text
stringlengths
296
254k
<s>[INST] But do you think it's useful to have a term like the I. D. W. To capture some set of people, some set of ideas or maybe principles that capture what I think the I. D. W. Okay you can say that it's not supposed to mean it doesn't exist. It doesn't mean anything but to the public to me. Okay I'll just speak to me, it represented something uh it represented, I think it's just like this to you. It's my in my first attempt to interview the great eric Weinstein, I said that I spoke about you, but I E. W in general is trying to point out the elephant in the room or that the emperor has no clothes, the set of people that do that in their own way, [/INST] if there are multiple elephants in the room. The point is, is that the I. D. W. Is more interested in seeing the totality of elephants and trying to figure out how do we move forward? As opposed to say, I can spot the other guy's elephant in the room, but I can't see my own and, you know, in large measure, we didn't represent an institutional base and therefore it wasn't maximally important that we look at our own hypocrisy because we weren't on the institutional spectrum. </s><s>[INST] This is where friendship comes into play with the different figures that are loosely associated with the I. D. W. Is you are somehow uh responsible for, you know, the exactly thing that you said, Did you hear what? I don't know, I forget the dame. Oh what Sam Harris said about the stuff. Uh that that kind of thing is [/INST] why chuckled </s><s>[INST] lovingly or chocolate. Like I [/INST] was angry at some people who had said things that cause Sam to say what Sam said about turning his imaginary club membership into the I. D. W. People said very silly things and you know, I think that there is just this confusion that um integrity means calling out your friends in front of the world and you know, I've been pretty clear about this uh try to choose my friends carefully and if you would like to recuse me because I'm not a source of reliable information, people that I know and love the most um maybe that's reasonable for you. Maybe you prefer somebody who was willing to throw a friend under the bus at the first sign of trouble by all means uh exit my feed. You don't have to subscribe to me. If that's if that's your concept of integrity, you're barking up the wrong tree. What I will say is that I knew these people well enough to know that they're all flawed. Thank you for the call back. And uh but the issue is that um I love people who are flawed and I love people who have to earn a living, even if you call them a grifter. And I love people who ah you know like the fact that donald trump didn't get us into new wars, even if you call them all right, I love the fact that um some people believe in structural oppression and want to fight it even if they're not woke because they don't believe that structural oppression is hiding everywhere. I care and love different people in different ways. And I just I think that the overarching thing like that we're not getting at is that we were sold a bill of goods that you can go through life, like and Eliza program with pre programmed responses. Well, that's what about ISM? It's both sides ISm It's all right. It's the loony left campus madness. You know, It's like, okay, why don't you just empty the entire goddamn magazine all of those pre recorded snips now that you've done all of that now, we can have a conversation, </s><s>[INST] your son put it really well, which is we should in all things resist labels, [/INST] but we can't deal without labels. We have two general lease, but we also have to keep in mind that just in the way in science you deal with an effective theory that isn't a fundamental one in science. Most of our theories we consider to be effective theories if I generalize about, about europe, about women, about uh, you know, christians, those things have to be understood to mean something and not to have their definitions extend so broadly that they mean nothing at all, nor, um, that they're so rigid that their claims that clearly won't bear scrutiny. Let's what do you really want to talk about? That's always my question to you, that always gets </s><s>[INST] me. That's a good thing. Maybe you are the therapist, [/INST] but like you and I could talk about people love up until now at least people have loved listening to the two of us in conversation. And my feeling is that we're not talking about neural nets, we're not talking about geometric unity and we're not talking about where distributed computing might go. And I don't think that we're really focused on some of the most exciting things we could do to transform education were still caught in this world of other people that we don't belong, I don't belong in the world as it's been created. I'm trying to build a new world and I'm astounded that the people with the independent means to help build that world are so demotivated that they don't want to build new structures and the people who do want to build new structures seem to be wild at </s><s>[INST] wild eyed. What do you mean by wild eyed? They're not, they're not, [/INST] I guarantee you that I will get some message in my DMS and says, hey eric, you know, I'm a third year chemistry student at uh, you know South Dakota State and I've got a great idea. I just need funding. I want to build, they </s>
<s>[INST] There's the google hiring process, touch on that passion. So like trying to determine because I think as far as I understand maybe you can speak to it that the google hiring process sort of helps the initial like determines the skill set. There is your puzzle solving, ability, problem solving, ability, good. But like I'm not sure but it seems that the determining whether the person is like fire inside them that burns to do anything really, it doesn't really matter. It's just some cool stuff I'm gonna do it uh that I don't know is that something that ultimately ends up in when they have a conversation with you or once it gets closer to. [/INST] So one of the things we do have as part of the process is just a culture fit, like part of the interview process itself in addition to just the technical skills in each engineer or wherever the interviewer is, is supposed to rate the person on the culture and the culture fit with google and so on, so that is definitely part of the process now, uh there are various kinds of projects and different kinds of things, so there might be variants and the kind of culture you weren't there and so on and yes, that does vary. So for example, tensorflow has always been a fast moving project and we want people who are comfortable with that, but at the same time now for example, we are at a place where we are also very full fledged product and we want to make sure things that work really, really work right, you can't cut corners all the time, so they're balancing that out in finding the people who are the right fit for fit for those is important and I think those kind of things do vary a bit across projects and teams and product areas across google and so you'll see some differences there in the final checklist, but a lot of the core culture, it comes along with just engineering excellence and so on, </s><s>[INST] what is uh the hardest part of your job, take your pick, I [/INST] guess it's fun, I would say right, hard, yes, I mean lots of things at different times. I think that that does very, </s><s>[INST] so let me clarify that difficult things are fun. Yeah, when you saw them right, it's fun in that, in that sense. [/INST] I think the key to successful thing across the board and you know, in this case it's a large ecosystem now, but you're in a small product is striking that fine balance across different aspects of it. Sometimes it's how fast you go versus how perfect it is. Sometimes that's how do you involve this huge community, who do you involve or do you decide? Okay, now it's not a good time to involve them because it's not the right fit. Sometimes it's saying no to certain kinds of things. Those are often the hard decisions, some of them you make quickly because you don't have the time, some of them you get time to think about them, but they're always hard when </s><s>[INST] both both choices are pretty good. It's that those decisions, what about deadlines is just do you find tensorflow to be driven mm uh by deadlines to a degree that a product might or is there still a balance to where it's less deadline? You had the deaf summit that came together incredibly looked like there's a lot of moving pieces and so on. So that that deadline make people rise to the occasion releasing, that's the flow. Two point of Alpha, I'm sure that was done last minute as well. I mean like the up to the up to the up to the last point. [/INST] Again, you know, it's one of those things that uh, you need to strike a good balance. There is some value that deadline spring that does bring a sense of urgency to get the right things together instead of, you know, getting the perfect thing out, you need something that's good and works well. And the team definitely did a great job in putting that together. So it was very amazed and excited by everything how that came together. Uh That's it across there. We try not to put artificial deadlines, We focus on key things that are important, figure out what, how much of it's important and, and we are developing in the open, but you know, internally and externally everything is available to everybody so you can pick and look out where things are. Uh, we do releases at a regular cadence, so fine. If something doesn't necessarily end up this month, it will end up in the next release in a month or two. Uh and that's okay, but we want to get like, keep moving as fast as we can in these different areas, um, because we can iterate and improve on things. Sometimes it's okay to put things out that aren't fully ready if you make sure it's clear that okay, this is experimental, but it's out there. If you want to try and get feedback, that's very, very useful. I think that quick cycle and quick iteration is important. That's what we often focus on rather than here's a deadline where you get everything else? </s><s>[INST] It's 2.0, is there pressure to make that stable? Or like for example, wordpress five point, I just came out and there was no pressure to, it was a lot of build updates to deliver it way too late but and they said, okay, well, but we're going to release a lot of updates really quickly to improve it. Does, do you see tensorflow two point on that same kind of way? Or is there this pressure to once it hits two point? Oh, once you get to the release candidate and then you get to the final that that's going to be the stable thing, [/INST] so it's going to be stable in just like when your ex was where every api that's there is going to remain and work? Uh it doesn't mean we can't change things in another covers, it doesn't mean we can't add things so there's still a lot more for us to do and we can't really have more releases. So in that sense there's still, I don't think we'll be done in like two months when we release this, </s>
<s>[INST] what do you think the future programming looks like? What do you hope the future programming looks like if we zoom in on the computational fields on data science machine learning. [/INST] I hope Swift is successful because the goal is swift. The way chris Latner describes it is to be infinitely hackable and that's what I want. I want something where me and the people I do research with and my students can look at and change everything from top to bottom. There's nothing mysterious and magical and inaccessible. Unfortunately with python, it's the opposite of that because python is so slow, it's extremely unhappy. Kable, you get to a point where it's like okay from here on down at sea, so your body doesn't work in the same way your profile, it doesn't work in the same way your build system doesn't work in the same way. It's really not very hackable. </s><s>[INST] What's the part you would like to be hackable? Is it for the objective of optimizing training of neural networks in France. The neural networks is a performance of the system or is there some non performance related? Just? [/INST] It's everything. I mean in the end I want to be productive as a practitioner. So that means that so like at the moment our understanding of deep learning is incredibly primitive. There's very little we understand most things don't work very well even though it works better than anything else out there. There's so many opportunities to make it better. So you look at any domain area, like I don't know, speech recognition with deep learning or natural language processing classification with deep learning or whatever every time I look at an area with deep learning. I always see like, oh it's terrible. There's lots and lots of obviously stupid ways to do things that need to be fixed. So then I want to be able to jump in there and quickly experiment and make them better. </s><s>[INST] Do you think the programming language is has a role in that [/INST] huge role? Yeah. So currently python has a big gap in terms of our ability to, uh, innovate particularly around recurrent neural networks and, um, natural language processing because because it's so slow the actual loop where we actually looked through words, we have to do that whole thing in CUDA C. So we actually can't innovate with the colonel the heart of the most important algorithm. And it's just a huge problem and this happens all over the place. So we hit, you know, research limitations. Another example, convolutional neural networks which are actually the most popular architecture for lots of things. Maybe most things in declining, we almost certainly should be using sparse convolutional neural networks. Um, but only like two people are because to do it, you have to rewrite all of that courtesy level stuff. And yeah, this researchers and practitioners don't so like there's just big gaps in like what people actually research on what people actually implement because of the programming language problem. </s><s>[INST] So, you think, uh, do you think it's it's just too difficult to write in code to see, uh, that programming like a higher level programming language like Swift should enable the the easier fooling around creative stuff with our own ends or was part competition, you know, it's kind of who, who, who's uh who's at fault, who's, who's in charge of making it easy for a researcher to player. [/INST] I mean no one's fault, he's got around to it yet. It's just it's hard. Right? And I mean part part of the fault is that we ignored that whole ap l kind of direction most nearly everybody did for 60 years, 50 years. But recently people have been starting to reinvent pieces of that and kind of create some interesting new directions in the compiler technology. So the place where that's particularly happening right now is something called lia, which is something that chris Lattner, the Swift guy is leading and because it's actually not going to be swift on its own, that solves this problem because the problem is that currently writing, hey, acceptably fast Gpu program is too complicated regardless of what language you use. And that's just because if you have to deal with the fact that I've got, you know, 10 0 threads and I have to synchronize between them all. And I have to put my thing into grid blocks and think about what's and all this stuff. It's just, it's just so much boilerplate to do that. Well you have to be a specialist at that and it's going to be a year's work too, you know, optimized that algorithm in that way. But with things like tensor comprehension, Xyz and tile and I R and T v m there's all these various projects which are all about saying let's let people create like domain specific languages for tensor computations, these are the kinds of things we do are generally on the Gpu for deep learning and then have a compiler which can optimize that tensor computation. A lot of this work is actually sitting on top of a project called Halide, which was is a mind blowing project where they came up with such a domain specific language. In fact to one domain specific language for expressing. This is what my tensor computation is. And another domain specific language for expressing. This is the kind of the way I want you to structure The compilation of that. Like do it block by block and do these bits in parallel and they were able to show how you can compress the amount of code by 10 x compared to optimized Gpu code and get the same performance. So that's like so these other things are kind of sitting on top of that kind of research and mm HLA is pulling a lot of those best practices together. And now we're starting to see work done on making all of that directly accessible through swift so that I could use swift to kind of write those domain specific languages and hopefully we'll get them swift cuda kernels written in a very expressive and concise way that looks a bit like jay and apple and then swift layers on top of that. And then I switched UI on top of that, you know, it'll be so nice if we can get to that point, </s>
