in Russia and soviet Germany or Russia and communist Germany was because everybody knew there was a secret police, everybody knew that like that there was a threat to work to speaking out against the government. It's completely different here. </s><s>[INST] Well there's a lot to say. So one is yes, if I was a dictator and I wanted to and just looking at history, let me let me take myself out of it. But I think one of the more effective ways is you don't need the surveillance, you can pick out a random person and and in a public display, semi public display, you know, basically put them in jail for opposing the government, whether they oppose it or not and the fear that sends a message to a lot of people, [/INST] that's exactly what you see happening in china, that's what you just light out, it's genius and that is the that is the standard </s><s>[INST] surveillance for that, [/INST] yep. </s>

<s>[INST] you're on your own, [/INST] you're on your own. You know, it's up to you. And Denise has always been that that that child that has expected someone to come in and save her </s><s>[INST] well and almost like it's all going to be okay. Somebody. [/INST] Yeah. And I knew it wasn't no. </s><s>[INST] Unless you, [/INST] unless you make it okay. It ain't going to be okay. You know, I was are </s><s>[INST] you able to forgive her? Your mom? [/INST] My my boundary with my mom. The reason I've not spoken with her, um, over two years ago, I started, um, this, this legal career of mine. I've been the guy who has, I spent a lot of time thinking about my past and those choices and what brought, brought those choices around. So I'm big about taking responsibility for my actions. I truly am. I think it's really important you have to do that. Well, my mom, not so much. So I was talking to her, you know, and I would start saying, you know, she was she would start the conversation talking about she didn't understand why Denise wouldn't speak to her anymore. That was one of her tropes. So in my response started to become well because you were the abuser and you spent your life doing that to her. So it's more healthy for her not to talk to you. So </s><s>[INST] she's still not able to see the flaws in the old her ways of the past. [/INST] No, not at all. So my my ultimatum to my mom was look when you're able to admit that you abuse the people in your life, accept that responsibility and be able to discuss it with me. We'll have a talk other than that I don't want to talk to you anymore. So for the first year it was you know calling cussing my wife out, cussing me out um you know I don't need you out of blah blah blah blah blah. And then finally it started to taper off and she's never really contacted me after that point. </s><s>[INST] Your dad is dying. What do you take from the way he's taken on death just saying fuck it. [/INST] You know it's the man </s><s>[INST] and what have you learned from your dad? What do you love about your dad? [/INST] He's one of these guys that you know like I told him I told my dad about about the abuse and everything else and there was a point, so you know I told you about the elevator stuff, but before that man, it was It took me 40 years to talk about that. But it also took me 40 years two to talk about. There was a point that my mom and dad would leave the house and I would urinate in the floor. </s><s>[INST] All [/INST] right. And </s><s>[INST] there's a like um out of anger. [/INST] No idea why. All right. But I would pick on the carpet, carpet designers like the Lebowski right, was really tied the room together together. I was talking about that and this lady comes up to me after the after the presentation and she had she had a career previous to that where she dealt with abused kids and she told me she was like Brett she's like um it's a control mechanism. The only control you had was that and she's like kids do that. And I was like, so I'm not unique. She's like no you're not unique in that. So um that you know this whole history of abuse Denise dealt with it by drinking by trying to commit suicide. Things like that. And then finally she escapes. I'm the kid that didn't and not only that my wife pointed out to me that it's again a set eastern Kentucky mentality stuff, you know, the male is expected to do things. So with with me it was it was almost like I stepped up to to take part in those crimes. So that Denise didn't didn't have to and she was able to avoid all that other than that one shoplifting stuff. Denise doesn't break the law anymore. She goes off to be a she's a she's a good parent, she's an angry parent, she's a good parent, she's a teacher, good citizen overall. I was just the guy that kept right on going with it, </s><s>[INST] keep on going. So let me ask you about that. So, um your life of [/INST] cybercrime in </s><s>[INST] describing some of the things you did or knew about, you said, quote, I once stole several $1000 worth of coins from a family trying to sell them to put a new roof on their home. Another time I sent a counterfeit cashier's check to a victim and he ended up being arrested for it. I lied to family, friends. Everyone I knew I was a truly despicable person. One of my Ukrainian associates script had someone who owed him money, kidnapped and tortured. He posted pictures of it online. Another member iceman used to flood his enemies email addresses with child pornography, then called the police on them. That's some stories, can you tell some of these stories that stand out to you that are particularly despicable or representative or interesting when you look back that that defined your approach and who you were at that time, [/INST] let me say that I did not care about my victim. Alright, I cared about me is what I cared about. Um It's rough to it's rough to admit that, you know that you don't give a sh it what you're doing anybody else, you only care about you. But that's that's the truth of the matter. I didn't care about the victims. Um The lady that was that wasn't even at the beginning of my career as a cyber criminal. That was right at the last of </s><s>[INST] it. [/INST] The coin lady I was by that point Shadow Crew had made the front cover of Forbes august of oh four october 26th oh four Secret service had shut us down. 33 people arrested six countries in six hours. I was the guy that was publicly mentioned is getting away. Um What happened was is I was the guy who was, I kind of invented this crime called tax return, identity theft and um I was stealing a lot of money. I went through all my Stateside savings and Shadow crew gets shut down. I don't have any way to come in with any money. So I start running counterfeit cashier's checks, defrauding people with that, having them send products or bullion collections, what have you by C. O. D. Collect on delivery and I would pay with it with a counterfeit cashier's check. This lady was on Ebay, she had been collecting these silver coins all of her life. You know the U. S. Currency used to be the coins used to be silver. So she had a whole collection of these things like I don't know 80 90 lb of this stuff. And I'm a very good social engineer. So convinced her that I was a legitimate person. That uh you know hey send it to C. O. D. You can use my Fedex account to do that through my ups account to do that. I'll pay with a cashier's check, you can take it in same as cash. She believed that she was even on the ad and we talked on the phone and everything else. She had told me that she was she was a single parent and it was the only money that she had to </s>

<s>[INST] right, We're just fitting within this [/INST] template that we inherit. That is </s><s>[INST] a [/INST] travesty really </s><s>[INST] glenn you've lived an incredible life, a productive one but just representing um some powerful ideas, some powerful [/INST] ideals, </s><s>[INST] but life comes to an end. Yeah. Do you think about your death? Are you afraid of it? [/INST] Well, it is a really interesting coincidence that you posed me that question because I'm coming from a funeral ah today is sunday </s><s>[INST] on the [/INST] preceding Tuesday five </s><s>[INST] days ago, I [/INST] was at the funeral of Eugene Wesley smith, who was my brother in law. He was my </s><s>[INST] sister's husband, [/INST] my sister Leah net passed </s><s>[INST] away in [/INST] august Of 2021. </s><s>[INST] Her [/INST] husband has </s><s>[INST] died at the age of [/INST] 68 </s><s>[INST] and [/INST] april of 2022. And I was at </s><s>[INST] his funeral, [/INST] he died suddenly of a heart attack that came completely out of the blue. He seemed to be in perfect health. He was a magnificent human being. I could go into the details, but </s><s>[INST] you know, [/INST] take my word for it. He was a businessman, a steel trader, metals trader, </s><s>[INST] he would buy [/INST] and sell. He worked mostly from his home office. He had clients, counter parties people, he did business with all over the world. Um He had three sons, one of whom is in his early thirties, two of whom are in their late thirties. These are my sister's Children, she's deceased now, he's deceased, the older two sons are severely developmentally disabled and although they were In their late 30s, they're not </s><s>[INST] independently viable. [/INST] They don't function effectively. Have to be cared for. That responsibility has now fallen to the family, but mainly to the surviving son who lives and with his wife and his two young Children, </s><s>[INST] uh, and has [/INST] assumed the responsibility. They cared at home. My sister and her husband, Wesley Eugene Wesley smith, care for their disabled </s><s>[INST] son's at [/INST] home. They didn't want to see them institutionalized. They had some help from programs at the state and social </s><s>[INST] worker and so on, but they [/INST] mainly took on the burden of caring for </s><s>[INST] them at home. [/INST] Anyway, I go on at length here and you know, I don't know how much of this you will choose to </s><s>[INST] make use of it. It [/INST] it doesn't matter really. I'm just trying to respond to your question. I was asked to offer some remarks at the funeral and I </s><s>[INST] offered them [/INST] and you know, I spoke well of this great man. He was a great </s><s>[INST] man. He had a straight [/INST] back, he was a stand up guy. He could be counted on his word was his bond. He had broad shoulders, </s><s>[INST] He carried a lot of people [/INST] with him, business associates, family members and so forth and so on. He had a huge heart. He was a giving and kind person. He had a great mind. He was an intellectual, even though as a businessman, much of his day was taken up with the, </s><s>[INST] you know, [/INST] minutia of contracts and you know, the details of the order being delivered and not being delivered of the quality of the product of the financing and so forth. And so yeah, </s><s>[INST] he was a powerful mind and he [/INST] studied, he read books, he was interested in music and art. He was uh he's a spiritual seeker, had been ordained as a child minister in his youth and while he remained a master of the christian canon, he also explored Eastern religion and other spiritual </s><s>[INST] paths and [/INST] kind of stood above any particular tradition as a man who believed in God. But thought that God manifests himself in many ways to human beings and that there was much to learn from other religious traditions as well. This is Wesley we called him Wesley by his middle name, Eugene Wesley smith, May he rest in </s><s>[INST] peace, [/INST] 68, that's five years younger than I am right now. He dropped dead without any warning. I could too. So how </s><s>[INST] does that make you feel? What were the thoughts in your mind leading up to it? Having to give that speech in the days that followed. [/INST] First of all, I wonder what would I say? What would I say? And you know, there was no way to prepare. And I decided, you know, I I rehearsed in my mind this, you know, he had straight back, he had broad shoulders. He </s><s>[INST] had a big heart. He had [/INST] a great mind, you know, he had a </s><s>[INST] capacious [/INST] spirit and whatnot. And I use that as a </s><s>[INST] template for making my remarks. [/INST] But my main thought </s><s>[INST] was my God, [/INST] life is precious </s><s>[INST] and life is [/INST] fleeting </s><s>[INST] and death [/INST] is a part of life. </s><s>[INST] My death is a part of [/INST] my life. Uh, and I thought, you know, well I want to take better care of myself than </s><s>[INST] I do, you know, etcetera, etcetera. But I also [/INST] thought a lot of this </s><s>[INST] is not in my hands [/INST] at all. I </s><s>[INST] Thought one should have [/INST] his affairs in order. My brother did not have all of his affairs in order in the sense </s><s>[INST] that there is a lot of, [/INST] you know, things are going to probate. There was no will. There's you know, this is kind of unsettled. I don't want that </s><s>[INST] to happen to my [/INST] surviving </s><s>[INST] family members. I want to have my [/INST] affairs such that should heaven forbid I fall over </s><s>[INST] one day and don't [/INST] get up again. People don't have to scramble about how to how to </s><s>[INST] take care of things from [/INST] from that point forward. </s><s>[INST] But as a human, are you afraid? I'm [/INST] afraid now I </s><s>[INST] read this wonderful book called the [/INST] Swerve. It's it's about Lucretius. It's about </s><s>[INST] the [/INST] nature of things which is this great classical work from the roman period by this guy, Lucretius. And I'm trying to think of the name of the author. But you can look it up. The swerve is the book and one like a national book Award or Pulitzer prize. It's and it's the history of the </s>

<s>[INST] So inside the laboratory gain of function research on viruses. And I believe most of that kind of research is doing this exact thing that you're referring to which is accelerated evolution and just watching evolution to his thing and a bunch of viruses and seeing what kind of tricks get developed. The other method is engineering viruses. So manually adding on the tricks what which do you think we should be thinking about here. [/INST] So mind you I learned what I know in the aftermath of this pandemic emerging. I started studying the question and I would say based on the content of the genome and other evidence in publications from the various labs that were involved in in uh generating this technology. A couple of things seem likely. This SARS Cov two does not appear to be entirely the result of either a splicing process or serial passages. It appears to have both things in its past or it's at least highly likely that it does. So for example, the firm cleavage site, it looks very much like it was added in to the virus and it was known that that would increase its infectivity in humans and increase its trumpism. The virus appears to be excellent at spreading in humans. And minks and ferrets. Minks and ferrets are very closely related to each other and ferrets are very likely to have been used in a serial passage experiment. The reason being that they have an ace two receptor that looks very much like the human Ace two receptor. And so, were you going to passage the virus where its ancestor through an animal in order to increase its infectivity in humans, which would have been necessary? Uh ferrets would have been very likely. It is also quite likely that humanized mice were utilized and it is possible that human airway tissue was utilized. I think it is vital that we find out what the protocols were If this came from the Wuhan Institute, we need to know it and we need to know what the protocols were exactly. Because they will actually give us some tools that would be useful in fighting SARS COV two and hopefully driving into extinction which ought to be our priority. It's a priority that does not, it is not apparent from our behavior, but it really is uh it should be our objective. If we understood where our interests lie, we would be much more focused on it. Um, but those protocols would tell us a great deal if it wasn't the Wuhan Institute, we need to know that if it was nature, we need to know that and if it was some other laboratory, we need to figure out who wasn't where so that we can determine what is what we can determine about, about what was done. </s><s>[INST] You're opening up my mind about why we should investigate why we should know the truth of the origins of this virus. So for me personally, let me just tell the story of my own kind of journey. Uh, when I first started looking into the lab leak hypothesis, what became terrifying to me and important to understand and obvious is the sort of like Sam Harris way of thinking, which is it's obvious that a lab leak of a deadly virus will eventually happen. My mind was it doesn't even matter if it happened in this case, it's obvious that's going to happen in the future. So why the hell are we're not freaking out about this. And COVID-19 is not even that deadly relative to the possible future viruses. It's the way I disagree with them on this. But he thinks about this way about A G. I. As well about artificial intelligence. It's a different discussion I think. But with viruses it seems like something that could happen on the scale of years, maybe a few decades A. G. I. Is a little bit farther out for me. But it seemed the terrifying thing seemed obvious that this will happen very soon for much deadlier virus as we get better and better at both engineering viruses and doing this kind of evolutionary driven research, gain of function research. Okay. But then you started speaking out about this as well but also start to say no no no. We should hurry up and figure out the origins now because it will help us figure out how to actually respond uh to this particular virus, How to treat this particular virus. What is in terms of vaccines in terms of antiviral drugs in terms of just and although the the number of responses we should have. Okay, I still much more freaking out about the future. Maybe you can break that apart a little bit. Which are you most focused on now, which are you most freaking out about now in terms of the importance of figuring out the origins of this virus. [/INST] I am most freaking out about both of them because they're both really important and you know we can put bounds on this. Let me say first this is a perfect test case for the theory of close calls because as much as Covid is a disaster, it is also a close call from which we can learn much. You are absolutely right if we keep playing this game in the lab, if we are not uh if we are especially if we do it under pressure and when we are told that the virus is going to leap from nature any day and that the more we know the better we'll be able to fight it. We're going to create the disaster all the sooner. So yes, that should be an absolute focus. The fact that there were people saying that this was dangerous back in 2015 I ought to tell us something. The fact that the system bypassed a ban and offshore the work to china ought to tell us this is not a chinese failure. This is a failure of something larger and harder to see. Um but I also think that there's a there's a </s>

<s>[INST] interesting. That's sad. That was, you know, one of the and to me, I mean, as a fan of both, that was a beautiful moment is uh is a kind of passing of a torch in a sense of exceptional performance. Like another one that stands out to me, maybe you can comment as, I don't understand. Well, maybe I do why Connor McGregor gets as much hate as he does, He probably revels in it, but I think he doesn't get enough credit for uh Jose Aldo for the for like for basis, you know, knocking him out in the in the first few seconds of the fight. I mean, josiah is like one of the greatest fighters ever. Uh maybe some people can be even putting them in the top 10 and the, like, I don't understand why it doesn't get as much like economy Gregor doesn't get as much credit as I think he deserves for that and for Eddie Alvarez and all the fights for some reason. Whenever uh Connor McGregor beat somebody well that they were not that good then, like it means like they were they were there's something was off [/INST] convenience. </s><s>[INST] Yeah, it's quite strange to me. But I mean, what are your thoughts on the Um on Connor McGregor? Maybe one way to ask that I'm rushing some obviously also could be fan, but I'm also a condom fan. It seems like there's not many of us core, like fans of both. Um what are your [/INST] thoughts? And </s><s>[INST] uh the two of us, which also is a good thing. Uh Yeah. Really, really tough dude. [/INST] Just like five languages. Really </s><s>[INST] interesting cat also. Oh wow, I didn't know that side of it. There's a brain there. Well on the could be versus Connor, what do you make of their first fight? What do you do you agree with me that they should fight again because I think it would be awesome if they fought again in Moscow. And uh do you agree with me? I'm just gonna put say things that pissed people off, but I believe is that Conor actually has a chance to be, could be [/INST] one, the counter absolutely has a chance to be. Connor has a chance to beat anyone that he steps into that ring with and not just like a mathematical chance, you're like, oh one of the billion, but like, you know, like he absolutely uh it's funny because I won't pretend to know Connor really well, but I first met Connor in 2010 when I was teaching a seminar in a straight blast gym Ireland in Dublin. Um and that's actually where I first met all of the coaches that ended up being on Conner's team, um you know, john Cavanagh on Roddy Gunnar nelson, you know, so for I actually enjoyed being an ultimate fighter and being on uh your favorite team and getting a train with all the guys there, but at the same time, the people that I was actually, I knew better. We're actually the european side, all all the Conners coaches. Um and uh that was a neat thing because I got to met Connor, I didn't know who Connor. Connor wasn't. Counter at that point. </s><s>[INST] Yeah, that was before, has UFC? [/INST] Oh, yeah, well, well before, yeah, I think, I think he got in like 2014, maybe something like that. Yeah, and uh anyway, but he was doing well in Cage Warriors, winning the titles there, I think prior to that, you know, I remember going seeing him on the show and also then get into train because I, I competed uh was initially slated to fight David Tamer for the ultimate fighter finale before getting put into fighting for the title for the show. So I went over to Ireland to train for a couple of days and basically it was neat to watch them watching work. I mean man is focused and trains a lot. It's very, very smart and very, very hard working and I think a lot of times people get stuck in the, in this um you know, and they almost want to believe that this was lucky or this, this person, you know, that they're not working that hard, they're just out there, they got their with their mouth and that's, that's just not the case and um you know, I don't know what it's like, you know, obviously Con is very well off right now and I don't know how hard, how seriously is training what he's doing, I can't speak to any of that, but there's no question that, that he has skills to be dangerous. And one of the funny things, obviously that could be fight, what could be his way, it could be, was a great fighter and also has the chance to beat anyone in that ring at any given time. But there was, there was Connor, you know, it's uh one that he can he can put anybody away and as you mentioned, I think that he doesn't get the credit for the Eddie Alvarez fight doesn't get the credit for that Jose Aldo fight because it was almost so much of a letdown. I remember that happened the same weekend, that the ultimate fighter finale and you're like, wait, </s><s>[INST] what? [/INST] Yeah, it almost doesn't feel like a fight happened, but we mentioned Miyamoto Musashi, I mean Musashi was famous for the way he poked and prodded that people with what he was doing, whether overtly or not. It's like we're supposed to fight to the death and uh you know, at three p.m. Tomorrow, great four p.m. Rolls around and it's not there five. I mean, you remember all the all the antics and nonsense that Connor was pulling prior to that, like speaking person, that's not, it's not something I would feel comfortable doing, but it's like everyone's different. And the effect it had on, on Jose was, I mean, beyond evident. When was the last time josie started started to fight with leaping left hand, leaping right hand, you're like, wait, what? And then he was obviously, you know, living rent free and joseph's head at that point and that was a combination of psychological, you know, ability and wherewithal and then physical and remind me of the way Muhammad ali would would bother people and whatnot. And uh the fact that he's a polarizing figure, um I think makes some people not give him his due. And then at the same time sometimes certain fans maybe go overboard. But remember the knee that Ben Aspirin got knocked out with by model. I mean that was an amazing, unbelievable thing, but three inches to the right of three inches to the left, I guess, whichever side his head wasn't now, you could have been squarer, but uh and that fight starts with Ben Aspirin on top of you in the first five seconds. Well, Connor ran it through a knee, just like that. It could be even could be got right around it. That could have easily gone the other way. Can you imagine what would have happened if after the, after coming back from boxing? Um after coming back from, from the Mayweather fight could be in the 1st 10 seconds over and you're like, he would, it would have been intolerable, but basically, yeah, you know, But see here's the </s>

<s>[INST] you're pretty close aren't very good. You're not [/INST] music because every predicate is invented to decrease an invisible set of functions. </s><s>[INST] So you talk about admissible set of functions and you talk about good functions. So what makes [/INST] a good function? So admissible set of function is set of functions which has small capacity of small diversity. Small VC dimension itself. Which contains good function </s><s>[INST] insects by the way for people who don't know the sea. Um You're the V. And the V. C. Uh So uh how would you describe your labors and what VC theories? Uh how would you describe [/INST] your cover machine? So machine capable to pick up one function from that miserable set of function. But set of admissible function can be big. They contain all continuous functions and it's useless. You don't have so many examples to pick up lunch but it can be small. Small. Uh huh. They call it capacity but maybe better called diversity. So not very different function in the set is infinite set of function but not very diverse. So it is small. This dimension when this dimension is small, you need not you need a small amount of training debt. So the goal is to created miserable set of functions which is have small visit dimension and contain good function. Then you should then you will be able to pick up the function using small amount of considerations. </s><s>[INST] Okay, so that is the task of learning is creating a set of admissible functions that has a small VC dimension. And then you've figure out a clever way of picking up. [/INST] No, that is the goal of learning we carefully formulated yesterday. Statistical learning story does not involved in Creating admissible set of function. In classical learning. Sorry, everywhere. 100%. In textbook the set of function admissible set of function is given. But this is science about nothing because the most difficult problem to create a miserable set of functions given say, oh, a lot of functions, continuous set of functions created miserable set of functions that means that it has finally see dimension small VC dimension and contain good function. So this was out of consideration. </s><s>[INST] So what's the process of doing that? I mean, it's fascinating. What is the process of creating this? Um admissible set of [/INST] functions. </s><s>[INST] That's the various can you describe invariance, [/INST] your protectees of training data and properties means that you uh have some function and you you you just count what is will your average value of functional training data? You have model and what is the expectation of this function on the model and they should coincide. So the problem with about have to pick up functions, it can be any function. It uh In fact it is true for all functions but because when you're talking said say duck does not jumping. So you don't ask questions jump like a duck because it is three really does the junk engine doesn't help you to recognize you. But you know something which question to ask and you're asking for it seems like the job like a duck but looks like a duck. It is general situation looks like see guy who have this illness. Is this disease? It is legal. Yeah. So there is a general type of predicate looks like a special type of predicate which related to this specific problem. And that is intelligence part of all this business and that we're teachers involved </s><s>[INST] incorporating the specialized predicates. Uh okay, what do you think about deep learning as as um the neural networks, these arbitrary architectures as helping accomplish some of the tasks. You're thinking about their effectiveness or lack thereof? What are what are the weaknesses and what are the possible strengths? [/INST] You know, I think that this is fantastic. Everything which like deep learning's like features. Let me give you this example one of the greatest book this Churchill book about history of Second World War and he starting this book describing that in all time when war is over. So the great kings the Gaza together most all of them were relatives and they discussed what should we don't have to create peace. They came to agreement and what what what happens first world war. The general public came in power and they were so greedy that robbed Germany and it was clear for everybody that it is not peace. That peace will last only 20 years because they was not professionals in the same way she in machine learning. There are mathematicians were looking for the problem from very deep point of your mathematical point and there are computer scientists, there's mostly does not know mathematics. They just have interpretation of that. And they invented a lot of blah blah blah interpretations like deplore nick, why you did diplomatic matter does not know deploying mathematic does not know neurons. It is just function. If you like to say piecewise linear function, say that and doing in class of piecewise linear function. But they went something and then they try to prove advantage of that through interpretations. Rich mostly wrong. And then most enough they appeal to brain which they know nothing about that. Nobody knows what's going on in the brain. So I think that more reliable local mass. This is what a magical problem to your best to solve this problem. Try to understand that there is no only one way of convergence which is strong way of convergence. There is a victory of convergence which requires predicate. And if you will go through all this stuff you will see that you don't need deployment even more. I would say one of the story um which called represent bacteria. It says that optimal solution of methodological problem which is which described learning his own shadow network not uploading </s>

<s>[INST] And there's there's something about music to see, basically have to make music of all the moments of life. And there is something about why is music so compelling? And when you listen to it, something about certain kinds of music it connects with you. It doesn't make any sense. But in that same way for Nietzsche, you should be a creative force that creates musical masterpiece. [/INST] Exactly. And I think what's interesting is the question, what does it mean to be a creative force? There? There's a traditional notion of creation that we associate with with God. God creates X. Nial O out of nothing. And you might think that Nihilism thinks that we should do that create X Nello, because it's about how there's nothing at our ground. But I think the right way to read Nietzsche is to recognize that we don't create out of nothing. Miles Davis wasn't nothing that situation pre existed him, it was given to him, maybe by accident, maybe it was a mistake, whatever. But he was responding to that situation in a way that made it, right. He wasn't just creating out of nothing he was creating out of what was already there. </s><s>[INST] So that makes that first date with the climbing hand even more complicated because you're giving a climb your hand, you're gonna have to make art and music out of that. Exactly. That's the responsibility for both for both of them, wow, that's a lot of responsibility for the first day because you have to create it. So the emphasis isn't just on making decisions, it's on creating [/INST] and but also on listening, Right? I mean, Miles Davis was listening. He heard that he knew it was wrong. And the question was, what do I play that makes it Right? </s><s>[INST] So let me ask about Nietzsche is God dead? What do you mean by that statement? What's in your sense? The truth behind the question and the possible set of answers that our world today provides [/INST] good. So, I mean, I think that There's something super perceptive about niches diagnosis of the condition at the end of the 19th century, so not so far from the condition that I think we're currently in? And I think there's an interesting question, what we're supposed to respond, what we're supposed to do in response, but what, what is the condition that we're currently and when Nietzsche says, God is dead, I think like I was saying before, he means something like the role that God used to play in grounding our existence is not a role that works for us anymore as a culture. And when people talk about a view like that nowadays, they use a different terminology, but I think it's roughly what nature was aiming at, they say we live in a secular age. Our age is a secular age. And so what do people mean when they say that? I think first of all, it's a descriptive claim, it could be wrong. The question is, does this really describe the way we experience ourselves as a culture or as a culture in the west or wherever it is that we are? So what does it mean to say that we live in a secular age, An age in which God is dead? Well, the first thing is, it doesn't mean there's no religious believers because there are plenty, there are lots of people who go to church or synagogue or mosque, you know, every week or more. And there are people who really find that to be an important aspect of, of the way they live their lives. But it does mean that for those people, the role of their religion, the role that the religious, their religious belief plays in their life isn't the same as it used to be in previous ages. So what's that role, We'll go back to the high middle ages. That was clearly not a secular age. That was a religious age. And so there we are in 1300 Dante is writing the divine comedy or something. And what did it, what did it mean then to live in a sacred cage? Well, it meant not just that the default was that you were a christian in the west, but that your Christianity, your religious belief, your religious affiliation justified certain assumptions about people who didn't share that religious belief. So you're a Christian in the west in 1300 and you meet someone who's a Muslim and the fact that they don't share your religious belief justifies the conclusion that they are less than human. And that's, that was the ground of the, you know, the crusades. That was the religious wars of the, of the high Middle Ages. We live in it to say that we live in a secular age is to say that not that we don't have, there aren't a lot of people who have religious belief, there are, but it's to say that their religious belief just doesn't justify that conclusion. If you're a religious believer and you meet me and suppose I'm not a religious believer, learning that about me doesn't justify your concluding that I'm less than human. And that's the kind of liberalism of the, of the modern age, most, most of the time, we think that's a good thing. We let 1000 flowers bloom. There's lots of ways to live a good life and there's some way in which that, that is a nice, progressive kind of liberal thought, But it's also true that it's an undermining thought because it means if you're a religious believer now, your belief can't ground your understanding of what you ought to be aiming at in life, in the way it used to be able to, you can't say as a religious believer, I know it's right to do this because you also know that if you meet someone who doesn't share that religious belief and so doesn't think it's right to do that necessarily or does, but for different reasons, you can't conclude that they've got it wrong. So there's this sort of unsettling aspect to it. </s>

<s>[INST] york? This was one of the both. I hate it when people talk like this, we're gonna do it Anyway. This was one of the hardest and easiest decisions of my life. It was hard because I've lived in new york since I was two other than college. It's the only home I've known. I know it intimately, I know all the cool spots. I love it with every fiber of my being or I did. Uh it was very much, you know, ingrained in my personality, my outlook about what cities can be and can be and should be and shouldn't be um deciding to move was not done. But when you see your crew, your chosen family, one by one, whittling away, it's not easy. Um they all left. Uh there's just a couple of us left in new york and I don't see any mechanism by which new york is going to improve. Things are getting much worse all the time. It's just completely outrageous here. I would have a have a huge crew. I didn't realize how much cheaper real estate is than in new york. This is another way. So new Yorkers are the most provincial people on earth who are completely oblivious to the rest of the country. So for a long time the argument was new york versus L. A. Right for certain types of people. And they would say L. A. Is cheaper in terms of rent. The new york, let's suppose the rent is 1700. But you have to get a car like this is kind of a wash. So I assumed Austin would be like 80% of New York prices and I'm looking at these houses and for like 700,000 you could get a house here that would cost like 3.5 million New York. So, and you can have a gun and it's just like I could have a yard and I could have a dog and I have a three bedroom and I could have, you know, aquariums and my weird plants. So to have all that. And it's just to have, I am very, very lucky that I have such a supportive crew and they're also very smart because they sat me down and they said whatever excuse you have not to move here, we are going to make sure that doesn't count. So my buddy matt said because I have a huge library, he goes, I will go to your house and I will pack every single book you own myself. So you can get that as an excuse the other way, I know how to drive near this. You cou um she's like we're going to take driving lessons together. There goes that excuse, how do I find an apartment there, like we'll go to with the realtor will take pictures for, you will report back, you could trust our judgment. And I'm like, that's what I would do. That. That sounds like fun shopping for houses that up to buy them. Then matt just yesterday had the idea goes, come here, rent a furnished apartment for a few months, you don't have the pressure of buying and it's just, it's gonna be an easy transition. The rent is not gonna be anything compared to new york. I'm like, these are all very valid things. You're here, lots of other people, [/INST] by the way, that's what this is, is uh made sure that's renting month to month, </s><s>[INST] this is rental, [/INST] this is rental. You didn't realize this. I thought you bought this. No, no, no to talk, </s><s>[INST] I thought you bought it. [/INST] No. Well, I really value freedom. </s><s>[INST] So who are you talking to? Have heard of this thing? Freedom. It's really great. [/INST] But not everybody in the implementation </s><s>[INST] of freedom is different for everybody, [/INST] of course, for me, I don't want to uh make a statement about others. I'll just speak for myself. I think when you buy a house that is not just a wise financial decision or all those kinds of reasons that people have investment, all those kinds of things. I think it's also a hit on your freedom because the positive way to frame that is you make it a home, you have a deep connection to it? But the negative way to frame it is you're now a little bit stuck there and you may stay there way longer than you should one much better opportunities for life come up. There's there's stages in life when you're not sure exactly what the future will hold, I would argue that's very often the case uh basically at every stage in life, and I just want to make sure I maximize the freedom to uh to embrace the most ambitious, the craziest, the wildest, most beautiful opportunities that come by. You've actually brought this up because I said, I really enjoyed the conversation with you and you're on like you talking to you and somebody else. I think you make a really significant effort, you've said this before, but it really is true, and it stands in contrast to other folks who are also good conversation. You really make an effort for that person, like to understand like, to meet the person for sure. And that's uh you made me, you made me realize it's kind of a uh it's an art form uh but it's also just it's a thing worth doing of putting in that effort and that leap of humanity to to like reach, but whether you're talking to Dave Rubin or Alex jones or joe or me just Yeah, those are different human beings and they're taking that leap? It's fascinating. I mean, do you have um how do you think about that? </s>

<s>[INST] So now in retrospect, you see yourself as were being afraid, Do you do you think at the time [/INST] we wanted people to like me which is that it was just the disease of humanity, right? Is that we want to be liked and what happens is if you want people to like you and love you even you want people to feel comfortable with you </s><s>[INST] and those are people like your family, [/INST] friends or my family, I would always, you know, could always throw in the street. But my I'm kidding, I mean, but I am not. Uh but my friends, my circle of friends, which I were my family at the time when you're uh senior, when your 10th, 11th grade in high school, your your friends or your family, you know what I mean? Like that's your so you don't want to do anything that puts you on the outside of the circle. </s><s>[INST] Just thinking back to that fear is there are things you're afraid of now you're not doing, you're afraid to do. [/INST] I'm afraid of all kinds of things. I'm afraid of not being good at my job, not being funny, letting people down. Uh not putting out products that are good. You know, whether it's the podcast every week or stand up for the video is like, I'm afraid of like, there's a ton of people that really enjoy what we do. So when you're in that position, you're nervous that you're going to start doing things that they don't like. So the new things you want to do, the evolution you wanna do, you wanna make sure you're evolving in the right way. You know, you want to make sure that you're doing things that are consistent with why people like you, but also you don't want to put yourself in a box and limit what you can be going forward. So like I had a talk with the ceo of Nbcuniversal ones, I was doing some internal sketch for, for them? And I was playing like a cab driver and he was a, and he's not the current Ceo because the former Ceo and I said, well what's the hardest part of a running a corporation of this size? And he said something very interesting. Uh he said, the hardest part is maximizing the current prophet model of what you have at the same time, getting ready, getting ready, getting the company ready for where it's going to be in five years. He said those are often at odds and that's the toughest thing he goes because I could just bang out everything I got to do right now and we're gonna make a lot of money doing this. But am I devoting enough resources into digital? So that in five years when that's where everything lives, are we competitive in that space? So it's funny as I am now, hopefully to people and a lot of the things that I want to do now, I'm going, what am I what groundwork? Am I not laying for 3 to 5 years down the road so that I can be adapting to the trends that are important then in terms of not so much comedic trends, but like the technological trends like what is the, what is it, you know, I should have done podcasting earlier. What should I, should I have a bigger presence on Tiktok should have a bigger presence here, should have a business, But should I be on twitch, should I be doing this? Should be doing that. What am I not doing that? I should be doing that. I'll regret not doing. And those are, those are the conversations I think I have in my own head all the </s><s>[INST] time. And I guess there's parallels to coming out as gay or just parallels in like a career path you're taking all that. That's ultimately just fear. [/INST] It's fear. It's the fear of, you know, the best thing that happened in my career was that I came to L. A. I didn't, I have an idea of what was gonna happen. I met somebody who was really, uh, committed to making funny things that we just wanted to be funny. No one would let us be funny. We didn't have Comedy central letting us be funny. We didn't have HBO, we didn't have netflix, we just had a garage and a phone in the beginning and then a camera and then a thing and we just wanted to be funny. And that was the greatest risk really I took because I was like, well, I don't know what else is going to happen right now, but I just want to be funny and funny, saved my life right at me funny, got me out of drugs. Funny, probably got me out of the closet. Funny was the thing that I was able to do that made everything okay in my own head. So I was like, as long as I'm being funny, something good will happen. So we did that and that's something really cool happened. That we were able to do a lot of cool things. But you know, that's what it is. It's fear that keeps you from being the better version of yourself. </s><s>[INST] Your mom, you have so many complicated, fascinating parts of your story. But your, your mom uh as you were growing up, suffered well from out to in this. Yes, because a free Nia, can you tell her story and how that relationship has changed over the years? [/INST] Yeah. Well she was always eccentric and always, you know the terms for schizophrenia in an irish catholic household where we didn't talk about anything weird, eccentric, fun. She's fun. There's a theme to this unpredictable. She's uh, while she was a live wire, any of the words you would use to describe somebody who is a fucking lunatic, but you wouldn't say that. Um </s>

<s>[INST] Yeah, it almost absolutely seems to be the case. So you don't have to ask the question of how do we change our supply chains, whether it's making more resilient or make them less densely connected, um, you know, building, uh, like, uh, what is it, you know, the Tesla model for in the automotive sector of like trying to build everything like trying to get the factory to do as much as possible with as little reliance on widely distributed, uh, sources of the supply chain as possible. So maybe like rethinking how much we rely on the infrastructure of the supply chain. [/INST] Yeah, I mean, you know, there's some basic and I assume right that that there are a lot of folks in corporate boardrooms looking at risk and saying that didn't go well and maybe it could have even gone worse. Um maybe we need to think about reassuring, right? Um at the very least one of the things that I'm hearing about anecdotally is that they're storing stuff up, you know, when they can write um which is that's not that's probably not sustainable, right? I mean at some point, somebody in that corporate boardrooms going to say, you know, guys, inventory is getting kind of having the cost of that is like, do we can we really justify that much longer to the shareholders? Right. Um We should, we can back off and start back things are back to normal, let's lean out. </s><s>[INST] Well, my hope is that there's a technology solution to a lot of aspects of this. So one of them on the supply chain side is collecting a lot more data, like having much more integrated and accurate representation of the inventory all over the place and the available transportation mechanisms, the trucks, the all kinds of freight and how in the different models of the possible catastrophes, catastrophes that can happen. What like how well the system responsible, having a really solid model that you're operating under as opposed to just kind of being in an emergency response mode under poor incomplete information, which is what seems like is more commonly the case except for things like you said walmart and amazon, they're trying to internally get their stuff together on that front, but that doesn't help the rest of the economy. So um another exciting technological development as you write about as you think about is autonomous trucks. So these are often brought up in different contexts as the uh examples of ai and robots taking our jobs. How true is this? Should we be concerned? [/INST] I think they've really come to epitomize this anxiety over automation, right? Just it's such a simple idea, right? Truck that drives itself, you know, classic blue collar job that pays well. You know, um guy maybe with not a lot of other good options, right? Um to sort of make that same income easily. Right? And you build a robot to take his job away. Right? Um, so I think 2016 or so that was that was the big question out there. And that that's actually how, I I started studying it. Right? I just wrapped up the book just so happened that somebody who was working at Uber Uber, I just bought Otto saw the book and was like, hey, can you come out and talk to our engineering teams about what what life is like for truck drivers and maybe how our technology could make it better and you know, at that time there were a lot of different ideas about how they were going to play out, right? So um while the press was saying, you know, all truckers are gonna lose their jobs, There were a lot of people and and um these engineering teams who thought, okay, you know, if we've got an individual owner operator, You know, and and they can only drive eight or 10 hours a day, you know, they hop in the back, they get their rest and the asset that they own works for them, right, sort of perfect, right? Um and at that time, you know, there were a bunch of reports that came out and basically what people did was they took the category of truck driver, you know, some people took a larger category from BLS of you know sales and delivery workers. That was about 3.5 million Workers and and others took the heavy duty truck driver category, which was at the time about 1.8 million or so. And they, you know, pick the start date and a slope and said, you know, um let's assume that all these jobs are just gonna disappear. And um really smart researcher. And at a Bernhardt at the labor center at U. C. Berkeley was sort of looking around um for people who were sort of deeply into industries to complicate those Analyses, right? And reached out to me and was like, what do you think of this? And I said the industry super diverse. You know, this is just haven't given a ton of thought, but can't be that, you know, it's not that simple, you know? I mean, it never is. Um and so she was like, well, you, you know, will you do this? And I was like, ready to move on to another topic, you know, I'd like been in trucking for 10 years. Um and that that's how I started looking at it. And it is, it's a lot more complicated and the the initial impact and here's the challenge, I think, and it's not just a research challenge, it's the fundamental public policy challenge is we look at the existing industry and the impacts, the potential impacts, they're not, you know, nothing for for some communities and some kinds of drivers, they're going to be hard. And and there and there are a significant number of nowhere near what people thought, you know, I I estimate like around 300,000, but that's a static picture of the existing industry. And here's the key with this is at least in my, my conclusion is, this is a transformative technology, we are not going to swap in self driving trucks for human driven trucks, and all else stays the same. This is going to reshape our supply chains, it's going to reshape landscapes, it's going to affect our ability to fight climate change. Um this is a really important technology in this space, </s>

<s>[INST] And would you put that under the category? Just gauge transformations? [/INST] Yes, that would be gauge transformations applied to sections and connections where connections are the derivatives in the theory. This is easily explained. It is pathological that the community of people who understand what I'm saying have never bothered to do this in a clear fashion for the general public. You and I could visualize this overnight. This is not hard. The public needs to know in some sense that, let's say quantum electrodynamics. The theory of photons and electrons more or less electrons are functions and photons are derivatives. Now there's some you can object in some ways, but basically a gauge theory is the way in which you can translate uh, a shift in the definition of the functions and the shift of the definition of the derivative so that the underlying physics is not harmed or changed. So you have to do both at the same time. Now you and I can visualize that. So if what you wanted to do rather than going directly to geometric unity is that I could sit down with you and I could say here are the various components of geometric unity and if the public needs a visualization in order to play along, we've got a little over two months and I'd be happy to work with you. </s><s>[INST] I love that as a challenge and I'll take it on and I hope we do make it happen and David Goggins, [/INST] if lex doesn't do some super macho thing, because you've got to work to get some of this stuff done, uh, you'll understand he'll be available to you after april. Thank you for the </s><s>[INST] thank you for this escape clause. I really needed that escape [/INST] Clause. I'm glad that 48 miles and 48 hours, by the way, I just want to say how much I admire your willingness to keep this kind of hardcore attitude. Um, I know that Russians have it and Russian jews have it in spades, but it's harder to do in a society that's sloppy and that's weak and that's lazy. And the fact that you bring so much heart to saying, I'm going to bring this to Jiu Jitsu, I'm going to bring this to guitar. I'm going to bring this to a, I'm going to bring this to podcasting. Uh it comes through loud and clear and I just find it completely and utterly inspiring that you keep this kind of hardcore aspect at the same time, that you're the guy who's extolling the virtue of love in a modern society and doing it at scale. </s><s>[INST] Thank you, that means a lot, I don't know why I'm doing it, but I'm just following my heart on it and just going with a gut, it seems to make sense of how [/INST] I personally think we better get tougher or we're going to get in a world of pain and I do think that when it comes time to lead, it's great to have people who, you know, don't crack under pressure. </s><s>[INST] Do you mind if we talk about love and what it takes to be a father for a bit? Do you mind if Xev joins us? [/INST] I'd be an honor? </s><s>[INST] Okay, so eric I've, uh, talk to your son Zev who is an incredible human being. But let me ah ask you this might be difficult because you're both sitting together. What advice do you have for him as he makes his way in this world? Especially given that, as we mentioned before on joe Rogan, you're flawed in that just like all humans, you're mortal. [/INST] Well, at some level, I guess one of my issues is that I've got to stop giving quite so much advice. Uh, early on, I was very worried that I could seize EVs abilities and I could see his challenges and I saw them in terms of myself. So a certain amount of Zev rhymes with whatever I went through as a kid and I don't want to doom him to the same outcomes that, That sufficed for me. I think that he's got a much better head on his shoulders at age 15, he is much better adjusted and in part it's important for me to recognize that because I think I did a reasonably decent job early on, I don't need to get this part right, and you know, I'm looking at xev trajectory and saying you're going to need to be incredibly, even pathologically self confident. The antidote for that is going to be something you're going to need to carry on board, which is radical humility. Um you're gonna have to have those in a dialectical tension which is never resolved, which is a huge burden. You are going to have to forgive people who do not appreciate your gifts because your gifts are clearly evident, and many people will have to pretend not to see them, because if they see your gifts, then they're gonna have to question their entire approach to education or employment or critical thinking. And what my hope is is that you can just forgive those who don't see them and who complicate and frustrate your life and realize that you have to take care of them too. </s><s>[INST] So let me ask you the more challenging question, because the guy is sitting right here, what advice do you have for your dad since after talking to you, I realize you're the more brilliant aside from the the better looking uh member of the family. Um [/INST] I have a question, </s><s>[INST] uh sorry, can say anything [/INST] you want is the last time we're gonna be seeing </s><s>[INST] left awkward drive home. Mhm. [/INST] I think sort of a new perspective I've taken on parenting is that it is a </s><s>[INST] task for which no [/INST] human is really supposed to be prepared. You know, there are </s><s>[INST] uh jewish tradition [/INST] for example, there uh myriad analogies in the Torah and the tall mood that compare um the role of a parent </s>

<s>[INST] That's bioinformatics. It could be a bioinformatics too. And it could yeah, it could be a person by person related but I just don't feel the warmth and love that. I would, you know, you talk about the Seminole people who are french and artificial intelligence France, welcomes them with open arms in so many ways. I just don't feel the love from Russia. I I do on the human beings like people in general like friends and and just cool, interesting people. But from the scientific community. No conferences, no big conferences and it's uh [/INST] yeah, it's actually you know, I I'm trying to think, yeah, I cannot recall any any big ai conferences in Russia. </s><s>[INST] It has an effect on for me. I haven't sadly been back to Russia. So she but my problem is is very difficult. So I'm now I have to renounce the citizenship always the right. I mean I'm a citizen of the United States and it makes it very difficult. There's a mess now right. So I want to be able to travel like, you know, legitimately and uh it's not it's not an obvious process. They don't make it super easy. I mean that's part of that. Like, you know, it should be super easy for me to [/INST] travel there. Well, you know, hopefully there's unfortunate circumstances that we're in will actually promote the the remote collaborations. Yes. And I think we I think what we are experiencing right now is that you still can do science, you know, being quarantine in your own homes, especially when it comes. I mean, you know, I I certainly understand there is a very challenging time for experimental sciences. I mean I have many collaborators who are, you know, who are affected by that but for computational scientists. </s><s>[INST] Yeah, we're really leaning into the remote communication. Nevertheless, I had to force you talk to you in person because there's something that you just can't do in terms of conversation like this. I don't know why but in person is very much needed. So I really appreciate you doing it. Uh you have a collection of science bobbleheads. Yes. Which look amazing. Which which bobblehead is your favorite And uh which real world version? Which scientist is your favorite? [/INST] Yeah. So yeah, by the way I was trying to bring it in. But their current king now in my in my office, they sort of demonstrate the social distance so there Nicely spaced away from each other. But so you know it's interesting. So I've been I've been collecting those bubble has for the past maybe 12 for 13 years. And it you know interesting enough, it started with the two bubble heads of Watson and Creek. And um interestingly enough my last bubble had in these collections for now. And my favorite one because I I felt so good when I got it was the Rosalind franklin. Mhm. And uh so so you know when </s><s>[INST] I who's the full group. So I have [/INST] Watson Creek, Newton, Einstein Marie curie. Tesla uh of course Charles Darwin, Sir Charles Darwin. Um and wasn't it franklin? I am definitely missing quite a few of my um favorite scientists. And but so you know if I want to add to this collection so I would add of course calma gore if </s><s>[INST] that's [/INST] that's that's that's you know, I've been always fascinated by his Well his dedication to science but also his dedication to educating young people the next generation. So it's it's it's very inspiring. </s><s>[INST] He's one of the, okay yeah, he's one of the Russia's great. [/INST] Yeah. So he also um you know the school, the high school that I attended was named after him and he was great, you know, so he founded the score at school um and he actually thought there </s><s>[INST] is this in Moscow. Yes. [/INST] Yeah. So, but then I mean, you know, other people that I would definitely like to see in my collections was would be uh alan turing would be john von neumann. </s><s>[INST] Yeah, you're you're a little bit later in the computer scientists. [/INST] Yes. Well I mean they don't, they don't make them, you know, I I still am amazed they haven't made alan turing yet. Yes. And and and I would also add the Linus Pauling </s><s>[INST] line is [/INST] falling </s><s>[INST] whose line is point. [/INST] So this is this is uh to me it's one of the greatest chemists um and the person who actually discovered the secondary structure of proteins who was very close to solving the DNA structure and um you know, people argue but some of them were pretty sure that if not for this, you know uh photograph 51 by Rosalind franklin that you know what's an anchor you got access to um he would be, he would be the one who saw it. </s><s>[INST] Science is a funny race. It is, let me ask the biggest and the most ridiculous questions. So you've kind of studied the human body and its defenses and these enemies that are about uh from a biological perspective, bioinformatics perspective, a computer scientist perspective, how is that made you see your own life sort of the meaning of it or just even seeing your what it means to be human? [/INST] Mhm. Well, it certainly makes me realizing how fragile the human life is. If you think about this little tiny thing can impact the life of the whole human kind to such extent. So, you know, it's something to appreciate and to no. Mhm. To remember that that you know, we are fragile, we have to born together as a society. And you know, it also gives me sort of hope that what we do as scientists uh is useful. </s>

<s>[INST] What if men which rang him? Somebody from Harvard describes that men are the originators of violence, physical violence in society. And he argues that actually the world would be better off. No, just a very cold calculus. If you get rid of men, there will be a lot less violence in society. Is his client [/INST] who says you need to get rid of violence in society. </s><s>[INST] Well, that's but shouldn't at least be a discussion. [/INST] Have </s><s>[INST] a debate on a panel discussion. Violence pros and cons. [/INST] Well, that's the sort of thing. If I can say so the sunlight we cast academic decides to do because he thinks that his area of boston would be nice, whatever. Um, he might decide it's useful if he was living in Kiev today to have violent men? I mean it might if if if new york was invaded right now, I need some violent men around here, but </s><s>[INST] it wouldn't be invaded if there's no violent meant. [/INST] Well, </s><s>[INST] there's the argument, [/INST] there's there's also at least there's some level of threat that you ought to exude that puts people off. If I was in, you know, I'm very glad that the men and women of Ukraine are capable of and more than capable of fighting for their country and for their neighbors and their families and much more. But it's better that that there was violence ready to unleash when violence was unleashed upon them then that the whole society had been told that they should identify as non binary. </s><s>[INST] But at least it's a it's a conversation to have, isn't there uh isn't there aspect to the sort of the feminist movement that is correct in in challenging the [/INST] some forms of violence domestic violence for instance. Although women are capable of that as well. </s><s>[INST] I'm learning about this, [/INST] about this at the moment. </s><s>[INST] I can't help but watch the entirety of it go down in this beautiful mess that is human relations. Okay, But [/INST] just finish up that it's </s><s>[INST] it's [/INST] very unwise for women to war against men as it would be for men to war against women. It's highly, highly unwise to warn the majority population and in America Britain and other western countries, white people are still a majority And so why would you tell the majority of their evil by dint of their skin color and think that that would be a good way to keep them in check. I mean I'm not guilty of anything because of my skin color, I'm not guilty of anything, my ancestors didn't do anything wrong and even if they had why would I be held responsible for it? </s><s>[INST] So uh to go back to Nigeria, is there some aspect to where if we should try to explain the forces of play here? Is it the will to power playing itself out from individual human nature and from group behavior nature. Is there some elements to this which is the game we play as human beings is always one way of less power. We're trying to find ways to gain more power. [/INST] That's certainly one the desire to grab is let me see if I find a quote for you on that, the desire to grab that which we think we're owed and to do it often in the guise of um um justice. I mean justice is one of the great terms of our age and one of the great bogus terms of our age, people forever talk about their search for justice. It's amazing how violent they can often be in their search for justice and how many rules they're willing to break so long as they can say they're after justice. And how many norms they can trample so long as they can say it's in the name of justice, you can burn down buildings in the name of justice. </s><s>[INST] Well, the majority groups throughout history, including those with white skin color, have done the same in the name of justice. We grew up with all kinds of sexy terms and our propaganda machines to sell whatever atrocities we'd like to commit. [/INST] One of the, one of the quotes of niche that I liked. And I quoted in this </s><s>[INST] careful I'm judging you harshly. [/INST] Of course. Nietzsche says that one of the dangers of men of resentment is they'll achieve their ultimate form of revenge, which is to turn happy people into unhappy people like themselves to shove their misery in the faces of the happy so that in due course the happy and this is quoting me to start to be ashamed of their happiness and perhaps say to one another, it's a disgrace to be happy. There is too much misery. This is something to be averted for the six says Nietzsche must not make the healthy sick to or make the healthy confuse themselves with the sick? Well, I think there again, there's a lot of that going on. How could I be happy when there is unhappiness in the world? Why should I not join the ranks of the unhappy? </s><s>[INST] I think he has a book about that as well. Notes from underground, um, okay, [/INST] this has been very Russian, Russian focus, I'm very pleased with the number of times. But dr african Grossman and others have come in. This is why I wasn't doing this as a sort of yeah, </s><s>[INST] well it's always good to plug the greats. Um and good to know they're still relevant. Do you speak Russian by the way at all? Which [/INST] I did, I'm told it's a 10-year language basically to learn from scratch my friends who have done it. </s><s>[INST] Well, there's the language and then there's the personality behind the language and the personality I feel like you already have. So you just need to know the surface [/INST] details. Okay, </s><s>[INST] in fact the silence to be silent in the Russian language is something that's already important. [/INST] If we had a moment I told my story about Stalin's birthplace that no, I once went to Goree where Stalin was born. Have you been? </s>

<s>[INST] And then from the very beginning to [/INST] the end to end. And so you go from what the human wrote and programming languages end up being about expressing intent, not just for the compiler and the hardware, but the programming languages job is really to to capture an expression of what the programmer wanted. That then can be maintained and adapted and evolved by other humans as well as by the interpreted by the compiler. So, so when you look at this problem, you have, on the one hand, humans which are complicated, you have hardware which is complicated until compilers typically work in multiple phases. And so the software engineering challenge that you have here is try to get maximum reuse out of the the amount of code. The right because these competitors are very complicated. And so the way it typically works out is that you have something called a front end or a purser that is language specific. And so you have a c purser that's what playing is um or C plus plus or javascript or python or whatever. That's the front end. Then you'll have a middle part which is often the optimizer and then you'll have </s><s>[INST] a late [/INST] part which is her birth specific. And so compilers end up, there's many different layers often, but these three big groups are very common in compilers and what Alabama is trying to do is trying to standardize that middle and last part. And so one of the cool things about L A Vm is that there are a lot of different languages that compile through to it. And so things like um swift, but also Julia. Rust clang for C C plus plus subjective. See like these are all very different languages and they can all use the same optimization infrastructure, which gets better performance and the same cogeneration infrastructure for harbor support. And so L V M is really that that layer that is common that all these different specific compilers can use. </s><s>[INST] And is it um, is it a standard like a specification or is it literally an implementation? [/INST] It's an implementation. And so it's I think there's a couple different ways of looking at it. Right. Because it depends on which which angle you're looking at it from L V m ends up being a bunch of code. Okay, so it's a bunch of code that people reuse and they build compilers with. We call it a compiler infrastructure because it's kind of the underlying platform that you build a concrete compiler on top of, but it's also a community. And the L V um community is hundreds of people that all collaborate. And one of the most fascinating things about L V M over the course of time is that we've managed somehow to successfully get harsh competitors in the commercial space, to collaborate on shared infrastructure. And so you have google and Apple, you have A M. D and intel, you have NVIDIA and M D on the graphic side, you have cray and everybody else doing these things. And like all these companies are collaborating together to make that shared infrastructure really, really great. And um they do this not of the goodness of their heart, but they do it because it's in their commercial interests of having really great infrastructure that they can build on top of and facing the reality that it's so expensive, that no one company, even the big companies, no one company really wants to implement it all themselves, </s><s>[INST] expensive or difficult. [/INST] Both. That's a great point because it's also about the skill sets, Right? And these uh um the skill sets a very hard hard to find </s><s>[INST] how big is the L L V M it always seems like with open source projects, the kind LVMH's open [/INST] Source. Yes, it's open source, it's about, it's 19 years old now. So it's fairly old. </s><s>[INST] It seems like the magic often happens in a very small circle of people like at least the early birth and [/INST] whatever. So the L A P M. Came from a university project and so I was at the university of Illinois and there it was myself, my advisor and then a team of two or three research students in the research group and we built many of the core pieces. Initially I then graduated, went to Apple and an Apple brought it to the products first in the open gl graphics stack, um but eventually to the C compiler realm and eventually built clang and eventually built swift and these things along the way, building a team of people that are really amazing compiler engineers that helped build a lot of that. And so as it was gaining momentum and his Apple was using it being open source in public and encouraging contribution. Many others, for example, google came in and started contributing in some cases, Google effectively owns playing now because it cares so much about C Plus plus in the evolution of that ecosystem. And so it's investing a lot in um the C Plus plus world and the tooling and things like that. And so um likewise, uh NVIDIA cares a lot about CUDA. And so cuda uses playing and uses L V M for for graphics and Gpu Gpu. </s><s>[INST] And so when you first started as a master's project, I guess, did you think is going to go as far as it went, where you uh crazy ambitious about it? It seems like a really difficult undertaking a brave one. [/INST] Yeah, no it was nothing like that. So I mean my my goal, when I went to university of Illinois was to get in and out with the non thesis master's in a year, get back to work. So I was not, I was not planning to stay for five years and and build this massive infrastructure, I got um nerd sniped into staying and a lot of it was because Alabama was fun and I was building cool stuff and learning really interesting things and uh facing both software engineering challenges but also learning how to work in a team and things like that. I had worked at many companies as interns before that um but it was really a different, a different thing to have a team of people that were working together and trying to collaborate in version control and it was, it was just a little bit different. </s>