<s>[INST] I mean, do you have a hope for the pandemic? So we'll talk about physics, but for the pandemic, can that be extracted? Do you think? [/INST] Well, I think the good news is the curves basically, you know, for reasons we don't understand the curves, you know, the clearly measurable mortality curves and so on for </s><s>[INST] the Northern hemisphere have gone down. But the bad news is that it could be a lot worse for future viruses. And what this pandemic revealed is we're highly unprepared for the discovery of the pockets of reducibility within a pandemic that's much more dangerous. [/INST] Well, my guess is the specific risk of, you know, viral pandemics, you know, that the pure virology and immunology of the thing, this will cause that to advance to the point where this particular risk is probably considerably mitigated. But you know, is the structure of modern society robust to all kinds of risks? Well, the answer is clearly no. And it's surprising to me the extent to which people, you know, as I say, it's kind of scary actually how much people believe in science. That is, people say, oh, you know, because the science does this that and the other will do this and this and this, even though from a sort of common sense point of view, it's a little bit crazy. And people are not prepared and it doesn't really work in society as it is for people to say, well, actually, we don't really know how the science works because they will tell us what to do. </s><s>[INST] Yeah, because my guess is that because then that was the alternative. For the masses, it's difficult to sit, it's difficult to meditate on computation or reducibility, and it's difficult to sit to enjoy a good dinner meal while knowing that you know nothing about the world. [/INST] It's difficult to sit, it's difficult to enjoy a good dinner meal. This is the place where you know, this is what politicians and political leaders do for a living so to speak as you've got to make some decision about what to do, and </s><s>[INST] tell some narrative that while amidst the mystery and knowing not much about the past or the future, still telling a narrative that somehow gives people hope that we know what the heck we're doing. [/INST] Yeah, and get society through the issue. Even though the idea that we're just gonna sort of be able to get the definitive answer from science and it's gonna tell us exactly what to do, unfortunately, it's interesting because let me point out that if that was possible, if science could always tell us what to do, then in a sense that would be a big downer for our lives. If science could always tell us what the answer is gonna be, it's like well, it's kind of fun to live one's life and just sort of see what happens. If one could always just say, let me check my science. Oh, I know, the result of everything is gonna be 42. I don't need to live my life and do what I do. It's just, we already know the answer. It's actually good news in a sense that there is this phenomenon of computational irreducibility that doesn't allow you to just sort of jump through time and say, this is the answer, so to speak. And that's, so that's a good thing. The bad thing is it doesn't allow you to jump through time </s><s>[INST] and know what the answer is. It's scary. Do you think we're gonna be okay as a human civilization? You said we don't know. Absolutely. Do you think it's, do you think we'll prosper or destroy ourselves as a- In general? [/INST] In general. We don't know? Absolutely. In general? In general. I'm an optimist. No, I think that the, you know, it'll be interesting to see, for example, with this, you know, pandemic, I, you know, to me, you know, when you look at like organizations, for example, you know, having some kind of perturbation, some kick to the system, usually the end result of that is actually quite good. You know, unless it kills the system, it's actually quite good usually. And I think in this case, you know, people, I mean, my impression, you know, it's a little weird for me because you know, I've been a remote tech CEO for 30 years. It doesn't, you know, this is bizarrely, you know, and the fact that, you know, like this coming to see you here is one of the rare moments in human interaction. This is the first time in six months that I've been like, you know, in a building other than my house, okay? </s><s>[INST] So, you know, I'm a kind of ridiculous outlier in these kinds of things. One of the rare moments of human interaction. But overall, your sense is when you shake up the system and throw in chaos, [/INST] that you challenge the system, we humans emerge better. Seems to be that way. Who's to know? But I think that, you know, people, you know, my sort of vague impression is that people are sort of, you know, oh, what's actually important, you know, what's, what is worth caring about and so on. And that seems to be something that perhaps is more, you know, </s>
<s>[INST] It's still good for marketing. But uh but what you're, you're [/INST] not, you don't like </s><s>[INST] expanding the definition of moore's law sort of, [/INST] Well, naturally it's an educator, you know, are, you know, is this like bond in politics? Does everybody get their own facts or do we have, you know, moore's law was a crisp, you know, more carver mead looked at his Morris conversations drawing on a log log scale a straight line and that's what the definition of moore's law is there's this other what intel did for awhile interestingly before jim joined them, they said, oh no moore's law isn't the number of doubling isn't really doubling transistors every two years moore's law is the cost of the individual transistor going down uh cutting in half every two years. No that's not what he said but they re interpreted it because they believed that the cost of transistors was continuing to drop even if they couldn't get twice. Some internships. Many people in industry have told me that's not true anymore that basically the more recent technologies that got more complicated the actual cost of transistor went up. So even even the corollary might not be true but certainly uh you know moore's law that was the beauty of Morris law. It was a very simple, it's like E. Equals M. C. Squared, right? It was like what an amazing prediction. It's always understand the implications are amazing and that's why it was so famous as a as a prediction. And this this reinterpretation of what it meant and and changing is you know his revisionist history and I would be happy. Uh and and and they're not claiming there's a numerous law, they're not saying by the way it's instead of every two years, it's every three years. I don't think they I don't think they want to say that. I think what's going to happen is new technology commissions. Each one is to get a little bit slower. So it is slowing down. The improvements won't won't won't be as great. Uh And that's why we need to do new things. Yeah I don't like </s><s>[INST] that. The uh the idea of moore's law is tied up with marketing. It would be nice if, [/INST] whether it's marketing or it's it's um, Well, it could be affecting business, but it could also be infecting the imagination of engineers is if if Intel employees actually believe that were frozen in 2019, well, that's that would be bad for Intel. The </s><s>[INST] not just intel, but everybody, it's inspired moore's law is inspiring. Yeah. To everybody. [/INST] But what's happening right now, talking to people who have working in national offices and stuff like that, A lot of the computer science community is unaware that this is going on, that we are in an era that's going to need radical change at lower levels that could affect the whole software stack this. You know, if if intel, uh if you're using cloud stuff and the servers that you get next year, basically only a little bit faster than the service you got this year, you need to know that. And we need to start innovating uh, to start delivering bonnet? If you're counting on your software, your software gonna have a lot more features assuming the computers can get faster. That's not true. So, are you going to have to start making your software stack more efficient? Are you going to have to start learning about machine learning? So it's, you know, it's kind of a it's a warning or call for arms that the world is changing right now. And a lot of people, a lot of computer science phds are unaware of that. So a way to try and get their attention is to say that more slaw is slowing down and that's going to affect your assumptions. And uh, you know, we're trying to get the word out and when companies like TSMC and intel say, oh no, no, no moore's law is fine, then people think, okay. And I don't have to change my behavior. I'll just get the next servers and you know, if they start doing measurements, they'll realize what's going on. </s><s>[INST] It would be nice to have some transparency and metrics for for the lay person to be able to know if computers are getting faster and not to forget. [/INST] Yeah, there are, there are a bunch of, most people kind of use clock rate, uh, as a, as a measure performance. You know, it's not a perfect one. But if you've noticed clock rates are more or less the same as they were five years ago, computers are a little better than they aren't. They haven't made zero progress but they've made small progress. So there's some indications out there and then our behavior, right? Nobody buys the next laptop because it's so much faster than the laptop from the past for cell phones. I think uh, I don't know why people buy new cell phones because of the new ones announced. The cameras are better. But that's kind of domain specific right there putting special purpose hardware to make the processing of images go much better. So that's that's the way they're doing it. They're not particularly it's not that the armed process in there is twice as fast as much as they've added accelerators to help the experience of the phone. </s><s>[INST] Can we talk a little bit about one other exciting space, arguably the same level of impact as your work with risk is raid in your In 1988 you co authored a paper, a case for redundant arrays of inexpensive discs, hence our ai de rate. So that's where you introduce the idea rate, incredible that that little I mean little that paper kind of had this ripple effect and had a really revolutionary effect. So, first what is? Right, [/INST] right. So this is what I did with my colleague randy cats and a star graduate student, Garth Gibson. So we had just done the 4th generation risk project and um randy cats which had had an early Apple uh Macintosh computer at this time. Everything was done with floppy disks uh which are old technologies uh that could store things that didn't have much capacity and you had to to get any work done. You're always sticking in your little floppy disk in and out because they didn't have much capacity. They started building what are called hard disk drives, which is magnetic material that can remember information storage for the Mac And randy asked the question when he saw this, a disk next to his Mac gee, he's a brand new small things before that for the big computers that the disk would be the size of washing machines and here's something the size of kind of the size of a book or so. So I wonder what we could do with that. Well, we The ready was involved in the 4th generation risk project here at Brooklyn eighties. So we figured out a way how to make the computation part, the processor park a lot faster. But what about the storage part? Uh can we do something to make it faster? So we hit upon the idea of taking a lot of these disks developed for personal computers at Macintoshes and putting Many of them together instead of one of these washing machine sized things. And so we worked, wrote the first draft of the paper and we'd have 40 of these little PC disk instead of one of these uh washing machine sized things and they would be much cheaper because they're made for PCS and they could actually kind of be faster because there was 40 of them rather than one of them. And so he wrote a paper like that and send it to one of our former Berkeley students at IBM and he said, well this is all great and good, but what about the reliability of these things now, you have 40 of these devices, each of which are kind of pC quality, so they're not as good as these IBM washing machines, IBM dominated the, the storage canisters. So reliable is gonna be awful. And so when we calculated it out instead of, you know, it breaking on average once a year, it would break every two weeks. So we thought about the idea and said, well we got to address the reliability so we did it originally performance, but we had the reliability. So the name redundant array of inexpensive disk is array of these disks inexpensive life for Pcs, but we have extra copies. So if one breaks we won't lose all the information, we'll have enough redundancy that we could let some break and we can still preserve the information. So the name is an array of inexpensive disk. This is a collection of these pcs and they are part of the name was the redundancy. So they'd be reliable. And it turns out if you put a modest number of extra disk in one of these are raised, it could actually not only be as faster and cheaper than one of these washing machine disc, it could be actually more reliable because you could have a couple of breaks even with these cheap disks. Whereas one failure with the washing machine thing would knock it out. </s>
<s>[INST] that a lot of them, [/INST] a person, a shrewd politician, a shrewd manager of public image could </s><s>[INST] build [/INST] on and create a circumstance in which more and more people will feel safe to express that view and the more </s><s>[INST] who express it, the [/INST] safe for those who have yet to express it, but who hold it </s><s>[INST] well feel [/INST] in expressing it. And to the extent that the view is very widespread but is kept under wraps, An explosion could happen. And </s><s>[INST] you can look up tomorrow and have a [/INST] very different country than you had today because the conspiracy of silence. The spiral of silence ends up getting unraveled by somebody who steps out away from the consensus dares to take the slings and arrows of exposing themselves as the naysayers. But taps into a sentiment that's uh, that's very widespread </s><s>[INST] and I [/INST] fear that with respect to many racial issues, this is uh, the situation that we actually </s><s>[INST] confront, that it [/INST] could unravel in a very ugly way, </s><s>[INST] but he could also unravel and in a beautiful way. So it is the depending there is a spiral of silence you're saying and it could be because speaking of Children, charismatic Children, uh there's a guy named Elon musk who might be a candidate for such an unraveling right? You [/INST] mentioned </s><s>[INST] the person that speaks out could be a donald trump, but in this current situation that we live in like as this week, Ellen has purchased twitter, that's what I hear and is pushing for um in all kinds of ways, the increase of free [/INST] speech on </s><s>[INST] twitter and [/INST] speaking about </s><s>[INST] some of the issues that we've been speaking about here with you, but maybe in broader strokes about just the fact that you have to, it's okay to point out that the emperor wears no clothes and to do so from all sides in a way that everybody is a little bit piste off, but not too much. What do you think about this whole effort of free [/INST] speech uh </s><s>[INST] in these public [/INST] platforms? Um </s><s>[INST] Ellen in particular twitter, your avid twitter user, um but just public platforms for discourse for us as a civilization to figure stuff out. Yeah, [/INST] well, the people on the left are very upset about the possibility that Elon musk uh and twitter </s><s>[INST] will be open [/INST] to more </s><s>[INST] open to [/INST] uh provocative </s><s>[INST] public [/INST] speech that has heretofore been </s><s>[INST] banned or suppressed [/INST] and I think they might be right to be concerned that that </s><s>[INST] could happen. [/INST] I don't know enough about the technology and about the market to really Yeah, I mean social media and whatnot, it seems like </s><s>[INST] it's a [/INST] complicated system of interactions </s><s>[INST] between [/INST] people and who the users are and so forth and so on. Um I do know that that the new york post story about Hunter biden's laptop </s><s>[INST] was real [/INST] news and could have affected the outcome of the election and it was suppressed and that twitter had a role in suppressing it. I do know that the question of where the covid 19 virus originated in the role that uh lab leak account could have played in the public processing of that event was </s><s>[INST] real news [/INST] and that it was suppressed by people who are trying to control misinformation, disinformation, Russian disinformation campaigns and whatnot. Uh so twitter has users, I'm one of them and it has a lot of users, it's not as big as facebook, I gather, it's not but um it's important the ability to construct counter platforms where people moving around and whatnot. Uh it's a kind of network dynamic, that maybe I should understand it better than I do being a social scientist, but I don't think anyone understands that even if </s><s>[INST] people include inside twitter, which is fascinating, it's a [/INST] monster because </s><s>[INST] of just the band with [/INST] messaging and you don't know </s><s>[INST] who is a bot and who is a human. That's a fascinating dynamic and the end the viral nature of negativity um that all of those dynamics, of course, you are probably the right person to understand it from a social scientist perspective from an economics perspective, [/INST] but nobody really understands </s><s>[INST] and it's fascinating within that [/INST] domain. How do you </s><s>[INST] allow for free speech not allow for free speech, encourage free speech to defend free speech and at the same time manage [/INST] millions of </s><s>[INST] ongoing conversations from [/INST] just </s><s>[INST] becoming [/INST] insanely </s><s>[INST] chaotic sort [/INST] of from from </s><s>[INST] twitter perspective, they want people to be happy to grow to actually have difficult critical [/INST] conversations </s><s>[INST] and they, you know, the [/INST] problem with humans is they think they know what that is </s><s>[INST] and they um I think they can label things as [/INST] misinformation as </s><s>[INST] as counterproductive for healthy conversations in quotes. And the problem is as we are learning, humans are not able to do that effectively. First of all, [/INST] power corrupts. </s><s>[INST] There's something [/INST] delicious about </s><s>[INST] having the power to label something as [/INST] misinformation. You </s><s>[INST] do that once [/INST] for </s><s>[INST] something that might be [/INST] obviously misinformation </s><s>[INST] and then you start getting greedy, you start getting excited. It feels good, it feels good to label something as misinformation and disinformation that you just don't like and over [/INST] time especially </s><s>[INST] if there's a culture inside of a company that leans [/INST] a certain </s><s>[INST] political direction. [/INST] Orleans in all the groups that </s><s>[INST] we talked about leans a certain way they'll [/INST] start to </s><s>[INST] labels misinformation things they just don't like and there's that power is delicious [/INST] and it corrupts, you </s><s>[INST] have to construct mechanisms like the founding fathers did for somehow preventing you from [/INST] allowing that power to get to delicious </s><s>[INST] at least. That's my perspective on what's going [/INST] on. I'll just tell you personally, I'm excited about the prospect. </s><s>[INST] I'm glad [/INST] to see musk making the move that he's making </s><s>[INST] and we'll see what happens at twitter [/INST] and so forth. </s>
<s>[INST] the physics of that is fascinating how to eject safely. Do [/INST] you know the story about how that was tested at all? I don't know the full story but there was </s><s>[INST] nobody knows the full story. Probably a lot of shady stuff going on. But uh you mean like in the early early days or [/INST] took a flight up to a rocket sled and just see how much their body could </s><s>[INST] take it. [/INST] And he turned a lot of his body in the in the mush in the in the process of getting that science done. But he saved a lot of life </s><s>[INST] people. You used to be tougher back in the day, that's how science used to be done. Um So how did your training continue? So how did take me take me further through your career Uh as you work towards graduating towards the F- 18s? [/INST] So in VT nine where I was a student, there's two phases. There's an intermediate and advanced Intermediate is getting very comfortable with the aircraft and at that point you truly here alright you're going jets now or you're gonna go one of the other aircraft that land on the aircraft carrier. I was told I was going to you know, jets at that point and then we go into the same squadron, same aircraft, same instructors but it's called advanced now and now we're um learning how to dogfight for the first time. We're um doing what we call tactical formation which is just like aggressive position keeping. Um We're doing um </s><s>[INST] dog [/INST] fighting and low levels and all sorts of great stuff. So it's really that first introduction to the tactical environment and putting really putting Gs on the jet on your body and maneuvering. </s><s>[INST] Is there like tactical formation is collaborating with other fighter jets are part of that. So flying in that's what you mean by formation. So literally having an awareness. Is this done for you or are you as a human supposed to understand like where you are in the formation, how to maintain formation, all that kind of stuff done autonomously or manually. [/INST] There's a great autonomy point on the end of that I've thought about. So, but what we do, it's all manual and so I'm looking at his wing and I'm looking at um different visual check points that form like a triangle, right? Like an equal out triangle essentially. And then as that triangle, you know, is no longer equal. I can tell my relative position against that </s><s>[INST] aircraft. [/INST] And so that's what I'm staring at for sometimes hours on end, you know, several feet away doing one of these from in the weather. That's all it is. </s><s>[INST] So you get, it's almost like is a peripheral vision or is it, you [/INST] know, we're staring directly at it. The peripheral is going on my on my um </s><s>[INST] that's interesting [/INST] stuff. Right? My sensors and on my instrument And so he is my gyroscope at that point. Right? </s><s>[INST] While you're flying, not looking straight, [/INST] correct? I'm flying like this for hours, it can hurt, you know, we don't like doing this as much and I don't think it's just me. Right? It's a weird thing where when you're like this, it's actually harder to fly formation slightly than here because being in line of your hand movements and of the aircraft somehow has an effect on our ability to be more precise and comfortable. It's strange. So, </s><s>[INST] but so that there's a symmetry to the formation usually. So one of the people on the other side really don't like being on that side. Is it is it does it, who gets the short straw? How do you decide which side of the formation you are? [/INST] It's a good question too because there's there's kind of rank in some sense. So if it's a four person formation right, you have the division lead who's qualified to lead a whole division, but maybe the other ones aren't and he has a dash to and that's his wingman essentially. And then in a division there's two other aircraft and then you have another senior flight leader that's the dash three position and then you have dash four the last one and if you are all lined up on one side like fingertip um 1234-4 guys gonna be at the end of that whip. So if you're flying formation, each one is making you know, movements relative to the lead. Dash four is kind of you know at the end of that error, you know, and so his movements are kind of like a whip. It's very difficult to fly in that position in close </s><s>[INST] if [/INST] this is a slightly and this is dash to slightly is rock steady and just doing his thing and flight two is going to be working that triangle moving a little bit right and he has a small air bubble that he's doing his best to stay and then dash 3-2 and so his air bubble is dash plus his own and more </s><s>[INST] and more stressful as you [/INST] get. Yeah </s><s>[INST] okay. Um What's the experience of that staring for long periods of time and trying to maintain formation. How stressful is that? Because like you know we're doing that when we drive staying in lane and that becomes after you get pretty good at it, it becomes somewhat it's still stressful um which actually surprisingly stressful when you look at like lane keeping systems, they actually relieve that stress somehow. And it's actually creates a much more pleasant experience while you're still able to maintain situational awareness and like stay awake, which is really interesting. Like I don't think people realize how stressful it is to lane keep when they drive. So this is even more stressful. So are you do you do you think about that or is this um Yeah, I guess how stressful is it from psychology perspective, [/INST] it's very stressful when so I taught students how to do this as well and so at our feet we have two riders and if I'm flying off a flight lead over here, what you'll find a lot of times you'll be flying or like if I'm an instructor and the students flying, I'll start to notice that he's having a harder and harder time keeping position. What I'll notice typically is he's locked out his leg the lock out the leg that's closest to the aircraft they're flying against and push on the rudder. So consciously because their whole bodies trying to get away from the aircraft cause they're so uncomfortable being close to it. And so I'll tell them, I can, I can fix their form with just a couple of words, I'll say wiggle your toes and they wiggle their toes and they'll realize and they'll loosen all the muscles in their legs. They realize they've been locked up and the formation flying will get a lot better. Uh, and so, you know, there's a lot of stress associated with that. There's some interesting um psychological or visual uh issues such as um vertigo as you're flying. So if you're flying with him and then you fly right into a cloud, right? That was very stressful because you have to be very close in order to maintain visual, you might be on thunderstorm right? Um, and so you have to be very tight, you might start raining. Um, and then he's turning, but you might not even know that you might not even be able to see that turn and so all of a sudden you might look while you're in a turn thinking you were straight and level and you look just maybe back at your instrument very quick and you realize you're like in a 30 degree turn and your whole concept of where you are in the world, starts getting very confused and you immediately get this this sense of, it's weird like I look at the hut and it it feels all my senses are telling me it's spinning but it's not you know and so I have to trust my instruments even though it feels like it's spinning and the same thing can happen when you're flying formation off of someone and it it can be very um very dangerous and disorientated. </s>
<s>[INST] So there's so many questions I want to ask. So one of the ways that people can help is by adding to the knowledge base and that's really basically anybody, if the tooling is right, and um, the other way I kind of want to ask you about your thoughts on this. So you've had, like you said in government and um, you have big clients had a lot of clients, but most of it is shrouded in secrecy because of the nature of the relationship of the kind of things you're helping them with. So that's one way to operate. Another way to operate is more in the open where it's more consumer facing. And so, uh, you know, hence something like open cycles born at some point where there's [/INST] no, that that's a misconception, </s><s>[INST] uh well, let's let's go there. So what, what is open psych and how is it born? [/INST] two things I want to say and I want to say each of them before the other. So it's </s><s>[INST] going to be difficult, [/INST] but we'll come back to open site in a minute. But one of the terms of our contracts with all of our customers and partners is knowledge you have that is genuinely proprietary to you. We will respect that. We'll make sure that it's marked as proprietary to you in the psych knowledge base. No one other than you will be able to see it if you don't want them to and it won't be used in inferences other than for you. And so however, any knowledge, which is necessary in building any applications for you and with you, which is publicly available. General human knowledge is not going to be proprietary. It's going to just become part of the normal psych knowledge base and it will be openly available to everyone who has access to psych. So that's an important constraint that we never went back on, even when we got pushed back from companies, which we often did, who wanted to claim that almost everything they were telling us was proprietary. Uh, so, </s><s>[INST] so there's a line between very domain specific companies specific stuff and the general knowledge that comes from that. [/INST] Yes. Or if you imagine, say it's an oil company, there are things which they would expect any new petroleum engineer they hired to already know and it's not okay for them to consider that that is proprietary. And they're sometimes the company will say, well, we're the first ones to pay you to represent that in psych. And our attitude is some polite form tough. The deal is this, take it or leave it. And in a few cases they've left it in most cases, um, they'll they'll see our point of view and take it because that's how we've built the psych system by essentially tacking with the funding winds where people would fund a project and half of it would be general knowledge that would stay permanently as part of psychic. </s><s>[INST] So, always with these partnerships, it's not like a distraction from the main psych development. It's uh, support of small distraction. It's a small, but it's not a complete one. So you're adding to the knowledge base. [/INST] Yes, absolutely. And we try to stay away from, um, projects, uh, that would not have that property. Um, so let me go back and talk about open psych for a second. So, I've had a lot of trouble expressing convincing other ai researchers how important it is to use an expressive representation language, like we do this higher order logic rather than just using some triple store knowledge, graph type representation. Um, and so as an attempt to show them why they needed something more, we said, oh, well, well represent this unimportant projection or shadow or subset of psych that just happens to be the simple binary relations, the relation, argument one, argument two, triples and so on. Um, and then you'll see how much more useful it is if you had the entire site system. So it's all well and good to have the taxonomic relations between terms like person and night and sleep in bed and house and eyes and so on. But think about how much more useful it would be if you also had all the rules of thumb about those things like people sleep at night, they sleep lying down, they sleep with their eyes closed, They usually sleep in beds in our country. Uh, they sleep for hours at a time. They can be woken up. They don't like being woken up and so on and so on. So it's that massive amount of knowledge, which is not part of open psych. And we thought that all the researchers would then immediately immediately say, oh my God, of course we need the other 90% that you're not giving us, let's partner and license psych so that we can use it in our research. But instead what people said is, oh, even the bit you've released is so much better than anything we had. We'll just make do with this. And so if you look, there are a lot of robotics companies today, for example, which use open psych as their fundamental ontology. Um, and in some sense, the whole world missed the point of open psych and we were doing it to show people why that's not really what they wanted. And too many people thought somehow that this was psych or that this was in fact good enough for them and they never even bothered coming, um coming to us to get access to the full psych, </s>
<s>[INST] but you can't just magically acquire skills by stepping on stage. All of us are able to fall [/INST] in confidence. Yes. So the question becomes who manages that fall best? And that can create </s><s>[INST] upsets. Absolutely. So you don't think Gordon could have fallen in confidence against a former teammate when the pressure is so high? There was just no basis for a fall to occur. You said he [/INST] doesn't have confidence issues. What do you attribute that to? That's because he never loses in the gym. There's no experience at his head that would make him say, I shouldn't be this confident. So it's the physical, it's like we talked about mental preparation. Don't get me wrong, if Gordon lost 20 matches in a row, of course his confidence would drop. Because experience is now, there's going to be a psychological dissonance between his recent experience and what he believes. If you believe you're the best in the world, you just lost 20 matches. At some point, reality is going to break in. But if you're just never losing in competition, dominating people in the gym, then there's nothing in your experience that would shake your confidence. </s><s>[INST] Can I ask you this just in a small tangent? Why is Gordon Ryan so good? So we're looking at, you've trained a lot of special athletes, you're a special human being yourself. I could just look at human history. There's a lot of, not a lot, there's some special humans. It seems like Gordon [/INST] Ryan is one of them. I totally agree with that. Can you try to dissect? That's what I meant when I said I had many students, but only one Gordon Ryan. Like I've taught many, many people, but they don't all have his skill level. So there's an obvious elephant in the room. What distinguishes him from other athletes? Great question. I'll try and give an answer. More than anyone else that I've ever taught, he has a memory for things that were taught to him. He has an ability to recall information that is extraordinary compared with other people in the room. So that's definitely a big part of it. Secondly, he has a pride in technique and technical prowess that will not allow him to settle for anything less than perfection. And he will hate himself when there is imperfection. So there is a love of excellence and a hatred of anything less than excellence. He has an ability to pull the trigger when opportunity arises, which is truly extraordinary. Many people know what to do, but when the moment comes, they back off and they'll doubt themselves. </s><s>[INST] If Gordon sees the opportunity, the trigger pulls every time. So can I just link on that? Absolutely. There's a few times where he gets a little bit of an advantage and he just chases it to get a big, like with Andre Galvao. There's a dance and you get one step ahead and he's able to chase that. Get a little glimmer of the back and he's able to chase that all the way to back control. So is that the trigger that you're referring to? [/INST] Yes. It runs deeper than that too. It's the idea that good athletes are greedy athletes. Okay. When they see a small opportunity, they try and get as big a bite of it as possible. The mantra that we always have in training, if you can see the back, you can take the back. And if Gordon sees an inch of your back, that's the direction he's going to be going. If your far shoulder is within an inch of the floor, he's going to be mounting you. If your shoulder comes off the floor, he'd be on your back on the other side. He's a maximalist with opportunity. He's not satisfied with, oh, let me get a good enough outcome. It's like, I want the maximal outcome. So when you combine all these things together, an ability to recall information, which is just far superior to anyone else I've ever coached, an ability to work in the training room towards not just good technique, but excellent technique, the confidence to pull the trigger whenever the opportunity arises, a maximalist mindset where it's never enough to have a good enough outcome. It's always got to be the best possible outcome. And the fifth element, which I believe is very, very important, is extraordinary depth in his technical prowess, in particular with regards his defensive acumen. Everyone looks at Gordon and focuses on his offensive prowess because they see him dominate other athletes. But what they don't see is what I see every day in the gym where he works from impossibly bad defensive positions. Someone locked in on a full heel hook on his body and a full Jujigitami Amba in a complete pin mounted with Gordon's two arms stretched out over his head in what looks like a hopeless position. And Gordon will work in these positions. And of course, because it's such a bad position, sometimes he'll have to tap. But he just works so relentlessly in these bad positions that when he steps on stage, he's like, if this guy got the worst possible position on me, there's nothing he could do with it. And within 30 seconds, I could turn it around on him and win this match. That gives his game an overall breadth and depth, which is very, very hard to deal with. It means there's no obvious weak point where you can just say, okay, I'm going to attack him here and use this strategy to beat him. And that goes back to his confidence. The reason why most people lack confidence is they fear bad outcomes. If you're a strong guard player, you've got an excellent guard, but you're terrified of leg locks and your opponent has strong leg locks, you will shut down your own guard and won't play as freely and well as you normally do, because you're afraid of the leg lock danger. You'll pull your feet and you'll play a very conservative guard game. But if you had extremely adept leg lock defense, then you just play with all the confidence you normally do from guard position. Gordon puts himself in that situation. He's so defensively </s>