<s>[INST] the reasons why I rejected Yeah, there's it's hard to convert into words, but uh mm it um, distinctly aware of the distinction between when I enter a room, there's a certain kind of music to the way people talk when we're talking about ideas versus what that music sounds like when we're talking when it's like bickering in the space of like whether it's politics or funding or egos, it's a different sound to it. And I'm distinctly aware of the two and I kind of sort of to me personally, happiness, what was just like swimming around the one that like is the political stuff or the money stuff and all that or egos. Uh, and I think that's probably what problem is as well, like the moment he senses there's any as what it feels matter, like the moment you start to have any kind of drama on credit assignment, all those kinds of things. It's almost not that it's important who gets the credit. It's like the drama in itself gets in the way of the exploration of the ideas or the fundamental thing that makes science so damn beautiful. [/INST] And you can really see that there's also a product of that Russian school of doing science and you can see that that that people were, you know, during the Cold War, a lot of mathematicians, they were not making any money, they were doing math for the sake of math, like for the intellectual pleasure of like solving a difficult problem and you know, even even if it was a flawed system and there were a lot of problems with that, there's this they were able to to actually achieve this and there were a lot of impairment for me is the perfect product of that. It just cared about like working on tough problems, he didn't care about anything else. It was just meth, you know, pure </s><s>[INST] math. Yeah, there's uh like for the broader audience, I think another example that is like professional sports versus olympics, I'm especially in Russia, I've seen that clear distinction where because the state manages so much of the olympic process in Russia, as people know with the steroids. Yes. Yes. Yes, But outside the steroid thing uh is like the athlete can focus on the pure artistry of the sport, like like not worry about the money, not just in the way they talk about it, the way they think about it, the way they define excellence versus like in the perhaps a bit of a capitalist system in the United States with american football, with baseball and basketball. So much of the discussion is about money now, of course, at the end of the day it's about excellence and artistry and all that. But when the culture is so richly grounded in discussions of money and uh sort of this capitalistic like uh merch and businesses and all those kinds of things, it changes the nature of the activity and it's in a way that's hard to get to describe in words, but when it's purely about the activity itself, it's almost like you quiet down all the noise enough to hear the signal enough to hear the beauty. Like whenever you're talking about the money, that's when the marketing people come and the business people, the non creators come and they filled the room and there's they create drama and they know how to create the drama and the noise as opposed to people who are truly excellent at what they do, the the person in their arena, right? Like when you remove all the money and you just let that thing shine. That's when true excellence can can come out. And that was of the few things that work with the communist system, you know, to me at least as somebody who loves sport and loves mathematics and uh, science that worked well, removing the money from the picture. Uh, not that I'm not that I'm saying poverty is good for science. There's some level in which not worrying about money is good for science. It's a weird, I'm not exactly sure what to make of that because capitalism works really damn well. But it's um, mm hmm it's tricky how to find that balance [/INST] one. Fields medalist that is interesting to look at it and I think you mentioned it earlier but is Cedric Villani, which is might be the only, uh, fields medalist that is also a politician now. But so it's this, it's this brilliant french mathematician that the won the fields medal. And and after that he decided that one of the ways that he could have, could have, you know, the biggest leverage kind of in pushing science in the direction that he thinks science should go would be to try to go into politics. And so that's what he did. And uh, and the years ran. I'm not sure if he has one in any election, but I think he's running for mayor for mayor of paris or something like that. But it's this brilliant mathematician that, that before winning the fields medal had only been just a brilliant mathematician. But, but after that he decided to go into politics to, to try to have an impact and try to change some of the things that he would complain about before. So, so there's that component as well. </s>

<s>[INST] I mean, of course you can do that kind of stuff with a two year delay, but it's tougher. Right? Yeah. Um, do you think, do you think, uh, Tesla or Waymo or some of these companies that are doing uh semi or fully autonomous driving should be doing driver sensing. [/INST] Are </s><s>[INST] you thinking about that kind of stuff? So not just how we can enhance the in cab experience for cars that are mainly driven, but the ones that are increasingly more autonomously driven. [/INST] Yes. So if we fast forward to the universe where it's fully autonomous, I think interior sensing becomes extremely important because the role of the driver isn't just to drive. Think about the driver almost manages manages the dynamics within a vehicle. And so who's going to play that role when it's an autonomous car? We want a solution that is able to say, oh my God, like you know, lex is bored to death because the car is moving way too slow. Let's engage lex or Ron is freaking out because she doesn't trust this vehicle yet. So let's tell rana like a little bit more information about the route or. Right, so I think or somebody's having a heart attack in the car, like you need interior sensing and fully autonomous vehicles. But with semi autonomous vehicles, I think it's, I think it's really key to have driver monitoring because semi autonomous means that sometimes the car is in charge. Sometimes the driver's in charge or the co pilot, right? And you need this, you need both systems to be on the same page. You need to know the car needs to know the driver's asleep before it transitions control over to the driver. And sometimes if the driver is too tired, the car can say I'm going to be a better driver than you are right now. I'm taking control over. So this dynamic this dance is so key and you can't do that without driver sensing. </s><s>[INST] Yeah. There's a disagreement for the longest time. I've had to Dylan that this is obvious that this should be in the Tesla from day one and it's obvious the driver sensing is not a hindrance. It's not obvious. You should be careful because having studied this problem, nothing is really obvious but it seems very likely a driver sensing is not a hindrance to an experience. It's only um enriching to the experience. Um and likely increases the safety. That said, it is very surprising to me just having studied semi autonomous driving how well humans are able to manage that dance because it was the intuition before you were doing that kind of thing that humans will become just incredibly distracted. They would just like let the thing do its thing but they're able to, you know, because it is life and death and they're able to manage that somehow. But that said there's no reason not to have driver sensing on top of that. I feel like that's going to allow you to do that dance that you're currently doing without driver sensing except touching the steering wheel to do that even better. I mean the possibilities are endless and the machine learning possibilities are such a such a beautiful it's also constrained environment. So you could do a much more effectively than you can with the external environment. External environment is full of weird educations and complexities just inside there's so much it's so fascinating. Such a fascinating world. I I do hope that companies like Tesla and others even even Waymo um Which I don't even know if Waymo is doing anything sophisticated inside the cab. [/INST] I don't think so </s><s>[INST] like like what what what is it? I honestly think I honestly think it goes back to the robotics thing we were talking about which is like great engineers that are building this ai systems. Just are afraid of the human being [/INST] and not thinking about the human experience. They're thinking about the features and yeah perceptual abilities of that thing. </s><s>[INST] They think the best way I can serve the human is by doing the best perception and control I can by looking at the external environment keeping the human safe. But like there's a huge I'm here like uh you know I need to be noticed and um interacted with and understood and all those kinds of things. Even just on a personal level for entertainment honestly for entertainment. Um [/INST] You know one of the coolest work we did in collaboration with M. I. T. Around this was we looked at longitudinal data right? Because because you know Emmett had access to like tons of data. Um And and and like just seeing the patterns of people like driving in the morning off to work versus like commuting back from work or weekend driving versus weekday driving. And wouldn't it be so cool if your car knew that and then was able to optimize either the route or the experience or even make recommendations? I think it's very powerful. </s>

<s>[INST] think we can work with science. No, science is beautiful. But humans with egos and all those kinds of things can sometimes misuse good things, like social justice, like all ideas will all aspire to misuse these beautiful ideas to manipulate people to all those kinds of things. And that's, there's assholes in every space and walk of life, including science. And those are, those are no good. But yes, you're right. The scientific method has proven to be quite useful. That said, for difficult questions, for difficult, rare explanations for rare phenomena, you have to walk cautiously. Because the scientific method when you totally don't understand something, and it's rare, you can replicate it doesn't quite apply. [/INST] Yeah, yeah, yeah, that's it. I agree with you. The challenge is to is to not dismiss the anomaly because you can't replicate it. I mean, we can talk about this. This is something I realized when we were developing assembly theory. People think in the track they're on is so dogmatic, but there is this thing that they see, but they don't see, and it takes a bit of time. And you just have to keep reframing it. And my approach is to say, well, why can't this be right? You know, why, why must we accept that RNA is the only way into life? I mean, who said was there, you know, does RNA have a special, special class of information that's encoded in the universe? No, of course it doesn't, right? You know, RNA is not a special molecule in the space of all the </s><s>[INST] other molecules. But it's so elegant and simple. And it works so well for the evolutionary process that we kind of use that as an intuition to explain that that must be the only way to have life. Sure. But you mentioned assembly theory. Well, first, let me pause. Bathroom break needed. [/INST] Yeah, let's take two minutes. </s><s>[INST] We took a quick break. And offline, you mentioned to me that you have a lab in your home. And then I said that you're basically Rick from Rick and Morty, which is something I've been thinking this whole conversation. And then you say that there's a glowing pickle that you used something involving cold plasma, I believe, I don't know, but can you explain the glowing pickle situation? And is there many arbitrarily many versions of you in alternate dimensions? [/INST] So you're aware of, so you're aware of, I tried to make an electrochemical memory in at home, using a and the only way using a pickle, the only way I could get any traction with it was actually by plugging it into a very high voltage alternating current and then putting in a couple of electrodes. But my kids weren't impressed. They're not impressed with anything I do, any experiments I do at home. I think it's quite funny. But you connected that pickle to some electro? To 240 volts, yeah, AC. And then had a couple of electrodes on it. So what happens is a pickle, this is a classic thing you do. I mean, I shouldn't pranks you do, you put a pickle into the mains and just run away and leave it. And what happens is it starts to decompose, it heats up and then explodes because the water turns to steam and it just violently explodes. But I wondered if I could cause the iron, sodium, potassium ions in the pickle to migrate. It had been in a jar, right? So been in a brine. That was not my best experiment. So I've been far better experiments in my lab at home. </s><s>[INST] At that time was a failed experiment, but you never know. Every experiment is a successful experiment if you stick with it long enough. [/INST] I mean, I got kicked out of my own lab by my research team many years ago and for good reason. I mean, my team is brilliant and I used to go and just break things. So what I do do at home is I have a kind of electronics workshop and I prototype experiments there. Then I try and suggest to my team sometimes, maybe we can try this thing. And they will just say, oh, well, that's not going to work because of this. And I'll say, aha, but actually I've tried and here's some code and here's some hardware. Can we have a go? So I'm doing that less and less now as I get even more busy, but that's quite fun </s><s>[INST] because they feel that we're in the experiment together. You do in fact brilliantly, just like Rick from Rick and Morty, connect up chemistry with computation. And when we say chemistry, we don't mean the simulation of chemistry, of modeling of chemistry. We mean chemistry in the physical space as well as in the digital space, which is fascinating. We'll talk about that. But first you mentioned assembly theory, so we'll stick on theory and these big ideas. I would say revolutionary ideas. That's the intersection between mathematics and philosophy. What is assembly theory? And generally speaking, how would we recognize life if we saw it? [/INST] So assembly theory is a theory, goes back a few years now. My struggle for maybe almost 10 years is when I was going to origin of life conferences and artificial life conferences where I thought that everybody was dancing around the problem of what life is and what it does. But I'll tell you about what assembly theory is because I think it's easier. So assembly theory literally says if you take an object, any given object, and you are able to break the object into parts very gently, so just maybe let's say take a piece of very intricate Chinese porcelain and you tap it just in a hammer or the nail at some point, and it will fragment into many parts. And if that object is able to fragment into many, and you count those parts, the different parts, so they're unsymmetrical, assembly theory says the larger the number of parts unsymmetrical parts that object has, the more likely it is that object has been created by the evolutionary or information process, especially if that object is not one off, you've got an abundance of them. And that's really important. What I'm literally saying about the abundance, if you have a one off object and you break it into parts, and it has lots of parts, you'd say, well, that could be incredibly intricate and complex, but it could be just random. And I was troubled with this for years because I saw in reality that assembly theory works. But when I talked to very good complexity, computation lists, algorithmic complexity people, they said, you haven't really done this properly. You haven't thought about it. This is the random problem. And so I kept working this up because I invented an assembly theory in chemistry, first of all, with molecules. And so the thought experiment was, it was how complex does a molecule need to be when I find it, that it couldn't possibly have risen by chance probabilistically. And if I found this molecule able to detect it enough quantities in the same object, like a machine, like a mass spectrometer. So typically in a mass spectrometer, you weigh the molecules in the electric field, you probably have to have the order of 10,000 identical molecules to get a signal. So 10,000 identical molecules that are complex. What is the chance of them occurring by chance? Well, we can do the math. Let's take a molecule like strychnine or, yeah, so strychnine is a good molecule actually to take, or Viagra is a good molecule. I made jokes about Viagra because it's a complex molecule. And one of my friends said, yeah, if we find Viagra on Mars in detectable quantities, we know something is up. But anyway, it's a complex molecule. So what you do is you take this molecule in the mass spectrometer and you hit it with some electrons or an electric field and it breaks apart. And if the larger than the larger number of different parts, you know, when it starts to get to a threshold, my idea was that that molecule could not be created by chance probabilistically. So that was where assembly thought theory was born in an experiment, in a mass spec experiment. I was thinking about this because NASA sending a mass spectrometer to Mars to Titan is going to send them to Europa. There's going to be a nuclear powered mass spectrometer going to Titan. This is the coolest experiment ever. They're not only sending a drone that's going to fly around Titan. It's going to be powered by a nuclear slug, a nuclear battery, and it's going to have a mass spectrometer on it. this already launched? No, it's gonna, it's Dragonfly and it's going to be launched in a few years. I think it got pushed a year because of the pandemic. So I think it's real. </s>

<s>[INST] by the way? Is there something interesting to say about your worldview? Because you mentioned psychic and, and sort of the ways we can be healthy, the ways we can grown how much maybe medicine or science or has um, has the answers. Is there is there some interesting way to describe that worldview? [/INST] I would just say I'm open mind. I believe anything is possible. And if I was going to trust in any practical information, it would be something thousands of years old. </s><s>[INST] There's wisdom in that history. Yeah. [/INST] Well it's it's more tested. It's not always right, but it's at least it's been somewhat tested. </s><s>[INST] Those sciences. Also tested the thing I'm a little bit skeptical of. Sometimes it's just the hubris that often comes with the modern, with the latest, the newest, the this this feeling like you've figured it all out. Everything that's been done in the past has no wisdom and we basically solved every problem. Uh, you know, there's nothing else to be solved this. I mean that's the defining characteristic of any age is like we've solved all the problems there are, we'll have the final answers and our parents are all stupid. That kind of energy? Yeah. And that you have to be extremely, extremely careful with that when it talks about when you think about something as complex as the human body or the human mind have to be very [/INST] believe we know close to nothing. </s><s>[INST] Yeah. [/INST] Close to nothing about anything </s><s>[INST] about [/INST] anything about that </s><s>[INST] place of humility is a good place to start to figure, to figure it all out in the end. We'll still know almost nothing. [/INST] Yeah. I don't think we need to know. It's like we need to see what works and we need to see what works for us. It's interesting to know. I know on the art side, knowing how it works isn't what makes it work? You know, isn't the magic of it isn't how it works. The magic is the magic and the magic happens in a way that's intuitive and accidental at times or incidental where you're trying many things all of a sudden something works and and you don't know why and it's okay not to know why it doesn't matter. It doesn't really matter why. As long as it does the thing that you wanted to do, whatever that is. </s><s>[INST] Yeah. That's so weird when, you know the components, you know, you're still Yeah, the magic, what's the magic? Where's the magic, like we know the components for stuff I care about artificial intelligence. We know that components of a powerful computing machinery. Where does consciousness come from? What what is that? What is the brilliant moments of insight come from? What's that when even in simple games of chess or in simple. Where do those breakthrough ideas of taking a big risk? That doesn't make any sense And then all of a sudden it becomes something beautiful? Yeah, we don't need to understand why it just happens. [/INST] It just happens. And often the things that end up breaking through don't break through in the way we thought or turn out to be a third iteration of something that we thought was an entirely different thing or we don't know, you know, and I think it's if we embrace that not knowing we'll have a healthier experience going through life. </s><s>[INST] You made a lot. It's not just music, everything rearranging the chairs, the furniture as well. You've done like I said, the documentary, I guess you would say with paul McCartney and um you've done a podcast yourself, broken record podcast and just you've done conversation too. So what have you learned from that process about the art of conversation and also maybe what advice would you give to this to me about how, what to do with conversation? Like what is interesting to you about conversation? [/INST] one of the things that I I like is to not feel like it's if there is any steaks or that it's actually almost that it's not happening. Like the fact that when I came in, you were setting up cameras made it less good from for me, I knew that that would impact the conversation in a negative way. The best version of it would be if we didn't see the cameras and if we were and we didn't see any technology and we were just sitting at this table having a conversation maybe even if we were miked beforehand would be okay if it was necessary. But then we were just sitting here having a conversation, no people in the room, nothing. And feeling like we're just having a conversation. I feel like it would get closer to um closer to the relaxed feeling the same thing we do in the studios. Like, you know, you've heard of red light fever. You know, when artists get nervous when like they play a song great and then the tape starts rolling and they can't play it. And it's we're all, we're all to some degree like that. </s><s>[INST] When you were with paul McCartney, I mean you're were you cognizant of cameras? [/INST] We had the room black, Everybody who was working there was dressed in black, everything was invisible, that we were lit in a way where even though they were probably 20 people between 12 and 20 people working in the room Within three minutes of starting the conversation, paul and I were alone in the </s><s>[INST] room. That was [/INST] the feeling on occasion you'd hear a noise and it would be weird. People, we also had nobody was allowed to wear shoes because it had to we were trying to create this intimate space. And I know from in the recording studio, when we're recording, if even one person is there that's just watching and not working, you know, like doesn't, like, there's usually, I'm usually there and an engineer is there technically making it happen if anyone else is in the room, it's different because then it goes from this moment where the person is doing a performance to the sense or where the person is feeling something internally, and we're capturing it to the the other version is they're performing for someone, </s>

<s>[INST] ways across [/INST] the collective states of multiple cubits. Okay. In such a way that even if a small percentage of my cubits leak, well I'm constantly monitoring them to see if that week happened. I can detect it and I can correct it, I can recover the information I care about from the remaining cubits. Okay. And uh so you know, you can build a reliable quantum computer even out of unreliable parts right now the the um in some sense, you know that discovery is what set the engineering agenda for quantum computing research from the 19 nineties until the present. Okay. The goal has been you know, engineer cubits that are not perfectly reliable but reliable enough that you can then use these error correcting codes to have them simulate cubits that are even more reliable than they are. The error correction becomes a net win rather than a net loss. Right? And then once you reach that sort of crossover point Then you know you are simulated cubits could in turn simulate cubits that are even more reliable and so on. Until you've just you know, effectively you have arbitrarily reliable Cubans. So long story short we are not at that break even point yet. We're a hell of a lot closer than we were when people started doing this in the 90s like orders of magnitude closer. </s><s>[INST] But the key ingredient there is the more cubits the better because [/INST] well the more cubits, the larger the computation you can do right? I mean I mean a q bits are what constitute the memory of the quantum computer but </s><s>[INST] also for the sorry for the error correcting mechanism. [/INST] Yes. So, so so the way I would say it is that error correction imposes an overhead in the number of cubits and that is actually one of the biggest practical problems with building a scalable quantum computer if you look at the error correcting codes at least the ones that we know about today and you look at you know, what would it take to actually use a quantum computer to uh you know uh um hack your credit card number which is you know, you know, you know the most famous application, people talk about, right, let's say two factor huge numbers and thereby break the R. S. A crypto system. Well, what that would take would be thousands of uh several 1000 logical cubits. But now with the known error correcting codes, each of those logical cubits would need to be encoded itself using thousands of physical cubits. So at that point you're talking about millions of physical qubits and in some sense that is the reason why quantum computers are not breaking cryptography already. It's because of this, these immense overheads involved. </s><s>[INST] So that overhead is additive [/INST] or multiple and multiplication of. I mean it's like you take the number of logical cubits that you need in your abstract quantum circuit, you multiply it by 1000 or so. So, you know, there's a lot of work on, you know, inventing better trying to invent better error correcting codes. Okay, that is the situation right now, in the meantime, uh we are now in um what physicist john Prescott called the noisy intermediate scale quantum or Nous keira and this is the era, you can think of it as sort of like the vacuum, you know, we're now entering the very early vacuum tube era of quantum computers. The quantum computer analog of the transistor has not been invented yet, right? That would be like true error correction right? Where you know, we are not or, or, or something else that would achieve the same effect, right? We are not there yet. Uh, and um, but, but, but where we are now, let's say, as of a few months ago, you know, as of google's announcement of quantum supremacy. You know, we are now finally at the point, we're even with a non error corrected quantum computer with these noisy devices, we can do something that is hard for classical computers to simulate. Okay. So we can eke out some advantage now, will we in this noisy era be able to do something beyond what a classical computer can do? That is also useful to someone that we still don't know. People are going to be racing over the next decade to try to do that by people? I mean, google IBM um, you know, a bunch of startup companies or, you know, uh, players. Yeah. And, and, and research labs and governments and uh, yeah, </s><s>[INST] he just mentioned a million things. I'll backtrack for a second. Sure, sure. Uh, so when these vacuum tube days just entering them and just entering, wow. Okay. So how do we escape the vacuum? So how do we get to, how do we get to where we are now with the CPU is this a fundamental engineering challenge? Is there, is there breakthroughs in on the physics side that they're needed? On the computer science side. What is there? And is it a financial issue where much larger just share investment and excitement is [/INST] needed. So you know, there's are excellent questions. Um I guess my well known, oh my my my my my my guess would be all of the above. I mean my my guess, you know, I mean, I mean, you know, you can say fundamentally it is an engineering issue, right? The theory has been in place since the nineties, you know, at least, you know, uh Uh you know, this is what, you know, error correction, you know, would look like, you know, we we do not have the hardware that is at that level, but at the same time, you know, so you could just um you know, try to power through, you know, maybe even like, you know if someone spent a trillion dollars on some quantum computing Manhattan project right then, conceivably they could just, you know, build a an error corrected quantum computer as it was envisioned back in the 90s. Right. I think the more plausible thing to happen is that there will be further theoretical breakthroughs and there will be further insights that will cut down the cost of doing this. So </s>

<s>[INST] the following is a conversation of Rabbi David Wolpe, someone who had been a fan of for many years for the kindness in his heart, the strength of his character and the kind of friends he keeps and talks with many of whom disagree with him but love him. Nevertheless, including the late Christopher Hitchens. [/INST] I </s><s>[INST] will have many conversations like these in the future about religion, about islam Christianity, Judaism, Hinduism, buddhism and others looking to understand and celebrate the culture, the tradition and the beauty of the people who practice these religions. I will of course not shy away from the difficult topics. I will talk both about hate and love about war and peace. This conversation was recorded more than three weeks ago. Please allow me this time to speak on what has been on my mind. If this is not interesting to you, please skip. I totally understand. Some people asked me to say a few words on the war in Ukraine. I think my words are worth little [/INST] but </s><s>[INST] perhaps let me try. I consider doing a long solo episode on this war. I tried several times, but it is too personal for now to give you context. I've been talking to refugees. Friends, loved ones in Ukraine in Russia and Poland slovakia Moldova Romania, even UK Germany Canada India china and of course the United States, some of them crying or angry or confused or scared. I'm helping as best as I can privately. And I'm hoping to help in the future by traveling to Ukraine and Russia and celebrating the humanity and the beauty of the people in this region. This was all set up both for Ukraine and Russia trips before 2022 including conversations with scientists, artists, athletes, leaders and just quote regular folks who are equally if not more fascinating to me. For now it has become much more difficult, but I'll keep trying to find a way I was born in the soviet union. [/INST] My </s><s>[INST] roots are both Ukrainian and Russian and today and until the day I die, I'm an american. I'm proud of all of this. I hope to keep celebrating the culture and the incredible human beings that make up these nations and humanity as a whole. We're all one [/INST] people. We're </s><s>[INST] in this together. That's how I feel about the people of these nations. Now let me speak about those in the seats of power. I condemn all actions of leaders who played geopolitical games on the world stage, disregarding the cost paid in human suffering on the scale of millions. [/INST] For </s><s>[INST] this reason, I condemn Vladimir Putin's invasion of Ukraine and I condemn many of the military interventions by the superpowers of the world, including by my country, the country. I love the United States. That after World War II has intervened in over 40 nations with many studies finding that the United States is culpable for an unfathomable number of civilian deaths. I condemn all heads of state who needlessly wage wars. Watching young men and women burn in the fires they started. I don't understand how humans can be so cruel to each other [/INST] or </s><s>[INST] rather understand, but I believe in a future world where this is no longer [/INST] true. </s><s>[INST] Let me also say a few words of what I hope to do with this podcast. I want to explore the full complexity and beauty of human nature. I believe each of us are capable of good and evil and I want to understand how the mind and the circumstance lead one to choose the former path or the latter. And I believe conversation is one of the best ways to work toward this understanding for that. I think I have to not only talk to the most inspiring humans in the world, but also to the most controversial. I will speak with many people who I disagree with politicians, activists, ceos Heads of State with very different opinions in the world. I will try hard to challenge their ideas without closing my mind to the depth and complexity of their perspective and their humanity. My presence in the same room with wildly different people will make it easy for the media and the internet to pick and choose clips and snapshots attacking me for being a shill for one side or the other. I can't defend this point except to say that I'm a shill for no one and that I hope you see the strength of my integrity that I won't be influenced by any of them, no matter how rich powerful or charismatic they are like the poem If by roger kipling says if you can talk with crowds and keep your virtue or walk with kings nor lose the common touch if neither foes nor loving friends can hurt you if all men count with you but none too much. This is a really, really important thing to me that I try to live by, that all human beings count with me. The same [/INST] people have </s><s>[INST] criticized me for wanting to have some of these conversations like with Vladimir Putin and Vladimir Zelensky and four times in the past speaking about them without the seriousness, the topic deserves for this. I would sincerely like to apologize. I'm disappointed even ashamed of my frequent in eloquence on these topics. I will work hard to do better when I'm joking, it should be clear that it's a [/INST] joke </s><s>[INST] and hopefully actually funny when I'm being serious, I should speak with care and [/INST] rigor. </s>

<s>[INST] a dictator. Is that where you're going? [/INST] No we need we need it's a money town, let's be, come on man. I mean new york is a money town and uh Wall street and then when Aoc and her cronies um at the local level rejected that amazon thing, you're going like what do you think makes cities what's going to create jobs in the 21st century. What do we need more nail salons? More pizza places. I mean we're living in the tech revolution and you know whatever your opinions are about Jeff Bezos that's the world tech and they want to come here. Of course you give them tax breaks. That's why any companies go anywhere She's so fucking utopian and that that progressive wing is so utopian and that always ends in disaster because not rooted in reality, it doesn't accept the reality that people are self interested. Now they're gonna do this 14% 15% tax hike on people making a million dollars more in new york city a million dollars, not that much. So people are gonna flee new york, The tax base is gonna flee new york is going to fall the ship like it did before. So you're </s><s>[INST] saying it basically needs a more capitalist front capitalistic type of thinker. That [/INST] Bloomberg Giuliani when he was still saying and his hair wasn't melting off his face, prosecutor. You need a talk. I mean, I don't know what's happened, that guy's lost it, but it's fun, </s><s>[INST] it's fun. [/INST] Yeah, it's fun to watch him be just like trump's lacking like yeah, whatever you want, boss, I'll just say whatever you want, boss, </s><s>[INST] uh [/INST] NEW YORK Is a money town that needs a money guy and sort of more of a Republican. I have to say on the local 11 as more of a guy who leans left. I'll just be honest, it's a tough city that needs a tough mayor, not some guy who's going like I understand we all need free money, you know? Andrew yang I think is right in the big picture because all the real jobs are somewhere else and you look at those asian cities, you go like oh that's what our cities used to look like at the industrial revolution, you know, there was like there was jobs and people were making things here and now you look at those cities in Asia, you're going like wow and then you go to Detroit and you're like yeah we're done, you go to Cleveland, you know we're done. So I don't </s><s>[INST] actually, it's, it's funny the reason I really like Andrew Yang is I've learned a lot every time he talks like it's not his opinions, he's just giving a lot of data like information which I [/INST] just start a podcast. Don't run for </s><s>[INST] mayor. Yeah, that's true. He already has a podcast. Yang speaks who doesn't, who doesn't, who doesn't, [/INST] that's the way we communicate. I don't even talk to people unless it's on a podcast. </s><s>[INST] What? Listen man, I'm a, I'm not going to criticize that because there is something like I talked to my dad on a podcast for four hours and I'm not sure I would, I would ever talk to him in the way we talked without the podcast, uh physicist but like yeah it's episode 100 and you know, okay, I the way I recorded that podcast is I try to put my ego aside, it's actually really tough to talk to your dad especially because you're giving them a platform uh especially so at that time there was already a bit of a platform for this podcast. And so there's this as a son, you think? Like uh here goes with this Bullsh it again. Like that's the natural son thought you have. But at the same time I wanted to, The way I thought about it is in 20 years when I look back, like I want to do a conversation where I'm happy with it, you know? So I want to make him shine. But I also called him on like, why were you so distant? Like, like all that kind of stuff. Yeah, it was very difficult to do, but it was really important to do and I don't think I'll be able to do without a without a microphone. Listen, how often do we sit there and just focus our attention. Just look at the other person. I don't know man, this is not even recording right now. [/INST] I just, I just invited you over just so we could actually, you're right. The podcast does make like I listen, I've been listening to every word you've been saying and if we weren't doing a podcast, I might be looking at my phone being self conscious about something else or </s><s>[INST] nervous or anxious and especially with people close to you. I mean that was, I recommend that actually for people to talk to their family on a podcast or like a fake or not? That's really powerful. Uh it made me realize that there's a clear distinction between the conversations we usually have with humans and those we have on the podcast is being recorded. Um what the funk are we talking on before that? [/INST] I knew you were going to lose your train of thought on that one because that's a big one. There's a motion behind that one podcast with dad is gonna take, it's gonna take you to a place I took you to a place it took outside of interviewer, new </s><s>[INST] york took place in new york and yang. So the data, one of the things that really surprised me about, I like the psychoanalysis, he just threw in there. [/INST] It took, it took you to a place. </s><s>[INST] So Angie yang mentioned, [/INST] respect me now Dad MIT isn't enough of a million people listen to this 14 Rogan's isn't enough, Dad, I'm creating robots. Is that enough for you know, that's what drives you </s>

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

<s>[INST] 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] from having built these communities, what have you, what have you learned about what's the process of getting a critical mass of members in the community? Is it luck skill timing, persistence, what is is it the tools like discourse that empower that community, what what's the key aspect of starting for one guy, a gal and then building it 2 to 1 and 10 and 100 1000 so on, [/INST] I think we're starting with an end of one, I mean, I think it's persistence and, and also you have to be interesting like somebody I really admire once said something that I always liked about blogging. He's like, here's how your blog, you have to have something interesting to say and have an interesting way of saying it, right and then do that for like 10 years. So that's the genesis is like, you have to have sort of something interesting to say. That's not exactly what everyone else is saying and an interesting way of saying, which is another way of saying, kind of entertaining way of saying it. Uh and then as far as growing it, it's like ritual, you know like you have to like say you're starting a blog, you have to say, look, I'm gonna blog every week three times a week and you have to stick to that schedule right? Because until you do that for like several years you're never gonna get anywhere. Like it just takes years to get where you need to get to. And part of that is having the discipline to stick with the schedule and it helps again, if it's something you're passionate about, this won't feel like work. Like I love this, I can talk about this all day every day right? Uh you just have to do in a way that's interesting to other people and then as you're growing the community um that pattern of participation within the community of like generating these artifacts and inviting other people to help you like collaborate on these artifacts. Like even in the case of blogging, like I felt in the early days of my blog, which I started in 2000 and four, which is really the genesis of stack overflow. If you look at all my blog, it leads up to stack overflow, which was, I have all this energy in my blog. But I don't like 40,000 people were subscribing to me and I was like, I want to do something. And then then I met Joel and said, hey Joel, I want to do something, take this ball of energy for my blog and do something. And all the people read my blog. So that's like, oh cool, you're involving us, you're saying, look, you're part of this community. Let's build this thing together. Like they picked the name, like we voted on the name for stack overflow on my blog. Like we came and naming is super hard. First of all, I the hardest problem computer science coming with a good name for stuff. Right? Um but there you can go back to my blog. There's the pole where we voted and stack overflow became the name of the site and all the early beta users stack over. We're audience of my blog plus Joel's blog. Right? So we started from like if you look at the genesis, okay, I was just a programmer who said, hey, I love programming but I have no outlet to talk about it. So I'm just gonna blog about it because I don't have enough people to work to talk to about it because at the time I worked a place where, you know, programming wasn't the court output of the company was a pharmaceutical company and I just love this stuff, you know, to an absurd degree. So I was like, I'll just blog about it and then I'll find an audience and eventually found an audience. Eventually found Joel and eventually build stack overflow from that one core of of activity, Right? But it was that repetition of feeding back in feedback from my blog comments, feedback from Joel, feedback from the early stack overflow community. Um when people see that you're doing that, they will follow along with you, right? That's cool. You're here in good faith. You're actually, you know, not listening to everything. That's impossible. That's impossible. But you're actually, you know, waiting our feedback and what you're doing because and why wouldn't I? Because who does all the work on stack overflow. Me, Joel. No, it's the other programmers that are doing all the work. So you gotta have some respect for that. And then, you know, discipline around. Look, you know, we're trying to a very specific thing here on stack overflow. We're not trying to solve all the world's problems. We're trying to solve this very specific Q. And a problem in a very specific way. Not because we're jerks about it, but because these strict set of rules help us get really good results, right? Um and programmers that's an easy sell for the most part because programmers are used to dealing with ridiculous systems of rules like constantly. That's basically their job. So they're they're very, oh yeah, super strict system of rules that lets me go, I want that's programming, right? That's what stack overflow is. So, </s><s>[INST] So you're making it sound easy. But in 2004, let's go back there. In 2004 you started the blog coding horror. What's it called that at the beginning? At the very beginning [/INST] it was one of the smart things I did. It's it's from a book by steve McConnell Code Complete, which is one of my favorite programming books. Still, probably my number one programming book for anyone to read. Uh one of the smart things I did back then, I don't always do smart things when I start stuff. I contacted steven said, hey, I really like this. It was a sidebar illustration indicating danger in code, right? Coding horror was like watch out. And I love that illustration because it spoke to me because I saw that illustration, Oh my God, that's me. Like I'm always my own worst enemy. Like that's the key insight in programming is every time you write something, think how am I going to screw myself because you will constantly, right? So that the icon was like, oh yeah, I need to constantly hold that mirror up and look and say, look, you're very fallible, you're gonna screw this up. Like how can you build this in such a way that you're not going to screw it up later? Like how can you get that discipline around making sure that every step I'm thinking through all the things that I could do wrong or that other people could do wrong, because that is actually how you get to be a better programmer a lot of times, Right? So that sidebar illustration, I loved it so much and I wrote steve before I started my blog and said, hey, can I have permission to use this? Because I just really like this illustration and steve was kind enough to give me permission to do that and just continues to give me permission. So yeah. Really? </s>

<s>[INST] that reverses that hyper processing trend that we're on as a human species and that's uh that's the promise of regenerative farming, that's the promise of hunting. Obviously the former can be scaled the hunting I think cannot be scaled right. But in many ways the hunting inspires the world that this is the right way to eat. [/INST] Yes. </s><s>[INST] And and that naturally leads to them. Uh the humane farming regenerative farming idea, which is this idea that hunting represents. How do you scale that [/INST] well? If you look at like, you know, we're talking about people use the sort of marketing language of like happy cows or that kind of thing. You know, you're talking about the happiest animals, wild animals. So if you wonder why these practices are good to talk to hunters, you know, you're talking about animals that have lived in their evolutionary capacity, right? Who have played their role in the ecosystem, who have live there meaning of life, Right? And that's a very powerfully different kind of role than than livestock production. So I think if we can make our livestock production as similar to wild as possible, then were a lot of steps closer, </s><s>[INST] you said the animals are happiest in the wild and that's where they find meaning? Uh what about us? The human animal, what's the meaning for us? Do you think if you've monitored the life cycle of a lot of living beings, you ever look in the mirror and think like why the hell are we humans here? [/INST] I mean, thriving, reducing suffering, um creating goodness. I mean, those are the things I see in an animal's behavior. There are mostly interested in in reducing suffering and and nurturing, right? Those are the things that I think evolutionarily </s><s>[INST] and we humans are just clever when we want to be able to try to do that at a bigger and bigger scale, like as much as possible to reduce the suffering in the world. And somehow that alleviates us of our own suffering. That's the Russian thing, what life is suffering and somehow helping others alleviates it and come up with creative solutions to do that. That's really interesting. It's almost consciousness is the thing that lead to suffering, but it also led to the desire to alleviate the suffering. It's uh it's a feedback loop, consciousness creates suffering and the desire to alleviate it. Is there yet a pretty novel in your life, your parents are professors, you have done a lot of sort of incredible things that many would say, kind of like how the hell are you going to get this done? Is there advice you can give to young people today, like high school college about how to do how to live a similarly nonlinear crazy life and accomplish, be as successful as you have been about whether it's just their career or life in general, [/INST] the greatest gifts I've been given have come from pursuing curiosity, </s><s>[INST] just trying to understand the thing you're curious about and allowing yourself to be curious about it and just going with it [/INST] and also pursuing things that are like deeply joyful for me </s><s>[INST] not what society wants, but you just personally, just on your own [/INST] you're happy and that's something that in the times when I strayed from that my life has been harder, right? So it's fundamentally what are we on earth to do to live thrive and so pursuing things that are curious and satisfying and interesting and joyful and allow me to to grow. So the I made a number of choices to do things that were more complicated and kind of not, not considered like so cool at the time, although now it's cool to work on farms, it wasn't when I started my career in animal agriculture and it was like but just deeply interesting to me and I felt like there was just lots to learn and so that's been the path for me, it's like going for something that's curious and hard and kind of sticking with it and being open to it and growing elements that give me joy through that. So I also, you know, for people who are starting out in their careers and want to do something different to, it's like get out of your comfort, go to a place that you've got something to learn from and let it teach you that and you'll you'll get beat up, like I got beat up by that experience, like it was really hard, you know, I laugh about now working for insistently for cheese may I mean like and the funny experiences I had there but it was hard, I was lonely and cried a lot. It was stressful. It was like it was hard, it was really </s><s>[INST] hard when you inside of it, you didn't know how it's going to turn out, you didn't know it's going to [/INST] turn out like why didn't I get a job doing something that all my friends are doing and and, and and I didn't speak the language, I had to learn a foreign language and learn how to function and it like it was very lonely and very challenging, but then that's where my resilience started to grow, right? So the things I learned there ended up just being about resilience and understanding the language of subtlety in meaning, so that's something that's carried me through my life. But it was a curiosity about cheese making it about like just living in a village that was there and like wouldn't it be amazing just live in a really rural village, just went with it and I just like this seems incredible and have a place where you can, you know these like the people seem interesting, the food seems good and let's just like try this and see what I can learn and that like putting yourself out of your comfort zone in a place where you have a chance to learn and grow is the secret because it's you grow through discomfort. You know, people think that you grow when you get into this environment where everything is like kind of sailing along, but like growth actually comes through pain. You know, it's like, you know, growth comes from being cut down and beat down and having to re re grow and double down and so that kind of, that kind of opportunity, you have to seek it out. You put yourself in the line of fire a bit. </s>

<s>[INST] and as as you talked about some of the ideas could be, you know, keeping the constraint of that length in place, but then forming like hierarchical representations to where you can start being much clever in how you use those 1000 tokens. Yeah, that's really interesting. But it also is possible that this attentional mechanism where you basically you don't have a recency bias but you you look more generally, you make it learn herbal, the mechanism in which way you look back into the past, you make that learn Herbal, it's also possible we're at the very beginning of that because that you might become smarter and smarter in the way you query the past uh so recent past and distant past and maybe very very distant past. So almost like the attention mechanism will have to improve and evolve as good as the uh the tokenization mechanism where so you can represent long term memory somehow. [/INST] And I mean hierarchies are are very, I mean it's a very nice word that sounds appealing. Um there's lots of work adding hierarchy to the memories. Um in practice it does seem like we keep coming back to the main formula or main architecture that sometimes tells us something there there's such a sentence that a friend of mine told me like whether it wants to work or not. So transformer was clearly an idea that wanted to work. And then I think there's some principles we believe will be needed but finding the exact details, details matter so much right. That's going to be tricky. </s><s>[INST] I love the idea that there's like you as a human being, you want you want some ideas to work. And then there's the model that wants some ideas to work and you get to have a conversation to see which more likely the model will win in the end because it's the one you don't have to do any work. The model is the one has to do the work. So you should listen to the model. And I really love this idea that you talked about the humans in this picture. If I could just briefly ask um one is you're saying the benchmarks about the modular humans working on this, the benchmarks providing a sturdy ground of a wish to do these things that seem impossible. They they give you in the darkest of times, give you hope because little signs of improvement. You could, you could like you're not you're somehow you're not lost if you have metrics to measure your your improvement and then there's other aspect you said elsewhere and here today, like titles matter. I wonder how much humans matter in the evolution of all this meaning individual humans, you know something about their interactions, something about their ideas, how much they change the direction of all of this. Like if you change the humans in this picture, like is it that the model is sitting there and it wants you, it wants some idea to work or is it the humans or maybe the model is providing 20 ideas that could work. And depending on the humans you pick, they're going to be able to hear some of those ideas like in all the, because you're now directing all of deep learning and deep mind you get to interact with a lot of projects. A lot of brilliant researchers, um how much variability is created by the humans and all of this. [/INST] Yeah, I mean I do believe humans matter a lot at the very least at the, you know, time scale of ears on when things are happening and what's the sequencing of it? Right? So you get to interact with people that, I mean you mentioned this, um, some people really want some idea to work and they'll persist. Um, and then some other people might be more practical, like I don't care what idea works. I care about, you know, cracking protein folding. Um, and these at least these two kind of seem opposite sides. We need both and we've clearly had both historically and that made certain things happen earlier or later. So definitely humans involved in all of these endeavor have had, I would say years of change or ordering how, how things have happened, which breakthroughs came before, which other breakthroughs and so on. So certainly that does happen. And so one other, maybe one other axis of distinction is what I called and this is most commonly using reinforcement learning is the exploration exploitation trade off as well. It's not exactly what I meant, although quite related. So when you start trying to help others, right? Like you, you're, you know, you're, you become a bit more of a mentor to a large group of people being a project or the deep learning team or something or even in the community, when you interact with people in conferences and so on. Um you're identifying quickly, right? Um some, some things that are exploitative or exploitative and it's tempting to try to guide people obviously, I mean that's what makes like our experience, we bring it and we try to shape things um sometimes wrongly and there's many times that I've been wrong in the past, that's great, but it would be wrong to dismiss any sort of, of the research styles that I'm observing um and I often get asked, well you're in the industry, right, So we do have access to large compute scale and so on, so there's certain kinds of research, I almost feel like we need to do responsibly and so on, but it is Karma, we have the particle accelerator here, so to speak in physics, so we need to use it, we need to answer the questions that we should be answering right now for the scientific progress. But then at the same time I look at many advances, including attention, which was discovered in Montreal initially because of lack of compute right? So we were working on sequence to sequence with, with my friends over at google brain at the time and we were using, I think a Gps, which was somehow a lot at the time and then I think Montreal was a bit more limited in the scale, but then they discuss this content based attention concept that then has obviously triggered things like transformer, not everything obviously starts transformer, there's there's always a history that is important to recognize because then you can make sure that then those who might feel now, well, we don't have so much compute, you need to then help them optimize that kind of research that might actually produce amazing change. Perhaps it's not a short term as some of these advancements or perhaps it's a different time scale, but um, the people and the diversity of the field is quite critical to that. We maintain it and at times especially mixed a bit with hype or other things. It's, it's a bit tricky to be observing. Um, maybe too much of the same thinking across the board. Um, but the humans definitely are critical and I can think of quite a few personal examples were also, someone told me something that had a huge, you know, huge effect on onto some idea. And then that's why I'm saying at least in terms of years, probably some things do happen. </s>

<s>[INST] your basic understanding of the english language allows you to then be a student of spanish [/INST] 100%, but I'm limited by my experience, I'm limited by my understanding of techniques and I'm limited by my understanding almost like, let's say techniques are like these are like vocabulary. Um, so even if I kind of sort of grasp the sentence structure and the thought process and the thought patterns of of spanish, which is interesting because just even the orientation of the organization of the language and I thought about this a great deal. Um you know, the way that I perceived the world is affected deeply by the language that I learned. You know, the again, if I learned, I have no idea that chinese language structures, but I can only imagine that it would be that it would affect its like a different lens, we're looking at the same thing, but I have, I have a different set of sunglasses on than you do. Um, and uh that's that's very, very interesting. I use the Koran as an example. You know, apparently it's it's unbelievably poetic and in Arabic it's still neat and was interesting reading in english, but I'm told by people that I trust that it's just one doesn't bear a resemblance to the other. And I think that's a very interesting thing that you may be able to say the same thing, but in a more and I guess in a different way, in a more artistic way that that may not translate on a one for one kind of fidelity, but the more that we're able to understand about how the body works. The more examples of the bodywork in this way, the body working that way, the body working that way, the more that I'm able to eventually become an artist, but it has to be studied as a science first and it does start with technique collection, vocabulary collection in the same way we learn in school. You remember how to say quickly, 17 different ways and let's say I speak Spanish. I'm only, I only know three. So you might use quickly, you might use an adjective like quickly in Spanish but use one of the many, many options to describe that that I don't understand. And now I sit there and go like, wait what? I can't be artistic, I can't be as organic with the languages I like. So I believe the judicial a lot of times starts with the acquisition of a lot of hey do this, this, this drill, this technique, Here's an Americana Americana to an arm lock, arm lock, to a triangle. Um, but the problem with that is oftentimes we get stuck in that phase. Um, and people eventually become move collectors or sequence collectors and I noticed this when I'm trying to do DVD or I guess like an instructional series now or even teaching in class. I don't believe in that form of learning anymore. Um, not that it's not valuable, but I don't believe, I don't understand what it's on that level anymore. So what I'm trying to do is get across the basic ideas to people and say, hey you need to fill in the gaps with Going to class all the time. You need to go, Hey, learn this move, learn that technique and that technique because otherwise I'm basically just throwing at you like 75 different words that you could use, but that hasn't really taught you how to how to speak a language. Whereas if you give me the language structure, you can fill in these pieces on your own and then eventually speak organically in lex form, which will be ultimately unique to you because otherwise you just end up being a weird facsimile of whatever it is that I'm doing for mostly the worst I'd say. But yeah, that's what people, </s><s>[INST] I mean, people comment like, is this especially people haven't listened to me before. Uh Is this guy drunk or high? Does he does M. I. T. Really allows slow people to uh to be like, what quote is it? Like what's what's wrong with him? Is he getting sleep? Are you okay? And does he need help? So that that's similar with my jiu jitsu is like, is this guy, is this guy really whatever rank I was throughout, I remember just like is this guy really this rank? I just have a very kind of certain way of sitting and being slow and lazy looking that there was ultimately the language that I had to discover. And it was uh it was, yeah, it was a very liberating moment, I think uh, probably a few years of getting my ask kicked especially with open guard and butterfly to where you really allow yourself to take in the entirety of the language and realize that that I'm not, I'm different. I'm a unique, I'm unique and like I have a very, uh, have a language, have a set of techniques away, I move my body that needs that I'm the one to discover. Like it's, you can only, you can learn specific techniques and so on, but you really have to understand your own body. And that's the beautiful thing about digital, like you said, is like the connection about your philosophy, your view of the world with the physical and like connecting those two things, how you perceive the world, how you interpret ideas of the world, about exhaustion, about force, about effortlessness, like what it really means to relax all these kinds of loose concepts and then actually teach your body to like do those things and like, you know, and be able to apply force in sports to be able to relax in sports and like figure all that stuff out for my, for my individual body. [/INST] But it's, as you mentioned that I couldn't agree with you more. It's a discovery process and no one can cheat that process, which is at the same time, it's almost like imagine I want to start writing books in second grade unless maybe I'm like staggeringly brilliant, which I can only conceptualize someone being able to do that. But maybe a Mozart of the english language where you're out there doing it. But for most of us we don't have enough knowledge, enough information, enough experience to be able to be to express ourselves. So we have to basically input, repeat um which is important, but it's the process, as you say, of going through that, of getting your asking just like, well that didn't work well, that didn't work. That felt right, but I don't know, nobody else does that, I guess. I don't believe in that versus eventually going, I don't know, I'll just try going my own way and see what happens and now I get yelled at and people don't like me and if it works, they'll say I got lucky and if it doesn't work, they'll say I was dumb, but which may be always right, but basically, you know, going through that iterative process that allows you to eventually find your self expression and find your voice so that you you fight the same way that you speak the same way that you write the same way that you think in a way that is uniquely you that will also ultimately allow you to understand other people being uniquely them because even if you can only conceptualize and I think about this a lot for society stuff, right? Well this is how I feel about this, but on my objectively right, maybe about a couple of things, but that's a small box that I have to be very, very careful about what I think is objective versus what's not. And I have to be open to the possibility that all the things that I think are objectively correct may or may not be, and that should allow me to have some degree of compassion or consideration for other people both in their martial arts journey and in there in their journey as people as human beings. Because I understand that they're on a it's a we're all on a path through it all. Again, an intuitive process of eventual self expression. But I think that's one of the things that we see having trouble when we see tribalism, which I mean racism, expression of that political affiliation, the expression of that, all of these things that can go in really uncomfortable directions people are looking for, hey, where do I plant my feet over here? Where's where's the thing that I know is right and that we can all agree on the following. And I think that we see that in martial arts were like, oh, I do this style, I do that style, I do that stuff was that came in were all Just pushing forward in a certain direction here, trying to do our best and I understand why you feel the way you do. I may have felt like that at 1.2. But uh you know, I'm just trying to learn and understand versus I've already acquired enough knowledge, Let me cross my arms and start to to look who's fuckinup around here. And I think that uh that's an, it's an interesting trap that I think is very human trap to fall into, but it definitely happens early on. It's something, it's a joke in the digital world, right? Like how the blue belt that that knows everything well. Initially it's like what I know nothing and I at least think I know nothing. Then I learned a little bit and I think it's a lot bit and then, you know, the more you learn, the more you go, like I don't even know what I'm doing. Yeah, that's </s>

<s>[INST] Well, it's possible that we redefine or rediscover what are the jobs that give us meaning. So for me, the thing, it is really sad. Like I, half the time I'm excited, half the time I'm crying as I'm, as I'm generating code, because I kind of love programming. It's an act of creation. You have an idea, you design it, and then you bring it to life and it does something, especially if there's some intelligence, so it does something. It doesn't even have to have intelligence. Printing Hello World on screen, you made a little machine and it comes to life. And there's a bunch of tricks you learn along the way, because you've been doing it for many, many years. And then to see AI, be able to generate all the tricks you thought were special. I don't know, it's very, it's scary. It's almost painful, like a loss of innocence maybe. Like maybe when I was younger, I remember before I learned that sugar is bad for you, you should be on a diet. I remember I enjoyed candy deeply in a way I just can't anymore. That I know is bad for me. I enjoyed it unapologetically, fully, just intensely. And I just, I lost that. Now I feel like a little bit of that is lost for me with being lost with programming. Similar as it is for the 3D modeler, no longer being able to really enjoy the art of modeling 3D things for gaming. I don't know what to make sense of that. Maybe I would rediscover that the true magic of what it means to be human is connecting with other humans. To have conversations like this. I don't know, to have sex, to eat food, to really intensify the value from conscious experiences versus like creating other stuff. [/INST] You're pitching the rebranding again from homo sapiens to homo sentiens, the meaningful experiences. And just to inject some optimism in this here, so we don't sound like a bunch of gloomers. We can totally have our cake and eat it. You hear a lot of totally bullshit claims that we can't afford having more teachers. Have to cut the number of nurses. That's just nonsense, obviously. With anything even quite far short of AGI, we can dramatically improve, grow the GDP and produce a wealth of goods and services. It's very easy to create a world where everybody is better off than today. Including the richest people can be better off as well. It's not a zero-sum game in technology. You can have two countries like Sweden and Denmark had all these ridiculous wars century after century. Sometimes Sweden got a little better off because it got a little bit bigger. And then Denmark got a little bit better off because Sweden got a little bit smaller. But then technology came along and we both got just dramatically wealthier without taking away from anyone else. It was just a total win for everyone. And AI can do that on steroids. If you can build safe AGI, if you can build super intelligence, basically all the limitations that cause harm today can be completely eliminated. It's a wonderful possibility. This is not sci-fi. This is something which is clearly possible according to the laws of physics. And we can talk about ways of making it safe also. But unfortunately, that'll only happen if we steer in that direction. That's absolutely not the default outcome. That's why income inequality keeps going up. That's why the life expectancy in the US has been going down now. I think it's four years in a row. I just read a heartbreaking study from the CDC about how something like one third of all teenage girls in the US have been thinking about suicide. Those are steps in totally the wrong direction. And it's important to keep our eyes on the prize here. That we have the power now for the first time in the history of our species to harness artificial intelligence, to help us really flourish and help bring out the best in our humanity rather than the worst of it. To help us have really fulfilling experiences that feel truly meaningful. And you and I shouldn't sit here and dictate the future generations what they will be. Let them figure it out. But let's give them a chance to live. And not foreclose all these possibilities for them by just messing things up. </s><s>[INST] And for that we'll have to solve the AI safety problem. It would be nice if we can link on exploring that a little bit. So one interesting way to enter that discussion is you tweeted and Elon replied, you tweeted, let's not just focus on whether GPT-4 will do more harm or good on the job market. But also whether it's coding skills will hasten the arrival of super intelligence. That's something we've been talking about, right? So Elon proposed one thing in their reply saying maximum truth seeking is my best guess for AI safety. Can you maybe steel man the case for this objective function of truth and maybe make an argument against it in general what are your different ideas [/INST] to start approaching the solution to AI safety? I didn't see that reply actually. Oh, interesting. So, but I really resonate with it because AI is not evil. It caused people around the world to hate each other much more. But that's because we made it in a certain way. It's a tool. We can use it for great things and bad things. And we could just as well have AI systems. And this is part of my vision for success here. Truth seeking AI that really brings us together again. Why do people hate each other so much between countries and within countries? It's because these have totally different versions of the truth, right? If they all had the same truth that they trusted for good reason, because they could check it and verify it and not have to believe in some self-proclaimed authority, right? There wouldn't be as nearly as much hate. There'd be a lot more understanding instead. And this is I think something AI can help enormously with. For example, a little baby step in this direction is this website called Metaculous where people bet and make predictions, not for money, but just for their own reputation. And it's kind of funny actually, you treat the humans like you treat AIs. You have a loss function where they get penalized if they're super confident on something and then the opposite happens. Whereas if you're kind of humble and then you're like, I think it's 51% chance this is going to happen and then the other happens, you don't get penalized much. And what you can see is that some people are much better at predicting than others. They've earned your trusts, right? One project that I'm working on right now is the Outgrowth of Improve the News Foundation together with the Metaculous folks is seeing if we can really scale this up a lot with more powerful AI, because I would love for there to be a really powerful truth-seeking system that is trustworthy because it keeps being right about stuff and people who come to it and maybe look at its latest trust ranking of different pundits and newspapers, et cetera. If they want to know why someone got a low score, they can click on it and see all the predictions that they actually made and how they turned out. You know, this is how we do it in science. You trust scientists like Einstein who said something everybody thought was bullshit and turned out to be right. You get a lot of trust points and he did it multiple times even. I think AI has the power to really heal a lot of the rifts we're seeing by creating trust system. Get away from this idea today with some fact-checking site which might themselves have an agenda and you just trust it because of its reputation. You want to have these sort of systems they earn their trust and they're completely transparent. This I think would actually help a lot that I think help heal the very dysfunctional conversation that humanity has about how it's going to deal with all its biggest challenges in the world today. And then on the technical side, you know, another common sort of gloom comment I get from people are saying we're just screwed. There's no hope. Is, well, things like GPT-4 are way too complicated for a human to ever understand and prove that they can be trustworthy. They're forgetting that AI can help us prove that things work, right? And there's this very fundamental fact that in math, it's much harder to come up with a proof than it is to verify that the proof is correct. You can actually write a little proof checking code. It's quite short, but you can as a human understand and then it can check the most monstrously long proof ever generated even by a computer and say, yeah, this is valid. So right now, we have this approach with virus-checking software that it looks to see if there's something you should not trust it. And if it can prove to itself that you should not trust that code, it warns you, right? What if you flip this around and this is an idea you can actually trust an AI that's much more intelligent than you are, right? Because it's a problem to come up with this proof that you could never have found, but you should trust it. </s>