<s>[INST] So even in low point, there's that you had strength. Is there anything you can give by way of advice from people that for whom the wave function collapses as it does for many of us? Like, holy fuck, the world is not full of opportunity and you're kind of a failure. [/INST] Like I've been there. Yeah, I don't know. It's rough because like I usually ask for compassion from people that have it better off because like once you're down there, like the only reason I say I got lucky but it wasn't even really lucky or it was lucky but it was more lucky. It wasn't just lucky that I got into streaming. It was lucky that I was in the computers in an early age. It was lucky that I played video games at an early age. It was lucky that all the tech came up at exactly that right point in time. Like I was a pretty smart guy but it was definitely a preparation meets opportunity and that opportunity was like at the exact precise moment of my life. If anything had gone differently then I would just be cleaning carpets today, so. </s><s>[INST] So in the many worlds interpretation of quantum mechanics, this is like one out of like There's many, many Stevens, they're just still carpet cleaning [/INST] and they're full of pain and resentment. Yeah, the one piece of advice that I give, I hate that I have to push back against all these crypto bros and everybody online. For decently intelligent people that are successful, I've never heard anybody give a contradiction to this. Maybe you will, you can tell me if you disagree. I always look at kids in high school and I'm like, just try a little bit harder. Like 30 minutes a night, if you don't study, just do 30 minutes, just do a little bit more. It is, you are laying the foundation for the rest of your life and you can't appreciate it in high school and college, but oh my God, when you get out, everything in your life is so much easier. You have probably more responsibility over the direction of your life when you're like 13, 14 years old, than you ever will once you're like 25 and older, because this is like when you're determining the foundations that everything's gonna be able to accept. </s><s>[INST] But yeah, 100%, so first of all, it does seem that the liberating aspect of being young is like anything you learn. So working hard at learning something will pay off in like nonlinear ways, like you said with video games. I feel like so people who are like, I hate school, all right, well fine, but find something where you're challenging yourself, you're growing, you're learning, you're learning a skill, you're learning about a thing. Of course, you could push back and say, well, there's some trajectories that might not be productive. Like if you spend the entirety of your teen years playing, I don't know, League of Legends, game you have love and hate relationship with. No, just a hate and hate relationship. Okay, well, we'll talk about, I think you have a love-hate relationship with hate, in general, we'll just talk, and love. Okay. We'll try to de-complexify that one. I think in general, just investing yourself fully with passion, it really does pay off. But that said, also school, I feel like doesn't get enough credit, like high school in particular. Middle school and high school. Because it's general education. I think, especially if you're lucky to have good teachers, but honestly, I haven't, mostly. The textbooks themselves were good teachers. It's a one chance in life, you have to really explore a subject. Fuck grades, like getting good grades is attention, I would say, with actual learning. That is true. But just get a biology textbook, and to explore ideas in biology, and allowing yourself to be inspired by the beauty of it. Yeah, I don't know. I think that really, really, really pays off, and you never get a chance to do that again. And maybe not even textbooks, like reading, straight up reading. I think if you read, this is the one time in life you get a chance to read, really read. Like read a book a day, read. [/INST] You could really invest in young. </s><s>[INST] It's like, and you can really grow by reading. [/INST] I mean, I must, all those guys talk about it. It's very, very rare that you meet a dumb person who reads a lot. </s><s>[INST] I don't know if that's ever happened in my life. Dumb or not successful. And the cool thing is, it seems like the reading, it's like investment, the reading you do early on in high school pays off way more than the reading you do later. So like the really influential reading is doing those high school years, because you're basically learning from others the mistakes they've made, the solutions to problems. You're basically learning the shortcuts to life. Like whatever the hell you wanna do. Music, read from the best people that the music theory, like learn music theory, learn, read biographies about jazz musicians, blues musicians, see all the mistakes, see what they did, see the shortcuts. If you wanna do podcasting, read about other podcasts. If you wanna do streaming, read about other streamers, physicists and so on. And I feel like you figure out all the mistakes and you get to shortcut through life because most people show up to college without having done that. And now you get a chance to shortcut your way past them. Yeah, 100%. But nobody really teaches you that. They're like, go to school from this time to that time, you're, shut up, this is just what you do, [/INST] eat your broccoli. I think I was like, there's two huge problems. One is, now that I'm older, cause you don't know anything as a kid. You can't really criticize as adults as a kid because you're a kid. But you're ageist, if I may be specific, I am super ageist. As I get older, I get even more ageist. There are a lot of people who are arguing, I was like man, dude you're really 22, aren't you? I can tell every word you say. There's a sense of like 22 year olds, </s>
<s>[INST] That's not as less as more. One of the things that, one of the things that inspires me about Rogan, for example, is he almost never does this kind of stuff. [/INST] Yeah. Yeah. And how suddenly does this podcast? Cause you're right, less is more. What does he do it like once a month? No, he does it three times a fucking week. </s><s>[INST] More is perfect. But for example, when he does like a story or something like this, he does one take. It's kind of shitty. [/INST] It's the same. It's the same. It's elk with a bunch of jalapenos, a knife that he had sent to him by a fucking knife maker, and him going, look at this. Look at this, Traeger Smoker. I reverse seared this. This is what's great. Look at this. I'm about to put it in the butter. This is grass-fed butter. This elk really raises my testosterone. Rogan is, you're right. With guys like Rogan, when he does do a story, they're a little precious. </s><s>[INST] Yeah. And I don't think he's ever done a second take of those stories. No. You have to really admire that. If the shot is framed poorly, if the audio sucks, it doesn't matter. [/INST] Do you remember when he... This is like, I can get on the weeds on Rogan, and especially when it's Instagram. Do you remember when he got his polar plunge and he couldn't sit it in a minute, and then the next day, and then he must have gotten it on the internet bad. He must have gotten it bad. The next day, he sat in for 20 minutes and he lowered his core temperature by like two degrees and it took him like a month to get that back. That is that fucking man. What an interesting, you know, I told you at the beginning, we were just talking. I like, I really enjoy, I draw inspiration for men I'm not like. You, David Goggins, Cam Haynes. Andrew Huberman, we're talking. Huberman, I love fucking, I mean, there's so many guys like that, Rogan, you know, Tim Kennedy. Like there are a lot of guys that are like just very different men than me and I love Jocko Wilnick. Like I love, I love reading their stuff or listening to their audio books or listening to their podcasts because I'm so not like that. But that took for me when I add a little bit of that in my life. Like I remember you went, I don't know what you were doing, but you were walking us through your day. And it was so fascinating. It was like, it was like, I ran eight miles today. I listened to an audio book. I was running eight miles and then I came and I worked for about three hours straight on AI stuff. And I'm like, and I was like, wait, you sat at a desk? Like you like sat at a desk and like, and I actually, I wouldn't even know what to do. I would start doing crafts. I was like, is your computer? </s><s>[INST] Have you set for four hours focused on a single task? Me? [/INST] No. Oh, I'm sleeping for four hours. I don't have a brain that... I really admired it when I listened to you do it because then you were like, You were talking, you were fasting at the time, you were doing your fast and then you talk about what you ate. And I was jealous. I wanted to be able to be like that. And I think at that time we started, I think you were doing maybe bone broth or something. And we started doing bone broth pretty religiously and adding that into a fast. Cause I was like, it does for someone like me, it does feel cool to add a little bit of control into life. </s><s>[INST] So integrating a little bit of a way of being from another person that you're not like, [/INST] Yeah, like, so David Goggins is consistently pushing himself. I love. I did it over the pandemic more, but I love to go in. Today, I'm running a marathon. I'm going to get on the treadmill, and it's not going to be all at once, but I'm going to get through a marathon today. So let's get up, get up at 6 o'clock for some coffee, and let's see if we can do like five miles, and then know that we started there. And that was really fun. Cam Haines does that too, where he goes like, He almost just sets the limit and then achieves that. His son Truett is really fascinating because his son Truett's right now is trying to get the, and I bet people would never think that this is who I watch, but I get real inspiration from those people because I showed Jaco, I showed a clip to Jaco to Isla because Isla's like me, like a person of her fluids, impulse. I walked in on her one time. She was in the pantry in a bathrobe in the dark drinking a root beer. Yeah. And I opened the door and she went, I said, what? She goes, I thought you were a mom. Shut the door. And I shut the door to let her finish the root beer. Yeah. She has a hard time waking up. So I go, I look, come in here. I want you to see this clip from Jaco. She goes, who's Jaco? I say, he's a Navy SEAL. She goes, he works at the zoo. I went, no. He said, Navy fucking SEAL. I go, it's a badass job. She goes, it's a silly name. And I went, no, it's not. It isn't a silly name. These guys are the toughest dudes in the world. </s><s>[INST] She goes, she's kind of right though about the silly name. I never even realized that. [/INST] Well, yeah, you talk to a child. Yeah. And so I go, watch this, what he says about waking up. So it hits the thing and Jaco goes, first thing you do when you hear that alarm clock, you could roll over, you could go back to bed, you could hit snooze, but you get out of bed and that's your first victory. And Isla hits pause and she goes, How great is that nap right after you hit snooze though? It is pretty fun. You're missing the point. He's with Casey Neistat when he's telling the speech. He's with Casey Neistat. And uh, so I hit it and then he goes and then you've got a victory under your belt. Then you go to the gym and you work out and I go, you listen to this island and she goes, yeah. And he goes, and then when you go to the work, now you've got two victories. You've worked out and you've woken up on time. You didn't hit that snooze button. So when you go into that break room and you see Donuts and she hit the pause, she goes, um, if he's about to say no to donuts, I'm done listening. I was definitely going to say no to donuts. Do you think he's going to have a donut? And she goes, You like this guy, I go, I fucking love him. And she goes, do you think he'd like you? And I go, what do you mean? She goes, dad, you hit snooze, you skip working out and you love donuts. And I'm like, yeah, you're making a good fucking point. I go, I, but I, but I do love that. Like I love to watch that brain work and go like, Like I don't, I don't hit snooze. Like I don't hit snooze now. I go, fuck it. Cause I'm up. But I, and then, and then I go to the gym every single morning. I go to the gym every single morning. And today is national donut day. I didn't have a donut. And so like, I, I, like, I try, I like try to apply these a little bit. Cause I, I mean, the other side of me is like, tonight, after we do this, I'll do another podcast and then I'm going to call Leanne and go, yo, we're in Beverly Hills. Meet me out here. Let's go have drinks. Let's go have a fucking couple of compari spritz. I was over at a friend's house and overnight. Let's get some edibles and let's fucking have a night about it. Get some sushi. Go have sex in the hot tub. And I got to work out at fucking 10 in the morning. </s>
<s>[INST] it is uh kind of [/INST] a strong </s><s>[INST] first step in creating a fake identity. [/INST] Very strong, very strong so that </s><s>[INST] so that was like gas. Co just on on on the point he made that if you're going to be successful in this you should have people you trust. Is he right on that? [/INST] Always? Absolutely right. Absolutely. </s><s>[INST] So you have to have, this is like mob, [/INST] you have to </s><s>[INST] you have to have an inner circle of trust. [/INST] You know, I'm sure you've probably heard me say this before, successful cybercrime. All right, there are three necessities to being successful online if you're a criminal, three necessities are gathering data, committing the crime and then cashing it out, all three of those necessities have to work in conjunction. If they don't, the crime fills the problem and it's a huge problem is that one guy can't do all three things. You know, you've got to you've got the people who gather the data, basically the the general store sales people who sell P. Ii. Credit card logins, data tools, they always sell the sport phone numbers and our GPS stuff like that. A lot of the times those people don't know how to commit the crime and those people certainly don't know how to launder the money out and put cash in pocket. So you've got either because of a skill level, sometimes a geographic location limits what that individual can do. All right. So you have to rely on people who are good in areas where you are not in order for that crime to succeed. And that means you have to trust those people. So what happens with Shadow crew? Alright, so counterfeit library is the start. All right, counterfeit library transitions over to Shadow crew. Right before that transition, there's a Ukrainian guy by the name of Dmitry Golovanov. He was a spammer at that point in time. He saw what we were doing with with counterfeit library and he liked it. He was getting all these credit card details and this kid, I mean, he's a kid, this kid has an idea and his idea was I wonder if people would buy stolen credit card details. That's </s><s>[INST] pretty good. Uh Ukraine Russian accent. So [/INST] he he picks up the phone, he calls his buddies, They call their buddies. They have a physical conference in Odessa, 150 of these cybercriminals show up and they launched this idea that launches a website called carter planet, which is the genesis of all modern credit card theft as we know it. All right. And so remember I mentioned those three necessities of cybercrime, Dimitri had all the credit data in the world and he partnered with all these other Ukrainians that had all this data as well. The problem was that so much fraud had been committed on that eastern side of europe that every card had been shut down even if you were a legitimate cardholder and tried to cash it out and you weren't doing it at that point. So again, those three necessities gathering data committing crime cashing out Dimitri had the data, they could commit the crime, They could not put cash in pocket. So we were running counterfeit library one day I get this message or not a message one day script shows up. And he posts just on the general forum, he posts, hey, I've got credit card data. Give me an address, give me a burner phone number, wait five business days or whatever you want to. We had never seen anything like that. We were a Paypal fraud and Ebay fraud side, it's what we were and fake driver's licenses. So then and we had, I guess we had to 3000 members at that point. So the response from the members was that can't be real, you've got to be law enforcement. It's gotta be in trying to get us arrested and everything else. What let me backtrack a little bit. So the driver's license that I had got Beelzebub had an idea what he wanted to do is he wanted to sell driver's licenses. Mr X wanted to sell social security cards. He made a very passable social security card. Me I didn't, I had no skill level on that. I knew Paypal fraud and Ebay fraud. So Beelzebub was like, tell you what, you be the reviewer that way you get every product or service that comes in, they'll have to send it to you or let you have access to it. You can learn the entire game and because you're not selling anything, it gives you legitimacy on the reviews. All right. So I started out as a reviewer, the only review or on counterfeit library. So over the next year, Beelzebub turns out he was a pot grower. He goes back to growing pot because he wasn't making shit selling driver's licenses Mr X about a year and a half in, he gets arrested, cashing out drivers, credit card, not credit cards, cashing out casinos doing some show with that. So I'm the only guy left standing and I'm at the top of the heap. So, and it becomes this thing where if I review somebody, they make a lot of money if I don't, you don't do business here. So script shows up saying he's got this, I'm the only reviewer on site. People think he's law enforcement. First week it goes like that After a while I'm like okay I gotta do something and I'm scared man because I'm like, he may be law enforcement. So I get him on IC. Q. And I'm like, hey you have to be reviewed. And he's like, what the hell is that? So I tell him what it is, he's like you review me and I was like, yeah that's the idea. So give him a drop address, give him a burner phone number, wait five business days and I tried to hit dale for $5000. The order fails. I got back on IC Q. Hey man, it didn't work. He's like, give me one more chance. I was like, look, I'll give you one more chance, but it's your ass after that and he's like one more chance. Like okay, give him another address, another phone number. Wait another five business days hit Thompson's computer warehouse for $4000 dale for $5000 order, goes through, get the products in, I post that review on counterfeit library and literally overnight we turn from an Ebay Paypal fraud site to accredit theft site and that becomes a lot of money really quickly for members. So we were doing now it's called CNP fraud card not present fraud. So you hit, you used hit an online merchant with stolen credit card data Back then a fairly experienced fraudster could profit 30 to $40,000 a month. Okay. Just buying you know laptops, what have you and cashing out, you know put them on Ebay for sale and sell them like that. 30 to 40 K. A month. Was the profit on that script. Had a lot of buddies. He had people like roman vega. These other guys that would sell not just credit card data but counterfeit physical credit cards as well. We had counterfeit </s>