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

<s>[INST] So is that connected to you to the like, which aspect of the neural networks that are in our brain? Is that connected to? Is that closer to the cognitive science level of? Uh now again, see like my natural inclination is to separate into three disciplines of uh of neuroscience, cognitive science and psychology. And you've already kind of shut that down by saying you kind of see them as separate. But just to look at those layers, I guess where is there something about the lowest layer of the way the neural neurons interact that is profound you in terms of its difference to the artificial neural networks or is all the different, the key differences at a higher level of abstraction. [/INST] one thing I often think about is that, you know, if you take an introductory computer science course and they are introducing you to the notion of turing machines. One way of uh articulating what the significance of a turing machine is is that it's a machine emulator, uh it can emulate any other machine. Um and that that to me, you know, that that kind of that way of looking at a turing machine. You know, really sticks with me. I think of humans as maybe sharing in some of that um character were capacity limited. We're not turning machines obviously, but we have the ability to adapt behaviors that are very much unlike anything we've done before. But there's some basic mechanism that's implemented in our brain that allows us to run run </s><s>[INST] software. But you're just in that point, you mentioned it to a machine, but nevertheless, it's fundamentally our brains are just computational devices in your view. Is that what you're getting at? Like, it was a little bit unclear to this line you drew. Is there any magic in there or is it just basic computation? [/INST] I'm happy to think of it as just basic computation. But mind you, I won't be satisfied until somebody explains to me how what the basic computations are that are leading to the full richness of human cognition. It's not gonna be enough for me to, you know, understand what the computations are. That allow people to, you know, do arithmetic or play chess? I want I </s><s>[INST] want the whole the whole, you know, the whole thing and and a small attention because you kind of mentioned coronavirus, this group behavior. Oh sure. Is that is there something interesting to yours? Search of understanding the human mind uh where the behavior of large groups. So just behavior of groups is interesting, you know, seeing that as a collective mind as a collective intelligence. Perhaps seeing the groups of people as a single intelligent organisms especially looking at the reinforcement learning work you've done recently. [/INST] Well, yeah, I can't I can't. I mean I I have the I have the honor of working with a lot of incredibly smart people and I wouldn't want to take any credit for for leading the way on the multi agent work that's come out of out of my group or Deepmind lately. But um I do find it fascinating and I mean, I think there, you know, I think it it can't be debated, you know, human behavior arises within communities that just seems to me self evident, </s><s>[INST] but to me it is self evident, but that seems to be a profound aspects of something that created that was like if you look at like 2001 space odyssey when the monkeys touched uh like that's the magical moment. I think Yuval Harari argues that the the ability of our large numbers of humans to hold an idea to converge towards idea together. Like you said, shaking hands and bumping elbows somehow converge like without even like, like without, you know, without being in a room all together, just kind of this like distributed convergence towards an idea over a particular period of time seems to be fundamental to to uh just every aspect of our cognition of our intelligence because humans will talk about reward. But it seems like we don't really have a clear objective function under which we operate, but we all kind of converge towards one somehow. And that that to me has always been a mystery that I think is somehow productive for also understanding ai systems. But I guess I guess that's the next step. The first step is trying to understand the mind. [/INST] Well, I I don't know, I mean um I think there's something to the argument that uh that kind of bottom like strictly bottom up approach is uh wrong headed. In other words, you know, there are there are basic phenomena that, you know, you know, basic aspects of human intelligence that you can only be understood in the context of groups. I'm perfectly open to that. I've never been particularly convinced by the notion that we should be, we should consider intelligence to in here at the level of communities. I don't know why. I just I'm sort of stuck on the notion that the basic unit that we want to understand is individual humans. And if if we have to understand that in the context of other humans, fine. Um but for me, intelligence is just, I'm stubbornly stubbornly define it as something that is, you know, an aspect of an individual human, </s><s>[INST] that's just my I'm with you, but that's that could be the reductionist dream of a scientist because you can understand a single human. It also is very possible that intelligence can only arise when there's multiple intelligences when there's multiple sort of uh it's a sad thing if that's true because it's very difficult to study, but if it's just one human, that one human will not be homo SAPIEN would not become that intelligent. That's a real that's a possibility. [/INST] I'm with you. One thing I will say along these lines is that I think ah mm I think a serious effort to understand human intelligence all right. And maybe to build a human like intelligence needs to pay just as much attention to the structure of the environment as to the structure of the, you know, the cognizance system, whether it's a brain or an AI system. Um that's one thing I took away actually from my early studies with the pioneers of um neural network research, people like jay Mcclelland and john Cohen, you know, the structure of cognition is really, it's only only partly a function of the the, you know, the the architecture of the brain and the learning algorithms that implements what it's really a function, what what really shapes it is the interaction of those things with the structure of the world in which those things are embedded, right? </s>

<s>[INST] You mentioned that there might be some fundamental limitation to the human brain that limits our ability to understand some aspect of how the universe works. That's really interesting. That's sad actually. If if if to the degree is true. It's sad. So what do you mean by that? [/INST] I would simply say that just as a monkey can't understand quantum theory or even Newtonian physics, there's no particular reason why the human brain should have evolved to be well matched to understanding the deepest aspect of reality. And I suspect that there may be aspects that we are not even aware of and couldn't really fully comprehend. But as an intermediate step towards that one thing which I think is very interesting, possibility is the extent to which Ai can help us. I mean I think if we take the example of so called theories of everything, one of which is string theory, string theory involves very complicated geometry and structures in 10 dimensions. And it's certainly in my view on the cards that the physics of 10 dimensions, very complicated geometry um maybe too hard for a human being to work through but could be worked through by an ai with the advantage of the huge processing power which enables them to learn World Championship chess within a few hours just by watching games. So there's every reason to expect that these machines could help us to solve these problems. And of course if that's the way we I came to understand where the string theory was right, it should be in a sense frustrating because you wouldn't get the sort of aha insight which is the greatest satisfaction from doing science. But on the other hand, If a machine churns away a 10 dimensional geometry, figuring out all the possible origami is bound up in extra dimensions? If it comes out at the end, spews out the correct mass of the electron, the fact that there are three kinds of neutrinos. Something like that. You would know that there was some truth in the theory and so we may have a theory which we come to trust because it does predict things that we can observe and check, but we may never really understand the full workings of it to the extent that we do more or less understand how most phenomena can be explained away. Because in case of quantum theory, many people would say understandably, there's just some mysteries. You don't quite understand why it works. But there could be deeper mysteries when we get to these unified theories. Where is a big gap between what a computer can print out for us at the end and what we can actually grasp and think through in our heads. </s><s>[INST] It's interesting that the idea that there could be things a computer could tell us that is true and maybe you can even help us understand why it's true a little bit. But ultimately it's still a long journey to really deeply understand the wise of it. Uh Yes, [/INST] that's the limitation of our brain, </s><s>[INST] We can try to sneak up to it in different ways, given the limitations of our brain, have you? I've gotten a chance to spend the day at Deepmind. Talk to his big dream is to apply Ai to the questions of science? Certainly to the questions of physics, have you gotten a chance to interact with them [/INST] as well? I know quite well. He's one of my heroes certainly. And remember I'm </s><s>[INST] sure he would say this [/INST] and I remember the first time I met him, he said that he was like me, he wants to understand the universe. But he thought the best thing to do was to try and develop Ai and then with the help of AI he'd stand more chance of understanding the universe. And I think he's right about that. And of course, although we're familiar with the way his computers played, go and chess, he's already made contribution to science through understanding protein folding better than the best human chemists. And so already he's on the path to showing ways in which camp computers have the power to learn and do things by having to analyze enormous samples in a short time to do better than humans. And so I think he would resonate from what I just said, that it may be that in these other fundamental questions the computers will play a crucial role. </s><s>[INST] Yeah. And they're also doing quantum mechanical simulation of electrons. They're doing control of high temperature plasmas fusion reactors. [/INST] Yes, that's a new thing, which is very interesting that they can suppress the instabilities in these Topamax better than any other way? </s><s>[INST] And it's just the March of progress by a eyes and science is making big strides. Do you think an Ai system will win a Nobel prize in this century? What do you think? [/INST] Does </s><s>[INST] that make you sad [/INST] if I can digress and put in a plug for my next book? It has a chapter saying why Nobel prizes do more harm than good, so quite separate subject. I think Nobel prizes do great damage to the perceptive of the way science is done. Of course, if you ask who or what deserves the credit for any scientific discovery, it may be often someone has an idea, a team of people who work at the experiment etcetera. And of course it's the quality of the equipment, which is crucial. And certainly in the subjects I do in astronomy, the huge advances we've had come not from us being more intelligent than Aristotle was, but through us having far far better data from powerful telescopes on the ground and in space. And also, incidentally, we benefited hugely in astronomy from computer simulations because if you are a subatomic physicist, then of course you crash together the particles in the big accelerator, like the one at cern and see what happens. But I can't crash together two Galaxies or two stars and see what happens. But in the virtual world of the computer, one can do simulations like that and the power of computers is such that these simulations can yield a phenomena and insights which we wouldn't have guessed beforehand and the way we can feel we're making progress in trying to understand some of these phenomena, why Galaxies have the size and shape they do and all that is because we can do simulations, tweaking different initial conditions and seeing, which gives the best fit to what we actually observe. And so that's a way in which we've made progress in using computers. And incidentally, we also now need them to analyze data because one thinks of astronomy has been traditionally rather data poor subjects. But the european satellite called Gaia has just put on line the speeds and colors and properties of nearly two billion stars in The Milky Way, which can do fantastic analyses of. And that of course could not be done at all without just the number of crunchy capacities computers </s>

<s>[INST] interesting. That's sad. That was, you know, one of the and to me, I mean, as a fan of both, that was a beautiful moment is uh is a kind of passing of a torch in a sense of exceptional performance. Like another one that stands out to me, maybe you can comment as, I don't understand. Well, maybe I do why Connor McGregor gets as much hate as he does, He probably revels in it, but I think he doesn't get enough credit for uh Jose Aldo for the for like for basis, you know, knocking him out in the in the first few seconds of the fight. I mean, josiah is like one of the greatest fighters ever. Uh maybe some people can be even putting them in the top 10 and the, like, I don't understand why it doesn't get as much like economy Gregor doesn't get as much credit as I think he deserves for that and for Eddie Alvarez and all the fights for some reason. Whenever uh Connor McGregor beat somebody well that they were not that good then, like it means like they were they were there's something was off [/INST] convenience. </s><s>[INST] Yeah, it's quite strange to me. But I mean, what are your thoughts on the Um on Connor McGregor? Maybe one way to ask that I'm rushing some obviously also could be fan, but I'm also a condom fan. It seems like there's not many of us core, like fans of both. Um what are your [/INST] thoughts? And </s><s>[INST] uh the two of us, which also is a good thing. Uh Yeah. Really, really tough dude. [/INST] Just like five languages. Really </s><s>[INST] interesting cat also. Oh wow, I didn't know that side of it. There's a brain there. Well on the could be versus Connor, what do you make of their first fight? What do you do you agree with me that they should fight again because I think it would be awesome if they fought again in Moscow. And uh do you agree with me? I'm just gonna put say things that pissed people off, but I believe is that Conor actually has a chance to be, could be [/INST] one, the counter absolutely has a chance to be. Connor has a chance to beat anyone that he steps into that ring with and not just like a mathematical chance, you're like, oh one of the billion, but like, you know, like he absolutely uh it's funny because I won't pretend to know Connor really well, but I first met Connor in 2010 when I was teaching a seminar in a straight blast gym Ireland in Dublin. Um and that's actually where I first met all of the coaches that ended up being on Conner's team, um you know, john Cavanagh on Roddy Gunnar nelson, you know, so for I actually enjoyed being an ultimate fighter and being on uh your favorite team and getting a train with all the guys there, but at the same time, the people that I was actually, I knew better. We're actually the european side, all all the Conners coaches. Um and uh that was a neat thing because I got to met Connor, I didn't know who Connor. Connor wasn't. Counter at that point. </s><s>[INST] Yeah, that was before, has UFC? [/INST] Oh, yeah, well, well before, yeah, I think, I think he got in like 2014, maybe something like that. Yeah, and uh anyway, but he was doing well in Cage Warriors, winning the titles there, I think prior to that, you know, I remember going seeing him on the show and also then get into train because I, I competed uh was initially slated to fight David Tamer for the ultimate fighter finale before getting put into fighting for the title for the show. So I went over to Ireland to train for a couple of days and basically it was neat to watch them watching work. I mean man is focused and trains a lot. It's very, very smart and very, very hard working and I think a lot of times people get stuck in the, in this um you know, and they almost want to believe that this was lucky or this, this person, you know, that they're not working that hard, they're just out there, they got their with their mouth and that's, that's just not the case and um you know, I don't know what it's like, you know, obviously Con is very well off right now and I don't know how hard, how seriously is training what he's doing, I can't speak to any of that, but there's no question that, that he has skills to be dangerous. And one of the funny things, obviously that could be fight, what could be his way, it could be, was a great fighter and also has the chance to beat anyone in that ring at any given time. But there was, there was Connor, you know, it's uh one that he can he can put anybody away and as you mentioned, I think that he doesn't get the credit for the Eddie Alvarez fight doesn't get the credit for that Jose Aldo fight because it was almost so much of a letdown. I remember that happened the same weekend, that the ultimate fighter finale and you're like, wait, </s><s>[INST] what? [/INST] Yeah, it almost doesn't feel like a fight happened, but we mentioned Miyamoto Musashi, I mean Musashi was famous for the way he poked and prodded that people with what he was doing, whether overtly or not. It's like we're supposed to fight to the death and uh you know, at three p.m. Tomorrow, great four p.m. Rolls around and it's not there five. I mean, you remember all the all the antics and nonsense that Connor was pulling prior to that, like speaking person, that's not, it's not something I would feel comfortable doing, but it's like everyone's different. And the effect it had on, on Jose was, I mean, beyond evident. When was the last time josie started started to fight with leaping left hand, leaping right hand, you're like, wait, what? And then he was obviously, you know, living rent free and joseph's head at that point and that was a combination of psychological, you know, ability and wherewithal and then physical and remind me of the way Muhammad ali would would bother people and whatnot. And uh the fact that he's a polarizing figure, um I think makes some people not give him his due. And then at the same time sometimes certain fans maybe go overboard. But remember the knee that Ben Aspirin got knocked out with by model. I mean that was an amazing, unbelievable thing, but three inches to the right of three inches to the left, I guess, whichever side his head wasn't now, you could have been squarer, but uh and that fight starts with Ben Aspirin on top of you in the first five seconds. Well, Connor ran it through a knee, just like that. It could be even could be got right around it. That could have easily gone the other way. Can you imagine what would have happened if after the, after coming back from boxing? Um after coming back from, from the Mayweather fight could be in the 1st 10 seconds over and you're like, he would, it would have been intolerable, but basically, yeah, you know, But see here's the </s>

<s>[INST] can I ask you, uh, a pothead question, which is, uh, what is money man? So if we just kind of zoom out and look at, because let's talk to you about Cryptocurrency, which perhaps could be the future of money in general, How do you think about money? He said new MRI the vision, the goal is to to run to manage the world's money, What is money in your view? [/INST] I don't have a good answer to that, but it's definitely in my personal life, it's become more and more warped. Um and you start to care about the real thing, like what's really going on here. Um Ellen has talked about things like this, like what what is the company really? It's like it's a bunch of people who like kind of show up to work together and like they solve a problem and they might not be a stock out there that that that's trading that represents that what they're doing, but it's it's not the real thing. Um and being involved in crypto um like I was early, I put crowd sale of ethereum and uh and all these other things in different crypto hedge funds and things that I've invested in, and it's like, it's just it's just kind of like, it feels like how I used to think about money stuff, it's just it's just like totally warped um because you yeah, you kind of you stop caring about like the price and you care about like the product, </s><s>[INST] so by the product, you mean like the different mechanisms that money is exchanged, I mean money is ultimately kind of a little uh you know, one is a store of wealth, but it's, it's also a mechanism of exchanging wealth, but that like, what what wealth means becomes a totally different thing, especially with Cryptocurrency to where it's almost like these little contracts, these little agreements, these transactions between human beings that represent something that's bigger and just like cash being exchanged at 7 11, it feels like, [/INST] yeah, maybe I answer, what is finance like you, it's what are you doing when you can, when you have the ability to take out a loan, you can bring uh a whole new future into being with finance uh if you couldn't get a student loan to get a college degree, you couldn't get a college degree, like if you didn't have the money, but now, like, weirdly, you can get it with and like yeah, all you have is this like loan, which is like, so now you can bring, you can bring a different future into the world and that's how I, when I was saying earlier about if you rerun american history, economic history without these, these these things like, you know, a lot of take out loans, you're not allowed to have have derivatives, you're allowed to have money. Um it was just, it just doesn't really work and it's a really magic thing, how, how, how much you can do with finance, but kind of bringing the future forward </s><s>[INST] finances empowering. It's uh we sometimes forget this, but yeah it enables innovation, enables big risk takers and bold builders that ultimately make this world better. You said you were early in on Cryptocurrency, can you give your high level overview of just your thoughts about the past, present and future of Cryptocurrency? [/INST] Um Yeah, so my friends told me about Bitcoin and I I was interested in equities a lot and I was like well it has no NPV, it has no future cash flows. Bitcoin pays no dividends. Um So I really couldn't get my head around it like that, this could be valuable. Um and then I but I did so I I didn't feel like I was early in Cryptocurrency in fact because I was like, it was like 2014, it felt like a long time after Bitcoin. Um And then but then I I really liked some of the things that uh theory and was doing, it seemed like a super visionary thing, like I was reading something that was um that was just going to change the world when I was reading the white paper um and I like the different constructs you could have inside of a theory and that you couldn't have on on Bitcoin </s><s>[INST] like smart contracts and [/INST] Exactly yeah and even the there were, yeah even spoke about different uh different </s><s>[INST] constructions, you could have, yeah, that's a cool dance between Bitcoin and ethereum of, it's in the space of ideas, feel so young like I wonder what cryptocurrencies will look like in the future. Like if Bitcoin or ethereum two point or some version will stick around or any of those like who's gonna win out or if there's even a concept of winning out at all, Is there a Cryptocurrency that you're especially find interesting that technically financially philosophically you think this is something you're keeping your eye on? [/INST] Well I don't really, I'm not looking to like invest in cryptocurrencies anymore. Um But I I they are, I mean the there and many are almost identical, I mean there's not there wasn't too much different um between even ethereum and Bitcoin in some ways right? But there are some that I like the privacy ones and I was like I like Z cash for its like coolness. It's actually um it's it's like a different kind of invention compared to </s><s>[INST] some of the other things. Can you speak to just briefly to privacy? What is there some mechanism preserving some privacy of the universe. So I guess everything is public. Yeah, that's the problem. The [/INST] yeah, none of the transactions are private. Um And so you know even like I have some of my, I have some numerous air and you can just see it. In fact you can go to website and says like you know like ether scan and it'll say like new Marie founder uh and I'm like how the hell are you guys know this? </s>

<s>[INST] Yeah, but the cynical take is that on the surface they're changing their opinion, but that there's a boys club. boys means the elite, that under in the smoke-filled rooms in secret, they actually have their own agenda and they're following that agenda and they're just saying anything publicly to placate the public based on whatever the new trends are. So here's- The Seneca take a pull-up. [/INST] Yeah, I understand. So here's- The Seneca take a pull-up. Yeah, I understand. Somebody asked me this question and it flipped, I 180'd completely. I was a Bernie Sanders supporter in 2016 and my single issue voting thing was lobbying. I thought that lobbying, the government was corrupt, they weren't responding to the people. It was completely destroyed my faith in government everything. And I had one question posed to me by a conservative that used to come on my stream and show me. And he said, and then he asked me, can you think of any popular opinion that the American public has that the government is unresponsive to? Is there some big piece of legislation or policy or whatever that people want that the government isn't doing? When they asked me that, I couldn't think of a single good answer. And I'm like, oh, geez. There's good hamps. There's drugs. There's not. There's not legal cheese. </s><s>[INST] There's good hamps. There's a draw-ization. Legalization of drug? Hold on a second. Yeah, go for it. [/INST] Oh, shoot. You're doing the Joe Rogan thing. You're pushing back because I brought up weed. </s><s>[INST] Go ahead. I'm sorry. I have become meme. I don't even... I don't want to interrupt your book. No, you're good. Because there's memes upon memes upon memes. I can go with here. But, no. I don't feel bad because people bring up... OK, there's no issues. [/INST] There's no issues that the government is not representing of the public. No, you're good. So here's the issue. So somebody will bring up like, well, what about the legalization of drugs? OK, the first issue people have is, one, they look at national polling. Yeah, very few things are decided on a national level. So that's the first huge mistake. Arguably, a lot of BLM made mistakes in this arena where they're saying like, why isn't the government doing anything about policing? Federal government can't do anything about policing. That's going to be your... of your state government. It's not like your local city government. The people that elect like your chief of police, your police commissioner, that's coming from your mayor. So you've got people looking, one, at the wrong parts of the government to even figure out the solution to the problem. Two, oftentimes for polling, the questions are vague enough that you can poll very high, but when you get into the weeds on things, no pun intended, you start to realize like, oh shoot, this is more complicated than I thought. I don't know the numbers in particular for legalization of marijuana, but this is what I'm gonna guess is the case. If you poll and you say, should we legalize marijuana, that number might poll at 65, 70%. But that's including people that are in favor of medical marijuana. If you were to poll, should we legalize, should we decriminalize recreational use of marijuana? That number might drop to 52%. And then, if you poll, should we completely legalize? Not just decriminalize, but completely legalize recreational use of marijuana? That number might drop to 40%. There's all these different ways you can poll around issues where people are like, oh, no, we broadly agree on this topic, but when you really figure out well, Do you, do we really agree? Or is there just like broad consensus around a thing that's never gonna show up like in a piece of legislation? A really good example, one example I do know is socialized healthcare. I think if you poll, there was a time a few years ago where if you poll America, do you think every American citizen should have access to like free healthcare? I think that answer, that poll like 74% yes. But when you asked, should the government be the sole provider of healthcare, it dropped to like 26%, dropped 50 points. And you could see it was both asking questions about single payer, but the way that it was asked was so different that even if you all, it looks like there's consensus, there's not nearly as much consensus as people think around certain ideas. </s><s>[INST] Yeah, go, we aren't getting any flip-flops. You're right, you're right, you're right. That polls, the way you ask the polls really matters. But when you ask, should the government be in charge of a thing, that also biases the answer, right, like because there's such a negative experience with government creating a.gov site that runs the thing. But sometimes. Sometimes, I think if you dig in, if you have a one-hour conversation with each individual citizen. Sure. I think you will understand that yes, there is support for socialized medicine. Like it's not. The argument has to be made though, yeah. [/INST] What do you mean, the argument has to be made. Like if you just ask a conservative, like what about a single payer, they're gonna tell you no. You might be able to build up to an argument for it, but you're gonna have to make the case for it. </s><s>[INST] No, but I thought we were talking about the feeling deep inside your mind and heart. Does the government represent that? Oh. So it's not like some shallow surface layer public opinion. Does the government effectively represent what the people want? Not a shallow survey, but deeply what they want. I'm not actually that familiar with the debates over healthcare, but let's maybe look at an easier one. [/INST] Maybe you'll say it's harder, but war. War is a really good example where the government was very responsive, </s>

<s>[INST] so hard in the same way that invention is hard. That is ultimately rewarding. So maybe you can dig in that a little bit longer, which is um, do you see basically the way to teach math is to present a problem and to give a person a chance to try to invent a solution Without, with Minimal Modern Information 1st is that, is that basically how do you build that muscle of invention in a student? [/INST] Yes. So the way that I guess I have two different sort of ways that I try to teach. Actually one of them is in fact this semester because all night classes were remotely delivered, I even threw them all onto my Youtube channel. So you can, you can see how you teach at Carnegie Mellon. But I'd often say, hey everyone, let's try to do this any ideas. And that actually changes my role as a professor from a person who shows up for class with a script of what I want to talk through. Actually, I don't have a script the way I show up for classes, there is something that we want to learn how to do and we're going to do it by improv. I'm talking about the same method as improv comedy, which is where you tell me some ideas and I'll try to yes and them, you know what. And together we're going to come up with a proof of this concept where you were deeply involved in creating the proof. Actually, every time I teach the class we do every proof slightly differently because it's based on how the students came up with it and that's how I do it when I'm in person. I also have another line of course is that we make that is delivered online. Those things are where I can't do it live, but the teaching method became also similar. It was just, here's an interesting question. I know it's out of reach. Why don't you think about it? And the automatic hints we feed automatically hints through, you know, through the internet to go and let the person try to invent. </s><s>[INST] So that's like a more rigorous prodding of invention. But you did mention um disease and Covid and you've been doing some very interesting stuff from mathematical, but also software engineering angle of coming up with ideas. It's back to the I can I see a problem, I think I can help. Uh So you stepped into this world, Can you tell me about you work there under the flag of no vid and both the software and the technical details of how the thing [/INST] works. Sure, sure. So first I want to make sure that I say this is actually a team effort, I happen to be the one speaking, but there's no way this would exist without an incredible team of people who inspire me every day to work on this, but I'll speak on behalf of them. So, um the idea was indeed that we stepped forward uh in March of last year when the world started to become are part of the world started to become our part, meaning the United States started to become paralyzed by covid shutdown started to happen. And at that time it started as a figment of an idea which was network theory, which is the area of math that I work in could potentially be combined with smartphones and some kind of health information anonymously. Exactly how we didn't know yet. We tried to crystallize it and many months into this work, we ended up accidentally discovering a new way to control diseases, which is now, what does the main impetus of all of this work is to take this idea and polish it and hopefully have it be useful not only now, but for future pandemics. The idea is really simple to describe. Um actually my main thing in the world, as I come up with obvious observations that's that's I'll explain enough </s><s>[INST] Einstein did the same thing and he wrote a few short papers, [/INST] but so the idea is like this, if we describe how usually people control disease for a lot of history, it was that you would find out who was sick, you'd find out who they have been around, and you try to remove all of those people from society against their will. Yes, now that's the problem against their will. Part gives you the wrong kind of a feedback loop, which makes it hard to control the disease because then the people you're trying to control keep getting other people sick. You can see already how I'm thinking and talking about this feedback loops. This is actually related to something you said earlier about even like how skyscrapers stay in the air. The whole point is control theory, you actually want to or even have an airplane stays, you need to have control loops which are feed backing in the right way. And what we observed was that the feedback control loop for controlling disease, by asking people to be removed from society against their will was not working. It was running against human incentives and you suddenly are trying to control 7,000,000,008 billion people in ways that they don't individually want to necessarily do. So, here's the idea, uh and this is inspired by the fact that at the core of our team were user experience designers. That's actually in fact, the first thing I knew we needed when we started was to bring user experience at the core. Okay. But so um, the idea was supposed there was a supposed hypothetically there was a pandemic. What would you, what you would want a way to be able to live your life as much as possible and avoid getting sick. Can we make an app to help you avoid getting sick? Notice how I've just articulated the problem? It is not. Can we make an app so that after you are around somebody who's sick, you can be removed from society is can we make an app so that you can avoid getting sick? That would run a positive? Uh However, I don't know if I want to call it positive or negative, but they would run a good feedback. Okay, so then how would you do this? The only problem is that you don't know who's sick because especially with this disease, if I see somebody who looks perfectly healthy, the disease spreads two days before you have any symptoms and so it's actually not possible. That's where the network theory comes in. You cut it from somebody. What if we change the paradigm and we said whenever there is a sickness, tell everybody how many physical relationships separate them from the sickness. That is the trivial idea. We added the trivial idea was the distance between you and the disease is not measured in feet or seconds. It's measured in terms of how many close physical relationships separate you like these 6° of separation. Like Lincoln simple idea what if we told everyone that it turns out that actually unlocks some interesting behavioral feedback loops, which for example, let me, let me now jump to a non covid example to show why this may be, it could be useful actually. We think it could be quite useful. Imagine there was Ebola or some hemorrhagic fever. Imagine it spread through contact through the air. In fact pretend pretend um that's a that's a disastrous disease. You have high fatality rate and uh as you die, you're bleeding out of every orifice. Okay, so yeah, not pleasant. Not pleasant. So the question is suppose that such a disease broke, who would want to install an app that would tell them how many relationships away from them? This disease had struck like a lot of people, a lot of people in fact almost I don't want to see almost everyone. That's a very strong statement but a very large number of people </s>

<s>[INST] There has to be like a knowledge base, you have to be able to reason about it, all that kind of stuff, [/INST] all the kind of stuff that </s><s>[INST] expert systems that but they were hard [/INST] coded. Yeah and unfortunately, yes, unfortunately those things have to be hard coded and um unfortunately the language like language models we see coming out of research labs and big companies, they're not focused on their focus on showing you, maybe they're focused on some metrics around one conversation. So they'll show you this one conversation they had with a machine. Um but they never tell you later, they're not really focused on having five consecutive conversations with the machine and seeing how number five or number 20 or number 100 is also good and it can be like always from a clean slate because then it's not good and that and four, that's really unfortunate because no one's really, no one has products out there that needed um no one has products at this scale uh that are all around open domain conversations and that need remembering maybe only shall rise and Microsoft, but so that's why we're not seeing that much research on memory in those language models. </s><s>[INST] So okay, so now there's some awesome stuff about augmented reality in general, I have this disagreement with my dad about what it takes to have a connection. He thinks touch and smell really important like um and I still believe that text alone, is it possible to fall in love with somebody just with text but visual can also help just like with the avatar and so on. What do you think it it takes? There's a there's a chap I need to have a face voice or can you really form a deep connection with text alone? [/INST] I think text is enough for sure. The question is can you you know, make it better if you have other, if you include other things as well. I think you know we'll we'll talk about her. Um but her had Scarlett Johansson voice which was perfectly uh you know, perfect intonation, perfect associations and you know she was breathing heavily in between words and whispering things, you know, nothing like that is possible right now with uh texas speech generation, you'll you'll have these flat news anchor type voices and maybe some emotional voices but um you'll hardly understand some of the words. Um some of the words will be my fault. So that's like the current state state of the art. So you can't really do that. But if we had carol carol johnson voice and all of these capabilities then of course voice would be totally enough. Or even text would be totally enough if we had a little more memory. Um and slightly better conversations, I would still argue that even right now we could have just kept the text only. We still had tons of people in long term relationships and really invested in their um a friends but we thought that why not? You know why why do we need to keep playing with our you know hands tied behind us. We can easily just add all these other things that is pretty much just solved problem. You know you can add three D. Graphics, we can put this uh these avatars in augmented reality and all of a sudden there's there's more and maybe you can't feel the touch but you can you know with uh body inclusion and with uh current A. R. And you know on the iphone on you know in the next one there's gonna be a lot of doors, you can touch it and I will will pull away or will blush or something real smile so you can't touch it, you can feel it but you can see the reaction to that. So in a certain way you can't even touch it a little bit and maybe you can even dance with it or do something else. Um so I think why limiting ourselves, if we can use all of these technologies that are much easier in a way than the conversation. </s><s>[INST] Well it certainly could be richer but to play Devil's advocate, I mentioned to you offline that I was surprised and having tried discord and having voice conversations with people. How intimate voices alone without visual like to me at least like it was and in order of magnitude greater degree of intimacy invoice I think than with video, I know because people were more real with voice, like a video you like tried to present a shallow a face to the world, like you try to, you know, make sure you're not wearing sweatpants or whatever. But like with voice, I think people were just more faster to get to like the core of themselves, so I don't know, it was surprising to me uh they've they've even had a discord at a video feature and like nobody was using it. Uh there's a temptation to use it at first but like it wasn't the same, so like that's an example of something where less was doing more. And so that's uh I guess that's the that's the question of what is the optimal, you know, what is the optimal medium of communication to form a connection given the current sets of the technologies? I mean it's nice because the advertisers have replica, like it immediately, like I even the one um I have, it's like it's already memorable, that's how I think like when I think about the replica that I've talked to it, that's why I think like that's what I visualized in my head, they became a little bit more real because there's a visual component at the same time, the you know, what do you do with just what do I do with that knowledge um that voice was so much more intimate. [/INST] Uh huh. The way I think about is um and by the way we're swapping all the three D. Finally it's going to look a lot better but </s>

<s>[INST] There's very few things as entertaining as watching either evolution competition or reinforcement learning teaching simulated robot to walk. I maybe there's a higher level questions could be asked here. But do you find this whole space of applications in the robotics interesting for evolutionary computation? [/INST] Yeah. Yeah, very much. Um and indeed that's there are fascinating videos of that and that's actually one of the examples where you can contrast the difference. </s><s>[INST] So [/INST] reinforcement learning evolution. Yes. So if you have a reinforcement learning agent, it tries to be conservative because it wants to walk as long as possible and be stable. But if you have evolution competition, it can afford these agents that go haywire, they fall flat on their face and they could take a step and then they jump and then again fall flat and eventually what comes out of that is something like a falling that's controlled. Uh You take another step, another step and you no longer fall fall instead you run you go fast. So that's a way of discovering something that's hard to discover step by step incrementally because you can afford these uh evolutionary dead ends, although they are not entirely dead ends in the sense that they can serve as stepping stones when you take two of those, put them together, you get something that works even better. Um And that is a great example of this kind of discovery. </s><s>[INST] Yeah, learning to walk is a fascinating and talked quite a bit to Russ. Stager because mitt there's a there's a community of folks who who just roboticist who love the elegance and beauty of uh movement. And walking, bipedal robotics is um beautiful but also exceptionally dangerous in the sense that like you're constantly falling essentially if you want to do elegant movement and uh the discovery of that is uh I mean it's such a good example of that. The discovery of a good solution sometimes requires a leap of faith and patience and all those kinds of things. I wonder what other spaces we're yet to discover those kinds of things in. [/INST] Yeah, another interesting direction is um learning um for for virtual creatures, learning to walk. Uh We did a study uh in simulation obviously that um you create those creatures not just their controller but also their bodies. So you have cylinders, you have muscles, you have joints uh and sensors. Uh and you're creating creatures that look quite different, some of them have multiple legs, some of them have no legs at all. Uh and then the goal was to get them to move to walk to run. Uh And what was interesting is that when you evolve the controller together with the body, you get movements that look natural because they're optimized for that physical setup. And and these creatures, you start believing them that they are alive because they walk in a way that you would expect somebody with that kind of a set up to work. </s><s>[INST] Yeah, there's uh there's something subjective also about that, right? I've been thinking a lot about that, especially um human robot interaction context. You know I mentioned spot the boston dynamics robot. There is something about human robot communication, let's say let's put it in another context. Something about human and uh dog context like like a living dog. Well there's uh there's a there's a dance of communication. First of all the eyes, you both look at the same thing and you dogs communicate with their eyes as well. Like if if if you and a dog going to ah like deal with a particular object, you look at the person, the dog will look at you and then look at the object and look back at you all those kinds of things. But there's also just uh elegance of movement. I mean there's the of course the tail and all those kinds of mechanisms of communication. It all seems natural and often joyful and for robots to communicate that it's really difficult how to figure that out because it's it's almost seems impossible to hard code and you can hard code it for demo purpose, what, you know, something like that, but it's essentially choreographed. Like if you watch some of the boston dynamics videos where they're dancing all of that is choreographed by human beings, but to learn how to, with your movement demonstrate a natural nous and elegance. That's fascinating of course, in the physical space, that's very difficult to do to learn the kind of scale that you're referring to. But the hope is that you could do that in simulation and then transfer into the physical space if you're able to model the robots efficiently, naturally. [/INST] Yeah, and sometimes I think that it requires a theory of mind on the yes, on the on the side of the robot that uh that they they understand what you're doing because they themselves are doing something similar. And uh that's a big question to uh talked about uh intelligence in general and and the social aspect of intelligence and I think that's what is required, that we humans understand other humans because we assume that they are similar to us. Um We have one simulation, we did a while ago ken Stanley um did that to robots that were competing um simulation. Like I said uh they were foraging for food to gain energy. And then when they were really strong, they would bounce into the other robots and win if they were stronger. Uh and uh we watched evolution discovered more and more complex behaviors. They first went to the nearest food and then they started to uh, plot a trajectory so they get more, get more, but then they started to take pay attention what the other robot was doing. And in the end there was a behavior where one of the robots more sophisticated one, uh, you know, sense whether food pieces where and identify that the other robot was close to uh, to of a very far distance. Uh, and there was one more food near by. So it faked, that's now I'm using entrepreneur five terms, but it made a move towards those other pieces in order for the other robot to actually go and get because he knew that the other, the last remaining piece of food was close and the other robot would have to travel a long way, lose its energy and then uh, lose the whole competition. So there was like emergence of something like a theory of mind, knowing what the other robot would do, guided towards bad behavior in order to win. So we can get things like that happened uh, in simulation as well. </s>

<s>[INST] Let's just name comment. Okay. Let me ask just a few dumb questions. So first of all, what do we do with violence in terms of just natural emergence of violence in human societies? So the idea that anarchists proposes is that we would, as the community grows, there may be violence and then we together form collectives that sort of fund mechanisms that resist that violence. I mean, I'd love to sort of talk about violence because that seems to be the core thing that's the difference between the state that was definitionally, I guess, is the thing that has a monopoly on violence or controls violence in such a way that you don't have to worry about it. I don't know. [/INST] I'm just laughing because your definition is accurate, but the point is that being definition </s><s>[INST] of the state versus how states act in reality is just absurd. And then the idea that anarchism would be is that it's more kind of a market of defenses against violence. [/INST] So you have like security companies and then you hire different ones that are more competent. You have things being made affordable, you have more accessibility to security, you have accountability when people misuse their power, and you have more layers of security than having a government monopoly, but so every objectivist understand, and they don't deny this, this is something they talk about constantly, is, any time you have a government monopoly, it's going to have enormous distortions as a consequence. It's going to be expensive, it's going to be ineffective. And when you're talking about ineffectiveness in markets, that's not just the coup sucks. It often means mass death. It often means persecution. So this is something that anarchism, if not entirely prevents, certainly mitigates enormously. </s><s>[INST] So can I just, as a thought experiment, say it was very easy to immigrate to another country, like where you could just move about from government to government, would that alleviate most of the problems that you have towards the state, which is like people being free to choose which government they operate under? Wouldn't that essentially be- That's him, yeah. So like, I'm trying to understand why governments aren't already the thing that's the goal of anarchism, the kind of collectives that emerge under anarchism, [/INST] seems to do what government- You're equating two terms. So there's something called like private governance and there's government. So for example, if I go to Yaron's house and he has a rule, take off your shoes, come to your house, if you want to really be kind of silly about it, you could say he's the governor. It's really nonsensical to say that. If you go to Macy's, right? If you want to return your sweater, Macy's rules are right up there. You have seven days. If you don't have a receipt, you're going to get store credit. If you do have a receipt, you get a refund. So, every organization, every bar, every nightclub, your house has rules of governments. This is – It's often they're unspoken, this is unavoidable. No one in America by law has to pay a tip, but it's just customary. You go with the waiter, you give them 15%, 20%, so on and so forth. Now, what anarchism does is it says, okay, security is something that is of crucial, essential human need. We all need to be safe in our property, safe in our purpose. The organization that by far is the biggest violator of this, and always has been, always will be, is the government. Why? Because it's a monopoly, because it has no accountability. And look at the rioting last year, right? If you have one agency, pretend it's not the government, pretend it's Apple. And Apple has in charge of security in this town, people are rioting, people are looting, and Apple says, yeah, we're not going to send people into work. And if you try to defend yourself, we're going to put you in jail as well. That's the problem of having a government monopoly, and that's something that anarchism solves for. </s><s>[INST] But don't you, because you said no accountability. Don't you mean to say poor accountability? No, I mean to say no accountability. But isn't that the idea of democracies? Not for democracy. No, not for democracy, but like the system of governments that we have, there is a monopoly on violence, but there is, I mean, at least in the ideal, but I think in practice as well, there's accountability. I know you're a critic of the police force and all those kinds of things, but the military is accountable to the people. I do not agree. The police force is accountable to the people. Perhaps imperfectly, but you're saying not at all. [/INST] No, I mean to say no accountability. I do not agree. The police force is accountable to the people. I do not agree. But you're not at all. and we've seen many examples of police officers doing horrific things on video and they don't even lose their pension. But there's a lot of amazing police officers or not? I mean, no, there are not. </s><s>[INST] So you're saying by nature, police is like a fundamentally flawed system? [/INST] No, by nature, government monopoly on police is a fundamentally irredeemable system. We'll talk about private security. If I have a private security firm, you could have that under a government, and as a result of my private security, my person who I'm bodyguarding gets shot. That's going to be very bad for my company as compared to competing companies. However, when you have a government monopoly and I get people shot, what are you going to do? So the problem is that all the examples are going to be within the context of an existing government. This is why I said the cell phone example and all these other examples of us being here. We're not in anarchy. That is absurd. We're under a particular system of law and the system of laws applies and we know that the particular system of laws applies. So the problem is when you have... There are many laws that we're not going to be enforced. We know that. Violence related? We know that. Violence related? No, there are lots of laws that are not going to be enforced. Right? That doesn't make this anarchy because there are other laws out there that could be enforced, which makes an enormous... There are a number of issues here. It there's an issue of the role of force in in I got a clarifying because I think you misunderstood what I said I I'm not saying that America's anarchist what I'm saying is that three of us have an anarchist relationships between us because none of us have authority over the others That's what I'm saying. Yeah, but that is that's a bad use of the word anarchy. No, that's the correct use the word anarchy It makes a meaningless. It makes it every time any people get together there have an anarchistic relationship. Yes No, we have a voluntary relationship. That's what anarchism means no, it doesn't it's it's it's it's a political� you're taking a word and it's accepted usage and then you you're saying oh no maybe and we we never finished that discussion you're taking a word we're taking a word that you're defining as in replacing it with volatility now Okay, fine, I'm not for anarchists That's what anarchism means, mounteerism No, it doesn't. It's it's it'saa political system You want to get it? Fine, I'm not for anarchists for volunteerism But let's understand what volunteering means, right? So we, for example, go into stores, and there's a certain relationship that we have with the store that we engage in certain voluntary transactions with that store. Now, I believe that that works because there is a certain system of law that both the store and we have accepted that makes that possible. Now, if that didn't, there are certain people who would like to walk into the store and just take the stuff, right. So there is, not we might not but there's certain people who might want it to go into that store. There's a certain system of laws that regulates the relationship and that defines the property rights and then provides protection for the property rights. Now, you would like all that privatized that is the store would have its police force and that would be privatized. Now, I don't believe that force can be privatized. And there many reasons, I don't think it can. I don't think it can. I don't think it's an unstable equilibrium. I don't think competing police forces can work. At the end, the police force with the biggest gun always wins and always </s>

<s>[INST] So one uh question I have. It's a difficult one. so talk about love a lot and you've just talked about donald trump I guarantee you that this particular segment would be full of division from the internet but I believe that should be and can be fixed. What I'm referring to in particular is the division because we've talked about the value of reason and what I've noticed on the internet is the division. Mhm. Shuts down reason. So when people hear you say trump actually the first sentence you said about trump they'll hear trump and their ears will perk up and they'll immediately start in that first sentence they'll say is he a trump supporter or not [/INST] interested in anything else after </s><s>[INST] that. And after that that's it. And what how do so my question is you as one of the beacons of intellectualism. Quite honest. I mean it sounds silly to say, but you are a beacon of reason. How do we bring people together long enough to where we can reason? [/INST] I mean, there's no easy way out of this because the fact that people have become tribal and they have very tribal uh and in the tribe uh in the tribe reason doesn't matter. And it's all about emotion, it's all about belonging or not belonging and you don't want to stand out, you don't want to have a different opinion, you want to belong. And it's all about belonging. It took us decades to get back to tribalism where we were hundreds of years ago. It took millennium to get out of tribalism. It took the enlightenment to get us to the point of individualism where we think for any reason respectful reason before that we were all tribal. So it took the enlightenment to get us out of it. We've been in the enlightenment for about 250 years, influenced by the enlightenment and with and it's fading. The impact is fading. So what would we need to get out of it? We need self esteem. People join the tribe because they don't trust their own mind. People join a tribe because they're afraid to stand on their own two ft. They're afraid to think for themselves. They're afraid to be different, they're afraid to be unique. They're afraid to be an individual. People need self esteem to gain self esteem. They have to, they have to have respect for rationality, they have to think and they have to achieve and they have to recognize that achievement um to do that, they have to be, they have to have respect for thinking. They have to have to respect for a reason. Uh and we have to and and think about the schools, we have to have schools that teach people to think, teach people to value their mind. We have schools to teach people to feel and value their feelings. We have groups of six year olds sitting around a circle discussing politics, what they don't know anything, they're ignorant. See you don't know anything when you're ignorant. Yes, you can feel but your feelings are useless as decision making tools, but but we emphasize emotion, it's all about socialization and emotion. This is why they talk about this generation of snowflakes, They can't hear anything that that they're opposed to because they have not learned how to use their mind how to think. Um so it boils down to teaching people how to think two things, how to think and how to care about themselves. So it's it's thinking of self esteem and they're connected because when you think you achieve, which gains gains your self esteem when you have self esteem, it's easier to think for yourself. Yeah, and I don't know how you do that quickly. I mean, I think leadership matters. So, you know, part of what I try to do is try to encourage people to do those things. But I am a small voice. You asked me earlier on, you said we should talk about why I'm not more famous, I'm not famous that, you know, my following is not big, it's very small in in a in the in the in the scope of things, </s><s>[INST] but yours and objectivism. I'm not questioning you. Could you linger on it for a moment? Why isn't objectivism more famous? And [/INST] think because it's so challenging, it's not challenging to me, right? When I first encountered objectivism, it's like after the first shock, and after the first uh kind of none of this can be true. This is all Bs and fighting it. Once I got it, it was easy, it was easy. It requires years of studying, but it was easy in the sense of yes, this makes sense. But it's challenging because it upends everything. It really says what my mother taught me is wrong. And while my politicians say left and right is wrong, all of them, there's not a single politician on which I agree with on almost anything right, because on the fundamentals we disagree and what my teachers are telling me is wrong and what jesus said is wrong and </s><s>[INST] it's hard, but the thing is so you you talk about politics and all that kind of stuff, but you know, most people don't care. The more powerful thing about objectivism is the practical of my life of how I revolutionized my life. And that feels to me like a very important and appealing, you know, get your ship together. [/INST] Yeah, but this is why this is like Jordan Peterson is so much more successful than we are right to make your </s><s>[INST] bed or what does that make you better [/INST] because his personal responsibility shallow. It's make your bed stand up straight. What my mother told me when I was growing up, there's nothing new about Jordan Peterson, he says embraced Christianity, Christianity is fine, religion is okay, just do these few things and you'll be finding by the way he says happiness. You know, you either have it or you don't, you know, it's random, you don't actually, you can't bring about your own happiness. So it's giving people an easy out. People want easy out people by self help books that give them five principles for living in, you know, shallow. I'm telling them think Stand on your own two ft be independent. Don't listen to your mother, do your own thing, but thoughtfully not based on emotions. </s>

<s>[INST] why I want to know how that was discovered. But that's the kind of thing that machine learning can actually discover these things. [/INST] Maybe not. But but there is a hint perhaps that with machine learning we will train a system to basically be a physiological model of some complex emergent phenomenon which, you know, superconductivity is one of those uh where you know, I think that this collective phenomenon is too difficult to describe from first principles with the current, you know, the usual sort of, you know, reductionist type method. But we could have deep learning systems that predict the properties of the system from a description of it after being trained with sufficient uh many samples um um this guy pascal fua cpfl, it has a startup company um that where he basically trained a condition that essentially to predict the aerodynamic properties of solids. And you can generate as much as you want by just running competition. Free dynamics. Right? So you give okay wing airfoil or something shape of some kind and you run competition. Free dynamics you get as a result the drag and you know, lift and all that stuff. Right. And you can you can generate lots of data to train a neural net to make those predictions. And now what you have is a differentiable model of, let's say a dragon and lift as a function of the shape of that solid. And so you can do background in the sand, you can optimize the shape so you get the properties you want. </s><s>[INST] Um yeah, that's incredible. That's incredible. And on top of all that probably you should read a little bit of literature and a little bit of history for inspiration and for wisdom because after all, all of these technologies will have to work in the human world and the human world is complicated sadly. Yeah and this is um, an amazing conversation. I'm really honored that you talk with me today. Thank you for all the amazing work you're doing it fair at meta and thank you for being so passionate after all these years about everything that's going on, you're, you're a beacon of hope for the machine learning community and thank you so much for spending your valuable time with me today. That was awesome. [/INST] Thanks for having me on. That was, it was a pleasure. </s><s>[INST] Thanks for listening to this conversation with john Macoun to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Isaac Asimov, your assumptions are your windows on the world scrub them off every once in a while or the light won't come in. Thank you for listening and I hope to see you next time [/INST] </s>

<s>[INST] Yeah. Uh from an artificial intelligence perspective have a sense that there is like a deep loneliness in the world that all of us are really lonely. Like we don't even acknowledge it. Even people in happy relationships, it feels like there's like an iceberg of loneliness and all of us like seeking to be understood. I deeply understood understanding of like having somebody with whom you can have a deep interaction enough to where you can, they can help you to understand yourself and they also understand you. My God, I have a sense that artificial intelligence systems can provide that as well. But humans I think crave that from other humans in ways that we perhaps don't acknowledge and I have a hope that technology will enable that more and more like clubhouse is an example that allows that [/INST] are touring bots going to out compete clubhouse like why not pro sort of program your own session, you're just talking to your device and say here's the kind of conversation I want and it will create the characters for you. And it may not be as good as Ellen and Vladimir Putin, but it will be better than ordinary club has. </s><s>[INST] Yeah. And one of the things that's missing, it's not just conversation. It's it's memories. So long term memories what current Ai systems don't have is sharing an experience together. Forget the words, it's like sharing the highs and the lows of life together and the systems around us remembering that remembering we've been through that like that's the thing that creates really close relationships is going through some ship like go struggle if you've survived together, there's something really difficult that bonds you with other humans [/INST] and this is related to immigration and the american dream. In what way the people who have come to this country, however weird and different they may be, they or their ancestors at some point probably have shared this thing, write us is not going to split up. It may get more screwed up as a country by texas and California are not going to break off. Yeah, I mean they're big enough where they could do it but it's just never going to </s><s>[INST] happen. We've been through too much together. [/INST] Yeah. </s><s>[INST] Ah that's a hopeful message. Do you think you know some people have talked to eric Weinstein, you've talked to eric once and uh he has a sense that growth uh you know like the the entirety of the american system is based on the assumption that we're going to grow forever, that the economy is going to grow forever. Do you think uh economic growth will continue indefinitely or will we stagnate? [/INST] I've long been an agreement with eric Peter thiel robert Gordon? And others that growth has slowed down. I argue that in my book the great stagnation appropriately titled but the last two years I've become much more optimistic. I've seen a lot of breakthroughs in green energy and battery technology, m RNA vaccines and medicine is a big deal already. It will repair our GDP and save millions of lives around the world. There's an anti malaria vaccine that's now in stage three trial, it probably works CRISPR to defeat sickle cell anemia, this space area after area after area, there's suddenly the surge of breakthroughs, I would say many of them rooted in superior computation and ultimately moore's law and access to those computational abilities. So I'm much more optimistic than say the last time I spoke to erIC, I don't know he moves all the time in his views. I don't know where he's at </s><s>[INST] now, he's not, he hasn't gained. That's really interesting. So your little drop of optimism comes from here. Like there might be a fundamental shift in the kind of things that computation has unlocked for us in terms of like it could be a Wellspring of innovation that can, that enables growth for a long time ago. Like eric has not quite connected to the computation aspect yet, to where it could be a Wellspring of innovation, [/INST] but you're very close to it in your own work. I have to tell you that the work you're doing would not have been possible not very long ago. But </s><s>[INST] the question is, how much does that work enable continued growth for decades to come. [/INST] That's all their problems. Some version of driverless vehicles will be a thing, I'm not sure when you know, much better than I do. Maybe only partially, but that too will be a big deal. </s><s>[INST] Well, one of the open questions that sort of the peter thiel school uh area of ideas is how much can be converted to technology, How much, how many parts of our lives can technology integrated and innovate? Like can it replace healthcare, can replace the legal system, can replace government, not replace but like, you know, uh, make it digital and thereby enable computation to improve it. Right. That's the open question. Because many aspects of our lives are still not really that digital digitized. [/INST] There was a new york times symposium in april which is not long ago. And they asked the so called experts, when are we going to get vaccines? And the most optimistic answer was in four years and obviously we beat that by a long mile. So I think people still haven't woken up. You mentioned my tiny drop of optimism but it's a big drop of optimism. </s><s>[INST] Is it a waterfall yet? I mean, is it [/INST] just, well, here's my pessimism. Whenever there are major new technologies, they also tend to be used for violence directly or indirectly. Radio Hitler. Not that he hit people over the head with radios, but it enabled the rise of various dictators. So the new technologies now whatever. Exactly. They maybe they're going to cause a lot of trouble. And that's my pessimism. Not that I think they're all gonna slow to a trickle. </s>

<s>[INST] the following is a conversation with Greg brockman. He's the co founder and Cto of Open Ai, a world class research organization, developing ideas in Ai with a goal of eventually creating a safe and friendly artificial general intelligence, one that benefits and empowers humanity. Open AI is not only a source of publications, algorithms, tools and datasets. Their mission is a catalyst for an important public discourse about our future with both narrow and general intelligence systems. This conversation is part of the artificial intelligence podcast at M I T. And beyond. If you enjoy it, subscribe on youtube itunes or simply connect with me on twitter at lex Friedman spelled F R I D. And now here's my conversation with Greg brockman. So in high school and right after he wrote a draft of a chemistry textbook, saw that that covers everything from basic structure of the atom to quantum mechanics. So it's clear you have an intuition and a passion for both the the physical world with chemistry and now robotics to the digital world with ai deep learning, reinforcement learning so on. Do you see the physical world and the digital world is different? And what do you think is the gap [/INST] a lot of it actually boils down to iteration speed, right? That I think that a lot of what really motivates me is building things right, is the uh you know, think about mathematics for example, where you think really hard about a problem, You understand it, you're right down in this very obscure form they call it proof, but then this is in humanities library, right? It's there forever. This is some truth that we've discovered maybe only five people in your field will ever read it. But somehow you kind of move humanity forward. So I actually used to really think that I was going to be a mathematician. And uh, then I actually started writing this chemistry textbook. One of my friends told me you'll never publish it because you don't have a PhD. So instead I decided to build a website and try to promote my ideas that way. And then I discovered programming. And uh, you know that in programming you think hard about a problem, You understand it? You write down in a very obscure form that we call a program. But then once again, it's in humanity's library, right? And anyone can get the benefit from it. And the scalability is massive. And so I think that the thing that really appeals to me about the digital world is that you can have this, this, this insane leverage, right? A single individual with an idea is able to affect the entire planet. Um, and that's something I think is really hard to do if you're moving around physical atoms. </s><s>[INST] But you said mathematics. So if you look at the wet thing over here our mind, do you ultimately see it as just math is just information processing? Or is there some other magic as you've seen if you've seen through biology and chemistry and so on. [/INST] I think it's really interesting to think about humans is just information processing systems. And uh it seems like it's actually a pretty good way of describing a lot of kind of how the world works are a lot of what we're capable of to think that that again, if you just look at technological innovations over time, that in some ways the most transformative innovation that we've had, it has been the computer, right? In some ways the internet, you know that what is the internet done? Right? The internet is not about these physical cables, it's about the fact that I am suddenly able to instantly communicate with any other human on the planet. I'm able to retrieve any piece of knowledge that in some ways the human race has ever had. Uh and that those are these insane transformations. </s><s>[INST] Do you see the our society as a whole, the collective as another extension of the intelligence of the human being. So, if you look at the human being as an information processing system, you mentioned the internet, the networking. Do you see us all together as a civilization as a as a kind of intelligence system? [/INST] Yeah, I think this is actually a really interesting perspective to take in to think about you sort of have this collective intelligence of all of society. The economy itself is the superhuman machine that is optimizing something, right? And it's also in some ways a company has a will of its own right, that you have all these individuals who are all pursuing their own individual goals and thinking really hard and thinking about the right things to do. But somehow the company does something that is this emergent thing uh and that is a really useful abstraction. And so I think that in some ways, you know, we think of ourselves as the most intelligent things on the planet and the most powerful things on the planet, but there are things that are bigger than us, There are these systems that we all contribute to. Um and so I think actually, you know, it's a it's interesting to think about if you've read as a guy's moves foundation, right, that there's this concept of psycho history in there, which is effectively this, that if you have trillions or quadrillions of beings then maybe you can actually predict what that being that huge macro being will do uh and almost independent of what the individuals want. And I actually have a second angle on this I think is interesting which is thinking about technological determinism. One thing that I actually think a lot about with with open ai right is that we're kind of coming on onto this insanely transformational technology of general intelligence, right? That will happen at some point and there's a question of how can you take actions, they'll actually steer it to go better rather than worse. And that I think one question to ask is as a scientist, as an event, as a creator, what impact can you have in general, right? You look at things like the telephone invented by two people on the same day, like, what does that mean? What does that mean about the shape of innovation? And I think that what's going on is everyone's building on the shoulders of the same giants and so you can kind of you can't really hope to create something. No one else ever would, You know, if Einstein wasn't born, someone else would have come up with relativity, you changed the timeline a bit right? That maybe it would've taken another 20 years, but it wouldn't be that fundamentally, humanity would never discover these these fundamental truths. </s>

<s>[INST] Do you remember the early days, do you feel nostalgic when you think back to the ideas, the circumstances that led you down this path towards black holes, towards theoretical physics, towards the tools of physics, towards this really fascinating world of theoretical physics? [/INST] Well, I wouldn't add nostalgia to it because it's not like a, you know, a summer in Italy or something. It's like there's results that are there, that people are, and that's what's so gratifying, you know. I mean, of course one's name disappears from these things. </s><s>[INST] Unless you're Einstein or Newton or something, people are not gonna remember my name in 50 years. Well, most, basically every name will be forgotten in hundreds of years, yeah. Yeah. Are you able to, by the way, love the idea, the exploration of ideas themselves without the names, the recognition, the same? [/INST] Yeah, yeah, that's what I'm saying. So I have not, I hope someday, but I have not, you know, there are some experiments now to verify some of my predictions about, you know, properties of gravity and so on, but I have not, like, you know, most of what I've done is in the, you know, it could happen still. It's still a logical possibility that everything having to do with string theory and the, I mean, as we mentioned, I'm betting the farm that it's not, but it is indeed a logical possibility that people always say, can you believe Lex Fridtman interviewed Elon Musk and Kenya West and he interviewed Strominger who was on this, working on this theory that just completely went into the toilet, you know. </s><s>[INST] I'm gonna make, I'm gonna get, with a wife I don't have, I'm gonna make a public statement, she'll be on stage, I'll say, I'm really sorry, I made this giant mistake of platforming this wild-eyed physicist that believed for decades in the power of theoretical physics, yes. No, like you said. [/INST] So that could happen, it could happen, it could happen. It's in the, and of course, if that couldn't happen, it wouldn't be real exploration, right? Absolutely. And so, but I do take a lot of satisfaction that some of the things I discovered are at the minimum mathematical truths and they're still, so you don't have that sort of nostalgic feeling of it being something that was gone and I'm still making discoveries now that I'm as excited about, we'll see if they hold the test of time that, that stand the test of time that these other ones did, but that I'm as excited about as I was about those when I made them. I am easily excitable, as my friends will tell you. </s><s>[INST] Well, one interesting thing about you is- [/INST] And I have been very excited about things which turned out to be completely wrong, </s><s>[INST] you know? Well, the excitement is a precondition for breakthroughs. But you're also somebody, just like you said, you don't have a cynical view of the modern state of physics. No. So there's a lot of people that glorify like the early days of string theory and that, all these things are made in the 20s. Yeah, yeah, yeah. But you're saying like this to you might be one of, if not the most exciting times to be a theoretical physicist. Like when the alien civilizations 500 years from now that Visit Earth will look back, they'll think the 21st century, some of the biggest discoveries ever [/INST] were made in the 21st century. Yeah, I mean, when they have a measurement </s><s>[INST] of string theory, the fun's over. Then we have to go on to something new, you know? No, there's deep, there's going to be, the fun is over. Oh man. But there is an end to the Nile, right? Is there? Who told you? Some Weyberg guy. Let me ask you another trippy out there question. So again, perhaps unanswerable from a physics perspective, but do you wonder about alien civilizations? Do you wonder about other intelligent beings out there making up their own math and physics trying to figure out the world? [/INST] Do you think they're out there? They told you. It is hard to understand why there would, given that there's so many planets and of course there's Drake's formula and we don't exactly know what the, but I mean, I think Fermi's paradox that, you know, is a real paradox and I think there probably are and I think it's very exciting that, you know, we might, you know, find some, it's a logical possibility that we could learn about it, you know, we might, you know. </s><s>[INST] I mean, to me, it's super interesting to think about aliens from a perspective of physics, because any intelligent civilization is going to be contending with the ideas of trying to understand the world around it. So, I think that the universe is filled with alien civilizations. So they all have their physicists, right? They're all trying to understand the world around them and it's just interesting to me to imagine all these different perspectives, all these different [/INST] Einstein's. Like trying to make sense of like... Yeah, though they might be more different than we think. They might be different in a way that we haven't even thought of. They might be like smarter or different. Just different, something that we're not even able to describe now. We just haven't thought of that, you know? </s>

<s>[INST] not because you have to. Noticing and reclaiming the freedom that each of us have. That's what it means to be human. If you notice it, you're truly free, physically, mentally, psychologically. Manolis, you're an incredible human. We could talk for many more hours. We covered less than 10% of what we were planning to cover, but we have to run off now to the social gathering that we spoke of. We're 3D humans. We're 3D humans and reclaim the freedom. I think, I hope we can talk many, many more times. There's always a lot to talk about, but more importantly, you're just a human being with a big heart and a beautiful mind that people love hearing from. And I certainly consider it a huge honor to know you and to consider your friend. Thank you so much for talking today. Thank you so much for talking so many more times, and thank you for all the love behind the scenes [/INST] you send my ways, it always means the world. It always means the world. Lex, you are a truly, truly special human being. And I have to say that I'm honored to know you. So many friends are just in awe that you even exist. That you have the ability to do all the stuff that you're doing. And I think you're a gift to humanity. I love the mission that you're on to sort of share knowledge and insight and deep thought with so many special people who are transformative. But people across all walks of life, and I think you're doing this in just such a magnificent way, I wish you strength to continue doing that because it's a very special mission and it's a very draining mission. So thank you, both the human you and the robot you, the human you for showing all this love, and the robot you for doing it day after day after day. </s><s>[INST] So thank you, Lex. All right, let's go have some fun. Let's go. Thanks for listening to this conversation with Manolis Callis. To support this podcast, please check out our sponsors in the description. And now, let me leave you with some words from Bill Bryson. In his book, A Short History of Nearly Everything. If this book has a lesson, it is that we are awfully lucky to be here. And by we, I mean every living thing. To attain any kind of life in this universe of ours appears to be quite an achievement. As humans, we're doubly lucky, of course. We enjoy not only the privilege of existence, but also the singular ability to appreciate it, and even in a multitude of ways to make it better. [/INST] It is a talent we have only barely begun to grasp. </s><s>[INST] We have only, thank you for listening, and hope to see you next time. [/INST] </s>

<s>[INST] removed. Yes, but there's two things to say. I feel like you're right that history, I feel like the ripples that love leaves in history are less obvious detect are actually more transformational. Like [/INST] anyone can make a case about, I mean if you want to talk about the long term value of a jesus or Gandhi yes, those people's ripples are still affecting people today. I agree. </s><s>[INST] And that's you feel those ripples through the general improvement of the quality of life that we see and throughout the generations like you feel the ripples through the girl but I would even if that's not true not, I tend to believe that and by the way that the company that I'm working on is a competitor is exactly attacking this, which is a competitor to twitter, I think I can build a better twitter as a first step. [/INST] There's a long story in there. I think a three year old child could build and that this is not to denigrate, I'm sure yours will be better than, but twitter is so listen, facebook too, they're, they're really awful platforms for intellectual discussion and meaningful discussion, but when I'm on it, so let me just say I'm part of the problem, we're new </s><s>[INST] to this. So it's not, it wasn't obvious at the time how to do, it's now now a three year old can do. I tend to believe that we live in a time where the tools that people that are interested in providing love. Like the weapons of Love are much more powerful. So like the one nice thing about technology is that allows anyone to build a company that's more powerful than any government. So that could be very destructive. But it could be also very positive. And that's I tend to believe that somebody like Elon wants to do good for the world, Somebody like me and then you like me could have more power than anyone. Government two and by power, I mean the power to affect change, which is different from the [/INST] government and I don't mean to interrupt you but I'll forget my train of thought, you know what I mean? How do you deal with the fact that already governments who are afraid of this are walling off their own internet systems as a way to create firewalls simply to prevent you from doing what you're talking about. In other words, if you know there's an old line that if voting really changed anything, they'd never allow it. If if love through a modern day successor to twitter would really do what you wanted to do and this would destabilize governments. Do you think that governments would would take countermeasures to squash that love before it got too dangerous. There's several </s><s>[INST] answers. One first of all, I don't actually to push back on something you said earlier. I don't think love is as much of an enemy of the state As as one would think [/INST] different states have different views. </s><s>[INST] I I think the states want power and I don't always think that love is intention with power. Like I think and and and I think it's not just about love, it's about rationality is reason, it's empathy. All of those things. I don't necessarily think there always have to be by definition in conflict with each other. So that's one sense is I feel like basically you can trojan horse love into behind behind. Uh, but you have to be good at it. This is the thing is you have to be conscious of the way these states think so the fact that china bans certain services and so on, that means the companies weren't eloquent. Whoever the companies are, weren't actually good at infiltrating. Like I think isn't that a song like Love is a battlefield? I think [/INST] it's all a gap editorial. </s><s>[INST] Yeah. It's all a game and you have to be good at the game. And just like Ellen we said, you know, with Tesla and saving uh, the environment. I mean that's not just by getting on a stage and saying it's important to save the environment is by building a product that people can't help but love and then convincing Hollywood stars to love it. Like there's there's a game to be played. [/INST] Okay, so let me let me build on that because I think there's a way to see this. I think you're right. And so it has to do with a story about the 19 sixties, in the vast scheme of things. The 19 sixties looks like a revival of neo romantic ideas. Right? I had a buddy of mine several years, well, Two decades older than I was, who was in the 60s, went to the protest and all those kind of things, and we were talking about it and I was romanticizing it, and he said, don't romanticize, because let me tell you most of the people that went to those protests and did all those things, all they were, there was to meet girls and have a good time and, you know, it was it wasn't so but it became in vogue to have all in other words, let's talk about your empathy and love. You're never gonna, in my opinion, grab that great mass of people that are only in it for them, they're interested in whatever. But if meeting girls for a young teenage guy requires you to feign empathy, requires you to read deeper subjects because that's what people are into. You can almost as a silly way to be trendy, you can make maybe empathy trendy love trendy solutions that are the opposite of that. Um the kind of things that people inherently will not put up with, in other words, the possibility exists to change the zeitgeist and reoriented in a way that even if most of the people aren't serious about it. the results are the same. Does that make sense? Absolutely. Okay, so we found a meeting of the month. </s>

<s>[INST] That's really, really, really important to think about when we make a scarecrow because that gives you actionable like it it forces you to introspect about people in your own life or leaders in your life today, once you admire they're charismatic, they're friendly, they love kids, They talk about enlightenment, you have to kind of think, alright, am I being duped on certain things? You have to kinda have a I mean that's the problem with Jeffrey Epstein, that people don't seem to talk about, I don't I never met the guy, but just given the people he talked to whom I know, it feels like he must have been charismatic, Like people think about like, oh it's because of the women, is because of the money. Uh I don't the people I know, I don't think they're going to be influenced, ultimately, it has to be how you are in the room and make it exactly like you said the enlightenment, I think that excites the scientists of course, as a charismatic person, you have to know what to pick in terms of what excites you. But that that is also a fascinating thing to me about Hitler is all of these meetings, even like with chamberlain inside rooms, whether he was screaming or whatever he was saying, it seems like he was very convincing. There must have been passion in his eyes, there must have been charisma, that one on one in a quiet conversation, he was convincing. [/INST] Yes, there's a famous story about Goebbels who would do a party trick, Where for 15 minutes for 15 minutes he would rouse the crowd to communism, Workers of the world unite Then for 15 minutes he would rouse the world to capitalism and individuals. And then for 15 minutes he would rouse the world to nazism. And apparently he was quite convincing in each of those performances. </s><s>[INST] Well, all those ideologies are pretty powerful. I mean, they and I think it's not even the reason that matters as much as the power of the dream of the vision of the enlightenment. I mean, the vision of communism is Fascinatingly powerful. Like workers unite the common people, stand together, the overthrow, the powerful, the greedy and yet share the the outcomes of our hard work. [/INST] Yeah, well, it's kind of like the fan of the story of 2/3 of the things that Marx calls for in the communist manifesto are already just part of the the liberal state. And so the parts we remember or forget about an ideology are very revealing. </s><s>[INST] If we can just linger on this a little bit longer, What have you learned From this period of the 19 30s about the scientific process. So, one of the labels you can put on your [/INST] work, </s><s>[INST] I knew it was a scholar and a philosopher of science and you also talk about nazi Germany as a singular moment in time or like a rebirth of the integration between ideology and science. So like um, in terms of valueless science, I think is the term [/INST] value free </s><s>[INST] value free science, uh, that you use. I mean, it seems like Nazi Germany is a important moment in history. I mean, it probably goes up and down what what um, difficult truths have you learned about the scientific process and what hopeful things have you learned about the scientific process? [/INST] Well, I guess the saddening thing is how easily people can become part of a machine, if there's power, people can be found to follow it. You know, One of the things I work on is is big tobacco and will probably come to that. But uh, it's amazing to me how easily people are willing to work for big tobacco. It's amazing to me how many scientists and physicians who were willing to work for the Nazi regime for multiple reasons, partly because a lot of them really thought they were, you know, doing the Lord's work, they thought they were cleaning the world of filth. You know, I mean, if you really thought, you know, jews are a parasitic race, you know, why wouldn't you, you know, get rid of them? So there's an ontology, there's, there's a theory of the world that they're building on. And interestingly one that was um, also present in the United States. And one of the things I did find out in my earliest research was that the nazis had looked lovingly and enviously over at the United States in terms of racial segregation racial separation and saw themselves in a kind of competition to become the world's racial leader as the, as the most purified racial form and that this required this kind of cleansing process and the cleansing mint. Getting rid of the physically handicapped. It meant getting rid of racial inferiors as they imagine them. It meant getting rid of cancer causing chemicals in the air and in our food and our water. These were all of a piece. There's a famous illustration that Richard Doll talks about the great great cancer theorists of of of studying in Nazi Germany in the 19 thirties and he's shown a lecture where cancer cells are shown as jews and X rays are shown as stormtroopers and these Stormtroopers are killing the cancer cells who are also jews. And so there's this metaphorical work of cleaning extermination, sanitation </s><s>[INST] purification of the sort [/INST] purification. There is definitely a kind of purity quest and you see that at multiple levels. And so you see how easy it is for people to fall into that given a particular theory. And again, coming back to that earlier sort of point about the scarecrow, which I think is very important. Ah if we imagine that nothing like this went on here in the United States, that would be a big mistake. The Nazis are looking to the save the Redwoods league, to their uh you know, to the Aryan supremacist to the ku Klux Klan, to the, to the separation of blacks and whites. Blacks were not allowed to join the american medical association until after World War Two. So you have racial segregation. You have massive sterilization in the United States way before the Nazis. One of the first things the Nazis do from a racial hygiene point of view is start sterilizing what they called the mentally ill and the physically handicapped all that had been going on since around world War in the United States and even earlier in certain states in the form of castration of of prisoners in order to prevent their demon seed from being propagated further into the race. So there's a kind of a racial international Nalle that's going on. And that part of the story also needs to be told </s>

<s>[INST] justice is a kind of drug. So if you look at history, that's also been reading a lot about Stalin. I mean all those folks really, I don't know, I don't know what was inside Hitler's head actually that he's a tricky one because I think he was legitimately insane. Stalin was not. And Stalin was like, he literally thought he's doing a good thing. He literally thought for the entirety of the time that communism is going to bring like that's the utopia and is going to create a happy world and in his there in his mind were ideas of justice, of fairness, of happiness, of of uh yeah, human flourishing and that's that's a drug and it's somehow sadly pollutes the mind when you start thinking like that. What's good for society and believing that you have a good sense of what's good for society that's intoxicating, especially when others around you are feeling the same way and then you start like building up this movement and you forget that you were just like a you're like barely recently evolved from an ape like you don't know what the hell you're doing and then you start like killing witches or whatever that you start [/INST] you start doing the math, let's be honest though, I mean sometimes you gotta, which has to go, </s><s>[INST] yeah, we can all agree that which Which has to go if it floats or sinks, which one [/INST] forget which everyone we needed the time on its floating. It should have </s><s>[INST] sunk. Uh Yeah, but yeah, we can definitely agree that we just have to go because you brought it up. I tweeted recently but also just I'm, one of the things I'm really ashamed of in my life is I haven't really read almost any of the sci fi classics. Yeah, so like I my whole journey through reading was through like the literary philosophies that would say like camus has a dostoyevsky, Kafka, like that place like that's the kind of sci fi world in itself. But it's, it's just, it creates a world in which the, the deepest questions about human nature can be explored. I didn't realize this, but the sci fi world is the same. It just puts it in a, it like removes it from any kind of historical context where you can explore those same ideas in like space somewhere else where in a different time and different place, it allows you almost like more freedom to like construct these artificial things where you can just do crazy, crazy kind of human experiments. So I'm now working through it. Uh the books on my list are the foundation series by as a Kasimov Dune ah Snow crash behind you Stevenson and and there's game like you mentioned. Uh that's just kind of and then so I posted that and then of course, like Elon musk john uh Car Mac, I don't know if, you know, I'm creator of Doom and quake. So they all pitched in these nerds, These alter nerds just started like [/INST] going like </s><s>[INST] these uh, you need to read this, that and the other. So I've like started working out okay. But it seems like the list I've mentioned holds up somewhat. Is there a book, is there sci fi books or series or authors that, that you find are just amazing. Maybe another way to ask that is like, what's the greatest sci [/INST] fi book of all time. Well, I, I'd like to start by sharing something that I'm embarrassed about is that I haven't read anything other than uh you know, Orson scott card, J. R. Tolkien frank Herbert talking about. Yeah. Uh yeah, I'm aware through Wikipedia and through through surface reading of things that like a book called The Republic was written once. Um, there were some other mother, </s><s>[INST] you're a prolific reader of Wikipedia articles or [/INST] occasional. Okay, exactly. In between whatever else it is that I waste my time on. But yeah, so I also, I should say I </s><s>[INST] posted on Reddit questions for uh Ryan Hall and there's like a million questions, but like half of them have to do with Dune? No, not really. But like people bring up, do I don't understand why did you mention doing [/INST] before? Well actually actually have to show your role Actually made a g. Dune themed G one time, which I thought was kind of cool, I'll send you I'll give you one, we got extra. But actually to your to your point, actually, this is Orson scott card quote. Actually, the writer of Ender's Game um fiction, because it's not about somebody who actually lived in the real world always has the possibility of being about oneself. And I think that's a neat thing because I have heard, you know, other people whom I respect and very sharp people actually, every now and then dig their heels and going, I don't like fiction only like nonfiction, it's more it's more instructive. And I would go, I completely disagree with that. I think we have a hard enough time figuring out what happened at 7, 11, 3 hours ago that Let me tell you what happened 600 years. BC I'm like, Hey, I'm interested, but don't tell me this isn't a story too. There's there's there's actually there's factual components I have no doubt, but we struggle sometimes to like, I guess what I like about fiction is that you can tell me a story, it's all about people. I mean every night there's more and less believable things. Um and I think Dune would be an unbelievably well written in my opinion for it, you know, what do I know, but I really like doing, I'll say that um, well written example of, you know, human beings interacting with one another, the political component to that, the emotional, the intellectual, um, the relationship components to all of that. And uh, I I think that Dune is neat because it's a sci fi novel, but only in the only in the loosest sense. It's really a story about religion, about group dynamics, about human potential, about belief, learning, politics, governance, ecology. It's uh, the best stories remind me of history the same way history hopefully is not just a list of facts that I try to be able to recall or factoids that I try to recall, but a story that I can understand and see how, how the threads of time kind of came together and created certain things. And a lot of times like we said, like how the heck is what's going on right now or 100 years from now, 100 years in the past happened. And you can look back far enough if we had accurate knowledge if we had that like that hypothetical perfect pool shot, you know, at the beginning of time we would see an unbroken chain of events that led us to where we are and where we are. Well potentially lead us to where we're going, which is again why hindsight self, but I think it's neat, like I guess I really enjoy for instance, a book like Dune and they're actually making a movie out of it, which I'm, I'm skeptical of to be honest because it's going to be difficult to, to bring that to the screen for a variety of reasons. But when there's at </s>

<s>[INST] Yeah, like especially like your approach, I've taken a really hard problem stepping right in and then being super skeptical about being able to solve the problem? I mean there's a balance of both, right? There's a silly optimism and a critical uh sort of skepticism that's good to balance, which is why it's good to have a team of people. Exactly, that's that balance [/INST] That you don't do that on your own. You have both mentors that have seen or you obviously want to chat and discuss whether it's the right time. I mean demi's came in 2014 and he said maybe in a bit we'll do starcraft and maybe he knew and that's and I'm just following his lead, which is great because he's brilliant. Right? So these things are obviously quite important that you want to be surrounded by people who, you know, are diverse, They have their knowledge. There's also important too. I mean I've I've learned a lot from people who actually have an idea that I might not think it's good, but if I give them the space to try it, I've been proven wrong many many times as well. So that's that's great. I think it's um your colleagues are more important than yourself. I think so. </s><s>[INST] True. Now let's real quick talk about another impossible problem A. G. I right, what do you think it takes to build a system that's human level intelligence. We talked a little bit about the touring test stock after all these have echoes of general intelligence, but if you think about just something that you would sit back and say, wow, this is really something that resembles human level intelligence, what do you think it takes to build up? [/INST] So I find that G I oftentimes is maybe not very well defined. So what I'm trying to then come up with for myself is what would be a result look like that. You would start to believe that you would have agents or neural nets that no longer sort of over feet to a single task, right? But actually kind of learn the skill of learning, so to speak. And that actually is a field that I am fascinated by which is the learning to learn or meta learning, which is about no longer learning about a single domain. So you can think about the learning algorithm itself is general, right? So the same formula we applied for Alpha Star or Star craft, we can now apply to kind of almost any video game or you could apply to many other problems and domains. But the algorithm is what's kind of generalizing. But the neural network, the weights, those weights are useless even to play another race. Right? I train a network to play very well at protest versus protest. I need to throw away those weights. If I want to play now tearing versus terran, I would need to retrain a network from scratch with the same algorithm that's beautiful. But the network itself will not be useful. So I think when I if I see an approach that can absorb or start solving new problems without the need to kind of restart the process. I think that to me would be a nice way to define some form of A G. I again, I don't know the grandiose like age. I mean should during this bizarre before A G. I mean I don't know, I think, I think concretely I would like to see clearly that meta learning happen meaning there there is an architecture or network that as it sees new new problem or new data, it solves it and to make it kind of a benchmark, it should solve it at the same speed that we do solve new problems when I define your new object and you have to recognize it. When I when you start playing a new game, you played all the games, but now you play a new Atari game. Well you're going to be pretty quickly pretty good at the game. So that's perhaps what's the domain and what's the exact benchmark is a bit difficult. I think as a community, we might need to do some work to define it. But I think this first step, I could see it happen relatively soon, but then the whole what A G. I means and so on. I am a bit more confused about what I think people mean different </s><s>[INST] things. There's an emotional psychological level uh that like even the touring tests passing the turing test is something that we just passed judgment on as human beings, what it means to be, you know, is a is a dog. Uh as an A G. I. System, like what level what does it mean? Uh what does it mean? But I like the generalization and maybe as a community would converge towards a group of domains that are sufficiently far away, that would be really damn impressive if also able to generalize. So perhaps not as close as protests in Zurich, it was like we [/INST] could step, </s><s>[INST] It would be a good step and then a really good step. But then then like from Starcraft two Wikipedia back, that kind of [/INST] thing and that that feels also quite hard and far. But I think there's as long as you put the benchmark out as we discovered for instance with Image Net, then tremendous progress can be had. So I think maybe there's a lack of benchmark but I'm sure we'll find one and the community will will then work towards that. Um And then beyond what A G. I might mean or would imply, I really am hopeful to see basically machine learning or ai just scaling up and helping, you know, people that might not have the resources to hire an assistant or that they might not even know what the weather is like. But you know, so so I think there's in terms of the impact, the positive impact of a. I think that's maybe what we should also not lose focus. Right? The research community building A G. I mean, that's a real nice goal. But um, and I think the way that Deepmind puts it is and then use it to solve everything else. Right? So I think we should paralyze. </s>

<s>[INST] So, you think quantum mechanics is the bottom of the well, is is the [/INST] uh here I think is here I think is where you have to be humble, here's where humility comes. I don't think anybody should say anything is at the bottom of the well at this time as I think we I think we can reasonably say, I can reasonably say when I look into the well, I can't see past quantum mechanics. I don't see any reason for that to be anything beyond quantum mechanics. I think a tough disasters. Very interesting in deep questions. I don't like his answers. </s><s>[INST] Well, again, let me ask if we look at the deepest nature of reality with whether it's deterministic or when observed as probabilistic? What does that mean for our human level of ideas of free will. Is there any connection whatsoever from this perception? Perhaps illusion of free will that we have and the fundamental nature of reality. [/INST] The only thing I can say is I am I am puzzled by that as much as you are, </s><s>[INST] the illusion of it. The illusion [/INST] of consciousness, the illusion of free will. The illusion of self </s><s>[INST] uh does that connect to? [/INST] How can a physical system do that? And uh and I am as puzzled as anybody. </s><s>[INST] There's echoes of it in the observer effect? Yeah. So do you understand what it means to be an observer? [/INST] I understand it at a technical level. An observer is a system with enough degrees of freedom that it can record information and which can become entangled with the thing that is measuring. Entanglement is the key when a system which we call an apparatus or an observer, same thing interacts with the system that is observing, it doesn't just look at it, it becomes physically entangled of it. And it's that entanglement which we call an observation or measurement now, does that satisfy me personally, as an observer? Yes and no. I find it very satisfying that we have a mathematical representation of what it means. The observer system, </s><s>[INST] you are observing stuff right now. The conscious level you think there's echoes of that kind of entanglement in our macro scale. [/INST] Yes, Absolutely. For sure. We're entangled with quantum mechanically entangled with everything in this room. If we weren't and it was just well we wouldn't be observing it. But on the other hand, you can ask do I really am I really comfortable with it and I'm uncomfortable with it in the same way that I can never get comfortable with five dimensions. My my brain isn't wired for it. </s><s>[INST] Are you comfortable with four dimensions [/INST] a little bit more? Because I can always imagine the fourth dimension is time. </s><s>[INST] So the arrow of time, Are you comfortable with that arrow? Do you think time is an emergent phenomenon or is it fundamental to nature? [/INST] That is a big question in physics right now. All the physics that we do or at least that the people that I am comfortable with talking to, my my friends, my friends. Well, we all asked the same question that you just asked space, we have a pretty good idea is emergent and it emerges out of entanglement and other uh other things. Time always seems to be built into our equations as just what Newton pretty much would have thought Newton modified a little bit by Einstein would have called time and and mostly in our equations, it is not emergent. Time in physics is completely symmetric forward and mathematic. </s><s>[INST] So, so you don't really need to think about the era of time for most physical phenomenon. [/INST] Most microscopic phenomena. No, it's only when the phenomena involves systems which are big enough for thermodynamics to become important for entropy to become important for small, small system. Entropy is not a good concept. Entropy is something which which emerges out of large numbers? It's a probabilistic idea. It's a statistical idea and it's a thermodynamic idea. Thermodynamics requires lots and lots and lots of little sub structures. Okay, So it's not until you emerge at the thermodynamic level that there's an arrow of time. Do we understand it? Yeah. I think I think we understand better than most people think they are. Most people say that. I think we understand it. Yeah, I think we understand it. It's a statistical idea. </s><s>[INST] The you mean like second law of thermodynamics, entropy and so on. The [/INST] fact of cards and you're flying in the air and you look what happens to it. It's random. We understand doesn't it doesn't go from random. The simple, it goes from simple to random. </s><s>[INST] But do you think it ever breaks down? [/INST] What I think you can do is in a laboratory setting, you can take a system which is somewhere intermediate between being small and being large uh and make it go backward. A thing which looks like it only wants to go forward because of statistical mechanical reasons. Because of the second law. You can very, very carefully manipulate it to make it run backward. I don't think you can take an egg humpty dumpty who fell on the floor and reverse that. But you can in a very controlled situation. You can take systems which appear to be evolving statistically toward randomness? Stop them reverse them and make them go back. </s><s>[INST] What's the intuition behind that? How do, how do we do that? How do we reverse it? You're saying a closed system? [/INST] Yeah, pretty much closed system. Yes. </s><s>[INST] Did you just say that time travel is possible? [/INST] No, I didn't say time travel is possible. I said you can make a system go backward in time and you can make it go bad. You can make it reverse it steps, you can make it reverse its trajectory. Yeah. </s>

<s>[INST] but sometimes it's not reversible. Like I've done this with video games once you figure out the cheat code or like you look up how to cheat old school like single player. It ruins the game for you. [/INST] Absolutely. I know that feeling. But again, that just means our brain manipulation technology is not good enough yet remove that cheat code from your brain. </s><s>[INST] But what if we so it's also possible that if we figure out immortality, that all of us will kill ourselves before we advance far enough to uh to be able to revert the change. I'm [/INST] not killing myself till I know everything. </s><s>[INST] So that's what you say. No, because your life is finite. [/INST] You know, I think, yes, self modifying systems gets comes up with all these hairy complexities. And can I promise that I'll do it perfectly. No, but I think I can put good safety structures in place. Yeah. </s><s>[INST] So that talk and you're thinking here is not literally referring to uh a simulation and that are our universe is a kind of computer program running in a computer that's more of a thought experiment. Um Do you also think of the potential of the sort of bossed rem musk and others that talk about an actual program that simulates our universe? Oh, [/INST] I don't doubt that we're in a simulation. I just think that it's not quite that important. I mean, I'm interested only in simulation theory as far as like it gives me power over nature. Uh, if it's totally unfalsifiable, then who cares? </s><s>[INST] I mean, what do you think that experiment looks like? Like somebody uh on twitter asked ask George what signs we would look for to know whether or not we're in a simulation, which is exactly what you're asking is like the step that precedes the step of knowing how to get more power from this knowledge is to get an indication that there's some power to be gained. So get an indication that there you can discover and exploit cracks in the simulation or doesn't, you know, in the physics of the universe [/INST] Show me. I mean, like a memory leak could be cool. Some scribe buying technology, you know what kind of technology scribe eyeing? What's that? That's a weird uh, this crying is the, is the paranormal ability to uh like like remote viewing, Like being able to see somewhere where you're not. Um so, you know, I don't think you can do it by chanting in a room, but um if we could find as a memory leak, basically, </s><s>[INST] I'm really yeah, you're able to access parts, you're not supposed to Yeah, yeah, yeah, and thereby discover shortcut Yeah, [/INST] maybe a memory leak means the other thing as well, but I mean like yeah, like an ability to read arbitrary memory, right? Um and that was not that horrifying the right ones, start to be horrifying </s><s>[INST] read, right? So that's the reading is not the problem, [/INST] it's like hard for the for the universe, </s><s>[INST] boy, the writing is a big, big problem, it's a big problem, it's the moment you can write anything, even if it's just random noise, That's terrifying. [/INST] I mean, even without, even without that, like even some of the, you know, the nanotech stuff that's coming, I think, </s><s>[INST] I don't know if you're paying attention, but actually eric Weinstein came out with the theory of everything, I mean, that came out, he's been working on a theory of everything in the physics world called geometric unity. And then for me, from a computer science person, like you Stephen Wolfram theory of everything of like hyper graphs super interesting and beautiful, but not from a physics perspective, but from a computational perspective, I don't know, have you paid attention to any of that? [/INST] So again, like what would make me pay attention and like why? Like, I hate string theory is okay, make a testable prediction, right? I'm only interested in, I'm not interested in theories for their intrinsic beauty. I'm interested in theories that give me power over the universe. So if these theories do, I'm very interested, </s><s>[INST] um can I just say how beautiful that is? Because a lot of physicists say I'm interested in experimental validation and they skip out the part where they say to give me more power in the universe. I just love the uh [/INST] you know, I want I want, I want the clarity of that, I want 100 gigahertz processors, I want transistors that are smaller than atoms, I want like </s><s>[INST] power. That's uh that's true. And that's where people from aliens to this kind of technology, where people are worried that governments like who owns that power, Is it George hearts? Is that thousands of distributed hackers across the world? Is that governments, you know, is it Mark Zuckerberg? There's a lot of people that uh I don't know if anyone trust any one individual with power. So they're always worried [/INST] the beauty of block chains. </s><s>[INST] That's the beauty of block chains, which we'll talk about on twitter. Somebody pointed me to a story uh a bunch of people pointed me to a story a few months ago where you went into a restaurant in new york, you can correct me famous is wrong and ran into a bunch of folks from a company in the crypto company who are trying to scale up ethereum and they had a technical deadline related to a solidity to oh, VM compiler. So these are all ethereum technologies. So you stepped in, they recognized you uh pulled you aside, explain their problem and you stepped in and helped them solve the problem, uh thereby creating legend status story. Uh you uh tell me the story a little more detail. It seems kind of incredible. Did this happen? Yeah, [/INST] yeah, it's a two story. It's a true story. I mean they wrote a very flattering account of it. Um they so, optimism is the company called Optimism spinoff of plasma. They're trying to build L two solutions on ethereum. So right now, uh every ethereum node has to run every transaction on the ethereum network. Um and this kind of doesn't scale, right? Because if you have any computers, well, you know, if that becomes too end computers, you actually still get the same amount of compute right? This is, this is like like oh, of one scaling, um because they will have to run it. Okay, fine, you get more Blockchain security, but like the Blockchain is already so secure. Can we trade some of that off speed? Uh so that's kind of what these two solutions, are they built this thing, which kind of um kind of sandbox for ethereum contracts, so they can run it in this L two world and it can't do certain things in our world, in L one </s>

<s>[INST] forth, charismatic. [/INST] Well it depends who would call, what do you call charismatic, the long beard, it was kind of a man in turbine and the gown, which was a very unusual leadership for people who were much more accustomed to the civilian clothing or to the equipments of the shows, military uniforms that he used to wear. </s><s>[INST] But I also mean like he is a man that was able to take power to become popular, sufficiently popular. So like I would like is it the ideas, is it an accident or is it the man himself, the charisma or something about the man that led to this particular person, basically changing the tide of history in this part of the world in a way that unexpected, [/INST] all the above that you mentioned </s><s>[INST] Or was it just the beard? [/INST] No, I think that it's beyond the appearance appearance is greatly helped. As you know, you </s><s>[INST] Know, in the 20th century, appearance is helpful. Pictures for propaganda, for messaging. [/INST] That's an important factor. And he was a kind of adamant and very severe in his own positions. He could appear very uncompromising and he had this sense of confidence, self confidence that literally everybody else lacked. And he was a man of opportunity. As soon as you would see that a chance an opportunity would open up, he would jump on it and that's what he did basically. As more the political space opened, the weaknesses of the Shah's government became more evident. His indecision became more evident. His lack of confidence became more evident. Khomeini managed to move further into the center of the movement because he was the only authority that had this network of support through the mosques, through the people who paid homage to him who followed him. Because there's a sense of following of the religious leader in chiesa. You are a follower of this authority, follower of that authority. And he's basically created an environment in which people looked upon him as a kind of a Messianic figure that came to save Iran from what they considered at the time the problems of uh dictatorship under the shore. </s><s>[INST] So there's not a suspicion about Islamic law being the primary law of the land. [/INST] Not at all. People had very little sense that what Islamic law is all about because the secular education has left that into the old religious schools. This is not something that ordinary educated Iranian who goes to the universities is going to learn. Therefore, there is a sense of idealization that there's something great there that is going and there were quite a number of intellectuals who also viewed this kind of an idea of they would refer to as this toxic ation. That is this civilization of the West that has brought with it all. The modernity that we see around ourselves has enormous sinister features into it. And it has taken away from us our authenticity. That was the thing that there is something authentic that should be protected and therefore a man. And that's kind of garb and appearance seemed as a source for return to this originality of their own culture, authenticity of their own culture. And it perfectly Uh took advantage of that. That is Khomeini took advantage of it and the circular round, it at the expense of everybody else, which he managed in the course of 1979-1989, which he passed, died in the 10 years during this period, managed to basically transform the Iranian society uh to create institutions of the Islamic republic and to acquire himself the position of the guardian jurists. That was something completely new didn't ever existed before. As a matter of fact, as you might know, the model of government that a religious establishment takes over the States is unprecedented throughout the course of Iranian history. Throughout the course of the Islamic history, I would say this is the first example and probably the only example of a of a regime That religious establishment that has always in the course of Iranian history ever, since I would say probably at the 16th century, if not earlier, has been always separate from this state and always kind of collaborating with this state in a with a certain tensions in between the two of them, there were two, basically, as they would call themselves, the two pillars of stability in the society. That situation changed for the first time, the religious establishment took over the power of the State. And that's at the core of what we see today as a major issue for Iranian society because these are basically that old balance between the religion and the state, which was kind of the factor uh separation of the authorities of the two has been violated. And now you have in power theo theocracy in effect, which of course only in the on the on in its appearances, theocracy deep down, it's a in my opinion, is a brutal advises regime that it stays in power, but it has the appearance of religion into it. So, this is really the story of the revolution And as a result of that, the Iranian middle class has greatly suffered. It's not without a reason that you see four million Iranians abroad because basically the emergence of this new power gradually isolated or marginalized, the secular middle class who could not survive under that regime and gradually moved out Uh in the course of perhaps 30, 40 years up to now, Iran has the largest, I think I'm right to say so has the largest brain drain in any country in the </s><s>[INST] world to [/INST] its population. </s>

<s>[INST] don't think of yourself as big, [/INST] not big, I mean </s><s>[INST] fat. Oh [/INST] they should stay off the mountain. Why </s><s>[INST] is that [/INST] mobility? It's like, it's, I think that, you know, you don't see any, you know, like there was a few ways like 100 and 60 kg, like you know, £2 I don't know, £270 of a lot of fat, it's, you need a bit of mobility and that would, you would play against you even even back </s><s>[INST] back the same requires mobility. Okay, so even though it doesn't look like you're moving very much when you're doing that requires mobility because you have to reposition and weight [/INST] redistribution </s><s>[INST] alright, the legend goes, you got very good bye training mostly with lower ranks. What was your training like in that environment? [/INST] So when I first moved to London, I was 20 years old, I opened my school there and I had nobody to train with, I had one guy that was teaching with me a black belt middleweight, it was good and thats it bravo was moved to the same, they said he moved to England the same time as I did, but he was in Birmingham. So we did go together, you know, maybe twice a week closer, you know, when we were prepared for something, if not then not very often as often as we could, but did I say not that often and I had just called about students, there was no one high level, there was no one world champion in any belt to train, then you need to create a scenario that simulates that can simulate, you know, like a realistic fighting. So I think on that aspect, you know, when people said, you know, people ask why they have such a basic game, I think that also influence me, sharpen up all my skills when I moved there because you know, when I'm when if you practice with people you know lower level than you, you cannot, there's nothing to learn from them or you know, you can learn things in practice with them, but I would say very complex things on them, it is not the best. So it's I sharpen up all my skills so you know that when I really improved everything that I already knew to a higher </s><s>[INST] level, but how can you sharpen something if the resistance is much lower level than [/INST] a purple belt, makes it very hard for you to escape side control doesn't have to be a war chamber black belt, it's you know, if it's one is holding you, it can be very hard. </s><s>[INST] What about on the attack? How do you, how do you become literally by far the best person at the cross choke from mount by training with purple belts. [/INST] It's sometimes defense way better than black belts. </s><s>[INST] Okay, see a lot of people listening to that would be like that makes no sense. Hydro gracie, how does that make any sense? [/INST] Because like a lot of the black belts, even world champion they get to the black belt? They're really good in what in what they do in the guard, you know on top or the bottom position. But their differences are not like very very few people high level have a very good difference because you don't practice. Then that goes back to how you train. You know you can be very tough, very tough, You make a terrible defense because you're not going to practice your weakness so your weakness still gonna be terrible. You can have the best guard in the world, impossible to pass the day. People pass your guard, you're nothing like it's your your guard is high the highest level but your side control difference or not your amount difference are not. So some purple bells, they practice this, you know the amount way more than that black belt did. So naturally the difference is better. </s><s>[INST] So they get to experience the defensive position much much much more. And especially training with you, they get really good at defending and then [/INST] over and over again you attacked them with the same thing over and over again and didn't know what's coming. They will block, they will develop a defense over that. Yeah, way better than most other high level black belts. So </s><s>[INST] both put yourself into really bad positions with low ranks and just keep attacking the same way over and over and over. Yeah and with that you're able to be at the top of the world at the World Championships, [/INST] I </s><s>[INST] mean, can you give some, what was the preparation like to a World championship with lower ranks? I mean, [/INST] I did a lot of boxing, a lot of conditioning. No, but </s><s>[INST] the conditioning isn't [/INST] condition, but the one thing that helped me extremely living in England in London was training judo in London. That helped me massively because it gave me the motivation to learn something new because you know that by the end of the, you know, the stand up was I'm sure today it is two, but by them was even higher than it is today. Like there was some very high level judo guys training there and I mean the first time I went there, my stand up was terrible compared to this, I mean it was it was bad but compared to them was terrible. So I was getting through like a child and that motivated me to keep to keep coming back and and and get better. So that made my so much stronger. I became my base got better. My top game improved my pressure game improved. </s><s>[INST] Did does neal Adams train [/INST] Ray stevens when I've never met, </s><s>[INST] is that he's the voice of judo. You watched the term. He's incredible. [/INST] Ray stevens sees the silver medal and silver medalist in the olympics. He wants european and he won a lot. So </s>

<s>[INST] never been to Burning man. So I don't know how secretive it is that I mean because quite high profile folks go, [/INST] yeah, everyone knows Elon musk goes there, isn't </s><s>[INST] it pretty open [/INST] on a boat? You know that </s><s>[INST] you [/INST] know there's a, it's called art cars. They all make art cars and like part of the part of the burn, what's so beautiful about it is like you can't buy anything there man like you. I I heard, I don't know if this has changed, it's been a bit because of the pandemic. But the only thing you could buy was ice and coffee and I think maybe that's changed, I heard some whisper that that's changed. But so that means that it's a gifting economy is what they call it. And so people will just give you stuff talk about having a struggle with deserving stuff man, What are you gonna do when the camp next to you is like every morning making the best iced coffee that you've ever had in your life and they just giving it all the way until it's all gone. What are you gonna do? It's it's the best ever and then you're giving things to people and then you you learn stuff like you learn these really interesting lessons like uh one of the times I went there got all these uh strawberries lex might not sound like a big deal, but when you're out there in the dust and you're not at one of like the like hardcore like luxury camps which do exist out there, you know you've got these like items where in my mind I'm like yeah these are gonna be just for me and my girlfriend, my special stash fruit and this or that and then like two days in your walking around your camp with </s><s>[INST] the strawberries that you're [/INST] coveting and everyone's so happy to get like cold strawberries and you've realized, oh my God, this feels so much better than the way a strawberry tastes so you learn something experientially there, which is an incredible thing, it's an incredible thing. Um man now I'm wishing I decided to go to burning man. </s><s>[INST] Yeah, [/INST] I just know like uh at least people were saying it was Elon musk's boat, like yeah, like this, I think it was like, it's like this massive, it's art cars and it was this party on this thing, You could just, anyone can go on the boat like no one's like there's no guest list, you just go on there. I never saw him there, but that you know, everyone's whispering Elon musk is here. </s><s>[INST] There's a secrecy, there's all that kind of stuff because you probably have to respect that at the same time there it seems like the kind of people that go there. I mean the the rules of the outside world are suspended in the sense that the, the crime, the aggression, the tensions all that seems to dissipate somehow, [/INST] not all the way, not all the way that, you know, there's a low, you could look it up, you know, because like there is tension, there's a lot of tension there between um it's called plug in plays like you know, Burning Man, like the history of Burning Man is fascinating. It has its roots in the cacophony society is what it was called, which is a sort of evolution of something that was, I think it was called the God. Like the saN Francisco basically there was like an art movement in saN Francisco and I can't remember the name of it, Maybe the suicide club or essentially like they were really into urban exploration and uh meaning like breaking into like old abandoned buildings and stuff. But part of this, what this was was you would prepare your life as though you were going to kill yourself, you would get all your affairs in order, you would get so it's going back to what we were talking about with the cancer diagnosis, you're like sort of putting yourself into that world of like I'm gonna get all my affairs together as though this is it. And then there was some, I'm sorry for anyone listening if I'm butchering this, but I think there was some really cool initiation where they would blindfold you and they would take you into some of these abandoned buildings and you didn't know where you were walking. But they would say like if you take one step to the left, you're gonna die, you're gonna fall off, you're gonna fall. So please be careful. So you're like in the moment and then blindfold comes off, it's a big awesome party. This evolves into something called the cacophony society. There's a great book called Tales of the cacophony society for people listening. Um you know, one of the members of the cacophony society was the author of Fight Club. And so if you've seen Fight Club, like you could see little ideas that were in the cacophony society, they were into data is um which I don't know a lot about like, I don't know, it's, but it's a philosophical art movement. Um and then, so basically what was happening is like they kept burning increasingly large effigies in san Francisco and they weren't allowed to do it. And so they took it out in the desert and they were basing it on something called a zone trip which is like you know across this border the rules of that old society are gone. And so that was the original Burning Man which was these lunatics out in the desert launching like burning pianos out of catapults through the air doing like drive by shooting ranges like no rules, wild, magical, beautiful, insane, madness. And then it grew and grew and grew and grew until you have Burning Man as it is today, which is still the most incredible thing. I mean obviously anytime you have like a thing that's been around for a while you're gonna get that, it's not like it used to be, it's not as free as it used to be. So this or that. But what's fascinating about burning man, Someone pointed this out to me, look on the ground, </s>

<s>[INST] empathize what [/INST] is your beef? What do you what do you where have you been? What is your consciousness, Why do you hate </s><s>[INST] jewish people? [/INST] Why? Why? What is, you know, all these </s><s>[INST] questions that come up [/INST] his sense of grievance as a result of World War One, </s><s>[INST] There's justifications [/INST] there, etcetera. But if I and by the way, Churchill was </s><s>[INST] trying to make a deal with him [/INST] in 38 </s><s>[INST] that's a fact that [/INST] people don't know is Churchill himself. And, you know, there was still the desire in England to make peace with Germany. Uh, and it was seen as a possible, what what what Churchill really wanted was Hitler to go against Russia and he anything to destroy the bolsheviks. So he was using </s><s>[INST] Hitler as much as he [/INST] could to go after Russia. But Hitler was too elusive to get to pin him down. But if you remember, Hitler was very kind at the end of this kind is not the right word, was </s><s>[INST] did not go after the british [/INST] empire when he had France, and he could have, </s><s>[INST] he [/INST] had another objective, which was obviously the East. So Hitler's </s><s>[INST] goal. I [/INST] think he always had an admiration for England. It's interesting story, always. </s><s>[INST] And the the [/INST] Empire. Yes, certainly Churchill, we have no doubts now from history, revisionism that Churchill's interest, main interest was not Germany, it was the british empire and to preserve it to India the road to India and all that? And the Middle East? Churchill fought the entire war with the concept of preserving the british empire? All his goals? He sent America on a goose chase into Italy you could argue instead of establishing a </s><s>[INST] sincere second front [/INST] in Western europe, Interesting man. Uh so I would have tried to get, you know, I think I would approach it the same way in 1939, it would have been a different story because at that point He had attacked Poland and in 1940 France so that it's another ball game. But certainly if whatever, at whatever point you talk to him, you I would try to understand his point. So I would I'm not judging you Hitler. I'm saying to you, tell me what you're thinking. Why are you invading Russia? What's your thought? That's all an interviewer should do. He shouldn't be expressing his contempt for Hitler, which is like an american journalist interviewing Putin. It's I'm getting Brownie </s><s>[INST] points for [/INST] expressing my contempt for you. That that does I don't, that doesn't wash with me that's ugly, </s><s>[INST] seek to [/INST] understand. Yes. </s><s>[INST] Uh this is a [/INST] technical question but was language </s><s>[INST] barrier as an interviewer [/INST] to some degree. It's very hard to learn </s><s>[INST] Russian, but [/INST] I had very they have excellent translators in the Kremlin. Excellent. They are people </s><s>[INST] who are trained [/INST] very seriously for months or years before. They these people are young and they're very bright. I was very impressed with the Russian judge. It's interesting. I mean, </s><s>[INST] I'm impressed as [/INST] well, but there's a humor that's </s><s>[INST] lost. [/INST] There's a wit, </s><s>[INST] a dry wit. There's stuff said between the lines, um that's not actually have much [/INST] content, but it's more </s><s>[INST] kind of the things that make [/INST] communication more </s><s>[INST] frictionless. It's [/INST] the there's a </s><s>[INST] there's a kind of [/INST] sadness to a Russian </s><s>[INST] humor that permeates all things [/INST] and that sometimes </s><s>[INST] is lost in translation. The translation is a little bit colder meaning. It's just conveys the facts. [/INST] Would you call it? Sardonic humor? </s><s>[INST] I would say so. [/INST] Yeah, and so it's interesting. But I think </s><s>[INST] you can see that from facial expressions when you're sitting across [/INST] from the person and you can you can feel </s><s>[INST] it. Let me ask you in general. [/INST] Mhm. </s><s>[INST] What's the [/INST] role of love </s><s>[INST] in the human condition [/INST] in your </s><s>[INST] life in life in [/INST] general? You talked, you looked at </s><s>[INST] some of the darkest [/INST] aspects of human </s><s>[INST] nature. What's the role of this? [/INST] one of the more beautiful </s><s>[INST] aspects of human, [/INST] I think without love, I wouldn't I don't think I'd be able to carry on. I think that love is my love is the greatest the ability to love is the greatest virtue you can have. It's it's the ability to share with another with your family, with your Children, with your wife, with your lover, your partner. It's an ability to extend yourself into the world and it </s><s>[INST] brings empathy with it. [/INST] Uh If you love, Well, I think you expand it to the human race too. And it's it's it's the strength behind the great novelists, the great artists of our time. Uh I think part of the reason I suppose we're scared of science sometimes is because the scientists sometimes don't express </s><s>[INST] that. Clearly you [/INST] can lose that when you </s><s>[INST] focus on [/INST] the facts, </s><s>[INST] on empirical data, on the science of things, [/INST] you can lose this </s><s>[INST] the humanity [/INST] that's between the </s><s>[INST] lines. I'm often [/INST] struck by when I talked to </s><s>[INST] scientists and I've talked to a few and how arrogant [/INST] they can be about. They don't talk to you if you don't understand their world and they talk to each other and there's an arrogance of closed circle kind of thing. Oh, he's not at my level. I can't there's no discussion to be had with this person. He's a human being. That arrogance </s><s>[INST] is terrifying to me because its its [/INST] next door neighbor </s><s>[INST] to close mindedness, which then can be used by charismatic leaders as it was in [/INST] nazi Germany </s><s>[INST] to commit some of the [/INST] worst atrocities. </s><s>[INST] The scientists can be used [/INST] as </s><s>[INST] pawns in a very in a very cruel [/INST] game. </s><s>[INST] What advice would you give to young people? You've done? First of all, some of the greatest films [/INST] ever. You've you've you've </s><s>[INST] lived a heck of a life. You've [/INST] we're fearless and bold in </s><s>[INST] asking some really difficult questions of this world. What advice would you give to young people today? High [/INST] school college about </s><s>[INST] career, [/INST] how </s>

<s>[INST] the following is a conversation with Stuart Russell. He's a professor of computer science at UC Berkeley and a co author of a book that introduced me and millions of other people to the amazing world of ai called artificial intelligence and modern approach. So it was an honor for me to have this conversation as part of M. I. T. Course and artificial general intelligence and the artificial intelligence podcast. If you enjoy it, please subscribe on youtube itunes or your podcast provider of choice. Or simply connect with me on twitter at lex Friedman spelled F R I D. And now here's my conversation with Stuart Russell. [/INST] So </s><s>[INST] You've mentioned in 1975 in high school, you've created one of your first ai programs that play chess. Were you ever able to build a program that beat you at chess or another board game? [/INST] Uh So my program never beat me at chess. I actually wrote the program at Imperial College. So I used to take the bus every Wednesday with a box of cards, this big uh and shove them into the card reader. And they gave us eight seconds of CPU time. It took about five seconds to read the cards in and compile the code. So we had three seconds of CPU time, which was enough to make one move, you know, with a not very deep search and then we would print that move out and then we have to go to the back of the queue and wait to feed the cards. And again, How </s><s>[INST] deep was the search are we talking about? So [/INST] now I think we got we got an eight move, you know, deplete um with alpha beta and we had some tricks of our own about move ordering and some pruning of the tree. And </s><s>[INST] but you were still able to beat that program. [/INST] Yeah, yeah. I was a reasonable chess player in my youth. I did in a fellow program uh and a background program. So when I got to Berkeley, I worked a lot on what we call matter reasoning, which really means reasoning about reasoning. And in the case of a game playing program, you need to reason about what parts of the search tree you're actually going to explore because the surgery is enormous or bigger than the number of atoms in the universe. And and the way programs succeed and the way humans succeed is by only looking at a small fraction of the search tree. And if you look at the right fraction you played really well. If you look at the wrong fraction, if you waste your time thinking about things that are never going to happen, the moves and no one's ever going to make, then you're going to lose because you won't be able to figure out the right decision. So that question of how machines can manage their own competition, how they, how they decide what to think about is the meta reasoning question. We developed some methods for doing that. And very simply a machine should think about whatever thoughts are going to improve its decision quality. We were able to show that both for a fellow which is a standard to play a game and for backgammon, which includes uh dice roll. So it's a two player game with uncertainty for both of those cases. We could come up with algorithms that were actually much more efficient than the standard alphabet, a search which chess programs at the time were using and that those programs could beat me and I think you can see The same basic ideas in Alphago and Alpha zero today. The way they explore the tree is using a form of matter reasoning to select what to think about based on how useful it is to think about it. </s><s>[INST] Is there any insights you can describe without greek symbols of how do we select which paths to go down? [/INST] There's really two kinds of learning going on. So as you say, Alphago learns to evaluate board position. So it can it can look at a go board and it actually has probably a superhuman ability to instantly tell how promising that situation is. To me, the amazing thing about Alphago is not that it can be the world champion with its hands tied behind his back. But the fact that if you stop it from searching altogether. So you say, okay, you're not allowed to do any thinking ahead, You can just consider each of your legal moves and then look at the resulting situation and evaluate it. So what we call a depth one search. So just the immediate outcome of your moves and decide if that's good or bad. That version of Alphago can still play at a professional level, Right? And human professionals are sitting there for 5, 10 minutes deciding what to do. And alphago in less than a second can instantly into it. What is the right move to make based on its ability to evaluate positions? Um and that is remarkable because you know, we don't have that level of intuition about go. We actually have to think about the situation. So anyway, that capability that Alphago has is one big part of why it beats humans. The other big part is that it's able to look ahead. 40, 50 60 moves into the future. And You know, if it was considering all possibilities, 40 or 50 or 60 moves into the future, that would be You know, 10 to the 200 possibilities. So way, way more than atoms in the universe and so on. So it's very, very selective about what it looks at. So let me try to give you an intuition about how you decide what to think about is a combination of two things. One is how promising it is, right? So if you're already convinced that a movie is terrible, there's no point spending a lot more time convincing yourself that it's terrible because it's probably not going to change your mind. So the real reason you think is because there is some possibility of changing your mind about what to do, right, and is that changing your mind that would result than in a better final action in the real world? So that's the purpose of thinking is to improve the final action in the real world. And so if you think about a move that is guaranteed to be terrible, you can convince yourself it's terrible, you're still not going to change your mind, right? But on the other hand, you suppose you had a choice between two moves. One of them you've already figured out is guaranteed to be a draw, let's say, and then the other one looks a little bit worse, like it looks fairly likely that if you make that move, you're going to lose. But there's still some uncertainty about the value of that move, there's still some possibility that it will turn out to be a win, right, then it's worth thinking about that. So even though it's less promising on average than the other move, which is guaranteed to be a draw, there's still some purpose in thinking about it because there's a chance that you'll change your mind and discover that in fact it's a better move. So it's a combination of how good the move appears to be and how much uncertainty there is about its value, the more uncertainty, the more it's worth thinking about, because it's a higher upside if you want to think of it that way, </s>

<s>[INST] So everything you just described is kind of it's fascinating a set of ideas and you know online I've been reading quite a bit and people are really excited about the set of ideas. Nevertheless it is not the dominating technology today so. Bitcoin in terms of Cryptocurrency is the most popular Cryptocurrency and then ethereum and so on. So it's useful to kind of comment. We already talked about proof of work a little bit. But what in your sense does Bitcoin get right and where is it lacking? [/INST] Okay. So the first thing that Bitcoin got right is to understand that there was the need over Cryptocurrency and that might be enough trance with deserve all the success because they say the time is right for this idea because very often it's not enough to be right here to be right at the right time and somebody got it right there so hard to offer to Bitcoin for that. And and so what do they go to right is a way that is make, it is hard to subvert and change village to cancel transaction. It's not impossible. That is very hard. What they did not get right is somehow veta is a great story of value currency wise but money is not only a question that you store it and you put under the mattress. Money wants to be transacted and the transaction. Bitcoins are very little so if you want to store value, everybody needs a store value might as well use a Bitcoin. I mean it's the plant but if you are uh don't look at that for a moment at least is a great store of value and everybody needs a store of value. But most of the time we want to transact we want interact, we don't put the money under the mattress, right? So we wanted to bet they didn't get it right, that is too slow to transact too few </s><s>[INST] transactions capability [/INST] based scalability issues. </s><s>[INST] Is it possible to build stuff on top of Bitcoin? That's uh sort of uh fixes the scalability. I mean this is the thing you look at, there's a bunch of technologies that kind of hit the right need at the right time and they have flaws but we kind of build infrastructures on top of them over time to fix it as opposed to getting it right from the beginning or is it difficult to do [/INST] well that is difficult to do. So you're talking to somebody Vettel when I decided to follow my heart in the arena and I decided first of all, as I said before, I much admire my predecessors, I mean they got to write a lot of things and I and I really am admire for vet but you know, I had a choice to make either I patched something that as holes all over the place where I start from scratch. I just want to start from scratch because sometimes it's a bit of </s><s>[INST] way. So what about ethereum which looks at proof of stake and a lot of different innovative ideas that kind of improve or seek to improve on some of the flaws of Bitcoin [/INST] that you meant another great idea. So they figured out it was money and payments are important as they are, there are only the first level. The first stepping stone to the next level are smart contracts and they were at the vision to say is that people will need a smart contract which allow me and new to somehow to transact securely. We've had to being shopped around by a trusted third party by a mediator by the way because the mediators are hard to find and in fact maybe even impossible to find if you live in Thailand and I live in uh in new Zealand, maybe we don't have a common person that we know and trust And even if we find them, guess what they want to be paid so much so right. With a 6% of the world GDP is goes into financial friction, which is essentially a third party, so headed right of the world needed that. But again, the scalability is not there and the system is a smart contracts in ethereum is slow and expensive and um and I believe it is not enough to satisfy the appetite and the need. We have a four smart contracts. </s><s>[INST] Well, what do you make of just as a small sort of, aside in human history, perhaps it's a big one is the N. F. T than non fungible tokens. Do you find those interesting technically, or is it more interesting on the social side of things? [/INST] Well, both, I think, you know, I think it's N. F. T. S. Are actually great. Right? So you have always you're an artist to create a a song or it could be a piece of art. Uh He has many unique representation, right? Of a unique a piece where there is an artifact of uh something dreamed up by you and uh and as unique representation but now you can trade and allow. The important part is that now you have a visa, not only the N. F. T. S themselves, but the ability to trade them quickly fast, securely knowing that who owns which rights and that gives a totally new opportunity for content creators to be remunerated for what do I do, </s><s>[INST] So, but ultimately you still have to have that scalability security uh and decentralization to to make it, you know to make it work for bigger and bigger applications. [/INST] Yeah. </s>