<s>[INST] Anyway. Um, it's just so inspiring to me that Brendan Eich and all the other folks involved are able to innovate in this space, the history of technology or at least the history of the internet is largely told through the battles of the way we access the internet. And there's been a couple of browser wars with the Internet Explorer and Netscape with Firefox and all those kinds of things and the different html CSS javascript, all that kind of stuff that's operating through the browser to create the thing that we know and love called the internet. Now, the fact that there's new players in the game that can become super popular and can bring new innovations to the table is really exciting to me. And that's exactly what brave does. They also have a bunch of other things like thing I do want to mention is Brave search engine. They have that too. You should use it as a lot of other exciting benefits over the alternatives. All of this at brave dot com slash lex. This show is brought to you by missing domain. The maker of comfortable, stylish dress shirts and other men's wear. I wear the black dress shirt and I love it. It combines comfort and flexibility of athletic wear with the fit and style of a custom dress shirt. It's lightweight, breathable and moisture wicking. They have a bunch of super cool looking styles that is uh, almost too intense for me because as you may or may not know, all I wear is either a white or a black dress shirt with a black tie. That's in terms of dressy, kind of stylish, classy wear. That's, that's all I wear. And for that purpose they have exactly the thing I go to, which is their black dress shirt. It feels, it feels kind of incredible. So first of all, look wise, it looks like you would think uh a dress shirt looks like, but it fits your body well. At least mine, it just feels right. And that's not a true real thing to find funny enough, something you feel great in something you feel both comfortable and just, I feel bad as in right now, if you go to missing the main dot com and use promo code lex, you'll receive 35 bucks off any regular price order of 100 and $25 or more. So go to mizzen and main dot com and use your promo code lex. This show is brought to you by Athletic Greens and the A. G1 drink, which is an all in one daily drink to support better health and peak performance. It replaced the multivitamin for me and went far beyond that with 75 vitamins and minerals. It's the first thing I drink every day. I drink it twice a day now after a long run, which is what I'm about to go on. I'll come home, I'll mix in athletic greens A G one drink, I'll put it in the freezer, jump in the shower and by the time I'm out it's nice and chilled, which is just perfect. And I go to the zen place where I can think about how amazing life is. I can think about anything at all or nothing at all. And most of the time it's nothing at all the clarity of mind that comes after a long run listening to audiobooks or listening to brown noise or just listening to nothing. It's a part of life that brings me joy and most things in life bring me joy. But this is one of the intense constance of my joyful life anyway. They'll give you one month supply of fish oil when you sign up to athletic greens dot com slash lex. This show is also brought to you by indeed a hiring website. I've used them as part of many hiring efforts I've done for the teams I've led in the past. There is very few things in life as important as the people you work with, maybe your family, your friends and the people you work with. And quite honestly, some of the hardest things you do in life is with the people you work with and for many of us, if our work is our passion or at least some elements of our work is our passion. Some of the most passionate hours of our life is spent with the people we work with. So we should find the right team whether you're the person hiring or you're the person being hired. Indeed is the right tool Right now you get a free $75 sponsored job credit to upgrade your job post and you can get up to $500 extra and sponsored job credits with Indeed virtual interviews at Indeed dot com slash lex get it at. Indeed dot com slash lex offer is good for only a limited time terms and conditions apply go to indeed dot com slash lex. This show is brought to you by Graham early, a writing assistant tool that checks spelling grammar, certain structure and readability. Graham early premium. The version you pay for the version. They hope I convinced you to get the version I use. Which is one reason you might want to consider it because we're brothers in this Brothers and sisters united in this effort of achieving greater clarity and linguistic eloquence in the writing that we do because you don't want to descend into a ulysses of Finnegans wake by James, Joyce type of stream of consciousness. Writing that many of us descend into because a mix of tiktok and twitter and texting and whatever else the kids do these days has broken or damaged or at least led to us becoming stale in our ability to be deeply thoughtful and eloquent and clear in our writing which writing language is the way we can reach to another human soul and uh inspire anyway, Graham early is available on basically any platform and major sites and apps like Gmail and twitter and so on. Do more than just spell check, get your point across more effectively with Graham early premium. You get 20% off Graham early premium by signing up at Graham early dot com slash lex, that's 20% off at Graham early dot com slash lux. This is Alex Friedman podcast. To support it, please check out our sponsors in the description and now Dear friends, here's dan Reynolds. So we were talking off line that you're not just getting into programming, what what's uh the most beautiful program you've ever written, Something that brought you joy. [/INST] There's something I really love completion. It's the reason that I'm addicted to songwriting. I like there being nothing and then having some blocks or tools and building them into what you want it to look like. And then I find it incredibly rewarding to stand back and look at what you did at the end. It could be anything for me. It's, it was, is simple to begin with as just, you know, because it's our object oriented, like making a cube move like that. As simple as that, understanding that and knowing that I built that and made it do that is really rewarding and I think it's the thing that drew me into to wanting to learn more. But as far as what is some grandi like some big piece of code that I've done, like, absolutely not. It's more, I'm still a level where it's more like what is a tutorial that I followed and and got, you know, and and then, you know, yes, so I couldn't say I'm at a level where I've done anything beautiful at all, </s>
<s>[INST] 15, knowledge is like the Mozart of Rap. [/INST] Just bobby Fischer </s><s>[INST] bobby Fischer just born something something in them or maybe those early years just because he's uh he's not just good at the lyrics. He's also he goes deep with it just like you. So he's like there's there's depth. It's not just uh like mastery of the ward smith thing. It's just the message you actually uh sent across. Yeah. [/INST] And to us more phrase All right, that's the whole thing of energy. How do we condense all that energy into disk so that it could feel that? And he's definitely one of those artists emcees that does that And he was doing it at 15. You know, like I said, I'm thinking five years or four or five years older than ours. So I was always feeling, you know, my confidence of what I was doing about it. I was like this kids only </s><s>[INST] 15 Gotta step up my game [/INST] When he turned 19. Then we got automatic. Yeah. </s><s>[INST] From you. Or what are the best, the most memorable lyrics you've ever written? [/INST] Mm wow, That's a hard question for me. </s><s>[INST] The stuff stand out like stuff you're really proud of that was like important in your career. [/INST] Yeah. I mean, I think I did a song called Sun Sun shower. I don't know if we put it on the roof tank forever. Double cd, but only on the international version, But if anybody could go get those lyrics and write those lyrics down, you can just put that in your pocket and I'm sure to get an answer. At least about 25% of your life's problems. </s><s>[INST] Uh well that's a good one. Sunshine, you're where you talk about religion and God. That's that's good [/INST] tomorrow. I think it's on a diagram. </s><s>[INST] I'm not a record guy. [/INST] I'm a song a diagram. Yeah. </s><s>[INST] The answer to all questions. You're talking about God, the spark of all suggestions of righteousness, the pathway to the road of perfection. Who gives you all and never ask more of you, the faithful companion that fights every war with you before the mortal view of the pre historical, historical. He's the all in all. You're searching for the oracle. Goodnight man. This is such, this is so good, a mission impossible. It's purely philosophical. But you can call on your deathbed when you're laying in the hospital [/INST] on your death bed. I had a big have a scientist friend. Well, my wife's best friend, Rebecca. Uh, she married a science. They both signed and they both were scientists and she married uh dr Neil, I was gonna say their last names. But Neil and Rebecca, you know, you know, you know, my wife best friend. So they come over and me and Neil, we go through the longest debates of science and religion, we just go, we'll break, we could go break day with it. And you know, before he had a child, he was more adamant and you know, there's, you know, I don't believe in God, You know what I mean? After a child, he still kept his thing. But I just hit him with the question, if you was about to die because now you've got a child thinking about sleeping when you're thinking about yourself, you're about to die. You don't think you're gonna make that call. He's like, I'll make that call. And it kind of inspired my lyric because it was like, yeah, who you gonna? And I just want to say how far so you mention, look, that is one of my favorite lyrics, but that's part two to sun shower was the prequel to Sunshine. So if you ever get a chance to check out sun shower, Uh starts off with trouble follows a wicked mind. 2020 vision of the prism of life, but still blind because you lack the inner. So every center could end up in the everlasting winter of hellfire with thorns and splinters prick your eye out, You cry out, your words fly out, You remain unheard suffering, internal and external. Along with the wicked fraternal of generals and colonels land off thermal nuclear heat that burns you firmly and permanently upon the journey through the Journal of the Book of Life. But those who took a life without justice will become just ice. It's been taught your worst enemy couldn't harm you as much as your own wicked thoughts. But people ought to be not and listen what? So they find themselves persecuted inside their own universal court. So that is a long one. It's like a three pager, wow, that </s><s>[INST] is about life, that's like character integrity, how to be, how to be in this world and that ultimately connects to God, [/INST] who is God do you? I'm glad you just asked that question, because I actually, I'm going to have to make a distinguishable separation here. All right. Um and it's funny because I heard recently, uh heard a rabbi was debating with uh, this historian, Dr Ben, I can't pronounce stock the band name, but it was debating. And then the debate, they started going back through the Entomology. They went way back beyond antiquity because they was debating. And so there was, you know, some things that was going deep and they really went far far back to kind of the first word of of God. And it was when they pronounced it on this particular debate, it was Allah and it's definitely got Elohim. Um I've already agreed in my heart in my life that the father of this universe proper name is Allah. Um and of course in the law, get all, you know. Um and I don't think that God is the same as that. I think a law gives birth to God. In fact, if you take the word Allah A L L A H. And you take it through numerology or numbers, the number a being letter A being one L B 12 and you add it all up to its lowest, uh, you know, the last denominator, you're going to get the number seven And the # seven is going to bring you right back to that letter G. So Law Borns God, but God don't Born a Law. </s>
<s>[INST] So that's really interesting. So I guess the presence of compute and the President's supervised data allowed the empirical evidence to do the convincing of the majority of the computer science community. So I guess there's a key moment with Jitendra Malik and uh Alex Alyosha Effros, who were very skeptical, right? And then there's a Geoffrey Hinton that was the opposite of skeptical and there was a convincing moment and I think emission had served as that moment and that represented this kind of where the big pillars of computer vision community, kind of, the wizards got together and then all of a sudden there was a shift and it's not enough for the ideas that I'll be there and the computer be there. It's for it to convince the cynicism that existed that that's interesting that people just didn't believe for a couple of decades. [/INST] Yeah, Well, but it's more than that, it's kind of when put this way, it sounds like, well, you know, those silly people who didn't believe what we're what we're missing. But in reality things were confusing because neuron really did not work on anything and they were not the best method on pretty much anything as well. And it was pretty rational to say, yeah, this stuff doesn't have any traction. And that's why you need to have these very hard tasks which are which produced undeniable evidence and that's how we make progress and that's why the field is making progress today because we have these hard benchmarks which represent true progress and so and this is why we were able to avoid endless debate. </s><s>[INST] So incredibly you've contributed some of the biggest recent ideas in ai in computer vision language, natural language processing, reinforcement learning sort of everything in between? Maybe not Ganz is there? There may not be a topic you haven't touched. And of course, the fundamental science of deep learning. What is the difference to you between vision language and as in reinforcement learning action as learning problems. And what are the commonalities do you see them as all interconnected? Are they fundamentally different domains that require different [/INST] approaches? Okay, that's a good question. Machine learning is a field with a lot of unity. A huge amount of unity. </s><s>[INST] What do you mean by unity? Like overlap of ideas [/INST] overlap of ideas, overlap of principles. In fact, there is only one or two or three principles which are very, very simple and then they apply in almost the same way in almost the same way to the different modalities to the different problems. And that's why today when someone writes a paper on improvement, optimization of deep learning envision it improves the different NLP applications and it improves the different reinforcement learning applications, reinforcement learning. So I would say that computer vision and NLP are very similar to each other today. They differ in that they have slightly different architectures, we use transformers in NLP and use convolutional neural networks envision, but it's also possible that one day this will change, everything will be unified with a single architecture because if you go back a few years ago in natural language processing, there were a huge number of architecture for every different tiny problem had its own architecture today there's just one transformer for all those different tasks and if you go back in time even more you had even more and more fragmentation and every little problem in ai had its own little sub specialization and sub little set of collection of skills, people who would know how to engineer the features. Now it's all been subsumed by deplaning, we have this unification and so I expect vision to become unified with natural language as well or rather I didn't expect, I think it's possible. I don't want to be too sure because I think on the commercial, you know that is very competition. The efficient a rail is different. A real doesn't require slightly different techniques because you really do need to take action. You really do need to do something about exploration, your variance is much higher. But I think there's a lot of unity even there and I would expect for example that at some point there will be some broader unification between RL and supervised learning where somehow they are l will be making decisions to make the super fast, don't even go better and it will be I imagine one big black box and you just throw you know, you shovel shovel things into it and it just figures out what to do with it, whatever you shovel at it. </s><s>[INST] I mean reinforcement learning has some aspects of language and vision combined almost there's elements of a long term memory that you should be utilizing and there's elements of a really rich sensory space. So it seems like the It's like the Union of the two or something like that, [/INST] I'd say something slightly differently. I'd say that reinforcement learning is neither, but it naturally interfaces and integrates with the two of them. </s><s>[INST] You think action is fundamentally different. So yeah, what is interesting about what is unique about policy of learning to act [/INST] Also, one example, for instance is that when you learn to act your fundamentally in a non stationary world because as your actions change the things you see, start changing you you experience the world in a different way and this is not the case for the more traditional static problem, you have some distribution and just to play a model to that distribution. Mhm. </s><s>[INST] You think it's a fundamentally different problem or is it just a more difficult generally it's a generalization of the problem of understanding. [/INST] I mean it's it's it's a question of definitions, almost there is a huge um you know, there's a huge amount of commonality for sure. You take gradients, you try, you take gradients, we try to approximate gradients in both cases and some in the case of reinforcement learning, you have some tools to reduce the variance of the gradients, you do that, there's lots of commonalities, the same neural net in both cases you compute the gradients, you apply adam in both cases, so I mean there's lots in common for sure, but there are some small differences which are not completely insignificant, it's really just a matter of your your point of view, what frame of reference, how much do you want to zoom in or out as you look at these problems, </s>