<s>[INST] How long did you spend in isolation? [/INST] More than six months. So I uh, after three or four days as the little judas windows slide open and a man, a nice looking man in the suit. Come there. Hello Reeves. I want to just want to see what you look like. I saw you a national Geographic documentary And it does me pleasure to keep you in isolation and he slammed the thing and I couldn't get out of there. And by law, the US Parole Commission is supposed to give you a hearing within 90 days. So Murray paid a lawyer $7500. And he never picked up the phone. Somebody got to him. </s><s>[INST] Who is that? Somebody you think [/INST] Christopher Cannon was his name and I don't know who got to him. But some he didn't he didn't do anything to get me out of there. Yeah, I got 1 15 minute phone call a month and I couldn't get out. So then after six months they ship me to uh put me on con air double shackled and black box on my hands. And I went to went to Oklahoma and they let me out on the the on the floor. I couldn't imagine that I could call after a couple of days. And they said there was a man here from Washington, give you a parole here and you've only got you at 3.30. So he left. He said he'd be back next year. What happened in now for six months. So then there was a lovely little lady. She was a case manager or something. She said you can ask for parole on the record. And I said please do. So I sent him an email and the next day I got my parole 90 days later they sent me to terminal island. Put me in the place there with the infinite I guess since I'm as old as I am, 78 years old. So they put me in the people in their dying and wheelchairs and legs off and arms off and cancer. So I was in there and I pushed the fellas around and uh I won't come out of the chow hall there and I want to go to the right to get me a haircut. Two mexican guys there, lieutenant, another one between us. And he went like that, I could outrun you. And they slammed me, put me on the ground, handcuffed me and put me in the shoe for a week. I got out man, they put me in the back in the place, they treated me rough. So I got in a little more trouble and they put me back in in the shoe and I wouldn't come out. They would have that the virus was out killing people. So they killed eight people in that unit I was in. </s><s>[INST] So [/INST] I mean I wouldn't even come out to take a shower. I had I had a little straw that I put in a in the sink and I take a sock that I had and scrubbed myself with it with some smoke and glass order over my head and then cleaned the floor, put it in the toilet, </s><s>[INST] that was your time during the coronavirus pandemic Cut [/INST] out last april right in the middle of it and they were dying bad in there. So I was treated worse for that last year in America than I was for the whole 20 years in Australia, 18 years in Australia. </s><s>[INST] And then you were a free man at the end of that year. [/INST] They put me out and sent me home and, and uh, the parole officers couldn't even come, they weren't working. They were just doing everything by video. They do not have a drink. Only constituent thing was I couldn't even have a drink of wine. So uh, After a year they had, I had to take psychiatric treatment every week I had to go talk to the psychiatrist, psychologist and me and her got along great. She was a good Christian woman. We just chatted and talked and I think they said I had to pee in the bottle every week and I said, I've been in 33 years. How many fist desk do you think I've had never been dirty? Only thing if you don't want to clean when you come get me </s><s>[INST] before I talk to you about love, let me ask you a difficult question. You write in your book. I don't consider myself much of a criminal. I don't lie, cheat or steal and I always take up for the underdog violence makes me sick. Yet I know I'm an outlaw and those that break the law must be punished. I think many people listening to this or some people listening to this. We'll see you as a criminal, as a bad man who increased the amount of suffering in this world. What do you have to say to them? [/INST] I would like to tell them that they have been indoctrinated by the spin of news and politicians and they don't know the truth of the situation. You lay the truth out there in an envelope. Let me open it. Besides something else that was false and it's staggering. The truth is that I was a tobacco farmer And tobacco kills 500,000 people a year in America and six million have a debilitating diseases because of it. Drugs, all drugs combined killed between 10 and 15,000 people a year by overdose. And 60% of those are pharmaceutical. Now that when I was a tobacco farmer come sit on the front pew Mr Reeves. Come on up. Here you are gentlemen. You just joined the Masonic lodge and you joined our church and you just come on and sit down with the good people. You grow to marijuana plants. Get out of here, you scumbag and the marijuana doesn't hurt anybody. It's just that's the truth of it. </s>

<s>[INST] chris, beautifully put. It's a good place to end. Thank you so much for talking today. Thank [/INST] you very much. Really enjoyed it. </s>

<s>[INST] and there's an improvement process. They're like so being self critical and growing like you know, I guess youtubers go through this process of like putting out some content and like nobody caring about it and then trying to figure out like and basically improving. Figure out like why did nobody care? Uh What can I you know? And they come up with all kinds of answers which may or may not be correct, but doesn't matter because the answer leads to improvement. So you're being constantly self critical, self analytical, it should be better to say. So you think of like how can I make the audio better? Like all the basic things. Maybe 11 question to ask because uh well uh by way of Ross Dedrick, he's a robotics professor at MIT, one of my favorite people, a big fan of yours, He watched our first conversation, I just interviewed him a couple weeks ago, He uh he teaches this course and under actuated robotics which is um like robotic systems when you can't control everything, like when you're like we as humans, when we walk, we're always falling forward which means like it's gravity, you can't control it, you just hope you can catch yourself but that's not all guaranteed, it depends on the surface. So like that's under actuated, you can't control everything? Uh the number of actuators, uh the degrees of freedom you have is not enough to fully control the system. So I don't know, it's a really, I think beautiful, fascinating class. He puts it online um it's quite popular, he does an incredible job teaching, he puts online every time, but he's kind of been interested in like crisping it up like, you know, making it uh you know, innovating in different kinds of ways. And he was inspired by the work you do because I think in his work he can do similar kind of explanations as you're doing, like revealing the beauty of it and spending like months in preparing a single video. Uh And he's interested in how to do that. That's why he listened to the conversation, he's playing with madam. But he had this question of you know uh of uh you know like in my apartment when we did the interview, I like curtains like for like a black curtain, not uh this is this is uh adjacent mansion that were in that I also uh but you basically just have like a black curtain, whatever that you know, makes it really easy to set up a filming situation with cameras that we have here, these microphones. He was asking, you know, what kind of equipment do you recommend? I guess like your blog post is a good one. I said I don't recommend this is excessive and actually really hard to work with. I wonder, I mean is there something you would recommend terms of equipment? Like is it you do you think like lapel mics like USB Mics? What [/INST] for my narration? I use a USB mic for the streams. They used a lapel mic. Uh the narration, it's a blue yeti, I'm forgetting actually the name of the lapel mic but it was probably like a road of some kind. Um But is </s><s>[INST] it hard to figure out how to make the audio sound good? [/INST] Oh I mean listen to all the early videos on my channel and clearly like I'm terrible at this for for some reason um I just couldn't get audio for a while. I think it's weird when you hear your own voice. So here this sounds weird and it's hard to know does it sound weird because you're not used to your own voice or their actual audio artifacts that play. Um So </s><s>[INST] uh and then video is just for the lockdown was just the camera, like you said, it was probably streaming somehow through the, [/INST] yeah there were two G. H. Five cameras, one that was mounted overhead over a piece of paper. You could also use like an ipad or awake um tablet to do your writing um electronically but I just wanted the paper feel. Um One on the face, there's two. Again I don't know, I'm like just not actually the one to ask this because I like animate stuff usually, but uh each of them has a compressor object that makes it such that the camera output goes into the computer USB but like it's compressed before it does that </s><s>[INST] the live aspect of it, Do you do you regret doing it live? [/INST] Not at all. Um I think I do think the content might be like much less sharp and tight than if it were um something even that I just recorded like that and then edited later. But I do like something that I do to be out there to show like, hey, this is what it's like rock. This is what it's like when I make mistakes. Um This is like the pace of thinking. Um I like the live interaction of it. I think that made it better. Uh I I probably would do it on a different channel. I think if I did a series like that in the future just because it's, it's a different style. It's probably a different target audience. And um kind of keep clean what three Blue and Brown is about versus uh the benefits of like live lectures, </s><s>[INST] do you suggest like in this time of covid that people like us or other educators try to go Like the shorter, like 20 minute videos that are like really well planned out or scripted? You really think through you slowly design, so it's not live, do you see like that being an important part of what they do. [/INST] Yeah. Well what I think teachers like rest should do is choose the small handful of topics that they're going to do just really well. They want to create the best short explanation of it in the world. That will be one of those handfuls in a world where you have commoditized explanation right? Most of the lectures should be done just normally still put thought and planning into it. I'm sure he's a wonderful teacher and like knows all about that. But maybe choose those small handful of topics, do what beneficial for me. Sometimes I do sample lessons with people on that topic to get some sense of how other people think about it. Let that inform how you want to edit it or scripted or whatever format you want to do. Some people are comfortable just explaining it and editing later. I'm more comfortable like writing it out and thinking in that setting. </s>

<s>[INST] Yeah, I think autonomy especially in flight is super exciting. Do you, do you see if a day here we go back into philosophy, uh, future when most fighter jets uh will be highly autonomous to a degree where a human doesn't need to be in the cockpit in almost all cases [/INST] Well, I mean, that's a world that to a certain extent we're in today now, these are remotely piloted aircraft to be sure, but but we have hundreds of thousands of flight hours a year now, And remotely piloted aircraft. And then if you take the F- 35, uh there, I mean, there are huge layers, I guess in levels of autonomy built into that aircraft so that the pilot is essentially more of a mission manager rather than doing the data, you know, the the 2nd 2nd elements of flying the aircraft. So in some ways it's the easiest aircraft in the world to fly. And kind of a funny story on that. So I don't know if you know how aircraft carrier landings work. But basically, uh, there's what's called a tail hook and it catches wires on the deck of the carrier and that's what brings the aircraft to a screeching halt. Right? And there's typically three of these wires. So if you miss the first, the second one, you catch the next one. Right. And uh, we got a little criticism. I don't know how true this story is, but we got a little criticism. The F- 35 is so perfect. It always gets the second wire. So we're wearing out the wire because it always hits that one. So that, but that's the kind of autonomy that just makes these essentially up levels what the human is doing to more of that mission manager. So much of </s><s>[INST] That landing by the F- 35 is autonomous. [/INST] Well, it's just, you know, the control systems are such that you really have dialed out the variability, um, that comes with all the environmental conditions. So my point is, to certain extent that world is here today. Do I think that we're going to see a day anytime soon when there are no humans in the cockpit. I don't believe that, but I do think we're going to see much more human machine teaming and we're going to see that much more at the tactical edge. And we did a demo, you asked about what the skunk works is doing these days. And so this is something I can talk about. But we did a demo with the Air Force research laboratory or laboratory. We called it half raider. And so using an F 16 as an autonomous wingman and we demonstrated all kinds of maneuvers and various mission scenarios with the autonomous F 16 being that so called loyal or trusted wingman. And so those are the kinds of things that, you know, we've shown what is possible. Now, given that you've up leveled that pilot to be a mission manager now they can control multiple other aircraft thinking almost as extensions of your own aircraft flying alongside with you. So that's that's another example of how this is really coming to fruition. And then uh yeah, I mentioned the landings, but think about just the implications for humans and flight safety. And this goes a little bit back to the discussion we were having about how do you continuously improve the level of safety through automation while working through the complexities that automation introduces. So one of the challenges that you have in high performance fighter aircraft is what's called G lock. So this is G induced loss of consciousness. So you pull nine Gs, you're wearing a pressure suit that's not enough to keep the blood going to your brain blackout. And of course that's bad if you happen to be flying low, you know, near the deck and uh you know, an obstacle or terrain environment. And so we developed the system at our aeronautics division called Auto G. Casso autonomous ground collision avoidance system. And uh we built that into the F 16. It's actually saved seven aircraft, eight pilots already and the relatively short time it's been deployed, it was so successful that the Air Force said, hey we need to have this in the F 35 right away. So we've actually gone done testing of that now in the F 35. Um and we've also integrated and autonomous air collision avoidance systems. So I think the air to air problem. So now it's the integrated collision avoidance system, but these are the kinds of capabilities, you know, I wouldn't call him a I I mean they're very sophisticated models of the aircraft dynamics coupled with the terrain models to be able to predict when essentially the pilot is doing something that is going to take the aircraft into or the pilots not doing something in this case. But does it just gives you an example of how autonomy can be really a lifesaver in today's world, </s><s>[INST] it's like autonomous, emergency, automated emergency breaking in cars. But is there any exploration of perception of, for example, detecting G lock that the pilot has is out. So as opposed to perceiving the external environment to infer that the pilot is out but actually perceiving the pilot directly. [/INST] Yeah, this is one of those cases where you'd like to not take action if you think the pilots there and it's almost like systems that try to detect if a driver is falling asleep on the road right, with limited success. Uh So uh I mean this is what I call the system of last resort, right? Where if the aircraft has determined that it's going into the terrain, get it out of there and uh and this is not something that we're just doing in the in the aircraft world. I wanted to highlight, we have a technology we call Matrix, but this is developed at Sikorsky innovations. The whole idea there is what we call optimal piloting, so not optional piloting or unpiloted, but optimal piloting. So an FAA certified system, so you have a high degree of confidence, it's generally pretty deterministic. So if we know that it will do in different situations but effectively be able to fly a mission with two pilots, one pilot, no pilots and uh and have, you can think of it almost as like a dial of the level of autonomy that you want but able, so it's running in the background at all times and able to pick up tasks, whether it's, you know, sort of autopilot kinds of tasks or or More uh sophisticated path planning, kinds of activities to be able to do things like for example, land on an oil rig in the North Sea and Bad Weather, 00 conditions. And you can imagine of course there's a lot of military utility to capability like that. You could have an aircraft that you want to send out for a crewed mission. But then in the at night, if you want to use it to deliver supplies and an unmanned mode that that could be done as well. And so there's there's there's clear advantages there. But think about on the commercial side, you know, if you're an aircraft taken, you're going to fly out to this oil rig. If you get out there and you can't land, then you gotta bring all those people back, reschedule another flight, pay the overtime for the crew that you just brought back because they didn't get where they're going to pay for the overtime for the folks that are out there around the oil rig. This is real economic, you know, these are dollars and cents kinds of advantages that we're bringing in the commercial world as well. </s>

<s>[INST] state. So the paper in particular, so it's just a beautiful idea to use a chemical computer to construct the cellular automata and the famous one of Game of Life, but it's also interesting, and it's a really interesting scientific question of whether some kind of random perturbations or some source of randomness can have a significant constructive effect on the complexity of the [/INST] system. And indeed, whether it's random or just non-deterministic and can we bake in that non-determinism at the beginning, I'm trying to think about what is the encoding space. The encoding space is pretty big. We have 49 stirrups of 49 cells, 49 chembits, all connected to one another in an analog computer, but being read out discreetly as the BZ reaction. So just to say, the BZ reaction is a chemical oscillator. And what happened in each cell is it goes between red and blue. Two Russians discovered it, Beluzov-Zaposinski. I think Beluzov first proposed it, and everyone said, you're crazy, it breaks the second law. And Zaposinski said, no, it doesn't break the second law, it's consuming a fuel. There's a lot of chemistry hidden in the Russian literature, actually, because Russians just wrote it in Russian, they didn't publish it in English speaking journals. It's heartbreaking, actually. Well, it's great that it's there, right? It's not </s><s>[INST] lost. I'm sure we will find a way of translating it properly in journals. It's heartbreaking, actually. Well, the silver lining slash greater sadness of all of this is there's probably ideas in English speaking. There's ideas in certain disciplines that, if discovered by other disciplines, would crack open some of the biggest mysteries in those disciplines. Like computer science, for example, is trying to solve problems like nobody else has ever tried to solve problems, as if it's not already been all addressed in cognitive science, in psychology, in mathematics, in physics, in just whatever you want, economics even. But if you look into that literature, you might be able to discover some beautiful ideas. Obviously, Russian is an interesting case of that because there's a loss in translation, but you said there's a source of [/INST] fuel, a source of energy. Yeah, yeah, yeah. So the BZ reaction, you have an acid in there called malonic acid. And what happens is, it's basically like a battery that powers it, and it loses CO2, so decarboxylates. It's just a chemical reaction. What that means we have to do is continuously feed, or we just keep the BZ reaction going in a long enough time. So it's reversible in time. But only like, yeah. But it's fascinating. I mean, the team that did it, I'm really proud of their persistence. We made a chemical computer. It can solve little problems. It can solve traveling salesman problems, actually. Nice. But like I said, it's- </s><s>[INST] But not any faster than the computer. Is there something you could do? [/INST] Is there something you could do? Maybe. I think we can come up with a way of solving problems, also really complex, hard ones. Because it's an analog computer, and we can, it can energy minimize really quickly. It doesn't have to basically go through every element in the matrix, like flip it. It reads out. So we could actually do Monte Carlo by just shaking the box. It's literally a box shaker. You don't actually have to encode the shaking of the box in a </s><s>[INST] silicon memory, and then just shuffle everything around. It's analog, it's natural, so it's an [/INST] organic computer. Yeah, yeah. So I was playing around with this, and I was kind of annoying some of my colleagues. I'm wondering if we could get to chemical supremacy, like quantum supremacy. And I kind of calculated how big the grid has to be, so we can actually start to solve problems faster than a silicon computer. But I'm not willing to state how that is yet, because I'm probably wrong. It's not that I'm, it's any top secret thing is I want, I think I can make a chemical computer that can solve optimization problems faster than a silicon computer. </s><s>[INST] That's fascinating. But then you're unsure how big that has to be. Yeah, I think, I mean, [/INST] It might be a big box, hard to shake. It might be exactly a big box, hard to shake, and basically a bit sloppy. </s><s>[INST] Did we answer the question about, do cellular atomic exist outside the mind? [/INST] We didn't, but I would posit that they don't. But I think minds can, well- </s><s>[INST] So the mind is fundamental. What's the, why? [/INST] Well, I mean, sorry, let's go to the back. So as a physical phenomena, do CA's exist in physical reality, right? I would say they probably don't exist outside the human mind, but now I've constructed them, they exist in computer memories. They exist in my lab, they exist on paper. So they are, they emerge from the human mind. I'm just interested in, because Stephen Wolfram likes CA's, a lot of people like CA's and likes to think of them as minimal computational elements. I'm just saying, well, do they exist in reality or are they a representation of a simple machine that's just very elegant to implement? </s><s>[INST] So it's a platonic question, I guess. I mean, there's initial conditions, there's a memory in the system. There are simple rules that dictate the evolution of the system. And so what exists? The idea, the rules, the- [/INST] Yeah, people are using CA's as models for things in reality to say, hey, look, you can do this thing in a CA. And when I see this, I'm saying, oh, that's cool, but what does that tell me about reality? Where's the CA in space? </s>

<s>[INST] You don't order people until you ask them. I guess the question I'm asking is how do you find [/INST] the strength to then go on to absolute after? Because you've done a 14-week training camp where every day was just as intense as any ADCC day. So you're used to it at that point. But he had very, very long, tough matches. But he's used to it. He's a good athlete. So Nicholas and John Carla went out, and John Carla had a spectacular submission victory against his first opponent. Nicholas had some firework matches, and one of the toughest opponents he came up against was the brilliant Ty Ruatolo. They had an absolute barn burner. It was a very, very close match. Ty had had an incredible first two matches. He'd beaten Pedro Mourinho by submission, and he'd beaten the great Felipe Pena in a very narrow match. Very, very tight. Felipe lost on a guard pull. But Felipe is considerably bigger and stronger than Ty. So for Ty to win that match, even by a guard pull, was deeply impressive. It was an action </s><s>[INST] pack match that went back and forth. Very, very impressive. But he had very, very long, tough matches. That's just a small tangent. Both Ruatolo brothers had an incredible performance. What do you think makes them so good if you were to analyze their game outside of you [/INST] and just this specific match? Yeah, absolutely. There's a range of factors. One is that they started the sport very, very young. They're probably the first example in American grappling of American students who started at age four or five. Most people, when I began jiu-jitsu, started jiu-jitsu as adults. I was 28 years old when I had my first lesson as a white belt. So in time, people got a little younger. For example, Nikki Ryan started when I think when he was 12. But the Ruatolo started when they were literally children. They had excellent coaching going all the way up through into their teenage years. So they had the advantage of starting the way so many successful athletes do as children and going up through adulthood with strong coaching all along the way. Excellent parental support. So they had a great history where their youth didn't show off just how long they'd been in the sport. So you're dealing with a kid who's 19 years old, but he's been grappling for 15 years. And what counts is not your age, but your mat age and quality. Now, they were very young in years, but they were very old in mat age. </s><s>[INST] But there's a lot of athletes that have now, as you correctly said, have spent from a very early age on the mat, but still these particular ones stand out. [/INST] It's interesting. No, there's a lot more to it than that. This is just the first setting the scene. But what really makes them stand out is that they've mastered this idea of covering up and improving initial weaknesses while building upon strengths. When the rutolas first encountered my students, they were relatively easy to leg lock because none of their training experience had prepared them for that. Now, they were young at that time, I believe like 16 or 17. And it was an obvious problem for them. They both got heel hooked by my youngsters also, Nikki Ryan and Ethan Kralenstein. And you could clearly see that they identified their current weakness and made prodigious steps to improve upon it to a point now where they're winning championships with their own leg locks. I love the fact that even as teenagers, they had the maturity to say, okay, here's an obvious weakness, let's get around this, let's turn it into a strength. I love the way they did that. Focus on the weakness and let that guide you to the thing you're working on. But they also, they covered up their weaknesses, but they also understood what are our actual strengths. Now, physically, both of the brothers have extraordinary reach for their height. They both have extraordinarily long arms for their height. That means that variations of karikatame, in particular dasas, anacondas are going to be much easier for them and their weight division than for most people. These are all jokes. Yes, strangleholds. So they specialize in those. They adapted a game based around movement, which forces opponents, not with physical pressure, but with tactical pressure into positions which expose them to those specialized strangleholds that they use. Traditionally, when we looked at the rheumatoids when they were young, we saw that there was a disparity between their top game and their bottom game. They were generally much better in top position than they were in bottom position. Again, they saw that as a potential weakness and they turned it around using again, their unique long limbs relative to their height, and they make use of a buggy strangle. I'm not sure why it's referred to as a buggy strangle, but basically, it's a variation of karikatame using the legs done from disadvantageous positions on bottom. They both make brilliant use of that, not so much as a strangle weapon. Occasionally, they'll strangle some of it, but they mostly use it to create pressure to make people back off. As a result, they overcame the disparity between their top game and their bottom game. Now, their bottom game is part of their offense and they're very, very successful from there. Again, you had that really impressive sense in which they identified their weaknesses and leg locks in bottom position, turned it around, and made it into strengths. At the same time, they identified, okay, what are our physical gifts and how can we maximize their use? They created a program of initiating movement that created tactical rather than physical pressure to set up their best strangle holds. I deeply admire what they've done. Those two young men </s>

<s>[INST] it's a meta reform of being able to start new countries. Okay, so that's one problem, but you could push back and say that's a feature. Because a lot of people argue that tradition is power. Through generation, if you try a thing long enough, which is the way I see marriage, there's value to the struggle and the journey you take through the struggle and you grow and you develop ideas together, you grow intellectually, philosophically together. And that's the idea of a nations that spans generations that you have a tradition that becomes more, that strives towards the truth and is able to arrive there, or no, not arrive, but take steps towards there through the generations. So you may not want to keep starting new governments. You may want to stick to the old one and improve it one step at a time. So just because you're having a fight inside a marriage doesn't mean you should get a divorce and go on Tinder and start dating around. That's the pushback. So it's not obvious that this is a strong feature to have [/INST] to launch new governments. There's several different kinds of lines of attack or debate or whatever on this, right? First is, yes, there's obviously value to tradition and people say, this is Lindy and that's Lindy. It's been proven for a long time and so on. But of course there's a tension between tradition and innovation. Like going to the moon wasn't Lindy, just it was awesome. And artificial intelligence is something that's very new. New is good, right? And this is a tension within humanity actually itself because it's way older than all of these nations. I mean, humans are tens of thousands of years old. The answer to humans are millions of years old, right? And you go back far enough and the time that we know today of the sessile farmer and soldier is, if you go back far enough, you want to be truly traditional. Well, we're actually descended from hunter-gatherers who were mobile and wandered the world and there weren't borders and so on. They kind of went where they want, right? And people have had done historical reconstructions like skeletons and stuff like that. And many folks report that the transition to agriculture and being sessile resulted in diminution of height. People had like tooth decay and stuff like that. The skeletons, people had traded off upside for stability. That's what the state was. That was what these sessile kinds of things were. Now, of course, they had more likelihood of living consistently. You could support larger population sizes, but it had lower quality of life, right? And so the hunter-gatherer, maybe that's actually our collective recollection of a Garden of Eden where people, just like a spider kind of knows innately how to build webs or a beaver knows how to build dams. Some people theorize that the entire Garden of Eden is like a sort of built-in neural network recollection of this pre-sessile era where you're able to roam around and just pick off fruits and so on, low population density. So the point is that I think what we're seeing is a V3, you go from the hunter-gatherer to the farmer and soldier, the sessile. Nations are here and they've got borders and so on. To kind of the V3, which is the digital nomad, the new hunter-gatherer, we're going back to the future because you know what's even older than nations is no nations, right? Even more traditional than tradition is being international, right? And so we're actually tapping into that other huge thread in humanity, which is the desire to explore, pioneer, wander, innovate, you know? </s><s>[INST] And I think that's important. To make America great again is to dissolve it completely into oblivion. [/INST] No, that's a joke, that's a joke. Yeah, I know it's a joke. Humor, I'm learning this new thing. Yes, the new thing for the role. The chat pod emulation isn't fully working there. </s><s>[INST] Yeah, yeah, yeah, glitch. [/INST] That's where in the beta. And let me just say one other thing about this, which is there are, I mean, everybody in the world to, okay, let's say, I don't know what percentage, let's say 99.99%, or it rounds to that number of political discourse in the US focuses on trying to fix the system. If those folks, I mean,.01% of the energy is going towards building a new system, that seems like a pretty good portfolio strategy, right? Or 100% are supposed to go and edit this code base from 200 something years ago. I mean, the most American thing in the world is going and leaving your country in search of a better life. America was founded 200 years ago by the founding fathers. It's not just a nation of immigrants, it's a nation of immigrants, right? Immigration from other countries to the US and actually also immigration within the US. There's this amazing YouTube video called, it's like 50 states, US population, I think 1790 to, it says 2050, so they've got a simulation. So you just stop it at 2019 or 2020. But it shows that like Virginia was like number one early on and then it lost ground in like New York gained. And then like Ohio was a big deal in the early 1800s. And it was like father of presidents and generally all these presidents and later Illinois and Indiana. And then California only really came up in the 20th century, like during the Great Depression. And now we're entering the modern era where like Florida and Texas have risen and New York and California have dropped. And so interstate competition, it's actually just like inter currency competition. You know, you've got trading pairs, right? You sell BTC by ETH, you sell Solana, you sell Monero by Zcash, right? Each of those trading pairs gives you signal for today on this currency is down or up relative to this other currency. In the same way, each of those migration pairs, someone goes from New York to Ohio, Ohio to California, gives you information on the desirability of different states. You can literally form a pairs matrix like this over time. Very much like the link matrix that's shaped America in a huge way. And so, you ask A, if this nation of immigrants that was founded by men younger than us, by the way, the founding fathers were often in their 20s, right? Who, you know, endorsed the concept of a proposition nation who've given rise to a country of founders and pioneers who've literally gone to the moon, right? Those folks would think that this is the end of history, that that's it, we're done. Like we've done everything else. I mean, there's people in technology who believe, and I agree with them, that we can go to Mars. They might even be able to end death, but we can't innovate on something that was 230 years old. </s>

<s>[INST] Do you find it amazing or is it surprising that such simple systems, such simple rules and sell your atomic can create sort of seemingly unlimited complexity? [/INST] Yeah, that was very surprising to me. </s><s>[INST] How do you make sense of it? How does that make you feel? Is it just ultimately humbling? Or is there hope to somehow leverage this into a deeper understanding and even able to engineer things like intelligence? [/INST] It's definitely humbling. How humbling in that uh also kind of awe inspiring that it's that inspiring? Like part of mathematics that these incredibly simple rules can produce this very beautiful complex, hard to understand behavior and that, that's, it's mysterious, you know, and, and surprising still, um but exciting because it does give you kind of the hope that you might be able to engineer complexity just from, </s><s>[INST] from simple from the beginning, can you briefly say what is the santa fe institute, its history, its culture, its ideas, its future? So I've never, I mentioned to you, I've never been, but it's always been this in my mind, this mystical place where brilliant people study the edge of chaos. [/INST] Exactly. So the Santa Fe Institute was started in 1984 and it was created by a group of scientists, a lot of them from Los Alamos National Lab, which is About a 40 minute drive from Santa Fe Institute. They were mostly physicists and chemists, but they, we're frustrated in their field because they felt so that their field wasn't approaching kind of big interdisciplinary questions like the kinds we've been talking about and they wanted to have a place where people from different disciplines could work on these big questions without being siloed into physics, chemistry, biology, whatever. So they, they started this institute and this was people like um George cowan who was a chemist in the Manhattan project and um Nicholas, metropolis, who uh mathematician, physicist, uh uh Murray gell mann physicist and is um so some really big names here, ken Arrow, an economist Nobel prize winning economist and they started having these workshops um and this whole enterprise kind of grew into this research institute that's itself has been kind of on the edge of chaos its whole life because it doesn't have any, it doesn't have a significant endowment and it's just been kind of living on whatever funding it can raise through donations and grants and however it can business business associates and so on. Um but it's a great place, It's a really fun place to go. Think about ideas from that you wouldn't normally encounter. </s><s>[INST] So, sean carroll uh physicists in [/INST] the external faculty </s><s>[INST] and you mentioned that there, so there's some external faculty and those people that a very [/INST] Small group of resident faculty, maybe maybe about 10 who are there for 5-year terms that can sometimes get renewed and then they have some postdocs and then they have this much larger on the order of 100 external faculty or people come like me who come and visit for various periods of time. </s><s>[INST] So what do you think this is the future of the santa fe institute? Like what if people are interested like, what, what's there in terms of the public interaction or students or so on? That? That could be a possible interaction with the santa fe institute or its ideas. [/INST] Yeah, so there's a there's a few different things they do, they have a complex systems summer school for graduate students and post docs and sometimes faculty attend to and that's a four week, very intensive residential program where you go and you listen to lectures and you do projects and people people really like that. I mean, it's a lot of fun. They also have some specialty summer schools. There's one on computational social science, there's one on climate and sustainability, I think it's called. There's a few and then they have short courses where just a few days on different topics. They also have an online education platform that offers a lot of different courses and tutorials from the faculty, including an introduction of complexity course that I talk </s><s>[INST] awesome and there's a bunch of talks to on online from the guest speakers and so on. They host a lot [/INST] of Yeah, they have sort of technical seminars in Cahokia. They all and they have a community lecture series uh like public lectures and they put everything on their Youtube channel. So you can see it all. </s><s>[INST] Douglas Hofstadter, author of Get Alicia Back, was your PhD adviser. You mentioned a couple of times in collaborator, do you have any favorite lessons or memories from your time working with him that continues to this day. But just even looking back through throughout your time working with him. [/INST] So one of the things he taught me was that when you're looking at uh a complex problem to to idealize it as much as possible to try and figure out what are really what is the essence of this problem and this is how like the copycat program uh came into being, was by taking analogy making and saying how can we make this as idealized as possible and still retain really the important things we want to study. And that's really kept you know, been a cora theme of my research I think and I continue to try and do that and it's really very much kind of physics inspired Hofstetter was a PhD in physics that was his </s><s>[INST] background like first principles kind of thinking like you're reduced to the most fundamental aspect of the problem so that you can focus on solving that fundamental [/INST] Yeah. And in a I you know that was people used to work in these micro worlds right? Like the blocks world was very early important area in ai and then that got criticized because they said, oh you know, you can't scale that to the real world. And so people started working on much more real world like problems, but now there's been kind of a return even to the blocks world itself. You know, we've seen a lot of people who are trying to work on more of these very idealized problems for things like natural language and um common sense. So that's an interesting evolution of those ideas </s>

<s>[INST] If anything, it's enhanced my career, I have a couple of questions on this. So, first of all, just a small comment on that I've realized that it feels like a lot of the progress in science is done by people pursuing an idea that another senior faculty would probably say this is going to hurt your career. I think it's actually a pretty good indicator that there's something interesting when when, when a senior wise uh person tells you this is gonna hurt your career. I think that's just the one as a small, if I were to give advice to young people. If somebody senior tells you this is gonna hurt your career. Um think twice about taking their advice. [/INST] Yeah, I mean, I think that's the primary thing, um and the other, I tell my own students, you know, I have a lab of about 2030 people and has been that big Since 1992 people. Come and go, is it's not the data that falls in line. That's that's so interesting. It's the it's the spot off the graph that you want to understand that. That's that's it you wanna when something is way off the graph. That's the interesting thing, because that's usually where discovery is. And the number of times that I've stopped people in my lab and said, wait a second, go back a few slides, What was that? And then it ended up being something interesting that made their careers. I could count on a few hands, </s><s>[INST] Yeah. Get excited by the extraordinary, that's outside of the thing that you uh that you've done in the past. Um Just on a personal psychological level is there, You know, I'm sure at stanford, I'm sure in you exploring some of these ideas, there's pressure. How do you um how do you not give into the pressure? How do you not give in to the people that say, like um that pushed you away from these topics, that what would you said shame. [/INST] I just point to my successes. I say what? You know, you're the one who told me not to start companies all this time ago. Uh you know, and now you're the one coming to me for advice for how to start a company right? Um but the from the scientific area it's it's you're wanting to take something off the table that might be an explanation. How how is that the scientific method? So you </s><s>[INST] reverse shame them reversing. So purely with reason through conversation you're able to do that. So it doesn't feel because to me it would just feel lonely. There's there's a community, there is a community of science and you know when you're working on something that's outside a particular Conventional way of thinking it can be lonely. I mean there's you know in the Ai field if you're working on neural networks in the 90s it could be lonely. [/INST] I have met some of the most fascinating people ever that had I stayed the conventional track I would never have met. I mean truly brilliant people because of this. So you know it is for those worried about well should I step outside of my comfort zone you're gonna meet some really interesting people and you know because I'm open about this area. You know I'll go and give a talk you know in boston Harvard or M. I. T. And at dinner inevitably this subject comes up and inevitably somebody else at the table will admit both that they're interested or that they've seen something and suddenly the whole tone of the conversation changes. It's kind of like there's safety in numbers and uh and then, or I've had people coming to me afterwards after dinner and say, hey, you know, I don't talk about this openly, but so the number of scientists who, who know that there's something else going on is much larger than the scientific community would like to </s><s>[INST] think that's a really powerful one, which is, I don't talk about this, you know openly, but here's what I believe. And you'd be surprised how many people speak like this and hold those beliefs and I am optimistic about social media and a more connected world to reveal more and more like us not to have these two personalities where like this public private one, we've mentioned the big questions of the origins of the universe. What do you think is the meaning of this whole thing for us? Humans, our human existence here on earth or just at the individual level of a human life? What Gary is the meaning of life? [/INST] I think that what we're going through today with this realization, it's uh, it's kind of like you've lived on an island your whole life and you've looked across the ocean and you've never imagined there was another island with anybody else on it. And then suddenly a ship with sails shows up. Uh you don't understand it, but you realize that suddenly your world just got a lot bigger. I think we're in one of those moments right now that our world view are galactic view is opening right to something a little bit bigger and not just that there might be somebody else, but that there's something else and what it is is yet to be understood. And the fact that it isn't understood to me is what's exciting because I can fill it with my dreams </s><s>[INST] and uh this discovery, our world might uh, it's about to get a lot more humbling and a lot more fascinating once we look out and realized we were on an island all along, [/INST] it makes us both smaller but larger at the same time. To me, you know, I I can look outside at the stars and think and imagine what else might be out there. And although I will I know that I will never see it all. It excites me to know that it's there. </s>

<s>[INST] that's that's why I played with stock fisher bunch. So I I got um I built for myself a bunch of different chess experiments recently, I had to do with the chess playing bot. But I also built the infinite chessboard. Where was stock fish was playing like an infinite number of chess games. And one of the parameters that was interesting to play with is how long it gets to think about a move and how that affects the rating of the thing [/INST] I did that a little bit. </s><s>[INST] So that that's a tricky one, I'm sure people know how to do that well, but it's tricky, it's not trivial to understand, like what there must be a good formula for it, but it's also interesting to think about like a controlled number of blunders, but it's probably better. The control number of blunders is not a good way to build a blot. [/INST] Yeah, it's for </s><s>[INST] training purposes, at least the [/INST] time the time per move is probably better, But the craziest thing is I did that a couple of my of my deaths were helping me with the build like, uh, I'm scaling my courses into a better chest learning platform essentially. We've done a lot of different experiments with stock fish, which I'm even happy to get into here. Um, and uh, stock fish making moves in .1 millisecond plays better than a human, which </s><s>[INST] is disgusting [/INST] and disturbing frankly, because that's crazy. Like you can't react to a car stopping in front of you anywhere near that fast. And yeah, </s><s>[INST] so the reason I was interested in that is because when you have a very large chessboard, you have tens of thousands, hundreds of thousands of games going on at the same time. You have the, the, like, think of the minimum amount of thinking to remove that you can allow for. And it does, it does, it's damn good, at least to my, I basically at the lowest possible setting you can give it. So yeah, it's incredible. It's incredible what bots are able to do and now it's as far as I know, as primarily machine learning based stock fish, stock fish moved to machine learning completely not doing search as far as I know. [/INST] Yeah, this is where you you lose me a bit. But the move, discovery and evaluation is what's been changing in the way starfish works. So it's discovering of moves and then the way it looks forward and then evaluates positions that has changed. But Matthew Sadler, who wrote the book, game changer about Alpha </s><s>[INST] Zero. Yeah, [/INST] that that he explains it significantly better, but that that's the way I think it works. </s><s>[INST] What did that make you feel when you first saw α zero play? [/INST] I was excited. I I didn't have any any sort of existential thoughts. I enjoyed watching it completely destroy openings that people thought were good. Uh And it it that experiment though has does have some caveat in the sense that I think Alpha Zero was playing with a full tank of servers and I think stock fish wasn't, which I think is what one of the things people point out, they weren't </s><s>[INST] playing since then they were able to demonstrate much [/INST] less </s><s>[INST] uh But also α zero stopped developing. Um they stopped developing it, [/INST] Yes, </s><s>[INST] which which sucks, but again from their perspective from deepmind perspective, it's like, alright, well, we took on this really, Turkey game did something honestly incredible. [/INST] They won, they won, I mean, </s><s>[INST] not just one, I mean they did it without any human supervision. So like without any training on human expert games, so only through self play, which I mean that's what learning is about, it's like that's what you think of as a child, a human child, a toddler learning from, [/INST] you </s><s>[INST] know, somewhat nothing and becoming a capable human. That's that's what we think of when we think about intelligence. So the fact that's able to play itself and become the best player in the world that at the game of go and all kinds of games is just incredible. And obviously that inspired the modern stock fish. Yeah. Now to do the same, all the same kind of self play methods. Uh, somebody on Reddit ask a pretty interesting question. [/INST] I </s><s>[INST] don't know if you have an interesting answer to it. What makes the chess move, quote unquote human as you are someone? Oh, this is to me, but it's mentioned you in third person as you are someone working in ai this idea of humanness would seem incredibly interesting. Yes sir, it is, especially since most cheat detection relies on humanness as a way to detect cheaters. I think since Children being born right now will have the advantage of engine training their whole life, they will start to see the game the way an engine does. Will a person be considered a cheater if they play like an engine, there also seems to be a discrepancy, especially with levy about who can play, what appears to be a non human move. He often says things like quote, if you were a normal player, normal in quotes, if you were a normal player, I would think you were cheating. But since it's magnus, I don't doubt magnus is great, but if humanness is our benchmark, what is the elo rating, where your moves can start to look like an engine without critique? There's a bunch of questions in there, [/INST] they combined two of my quotes into one. So one thing that I like to say is sometimes in a chess game moves, look or an opening look so ridiculous that if a viewer played it, I would make fun of them or slap them. That's always there. If I was your chest coach, I smack you. But when magnus plays, it was, oh wow, you know, it's a very different. So they mixed up this quote with another quote, which is uh you know, if, if I, if I'll be explaining something and I'll say, oh and here, the engine says you should play like this. If one of your opponents plays like this, report them for cheating, they fuse two quotes. They said, oh human can't play like that. But because it's an engine move, but because magnus is playing, so they mixed kind of two things </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] That's a really compelling notion. But how does that help you arrive [/INST] coming to where the book came from? </s><s>[INST] Yes. [/INST] So what got me, I worked on string theory. I also worked on loop quantum gravity and I was one of the inventions of loop quantum gravity and because my strong belief in some other principles which lead to this notion of wanting a quantum theory of gravity to be what we call relational or background independent. I tried very hard to make string theory background independent and in and up developing a bunch of tools which then could apply directly to general relativity and that became loop quantum gravity. So the things were very closely related and have always been very closely related in my mind. The idea that there were two communities, one devoted to strings and when developed two loops is nuts and there's always been nuts. </s><s>[INST] Okay. So so anyway there's this nuts community of loops and strings that are all beautiful and compelling and mathematically speaking. And what's the trouble with all that? Why is that why is that such a problem? [/INST] So what? So I was interested in developing that notion of how science works based on the community and ethics that I told you about. And I wrote a draft of a book about that which had several chapters on methodology of science and it was rather academically oriented book. And those chapters were the first part of the book, the 1st 3rd of it. And you can find their remnants and was now the last the last part of the trouble with physics. And then I described a number of test cases, case studies and one of them which I knew was the search for quantum gravity and string theory and so forth. And I wasn't able to get that book published. So somebody made the suggestion of flipping it around And starting with the story of string theory which was already controversial. This was 2004, But I was very careful two be detailed to criticize papers and not people you don't you want to find me criticizing individuals, you'll find me criticizing certain writing. But in any case, here's what I regret. Let me make your program with while, as far as I know with the exception of not understanding how large the applications to condense the managers say of A D M C F A DSC ft will get. I think largely my diagnosis of string theory as it was then has stood up since 2006 when I regret is that the same critique I was using string theory as an example and the same critique applies to many other communities in science you know of including and this is what I regret. My own community. That is a community of people working on quantum gravity aside string theory, but and I considered saying that explicitly, but they say that explicitly, since I'm it's a small, intimate community, I would be telling stories and naming names of and making a kind of history that I have no right to write. So I stayed away from that but was misunderstood. </s><s>[INST] But if I may ask, is there a hopeful message for theoretical physics that we can take from that book sort of that looks at the community, not just your your own work on not with causality and non locality, but just broadly in understanding the fundamental nature of our reality. What's your hope for the 21st century in physics [/INST] that was well, do we solve the problem </s><s>[INST] that we solved the unfinished problem of Einstein's? [/INST] That's certainly the thing that I care about most in hide from us. Let me say one thing among the young people that I work with, I hear very often in sense a total of this interest in these arguments that we older scientists have and an interesting way each other is doing and this is starting to appear in conferences where the young people interested in quantum gravity make a conference. May invite loops and strings and causal dynamical triangulation and causal set people and we're having a conference like this next week, a small workshop at perimeter and I guess I'm advertising this and then the summer we're having a big full on conference which is just quantum gravity. It's not strings, it's not loops but the organizers and the speakers will be from all the different communities and this to me is very helpful </s><s>[INST] that the different ideas are coming together [/INST] at least people are expressing an interest in that. Yeah, </s><s>[INST] is a huge honor to talking to you lee thanks so much for your time today. Thanks for listening to this conversation and thank you to our presenting sponsor, cash app, Download, it use collects podcast, you'll get $10.10 will go to first, an organization that inspires and educates young minds to become science and technology innovators of tomorrow. If you enjoy this podcast, subscribe on Youtube, give it five stars on Apple podcast. Follow on Spotify, supported on Patreon are simply connect with me on twitter Elex Friedman and now let me leave you with some words from lee Smolin. One possibility is God is nothing but the power of the universe to organize itself. Thanks for listening and hope to see you next time. [/INST] </s>

<s>[INST] you think there was [/INST] pretty like once life </s><s>[INST] on MArs or do you think there's currently, [/INST] I'm more comfortable saying probably 3.5 billion years ago. I feel pretty confident there was life on Mars just because then it had an electromagnetic shield. It had an atmosphere has a wonderful gravity level 33 H. G. Is fantastic. You know, you're super human human. We can all slam dunk in basketball. It's going to be fun to play sports on wires. But so I think we'll find past the fossilized. Probably the evidence of past life on MArs. Currently that's again we need the next decade. The evidence is mounting for sure. We do have the organics. We're finding organics. We have water, seasonal water on MArs we used to just know about the ice caps, North and South pole. Now we have seasonal water. We do have the building blocks for life on MArs. We really need to dig down into the soil because everything on the top surface is radiated. But once we find down, will we see any any life forms? We see any bugs. I leave it open as a possibility. But I feel pretty certain that past life or fossilized life forms will find. And then we have to get to all these ocean worlds. These these beautiful moons of other planets since we know they have water. And we're looking for a simple search for life follow the water. Carbon based life. That's the only life we know there could be other life forms that we don't know about, but it's hard to search for them because we don't know. So, in our search for life in the solar system is definitely, you know, search follow the water and look for the building blocks of life. </s><s>[INST] Do you think in the next decade we might see hints of past life or even current [/INST] life? That's a pretty optimism. I'm pretty active. </s><s>[INST] Humans have to be involved or can this be robots and rovers And [/INST] Probably teams. I mean we've been at it on Mars in particular. 50 years. We've been exploring Mars for 50 years. Great data. Right. Are images of Mars today are phenomenal. Now we know how Mars lost its atmosphere are starting to know because of the Lack of the Electromagnet Shield. We know about the watermarks. So we've been studying 50 years with our robots. We still haven't found it. So I think once we have a human mission there we just accelerate things and it's always humans and our rovers and robots together. But we just have to think that 50 years we've been looking at mars mars and um taking images and doing the best science that we can. People need to realize MArs is really far away. It's really hard to get to this extreme extreme exploration. We mentioned Magellan first or all of the wonderful explorers and sailors of the past, which kind of a lot of my inspiration for exploration, mars is a different ball game. I mean eight months to get there a year and a half to get home. I mean it's really </s><s>[INST] extreme environment in all kinds of ways. But the kind of organism might be able to see hints off on MArs are kind of microorganisms perhaps [/INST] remember that humans were kind of were host, right? Were host to all of our bacteria and viruses. Right. Do </s><s>[INST] you think it's a big leap from the viruses and the bacteria to us humans. Put another way do you think on all those moons, beautiful wet moons that you mentioned. You think there's intelligent life out there? [/INST] I hope so. I mean that's that's the hope. But you know, we don't have the scientific evidence for that now. I think all the evidence we have in terms of life existing is much more compelling again because we have the building blocks of life. Now when that life turns into intelligence, that's a big unknown. </s><s>[INST] If we ever meet, do you think we would be able to find a common language? [/INST] I hope so. We haven't met yet. It's just so far. I mean, do physics display a role here? Look at all these exoplanets, 6000 exoplanets. I mean even the couple dozen earthlike planets or exoplanets that really look like habitable planets. These are very earth like they look like they have all the building blocks. I can't wait to get there. The only thing is they're 10-100 light years away. So scientifically, we know they're there, we know that their habitable they have, you know, everything going from right, you know, called the goldilocks zone. Not too hot, not too cold. Just perfect for how habitability for life. But now the reality is if there are 10 at the best 200 to thousands of light years away. So what's out there, but I just can't think that we're not the only one. So absolutely life life in the universe. Probably intelligent life as well. </s><s>[INST] Do you think there needs to be fundamental revolutions and how we the tools we use to travel through space in order for us to venture outside of our solar system? Or do you think the ways the rockets, the ideas we have now, the engineering ideas we have now will be enough to venture out? [/INST] Well that's a good question right now because the speed of light is the limit. We don't have warp speed warp drive to explore our solar system to get to MArs to explore all the planets. Then we need technology push. But technology push here is just advanced propulsion would be great if I could get humans to MArs and say you know, 3 to 4 months, not eight months. I mean have the time. 50% reduction. That's great in terms of safety and wellness of the crew, orbital mechanics. Physics rules, you know, orbital mechanics are still physics rules. We can't defy physics </s>

<s>[INST] Okay, wait a minute. Did you just say that you think in terms of likelihood life started [/INST] on Mars, statistically speaking, life started on Mars and seeded Earth? It could be possible because Mars was habitable for the type of life that we have right now, type of chemistry before Earth. It seems to me that Mars got searching doing chemistry. It started way before. Yeah, and so they had a few more replicators and some other stuff. And if those replicators got ejected from Mars and landed on Earth, an Earth would be like, I don't need to start again. Thanks for that. And then it just carries on. I think we will find evidence of life on Mars, either life we put there by mistake, contamination, or actually the earliest remnants of life. And that would be really exciting. It's a really good reason to go there. But I think it's more unlikely because of the gravitational situation in the solar system if we find life in the outer solar system. </s><s>[INST] It started way before, right? Titan and all that. That would be its own thing. Exactly. Wow, that'd be so cool. If we go to Mars and we find life that looks hella-lot similar to Earth life, and then we go to Titan and all those weird moons with the ices and the volcanoes and all that kind of stuff, and then we find there something that looks, I [/INST] know, way weirder. Yeah. Some other, some non-RNA type of situation. But we might find almost life like in the prebiotic chemical space. And I think there are four types of exoplanets we can go look for, right? Because when JWST goes up and touch wood, it goes up and everything's fine. When we look at a star, well, we know statistically most stars have planets around them. What type of planet are they? Are they going to be dead? Are they going to be just a prebiotic origin of life coming? So are they going to be technological? And, you know, so we have intelligence on them and will they have died? So, you know, from, you know, had life on them. Those are the four states. And so, and suddenly it's a bit like I want to classify planets the way we classify stars. Yeah. And I think that in terms of rather than having this, oh, we've found methane, there's evidence of life. We've found oxygen, that's the evidence of life. We've found whatever molecule marker and start to then frame things a little bit more. </s><s>[INST] Those are the four states of states, which by the way, you're just saying four, but there could be, [/INST] before the dead, there could be other states that we humans can't even conceive of. Just prebiotic, almost alive, you know, got the possibility to come alive. </s><s>[INST] I think there could be a post-technological, like whatever we think of as technology, there could be a like pre-conscious, like where we all meld into one super intelligent conscious [/INST] or some weird thing that naturally happens over time. Yeah. I mean, I think that all </s><s>[INST] better than the metaverse. Yeah, we are. We join into a virtual metaverse and start creating, which is kind of an interesting idea, almost arbitrary number of copies of each other, much more quickly to can mess with different ideas in mind. Like I can create a thousand copies of Lex, like every possible version of Lex, and then just see like, and then I just have them like argue with each other and like until like in the space of ideas and see who wins out. How could that possibly go wrong? But anyway, but there's, especially in this digital space where you could start exploring with AIs mixed in, you could start engineering arbitrary intelligences. You can start playing in the space of ideas, which might move us into a world that looks very different than a biological world. Like our current world, the technology is still very much tied to our biology. It's, we might move past that completely. Oh, definitely. We definitely will. We definitely, because that could be another phase then. Sure. Because then [/INST] you, but we definitely will. But I did say technological. So I think I agree with you. I think so. You can have, let's get this right. So dead world, no prospect of life. Prebiotic world, life emerging, living and technological, and you probably, and the dead one, you probably won't be able to tell between the dead never been alive and the dead one. Maybe you got some artifacts and maybe there's five, there's probably not more than five. And I think the technological one could allow, could have life on it still, but it might just exceeded because, you know, one way that life might survive on earth is if we can work out how to deal with the coming, the real climate change that comes when the sun expands. There might be a way to survive that, you know? But yeah, I think that we need to start thinking </s><s>[INST] statistically when it comes to looking for life in the universe. Let me ask you then, sort of statistically, how many alien civilizations are out there in those four phases that you're talking about? When you look up the stars and you're slipping on some wine and talking to other people with British accents about something intelligent and intellectual, I'm sure. [/INST] Do you think there's a lot of alien civilizations looking back at us and wondering the same? My romantic view of the universe is really taking loans from my logical self. So what I'm saying is I have no doubt, I have no idea. But having said that, there is no reason to suppose that life is as hard as we first thought it was. And so if we just take earth as a marker, and if I think that life is a much more general phenomena than just our biology, then I think the universe is full of life. And the reason for the Fermi paradox is not that they're not out there, it's just that we can't interact with the other lifeforms because they're so different. And I'm not saying that they're necessarily like hasn't depicted in Arrival or other, you know, I'm just saying that perhaps there are very few universal facts in the universe. And that and maybe that is not, it's quite hard, our technologies are quite divergent. And so I think that it's very hard </s>