<s>[INST] I believe the editors used to have much more [/INST] power and he was a young man whose name was Tate and he ended up being editor for years. But uh so he sent this for review to uh a theoretical physicist named Robertson who was also in this field of general relativity, who happened to be on sabbatical at that moment at caltech. Otherwise his institution was Princeton where I sign was and he saw that the way they set up the problem, the infinities were like I make it as a student because if you don't set it up bright and general relativity you get these infinities. And so he reviewed the article and told gave an illustration that if they set it up in what are called cylindrical coordinates, these infinities went away. He's uh Editor of Physical Review was obviously intimidated by Einstein. He wrote this really not a letter back, like I would get saying, you know, you're screwed up in your paper instead it was kind of uh what do you think of the comments of our referee Einstein wrote back, it's a well documented letter wrote back a letter to physical review saying uh I didn't send you the paper to to send it to one of your so called experts. I sentence you to publish, I know I withdraw the paper uh and he never published again in the in that journal, that was 1936. Instead he rewrote it with the fixes that were made, changed the title and published it in what was called the franklin Review, which is the franklin Institute in philadelphia, which is Benjamin franklin Institute, which doesn't have a journal now, but did at that time. So the article is published, it's the last time he ever wrote about it, it remained controversial. So it wasn't until Close to 1960, where there was a conference which brought that brought together the experts in general relativity to try to sort out whether there was um whether it was true that there were gravitational waves or not. And there was a very nice derivation by a british theorists from the heart of the theory that gets gravitational waves. Uh And that was number one, the second thing that happened at that meeting is Richard Feynman was there and Feinman said, well if there's a typical Feinman, if there's gravitational waves, they need to be able to do something otherwise they don't exist. So they have to be able to transfer energy. So he made a idea of a good Duncan experiment, that is just a bar with a couple of rings on it and then if a gravitational wave goes through it distorts the bar. Uh and that creates friction on these little rings and that's heat and that's energy. So that that meant, </s><s>[INST] is that a good idea? That sounds like a good idea. [/INST] Yeah. It means that he showed that with the distortion of space time, you could transfer energy just by this little idea. And it was shown theoretically. So at that point it was uh huh believe theoretically than by people that gravitational waves should exist. </s><s>[INST] No, we should be able to detect that [/INST] means we should be able to detect them except except that they're very, very small. </s><s>[INST] Just so what kind of uh there's a bunch of questions about what kind of events would generate gravitational waves? [/INST] You have to have. This, what I call quadruple moment that comes about. If I have uh for for example, to objects that go around each other like this, like the Earth, the Earth around the sun, or the moon around the Earth. Or in our case it turns out to be two black holes going around each other like this. </s><s>[INST] How is that different than basic oscillation? Back and forth. This is just more common in nature. [/INST] Oscillation is a dipole moment. </s><s>[INST] It has been three dimensional space kind of [/INST] So you have to have something that's three dimensional, that'll give what I call the quadruple moment that's just built into this </s><s>[INST] and luckily nature you have stuff uh [/INST] and luckily things exist and it is luckily because the effect is so small that you could say look I can take a bar bell and and spin it right and detected gravitational waves. But unfortunately no matter how much I spend it, how fast I spent it it's so I know how to make gravitational waves but they're so weak. I can't detect them. So we have to take something that's stronger than I can make otherwise. We would do what hurts did for electromagnetic waves? Go in our lab, take a bar bell, put it on something spinning </s><s>[INST] casket. Don't question. So a single object that's weirdly shaped. Does that generate gravitational waves? So if it's if it's rotating [/INST] sure it was just much weaker so it it's weaker. Well we didn't know what the strongest signal would be that we would see, we targeted seeing something called nutrients stars actually because black holes we don't know very much about it turned out were a little bit lucky there was a stronger source which was the black holes. </s><s>[INST] Well, another ridiculous question. So you say waves, what does what does the wave mean? Like uh the most ridiculous version of that question is what does it feel like to ride a wave as you get closer to the source or experience it. [/INST] Well if you experience a wave, imagine that this is what happens to you. I don't know what you mean about getting close. It comes to you. So it's like it's like uh this lightweight for something that comes through you. So when the light is you makes your eyes detective. I flashed it. What does this do is it's like going to the amusement park and they have these mirrors, you look in this mirror and you look short and fat and the one next to you makes your tall and thin. Okay. Imagine that you went back and forth between those two mirrors once a second that would be a gravitational wave with a period of once a second. Uh if you did it 60 times a second, go back and forth. And and then that's all that happens. It makes you taller and shorter and fatter back and forth as it goes through you at the frequency of the gravitational wave. So the frequencies that we detect are higher than one a second. But that's the idea. But and this amount is small </s>
<s>[INST] in that context of these world experts. The problem seems to be that reporting mechanism where there's a disproportionate power to a complaint of a young student, a complaint that an idea is painful or an idea is disrespectful to, you know, or ideas creating an unsafe space. And the conclusion of that, I mean I'm not sure what to do with that because it's a single reporting maybe a couple, but that has more power then the idea itself. And that's strange. I don't know how to fix that in the administration except to fire everybody. So like this is to push back against this storyline that academia, some are fundamentally broken. I think we have to separate a lot of things out. Like one is you have to look at faculty and you have to look at the administration and like at MIT for example, the administration uh does tries to do well, but they're the ones that often lack courage. They're often the ones who are the source of the problem when people criticize academia and I'll just speak to my myself, you know, I am willing to take heat for this is they really are criticizing the administration, not the faculty because the faculty oftentimes are the most brilliant. The Boulder thinkers that you think whenever you talk about, we need like the truth to be spoken, the faculty are often the ones who are in the possession of the deepest truths in their mind and in that sense. And they also have the capacity to truly educate in the way that you're, you're saying and so it's not broken, like fundamentally, but there's stuff that like needs that's not working that well and [/INST] you kind of took my words, that's what, that's what I thought, you're gonna ask me if I think the ivy League is broken and that's totally that's exactly it. </s><s>[INST] So you don't think so on the question, do you think that I really just broken? Like what, how do you think about it? The academia in general, I suppose. But I believe still, I think it represents some of the best qualities of academia. [/INST] What more is there to say there? I think the ivy League is producing tremendous thinkers to this day. I think the culture has a lot that can be improved, but I have a lot of faith in the people who are in these institutions. I think like you said, the administration and I have to be a little careful because um you know, I've been in some of these committees, um and I have talked to administration about these sorts of things. Um I think they have a lot of stakeholders and unfortunately it makes it difficult for them to always serve these brilliant faculty and the students in the way that they would probably like to. </s><s>[INST] Yeah, okay, so this is me speaking, right, The administration, I know the people and they're often times of faculty holding positions in these committees, right? But it's in in the role of quote unquote service. They they're trying to do well, they're trying to do good, but I think you could say it's the mechanism is not working, but I could also say my personal opinion is uh they lack courage and one courage and to grace when they walk through the fire. So courage is stepping into the fire and grace when you walk through the fire is like maintaining that like, like as opposed to being rude and insensitive to the lived quote unquote experience of others or like, you know, just not eloquent at all. Like as you step in and take the courageous step of talking, saying the difficult thing, doing it well, like doing it skillfully. So both of those are important, the courage and the skill to communicate difficult ideas and they often lack them because they weren't trained for it, I think. So you can blame the mechanisms that don't, that allow 1920 year old students to have more power than the entire faculty or you could just say that the faculty need to step up and grow some guts, and and skill of graceful [/INST] communication really. Administration. </s><s>[INST] Well, yeah, and the administration, that's right, that's the administration. [/INST] The faculty are sometimes some of the most brave outspoken people within the balance of their career. </s><s>[INST] So, uh, so that that takes, uh, that's like the founding kind of spark of a fire that uh led you to them say, okay, so how can I help? [/INST] Yeah. And I explored a lot, I explored a lot of options. I wrote many articles to my friends, talk to them and I realized it sort of need to be a cultural change. You need to be bottom up grassroots, um, something I knew the energy was there because you just look at the most recent institutional assessment from you all. This was basically the number one thing that students, faculty and alumni all pointed to. The administration was cultivating more conversations on campus and more difficult conversations on campus. So the people on campus know it. Um, And you look at the Gallup poll, 61% of students are on Ivy League campuses afraid to speak their minds because of the campus culture. Um, the campus culture is causing a sort of freezing effect on discourse. Can </s><s>[INST] you pause on that again? So what percentage your students feel afraid to speak their mind? [/INST] 61% nationally. And you're talking about places nothing like the ivy League, where I'd say, I'd imagine it would be even worse because of just the way that these communities kind of come about in the sorts of people who are attracted or are invited to these sorts of communities. Um, that's nationwide that college students and it's going up that college students are afraid to say what they believe because of their campus climate. So it's a majority. It's not, it's not a conservative thing, it's not a liberal thing, It's a group thing, we're all feeling it, the majority of us are feeling. And </s>
<s>[INST] you're almost making an argument against uh earlier statement, you've made your convincing me at first you said there's no way a computer could raise a child essentially. But now you've described making me think of it, if you have that kind of idea meritocracy, you have this rigorous approach to Bridgewater takes an investment and apply to raising a child. It feels like through the process you just described, we could as a society, arrive at a set of principles for raising a child and encoded into a computer. [/INST] That originality will not come from machine learning the first </s><s>[INST] time you do so that the original Yes, that's [/INST] what I'm referring to. </s><s>[INST] But eventually, as we could together develop it and then we can automate it. [/INST] That's why I'm saying the processing can be done by the computer. So we're saying the same thing. We're not inconsistent. We're saying the same thing that the processing of that information in those algorithms can be done by the computer in a very, very effective way. You don't need to sit there and process and try to weigh all those things in your equation and all those things. But that notion of okay, how do I get at that principle? </s><s>[INST] And you're saying you'd be surprised uh how much [/INST] you can express? That's right. You can do that. So this is where uh I think you're going to see the future. And right now we, you know, go to our devices and we get information to a large extent and then we get some guidance. We have our GPS and the like in my opinion. Principles. Principles. Principles. Principles. I want to emphasize that you write them down. You've got those principles, they will be converted into algorithms for decision making. And they're going to also have the benefit of collective decision making because right now individuals based on what's stuck in their heads are making their decisions in very ignorant ways. They're not the best decision makers. They're not the best criteria and their operating when those principles are written down and converted into algorithms, it's almost like you look at that and follow the instructions and it'll give you better results. Medic medicine will be much more like this. You can go to your local doctor and you could ask his point of view and whatever and he's rushed and he may not be the best doctor around and you're going to go to this thing and get that same information or just automatically have an input in that and it's going to tell you okay here's what you should go do and it's going to be much better than your local doctor and that the converting of information into intelligence. Okay. Intelligence Is the thing we're coming out with um again I'm 70 and I want to pass all these things along so um all these tools that I've found the need to develop all over these periods of time, all those things I want to make them available and what's gonna happen as you there, they're going to see this. They're going to see these tools operating much more that way? The idea of converting data into intelligence Intelligence for example on what they are like what are your strengths and weaknesses? Intelligence on who do I work well with under what circumstances? Intelligence. We're going to go from what are called systems of record which are a lot of okay information organized in the right way to intelligence. And we're gonna that that'll be the next big move in my opinion. And so you will get intelligence back </s><s>[INST] And that that intelligence comes from reducing things down two principles into [/INST] that's how it happens. </s><s>[INST] So what's your intuition if you look at the future societies do you think well be able to reduce a lot of the The details of our lives down two principles that would be further and further automated? [/INST] I think the real question hinges on people's emotional emotions and irrational behaviors. I think that there's subliminal things that we want. Okay and then there's cerebral, you know, conscious logic and the too often are at odds. So there's almost like to use in you, right? And so let's say what do you want? Um your mind will answer one thing, your emotions will answer something else. So when I think about it I think emotions are I want inspiration, I want, love is a good thing, being able to have a good impact, but it is in the reconciliation of your subliminal wants and your intellectual wants so that you really say they're aligned and so to do that in a way to get what you want. So irrationality is a bad thing if if it means that it doesn't make sense in getting you what you want, but you better decide what you you're satisfying is at the lower level you emotional subliminal one or is it the other. But if you can align them. So what I find is that by going from my you experience the decision, do this thing subliminally and that's the thing I want, it comes to the surface, I find that if I can align that with what my logical me wants and do the double double check between them and I get the same sort of thing that that helps me a lot I find for example meditation is one of the things that helps to achieve that alignment? It's fantastic for achieving that alignment. And often then I also want to not just do it in my head. I want to say does that make sense? Help you. So I do it with other people and I say, okay well let's say I want this thing and whatever does that make sense? And when you do that kind of triangulation, your to use and you do that with also the other way, then you certainly want to be rational, right? But rationality has to be defined by those things </s>
<s>[INST] by almost all of his opponents. It's nice to see Gordon looking small relative to his opponents, which is absurd to say, but it is the open division, plus 99 kilos. It was plus 99 kilos. Right, that's what I mean, sorry, by open plus 99 kilos. [/INST] Everyone looks like the Incredible Hulk. Yeah, Hulk, yeah. So our big thing is when we fight bigger, stronger opponents, we always go in two directions. You either go for the legs or you go </s><s>[INST] for the back. And so we constructed strategies based around those two methods. So going for submissions, and we should also mention that ADCC rule set is for regular matches, I think it's five minutes and five minutes. Total is 10 minutes, and then for finals matches, it's 20 minutes, and half the time is spent with no points. [/INST] So these can be very, very long matches. I mean, to put this in a perspective, a modern judo match is five minutes. Yeah. A modern wrestling match, I believe, is six minutes in international freestyle. So these matches can be 40 minutes long. Now, that's a long, long grappling match. </s><s>[INST] Depending on how you compete in it, that can have a huge toll on you. [/INST] Absolutely. You can get to the finals and just be absolutely spent. So our whole thing is, okay, Gordon's got to not only get to the finals, then he's got to fight the toughest ADCC rapper of all time after that. So we were looking for quick and energy efficient matches, and that meant going to the back or going to the legs. And in the overwhelming majority of cases, that's exactly what he did. He was able to get some very, very quick matches, courtesy of leg lock finishes. And in the few cases where he didn't finish on legs, then he would simply take his opponents back. And that's a very low stress position to occupy. In one case, his opponent deliberately kept his back on the ground to prevent the backtake, and he just chose mounted position instead. And so he was able to go through his weight division with an extremely low energy expenditure, which set him up well to go into the finals. No injuries, very little energy expenditure. Now, it sounds easy to say that, okay, the strategy worked. But in order to get that strategy to work, you have to have one hell of a set of skills. And we can see those now. Would </s><s>[INST] you like to? Yeah, I would love to go through them. And I should also mention, for people just listening to this, I'll try to commentate on different things we'll look at. But the thing that was made clear is, maybe you can speak to that. Maybe to you, it looks like efficiency. But to me, it looked like Gordon was not even trying. There was a relaxed aspect to the whole thing. So maybe it had to do with saving energy, but he made it look very easy. And he made the path of submission look very easy. So here, the first match against an opponent [/INST] that, again, looks bigger than him. Okay, I'll just give an initial comment here. First, you'll see that Gordon elected to sit to the bottom position. The hardest work in submission grappling is when two athletes take the standing position and joust for takedowns. That's where most of the energy gets burned up. So working on the idea of energy efficiency, let's go out and we chose to sit into guard position and then start looking to access our opponent's back. Because if our opponent's head position of far side arm drag makes a lot of sense, Gordon's able to beat the arm and quickly get behind his opponent. Now the question is going to be getting into a scoring position. It's too early to score at this point, but we're just concerned at this stage of just </s><s>[INST] energy expenditure and make the other guy work harder than us. So Gordon did the arm drag to [/INST] the back and now is working on the hooks. The hooks are not particularly important here. He'll use it just to get stability on his opponent. But interestingly, his opponent here had an interesting strategy too, which was to occupy bottom turtle position and look to get to the critical five-minute demarcation point where points begin to get scored. His idea, I believe, I'm speculating here based on his actions, was to keep Gordon at bay in a defensive turtle position until a five-minute mark occurred, in which case he would shake Gordon off, walk away and force a </s><s>[INST] takedown battle. How many people are comfortable in that? And what do you think about the defense [/INST] of turtle position versus always trying to come back to guard? Turtle position is the second bottom position of you did. Many people only associate guard position with bottom position and you did that. That's naive. There's two. There's guard position and turtle position. Now as a general rule, guard position offers a much, much greater variety of attacking options than turtle position does. But that's not to say turtle position absolutely can be an effective bottom position. You can work effectively from there. </s><s>[INST] So there's some case to be made that to wait out five minutes, turtle might be. [/INST] I mean, I personally think it against Gordon Ryan, I mean, I admire the fellow's courage. It's not easy. But there was a logic to what he was doing. People think, oh, he just got his back taken so easily. But he did have a strategy. Now, did he pick the right person to use that strategy against? Probably not. </s><s>[INST] So Gordon is able to break the turtle down, get one hook in. At which point is this becoming an extremely controlling position with Gordon in the back? [/INST] At which point is there, are you happy with where it is? At this point, it just started to dawn on me at this point, this guy actually had a strategy, which was to maintain a prone position that he's in now, and then shake Gordon off after the five minute mark. So once that became obvious, and I was now excited to look at the clock and how close we are, if we can take it up to five minutes. Right now, this guy's only intention is to stop Gordon from strangling him and finish. Okay, now the guy's trying to go up and vertical freeze it there. Now, do you see how he's taking his elbows off the mat in turtle position? In juditsu, there's only one reason you take your elbows off the mat from turtle position. That's to stand up. So now it's clear at this point what his actual strategy is. It's to get up, force a standing confrontation, win a takedown battle, and beat Gordon by points. So he did have a strategy. Now, our counter strategy is always based around the power half Nelson. This is a common move in the sport of wrestling, and it's a great way to break people down as they try to stand up. That looks so heavy. Yeah, I mean, Gordon is a master of it. So there's a power half </s>
<s>[INST] Let me ask perhaps a strange question. But you know, proponents of Bitcoin will say things like Bitcoin fixes everything. So why do we need a theory? Um, versus like Bitcoin plus Lightning network for scalability and then using Bitcoin for with this beautiful work for security. So in this kind of it is perhaps sort of a strange question, but it's a high level question, why do we need another technology? Yes, there's a bunch of nice features, but like doesn't Bitcoin fix everything already. [/INST] So in the thing that I always attracted me about Bitcoin is, you know, these values of decentralization creating these open provisional systems that anyone can participate in and that aren't just going to flop over and die if whoever created them gets bored and like, you know that our resistance to like whoever runs them breaking the rules and all of these things, right? And I think that pretty strongly that these principles are really valid and importance too much more things than just money, right? Like Bitcoin is the Blockchain for money and ethereum is built from the star decision a general purpose Blockchain, right? It's, you know, there is either the asset on ethereum, but then you can also make, you know, decentralized financial things, what what we call defy today. Um you know, you can make like DNS the decentralized domain name system um you can put make prediction markets on it. You can make totally non financial systems that just like keep track of whether or not some certificate was signed or whether or not some like cryptographic key got revoked. There is this big long list of like just interesting things that you could use about block chains to do right? Like basically they are sort of the missing piece that we are without them. The kinds of things that are decentralized computer network can do is we are limited and once you have them, you know, a lot of those invitations end up going away. Uh and yeah, so ethereum was like always from the beginning about that right. It's about like, hey, this isn't just money, there's just, there's so much more that you could do if you could just go ahead and make any infrastructure or you know, digital institution or tao or whatever you want to call it, where you, the kind of the base layer of the logic is just executed in this open and transparent way where everyone can see what's going on or you know, if you like your zero knowledge proofs at least everyone can see proofs that prove to you that what's going on follows the rules. Um and you know, you don't need to just constantly keep trusting centralized actors and </s><s>[INST] hence the smart contracts exactly as being a sort of a core technology as part of the theory. Um [/INST] Yes, exactly. Smart contracts, the computer programs that are running on ethereum? They are like the core of what makes ethereum general purpose. Um, so I think like I do think that, you know, there's a lot more than wrong with the world than just money, right? Like I'm not one of these people who thinks that, you know, if you get rid of fiat currency and you replace it with Cryptocurrency and then suddenly wars are going to go away, right? Because like, first of all, um, you know, like senior raj revenue is only a small portion of government revenue, right? It's like, what? 5 10% something like that. Second of all, if you are the sort of um this is one of the things I don't even get about their philosophy, like, let's say you're the sort of person who is a like an extreme and very distrusting libertarian and you think that these governments are terrible, right? Like we we know today the government's funds a combination of, you know, things like welfare and things like, you know, the military that, you know, goes in like bombs people in Afghanistan. Right? And so the question you have to ask is like, okay, you with your new, you know, magic newfangled cyber currency that takes over the world, Take away the government's ability to have senior as revenue. And so you reduce the government's revenue by 10 If the government, is that evil, which portion of its expenses, is it going to take that 10% from, is it going to stop the bombing people in Afghanistan? Or is it going to cut welfare if you think it's the first, you have a very optimistic view of the government. So that's, I guess my perspective on like why the whole, you know, we're going to save the world and create and create peace by like denying governments the right to stealth taxation kind of perspective doesn't really make much sense for me. And I do think that there is real value that comes from a decentralized and open currency. Like just the fact that there is a financial infrastructure that anyone in the world can, you know, go ahead and years right? Like it's uh, that's something that can usually be a big boon for people, right? There is a lot of places where the currency and is much less stable than the dollar. And you know, these people like, they don't like, well if they use Bitcoin, their only option is to get Bitcoins right, which, you know, are also pretty volatile. Um, if they use the theory, um, then, you know, they can get either, but then they can also get stable coins right? And you might think that, you know, you're not being ideologically pure and now you're giving them stable coins, which are mirroring dollars and obviously dollars are gonna collapse too. But the reality is that delivers are vastly more stable than the Venezuelan bolivar. Uh So like there are really meaningful and beneficial things that you can give to people by having a global and open financial system but I think if you want to actually do that like you have to have much more than just a currency right? And then if you want to go beyond financial things then you know we have to obviously Have much more than a currency and then you know you also have to actually take scalability seriously because the non financial applications like nobody's gonna pay $5 a transaction for them. </s>
<s>[INST] I think there's no better place to end it. Michael, thank you so much as an honor to meet you. Thanks for talking. Thank you. It's a pleasure. Thanks for listening to this conversation with Michael stevens and thank you to our presenting sponsor cash app, download it. Use code lex podcast. You'll get $10.10 dollars will go to first, a stem education non profit that inspires hundreds of thousands of young minds to learn to dream of engineering our future. If you enjoy this podcast, subscribe on Youtube, give it five stars on apple podcast, support on Patreon or connect with me on twitter and now let me leave you with some words of wisdom from Albert Einstein. The important thing is not to stop questioning curiosity has its own reason for existence. One cannot help but be in awe when he contemplates the mysteries of eternity, of life, the marvel structure of reality. It is enough if one tries merely to comprehend a little of this mystery every day, thank you for listening and hope to see you next time. [/INST] </s>
<s>[INST] So uh, john do you ever use this in one way or the other by saying, I don't think you can do this to motivate them to prove to prove you wrong? Or more general question of, you know, the mental toughness required to achieve or confidence required to achieve greatness? Like what's your role as a coach when you have these two athletes with regards to your first question, would I ever say to someone you can't do this as a kind of reverse psychology. I know um my job is to prepare people first and foremost with their skills and as Gordon pointed out earlier, if you're in any way, a rational human being and you're noticing that you're getting tremendous success with a given move in the gym against high level opponents who give a good read on what your actual opponent and the competition is like, you would have to be a moron too, not recognize that kind of success and say this is something I should be building into my game and you will carry the confidence that you earned in the gym into the arena. So I never tried to use reverse psychology, I build up ah everything I do in terms of confidence is to give people physical skills. I know people say, oh there's physicality, on the one hand, there's mentality on the other and confidence is squarely in the mental aspect of the game. But all the underpinnings and beginnings of confidence are physical, okay. A rational human being will see where they're having success and where they're having failure and confidence will surround those areas, where they're having success and will degenerate in cases where they're, they're having a failure. So my job as a coach is to set them up for success in the gym with a given set of skills and I don't have to do anything psychologically after that, I just, If I can set you up to be highly successful with a given move or a set of tactics 10 times in a row against quality opposition in the gym, I don't have to do a damn thing when it comes to instilling confidence, I will tell people, hey, you're doing a really good job with that move. It's working well for you. But when they nod in agreement, I'm not trying to force anything on them. They're recognized. They recognize that long before the words came out of my mouth. But on the other hand, intelligent, rational people will recognize when they're failing with given moves and no amount of talk on my part can ever change that. If I teach Gordon? Give an arm lock and 15 times in a row he tries it over a month and all 15 of failures, there's nothing I can say verbally to come out the door and say, hey, you're really good at that move. He's going to look at me and say bullshit and I'm terrible at it and that will create a crisis of confidence where Gordon? No longer believes the words coming out of my mouth, So I will never compromise that. But isn't there a lot? You just said 15, you have to believe that uh, doing this arm lock 15 times over a period of a month is worth it because eventually you might get it like, yeah, that's a separate issue. That, that's a separate issue that um, there are times where I've more or less pushed athletes to go in a certain direction. For example, um, when I first met Gary tonin, he never had a guillotine strangle and I would say to him, Gary, you know, you're a scrambler. Like one of the greatest weapons are scrambling and ever developed as a guillotine. Like it should be in your arsenal. And he was like, no, I just scrambled for the back. And they said, well there's gonna be a day you can't take someone's back and it's always good to go to strangle from front and back. Okay. Of course we all prefer strangled from the back. That makes sense. But there's gonna come a day where it's going to be useful for you. And so that was one of the few times where I put my foot down and said, you're learning this, shut the funk up. And um, uh, [/INST] like literally wouldn't teach him any anything else until he got a guillotine. Gary like asked him a question, he's like, let's say your </s>
<s>[INST] what ego looks like by the [/INST] way, I can prove it to, you </s><s>[INST] know, I know, but you don't have to rub it in. [/INST] Well they have a big budget. I don't, so if I can put it together, they should be able to. So I can only imagine that a scientist who studied, you know, the spiders that look like ants like at a certain like, oh, and this species does this with the gender dim or fizz. Um, their friends are only going to care so much. So if you meet someone who has a lot of money who now cares about ants, spiders, it's going to be </s><s>[INST] exciting. It will be very exciting. But I just wanted to push back on the, I think the act itself should be the biggest reward. I think you're always safe. We're talking about goodness being a safe default. I think it's a good default for, for plants and for writing it for science is to just enjoy the act even if nobody cares. [/INST] Okay, this is where this. Okay, now I'm, even now I'm wondering why I'm pushing back so hard and I realized what it was because I've made this point several times and I'm glad I can make it again. There's this window of time that happened in my life and I know it happens to a lot of people when you're in, you're like 24-27, right? So 21-24, like you still have your friends from college so on and so forth, right? But then it's kind of like a poker game and you know, every so often people cash out there, like I'm out, I'm out, they get married, they get a job, they move. And if you are someone who is a young, ambitious creative, that window is a very rough one because you're doing the right thing right? And you're not being, you know, drug addict, you're not being a philanderer, not that those things are wrong, but just like you're playing by the rules, you're creating your stuff what you want to be known for, contribution wanna make for the world and no one cares and it gets very lonely and there is this very emotional disconnect about how is it that I'm creating and I'm working hard and I'm making something happen. And it's just radio silence so that I don't think it's that easy when you're, you're, you're the scientist, not me. When you don't have any kind of external validation, humans only have so much fuel, </s><s>[INST] nothing worth having is easy. Michael, by the way yesterday talked on the phone with a person who said, he was deeply moved the first time you mentioned This age group of 24-27, he's like, he he's 26, he said, and uh, he feels the full responsibility of that in the excitement. So he left his like, um, corporate type of job to pursue something that he's really passionate about and that, that, that was like you were an inspiration to him, which I was deeply saddened by that. I [/INST] also inspired Michael Alex. </s><s>[INST] The the the amount of mass murder um those that were inspired by you will eventually lead to is is truly horrifying what we're talking about. So Jeffrey Epstein, so one thing I wanted to ask you, so let's put scientists aside. What about like uh World leaders, Bill Clinton, your favorite person? Why would he fly with Jeffrey Epstein? Why would he interact with that guy? [/INST] I mean don't you think that that's kind of the deal that I'm the president and I get big and powerful people flying around their jets and that's a symbiotic relationship. </s><s>[INST] Yeah, but don't you also have a good Bs detector like that, don't you have a good detector for people who just want to be in your presence? Like I already understand that there's people like this out there, like there's people that kinda when he used me for stuff and [/INST] you mean tim Dillon, </s><s>[INST] Tim Dillon? Um I love that guy you guys met, [/INST] we haven't met yet here, We haven't met, we met before in new york but we have not since I moved here. </s><s>[INST] Yeah, so you should be able to detect that those there's those people and there's the people that have kindness in their hearts, even if they can benefit from the interaction with you, but they have like they're good human beings, I feel like you want to, you run into a lot of trouble if you surround yourself or have any people that are manipulative. But [/INST] I think like that bad example because like let's look at clinton and let's look at Obama right? So Obama, even though their politics are very close and say in many ways Obama is apparent. We don't know, I don't know either of them. But to me it seems very apparent that he's very similar behind closed doors in front of camera. Yeah, he's he's Barack to me. Yeah, he's </s><s>[INST] good. [/INST] Clinton seems very clearly to be much more of a performer. He's in front of the cameras, he puts on a roll. But behind the cameras, he's very much has a temper. He's known for that. He's much more of a ledge. Um </s><s>[INST] Was that was perfect. Oh, lech with an E. Oh, cool. Lech. Is that like, that's a cool term. So I can use that on the internet. Like you're a ledge. Yeah, you can [/INST] use the internet, your dirty lunch. Well it's dirty is implied. Um </s><s>[INST] So it's okay, so being redundant. Um but it just feels like he needs an adjective to give it more power and I'm sorry, so clinton is a [/INST] ledge, right? So you can see how there's people who want to meet, you know the surface Bill clinton and I'm sure that gets old for him because he has to be on, but then there's the good old boys where he could be a pervert and this guy's like, yeah, I know what it's like and then he could, feels like he's himself. But I'm also, we're all speculating, I mean, I don't know what Bill Clinton is, like, what was in it for him? He certainly had, could afford private jets if he wanted to. There's no shortage of people who want to fly around the world to give speeches, you know, that, you know, </s>