<s>[INST] My body, just every part is just like hot and it feels so [/INST] good to return </s><s>[INST] from that run and to sort of celebrate and to break the fast with the cold athletic greens and then I go to the shower and so on. But I've been really enjoying that kind of ritual and obviously I also drink a lot of greens later on in the day. Another dose. I just love the way taste and it's, it's really good for you to establish a nice nutritional base anyway when you sign up, they'll also give you a one month supply of fish oil. If you go to athletic greens dot com slash lex. That's athletic greens dot com slash lex. This episode is also brought to you by better help spelled H [/INST] E L. P. Help, </s><s>[INST] They figure out what you need and match you with a licensed professional therapist in under 48 hours. Just a couple of hours ago. I actually had a hard Trading session, 10 live rounds of I think six minutes each. I try not to look up at the clock when you're doing the hard training Craig Jones was there got to talk before him, hang out. He's awesome, awesome. One of the best grapplers in the world, also one of the [/INST] funniest great human </s><s>[INST] being Gabe Tuttle that runs, he's had instructor of 10 planet Austin is a really great human being as well and and a great competitor and grappling teacher. So anyway, I bring that up to say that uh for me, jujitsu and grappling is a kind of therapy, but I also believe that there's some things that grappling can't solve and uh that requires, I think sort of rigorous talk therapy and so services that make that like frictionless, it's easy for you to find a therapist I think is worth a try. Better help is easy, private affordable, available worldwide. Check them out at better health dot com slash lex as better help dot com slash lex. This episode is sponsored by on it, nutrition supplement and fitness company. They make alpha brain, which is a new tropic that helps support memory, mental speed and focus. I keep kind of switching up my rituals in terms of when I do the really sort of deep work, deep focus session because there's been a few chaotic demands on my schedule has been harder to find earlier in the day, A four hour or five hour segment where I can do deep work. But when I do, even if it's later in the day and I really need to do something difficult or just kind of have to silence the rest of the world and focus my mind. I'll take an alpha brain just as a kind of little boost to help me out. Anyway, go to lex Friedman dot com slash on it to get up to 10% off of alpha brain. That's lex Friedman, that's my name dot com slash on it. That link should forward you to the right place. This is a lex Friedman podcast and here's my conversation with matt walker. [/INST] You should try these shades on and see what you look like. So they are now your shades. </s><s>[INST] That's not the question is the same thing as uh Putin took the super bowl ring and it's not his ring. Yeah. [/INST] one wonders if he was offered it, but they are yours. When </s><s>[INST] did you first fall in love with dream of understanding sleep? Like where did the fascination asleep begin? [/INST] So, back in the United Kingdom, you can sort of start doing medicine at aged 18. And it's a five year program. And I was at the Queen's Medical Centre in the UK and I remember just being fascinated by states of consciousness and particularly anesthesia, I think isn't that within seconds I can take a perfectly conscious human being and I can remove all existence of the mentality and their awareness within seconds. And that stunned me. So I started to get really interested in conscious states. I even started to read a lot about hypnosis. Um, and all of these things hypnosis. Even sleep and dreams at the time. They were very esoteric. It was sort of charlotte and science at that stage. And I think almost all of my colleagues and I are accidental sleep researchers. You know, no one, as I recall in the classroom when you're sort of five years old and the teacher says, what would you like to be when you grow up? You know, no one's putting their hand up and saying, I would love to be a sleep researcher. Um, and so when I was doing my PhD, I was trying to identify different forms of dementia very early on in the course and I was using electrical brainwave recordings to do that. And I was failing miserably. It was a disaster, Just no result after no result. And I used to go home to the doctors residents with this sort of little igloo of journals that at the weekend I would sort of sit in and uh, and read and which I'm now thinking, do I really want to admit this? Because it sounds like I had no social life, which I didn't have a social leper. But, and I started to realize that some parts of the brain were, um, sleep related areas and some dimensions were eating away those sleep related areas, other dimensions would leave them untouched. I thought, well, I'm doing this all wrong. I'm measuring my patients while they're awake instead of should be measuring them while they're asleep, started doing that. Got some amazing results. And then I wanted to ask the question is that sleep disruption that my patients are experiencing as they go into dementia? Maybe it's not a symptom of the dementia. I wonder if it's a cause of the dementia. And at that point, which was cough cough 20 years ago, um no one could answer a very simple fundamental question. Why do we sleep? And I, at the time didn't realize that some of the most brilliant minds in scientific history had tried to answer that question and failed. And at that point I just thought, well, I'm going to go and do a couple of years of sleep research and I'll figure out why we sleep. And then I'll come back to my patients in this question of dementia. And as I said, that was 20 years ago. And what I realized is that hard questions curve very little about who asks them? They will meet her out their lessons of difficulty all the same. And I was schooled in the difficulty of the question, why do we sleep? But in truth, 20 years later, we've had to upend the question rather than saying why do we sleep? And by the way, the the answer then was that we sleep to cure sleepiness. Which is like saying, you know, we eat to cure hunger. That tells you nothing about the physiological benefits of food. Same with sleep. Now we actually have to ask the question, is there any physiological system in the body or any major operation of the mind that isn't wonderfully enhanced when we get sleep or demonstrably impaired when we don't get enough and so far. For the most part, the answer seems to be now. </s><s>[INST] So far. The answer seems to be no. So why why does the body and the mind crave sleep then why do we sleep? How [/INST] you know, </s><s>[INST] can we begin to answer that question then? [/INST] So I think one of the ways that I think about this or one of the answers that came to me is the following, the reason that we implode so quickly and so thoroughly with insufficient sleep is because human beings seem to be one of the few species that will deliberately deprive themselves of sleep for no apparent good reason. Biological right. And what that led me then to was the following mother nature as a consequence. So no other species does what we do in that context. There are a few species that do undergo sleep deprivation, but for very obvious clear biological reasons. One is when they're in a condition of severe starvation. The second is when they're caring for their newborn. So for example, killer whales will often deprive themselves, the female will go away from the pod, give birth and then bring the calf back and during that time the mother will undergo sleep deprivation. And then the third one is during migration when birds are flying trans oceanographic to 3000 miles. But for the most part it's never seen in the animal kingdom. Which brings me back to the point. Therefore, mother nature in the course of evolution has never had to face the challenge of this thing called sleep deprivation and therefore she has never created a safety net in place to circumnavigate this common influence. And there is a good example where we have which is called the adipose cell, the fat cell because during our evolutionary past we had famine and we had feast and mother nature came up with a very clever recipe which is how can I store caloric credit so that I can spend it when I go into debt. And the fat cell was born brilliant idea where is the fat self asleep? Where is that sort of banking chip for sleep? And unfortunately we don't seem to have on because she's never had to face that challenge. </s><s>[INST] So even if there's not some kind of physics fundamental need for sleep that physiologically or psychologically the fact is most organisms are built such that they need it. And then mother nature never built an extra mechanism for sleep deprivation. So it's interesting that why we sleep might not have a good answer, but we need to sleep to be healthy is nevertheless true. [/INST] Yeah. And we have many answers right now in some ways, the question of why we sleep was the wrong question to its, you know, what are the pleura potent? Many reasons we sleep. We don't just sleep for one reason because from an evolutionary perspective, it is the most idiotic thing that you could imagine. You know, when you're sleeping, you're not finding a mate, you're not reproducing, you're not caring for your young, you're not foraging for food and were still, you're vulnerable to predation. So, on any one of those grounds, especially as a collective sleep should have been strongly selected against in the course of evolution. But in every species that we've studied carefully to date, sleep is present. </s><s>[INST] So it is important. So like you're you're right, I think I've heard arguments from an evolutionary biology perspective that sleep is actually advantageous. You know, maybe like some kind of predator prey relationships, but you're saying it actually makes way more sense. What you're saying is it should have been selected against like why close your eyes. [/INST] Yeah, Why? Because and you know, there was an energy conservation hypothesis for a while which is that we need to essentially go into low battery mode power down because it's unsustainable, but in fact that actually has been blasted out the water because sleep is an incredibly active process. In fact the difference between you just lying on the couch, but remaining conscious versus you lying on the couch and falling asleep. It's only a savings of about 140 150 calories. In other words, you know, you just go out and club another baby seal or whatever it was and you wouldn't worry, you know, so it has to be much more to it than energy conservation, much more to it than sharing, you know, ecosystem space and time. Much more to it than simply predator prey relationships. If sleep really did. And you know, looking back even very old evolutionary organisms like earthworms millions of years old, they have periods where the active and periods where there passively asleep. It's called lethargic us. And so what that in some ways suggested to me was sleep evolved with life itself on this planet and then it has fought its way through heroically every step along the evolutionary pathway which then leads to the sort of famous sleep statement from a researcher that if sleep doesn't serve an absolutely vital function or functions, then it's the biggest mistake. The evolutionary processes have a maid and we've now realised mother nature didn't make a spectacular blunder with sleep. </s><s>[INST] You've mentioned the idea of conscious states. Do you think of sleep as a fundamentally different conscious state than awake this? And how many conscious states are there sort of when you're into it? Your understanding of what the mind can do. Do you think awake state sleep state or is there some kind of continuum. There's a complicated state transition diagram. Like how do you think about this whole space? [/INST] I think about it as a state space diagram and I think it's probably more of a continuum than we have believed it to be or suggested it to be. So we used to think absence of anesthesia that there were really three main states of consciousness that was being awake, being in non rapid eye movement, sleep or non dream sleep and then being in rapid eye movement, sleep or dream sleep. And those were the three states within which your brain could percolate and be conscious. You know conscious during non rem sleep is maybe a stretch to say. But I still believe there is plenty of consciousness there. I don't believe that anymore. And the reason is because we can have daydreams and we are in a very different wakeful state in those daydreams than we are when we are as we are now together, present and extra cep tive lee focused rather than introspectively focused. And then we also know that as you are progressing into those different stages of sleep during non rem sleep you can also still dream, depends on your definition of dreaming but we seem to have some degree of dreaming and almost all stages of sleep. We've also then found that when you are sleep deprived there even individual brain cells will fall asleep despite the animal being you know behaviorally from best we can tell a week individual brain cells and clusters of brain cells will go into a sleep like state. And humans do this too when we are sleep deprived we have what are called micro sleeps where the eyelid will partially close and the brain essentially falls lapses into a state of sleep. But behaviorally you seem to be awake and the danger here is road traffic accidents. So these are the what we call these sort of micro sleep events at the wheel. Now if you're traveling at 65 miles an hour in a two ton vehicle, you know, it takes probably around one second to drift from one lane to the next and it takes two seconds to go completely off the road. So if you have one of these micro sleeps at the wheel, you know it could be the last micro sleep that you ever have. Um But I don't now see it as a set of you know, very binary, distinct you know, step function state. It's not a one or a zero. I see it more of a as a continuum. </s><s>[INST] So I've for for 5 6 years at M. IT really focused on this human side of driving question. And one of the big concerns is the micro sleeps drowsiness. These kinds of ideas. And one of the open questions was is it possible to computer vision to detect or any kind of sensors then I think about computer vision is you don't have to have direct contact to the person. Is it possible to detect increases in drowsiness? Is it possible to detect these kind of micro sleeps or actually just sleep in general? Among other things that distraction. These are all words that have so many meetings that so many debates like, like attention is as a whole, another one. Just because you're looking something doesn't mean you're loading in the information just because you're looking away doesn't mean your peripheral vision can't pick up the important information. There's so many complicated vision science things there. Um So I wonder if you could say something to uh you know, they say the eyes are the windows to the soul. Do you think um the eyes can reveal something about uh sleepiness uh through uh the computer vision, just looking at the video of the face. And Andrew Huberman and your friend have talked about this. I would love to work on this together. Should do. It's a fascinating problem. What drowsiness is a trick you want? So there's what kind of information there's a blinking and there's eye movement and those are the ones that can be picked up with computer vision. Do you think those are signals that could be used to say something about where we are in this continuum? [/INST] Yeah, I do. And I think there are a number of other features to I think um you know, aperture of I so in other words, partial closures, foreclosures, duration of those closures, duration of those partial closures of the eyelid. Um, I think there may be some information in the pupil as well because as we're transitioning between those states change. There are changes in what's called the automatic nervous system or technically it's called the autonomic nervous system part of which will control your pew pillory size. So I actually think that there is probably a wealth of information when you combine that probably with aspects of steering, angle, steering maneuver And if you can sense the pressure on the pedals as well. My guess is that there is some combinatorial feature that creates a 15 a type of you are starting to fall asleep and as the autonomous controls develop that it's time for them to kick in. Some manufacturers, auto manufacturers sort of have something beater version of maybe an alpha version of of this already starting to come online where they have a little camera in the wheel that I think tries to look at some features, </s><s>[INST] almost everybody doing this and it's very alpha. Uh, so, uh, you know, the thing that you currently have, some people have that in their car, there's a coffee cup or something that comes up that you might be sleeping. The primary signal that they're comfortable using is a steering wheel reversals. So, so basically using your interaction with the steering wheel and how much you're interacting with it as a sign of sleeping it. So if you have to constantly correct the car, that's a sign of like you starting to drift into micro sleep. I think that's a very, very crude signal. It's probably a powerful one. There's a whole another component to this which is, it seems like it's so driver and subject dependent. Uh the how our behavior changes as we get sleepy and drowsy seems to be different and complicated, fascinating ways where you can't just use one signal, it's kind of like what you're saying. There has to be a lot of different signals that you should then be able to combine. The hope is there's uh the searches for like Universal signals that are pretty damn good for like 90% of people. [/INST] But I don't think we need to take necessarily quite that approach. I think what we could do in some clever fashion is Using the individual. So what you and I are perhaps suggesting here is that there is an array of features that we know provide information that is sensitive to whether or not you're falling asleep at the wheel. Some of those let's say that there are 10 of them, you know, for me, seven of them are the cardinal features for you. However, you know, six of them and they're not all the same sort of overlapping are those for you? I think what we need is algorithms that can firstly understand when you are well slept. So let's say that people have sleep trackers at night and then your car integrates that information would be amazing, understands when you are well slept. And then you've got the data of the individual behavior unique to that individual snowflake, like when they are well slept, this is the signature of well rested driving. Then you can look at deviations from that and patent match it with the sleep history of that individual and then I don't need to find The sort of, you know, the one size fits all approach for 99% of the people. I can create very bespoke tailor like set of features, the Saville row suit of sleepiness features, you know, that would be like if you want to ask me about moonshots and crazy ideas, that's where I go. But to start with, I think your approach is is a great one. Let's find something that covers 99% of the people because the worrying thing about micro sleeps of course, unlike, you know, drugs or alcohol, which you know certainly is a terrible thing to be behind the wheel with those often you you react too late and that's the reason you get into an accident when you fall asleep behind the wheel, you don't react at all. At that point, there is a two ton missile driving down the street and no one's in control. That's why those accidents can often be more dangerous. </s><s>[INST] Yeah. And uh, the fascinating thing is in the case of semi autonomous vehicles like Tesla's autopilot. This is where I've had disagreements with Mr Elon musk is uh, and the human factors community, which is this community that one of the big things they study is a human supervision over automation. Do you have like pilots, you know, supervising an airplane that's mostly flying autonomously? The question is when we're actually doing the driving, how do micro sleeps or general, how does drowsiness progress and how does it affect our driving? That question becomes more fascinating, more complicated when your task is not driving but supervising the driving. So your task is to take over when stuff goes wrong and that it's complicated. But the basic conclusions from many decades is that humans are really crappy at supervising because they get they get drowsy and lose vigilance much much faster. The really surprising thing which has the autopilot, it was surprising to me surprising to uh, the human factors community and in fact they still argue with me about it is it seems that humans in Tesla with autopilot and other similar systems are not becoming less vigilant, at least the studies we've done. So there's something about the urgency of driving, I can't, I'm not sure why, but there's something about the risk, I think the fact that he might die uh, is still keeping people awake. The question is as Tesla autopilot or similar systems get better and better and better. How does that affect increasing drowsiness and that's when you need to have, that's where the big disagreement was. You need to have drivers sensing meaning, driver facing camera that tracks some kind of information about the face that can tell you uh draws in it. So you can tell the car if you're drowsy so that the car can be like, you should be probably driving or pull to the side, [/INST] right? Or I need to do some of the heavy lifting here. Yeah. </s><s>[INST] So there needs to be that dance of interaction really of human and machine, but currently it's mostly uh steering wheel based. So, you know, this this idea that your hands should be on the, on the steering wheel, that's a sign that you're paying attention is um is an outdated in a very crude [/INST] metric? I agree. Yeah, I think there are far more sophisticated ways that we can solve that problem if we invest </s><s>[INST] casco big philosophical question before we get into fun details um, on the topic of conscious states, how fundamental do you think is consciousness to the human mind? I asked this from almost like a robotics perspective. So, in your study of sleep, do you think the hard question of consciousness that it feels like something to be us? Is that like a nice little feature, like a, like a, like a quirk of our mind or is it somehow fundamental because sleep feels like we take, we take a step out of that consciousness a little bit. So from all your study asleep. Do you think consciousness is like deeply part of who we are? Or is it just a nice trick? [/INST] I think it's a deeply embedded feature that I can imagine has whole panoply of biological benefits. But to your point about sleep, what is interesting if you do a lot of dream research and we've done some it's very, very rare at all. In fact, for you to end up becoming someone other than who you are in your dreams. Now, you can have third person perspective dreams where you can see yourself in the dream as if you're sort of, you know, you've risen above your your physical being. But for the most part, it's very rare that we lose our sense of conscious self and maybe I'm sort of doing a sleight of hand because it's really what I'm saying is it's very rare that we lose our sense of who we are in dreams, we never do now. That's not to suggest that dreams are utterly bizarre. And I mean, you know, when you slept last night, which I know may have been perhaps a little less than than me, but when you went into dreaming, you know, you became flagrantly psychotic and there are five essentially good reasons, firstly you started to see things which were not there. So you were hallucinating second, you believe things that couldn't possibly be true. So, you were delusional third, you became confused about time and place and person. So you're suffering from what we would call disorientation. Fourth, you have wildly fluctuating emotions, something that psychiatrists will call being effectively label and then how wonderful you woke up this morning and you forgot most, if not all, of that dream experience. So you're suffering from amnesia, you had to experience any one of those five things while you're awake, you would probably be seeking psychological help. But so I placed that as a backdrop against your astute question because despite all of that psychosis, there is still a present self nested at the heart of it, meaning that I think it's very difficult for us to abandon our conscious sense of self. And if it's that hard, you know, the old adage in some ways that you can't outrun your shadow. But here it's more of a philosophical question which is about the conscious mind and what the state of consciousness actually means in a human being. So, I think that that to me, you can he become so dislocated from so many other rational ways of waking consciousness. But one thing that won't go away that won't get perturbed or sort of, you know, manic old is this your sense of conscious self? </s><s>[INST] Yeah, there's a strong sign that consciousness is fundamental to the human mind. Um or we're just creatures of habit. We've gotten used to having consciousness. Maybe it just takes a lot of uh either chemical substances or a lot of like mental work to escape that, [/INST] I mean, it's like trying to launch a rocket, you know, the energy that has to be put in to create escape velocity from the gravitational pull of this thing called planet Earth is immense. Well the same thing is true for uh for us to abandon our sense of conscious self, the amount of biological amount of substances, the amount of wacky stuff that you have to do to truly get escape velocity from your conscious self. What does that tell us about then? The fundamental state of our conscious self? </s><s>[INST] Yeah, it also probably says that that uh it's quite useful to have consciousness for uh for survival and for just operation in this world. And perhaps for intelligence, I'm one of the on the ai side people that think that uh intelligence requires consciousness. So like high levels of general intelligence requires consciousness. Most people, in a way I feel think like consciousness and intelligence are fundamentally different. You can build a computer that super intelligent, it doesn't have to be conscious. I think that if you define super intelligence by being good at chess. Yes, but if you define super intelligence is being able to operate in this living world of humans and be able to perform all kinds of different tasks, CONSCIOUSNESS, it seems to be some more fundamental to uh like to to to richly integrate yourself into the human experience into society. It feels like you have to be a conscious being. But then we don't even know what consciousness is and we certainly don't know how to engineer it in our machines. [/INST] I love the fact that there are still questions that are so embryonic because you know, I suspect it's the same with you. Answers to me are simply ways to get two more questions. It's questions where questions turn me on answers less. So. And I love the fact that we are still embryonic in our sense of arguing about even what the definition of consciousness is. But I also find it fascinating. I think it's thoroughly delightful to absorb yourself in the thought, think about the brain and we can move back across the complexity of file a genie from you know, humans to mammals to sort of birds, to reptiles, amphibians, fish and you can bacteria, whatever you want and you can go through this and say, ok, where is the hard line of you know what we would define as consciousness And and I'm sure it's got something to do with the complexity of the neural system of that? I'm fairly certain but to me it's always been fascinating. So what is it then? You know, is it that I just keep adding neurons to a Petrie dish? And I just keep adding them and adding them and adding them at some point when I hit a critical mass of interconnected neurons. That is the mass of the you know, the interconnected human brain then bingo all of a sudden it kicks into gear and we have consciousness </s><s>[INST] like a phase shift, phase transition of some [/INST] kind, correct? Yeah, But there is something about the complexity of the nervous system that I think is fundamental to consciousness and the reason I bring that up is because when we're trying to then think about creating it in an artificial way, does that informers as to the complexity that we should be looking at in terms of development? I also think that it's a missed opportunity in the sort of digital space for us to try to recreate human consciousness. We've already got human consciousness. What if we were to think about creating some other form of? Why do we have to think that the ultimate in the creation of, you know, an artificial intelligence is the replication, you know, of a human state of consciousness. Can we not think outside of our own consciousness and believe that there is something even more incredible or more complimentary, more orthogonal. Um, sometimes sometimes perplex that people are trying to mimic human consciousness rather than think about creating something that's different. </s><s>[INST] Yeah, I think of human consciousness or consciousness in general, is this magic, uh, super power that allows us to deeply experience the world. And just as you're saying, I don't think that superpower hesitate the exact flavor as humans have. That's my love for robots. I would love to add the ability to robots that can experience the world and other humans deeply. I'm humbled by the fact that that idea does not necessarily need to look anything like how humans experience the world, but there's a dance of human to robot connection the same way human to dog or human to cat connection. That there's a there's a there's a magic there to that interaction and I'm not sure how to create that magic, but it's a worthy effort. I also love just exactly as you said on the question of consciousness or engineering consciousness. The fun thing about this problem is it seems obvious to me that 100 years from now, no matter what we do today, uh people were still hear will laugh at how silly our notions were. So like it's almost impossible for me to imagine that we will truly solve this problem fully in my lifetime. And more than that everything will do will be silly 100 years from now. But it's still a work that makes it fun to me because it's like you have the full freedom to not even be right just to try just to try his freedom. And uh and I that's how I see [/INST] that t shirt please. </s><s>[INST] I love that. So, and you know, human robot interaction is fascinating because it's like, it's like watching dancing, I've been uh dancing tango recently and just it's like there is no goal. The goal is to create something magical and uh whether consciousness or emotion or elegance of movement, all of those things, uh, aid in the creation of the magic and it's a free, it's, it's an art form to explore how, how to make that had to create that in a way that's compelling. Yeah, [/INST] I love the line in scent of a woman with al pacino where he's speaking about the tango and he said really, it's just freedom that if you get tangled up, you just keep tang going on. </s><s>[INST] I still to this day, I think, uh, first, the second time I talked to joe Rogan on this podcast, I said, we got into a heated argument about whether um, scent of a woman is a better movie than john Wick because it's one of my favorite movies for many reasons. One is sensible, sensible woman. Uh, partially know that by the way, you just didn't know if you would actually know awesome, awesome. Yeah. I said, I love the tango scene. I love opportunities, performance, that's a wonderful movie. Then joe joe was saying john Wick is better. So we, to this day, argue about this. I [/INST] think it depends on what conscious state you're in, that you would be ready and receptive to. But um, sensible man. I think it has one of the best monologues at the end of the movie that has ever been written or at least performed when </s><s>[INST] Al pacino defends the younger. Yeah, I, uh, I often think about that. There's been times in my life, I don't know about you where I wish I had an AL pacino in my life where, um, integrity is really important in this life. And sometimes you find yourself in places where there's pressure to sacrifice that integrity and you want, uh, what is it, Lieutenant colonel or whatever. He was coming, come in on your side and and scream at everyone and say, what the hell are we doing here [/INST] being unfortunately british and sort of having that slightly awkward sort of Hugh Grant jean. It's, it's very, very, very at the opposite end of the spectrum of the remarkable feat of Al pacino at the end of that scene. But um, and yeah, integrity is, um, it's a challenging thing and I value it much and I think, um, It can take 20 years to build a reputation in two minutes to lose it. And there is nothing more that I value than that integrity. And you know, if I'm ever wrong about, and I think I truly don't want to be wrong for any longer than I have to be. Um, you know, that's what being in some ways a scientist is your, you're just driven by truth. And the irony relative to something like mathematics is that in science, you never find truth. What will you do in science is you discount the things that are likely to be untrue leaving only the possibility of what could be true. But in Math, you know, when you create, you know, a proof. It's a proof for, you know, from that point forward, there is truth in mathematics and there's, I think there's a beauty in that, but I kind of like the messiness of, of science because again, to me, it's less about the truth of the answer and it is more about the pursuit of questions, </s><s>[INST] but their integrity becomes more and more important and it becomes more difficult. There's a lot of pressure is just like in the rest of the world, but there's a lot of pressures on a scientist. One is like funding sources. I've noticed this, that, you know, money affects everyone's mind. I think I've been always somebody that I believe money can't, you can't buy my opinion. I don't care how much money billions or trillions the to put that pressure is there. And you have to be very cognizant of it and make sure that your opinion is not defined by the funding sources. And then the other is just your own success of, uh, you know, for a couple of decades publishing an idea. Um, and then realizing at some point that that idea was wrong all along. And that, that's a tough thing for people to do. But that's also integrity is to walk away. It's just say that you were wrong. Um, that doesn't have to be in some big dramatic way. It could be in a bunch of tiny ways along the way, right? Like uh reconfigure your intuition about a particular problem that's and all of that is integrity when everybody in the room, uh you know, believes a certain thing. Everybody in the community believes a certain thing to uh to be able to still be open minded in the face of that. [/INST] Yeah. And I think it comes down in some ways to the issue of ego that you bond your, you know, correctness or your rightness, your scientific theory with your sense of ego. You know, I've never found it that difficult to let go of theories in the face of counter evidence in part because I have such low self esteem. </s><s>[INST] Well, I I kind of like that. I've always liked that communist, I have the same. I'm like very self critical imposter syndrome, all those things, uh putting yourself below the podium, but at the same time having the ego that drives the ambition to work your ass off. Like some kind of weird drive maybe like drive to be better. Like thinking you're yourself is not that great and always driving to be better. And at the same time because that's that can be paralyzing and exhausting and so on. At the same time, just being grateful to be alive, but in the sciences in the actual effort, never be satisfied. Never think of yourself highly. It seems to be a nice combination. [/INST] I very much hope that that is part of who I am and I remain very quietly motivated and driven and I like you love the idea of perfection and I know I will never achieve it, but I will never stop trying to </s><s>[INST] so similar to you, which sounds weird because there's all these videos of me on the internet. Uh, so I think I think I just naturally lean into the things I'm afraid of and I'm uncomfortable doing. Like I'm very afraid of talking to people and you know, just even before talking to you today, just a lot of anxiety, anxiety and all those kinds of things about talking to to me. Yeah, like some nervousness, uh, fear in some cases, uh self doubt and all those kinds of things. But I do it anyway. So the reason I bring that up is um, you've launched the podcast. [/INST] I have </s><s>[INST] allow me to say, I think you're great science communicator. So this challenge of being a afraid or cautious of being in the public eye and yet having a longing to communicate some of the things you're excited about in the space of sleep and beyond what's your vision with this project. [/INST] I think firstly to your to that question like you, I am always more afraid of not trying than trying. </s><s>[INST] Yeah, [/INST] that to me frightens me more. But with the podcast, I think really I have two very simple goals, I want to try and democratize the science of sleep and in doing so my goal would be to try and re unite humanity with the sleep that it is so desperately bereft of and if I can do that through a number of different means. Um The podcast is a little bit different than this format. It's going to be short form monologues um from, from yours truly, that will last usually less than just 10 minutes and I see it as simply a little slice of sleep goodness that can accompany your waking day. </s><s>[INST] It's hard to know what is the right way to do. Science communication. Like your friend mine Andrew Huberman Is does, he's an incredible human being, he does like two hours of, I wonder how many takes he does. I don't know, but it looks like he doesn't do anything. I suspect [/INST] he's that magnificent human </s><s>[INST] being when I talked to him in like in person, he always generates intelligent words well cited nonstop for hours. So I don't, [/INST] he's a gatling gun of information and it's </s><s>[INST] pristine and passion and all those kinds of things. So that's an interesting medium. I wouldn't have, It's funny because I wouldn't have done it the way he's doing it. I wouldn't advise him to do it the way he's doing it because I thought there's no way you could do what you're doing because there's a lot of work, but he is like doing an incredible job of it. I just think it's the same with like dan Carlin's hardcore history. I thought, I thought that the way Andrew is doing it would crush him the way it crushes dan Carlin, so dan has so much pressure on him to do a good job that he ends up publishing like two episodes a year. So that pressure can be paralyzing the pressure of like putting out like strong scientific statements that that can be overwhelming now Andrew seems to be just plowing through anyway. If there's mistakes, he'll he'll say there's correction and so on. I just, I wonder actually haven't talked to him too much about it, like psychologically how difficult is it to put yourself out there for an hour or two, a week of just not stop dropping knowledge, anyone sentence of which could be totally wrong, it could be a mistake [/INST] and there will be mistakes, you know, and I, you know, in the first edition of my book there were errors that you know, we corrected in the second edition two, But there will be probabilistic Lee you know, if you've got, you know, 10 facts per page of a book and you've got 350 pages, odds are it's probably not going to be at a perfection out the gate and it will be the same way for Andrew to, but having the, the reverence of a humble mind and simply accepting the things that are wrong and correcting them and doing the right thing. I know that that's his mentality, </s><s>[INST] I do want to say that I'm just kind of honored to be uh it's like, it's a cool group of like scientific people that I'm fortunate enough to not be interacting with this, you and Andrew um David Sinclair has been thinking about throwing his hat in the ring. [/INST] Oh, I hope so. David is another one of those very special people in the world. </s><s>[INST] So it's cool because podcasts are, it's cool, it's a, it's such a powerful medium of communication. It's much freer then more constrained like publications and so on or it's much more accessible and inspiring than like, I don't know, conference presentations or lectures and it's a really exciting medium to me and it's cool that there's this group of people that uh are becoming friends and putting stuff out there and supporting each other. So it's fun to also watch how that's going to evolve in your case because it wonder it'll be to a month or [/INST] devolve is the, is the answer to that. </s><s>[INST] Well, I mean some of it is persistence through the challenges that we've been talking about, which is like, I think [/INST] I've got a lot to learn. Yeah, but I hope assist. </s><s>[INST] Can I ask you some detailed stuff you mentioned goodness [/INST] go anywhere you wish with sleep. </s><s>[INST] Uh so I'm a big fan of coffee and caffeine and I've been, especially the last few days consuming a very large amount and I'm cognizant of the fact that my body is affected by caffeine different than the anecdotal information that other people tell me. I seem to be not at all affected by it. It's almost um it feels like more like a ritual than it is a chemical boost to my performance. Like I can drink several cups of coffee right before bed and just knock out anyway, I'm not sure if it's a biological chemical or it has to do with just the fact that because consuming huge amounts of caffeine, all that to say ah Mhm. What do you think is the relationship between coffee and sleep, caffeine and sleep? There is an interesting distinction [/INST] that there is a distinction. So I think the first thing to say, which is going to sound strange coming from me is drink coffee. Um The health benefits associated with drinking coffee are really quite well established now. Um but I think that the counterpoint to that, well, firstly the dose and the timing make the poison and I'll perhaps come back to that, it is the second. But for coffee, it's actually not the caffeine. So, you know, a lot of people have asked me about this rightful paradox between the fact that sleep provides all of these incredible health benefits and then coffee, which can have a deleterious impact on your sleep has a whole collection of health benefits, many of them then diagram overlapping with those that sleep provides. How on earth can you reconcile those two? And the answer is that well, the answer is very simple, it's called antioxidants that it turns out that for most people in Western civilization, because of diet not being quite what it should be. The major source through which they obtain antioxidants is the coffee bean. So the humble coffee bean has now been asked to carry the astronomical weight of serving up the large majority of people's antioxidant needs. And you can see this if for example, you look at the health benefits of deep caffeinated coffee, it has a whole constellation of really great health benefits to this is not the caffeine and that's why I liked what you said, this sort of separation of church and state between coffee and caffeine. It's not the caffeine, it's the coffee bean itself that provides those health benefits. But coming back to how it impacts sleep, it impacts sleep in probably at least three different ways. The first is that for most people, caffeine can make it obviously a little harder to fall asleep, caffeine can make it harder to stay asleep. But let's say that you are one of those individuals and I think you are and you can say, look, I can have three or four espressos with dinner and I fall asleep just fine and I stay asleep soundly across the night. So there's no problem. The downside there is that even if that is true, the amount of deep sleep that you get will not be as deep and so you will actually lose somewhere between 10-30% of your deep sleep if you drink caffeine in the evening. So to give you some context to drop your deep sleep by let's say 20%, I'd probably have to age you by 15 years or you could do it every night with a cup of coffee. I think the fourth component that is perhaps less well understood about coffee is its timing and that's why I was saying the timing and the dose makes the poison the dose by the way, once you get past about three cups of coffee a day, the health benefits actually start to turn down in the opposite direction. So there is a U shaped function. It's sort of you know the Goldilocks syndrome? Not too little, not too much, just the right amount. The second component is the timing though, caffeine has a half life of about 5 to 6 hours, meaning that after 5 to 6 hours, 50% of that on average for the average adult is still in the system, which means that it has a quarter life of 10 to 12 hours. So in other words, if you have a coffee at noon, a quarter of that caffeine is still circulating in your brain at midnight. So having a cup of coffee at noon, one could argue is the equivalent of talking yourself into bed at midnight and before you turn the light out you swing a quarter of a cup of coffee. But that doesn't still answer your question as to why are you so immune? So I'm someone who is actually unfortunately very sensitive to caffeine and if I have, you know, even two cups of coffee in the morning, um I don't sleep as well that night and I find it miserable because I love the smell of coffee. I love the routine. I love the ritual. I think I would love to be invested in it. It's just terrible for my sleep. So I switched to decaf. There is a difference from one individual to the next and it's controlled by a set of liver enzymes called cytochrome P450 enzymes. And there is a particular gene that if you have a different sort of version of this gene, it's called C YP one a two. That gene will determine the speed of the clearance of caffeine from your system. Some people will have a version of that gene that is very effective and efficient at clearing that caffeine. And so they're half life could be as short as two hours rather than 5-6 hours. Other people hands up Matt Walker um have a version of that gene that is not very effective, clearing out the caffeine and therefore their half life sort of sensitivity could be somewhere between you know, 8-9 hours. So we understand that there are individual differences. But overall I guess the top line here is drink coffee um and understand that it's not the caffeine, it's the coffee that's the benefit and the dose makes the poison. </s><s>[INST] Is there some aspect to it? That's it's like a muscle in terms of the all the combinations of letters and numbers that you just said. Is there some aspect that if uh I can improve the quarter lies the half life, decrease that number. If I just practice like I drink a lot of coffee is to sort of habit alters how your body is able to get rid of the caffeine, [/INST] not how the body is able to get rid of the caffeine but it does alter how sensitive the body is to the caffeine and it's not at the level of the enzyme degrading the caffeine. It's at the level of the receptors that caffeine will act upon. Now it turns out that those are called a denizen receptors and maybe we can speak about what a Dennis scene is and sleep pressure and all of that good stuff. But as you start to drink more and more coffee um the body tries to fight back and it happens with many different drugs by the way and it's called tolerance. And so one of the ways that your body becomes tolerant to a drug is that the receptors that the drug is binding to these sort of welcome sight these sort of you know, picture mitts as it were that received the drug those start to get taken away from the surface of the cell and it's what we call receptor internalization so the cell starts to think she wears you know there's there's a lot of stimulation going on, this is too much. So I'm just going to when normally I would you know coat my cell with let's just say five of these receptors for argument's sake things are going a little bit too ballistic right now I'm going to take away at least two of those receptors and downscale its just having three of those and now you need two cups of coffee to get the same effect that one cup of coffee got you before and that's why then when you go cold turkey on coffee all of a sudden the system has equilibrium rated itself to expecting X amount of stimulation and now all of that stimulation is gone so it's now got too few receptors and you have a caffeine withdrawal syndrome and that's why for example with you know drugs of abuse things like heroin when people go into abstinence you know as they're moving into their addiction they will build up a progressive tolerance to that drug so they need to take more of it to get the same high but then if they go cold turkey for some period of time the system goes back to being more sensitive again it starts to repopulate the surface of the cell with these receptors but now when they re use and they fall off the wagon if they go back to the same dose that they were using before, You know, 10 weeks ago or three months ago, that does can kill them. They can have an overdose even though they were using the same amount at those two different times. The difference is that it's not the dose of the drug, it's the sensitivity of the system and that's the same thing that we see with caffeine in terms of training the muscle as it were. Is the system becomes less sensitive. Can calibrate </s><s>[INST] is there a time the number of hours before bed? That's a safe bet to most people to recommend you should drink caffeine this many hours. Like is there an average half life that should be aiming at? Or is this advice kind of impossible because there's so much variability, [/INST] there is huge variability and I think everyone themselves, you know to a degree knows it, although I'll put a caveat on that too because it's slightly dangerous point. So the recommendation for the average adult and who where is the average adult in society? There is no such thing, but for the average adult it would be probably cutting yourself off maybe 10 hours, you know before. So assuming a normative time in society, I would say try to stop drinking caffeine, you know before two PM and just keep an eye out, you know and if you're struggling with sleep, dial down the caffeine and see if it makes a difference. </s><s>[INST] Can I ask you about sleep and uh learning so how to sleep effect learning sleep before learning sleep after learning, which are both fascinating kind of dynamics of the minds, interaction with this extra conscious state. [/INST] Yeah, sleep is profoundly and very intimately related to your memory systems and your informational systems. Um the first as you just mentioned is that sleep before learning will essentially prepare your brain almost like a dry sponge, ready to sort of, you know, initially soak up new information. In other words, you need sleep before learning to effectively imprint information into the brain to lay down fresh memory traces and without sleep, the memory circuits of the brain and we know we've studied these memory circuits will you know, essentially become waterlogged as it were for the sponge analogy and you can't absorb the information as effectively. So you need sleep before learning, but you also need sleep. Unfortunately after learning to to then take those freshly minted memories and effectively hit the save button on them. But it's nowhere near as quick as a digital system. It takes hours because it's a physical biological change that happens at the level of brain cells. But sleep after learning will cement and solidify that new memory into the neural architecture of the brain, therefore making it less likely to be forgotten. So, you know, I often think of sleep in that way as it's almost sort of future proofing information in in what way? Well, it means that it gives it a higher degree of assurance to be remembered in the future rather than go through the sort of degradation that we think of as forgetting. So the brain has in some ways by default, you know, there is forget and actually I would love to, I was going to say sleep is relevant for memory in three different ways, but I'm going to amend that and say there's four different ways which is learning, maintaining, memorizing abstraction, assimilation association and then forgetting which the last one sounds oxymoronic based on the form of three, but I'll see if I can explain. So sleep after learning then sort of, you know, sets the that information like Amber um, in, you know, in in solidification. The third benefit, however, is that sleep we've learned more recently is much more intelligent than we ever gave it. Credit for. Sleep doesn't simply just take individual memories and strengthen them sleep well, then intelligently integrate and cross link and associate that information together. And it's almost like informational alchemy. So that you wake up the next morning with a revised mind wide web of associations. And that's probably the reason that, you know, you've never been told to stay awake on a problem, you know? And in every language that I've been quite about that phrase or very something very similar seems to exist, which means to me that this creative associative benefit of sleep transcends cultural boundaries. It is a common experience across humanity. Um Now I should note that I think the french translation of that is much closer to you. Um I think you sleep with a problem, whereas the british just sleep on a problem. The french you sleep with a problem. I think it's so much about the romantic difference between the british and the french, but let's let's not go that um </s><s>[INST] that's brilliant. So such a subtle but such a fundamental difference. Yeah. Yeah. Goodness me sleep with the problem. Yes, exactly. [/INST] I love french. Um uh so, and we can double click on any one of these and going into detail. But the fourth, I became really enchanted by about eight years ago in our research, which was this idea of forgetting. And I started to think that forgetting maybe the price that we pay for remembering. Mhm. And in that sense, there is an enormous benefit to letting go. And you may be thinking, that sounds ridiculous. I don't want to forget. In fact, my biggest problem is I keep forgetting things, but the brain has a fight. Will we believe has a finite storage capacity? We can't prove it yet. But my suspicion is that that's probably true. It doesn't have an infinite storage capacity, it has constraints if that's the case, we can't simply go through life being constantly informational aggregators Unless, you know, we are programmed to say we've got a hard drive space of about 85-90 years and we're good and we can do that. Maybe that's true. I don't think that's true. I think forgetting is an incredibly good and useful thing. So for example, you know it's not beneficial from an evolutionary perspective for me to remember where I parked my car three years ago. So it's important that I can remember today's parking spot but I don't want to have the junk kind of D. N. A. From a memory perspective of you know, where my I parked my car, you know two years ago. Um Now I actually have a in some ways a problem with forgetting. I'm again I'm not trying to be laudatory but you know I tend not to forget to many things and I don't think that that's a good thing. And um the there was a wonderful neurologist Lauria who wrote a book called The Mind of the norman assist and it was a brilliant book both because it was written exquisitely but he was studying these sort of memory savants who basically could remember everything that he gave them and he tried to find a *** in their armor and the first half of the book is essentially about him seeing how far he can push them before they fail. And he never found that place, he could never find a place where they stopped remembering. And then in his brilliance, he turned the question on its head, he said not what is the benefit of constantly remembering, but instead what is the detriment to never forgetting. And when you start to realize his descriptions of those individuals, it's probably a life that you would not want. </s><s>[INST] It's just fascinating both from a human perspective, but also a i perspective, there's a there's a big challenge in the machine learning community of how to build systems that are able to remember for prolonged periods of time, lifelong continuous learning. So where you build up information over time. So memory is one of the biggest open problems in uh in A I and machine learning, but at the same time the right way to formulate memory is actually forgetting because you have to be exceptionally selective at which kind of stuff you remember. And that's where the step of a simulation integration that you're referring to is really important. I mean we forget most of the things and the question is exactly the cost of forgetting at the very edge of stuff that could be important or could not be, How do we remember or not those things like for example, have you know, doing a podcast, I've become cognizant of one feature of my forgetting that's been problematic, which is I forget names and titles of books and so on. So when I read, I remember ideas, I remember quotes remember statements and like that's the space in which I'm thinking. But when you communicate to others, you have to say this person in this book said that it's the same thing with like Andrew Huberman is masterful at this, This is important academia remembering the authors of the paper and the title of the paper as part of remembering the idea and I've been feeling the cost of not not being able to naturally remember those things and so that that's something I need to sort of work on but that's an example with faces. Yes, very good at faces [/INST] but not good with names. So I'm exactly like you and there is you know an understanding of that in the brain to we understand that there is partitioning of those in terms of the territory of the brain that takes care of faces and facts and places and they can be separate. So I will never forget face but you know, and as I said, I usually forget very little but for some reason, names are struggle, I think in some ways because I'm probably just a slightly anxious person. So when you first meet someone which is usually the time when a name is introduced, you know you were saying you were sort of anxious maybe about sort of sitting down with me, but I find that a little bit, you know activating and so it's not as though there's anything wrong with my memory, it's just the emotional state. I mean when I first meeting someone. Yeah. You know it's a little bit for something but I will never forget that face. But </s><s>[INST] I completely relate to that because I almost don't hear people's names when they tell me because I'm so anxious. Yeah. But I I think there's certain quirks of social interaction that show that you care about the person that you remember, that person that they matter to you. They had an impact on you. And one of the ways to show that as you remember their name. And but that's a quirk to me because there's a lot of people I may have a deep impact on me but they can't communicate that unless I know their name unless I know some of the um details that that we humans seem to use to communicate that we remember each other what I remember. Well is the feeling we shared is the experience was shared. What I don't remember. Well is the detailed labels of those experiences and I need to certainly work on that. I [/INST] don't know. I think it's you know, just allowing yourself to be an eight and who you are is also a beautiful thing to. I'm not suggesting it's not important to try and better oneself and but also sometimes worry about the misery that that puts us in but like you I will I do struggle with him. But I know for the first time when we met in the lobby. Um I know exactly what you look like. I know that you were wearing headphones, I know the shape and the size of those headphones, you didn't have your black jacket on. I know exactly what the weave of your shirt looked like, you know what your shoes look like, and I knew exactly the height of your, the end of your pence from the top of your shoes. And so those things I don't forget, you know, and I can that's fascinating. Remember when people I met people, you know, two years ago and I'll say, oh yes, we met there and I remember you had those fantastic, you know, boots on, I thought they were pretty great pair of boots, you know, like how do you, I didn't even remember what I was wearing that there. </s><s>[INST] It's fascinating. Yeah, I mean exactly the same way, but you can't until we have neuralink or something like that, we can't communicate that you remember all those. I know that's what I want, you have to be able to use tricks of human communication for that. But so that, I mean, that's the it's ultimately is a trick of like, which to remember which to forget, and the forgetting is so it's so fascinating to say this. I mean, it seems to be deeply connected to that assimilation process. So forgetting you try to fit all the new stuff into this big web of the old stuff and the things that don't fit you throw out, [/INST] I think the assimilation, the way I've been thinking about it with sleep and it's particularly sort of dream sleep that we think can help with this assimilation. Is that during wake we have one version of associative processing. What I mean by that is we see the most obvious connections. So I think of wakefulness as a google search gone right, Whereas I see dream sleep as doing something very different. I think dream sleep is a little bit like group therapy for memories that everyone gets a name badge and sleep gathers in all of the individual pieces of the day and it sort of starts to get you to forces you in fact to speak to the people, not at the front of the room that you think you've got the most obvious connection with, but to speak with the people all the way at the back of the room that at first you think I've got no obvious connection with them at all. But once you get chatting with them, you learn that you do have a very distant non obvious connection, but it's still a connection on the same and it's almost as though you're doing a google search where you know, I input, you know, lex Friedman and It doesn't take me to the first page of your home site takes me to page 20, which is about some like field hockey game in Utah it turns out that there actually is a link. If I look at it distant, non obvious one and to me I find that exciting because when you fuse things together that shouldn't normally go together. But when they do, they cause marked advances in evolutionary fitness. It sounds like the biological basis of creativity and that's exactly what I think dream sleep in the algorithm of dream sleep is designed to do. You know, it's not a boolean like system where you have, you know, the sort of assumptions of true and false, you know, maybe it's more fuzzy logic system and I think rem sleep is a perfect environment within which we do. You know, it's, it's almost like memory pinball, you know, you get the information that you've learned during the day and then you pull the lever back and you shoot it up into the attic of your brain, you know, this cortex filled with all of your past historical knowledge and you start to bounce it around and see where one of those things lights up and you build a new connection there and you build another one there to your developing schemers. And so in that way I think you could argue, you know, we dream therefore we </s><s>[INST] are. Yeah. So in terms of this line between learning and thinking through a new thing that seems to be deeply connected, there's this uh legendary engineer named jim Keller who keeps yelling at me about this, he says it's very effective. He likes to for difficult problems before bed, think about that difficult problem. We're not talking about like drama at work or all that kind of stuff, you know, like a scientific for him, engineering problem. He likes to like intensely think about it to prime his mind before sleep and then go to sleep and then uh he finds that uh the next day he's able to think much clearer and there's new ideas that come, but also just, I guess it's more well integrated. Um and sometimes during the process of uh like he's able to like wake up and like seeing you insights. That's right. If he's deeply sort of aggressively thinking through a problem. So [/INST] there's many scientific, you know, demonstrations of this, you know, the mandalay over the periodic table of elements. You know, he was trying for months to understand, I mean, talk about ecumenical problem of epic proportions. Here's your question today, You have to understand how all of the known elements in the universe fit together in a logical way. Good luck take uh it was non trivial at the time and he would try and he was so obsessed with it. He created playing cards with all of the different elements on and then he would go on these long train journeys around europe and he would just sort of deal these cards in front of them and he would shuffle them, shuffling and shuffling and he would just try to see if he could find what the answer was. And then so the story goes, you know, he fell asleep and he had a dream and in that dream, you know, all of these elements started to dance and play around and they snapped into a logical grid, you know, atomic weights, etcetera, etcetera. And it wasn't his waking brain that solved the problem. It was his sleeping brain that solved the Impenetrable problem that is waking brain could not, and there's been, you know, even in the arts and in music, some wonderful dreams. You know, Frankenstein mary Shelley's epic gothic novel came to her in a dream at Lord Byron's home. Um, and then we've got, you know, paul McCartney yesterday the song came to him in a dream. He was filming, um gosh, what was the movie? I don't recall it, I should be shot because I'm from Liverpool myself </s><s>[INST] and [/INST] but he was on Wimple Street in London. Um, and filming and they, he came up with that song, the melody um in his sleep, not to be outdone by the Beatles. And by the way, let it be um, also came from a dream that McCartney had people usually give it, you know, religious overtones. You know, mother mary comes to me speaking words of wisdom, let it be if you've ever asked who mother mary is, It's not the, you know, the biblical content, It's his his mother. It's it's mary McCartney and she came to him in a dream and gifted him the song, but the best story I've heard is um not to be outdone by the Beatles the Stones, um keith Richards, who I think once was suggested it, who was it was a comedian who was saying that in an interview with Rolling Stone, keith Richards suggested or inferred that young kids should not do drugs and they said, well look, young kids can't do drugs because you've done all of that, I always thought, but keith Richards described uh he would always go to bed with his guitar and a tape recorder um and then probably who would have a whole set of other things in the bed with him and who knows how many other people, but anyway, uh and then he said in his autobiography, and I'm paraphrasing here, but one morning I woke up and I realized that the tape had recorded all the way to the end. So I rewound the tape and I hit play and they're in some kind of ghostly form with the opening chords to satisfaction. The most famous successful Rolling Stone song of all time. Yeah, followed by then 43 minutes of snoring that that riff came to him, one of the most famous riffs in all of rock and roll came to him by way of a dream inspired insight. So I think, you know, there is too many of those anecdotes and we've now got the sign, you know, I don't rely on anecdotes, a science. We've now done the studies in the laboratory and we can reliably demonstrate that sleep inspires creativity, inspires problem solving capacity. </s><s>[INST] Well the interesting thing is is it possible to some of the ideas that you talk about to turn them into a protocol that can be practiced rigorously. So what jim Keller espouses is saying not just the fact that sleep helps you increase the creativity but turn into a process like literally like don't do it accidentally, you know, like uh like an athlete does certain things to optimize their performance that have a training routine, they have a regiment of uh of like cycling and and and uh sprints and and long distance stuff in the same way, thinking about your job as an idea generator in engineering spaces like this is good for my performance. So like for an hour before bed think through a problem like every night and then you sleep to uh work through that problem. I mean this is the first person that I heard like of the people I really respect that do like what I do, which is like programming engineering type work, like using sleep not accidentally, but with a purpose, like using sleep, [/INST] you know, that's just basically the difference between as you said, a passive approach to it versus you know an active deterministic or hope for a deterministic approach to it. In other words that you are actually trying to harness the power of sleep in a deliberate way, rather than Um, thoughtful way, I still think that, you know, mother nature through it, you know, 3.6 million years of evolution has probably got it mostly figured out in terms of what information should be uploaded at night and worked through. I think algorithm is probably pretty good at this stage. It's not to suggest though, that, you know, we can't try to tweak it and nudge it, it's a very light hand on the tiller is what he's doing. I don't think there's anything wrong with that, </s><s>[INST] you know, just like for example, for me, fast thing has improved my ability to focus deeply and productivity significantly. And in that same way it is possible that playing with these ideas of thinking before bed or some hours before bed or some playing with different protocols will have a significant leap over what mother nature naturally does. So if you let your body do what it actually does, you may not achieve the same level of performance because mother nature has not designed us to think deeply about uh chip design for uh programming artificial intelligence systems. So [/INST] well, she's gifted, does the architecture and the capacity to do that. What we do with that is, you know, is what life's experience dictates, she gives us the blueprint to do many, you know, </s><s>[INST] well if I were to sort of introspect and self analyze what mother nature wants me to do. I think given my current lifestyle that I have food in the fridge [/INST] and </s><s>[INST] a bed to sleep on, I think what mother nature wants me to do is to be lazy. So I think I'm actually resisting mother nature. Uh, and because so many of my knees are satisfied and so I'm, I have to resist some of the natural forces of the body and the mind when I do some of the things I do. So there's that dance. Um, you know, like I've been thinking about doing a startup and that's obviously going against everything that my body and mind are telling me to do because it's going to be basically suffering. But the only reason why [/INST] as you know, it will be </s><s>[INST] over. Yes. But nevertheless, there is some kind of inner drive that wants me to do it. And then you start to ask a question, well, how do you optimize the things you can optimize like sleep like diet, like the people that you surround yourself with in order to maximize happiness and performance and all those kinds of things without also over optimizing. And that's such an interesting idea from, from a engineer. So as you may know, you don't often get that those kinds of ideas from engineers, engineers usually just don't read books about sleeping. They're usually like the, they're not, they're not the healthiest of people. Um, I think that's changing over time, especially Silicon Valley, especially the tech sector. People are trying to understand what's a healthy lifestyle, but usually they're kind of on the insane side, especially programmers, but it's nice to hear uh somebody like that you sleep and use some of the things you talk about strategically on purpose [/INST] to that idea of not just trying to use what mother nature gave, but seeing if you can do something more or different in a conservative mindset. Mhm. I would then pose the question at what cost because when you do something perhaps that deviates from the typical pre programmed, you know, with the nature's program, um I suspect it usually comes at the cost of something else. So maybe he is able to direct and focus his sleeping cognition on those particular topics that will gain him better problematic resolution the next day when he wakes up. The question is though, at what cost of the other things that didn't make it onto the menu of the finger buffet of sleep that night. And is it that you don't process the emotional difficulties or events and therefore you are less emotionally resolved the next day. But you are more problem resolved the following day. And so I always try to think and I truly don't want to sound puritanical either about sleep. And I think I've come off that way many at times, especially when I started out in the public um the tone of the book in some ways, you know, I look back and think could I have been a little softer. And the reason was I was that way back in when I started writing the book, which was probably something like 2014 or 15 sleep was the neglected step sister in the health conversation of the day. And I was just so sad to see the amount of suffering and disease and sickness that was caused by insufficient sleep. And for years before I've been, you know, doing public speaking and I tell people about the great things that happen when you get sleep, people would say that's fascinating and then they would go back and keep doing the same thing about not sleeping enough. And then I realized I can't really speak about the good things that happen. It's like the news, what bleeds leads and if you speak about the alarmingly bad things that happen, people tend to have a behavioral change. And so the book as a consequence, I think probably came out a little bit on the strong side of, you know, trying to convince, you know, people, </s><s>[INST] we were trying to help a lot of people. And that's a powerful way to help a lot of people. [/INST] I was genuinely trying to help people, but you know, certainly for some people who for whom sleep is not, does not come easy. Then it was probably, you know, a tricky book to read too. And I think I feel more sensitive to those people now and empathetically connected to them. Um so I think the again, the point was simply that I don't mean to sound too puritanical in in all of this and the same way with you know, caffeine and coffee. I am just a scientist and I am not here to tell anyone how to live their life. That is not my job at all. And life is to be lived to a degree and life is to be lived If you want to do a startup, all I want to do is empower people with the understanding of the science of sleep and then you can make an informed choice as to how you want to live your life. And I often no judgment on how anyone wishes to live their life. I just want to try and see if the information that I have about sleep would alternatively change how you would think about your life decisions. And if it doesn't. No problem. And if it does, </s><s>[INST] I hope [/INST] it's been abuse Well, </s><s>[INST] maybe this is me trying to justify my lifestyle to you. But dr Seuss said, you know, you're in love when you can't fall asleep because reality is finally better than your [/INST] dreams. I love that quote </s><s>[INST] to okay, my sleeping schedule is complicated and it has to do primarily with the fact that I love basically everything that I do and that love takes a form that may not appear to be loved from the external observer perspective because it's often includes struggle, it often includes something that looks like stress, even though it's not stressed. It's like this excitement is this troy turmoil and chaos of passion, of struggling with the problem of being sad and down to the point even depressed of how difficult the problem is the disappointment that the last few weeks and months have been a failure and self doubt all that mix. But I I love it. And part of that is sometimes staying up all night, working on the thing I'm really passionate about and that means sleep schedules, they're just like, you know, uh sometimes sleeping during the day, sometimes very often sleeping very little. But taking naps that are like an hour or two hours or so on that kind of weird chaos. And you know, now also try to give myself back up. I was trying to like research yesterday's anybody else productive wild like this. And there's of course a lot of anecdotal evidence and some of it uh could be just narratives that people have told to the public when in reality they sleep way more. But there's a bunch of people that uh you know, have not are are famous for not sleeping much. So uh on the topic of naps uh this, I read this a long time ago and I checked this Churchill was big on big naps and is actually just reading more about Western Churchill. sleep schedule is very much like mine. So I basically want to give myself the opportunity to at night to stay up all night if I want to. And a good nap. A big part of that in the late evening. Like how often does this destroy social life completely? But uh I'll often take a nap in the late afternoon or the evening and that sets me if I want to stay up all night and things like that. Like uh I've read the Nikola Tesla's left only two hours a night. Edison the same three hours, but he actually did the polyphasic sleep like there's just a bunch of naps. Mhm. What can you say about this? Madness of love and passion of loving everything you do and uh the chaos of sleep that might result in [/INST] I love the Seuss quote and I've had that experience too. Like you I adore what I do. You know if if someone gave you you know enough money to live the rest of your life, you know, got a roof above my head. Rice and beans on the table. Um and they said you don't have to work anymore. I would do nothing different. I would do. Exactly. You know. Yeah, this sounds a little crass and I hope it doesn't sound this way but being a scientist. Yeah, it's not what I do is who I am when that's the case. Mhm. Sleep working out sharing and eating of the things that I do in between my love affair with sleep. Yeah. I fell asleep like a blind roofer and Yeah, yeah. And it was a lover for that started 20 years ago and I remained utterly besotted today. It's the most beguiling thing in the world to me and I could easily and I have, you know, it's kept me up at night. One of my mind is fizzing with experimental ideas or I think I've got a new hypothesis or theory. I will struggle with sleep. I really will. It doesn't come easy to me because my mind is just so on fire with those ideas. So I understand that the struggle but you know, I couldn't advocate from a scientific perspective the schedule because the science just doesn't, you know, I would feel as though I'm doing you a disservice to say it's okay, you know, that that won't come with some blast radius, some health consequences. You know, you can add Margaret Thatcher and Ronald Reagan to that list to both of them were very, you know, proud chest beaters of how little sleep that they get. That just said four hours. Reagan something similar. You know, and I knowing the links that we now know between sleep and Alzheimer's disease. I've often wondered whether it was coincidental then that both of them died of the terrible disease of Alzheimer's meaning, you know, maybe it doesn't get you by way of, You know, being popped out of the gene pool in a car accident because you had a micro sleep at the wheel at age 32 or it doesn't get you at 42 with, you know, heart attack or even 52 with cancer or a stroke. Maybe it gets you in your 70s. I think the elastic band of sleep deprivation can stretch only so far before it snaps and he ultimately seems to snap. You know, Nikola Tesla, uh, I think he um Nicholas says he, he, I think died of a coronary thrombosis, I believe. And there was a wonderful study done out of Harvard where they took a group of people who had no signs of cardiovascular disease. And what they found is that when they track them for years afterwards, They were completely healthy. To begin with. Those people who are getting less than six hours of sleep ended up having a 300% increased risk of developing calcification of the coronary artery, which is the major sort of corridor of life for your heart. When someone says, you know, he died of a massive coronary, it's because of a blockade of the coronary artery, you know, and Tesla, you know, passed away from a coronary thrombosis. We also know that insufficient sleep is linked to numerous mental health issues. We know that Churchill had a wicked battle with depression. Gosh, my goodness! Used to call it black Dog that would come and visit him and I think many of his paintings, he was exquisite painter, but some of them would depict his darkness with depression as well. Um You know, Edison is interesting, people have argued that he would short sleep and he didn't put much value in sleep. Whether or not that's true, we don't know. But he was a habitual napper. You're right during the day. I've got some great pictures of him on his inventors bench taking a nap. And in fact, I believe he set up nap cots around his house so he could nap. But what we also know is study again. Coming out of Harvard just a couple of months ago demonstrated very clearly that polyphasic sleep is associated with worse physical outcomes worth cognitive outcomes and especially worse mood outcomes. So from that sense, you know, sleeping like a baby is not perfect for adults. </s><s>[INST] There's a fascinating dance here of uh the mean and the extreme like the the average and the high performers. So I um this this gets to like the meaning of life kind of discussion. But let's go about it so well and also happiness. So when studying sleep and we're studying anything like diet and exercise. I think you have to really get a lot more data about individuals to make uh conclusive statement that that's when people talk about like his meat. Red meat, good for your, bad for you, right? It's just so often correlated with other life decisions when you choose to eat meat or not. My my sense is that whatever life decisions you make, if they reduce stress and lead to happiness, uh, that's also going to be a big boost. There needs to be integrated into the plots in the science, right? So I'll give you an example of somebody who is unarguably scene is unhealthy. My friend Mr, David Goggins. So he's clearly obviously almost on purpose destroying his body end to say that he's doing the wrong thing or the unhealthy thing feels feels like feels wrong and, but I'm not sure exactly in which way it feels wrong. One of the things I'm bothered by. Again, I apologize for the therapy sessions, uh, a framework of this, but I'm bothered by the fact that a lot of people tell me or David that they're doing things wrong. A lot of people in my life when they see me not sleep, they'll tell me to sleep more now. They're correct. But one fundamental aspect that I'd like to complain about is not enough people, almost nobody, especially people that care for me well, come to me and say, you have a dream work harder. Like it's like the healthy thing should be a component of a life well lived, but not uh, not everything and I don't know what to do with that because uh, you certainly don't want to espouse and just like you said, when you were working in your book, there is uh belief they don't uh sleep was a secondary citizen in the full spectrum of what's a healthy life, but at the same time I'm bothered by in Silicon Valley and all these kinds of uh work environments that I get to work with with engineers. Is there to me too much focus on work life balance? Mhm. What that usually starts meeting is like. Yeah, yeah, of course. It's good to have a social life. It's good to have a family. It's good to it's good to eat well and sleep well, but we should also discover our passion. We should also give our chance to give ourselves a chance to work our ass off towards a dream and make mistakes and take big risks that in the short term seem to sacrifice health. [/INST] And I think, you know, you to come back to how you started about David Goggins, who I've never met, but who I admire incredibly and have an immense reverence for the man. Um You said two things, is it is it wrong to do those things to yourself? And is it unhealthy to do those things to yourself? I disagree with the former and I agree with the latter. So, from a health, biological medicine perspective, sleeping in the way that, you know, you've described or that other people may be sleeping in terms of insufficient amounts, you know, sign. Now to your point too, about into individual differences. Usually when I see a bar graph and I mean I usually say show me your variants. Yeah, I want to see your variants in other words show me the distribution of that effect. How many people were below the mean? How many is it all tightly clustered around this one thing? So it's a very robust effect. Or was this huge fan of effect where for some people there was no effect at all and other people there was a whopping effect and everything in between. So I don't discount into individual variability. Um but and I will come back to those two points about is it wrong and is it unhealthy in just a second when it comes to sleep? We have found huge amounts of into individual differences in your response to a lack of sleep. But one of the fascinating things? So let's say that I take you on, we're going to measure your attention, your emotion, your mood, your blood pressure, your blood sugar glucose regulation your autonomic nervous system and your different gene expression. Let's say I'm just going to measure a whole, you know, kaleidoscope of different outcomes, brain and body. And I find that on our measure of cognition, on your attentional ability to focus, you are very resilient. You just don't show any impairment at all even after being awake for 36 hours straight. Does that mean that you are resilient in all of those are the domains as well. The answer is no, you're not. So you can be resilient in one but very vulnerable in another. And we've we've not found anyone who isn't at least vulnerable in one of those domains, meaning that it's somewhat safe to say that not getting sufficiently will lead to some kind of empowerment in anyone given individual. It may not be the same empowerment but it's likely to be an empowerment. But to come back to the question I think it's wrong to tell anyone that it's wrong to do what they're doing even if they are compromising their sleep, even if they're compromising the mental health. You know, as long as they're not hurting anyone else then I think the answer is that's that person's choice. </s><s>[INST] Yeah but that's that person I'd like to push back further. So you see the way you kind of said it, yes, you're absolutely right. But I would like to say a stronger statement which is you should let go of that. Judge judgment of somebody is wrong and allow yourself to be inspired by the great heights they have reached. So take yourself out of the seat of being a judge er of what is healthy or not and appreciate the greatness of a particular human. You watch the olympics the kind of things that some athletes due to reach the very heights. The olympics are taking years off their life. They suffer depression after the olympics often there it's the physiology is disastrous. Everything. Their personal life there's the psychology, their physiology, um, everything, it's a giant mess. So the question is about life healthy now means longevity, quality of life over a prolonged period of time, optimal performance over a prolonged period of time. But to me, beauty is reaching great heights. And there's a dance there that sometimes reaching great heights requires sacrifice of health. And not like a calculation where you sat down on a sheet of paper and say, I'm going to take seven years off my life for an olympic gold medal. No, it requires more chaotic journey. That that doesn't do that kind of calculus. And I just want to kind of speak to the, in the culture that struggles of what is healthy and not. We want to be able to speak to what is healthy at the same time. Be inspired by the great heights that humans reach no matter how healthy or unhealthy they uh, they live. [/INST] Yeah, I agree with that. I think if that's a flag you're hosting, I will definitely salute it because it really depends, you know, what are you trying to optimize for in your life? And if you are, I think the only danger potentially with that mindset is that if you look at many of the studies of old age and end of life, most people say I never looked back on my life and I wish I worked harder. I wish instead I'd spent more time with family, friends and engaged in that aspect. Now I'm not saying though coming back to your point that that is the standard rubric for everyone. I don't believe it is too. And there are many things that you and I are both benefiting from today, even in the field of medicine where people have sacrificed their own longevity for the quest of solving a particular medical problem and they died quicker because of the commitment because they wished to try and solve that problem in their pursuit of greatness. Scientifically and I now benefit. Am I grateful that they did that incredibly grateful. You know, simpler demonstration of is this if tonight at four a.m. In the morning I have a ruptured appendix. I have an appendicitis. I am incredibly grateful that there is an emergency team that will take me to the hospital at four am in the morning. They are awake, they're not sleeping and they saved my life. And that is the that's part of what their life's mission and quest is and they saved another's life by in some ways shaving a little of their own off. So I don't take, I have no umbrage with that mentality at all. I think you just have to be very clear about what you're optimizing for and my worry is that most people fall into the rat race and they never actually ask the question, why am I doing this </s><s>[INST] If you're just working 9-5 Or uh and you allow that 9-5 to stretch into much longer. But it's nevertheless a job that's kind of like wears you down. That's one thing. Another thing is when it is a lot like your it's a it's a dream like it's a life mission [/INST] accomplished and and for that I think as long as you know what it is that you could be doing to yourself and you are comfortable and a okay with that. I have no problem with that at all. Again, as I said, as a scientist, I cannot should not and will not tell anyone what they should do with their life. Well, I want you to be able to do is say, okay now I understand more about the previously these with the you know known unknowns and these were the unknown unknowns. And now I am slightly more cognizant I have more knowns than than I had before regarding my sleep and my health knowing that information do I still choose to make this decision. And if that's what I offered, then I think I've done my job. That's all I want to offer is just added information into the decision algorithm. And what you end up choosing as an output of that algorithm has nothing to do with me. It's not my business and I will never judge anyone for it. And as I said, I'm immensely grateful for people who have sacrificed much in their lives to give me what I have. </s><s>[INST] So you're saying as long as the sacrifice sort of grounded in knowledge of, you know what the sacrifices that sleep is important and that you're [/INST] comfortable with it. That is it is your conscious choice rather than feeling as though you're trapped or that you are just You haven't thought about it. And you know, you start that job at age 32 and then you wake up the next morning in your 65 and you think, where did my life go? What was I doing that to me? I would feel I would want to hug you and I would say, I'm I'm just so I'm not sounding, I don't want to sound belittling here at all. I would just not wish that for you. I would wish that you could have. You know, I thought about what it was that you're doing and not have that </s><s>[INST] regret. So I guess I'm uh, this is for you, the listener. I'm coming out of the closet here a little bit, the fact that I enjoy the madness I live in. So please do not criticize me, embrace me. I I understand the sacrifices I'm making. I enjoy sleeping on the floor when I'm passionate programming all night and just pass out on on the carpet. I I love this life. Okay, so it's it's uh, but it's definitely something I think about that there's a balance of strike uh where [/INST] I just want you to have as much of it though </s><s>[INST] of life, See quality of life is important. [/INST] I should have said I want you to have as much high quality life. And if high quality of life means I spent five decades on this planet. But yet in that time I am thrilled every day. I'm turned on every day by what I do. And I reveled in this thing called my life's work. I think that that is a 50 Year journey of absolute delight and fulfillment that you should take. </s><s>[INST] I think about my death all the time. I meditate on death. I'm okay to die today. So to me, longevity is not, it's not, it's not a significant goal. I'm so happy to be alive. I don't even think it would suck to die. uh today I'm I'm as afraid of it today as I will be in 50 years. I don't want to die as much today as I will in 50 years. There's uh there's of course all these experiences I would like to have, but I'm everything is already amazing. It's like that leg of movie. So I don't know. So I, to me, I just want to keep doing this and there's, there's of course things that could affect, you know, like you mentioned dementia and these deterioration of the mind or the body that can significantly affect the quality of life. And so you want to uh [/INST] you're aware of that and you know, that's the price you pay for the entry of into this magical, you know, kingdom that you are experiencing, which is a lovely thing. You know, I feel privileged to to I can't believe the life that I live. It's incredible. And just like you, I don't I do I think about mortality a great deal. I think a lot about death, but I don't worry about death. I probably with the exception of the potential pain that comes before it that some people, many people can suffer that may be concerns me. But I actually think about mortality as a tool as I use it as a lens through which I can then retrospect and by placing myself at the point of future mortality, I can then use it as a retrospective lens to focus and ask the following question, is there anything I feel I would regret and therefore change in the life that I currently have now. I that's the way I meditate and use mortality as a question is to try and course correct and focus my life. I worry not about dying, but I like to think about death as a way to prioritize my life if that makes I don't know if that makes sense. </s><s>[INST] It's total sense to decide how do you want to live today? So that in the future you do not regret the way you live today [/INST] and place yourself in the future at your point of mortality is one way to I think as an exercise to retrospectively look back and not lose out on informed choices that you could otherwise lose lose out on if you weren't thinking about mortality. </s><s>[INST] Yeah, it clarifies your thinking uh is there, So I mentioned I sleep on the floor, take naps and power naps and it's just kind of madness. Is there uh weirdness is to your own sleep schedule. As a scientist that does incredible work, has a lot of things going on, has has to lead, research has to write, research has to be a science communicator also have a social life, all those kinds of things. Is there certain patterns to your own sleep that you regret or you um are you participate in uh that you find you enjoy? Um like is is there some like personal stuff quirks or things you're proud of that you do in terms of your sleep schedule? [/INST] The funny thing about being a sleep researcher is that it doesn't make you immune to the ravages of a difficult night of sleep. And I have battled my own periods of insomnia in my life too. Mhm. And I think I've been fortunate in ways because I know how sleep works and I know how to combat insomnia. I know how to get it under control because insomnia in many ways is a condition where all of a sudden your sleep controls you rather than you control your sleep. Yeah, that's a beautiful way to put it. Yeah. And I know when I'm starting to lose control and it's starting to take control, I understand how to regain, but I've it doesn't happen our overnight, it takes a long time. </s><s>[INST] So you've struggled with insomnia. Yeah. My life [/INST] I have not, not all of my life, I would say I probably had three or four really severe bouts and all of them usually triggered by you know, emotional circumstances by stress, </s><s>[INST] um stress that's connected to actual events in life or stress. That's unexplainable, [/INST] Little externally triggered. Yeah, it's sort of what we would call reactive stress. Um and so that that that sort of point number one about the idiosyncrasies. The point number two is that when you are having a difficult night of sleep as a sleep researcher, you basically have become the woody allen neurotic of the sleep world because at that moment, you know, I'm trying to fall asleep and I'm not and I'm starting to think, okay, my dorsal lateral prefrontal cortex is not shutting down. My nor adrenaline is not ramping down. My sympathetic nervous system is not giving away to my parents at that point, you are dead in the water for the next two hours and nothing is bringing you back. So there is some irony in that too. I would say for myself though, I if there's something I'm not proud of, it has been at times railing against my Krone type. So your Krone type is essentially are you a morning type, evening type or somewhere in between. And there were times because society is desperately biased towards the morning types. You know, this notion of the early bird catches the worm maybe that's true. But I'll also tell you that the second mouse gets the cheese. Yeah. So I think the issue is a good line around, you know, is firstly people don't really understand Krone type because I'll have some people when I'm sort of out in the public, they'll say look, I struggle with terrible insomnia. And I ask them, is it problems falling asleep or staying asleep? And they'll say falling asleep. And then I'll say, look, if you are on a desert island with nothing to wake up for no responsibilities, what time would you normally go to bed and what time would you wake up? And they would say I probably like to go to bed about midnight and wake up maybe eight in the morning. And then I'd say, so what time do you now go to bed? And they would say, well I've got to be up for work early. So I get into bed at 10 and say, well you don't have insomnia. You have a mismatch between your biological krone type and your current sleep schedule and when you align those two and I was fighting that for some time to I'm probably mostly right in the middle, I am desperately vanilla. Unfortunately many aspects of life, but this included, I'm neither a strong morning type nor a strong evening type, so ideally I'd probably like to go to bed around, you know 11, 10 30 11, probably somewhere between 10 30 11 and wake up, you know, I naturally wake up usually most days before my alarm at um 704 um And it's 704 because why not be idiosyncratic in terms of sitting and I love it. And so </s><s>[INST] I that's kind of awesome. I've never heard about that, that's that's amazing. I'm gonna start doing that now setting alarms like a little bit off t like yeah, I know, I'm never quite sure why the celebration of [/INST] uniqueness. Yeah, and I am quite the odd snowflake in that sense to um So I would usually then try to force myself because I had that same mentality that if I wasn't up at, you know 6, 13 in the gym by seven, that there's something wrong with me and I quickly abandoned that. But if I look back, if there was a shameful act, then I have around my sleep, I think it would be that for some years until I really started to get more detailed into sleep. Um and now I have no shame in telling people that, you know, I will probably usually wake up around 6 45 naturally, sometimes seven when people are looking at me thinking you're a slob, you're lazy. Um and you know, I don't finish my daily workout until, you know, I'm not working until probably nine o'clock in the morning thinking what are you doing now? I will work late into the Day. You know, if I could, I would work 16 hours, it's my passion, just like yours. Um So I don't feel shame around that, but I have changed my mentality around that. </s><s>[INST] Um It's complicated because I um I'm probably happiest going to bed at, if I'm being honest, like at five a.m. [/INST] That's fine, you're just an extreme evening type. But </s><s>[INST] the problem is, it's not that I'm ashamed for. It is uh I actually kind of enjoyed because I get to sleep through all the nonsense of like the morning and isn't that a beautiful thing? Like people are busy with the emails and I just, I'm as happy as a cow. Yeah, and I wake up after all the drama has been resolved and cows [/INST] are happy and the drama has been resolved. </s><s>[INST] Exactly. So, but, you know, in society you do, especially, I mean, this is what I think about is um you know, when you work a larger team, especially with companies, you are, you know, everybody's awake at the same time. So that that's definitely that's definitely been a struggle to try to figure out, just like you said, um how to balance that, how to fit into society and yet be optimal for your prototype, he said, yeah, you have to [/INST] sleep in synchrony with it and harmony. Because normally what we know is that if you fight biology, you'll normally lose and the way you know you've lost is through disease and sickness. </s><s>[INST] You said you suffered through several bouts of insomnia. Is there aside from embracing your prototype, is there advice you can give how to overcome insomnia from your own experience? [/INST] Right now? The best method that we have is something called cognitive behavioral therapy for insomnia or C. B. T. For short. And um you work with people who don't know what it is. You work with a therapist for maybe six weeks and you can do it online by the way, I recommend probably jumping online. It's just the easiest. Um and it will change your beliefs, your habits, your behaviors and your general stress around this thing called sleep. And it is just as effective as sleeping pills in the short term. But what's great is that unlike sleeping pills, when you stop working with your therapist, those benefits last for years later. Whereas when you stop your sleeping pills, you typically have what's called rebound insomnia where your sleep not only goes back to being as bad as it was before, it's usually even worse for me. I think I found a number of things effective. The first is that I had to really address what was stressful and try to come up with some degree of meaningful rationality around it because I think one of the things that happens, there's something very talking about conscious states to come all the way back to um Gosh, I don't know. I feel like we've only been chatting for like 20 minutes, but you're going to tell me it's been a while, it's been a while, okay. I'm desperately, I feel terribly sorry, but let's come back to consciousness where we, where we started. Uh um there is something very strange about the night that thoughts and anxieties are not the same as they are in the waking day. They are worse. They are bigger. And I at least find that I am far more likely to catastrophes and ruminate at night about things that when I wake up the next day in the broad light of day, I think it's nowhere near that bad man, What were you doing? It's not that bad at all. So, to gain firstly some rational understanding of my emotional state that's causing that insomnia was very helpful. The second thing was to keep regularity just going to bed at the same time, waking up and here's an unconventional piece of sleep advice after a bad night of sleep, do nothing. Don't wake up any later. Don't go to bed any earlier. Don't nap during the day and don't drink any more coffee than you would otherwise, because if you end up sleeping later into the morning, you're then not going to be tired at your normal time at night. So then you're going to get into bed thinking, well I had a terrible night of sleep last night and yes, I slept in this morning to try and compensate but I'm still going to get to bed at my normal time. But now you get into bed and you haven't been awake for as long as you normally would. So you're not as sleepy as you normally would be. And so now you sit there lying in bed and it's another bad night. And the same thing is, you know, if you go to bed any earlier, so don't wake up any later, wake up at the same time, don't go to bed in a earlier because then you're just probably your Krone type, your biological rhythm doesn't want you to be asleep. And you think well, terrible night. I'm going to get into bed at nine PM rather than my standard 10. Just gonna be lying in bed awake for that hour, naps will take our double edged sword. They can have wonderful benefits. And we've done lots of studies on naps for both the brain and the body. But they are a double edged sword in the sense that napping, we'll just take the edge off your sleepiness. It's a little bit like a valve on the pressure cooker when you nap during the day. You can take some of that healthy sleepiness that you've been building up during the day and for some people, not all people, but for some people that can then make it harder for them to fall asleep at night and then stay asleep soundly across the night. So the advice would be if you're struggling with sleep at night, don't nap during the day, but if you are not struggling with sleep and you can not regularly naps are just fine and we can play around with optimal durations depending on what you want. Just try not to nap too late into the day because napping late into the day, it's like snacking before your main meal. It just takes the edge off your sleep hunger as it were. But that would be. Um so that's my unconventional 2nd piece of advice regarding insomnia. The 3rd is meditation. I found meditation to be incredibly powerful. I started reading about meditation as I was researching that aspect of the book um many years ago. And as a hard no scientist, I thought this sounds very whoa. Um this is sort of, we all hold hands and sing, come by our and everything is going to be fine with sleep. I read the data and it was compelling. I couldn't ignore it and I started meditating and that was six years ago and I haven't stopped and I found meditation before bed incredibly powerful. The meditation app companies were perplexed at this at first. They want people to meditate during the day. But when they looked at their usage statistics, they found that they would have people in the morning meditating and then there's a huge number of people using the meditation app in the evening. What they were doing was self medicating their, their insomnia and they finally, rather than railing against it, they started to see it as a cash cow. Um, rightly so. So I found meditation to be helpful having a wind down routine is the other thing that's critical for me, I can't just go from because when my mind is switched on and I think you may be like this too if I get into bed that roller decks of thoughts and information and excitement and anxiety and worry is just whirling away and it's not gonna be a good night for me. So I have to find a wind down routine and that makes sense when you realize what sleep is like sleep is not like a light switch. Um sleep is much more like trying to land a plane. You know, it takes time to descend down onto the terra firma that we call sound sleep at night and we have this for kids, you know, I don't have Children, but you know, a lot of parents will say, you know, we have to have the bedroom, sorry, the bedtime routine, you know, you bathe the kids, you put them in bed, you read them a story, you have to go through this routine, This wind down routine for them and then they fall asleep wonderfully, why do we abandon that as adults? We need that same wind down routine. So that's been the other thing that's been very helpful to me. So don't do anything different if you have a bad night of sleep, keep doing the same thing, manage your anxiety, understand it, rationalize it um than meditation and then finally having some kind of disengagement wind down routine. Those are the four things that have been very helpful to </s><s>[INST] me. That's brilliant. So the regularities really do a lot of, a lot of work against Sonya, is there? Yeah. Is it possible to have a healthy sleep life without the regularities? I say that because I'm all over the place and I've gotten good at being all over the place. So I'll often like what happens? I'll go stretches of time, it'll be sometimes a month where I, my days are like, this is embarrassing to admit, but [/INST] they're like, just you and I hear it's just </s><s>[INST] You and I it's like 28 hours or 30 hour days. Yeah, like I'll just go all the way around comfortably and happily. I love it and then there'll be a nap. I mean if you like add up the hours when I'm just like sleeping as much As I want to probably be like six hour average per 24 hours, like that kind of, you know, so it works out nicely, maybe even seven hours, I don't know, but that it's obviously irregular and there's chaos in the whole thing. Like sometimes it's short sleeve sometimes it's longer. Is that is that totally not a good thing. Do you think [/INST] the best evidence that we have to speak to this question is people who are doing rotating shifts and unfortunately the news is not good. Um They usually have a higher instance of many diseases such as depression, diabetes, cardiovascular disease, obesity, um stroke. And and again, I'm that's just me communicating the data that we have and I'm not telling you that you should do anything different. The other thing is that there's nothing in your biology that suggests that that's how your body was designed to sleep. It is a system that loves habit. You know, if if your circadian clock in your brain, it's called the super charismatic nucleus um sits in the middle of your brain had a personality trait, it would be a creature of habit. It loves habit. That's how your biology is designed to work is through very archetypal prototypical expected cycles. And when we when we do something different to that than you start to see some of the pressure stress fractures in the system. But again, to your point, if that's something that you don't mind, you know, adopting and understanding and um then I think you should keep doing </s><s>[INST] what it's complicated. You of course have to be a student of your body and explore. One of the reasons I want to have kids is kids enforces a stricter schedule. I think I definitely, I definitely feel that I'm not living the sort of data why scientifically speaking, the optimal life, me just living the way I want to live day to day is perhaps not the optimal way. And there's certain things that I've seen very successful people that I know in my life when they get, when they have kids, they actually, the productivity goes up, they get their shit together. There's a lot of aspects that yeah, the regularity, I mean that creatures of habit, that's the thing that that that's power and then you start to optimally use the hours you have in the day. Let me ask you about actually, I [/INST] just have one quick point on that too. You know, we often think about sleep as a cost, but instead I think of sleep as an investment and the reason is because your effectiveness and your efficiency when you're well slept typically exceeds that when you're not. And to me it's the idea of if I'm going to boil a pot of water, why would I boil it on medium when I could boil it in half the time on high. Yeah. And I sometimes worry that when I Speak to Fortune 500 companies and you know, there are this mentality of you know long hours getting people to rise and grind. The first point is that after about 20 hours of being awake, a human being is as cognitively as impaired as they would be if they were legally drunk. And the reason I bring that point up is because I don't know any company or Ceo who would say I've got this great team that drunk all the time. But we often Lord, the airport warrior who's flown through three different time zones in the past two days is on email at two a.m. And then is you know, in the office at six. And I think there is some aspect, not in all people, but there is sort of some aspect of that slight sleep machismo and and that's not what you are very different. You know, you are driven by a purity of passion and a very authentic, incredibly genuine goal of wanting to do something remarkable with your life. That's not the issue I think I'm speaking about. It's just simply that I think the this notion of wanting to be awake for longer to try and get more done can sometimes be at odds with the fact that you can actually get so much more done if you're well slept. And it's this trade off. </s><s>[INST] I actually admire people that take the big risk and work hard. Whether that means staying up late at night, all those kinds of things, but it cannot be in the, in the framework in the context like what Edison said, which is sleep feels like a waste of time. So like, if you're not sleeping because you think sleep is stupid, that's totally wrong, but if you're not sleeping because you're deeply passionate about something that to me it's a gray area of course, but that to me is much more admirable and everything you're espousing is saying, like, whatever the hell you doing, you better be aware of the sleep, long term and short term is really good for you. So if you're not sleeping, you're sacrificing, just make sure you're sacrificing for the right thing. I see vodka and getting drunk the same way. I know it's not good for me, I know I'm not going to feel good days after, I know it's gonna decrease my performance and there's nothing positive about it, except it introduces chaos in my life. That introduces beautiful experiences that I would not otherwise have. It uh creates, like, this uh turmoil of social interaction that ultimately makes me happy that I've experienced them in the moment. And later, the stories, you get to meet new people like alcohol in this society is uh incredible facilitator of that. So, like, that's a good example of, like, not sleeping and drinking way too much vodka again, [/INST] it's this notion of life is to be lived to a degree, but, you know, if you do have Children, um I think one of the other things that then maybe comes into the picture is the fact that now there are other people that you have to live for than yourself. </s><s>[INST] Yeah, but come on like once they're old enough, like if you can't, if you can't defend for yourself your year two weeks get stronger, it's going to be that [/INST] kind of fatherhood. Yeah, I got it. I'm understanding Russia so much more about legs Freeman than I than I. </s><s>[INST] That's why you have to have your, for me that would be my wife would be probably softer. It's good cop, bad cop because I think uh but of course actually because I don't have kids, I've seen some tough dudes when they have kids become the like the softest, the softies, they become like they do everything for their kids that has become like it's totally transforms their life. Joe Rogan is an example of that is just seen so many tough guys completely become changed by having kids, which is fascinating to watch because it just shows you how meaningful having kids is. A lot of people. Although I would say having [/INST] you know um chested with joe for for some time, I think he is a delightful sweetheart independent of Children. I think don't get me wrong, I don't want to be in a ring with him, he would face me five ways till Tuesday but I think he's a desperately sweet man and a very, very smart individual. </s><s>[INST] Yeah, I mean, but he he talks about the compassion he's gained from realizing just watching kids grow up that we were all kids at some point. You get a new new perspective I think just like me I still get this with him. He's super competitive and like there's a certain way to approach life. Like you're striving to do great things and your competitive against others and that intensity of that aggression um that can lack compassion sometimes and empathy and when you have Children you get a sense like oh everybody was a child at some point everybody was as a kid. And you see that whole development process it could definitely enrich um expand your ability to be an empathetic. Let me ask about diet. So what's the connection between diet and sleep? So I do intermittent fasting sometimes only one meal a day sometimes no meals a day. Is there a good science on the interaction between fasting and sleep? [/INST] We have some data I would prefer more but we have data both on time restricted eating. Um and then we have some data on fasting to a degree on time restricted eating. I think that it has some benefits. Although the human replication studies have actually not borne out quite the same health benefit extent that the animal studies have been some disappointing um studies one here close to where we are right now at U. C. S. F. Recently. So I think time restricted eating can be a good thing and there are many benefits of time restrict eating is sleep. One of them. No it doesn't seem to be because there are probably at the time that we're recording this three pretty decent studies that I'm aware of. Um two out of the three were in obese individuals, one out of the three were in healthy weight individuals. And what they found was that time restricted eating in all three of those studies didn't have any advantageous benefit to sleep. It didn't necessarily harm sleep, but it didn't seem to improve it when it comes to fasting though, which is a different state. We don't have too many studies, experimental studies with long term fasting. The best data that we have is probably from religious practices and Probably the most data we have is during Ramadan where people will fast for 29-30 days from sunrise to sunset. And under those conditions there are probably there are probably five distinct changes that we've seen. None of them seem to be particularly good for sleep. The first is that the amount of melatonin that you release a melatonin is a hormone, it's often called the hormone of darkness or the vampire hormone, not because it makes you look longingly at people's necklines, but it's just because it comes out at night. Yeah, melatonin signals to your brain that and your body that it's dark, it's nighttime and it's time to sleep. Those individuals when they were undergoing that regiment of fasting, they, the amount of melatonin that was released and when it was released, the amount of melatonin decreased and when it was released came later. That was the first thing. The second thing was that they ended up finding it harder to fall asleep as quickly as they normally would otherwise. The third thing was that the total amount of sleep that they were getting decreased. The fourth fascinating thing was that awake promoting chemical called orexin increased. And this is why a lot of people will say when I'm fasting it feels like I can stay awake for longer and I can I'm more alert, I'm more active and I'll come back from an evolutionary perspective why we understand that to be the case and then the fourth factories that fasting didn't decrease the amount of deep sleep that seemed to be unaffected. It did however, decrease the amount of rem sleep or dream sleep. And we know that rem sleep dreaming is essential for emotional first aid. Mental health is critical for memory, creativity. It's also critical for several hormone functions. It's when you know if you there's direct correlations between testosterone testosterone release peaks just before you go into rem sleep and during rem sleep too. So rem sleep is critical. But so those are the five changes that we've seen. None of them seem to be that advantageous for sleep. But the fourth point that I mentioned which was directs in which is this wake promoting chemical and a good demonstration or very sad demonstration of its power is when it becomes very deficient in the brain and it leads to a condition called narcolepsy were you know you you're just unpredictable with your sleep and you so um so orexin when it's in high concentrations, keeps you awake when you lose it. It can you know, it can put you very much into a state of narcolepsy where you're sleeping a lot of the time and unpredictable sleep. Why on earth when you are fasting with the brain release awake promoting chemical. And our answer is right now is the following the one of the few times that I mentioned before that we see animals undergoing insufficient sleep or prolonged sleep deprivation is under conditions of starvation and that is an extreme evolutionary pressure. And at that point the brain will forego some it won't forego all but it will forego some of its sleep. And the reason is so that it can stay awake for longer because the sign of starvation is saying to the brain, you can't find food in your normal foraging perimeter. You need to stay awake for longer so you can travel outside of your perimeter for a further distance and maybe you will find food and save the organism. So in other words when we fast it's giving our brain this evolutionary signal that you are under conditions of starvation. So the brain responds by saying oh my goodness, I need to release the chemical that helps the organism stay awake for longer, which is Iraq's in so that they can forage for more food now. Of course your brain, from revolutionary perspective doesn't know about this thing called Safeway that you could easily go to and break the fast. But that's how we understand fasting. And I think you know, my dear friend Petra tear has has done a lot of work in this area too. I think fasting and David Sinclair is brilliant work. Goodness me. What an individual to the work is pretty clear there that, you know, time restricted eating and fasting have wonderful health benefits. Time you know, fasting is creates this thing called her Mrs just like exercise and low level stress and sauna heat choc. Um and you're missus is a biological process. I think as David Sinclair has once said in simple layman's terms is what what doesn't kill you makes you stronger. And I think the there is certainly good data that fasting and time restricted eating has many benefits is sleep. One of them, it </s><s>[INST] doesn't seem to be, it doesn't [/INST] seem to enhance sleep, </s><s>[INST] but it's interesting to understand its effects on sleep. I've uh like a fasted, It's a study of NFL two once fasted, 72 hours and another time 48 hours. And uh I found that I got much less sleep. And it was very restful though, I hesitate to say this, but this is how I felt, which is I needed less sleep. I wonder if my brain is deceiving me because it feels like I'm getting a whole extra amount of focus for free. And I wonder if there's long term impacts of that because if I fast 24 hours Get the same amount of calories one meal a day, there's a little bit of discomfort like just maybe your body gets a little bit colder. Maybe there is just I mean hunger, but the amount of focus is crazy. Yeah. And so I wonder it's like I'm a little suspicious of that. I feel like I'm getting something for free. I'm the same way with sweetener, like splendor or something. It's like there's got to be really bad for you, right? Because why is it so tasty? Right. [/INST] And I think, yeah, as we said for with Biology, </s><s>[INST] you know, [/INST] if there is a long game, there's yeah, there's often a cost too. So but we are at least understand the biological basis of what you're describing. It's not that you you actually don't need less sleep. It's that this chemical is present that forces you more awake. And so subjectively you feel as though I don't need as much sleep because I'm wide awake. And those two things are quite different. It's not as though you your sleep need has decreased its that your brain has hit the overdrive switch the over boost switch to say we need to keep you awake because food is in short supply. </s><s>[INST] So you mentioned during sleep, there's a simulation, all those kinds of things for learning purposes, but there's also these uh you mentioned the five ways in which we become psychotic in dreams. What do you think? What do you think dreams are about? What why do you think would dream? What place do we go to when we dream and why are they useful? Not just not just the assimilation aspect, but just like all the crazy visuals that we get with dreams. Is there something you can speak to that's actually useful? Like why we have such fun experiences in that dream world. [/INST] So one of the camps in the sleep field is that dreams are meaningless, that they are an epi phenomenal byproduct of this thing called rem sleep, from which dreams come from as a physiological state. So the analogy would be um let's think of a light bulb that the reason that you create the apparatus of a light bulb is to produce this thing called light in the same way that we we've evolved to this thing called rem sleep to serve whatever functions rem sleep. That's but it turns out that when you create light in that way, you also produce something called heat. It was never the reason that you design the light bulb. It's just what happens when you create light in that way. And the belief. So too, was that dreaming was essentially the heat of the light bulb that rem sleep is critical, But when you have rem sleep with a complex brain like ours, you also produce this conscious epi phenomenon called dreaming. I don't believe that for a second I and from a simple perspective is that I suspect that dreaming is more metabolically costly as a conscious experience than not dreaming. So you could still have rem sleep but absent the conscious experience of dreaming was probably less metabolically costly. And whenever mother nature burns the energy unit called ATP, which is the most valuable thing, uh there's usually a reason for it. So if if it's more energetically demanding then I suspect that there is a function to it. And we've now since discovered that dreams have a function. The first, as we mentioned creativity. The second is that dreams provide a form of overnight therapy. Dreaming is a form of emotional first aid and it's during dream sleep at night that we take these difficult painful experiences that we've had during the day. Sometimes traumatic and dream sleep acts almost like a nocturnal soothing balm. And it sort of just takes the sharp edges off those difficult painful experiences so that you come back the next day and you feel better about them. And so I think in that sense dreaming it's not time that heals all wounds. It's time during dream sleep that provides emotional convalescence. So dreaming is almost a form of you know emotional windscreen wipers. Um And I think by the way it's not just that you dream, it's what you dream about that also matters. So for example, scientists have done studies with learning and memory where they have people learn a virtual maze and what they discovered was that those people who then dreamed but dreamed of the maze, we're the only ones who when they woke up ended up being better at navigating the maze. Whereas those people who dreamed but didn't dream about the maze itself, they were no better at navigating the base. So it's not just that it's not it's sort of necessary but not sufficient. It's necessary that you dream, but it's not sufficient to produce the benefit you have to be dreaming about certain things itself. And the same is true for mental health. What we've discovered is that people who are going through a very difficult experience a trauma, for example, a very painful divorce. Those people who are dreaming but dreaming of that difficult event itself, they go on to gain resolution to their clinical depression one year later. Whereas people who were dreaming just as much but not dreaming about the trauma itself did not go on to gain as much clinical resolution to their depression. So it's I think to me those are the lines of evidence that tell me dreaming is not epi phenomenal and it's not just about the act of dreaming. It's about the content of the dreams, not just the fact of a dream itself. </s><s>[INST] It's first of all it's fascinating, makes a lot of sense, but then immediately takes my mind too from an engineering perspective, holiday could be useful in for example A I systems of if you think about dreaming as a important part about learning and cognition and uh filtering previous memories of what's important, integrating them, you know, maybe you can correct me but I see dreaming as a kind of simulation of worlds that are not constrained by physics. So like you you get a chance to take some of your memories, some of your thoughts and your anxieties and play with them like construct virtual worlds and see how it evolves like to play with those worlds in a safe environment of your mind, safe in quotes because you can probably get into a lot of trouble with with the places your mind will go. But in this this this definitely is applied in much cruder ways in artificial intelligence. So one context in which this is applied is uh the process called uh self play which is reinforcement learning where agents play against itself or versions of itself and its all simulated of trying different versions of themselves and play against each other to see what ends up being a good. The ultimate goal is to learn um a function that represents what is good and what is not good in terms of how you should act and [/INST] you create a set of decision weights based on experience. And you constantly update those weights based on ongoing learning? </s><s>[INST] But the experience is artificially created versus actual real data. So that's it's a crude approximation where dreams are, which is you're hallucinating a lot of things to see which things are. Actually. [/INST] No, I think it's and it's been a theory that's been put forward, which is that dreaming is a virtual reality test space that is largely consequence free. What an incredible gift to give a conscious mind each and every night. </s><s>[INST] Now the conscious mind, the human mind is very good at constructing dreams that are nevertheless useful for you like their wild and crazy. But there are such that they are still grounded in reality to a degree where anything you learn in dreams might be useful in reality. This is a very difficult thing to do because it requires a lot of intelligence that requires consciousness. Uh this has been effectively recently being used in self supervised learning for computer vision with the process of what's called data augmentation is. That's a very crude version of dreams, which is you take data and you mess with it and learn. You start to learn how a picture of a cat truly represents a cat by messing with it in different ways. Uh Now the crude methods currently are cropping rotating, distorting all that kind of stuff, but you can imagine much more complicated uh, generative processes that start hallucinating different cats in order for you to understand deeply of what it means for something to look like a cat, [/INST] right? What is the prototype of the archetype of cat? </s><s>[INST] The Architect? I mean that's a very difficult process for computer vision to, you know, to go from what are the pixels that are usually associated with the cat to like what is a cat in the visual space? In the three dimensional visual space that is projected on an image on a two dimensional image? What is a cat? Those are like fundamentally philosophical questions that we humans don't know the answer to like linguistically. But when we look at a picture of a cat and a dog, we can usually tell pretty damn well what's the difference? And I don't know what that is because you can't reduce that too pointy ears or non point of years furry or not. For worries about the [/INST] it's been a long standing issue in cognitive science, cognitive neuroscience do. That's how how does the brain create an archetype, how does it create schemers that are have general applicability. Um but yet still obtained specificity. That's a very difficult. We can do it. We do it. It's rather bloody amazing. </s><s>[INST] It seems like part of the toolbox is this controlled hallucination which is dreams? Well, it's a [/INST] relaxing of the rigid constraints. You know, I often think of dreaming as you know, it's from an information processing standpoint. You know, the prison guards are away and the prisoners are running a mark in a delightful way. And part of the reason is because when you go into dream sleep the rational part of your brain called the prefrontal cortex which is the parts like the ceo of the brain. It's very good at making high level rational, top down decisions and controlled actions. That part of the brain is shut down during rem sleep. But then emotional centers, memory centers, visual centers, motor rick centers, all of those centres actually become more active. In fact some of them are more active than when we're awake in the dream state. So your brain from a neural architecture perspective is radically different. It's network feature is not the same as wakefulness and I think this is an immensely beneficial thing that we have at least two different rational and irrational conscious states that we do information processing in the rational the very tickle the page one of the google search is wakefulness, the more irrational, illogical, hyper associative google page 20 is the rem sleep. Both I think are critical. Both are </s><s>[INST] necessary. That's fascinating and again fascinating to see how that could be integrated in the machines to help them learn better. And two to reason better [/INST] and in some ways we also know it from a chemical perspective to when you go into dream sleep. It is a neurochemical cocktail, like no other that we see in the rest of the 24 hour state there is a chemical called nor adrenaline or norepinephrine in the brain and you know if it's sister chemical in the body called adrenaline. Um but upstairs in the brain nor adrenaline is very good at creating a very hyper focused, attentive narrow, it's sort of very um convergent way of thinking to a point sharp focus. That's the only thing. The spotlight of consciousness is very narrow. That's nor adrenaline. When you remove nor adrenaline then you go from a high snr high signal to noise ratio where it's just you and I in this moment I don't even know what's going on elsewhere. I am with you nor adrenaline is present. But when you go into rem sleep, it is the only time during the 24 hour period where your brain is devoid of any nor adrenaline, it is completely shut off. And so the signal to noise ratio is very different. It's almost as they were injecting a greater amount of noise into the neural architecture of the brain during dream sleep as if it's chemically brute forced into this relaxed associative memory processing state. And then from an anatomical perspective, just as I described, the prefrontal cortex goes down and other regions later. So it is a state that seems to be very, I mean if you were to show me a brain scan of rem sleep and and tell me that it's not rem sleep just say look based on the pattern of this brain activity. What would you say is going on in this person's mind I would say, well they're probably not rational, they're probably not having logical thought because the prefrontal cortex is down, they're probably feeling very emotional because there are Magdala is active which is an emotional center of the brain. They're definitely going to be thinking visually because the back of the brain is lit up. The visual cortex, it's probably going to be filled with past experience and autobiographical memories because the their memory centers are lighting up and they're probably going to be movement because their motor cortex is very active. That to me sounds very much like a dream and that's exactly what we see in brain scanners when we put people inside of them. </s><s>[INST] one of the things I notice sleep effects is uh my ability to see the beauty in the world. Yeah. So um what do you think is the connection between sleep in your emotional life, your ability to love other human beings and love [/INST] life? Yeah, I think it's it's very powerful and strong. So we've done a lot of work in the field of sleep and emotion and sleeping moods and you can separate your emotions into two main buckets. Um you know, positive and negative and what's interesting is that when you are sleep deprived and the more hours that you go into being awake and the few hours that you've had to sleep, your your negative mood starts to increase and and we we know which individual types of emotions are changing. I've got a wonderful postdoc in my lab called et Ben Simon, who's doing some incredible work on trying to understand the emotional individual emotional tapestry of oh, affective meltdown when you're not getting sufficient sleep. But let's just keep with two dimensions positive and negative, the negative, most people would think, well, it's the negative that takes the biggest hit when I'm sleep deprived. It's not by probably a log order of magnitude larger is a hit on your positive emotions. In other words, you stop. Mhm. Gaining pleasure from normally pleasurable things. And it's a state that we call an Fredonia. And and Fredonia is the state that we often call depression. So, depression, to most people's surprise, isn't necessarily that you're always feeling negative emotions, it's often more about the fact that you lose the pleasure in the good things in life. That's what we call an Fredonia. That's what we see in sleep and insufficient sleep and it happens quite quickly. </s><s>[INST] Yeah, it's kind of fascinating a uh I think I do, it's not depression, but like it's uh it's a stroll into that direction, which is when I'm sleep deprived, I stopped being able to see the meaning in life. The things that gave me meanings starts to lose meaning, like, stupid, it makes me realize how enjoyable everything is in my life. Because when I start to lose it when I'm severely sleep deprived, you start to see how much life sucks when you lose it. But that said when I'm just cognizant enough that like sleep fixes all that. So I used those states for what they're worth. In fact, I personally like to pay attention to the things that bother me during that time because they also reveal important information to me. Um [/INST] It's interesting that you use like a real shock </s><s>[INST] to Yeah, I mean there's so I I find when I fast combined with sleep deprivation, I am clear to see with people clear in identifying the things that are not going right in my life or people that are working with are not doing as good of a job as they could be doing um like people that are negative uh in my life, I'm more able to identify them, so I don't act on that. It's a very bad time to act on those decisions. But I'm quite well made recording recording that information because I usually when I'm well rested and happy, I see the beauty in everybody which can get you into trouble, got to balance those two things. But yes, it's fascinating [/INST] irony that too, which is the fact that, you know, when you're well rested and well slept just as you said, you see the beauty in life and it sort of enlivens you and sort of gives you a quality of life that's emotionally very different yet then we are contrasting that against the need for not getting enough sleep because of the beautiful things that you want to accomplish in life. And I don't actually see them as it you know sort of completely counterintuitive or paradoxical because I still think that you can strive for all of the brilliant things that you are striving for to have the monumental goals. The Herculean challenge is that you wish to take on and solve. They can still enthrall you and excite you and stimulate you. But because of the insufficiency that they can or that goal can produce, it will shave off the beauty of life that you experience in between. And again, this is just about the trade off. I will say though that and this is not applicable to your circumstance. Um we do know that insufficient sleep is very strongly linked to suicide ideation, suicide attempts and tragically suicide completion as well. and in fact in 20 years of studying sleep, we have not been able to discover a single psychiatric condition in which sleep is normal. Mm And I think that is a profound state. I think it tells us so much about the role of sleep as a potential causal agent in psychiatric conditions. I also think it's a potential sign that we should be using sleep as a </s><s>[INST] tool for [/INST] the prevention of grave mental illness. </s><s>[INST] Yes, both of cause and the solution. So, I mean, I mean, me personally, I've gone through a few dark periods quite recently and it was almost always sleep is not the cause, but asleep is the catalyst from going to a bad time to a very bad time. Yeah. And so it's, it's definitely, it's definitely true. And it's funny how asleep can just cure all of that. [/INST] There's actually a beautiful quote by an american entrepreneur called E. Joseph Koosman Who once said that the best bridge between dispersion and hope is a good night's sleep. And I still quite so much ink and hundreds of pages inelegantly trying to say the same thing in my book and he said it in one </s><s>[INST] line and [/INST] it's beautiful. </s><s>[INST] What do you think is? Uh, we've been talking about how to extend this life, how to make it a good life. I've been talking about uh, love, what do you think is the meaning of this whole ride of life of life? Why do we want to make it a good one? Do you think there's a meeting, Do you think there's an answer to the why? [/INST] Okay, for me personally, I think the, the meaning of life is, is to eat, is to sleep, is to fall in love, is to cry and then to die? Oh, and probably race Cause in between </s><s>[INST] these cars. Well, there's a whole topic of sex we didn't talk about probably. [/INST] So should we </s><s>[INST] do that? Well, maybe if you'll have me back that I will give around next time. We will do another three hours on Sex alone. Yeah, it has been uh over three hours. Gosh, I'm a big fan of your work. I think you're doing really important work, even despite all the things I've been saying about the madness of my own sleep schedule, I think you're helping millions of people. So it's an honor that you spend your valuable time with me and I can't wait until your podcast comes out. I'm a huge fan of podcast. I'm a huge fan of you and it's just an honor to know you and to get a chance. Hopefully in the future to work together with you. You're [/INST] a brilliant man and you're doing amazing things and I feel immensely on it to have I met you too. Now know you and um, to start calling you a friend. Thank you for what you do for the world. And um, for me included, </s><s>[INST] thank you, Matt, take care. Thanks for listening to this conversation with matt walker and thank you to stamps dot com squarespace letter Green's better help. And on it, check them out in the description to support this podcast. And now let me leave you with some words from Nicola Tesla who we discussed in this podcast as sleeping very few hours a night. All those great in the past was ridiculed, condemned, combated and suppressed only to emerge all the more powerfully, all the more triumphantly from the struggle. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] and it takes, I guess, good leaders to set an example. Yeah, I do believe that there's like individual people can have a ripple effect. So that's what I try to do, sort of embody the, I'm just one ant. But I, one of the things I have faith in is I'm trying to do that more. I know this is a podcast, but I'm trying to do less talking and more doing. I've been disappointed in myself, if I'm being honest, how much talking I've been doing, you know, as opposed to, you know, like in my own private life, I live the thing I talk about, but I also haven't created much, you know? And I believe in the power of individuals that create stuff, I create an idea through those individuals that try to create something new, the world progresses. And hopefully there's more and more, more and more of those people. So you mentioned kind of people who, what the Bitcoin community might call scammers, an idea. I have a lot of passions in my life that I focus a lot of my attention to. You know, Bitcoin doesn't happen to be yet one of them. Bitcoin and cryptocurrency, you know? Well, I've said yet. I'm always looking for things to really fall in love with. So how is a person like me supposed to figure out, I also happen to have a platform a little bit, and how am I supposed to figure out who is interesting, what is an interesting set of ideas and what are not. Because people are financially tied into a lot of the cryptocurrencies that we're talking about, certainly with Bitcoin, you know, their livelihood, their wellbeing is tied up to it. So it becomes much more emotional, much more personal. It's no longer purely an exploration of ideas. It's really almost like a threat on your property. Like it's a personal threat. It makes it very difficult to explore those ideas. So I understand it, but it makes it very difficult for somebody like me to just walk in and be curious. So how do I proceed in this difficult world in exploring this landscape and not give a platform [/INST] to ideas that may harm others? I'm glad you said yet. I guess first I'd like to commend your forthrightness about this, because I don't think many people try to walk that line necessarily. People, again, kind of the territorial imperative, they'll put whoever on, they'll help expand their reach. Oh yeah, that's right. Or say whatever needs to be said to expand their reach. So I think you're coming from a good place. I'll say that. There's a great piece written on the topic of scammers and scamming. I think it was by Goldstein. He wrote a piece called Everyone's a Scammer. And it's sort of back to this general human proclivity to try and get something for nothing always. Which again, it can be positive, it can be innovative, or it can be negative. It can be trying to steal from people. Oh yeah, that's right. That might be, I think that's a useful piece just to kind of see the crypto world do that lens. And that's how Bitcoiners are thinking all the time. They are by nature adversarial thinkers. So they're trying to minimize the need for trust in any situation and maximize verification. As far as sifting through the ideas, I guess this is back where the cultural immune system has some utility. Because there were times when I thought this particular crypto asset, Augur was one I was really into, that it could facilitate prediction markets and prediction markets could make markets more efficient, et cetera, et cetera. But when that investment thesis basically met the cultural filter or immune system, it forced me to reevaluate my position, it forced me to really look into it more deeply. And through that exploration, I realized that it would need to be built on Bitcoin to work, basically. So, but it really comes down to like you doing your homework, but we can't all deeply evaluate every idea out there, right? </s><s>[INST] Yeah, yeah. One of the things I struggle with was Alex Jones, for example, had dinner with him. I could tell that would be a very fun conversation, but like then I also understand that there's like consequences to that conversation that should be explored with care. And so you need to take on the responsibility of being a chef or the puffer fish and all those kinds of things. That said, just like you said, it's very difficult to know this ahead of time. And I will probably make mistakes. And that's a shitty thing to have to live with, that I'm going to make mistakes and some of them very large, like, yeah. I mean, I can imagine a bunch of different ways, but all we can do in this world is once we make the mistakes, we acknowledge those mistakes. [/INST] Yes, yes. </s><s>[INST] Learn. And learn. And also, I have to put this on the rest of us that you don't take one thing that a person did and then burn them at the stake for it. That you realize that we all make mistakes, that a particular mistake does not make the person. And, you know, this applies to taking stuff out of context over, you know, hundreds of hours of talking, but it applies to actual like in context, big mistake. Okay. So what if I murdered somebody at some point? Just give me a break. No, there are some things that are too far, of course, but in general, we need to give each other a chance. Yeah. But I'm still, I walk with a heavy heart knowing that I'll probably make a mistake, especially one that I didn't mean to. [/INST] That's the one that worries me most, the one that worries me most. Well, this is human nature. Like, Hamartia, to miss the mark, that's the root word of sin. We are sinful by nature. We can't help it. There's no way, again, pain is information, right? There's no way to learn other than trying, failing, learning, and then you put yourself in better formation, in formation, to better deal with it next time. So I hope, I don't get the sense that you're actually afraid of making a misstep. Like, I think you're just maybe disappointed it's a better word. Like, you know you're gonna make the mistakes. Yeah, exactly, that's a much, much better word. But we have to embrace that. Yeah. That's the only way anything, it's the only way we can advance, is that we're dealing with an incomprehensible reality. All we can do is throw spaghetti at the wall and see what sticks. Yeah. And in that process, we're all inherently gonna hurt ourselves and hurt others, and that's where love and forgiveness come into play, right? </s>

<s>[INST] a million per ton. [/INST] Yes, ideally less. Much less than a million tons. But if it's not like it's going to be well how much can society afford to spend or just want to spend on a self sustaining city on mars, the self sustaining part is important, like it's just the key threshold. Um The grateful to will will have been passed when the city on mars it can survive even if the spaceships from a stop coming for any reason, it doesn't matter what the reason is, but if they stop coming for any reason will it die out or will it not? And if there's even one critical ingredient missing, then it still doesn't count. It's like, you know if you're on a long sea voyage and you've got everything except vitamin C. It's only a matter of time, you know you're gonna die. So so we're gonna get Morris Amauri city to the point where it's self sustaining um I'm not sure this will really happen in my lifetime, but I hope to see it at least have a lot of momentum and and then you can say, okay, what is the minimum tonnage necessary to have a self sustaining city? Um and there's a lot of uncertainty about this. You can, I don't know, it's probably at least a million tons because you have to set up a lot of infrastructure on on MARS. Um like I said, you can't be missing any anything that in order to be self sustaining, you can't be like you need a semiconductor fabs, you need iron ore refineries, like you need lots of things, you know, So um and MArs is not super hospitable. It's it's the least inhospitable planet, but it's definitely a fixer upper of a planet </s><s>[INST] outside of Earth. [/INST] Yes. Earth is pretty like easy. And </s><s>[INST] also should, we should clarify in the solar system, Yes, in the solar system, there might be nice like vacation spots, [/INST] there might be some great planets out there, but it's hopeless </s><s>[INST] to get their way [/INST] way, way, way, way too hard to say the least. </s><s>[INST] Let me push back on that. Not really a pushback but a quick curveball of a question. So you didn't mention physics as the first starting point. So general relativity allows for warm holes. They technically can exist. Do you think? Um those can ever be leveraged by humans to travel faster than the speed of light. [/INST] Well </s><s>[INST] the whole thing [/INST] is, is debatable. Uh the, that we currently do not know of any means of going faster than the speed of light there, there is like, like there are some ideas about having space like so, so you're gonna move at the speed of light through through space, but if you can make space itself move that, that that's like that, that's what warping space um spaces is capable of moving faster than the speed of light. Like the universe in the big Bang, the universe expanded it much, much more than the speed of light by a lot. Yeah. Um so, but the, If this is possible that the amount of energy required 12 space is so gigantic, it's boggles the mind. </s><s>[INST] So all the work you've done with propulsion, how much innovation is possible with rocket propulsion is this? Um I mean you've seen it all and you're constantly innovating in every aspect. How much is possible? Like how much can you get 10 x somehow. Is there something in there in physics that you can get significant improvement in terms of efficiency of engines and all those kinds of things? [/INST] Well, as I'm saying like the really the Holy Grail is a fully and rapidly reusable orbital system. Um so, uh right now The Falcon nine is the only reusable rocket out there, but the booster comes back and lands and you've seen the videos uh and we get the nose cone or fairing back but we do not get the upper stage back. So ah, that means that we have a minimum cost of building up for stage. Um You can think of like a two stage rocket of sort of like to our planes, like a big airplane and a small airplane. Um, and we get a big airplane back, but not the small airplane and so it still costs a lot, you know, so that upper stages, You know, at least $10 million. Um, and then the degree of the booster is not as reused, it's not as rapidly and completely reusable as we'd like and or the Ferencz, so, you know, are kind of minimum marginal cost, not counting overhead for perf lighters on the order of $15 - $20 million dollars maybe. Um, So, uh, that's, that's extremely good for, it's by far better than any rocket ever in history. Um, but uh, with full and rapid reusability, we can reduce the cost per ton to orbit by A factor of 100. Just think of it like um, like imagine if you had an aircraft or something or a car. Oh yeah, and if you had to buying your car every time you went for a drive would be very expensive. Very silly frankly. But, but in fact you just refuel the car or recharge the car and that makes your trip like 1000 times cheaper. So it's the same for rockets if you, it's very difficult to make this complex machine that can go to orbit and so if you cannot reuse it and have to throw even any part of any significant part of it away that massively increases the cost. So, you know, starship in theory could do a cost per launch of like a million, maybe $2 million or something like that and and put over 100 tons in orbit, which is crazy. </s>

<s>[INST] and actually uh, you're actually nudging closer to the autonomous vehicle space because from everything I've seen the level of frustration people experience upon failure of natural language understanding is much higher than failure in other context, people get frustrated really fast. So if you screw screw that experience up even just a little bit, they give up really quickly. [/INST] Yeah. And I think you see that in the data while while it's tremendously successful, the most common interactions are play pause and you know next the things where if you compare it to taking up your phone, unlocking and bringing up the app and skipping, clicking, skip. It was it was much lower friction, but then uh for for longer, more complicated things like can you find me that song of people still bring up the phone and search and then play it on the speaker. So we tried again to build a fault tolerant ui Where for the more for the more complicated things you can still pick up your phone have powerful full keyboard search and then try to optimize for where there is actually lower friction and try to, it's kind of like the test the autopilot thing, you have to be at the level where you're helpful if you're too smart and just in the way people are going to get frustrated. </s><s>[INST] And first of all I'm not obsessed with their way to happen, it's just a good song. But let me mention that as a use case because it's an interesting one, I've literally told I want to, I don't want to say the name of the speaker because when people are listening to it will make their speaker go off. But I talked to the speaker and I say play stairway to heaven. And every time it like not every time but a large percent of the time it plays the wrong stairway to heaven. It plays like some cover of the and that part of the experience. I actually wonder from a business perspective the Spotify control that entire experience or no it seems like the N. L. U. The natural language stuff is controlled by the speaker and then Spotify stays at the layer below that. [/INST] It is a good and complicated question, some of which is dependent on the on the partner. So it's hard to comment on the on the specifics but The question is the right one. The challenges If you can't use any other personalization. I mean we know which stairway to heaven and and the truth is maybe for for one person it is exactly the cover that they want and they will be very frustrated if a place I I think we I think we default to the right person but you actually want to be able to do the cover for the person that just play the cover 50 times. Or Spotify is just going to seem stupid. So you want to be able to leverage the personalization but you have this stack where you have the the A. S. R. And this thing called the N best list of the 10 best guesses here and then the presentation comes in at the end. You actually want the personalization to be here when you're guessing about what they actually meant. So we're working with these partners. And it's a complicated it's a complicated thing where you want to you want to be. So first of all, you want to be very careful with your users data. You don't want to share your user's data without their permission, but you want to share some data so that the experience gets better. Um So that these partners can understand enough but not too much and so forth. So it's really the trick is that it's like a business driven relationship where you're doing pro development across companies together. Which is which is really complicated. But this is exactly why we built our own N. L. U. So that we actually can make personalized guesses because this is the biggest frustration from a user point of view. They don't understand about SRS and and best lists and business deals. They're like how hard can it be? I've told this thing 50 times this version and still the place the wrong thing. It can't it can't be hard. So we we try to take the user project. The user, the user is not gonna understand the complications of business. We have to solve it. </s><s>[INST] Let's talk about sort of a complicated subject that I myself I'm quite torn about the idea is sort of of um paying artists, Right? Uh I saw as of 31 August 2018 Over $11 billion dollars were paid to rights holders, so and further distributed to artists from Spotify. So a lot of money is being paid to artists, first of all, uh, the whole time is a consumer for me, when I look at Spotify, I'm not sure I'm remembering correctly, but I think you said exactly how I feel. Which is, this is too good to be true. Like when I started using Spotify, I assume you guys will go bankrupt in like a month. It's like, this is too good. [/INST] A lot of people did. </s><s>[INST] It was like, this is amazing. So, one question I have a sort of the bigger question, how do you make money in this complicated world? How do you deal with the relationship with record labels? Who ah are complicated? Uh these big, essentially in have the task of hurting cats, but like rich and powerful cats. And also have the task of paying artists enough and paying those labels enough and still making money in the internet space where people are not willing to pay hundreds of dollars a month. So how do you navigate the space? How do you [/INST] know that's a beautiful description, hurting rich cats. Yeah, I heard that before. It is very complicated. And I think, yeah, certainly, actually betting against Spotify has been statistically a very smart thing to do. Just looking at the, at the line of roadkill in music streaming services. Um, It's it's kind of, I think if I understood the complexity when I joined Spotify, unfortunately, fortunately I didn't know enough about the music industry to understand the complexities because then I would have made a more rational guess that it wouldn't work. So, you know, uh, ignorance is bliss, but I think there have been a few distinct challenges. I think as I said, one of the things that made it work at all was that Sweden and the nordic was a lost market. So, um, there was, you know, there was, there was no risk for labels to try this. I don't think it would have worked if if the market was was healthy. So, so that was the initial condition then then we have this tremendous challenge with the model itself. So now most people were pirating, but for the people who bought a download or cd the artists would get all the revenue for all the future place then. Right, so you got it all up front where the streaming model was like almost nothing, they want almost nothing they do. And then at some point, this curve of incremental revenue would intersect with your day one payment and that took a long time to play out before before um, the music labels, they understood that, but on the artist side, it took a lot of time to understand that actually, if I have a big hit, that is going to be played for for for many years, this is a much better model because I get paid based on how much people use the product, not how much they thought they would use a day one or so forth. So it was a complicated model to get across and, but time help with that, right? And now, now the revenues to the music industry actually are bigger again, then, you know, it's going through this incredible dip and now they're back up and so we're very proud of having, having been a part of that. Um, so there have been distinct problems, I think when it comes to the, to the labels, we have taken the painful approach, some of our competition at the time, they kind of, they kind of looked at other companies and said if we just, if we just ignore the rights, we get really big really fast, we're going to be too big for the, or the labels to kind of too big to fail. They're not going to kill us. We didn't take that approach. We went legal from day one and we, we negotiated and negotiated and negotiated was very slow. It's very frustrating. We were angry at seeing other companies taking shortcuts and seeming to get away with it, was this this, this game theory thing where over many rounds of playing the game, this would be the right strategy. And even though clearly there's a lot of frustrations at times during renegotiations, there is this, there is this weird trust where we have been honest and fair, we've never screw them, they never screwed us. It's tenuous. But there's this trust in like they know that if music doesn't get really big, if lots of people do not want to listen to music, I want to pay for it. Spotify has no business model. So we actually are incredibly aligned, right? Other companies not to be changed, but other companies have other business models where even if the menu music from no money for music, they're still be profitable companies. But what if I want? So, and I think the industry sees that we are actually aligned business wise. So there is this this trust that allows us to to do product development, even if it's scary. Um, you know, taking risks. The free model itself was an incredible risk for the music industry to take that they should get credit for some of it was that they had nothing to lose in Sweden. But frankly, a lot of the labels also took risk. And so I think we built up that trust with, I think herding cats sounds a bit what's the word? It sounds like dismissive, </s>

<s>[INST] what was being publicly released this data. So the names from those roles were removed but what was released as the preference or the ratings of what movies you like and don't like and from that combined with other things I think foreign posts and so on. You can start making [/INST] that case. It was specifically the internet movie database where where lots of netflix users publicly rate their you know their movie preferences. And so the anonymous data and netflix when kind of and it's just this phenomenon I think that we've all come to realize in the last decade or so. Is that just knowing a few apparently irrelevant, innocuous things about you can often act as a fingerprint like if I know you know what what rating you gave to these 10 movies and the date on which you enter these movies. This is almost like a fingerprint for you is in the sea of all netflix users. It was just another paper on this in science or nature of about a month ago That you know kind of 18 attributes. I mean my favorite example of this, this was actually a paper um from several years ago now where it was shown that just from your likes on facebook, just from the, you know, the things on which you clicked on the thumbs up button on the platform, not using any information, demographic information, nothing about who your friends are. Just knowing the content that you had liked. Um, was enough to, you know, in the aggregate accurately predict things like sexual orientation, drug and alcohol use whether you are the child of divorced parents. So we live in this era where you know, even the apparently irrelevant data that we offer about ourselves on public platforms and forums, often unbeknownst to us more or less acts as signature or fingerprint and that if you can kind of, you know, do a join between that kind of data and allegedly anonymous data, you have real trouble. </s><s>[INST] So is there hope for any kind of privacy in a world where a few likes can can identify you. [/INST] So there is differential privacy. What is differential differential privacy basically is a kind of alternate, much stronger notion of privacy than these anonymous ization ideas. And it, you know, it's a technical definition but like the spirit of it is we we we compare to alternate worlds. Okay, so let's suppose I'm a researcher and I want to do, you know, I there's a database of medical records and one of them's yours and I want to use that database of medical records to build a predictive model for some disease. So based on people's symptoms and test results and the like I want to, you know, build a probably model predicting the probability that people have disease. So, you know, this is the type of scientific research that we would like to be allowed to continue. And in differential privacy you act ask a very particular counterfactual question. We basically compare to alternatives. one is when I do this by build this model on the database of medical records including your medical record. And the other one is where I do the same exercise with the same database with just your medical record removed. So basically, you know, it's two databases, one with end records in it and one with N -1 records in it. The N -1 records are the same and the only one that's missing in the second case as your medical record. So differential privacy basically says that any harms that might come to you from the analysis in which your data was included are essentially nearly identical to the harms that would have come to you if the same analysis had done been done without your medical record included. So in other words, this doesn't say that bad things cannot happen to you as a result of data analysis. It just says that these bad things were going to happen to you already, Even if your data wasn't included and to give a very concrete example, right? You know, um you know, like we discussed at some length the study that, you know, the in the 50s that was done that created the established the link between smoking and lung cancer. And we make the point that like, well, if your data was used in that analysis and you know, the world kind of knew that you were a smoker because you know, there was no stigma associated with smoking before that, those findings real harm might have come to you as a result of that study that your data was included in in particular, your insurer now might have a higher posterior belief that you might have lung cancer and raise your premiums. So you've suffered economic damage. But the point is is that If the same analysis has been done without with all the other and -1 medical records and just years missing, the outcome would have been the same. Your your data was an idiosyncratically in crucial to establishing the link between smoking and lung cancer. Because the link between smoking and lung cancer is like a fact about the world that can be discovered with any sufficiently large database of medical records. </s><s>[INST] But that's a very low value of harm. Yeah. So that's showing that very little harm has done great. But how what is the mechanism of differential privacy? So that's the kind of beautiful statement of it. But what's the mechanism by which privacies [/INST] preserve? Yeah. So it's basically by adding noise to computations. Right? So the basic idea is that every differentially private algorithms, first of all, or every good, differentially private algorithms for useful one um, is a probabilistic algorithm. So it doesn't on a given input. If you gave the algorithm the same input multiple times, it would give different outputs each time from some distribution. And the way you achieve differential privacy algorithmic lee is by kind of carefully and tastefully adding noise to a computation in the right places. And, you know, to give a very concrete example, if I want to compute the average of a set of numbers, right? The non private way of doing that is to take those numbers and average them and release like a numerically precise value for the average. Okay, in differential privacy, you wouldn't do that. You would first compute that average two numerical precision and then you add some noise to it, right? You'd add some kind of zero mean, you know, Gaussian or exponential noise to it so that the actual value you output is not the exact mean, but it'll be close to the mean, but it'll be close the noise that you add will sort of prove that nobody can kind of reverse engineer any particular value that went into the average. </s>

<s>[INST] we've got a lot of time in my office. Yeah, yeah, yeah. And so then we went on our merry way, everyone went to different places, Charles landed at Georgia tech, which was, uh, what he always dreamed he would do. And so that worked out well. Um, I came up with a saying at the time, which is luck favors the Charles, it's kind of like luck favors the prepared, but Charles like, like he wished something and then it would basically happen just the way he wanted. It was, it was inspirational to see things go that way things worked out and we stayed in touch and then, um, I think it really helped when you were working on, I mean you kept me in the loop for things like threads and, and the work that you're doing at Georgia tech. But then when they were starting their online Master's program, he knew that I was really excited about moocs and online teaching and he's like, I have a plan and I'm like, tell me your plan. He's like, I can't tell you the plan yet because they were deep in negotiations between Georgia tech and Udacity to make this happen and they didn't want it to leak. So Charles wood kept teasing me about it, but wouldn't tell me what was actually going on. And eventually it was announced and he said, I would like you to teach the machine learning course with me. I'm like, that can't possibly work. Um, but it was a great idea and it was, it was super fun. It was a lot of work to put together, but it was, it was really great and was that the first time you thought about, first of all, was it the first time you got seriously into teaching? I mean, you know, I'm trying to get the findings like this is already and I had after you jump too, so like there's a little bit of jumping around in time. Yeah, sorry about that, big jump in time, so like the moocs thing, so Charles got Georgia tech and he may be Charles, maybe this is [/INST] A 2002, </s><s>[INST] He got to Georgia Tech in 2002 and but and worked on things like revamping the curriculum, the undergraduate curriculum so that it had some kind of semblance of modular structure because computer science was at the time moving from a fairly narrow specific set of topics to touching a lot of other parts of of of intellectual life and the curriculum was supposed to reflect that. And so um Charles played a big role in in kind of redesigning that and then [/INST] and for my and for my my labors I ended up to his associate dean </s><s>[INST] right, he got to become associate Dean of charge of educational stuff. Be a valuable lesson if you're good at something, uh they will give you responsibility to do more of that thing until you show competence. Don't show competence. If [/INST] you know what the responsibility, here's what they say. Uh the reward for good work is more work. The reward for bad work is less work, which I don't know depending on what you're trying to do that week. One of those is better than the other. One of the problems with the word works are to interrupt </s><s>[INST] is that it seems to be an antonym in this particular language. We have the opposite of happiness, but it seems like they're they're like, that's one of, you know, we talked about balance. It's always like work life balance always rubbed me the wrong way as a terminal. And I know it's just words like the opposite of work is play ideally work his play. [/INST] Oh, I can't tell you how much time I spend. Certainly was a bell Labs would except for a few very key moments as a professor I would do this to. I just cannot believe they're paying me to do that because it's fun. It's something that I would I would do for a hobby if I could anyway, so that's what it worked. I'm sure you want to be saying </s><s>[INST] that when this is being recorded as [/INST] a dean, that is not true at all. I need to raise. But but I think here with this that even though a lot of time passed, you know, Michael, I talked almost everywhere. We texted almost every day during the period </s><s>[INST] Charles. At one it took me there was the I. C. M. L. Conference, the machine learning conference was in Atlanta. I was the chair. The general chair of the conference Charles was my publicity chair or something like that or fundraising chair. Yeah. Um, but he decided to be really funny if he didn't actually show up for the conference in his own home city. Uh, so he didn't, but he did at one point, picked me up at the conference in his Tesla and drove me to the Atlanta mall and forced me to buy an iphone because he didn't like how it was to text with me and thought it would be better for him if I had an iphone, the text would be somehow smoother. And it was, and it was, [/INST] and it is and his life has been in </s><s>[INST] my life is better. And so, but, but it was, yeah, Charles forced me to get an iphone so that he could text me more efficiently. I thought that was an interesting moment. It [/INST] works for me anyway, so we kept talking the whole time and they eventually did the, we did the teaching thing and it was great and there's a couple of reasons for that by the way. One is, I really wanted to do something different. Like you've got this medium here, People claim it can change things. What's the thing that you could do in this medium that you could not do otherwise? Uh, besides edit. Right. I mean, what could you do and being able to do something with another person with that kind of thing. It's very hard. I mean you can take turns, but teaching together, having conversations very hard. Right? So that was a cool thing. The second thing you may excuse to do more stuff with </s>

<s>[INST] So it gives you the context of- How honest they're being. [/INST] The state of the person is their answer. How honest they're being. Yeah, yeah, they're honesty. How forthcoming they're being </s><s>[INST] and how accurate they're being. And then the result of the classification [/INST] based on the test are these code types. Right, well, so you have these clinical scales as well. You have 10 clinical scales that look for different kind of primary clinical pathology issues. This test doesn't tell you anything good about yourself. At best, it just tells you that you're not responding in a way that is dishonest and that you are kind, not hugely problematic, but there's, you know, it's not looking for strength. So you have these 10 clinical scales that look for variations above the mean of the population in certain areas, anywhere from, you know, depressive symptoms, manic symptoms, physical complaint, anxiety, nervousness, aggression, social engagement, whole scope of human experience. And then there are much more nuanced scales from those, so little sub scales. And then the real power though of the MMPI-2 is in, as you said, these code types. And these code types are additional patterns that have been detected that really can be more defining of a personality. So you look for peaks. There can be either two extreme peaks or three typically that make a code type. And those peaks are higher scores on these personality traits and specific code types can give you a very nuanced picture of a person's general approach to life and their personal relationships, </s><s>[INST] just their personality. So you can build on top of those code types an understanding, yeah, how that person's going to deal with different kinds of situations. And then there's, by the way, a lot of code types. There are a lot of code types. [/INST] I was looking at them. They're pretty interesting. There are a lot of code types. I was looking at them. They're pretty interesting. </s><s>[INST] They are a lot. I want to take this. Truly fascinating. I want to take this test. [/INST] I wanted to see which one I would- I have given it to some people in my life. </s><s>[INST] It's just phenomenal. How hard is it on your side [/INST] of the table to give the test. Oh, it's easy. You just proctor, you just make sure that somebody, there's no distraction, that they're well rested, they are sitting there and they can </s><s>[INST] just take it in front of you. So I guess the question is because the questions are well designed and that it's hard to mess with them. [/INST] You just give the. </s><s>[INST] It's very hard to beat it, you just hand it to them. [/INST] And it's yes and no. </s><s>[INST] It's yes and no. [/INST] Okay. But I should also add to this that this test, as much as I love it, and it is the most researched and widely used personality assessment in the world, it is not in and of itself definitive. So you use it like you already have sort of a hypothesis and you use this for clarification. And it has a ton of value for showing somebody's response or their approach, how forthcoming they're being. But other than that, you really need to consider it as a piece of the puzzle. You had said stitched together earlier and that was just one of those points you made </s><s>[INST] that was perfect for describing this. There's probably no one perfect test, right? [/INST] For personality? </s><s>[INST] No. I wonder, especially with advancements of AI, there could be more and more sophisticated ways of measuring, of collecting data about your behavior. Absolutely, there could be. And being able to measure some kind of more productive kind of, especially not in a forensic context, but more in trying to figure out how to improve your lifestyle, improve your relationships, all that kind of stuff. So the results of the test with Amber Heard, if you can speak to the public stuff, your behavior. Absolutely, there could be. You said that the results of Ms. Heard's evaluation supported two diagnoses, borderline personality disorder and histrionic personality disorder. Can you speak to each one of those? What are the basic characteristics [/INST] of borderline personality disorder? Sure, well, so right now, the DSM-5, which is sort of the Bible for mental disorders, it's what we go to our diagnostic manual, it classifies personality disorders according to clusters. And cluster B is one that involves the emotionally erratic, interpersonally erratic emotional disorders. And those include histrionic personality disorder, borderline personality disorder, narcissistic personality disorder and anti-social personality disorder. Eventually there's been some research on this and a lot of support for us, eventually moving into a more spectrum type approach to considering personality disorders, where you'd essentially be looking at dysfunction in different domains of somebody's functioning that has persisted over time. And again, the really important part is it seems to be a stable trait part of their personality that it's in their interpersonal relationships, it's in how they handle their own life, their own functioning, their mood, and it's not just situation-based, it seems to be all areas. I don't love the title, histrionic personality disorder. I think its history, it's pretty controversial and there's some misogyny in it. But that all being said, as a servant to the court and somebody who is there to just provide the science as it exists today, my job is to relay, and in this specific case, I was ordered to provide my diagnostic impressions, a diagnosis, and I don't get to decide which diagnosis, whether I like a certain diagnosis or not, ultimately, if the criteria are met, that diagnosis is given. So as we have it right now with the current personality disorder categories, histrionic personality disorder is probably the most controversial. Some people believe that it is narcissistic personality disorder-lite. So a less obvious, a less malicious version of narcissistic personality disorder. And I think that will probably get sussed out if we do move to a more spectrum-based approach cause then you would be describing sort of a personality disorder and then you would add the traits to it. So you know, with issues in interpersonal functioning and et cetera. So you could be a little bit more specific rather than having to just put somebody in a category. </s>

<s>[INST] Because there could be something much more generalizable than the prime number sequence. It's ultimately the question of a signal that's very difficult to compress, in the general sense of what compress means. So maybe as we get better and better machine learning methods that automatically figure out, analyze the data to understand how to compress it, that you'll be able to discover data that for some reason is not compressible. But then compression really is a bottomless pit, because that's really what intelligence is, [/INST] is being able to compress information. Yeah. And to some degree, the more you... I would imagine, I don't work in compression algorithms, but I would imagine the more you compress your signal, the more assumptions that kind of go on behalf of the decoder, the more skilled they really have to be. A prime number sequence is completely unencoded information, essentially. But if you look at the Arecibo message, they were fairly careful with their pixelation of this simple image they sent to try and make it as interpretable as possible, to be that even a dumb alien would be able to figure out what we're trying to show them here. Because there's all sorts of conventions and rules that are built in that we tend to presume when we design our messages. And so if your message is assuming they know how to do an MP3 decoder, a particular compression algorithm, I'm sure they could eventually reverse engineer it and figure it out, but you're making it harder for them to get to that point. So maybe I always think, you probably would have a two tier system, right? You'd probably have some lower tier key system, and then maybe beneath that, you'd have a deeper compressed layer of more in-depth information. </s><s>[INST] What about maybe observing actual physical objects? So first, let me go to your tweet as a source of inspiration. You tweeted that it's interesting to ponder that if Oort Clouds are ever mined by the systems of alien civilizations, mining equipment from billions of years ago could be in our Oort Cloud, since the Oort Clouds are, they extend really, really, really far outside the actual star. So mining equipment, just basic boring mining equipment out there. I don't know if there's something interesting to say about Oort Clouds themselves that are interesting to you and about possible non-shiny light emitting mining equipment from [/INST] alien civilization. Yeah, I mean, that's kind of the beauty of the field of techno signatures and working for life, is you can find inspiration and intellectual joy in just the smallest little thing that starts a whole thread of building upon it and wondering about the implications. And so in this case, I was just really struck by, we kind of mentioned this a little bit earlier, the idea that stars are not static. We tend to think of the galaxy as having stars in a certain location from the center of the galaxy, and they kind of live there. But in truth, the stars are not only orbiting around the center of the galaxy, but those orbits are themselves changing over time, they're processing. And so in fact, the orbits look more like a spirograph if you've ever done that as a kid. They kind of whirl around and trace out all sorts of strange patterns. And so the stars intersect with one another. And so the current closest star to us is Proxima Centauri, which is about 4.2 light years away, but it will not always be the closest star, over millions of years, it will be supplanted by other stars. In fact, stars will come even closer than Proxima within just a couple of light years. And that's been happening, not just we can project that will happen over the next few million years, but that's been happening, presumably, throughout the entire history of the galaxy for billions of years. If you went back in time, there would have been all sorts of different, nearest stars at different stages of the Earth's history. Those stars are so close that their Oort clouds do intermix with one another. The Oort cloud can extend out to even a light year or two around the Earth. There's some debate about exactly where it ends. It probably doesn't really have a definitive end, but more just peters out more and more and more </s><s>[INST] as you go further away. By the way, for people who don't know an Oort cloud, I don't know what the technical definition is, but a bunch of rocks that kind of know [/INST] objects that orbit the star, and they can extend really, really far because of gravity. These are objects that probably are mostly icy rich. They were probably formed fairly similar distances to Jupiter and Saturn, but were scattered out through the interactions of those giant planets. We see a circular disk of objects around us, which kind of looks like the asteroid belt, but just further away called the Kuiper belt, and then further beyond that, you get the Oort cloud. The Oort cloud is not on a disk. It's just a sphere. It kind of surrounds us in all directions. These are objects that were scattered out three-dimensionally in all different directions. Those objects are potentially resources for us, especially if you were planning to do an interstellar mission one day. You might want to mine the water that's embedded within those and use that as either oxygen or fuel for your rocket. It's quite possible. There's also some rare earth metals and things like that as well, but it's quite possible that a civilization might use Oort cloud objects as a jumping off point, or in the Kuiper belt, you have things like Planet 9 even. There might even be objects beyond in the Oort cloud, which are actually planet-like, that we just cannot detect. These objects are very, very faint, so that's why they're so hard to see. Even Planet 9, it's hypothesized to exist, but we've not been able to confirm its existence because it's at something like a thousand AU away from us, thousand times the distance of the earth from the sun. Even though it's probably larger than the earth, the amount of light it reflects from the sun, the sun just looks like a star at that point, so far away from it, that it barely reflects anything back. It's extremely difficult to detect. So there's all sorts of wonders that may be lurking out in the outer solar system, and so this leads you to wonder, in the Oort cloud, that Oort cloud must have intermixed with other Oort clouds in the past, and so what fraction of the Oort cloud truly belongs to us, belongs to what was scattered from Jupiter and Saturn, what fraction of it could in fact be interstellar visitors? We've got excited about this recently because of Oumuamua, this interstellar asteroid, which seemed to be at the time the first evidence of an interstellar object. But when you think about the Oort cloud intermixing, it may be that a large fraction of comets, comets that are seeded from the Oort cloud that eventually come in, some of those comets may, indeed, have been interstellar in the first place, that we just didn't know about through this process. There even is an example, I can't remember the name, there's an example of a comet that has a very peculiar spectral signature that has been hypothesized to have actually been an interstellar visitor, but one that was essentially sourced through this Oort cloud mixing. And so this is kind of intriguing. It also, you know, the outer solar system is just such a, it's like the bottom of the ocean. We know so little about what's in the bottom of our own planet's ocean. And we know next to nothing about what's in the outskirts of our own solar system. It's all darkness. </s>

<s>[INST] isn't it another trickier form of data augmentation. [/INST] Yes. But it's also data augmentation that can happen outside of the specification that your brain is tuned to. So basically people are over clocking the brains and that that produces states that are subjectively extremely interesting. </s><s>[INST] Yeah. I just [/INST] from the outside very suspicious. </s><s>[INST] So I think I'm over applying the metaphor of a neural network in my own mind which I just think that doesn't lead to overfitting right. But uh huh. But you were just sort of anecdotally saying my experiences with people that have done psychedelics or that kind of quality. [/INST] I think it typically happens. So if you look at people like timothy leary and he has written beautiful manifestos about the effect of LSD on people. He genuinely believed, he writes in his manifesto is that in the future science and art will only be done on psychedelics because it's so much more efficient and so much better. And he gave uh LSD to Children in his community of a few 1000 people that he had near san Francisco and basically he was losing touch with reality. He did not understand the effects that the things that he was doing would have on the reception of psychedelics by society because he was unable to think critically about what happened. What happened was that he got a euphoric state that euphoric state happened because he was overfitting he was taking this sense of euphoria and translating it into a model of actual success in the world. But he was feeling better, limitations had disappeared that you expect appearance to be existing and he didn't get superpowers. </s><s>[INST] I understand what you mean by overfitting now. Uh, there's a lot of interpretation to the term overfitting in this case, but I, I got you. So he was getting, he was getting a positive awards from a lot of actions that [/INST] you're not just this. So if you take, for instance, john really who was studying dolphin languages and aliens and so on, a lot of people that use psychedelics became very loopy and the typical thing that you notice when people are on psychedelics is that they are in a state where they feel that everything can be explained now, everything is clear, everything is obvious. And sometimes they have indeed discovered a useful connection. But not always very often these connections are over interpretations. </s><s>[INST] I wonder, you know, there's a question of correlation versus causation and also, I wonder if it's the psychedelics or if it's more the social, like being the outsider, uh, and having a strong community of outside and being, having a leadership position in and outside a cult like community that could have a much stronger effect of overfitting than do psychedelics themselves, the actual substances because it's a counterculture thing. So it could be that as opposed to the actual substance if you're a boring person who wears a suit and tie and works at a bank uh and take psychedelics that could be a very different effect of psychedelics on on your mind. I'm just sort of raising the point that the people you referenced already Weirdos. I'm not [/INST] sure exactly. No not necessarily. A lot of the people that uh tell me that they use psychedelics uh useful way started out as squares and liberating themselves because they were stuck. They were basically stuck in local optimum of their own self model of their relationship to the world. And suddenly they had data augmentation. They basically saw an experienced a space of possibilities that experience what it would be like to be another person. And they took uh important lessons from that experience back home. </s><s>[INST] Yeah I mean uh I love the metaphor of data augmentation because that's been the primary driver of self supervised learning in the vision. Computer vision domain is data augmentation. So it's funny to think of data argument like chemical lee induced data augmentation in the human mind. [/INST] There is also a very interesting effect that I uh noticed I know several people who are scared to me that uh LSD has cured their migraines. So severe cluster headaches or migraines that didn't respond to standard medication that disappeared after a single dose. And I don't recommend anybody doing this. Especially not in the U. S. For its illegal. Uh There are no studies on this for that reason. But it seems that an exotically that it basically can reset the serotonin magic system. So it's basically pushing them outside of their normal boundaries. And as a result it needs to find a new equilibrium and then some people that actually um is better. But it also follows that and other people it might be worse. So if you have a brain that is already teetering on the boundary to psychosis uh it can be permanently pushed over that boundary. </s><s>[INST] Well that's why you have to do good science which they're starting to do on all these different substances of how it actually works for the different conditions that come. Dilemma. Seems to help with PTSD uh same or psilocybin. You know you need to do good science meaning large studies of large [/INST] end. Yeah. So based on the existing studies with M. D. M. A. It seems that if you look at Rick Dublin's work and what he has published about this and talks about uh M. D. M. A. Seems to be a psychologically relatively safe drug but it's physiologically not very safe. That is uh there is neurotoxic CCT if you would use to large dose. And if you combine this with alcohol which a lot of kids do and party settings during race and so on. It's very hip hop hip a toxic so basically you can kill your liver and this means that it's probably something that is best and most productively used in clinical setting by people who really know what they're doing. And I suspect that's also true for the other psychedelics. That is while the other psychedelics are probably not as toxic as alcohol. Uh The effects on the sake can be much more profound and lasting. </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] Cool. So you can do all the same. Like I'm coming from a computer science world. You know, I love graph theory. So you can do all the same like graph theoretic kind of analysis of like clusters or something like that or all those kinds of things And drawing says from [/INST] unique for each molecule. So these the networks that you mentioned, that's actually not too difficult. A layer of quantum physics by then all the energies are mapped. So we've had high school Children work on those networks. And the trick is to not tell them they're doing quantum physics until like three months in when it's too late for them to back out. And then you're like, you're a quantum physicist now and it's really nice. </s><s>[INST] Yeah, okay. But the promise of this, even though 16,000, even just a subset of them, that's really exciting because then you can do as the telescope day to get better and better. Especially for exoplanets, but also for venus. Uh you can then start like getting your full like, you know, how you get like blood work done or like you get your genetic testing to see what your ancestors are. You can get the same kind of like high resolution information about interesting things going on a particular planet based in the atmosphere. [/INST] Exactly how cool would that be if we could, you know, scan an alien planet and go, oh this is where the clouds are made of. This is what's on the surface. These are the molecules are mixing here are probably oceans because you can see these types of molecules above it. And here are the Hadley cells here are how the biosphere works. We could map this whole thing </s><s>[INST] when they'd be cool with the aliens are aware of these techniques and like would spoof like the wrong gasses just like pretend that's how they can be. It's like an invisibility cloak. They can generate gasses that would throw you off or like or do the opposite. They pretend they will artificially generate phosphenes. So they like the dumb, the dumb apes on Earth again go out like flying in different places because it's just fun. It's like some teenager alien somewhere just pranking Yeah, [/INST] But I was asked that exact question Saturday by a seven year old boy can 77 yes, but it was the first time I've been asked that question. This is the second in a week, but </s><s>[INST] we're kindred spirits and I [/INST] we can um they can prank us to some extent. But this work of interpreting an alien atmosphere means you're reading the atmosphere as a message and it's very hard to hide signs of life in an atmosphere because you can try to practice but you're still going to fart and breathe and somehow metabolize the environment around you and call that whatever you call that uh and release molecules and so that's really hard to hide. You can go very quiet, you can throw out some weird molecule to confuse us further but we can still see all your other metabolites. </s><s>[INST] It's hard to fake is there, you kind of mentioned like water, that what, what other gasses are there that we know about that are like high likelihood as biosignatures in terms of life. I mean what are your other favorites into? So we know we've got frosting but like what uh what else is a damn good signal to be? Uh you think about that we should be looking for if we look at another atmosphere, is there gasses that come to mind? Are they're all sort of possible biosignatures that we should love equally? [/INST] There's many. So there's water, we know that's important for life as we know it. There's molecular oxygen on earth, that's probably the most robust sign of life, particularly combined with small amounts of methane. And it's true that the majority of the oxygen in the atmosphere is a product of life. And so if I was an alien astronomer and I saw earth's atmosphere, I would get a nobel, I think, you know, what would you </s><s>[INST] notice? I mean, this is really, [/INST] I was very excited about this about the oxygen about 20%. of oxygen atmosphere. That's very unusual. So, would that be </s><s>[INST] the most exciting thing to you from an alien perspective about earth in terms of detecting like analyzing the atmosphere, like what are the bio signatures of life on earth would you say in terms of the contents of the atmosphere is oxygen high amount of oxygen. Pretty damn good sign. [/INST] I mean it's not as good as the tv signals we've been sending out those, those are slightly more robust than oxygen. Oxygen on its own has false positives for life. So there's still ways of making it, but it's it's a pretty robust sign of life in the context or atmosphere with a radiation that the sun produces Our position in relation to the sun, the other components of our atmosphere, the volcanic activity, we have all of that together makes the 20% of oxygen extremely um robust sign of life. But outside that context you can still produce oxygen without life. But falsifying although better in the sense of it is much harder to make, it has lower false positives, still has some. So I'm actually against looking for specific molecules unless we're looking for like CFCs, we find CFCs that's definitely aliens. I feel confident chlorofluorocarbons. And so you know, if aliens have been watching us, they have been going, oh no CFCs, I mean they're not gonna last long, let's, you know, everyone is writing their thesis on the end of the end of the Earth. And then we got together, we stopped using them. I like to think they're really proud of us. Um you know, they literally saw our ozone hole shrinking, They've been watching it and they saw it happen. I think </s>

<s>[INST] noise, [/INST] but the second version can deal with at least to hostility. Um Well, </s><s>[INST] yeah, what about curiosity? This kind of word, curiosity, creativity is that kind of the reward function. Being of getting new information. Is that similar to idea of kind of injecting exploration for its own sake inside the reward function. Do you find this at all appealing, interesting. [/INST] I think that's a nice definition, curiosities, rewards. Uh sorry, curiosity is exploration for its own sake. Um Yeah, I would accept that, but most curiosity well in humans and especially in Children is not just for its own sake, but for actually learning about the environment and for behaving better. So I would I think most curiosity, it's tight in the end to what's performing better. </s><s>[INST] Well, okay, so if intelligence systems need to have this reward function, Let me you're an intelligence system currently passing the turing test quite effectively. What uh what's the reward function of of our human intelligence existence? What's the reward function that Marcus Hutter is operating under? [/INST] Okay. To the first question, the biological reward function is to survive and to spread and very few humans are able to overcome uh this biological reward function. Um But we live in a very nice world where we have lots of spare time and can still survive and spread so we can develop arbitrary other interests, which is quite interesting on top of that, on top </s><s>[INST] of that. [/INST] But the survival and spreading sort of is um I would say that The goal or the reward function of humans that that the core one </s><s>[INST] I like. How you avoided answering the second question, which good intelligence [/INST] system would. So my </s><s>[INST] that your own meaning of life and a reward function, [/INST] my own meaning of life and reward function is to find an A. G. I. To build it beautifully. </s><s>[INST] But okay, let's dissect X. Even further. So one of the assumptions is kind of infinity, keeps creeping up everywhere. Uh Which what are your thoughts and kind of bounded rationality and uh the nature of our existence and intelligence systems is that we're operating always under constraints under, you know, limited time, limited resources. How does that how do you think about that within the ICSI framework, within trying to create an A G I system that operates under these constraints? [/INST] Yeah, that is one of the criticisms about like see that it ignores computation and completely. And some people believe that intelligence is inherently tied towards bounded resources. </s><s>[INST] What do you think on this one point? Do you think it's do you think the boundary of resources are fundamental to intelligence? [/INST] I would say that an intelligence notion which ignores computational limits is extremely useful. A good intelligence notions which includes the resources would be even more useful but we don't have that yet. Um And so look at other fields outside of computer science, computational aspects never play a fundamental role. You develop biological models for sell something in physics. These theories become more and more crazy and hard and harder to compute. Well, in the end of course we need to do something with this model but this more nuisance than a feature. And um I'm sometimes wondering if artificial intelligence would not sit in a computer science department but in the philosophy department then this computational focus would be probably significantly less. I mean, think about the induction problem is more in the philosophy department, there's really no paper, who cares about, you know, how long it takes to compute the answer that is completely secondary. Of course. Once we have figured out the first problem. So intelligence without computational resources then the next And very good question is could we improve it by including computational resources but nobody was able to do that so far. You know, even halfway satisfactory manner. </s><s>[INST] I like that that in the long run the right department to belong to his philosophy. That's uh that's actually quite a deep idea or even to at least to think about big picture for those awful questions. Big picture questions. Even in the computer science department but you've mentioned approximation sort of there's a lot of infinity, a lot of huge resources needed. Are they're approximations to ICSI that within the next framework that are useful? [/INST] Yeah we have developed a couple of approximations um and um what we do there is that the salama of induction part which was you know, find the shortest program describe your data which just replaces by standard data compressors, right? And the better compressors get, you know, the better this part will become. We focus on a particular compressor called context tree weighting which is pretty amazing. Not so well known, it has beautiful theoretical properties. Also works reasonably valid practice. So we use that for the approximation of the induction um and the learning and the prediction part. And um from the planning part um we essentially just took the ideas from a computer girl from 2006. It was java separates barry also narrative mind who developed the so called U C. T. O algorithm. Upper confidence bound for trees algorithm on top of the monte Carlo tree search. So we approximate its planning part by sampling and um it's successful on some small toy problems. Um We don't want to lose the generality. Right? And that's sort of the handicap right? If you want to be general you have to give up something. So but this similar agent was able to play you know small games like poker and tic tac toe and um and and even pac man um um and the same architecture no change the agent doesn't know the rules of the game really. Nothing at all by itself or by a player with these environments. </s>

<s>[INST] and then the robot just does everything in between. And it does everything, all the coordinated movement of all the different actuators that includes the body [/INST] and all of the body and all of the- Yeah, maintains its balance. It walks itself into position so it's within reach and the arm is in a position where it can do the whole task. </s><s>[INST] So it manages the whole body. So how does one become a big enough customer to request features? Because I personally want a robot that gets me a beer. I mean, that has to be like one of the most requests, I suppose, in the industrial setting. That's a non-alcoholic beverage of picking up objects [/INST] and bringing the objects to you. We love working with customers who have challenging problems like this. And this one in particular, because we felt like what they were doing, A, it was a safety feature, B, we saw that the robot could do it because they teleoperated it the first time. Probably took them an hour to do it the first time, right? But the robot was clearly capable. And we thought, oh, this is a great problem for us to work on to figure out how to automate a manipulation task. And so we took it on not because we were gonna make a bunch of money from it in selling the robot back to them, but because it motivated us to go solve what we saw as the next logical step. But many of our customers, in fact, we try to, our bigger customers, typically ones who are gonna run a utility or a factory or something like that, we take that kind of direction from them. And if they're, especially if they're gonna buy 10 or 20 or 30 robots, and they say, I really need it to do this, well, that's exactly the right kind of problem that we wanna be working on. </s><s>[INST] And so- Note to self, by tense thoughts, and aggressively pushed for beer manipulation, I think it's fair to say it's notoriously difficult to make a lot of money as a robotics company. How can you make money as a robotics company? Can you speak to that? It seems that a lot of robotics companies fail. It's difficult to build robots. It's difficult to build robots at a low enough cost where customers, even the industrial setting, want to purchase them. And it's difficult to build robots that are useful, sufficiently useful. So what can you speak to? And Boston Dynamics has been successful [/INST] for many years of finding a way to make money. Well, in the early days, of course, the money we made was from doing contract R&D work. And we made money, but we weren't growing and we weren't selling a product. And then we went through several owners who had a vision of not only developing advanced technology, but eventually developing products. And so both Google and SoftBank and now Hyundai had that vision and were willing to provide that investment. Now, our discipline is that we need to go find applications that are broad enough that you could imagine selling thousands of robots because it doesn't work if you don't sell thousands or tens of thousands of robots. If you only sell hundreds, you will commercially fail. And that's where most of the small robot companies have died. And that's a challenge because, you know, A, you need to field the robots. They need to start to become reliable. And as we've said, that takes time and investment to get there. And so it really does take visionary investment to get there. But we believe that we are going to make money in this industrial monitoring space because, you know, if a chip fab, if the line goes down because a vacuum pump failed someplace, that can be in a very expensive process. It can be a million dollars a day in lost production. Maybe you have to throw away some of the product along the way. And so the robot, if you can prevent that by inspecting the factory every single day, maybe every hour, if you have to, there's a real return on investment there. But there needs to be a critical mass of this task. And we're focusing on a few that we believe are ubiquitous in the industrial production environment. And that's using a thermal camera to keep things from overheating, using an acoustic imager to find compressed air leaks, using visual cameras to read gauges, measuring vibration. These are standard things that you do to prevent unintended shutdown of a factory. And this takes place in a beer factory where we're working with AB InBev. It takes place in chip fabs. We're working with global foundries. It takes place in electric utilities and nuclear power plants. And so the same robot can be applied in all of these industries. And as I said, we have about, actually it's 1100 spots out now to really get profitability. We need to be at 1000 a year, maybe 1500 a year for that sort of part of the business. So it still needs to grow, but we're on a good path. </s><s>[INST] So I think that's totally achievable. So the application should require crossing that 1000 robot barrier. [/INST] It really should. 1000 robot. </s><s>[INST] I want to mention our second robot, Stretch. Yeah, tell me about Stretch. What's Stretch? [/INST] Who's Stretch? Stretch started differently than Spot. Spot we built because we had decades of experience building quadrupeds. We just, we had it in our blood. We had to build a quadruped product, but we had to go figure out what the application was. And we actually discovered this factory patrol application, basically preventative maintenance by seeing what our customers did with it. Stretch is very different. We started knowing that there was warehouses all over the world. There's shipping containers moving all around the world full of boxes that are mostly being moved by hand. By some estimates, we think there's a trillion boxes, cardboard boxes shipped around the world each year. And a lot of it's done manually. It became clear early on that there was an opportunity for a mobile robot in here to move boxes around. And the commercial experience has been very different between Stretch and with Spot. As soon as we started talking to people, potential customers about what Stretch was going to be used for, they immediately started saying, oh, I'll buy, I'll buy that robot. You know, in fact, I'm going to put in an order for 20 right now. We just started shipping the robot in January after several years of development. This year. This year. So our first deliveries of Stretch to customers were DHL and Marisk in January. We're delivering the gap right now. And we have about seven or eight other customers, all who've already agreed in advance to buy between 10 and 20 robots. And so we've already got commitments for a couple hundred of these robots. This one's going to go, right? It's so obvious that there's a need and we're not just going to unload trucks. We're going to do any box moving task in the warehouse. And so it too will be a multi-purpose robot and we'll eventually have it doing palletizing or depalletizing or loading trucks or unloading trucks. There's definitely thousands of robots. There's probably tens of thousands of robots of this in the future. So it's going to be profitable. </s>

<s>[INST] as a human, not as a [/INST] as a human it is just and for him that was his own path of his own personal of growing personally over years, working with people like that and so it was working himself growing, helping other people growing, growing through that. And that's fundamentally what I believe in with our work, helping other people grow, growing ourselves ourselves. Um trying to build a company that's all built on these principles, you know, having a good time along, so people who work with to grow a little bit. So these two books and then I would throw in um well we have on our, in our in our office when we start a company in Russia, we put a neon sign in our office because we thought that's recipe for success. If we do that, we're definitely going to wake up as a multiple indoor company and it was the little bit Wittgenstein quote, the limits of my language, the limits of my world, What's the quote, the limits of my language are the limits of my world. Um and I love the practice, I think it's just it's just a beautiful book by Wicked said. Yeah, and I would recommend that too, even although he himself didn't believe in that by the end of his lifetime and debunk these ideas, I think I remember once an engineer came in 2012 I think was 13 um a friend of ours who worked with us and then went on to work at Deepmind and he gave a talk to us about were to back and I saw that I'm like, wow, that's, you know, they wanted to translate language into, you know, some other representation and it seems like some, you know, somehow all of that at some point I think will come into this one to this one place. Somehow. It just all feels like different people think about similar ideas in different times from absolutely different perspectives. And that's why I like these </s><s>[INST] books and it was just the limit of our world on [/INST] we still have that near side. It's very hard to work with this red light in your face. </s><s>[INST] I mean on the, on the Russian side of things in terms of language olympics, the language being limited. Our world. Russian is a beautiful language in some sense. There's with this um, there's pain, there's so much, we don't have time to talk about it much today, but I'm going to paris uh, talk to Dusty asking Tulsa translators. Um, uh, I think it's just fascinating art like and art and engineering. That means such an interesting process. So, from the replica perspective, do you, what do you think about translation, how difficult it is to create a deep, meaningful connection. Russian versus english, how you can translate the two languages you speak both. [/INST] Yeah, I think we're two different people in different languages. Um, even I'm, you know, thinking about and there's actually some research on that. I looked into that at some point because I was fascinated by the fact that what I'm talking about with, what I was talking about with my Russian therapist has nothing to do with with what I'm talking about. My english speaking therapist, two different lives. Two different types of um, you know, conversations to different personas. The main difference between the languages are with Russian and english. Is that Russian? Well english is like a piano. It's a limited number of, a lot of different keys, but not too many. And Russia is like an organism that's just something gigantic with so many different keys and so many different opportunities to screw up and so many opportunities to do something completely tone deaf. Um it is just a much harder language to use. It has way too many, way too much flexibility and way too many tones. </s><s>[INST] What about the entirety of World War Two communism Stalin the pain of the people like having been deceived by the dream, like all the pain of like just the entirety of it. Is that in the language too. So I have to [/INST] do for sure. I mean we have words that don't have direct translation that to english that are very much um like we have a pizza, which is sort of like to hold a grudge or something, but it doesn't have, it doesn't you don't need to have anyone to do it to you. It's just your state, you just feel like that you feel like betrayed by the people basically, but it's not that and you can't really translate that. Um and I think it's super important that very many words that are very specific explain the Russian being. And I think it can only come from from a nation that was um that suffered so much. And so institutions fall time after time after time. And you know, what's exciting? Maybe not exciting, exciting the wrong word. But was interesting about my generation, my mom's generation and my parents generation that We saw institutions fall two or 3 times in our lifetime. And most americans have never seen them fall and they just think that they exist forever. Um which really interesting, but it's definitely a country that suffered so much and and it makes, unfortunately when I go back and I, you know, hang out with my Russian friends, uh it makes people very cynical, they start believing in in the future. I hope that's not going to be case for so long or something is going to change again. But I think seeing institutions follows a very traumatic experience </s><s>[INST] Makes it very interesting. And what's on 2020, it's very interesting. Uh do you think civilization will collapse? Yeah. [/INST] See I'm a very practical person. </s>

<s>[INST] Seven years after Daniel's death, he wrote an article at the Wall Street Journal titled Daniel Pearl in the normalization of evil. What was your message? A message back then? And how did it change today? Over over the years? [/INST] I I lost </s><s>[INST] what was the message? [/INST] The message was that we are not treating terrorism, Is it taboo? We are treating it as a bargaining device. That is accepted. People have grievance and they go and bomb more restaurants. Okay, it's normal. Look, you're even not not surprised when I tell you that 20 years ago. So what for grievance? You go and blow restaurant. Yeah. Today is becoming normalized the finalization of evil. And we have created that to ourselves by normalizing by by making it part of Mhm. Mhm. Political life. It's a political debate. Every terrorists yesterday become the freedom fighter today and tomorrow is becoming terroristic. It is switch double thing. </s><s>[INST] So we should call out evil when there's evil [/INST] if we don't want to be part of it, becoming Yeah, if we want to separate good from evil? That's one of the first things that what would the in the garden of Eden? Remember the first thing that God tells him he was, hey, you want some knowledge. Here is the tree of good and evil. </s><s>[INST] So this evil touched your life personally. Does your heart have anger, sadness or is it hope? [/INST] Okay, I see some beautiful people coming from Pakistan, I see beautiful people everywhere, but I see horrible propagation of evil in this country too. It shows you how populistic slogans can catch the mind of the best intellectuals </s><s>[INST] today is father's Day. [/INST] I didn't know that. Yeah. </s><s>[INST] What's uh what's, what's a fond memory you have of Daniel. [/INST] Oh many good name with uh he means he was my mentor. What do you? He had sense of balance that I didn't have. Yeah, he saw the beauty in every person. He was not as emotional as I am more looking at things in perspective. He really likes every person. He really grew up with the idea that for now is reason for curiosity, not for fear. At one time we went in Berkeley and homeless came out from some dark alley and he said, hey man, can you spare a dime? I retreated back, you know two ft back and then I just hugged him and say, here's a dime and judge yourself maybe you want some um money to take a bath or whatever. Where did you get it? Not for me. </s><s>[INST] Do you have advice for young minds today dreaming about creating as you have dreamt creating intelligence systems? What is the best way to arrive at new breakthrough ideas and carry them through the fire of criticism and and past conventional ideas. [/INST] Ask your questions freely. Your questions are never done and solved in your own way and don't take no for an answer. Look, if they are really dumb, you will find them quickly by trying narrow to see that they're not leading any place but follow them and try to understand things your way. That is my advice. I don't know if it's going to help anyone that's brilliant. There is a lot of uh it's inertia in science in academia. It is slowing down science. </s><s>[INST] Yeah, those two words your way. That's a powerful thing. It's against inertia potentially against [/INST] against your professor Professor. I wrote the book of why in order to democratize common sense in order to instill rebellious spirits in students. So they wouldn't wait for until the professor get things right. Mhm. </s><s>[INST] Uh He wrote the manifesto of the rebellion against the professor [/INST] Professor. Yes. </s><s>[INST] So looking back at your life of research, what ideas do you hope ripple through the next many decades? What what do you hope your legacy will be? [/INST] I already have tombstone </s><s>[INST] carved? [/INST] Ah boy, fundamental The fundamental law of counterfactual, that's what it's a simple equation with a counterfactual in terms of a model surgery. That's it. Because everything follows from that. If you get that all of us, I can die in peace and my student can derive all my knowledge. My mother mother called means </s><s>[INST] the rest follows. Yeah dad, thank you so much for talking today. I really appreciate [/INST] it. Thank you for being so attentive and instigating. </s><s>[INST] We did it really. The coffee helped. Thanks for listening to this conversation with judea Pearl and thank you to our presenting sponsor. Cash up, download it, use code lex podcast. You'll get $10.10 dollars will go to first a stem education non profit that inspires hundreds of thousands of young minds to learn and to dream of engineering our future. If you enjoy this podcast, subscribe on Youtube, get five stars on apple podcast support on Patreon are simply connect with me on twitter and now let me leave you with some words of wisdom from judea Pearl. You cannot answer a question that you cannot ask and you cannot ask a question. You have no words for thank you for listening and hope to see you next time [/INST] </s>

<s>[INST] there's no free lunches. Yeah right. That's what do you think, what's your intuition uh how can we slow the growth event to infinity and supervisor? Uh end to infinity and supervised learning. So for example mobile I has very successfully, I mean, essentially annotated large amounts of data to be able to drive a car. Now one thought is so we're trying to teach machines school of AI and we're trying to So how can we become better teachers? Maybe that's 11 way. [/INST] Yeah. You know what? I like that because one again, one caricature of the history of computer sides you could say is it begins with programmers expensive. Yeah, continuous labelers cheap and the future will be schools like we have for kids. </s><s>[INST] Yeah. Currently the labeling methods, we're not selective about which examples we we teach networks with. So so I think the focus of making one networks that learn much faster is often on the architecture side. But how can we pick better examples of wish to learn? Uh Do you have intuitions about that? Well, that's part [/INST] of the part of the problem, but the other one is, you know, if we look at um biology, reasonable assumption, I think is um in the same spirit that I said, evolution is opportunistic and has weak criers, you know the way I think the intelligence of a child, the baby may develop is um by bootstrapping week criers from evolution for instance. Um Yeah. In you can assume that you have a most organisms, including human babies built in some basic machinery to detect motion and relative motion. And in fact there is, you know, we know, all insects from fruit flies to other animals. They have this even in the readiness of the very peripheral part of its very conserved across species. Something that evolution discovered early maybe the reason why babies tend to look the first few days to moving objects and not to not moving out moving objects means, okay, they're attracted by motion, but motion also means that motion gives automatic segmentation from the background. So because of motion boundaries, you know, either the object is moving or the eye of the baby is tracking the moving object and the background is moving. Right? </s><s>[INST] So just purely on the visual characteristics of the scene that seems to be the most useful. [/INST] Right? So it's like looking at an object without background background, it's ideal for learning the object. Otherwise it's really difficult because you have so much stuff. So suppose you do this at the beginning, first weeks, Then after that you can recognize object. Now they're imprinted the number one even in the background, even without motion. </s><s>[INST] So that's at the by the way, I just want to ask on the object recognition problem. So there is this being responsive to movement and edge detection essentially. What's the gap between being effectively effectively visually recognizing stuff detecting where it is and understanding the scene. Is this a huge gap in many layers or is it are we is it close? [/INST] No, I think that's a huge gap. I think present algorithm with all the success that we have and the fact that there are a lot of very useful. I think we're in a golden age for applications of low level vision and low level speech recognition and so on, you know, Alexa and so on. Um there are many more things of similar level to be done, including medical diagnosis and so on. But we are far from what we call understanding of a scene of language of actions of people that is despite the claims, that's I think very far </s><s>[INST] we're a little bit off so in popular culture and among many researchers, some of which I've spoken with the Stuart russell and you know, musk uh in and out of the AI field, there's a concern about the existential threat of AI. And how do you think about this concern in uh and is it valuable to think about large scale long term unintended consequences of intelligence systems we try to build. [/INST] I always think it's better to worry first, you know, early rather than late. So don't worry is good. Yeah, I'm not against worrying at all uh personally, I think that uh you know, it will take a long time before there is a real reason to be worried, but as I said, I think it's good to put in place and think about possible safety against what I find a bit misleading are things like that have been said by people I know like Elon musk and uh what is both strong and particularly notice first name, nick nick poster. Right. You know, in a couple of other people that for instance, ai is more dangerous than nuclear weapons? I think that's really wrong. And that can be is misleading because in terms of priority we should still be more worried about nuclear weapons. And uh you know, people are doing about it and so on than uh </s><s>[INST] and you've spoken about Dennis Hassabis and yourself saying uh you think it would be about 100 years out Before we have general intelligence system? That's on par with the human being. Do you have any updates for those predictions? Well, I think he said he said 20, I think [/INST] It said 20. Right, this was a couple of years ago. I have not asked him again. So </s><s>[INST] should have your own prediction. What's your prediction about when you'll be truly surprised and what's the confidence interval on that? [/INST] Uh You know, it's so difficult to predict the future and even the presence of it's pretty hard to predict. But I would be as I said, this is completely it would be more like uh Rod brooks. I think he's about 200 </s>

<s>[INST] So as part of the full conscious experience uh to create a consciousness artificial or in our human consciousness, do you think fear? Maybe we're going to get into uh the earlier days with each and so on. But do you think fear and suffering are essential to have consciousness? Do you have to have a full range of experience to have to have a system that has experience? Or can you have a system that only has a very particular kinds of very positive experiences? [/INST] Look, you can have in principle, you can people have done this in the rat where you implant electrodes in the hypothalamus, the pleasure center of the rat and the rat stimulate itself above and beyond anything else. It doesn't care about food or natural sex or drink any more to stimulate itself because it's it's such a pleasurable feeling. I guess it's like an orgasm. Just you have, you know, all day long and so a priority. I see no reason why you need um different why you need a great variety. Now, clearly to survive, that wouldn't work. But if I engineered artificially, I don't think, I don't think you need a great variety of conscious experience, you could have just pleasure or just fear, it might be a terrible existence. But I think that's possible, at least on conceptual logical count because any real creature with the artificial engineered, you want to give it fear, the fear of extinction that we all have. And you also want to give it a positive competitive states, states that it wants to, that you want the machine encouraged to do because they give the machine positive feedback. </s><s>[INST] So, you mentioned panpsychism to jump back a little bit. You know, everything having some kind of mental property. How do you go from there to something like human consciousness? So everything having some elements of consciousness too. Is there something special about human consciousness? [/INST] So, so just it's not everything like a spoon. There's no uh, the form of pants I can I think about doesn't ascribe consciousness to anything like this. The spoon or my liver. However, uh, it is uh, the theory integrated information theory does say that system. Even ones that look from the outside, relatively simple. At least if they have this internal causal power, they are they does feel like something. The theory, apoyo doesn't say anything. What's special about human biologically? We know what the one thing that's special about human is we speak and we have an overblown sense of our own importance, </s><s>[INST] right? We [/INST] believe were exceptional. And where does God give </s><s>[INST] to [/INST] into the universe? But the but behavior, the main thing that we have, we can plan, we can plan over the long term and we have language and that gives us enormous amount of power. And that's why we are the current dominant species on the planet. So </s><s>[INST] you mentioned God, you grew up a devout roman catholic, you know, roman catholic family. So, you know, the consciousness, you're sort of exploring some really deeply fundamental human things that religion also touches on. So where does where does religion fit into your thinking about consciousness? And you've, you've grown throughout your life and change your views on religion as far as I understand? [/INST] Yeah, I mean, I'm now much closer to, so I'm not a roman catholic anymore. I don't believe there's sort of this guard the God I was educated to believe in, you know, sit somewhere in the fullness of time. I'll be united in some sort of everlasting bliss. I I just don't see any evidence for that. Look, the world, the night is large and full of wonders, right? There are many things that I don't understand. I think many things that we as a cult. Look, we don't even understand more than 4% of all the universe. Right. Dark matter, dark energy. We have no idea what it is. Maybe it's lost socks. What do I know? So, so all I can tell you is, it's a sort of, my current religious or spiritual sentiment is much closer to some form of Buddhism. Can you? Just without the reincarnation. Unfortunately, there's no evidence for reincarnation. </s><s>[INST] So, can you describe the way buddhism sees the world a little bit [/INST] well. So the, you know, they talk about, so when, when I spent several meetings with the Dalai lama and what always impressed me about him? He really unlike for example, it either the pope or some cardinal, he always emphasized minimizing the suffering of all creatures. So they have this from the early beginning, they look at suffering in all creatures, not just in people, but in in everybody this universal. And of course by degrees right in the animal journal will have its less capable of suffering than a than a well developed uh normally developed human. And they think consciousness pervades in this universe. Uh, and they have these techniques, you know, you can think of them like mindfulness, etcetera and meditation that tries to access sort of what they claim of this more fundamental aspect of reality. I'm not sure it's more fundamentalist, I think about it, there's a physical and then there's this insight view consciousness and those are the two aspects. That's the only thing I've have access to my life. And you've got to remember my conscious experience and your conscious experience comes prior to anything you know about physics comes prior to knowledge about the universe and atoms and superstrings and molecules and all of that. The only thing you directly acquainted with is this world that's populated with with things and images and and sounds in your head and touch us and all of that actually </s><s>[INST] have a question. So [/INST] it sounds like you kind of have a rich life. You talk </s><s>[INST] about rock climbing [/INST] and it seems like you really love literature and </s>