<s>[INST] where you're called to do something else, so. What did it feel like to be a Muslim in a situation like that? Was there, were you a human being? [/INST] Were you a religious practitioner? I don't see, I can't separate anything about myself in that situation, right? So when I had to pray, I had to pray to help people out, to give people words of comfort, to try to appeal to the senses of whoever I could at the time. I didn't see myself as like a guy trying to, trying to show a particular part of Islam in there. I just saw myself as someone that was trying to help a family get their husband and father back, right? And so it was more of just like that part of me was there. You know, you can kind of see yourself, right? And this is the irony of it. When Christchurch New Zealand happened, that was kind of our worst nightmare as Texas Muslims because we've had armed groups in front of our mosques threatening to do what that man did in Christchurch. And so when you see a wife and kids wondering if they're gonna get their dad back, you kind of see yourself there. And so I just saw myself in that situation. What would I want people to be doing for me in that moment? What would I want people to be telling my family in that moment? So that's really where I went to. And that's really where I dug into. And I prayed a lot that day. A lot, a lot for the right words, </s><s>[INST] for the right actions, what I could do to just help. What are the lessons now a year later [/INST] that you take away from that day and the days? So many lessons just, don't be indifferent. Don't be indifferent to the suffering around you or even that's distant from you because it's somehow related to you. </s><s>[INST] So just don't be indifferent. So you're proud that you stepped up and you went there [/INST] and then- Yeah. Look, I don't think I did much. I'm being really honest. This is not me trying to be humble here. I don't think I did much. I think I did what I was called to do. I wish that it never happened, right, as a whole. but I'm glad that the relationships that have been built over time came into being in that day. When we could call upon people that we knew call upon each other and as a community really come together. Dallas has been through a lot of pain, but we've come together through a lot of pain as well. So it's kind of one of those things where we're united in our pain. When you suffer together, you build certain bonds together. So Dallas has been through a lot as a community, but we've come together through a lot as a community. </s><s>[INST] Yeah, the thing about violence and war, it destroys, it caused so much suffering, but it also sort of brings out some of the best aspects of human nature and unites people. So it's an interesting way [/INST] how our human civilization functions. Well, that's the beauty that you don't just want to see, but you also want to be. You know, we're living in a climate where there's a lot of that, right? So how do you actually get through that and actually not allow yourself to succumb to that </s><s>[INST] and be another voice in that polarization? It seems that throughout history and still in the world today, religion has been a source of some of the, of a lot of polarization, a lot of conflict, even war. [/INST] Why do you think that is? Listen, I think at the essence of it is always some sort of political instability that leaves behind a brutalized population and vulnerabilities that can be exploited. As I said, in the 20th century, with the bloodiest century that we've had to date, where does religion fall on any of that? Where does religion fall on the Ixoms? Where does religion fall in the world wars? Where does religion fall? And in much of that, even when we talk about things like the Crusades, remove the Islamic framing, the Crusades. The Crusades, were they really about religion? The Mongols and the destruction of the Mongols. Was it about religion? Myanmar and the Rohingya today, is it about Buddhism? So I think that these are essentially political issues, political causes where you have people that rise up and that use religion to disguise things that are far, far, far from religion. And if you want to manipulate a religious scripture, you could turn any book, any scripture, into a violent scripture if you have a violent aim. So I think that that's where you find people manipulating versus manipulating religion to justify sick ideologies </s><s>[INST] that are based and thrive in political instability. So these are fundamentally political, [/INST] geopolitical conflicts, not religious conflicts. Absolutely, look, when you talk about a group like ISIS, Islam has been in Iraq for a very, very long time. Iraq has been bombed by now five consecutive presidents or four, it's been bombed into the stone ages. There is no political infrastructure. It's devastation and destruction and desperation as a result of that. Many of the old Saddam loyalists and Saddam's regime was a secularist regime, are now heads of ISIS, right? It just moved into that. When you create that type of chaos, you generate an environment where groups like ISIS are bound to rise out of. And so Islam did not cause this. People didn't wake up in Iraq one day and say, hey, let's create a group called ISIS because Islam tells us to, right? Iraq was bombed into this place. And we have to, not just free religion from the responsibility, from having to bear the responsibility of much of the hatred and violence, but we have to interrogate the political instability that was caused where we justified as Americans, these are taxpayer dollars, where we justified with what was done in Iraq. Do we even know what was done in Iraq and Afghanistan? These drones that drop using our tax dollars under Democratic and Republican regimes and kill thousands of innocent people in weddings in Yemen and Somalia. Are these justified? And when you think about dehumanization, can the average American name a single victim of the Iraq war? Is there a picture that comes to your mind? Is there a person? Absolutely not, because that's the dehumanization. Now, I often talk about Dr. Martin Luther King Jr., his progression as a faith leader in America, as a political leader in America. Dr. King was deeply unpopular when he took his stand on Vietnam. And he mentions how first he had to see Vietnam through the lens of the soldiers because many of the soldiers that were lost, American soldiers, right? And that was a crime that they were sent to fight a war that they should not have been sent to fight. And there was an injustice that was done towards them. He said, but things really changed when he started to see it from the other side of the bullet, when he started to see the world through Vietnam, through the Vietnamese child. And that's where he resorted to breaking the silence. That's where he changed his tune. Because we dehumanize our victims so much that they're not even relevant to our discourse until they become able villains to our story. And then now they're attacking us because they hate us. Now they're blowing us up because they hate us. Their religion tells them to do this to us. What have we allowed to be done to them using our tax dollars in our name, right? So I think that we have to interrogate the political chaos that was caused, not just free religion from the groups that were created, but what was done to those countries and what continues to be done in many of these places. </s>
<s>[INST] Yeah, I think that's an exciting. There's a whole giant, there's a giant hole that's unfilmable by humans is asking too much of your people, your friends and people, you're in a relationship within your family to fill that hole because, you know, it's exploring the full like, you know, exploring the full complexity and richness of who you are, like who are you really like people, your family doesn't have enough patients to really sit there and listen to who are you really? And I feel like there's an opportunity to really make that connection with robots. [/INST] I just feel like we're complex as humans and were capable of lots of different types of relationships. So whether that's, you know, with family members, with friends with our pets or with robots, I feel like there's space for all of that and all of that can provide value in a different way. </s><s>[INST] Yeah, absolutely. So I'm jumping around currently, most of my work is in autonomous vehicles. So the most popular topic among general public is um, the trolley problem. So most, most, most of the bodies just uh kind of hate this question. But what do you think of this thought experiment? What do you think we can learn from it outside of the silliness of the actual application of it to the autonomous vehicle? I think it's still an interesting ethical question and that in itself, just like much of the interaction with robots has something to teach us. But from your perspective, do you think there's anything there? [/INST] Well, I think you're right that it does have something to teach us because but I think what people are forgetting in all of these conversations is the origins of the trolley problem and what it was meant to show us, which is that there is no right answer and that sometimes our moral intuition that comes to us instinctively is not actually what we should follow. Um, if we care about creating systematic rules that apply to everyone. So I think that as a philosophical concept, it could teach us at least that. Um, but that's not how people are using it right now. Like we have and these are friends of mine and like I love them dearly and their project as a lot of value. But if we're viewing the moral machine project as what we can learn from the trolley problems, the moral machine is, I'm sure you're familiar. It's this website that you can go to and it gives you different scenarios like, oh, you're in a car, you can decide to run over, you know, these two people or this child, you know, what do you choose? You choose the homeless person, you choose the person who's jaywalking. And so it pits these like moral choices against each other and then tries to crowdsource the quote unquote, correct answer, which is really interesting. And I think valuable data, but I don't think that's what we should base our rules in autonomous vehicles on because it is exactly what the trolley problem is trying to show, Which is your first instinct might not be the correct one. If you look at rules that then have to apply to everyone and everything. </s><s>[INST] So how do we encode these ethical choices in interaction with robots? So, for example, autonomous vehicles, There is a serious ethical question of, do I protect myself? Does my life have higher priority than the life of another human being? Because that changes certain control decisions that you make? So if your life matters more than other human beings, then you'd be more likely to swerve out of your current lane. So currently automated emergency braking systems that just break, uh they don't ever swerve. [/INST] So </s><s>[INST] swerving into oncoming traffic or or no, just in a different lane can cause significant harm to others, but it's possible that it causes less harm to you? So that's a difficult ethical question. Do you do you do you do you have a hope that like the trolley problem is not supposed to have a right answer? Right. Do you hope that when we have robots at the table will be able to discover the right answer for some of these questions? [/INST] Well, what's happening right now, I think is this this question that we're facing of what ethical rules should we be programming into the machines is revealing to us that our ethical rules are much less programmable than we, you know, probably thought before. And so that's a really valuable insight. I think that these issues are very complicated and that in in a lot of these cases it's you can't really make that call, like not even as a legislator. And so what's going to happen in reality I think is that, you know, car manufacturers are just going to try and avoid the problem and avoid liability in any way possible or like they're gonna always protect the driver because who's going to buy a car if it's, you know, program to kill someone, kill, kill you instead of someone else. Um, so that's what's going to happen in reality? But what did you mean by like once we have robots at the table, like do you mean when they can help us figure out what to do? </s><s>[INST] I mean when robots are part of the ethical decisions. So No, no, no, not not. They help us? Well, uh [/INST] oh you mean when, when it's like, should I run over a robot or a person? </s>
<s>[INST] So the adventure, I mean it was one heck of an adventure for the two of you, For the both of you. Were you able to enjoy or was it always danger? Was what was was it always something that threatened your relationship, your love, your family? Are we able to enjoy the adventure of it? You know? We all die. Life is short and to live that kind of adventure? [/INST] Well, whenever I did the first loot I got $10,000 and that was just about, that was just about two years pay on the fire department, take home. And I brought that home and I put my hand over my mouth. I said roger, I can't believe this. Oh my what in the world? And the doctor said let's go have dinner. And so we went to the restaurant that we would normally we would go to, you know, and and don't you dare look on the right hand side of the, of the menu, he's just order anything you want. And it was just as we were in the restaurant, you know, it was just we were giddy about it. Yeah, I was giddy about it. And </s><s>[INST] were you afraid that I mean did you think about the fact that it's illegal and Roger going to end up in prison? Oh yes. Did you guys talk about it? [/INST] Well, I just, I kind of thought I was bulletproof. I mean they didn't catch you. I thought if they didn't catch you was all right? And it was hard to get you hard to catch you in the </s><s>[INST] air. So you never thought to catch you in [/INST] there. I didn't know that. If your friend told on you five years later you'd still go to, right, that was a problem. I didn't know </s><s>[INST] that. Did you did you guys ever talk about walking away? [/INST] I asked Roger to walk to walk away and he says I can't marry just now, you know? And then of course the the amount of people that he began to support the family and the gifts </s><s>[INST] and deals. [/INST] The deals, yes. The deals yes. And then you always want to do, what do you do with the money? You know, So you want to I guess you clean it up or you want to invest in a in an enterprise or in a business? Well, it just doesn't work. They know the source of it and they take it and run every one of them. Yeah. Yeah. But he was very generous, extremely generous and benevolent. And when I started I I would ask about, I went to a lawyer and a good good people. The number of people in California that time want to legalize marijuana back in 1973. And I went to a lawyer and I said mr lawyer. I put $100 on the say what would they do if I caught me bringing marijuana across the border? He said uh if you have a criminal record. I said no, I've never had a speeding ticket. Nothing, not not even a traffic ticket shit. He worked for the fire department and you know, saying yes yes sir. He said you would get probation. The worst you'll do is you'll get one year and you spend 44 months raking leaves on a military base. So my mother and my father died some years before I brought mother and baby sister came out. I took him down to Disneyland and she said, what you doing boy? That's why I'm holding pot. Should how much you're making us and making $40,000 any day. I want to go. And she said, what do you do if they catch? And I told her what the lawyer said four months at the most what reckon leaves? That's what do you think? She said, do you need a co pilot son? </s><s>[INST] Yeah. Money is money. Yeah. Is um so your relationship persevered through some, some big challenges. Is there advice you can give about what makes for a successful relationship? [/INST] Oh well, you know, I think the initial igniting meeting someone, you know, that's that's the love, that's it. And that that that little fire just that fire just keeps burning and burning and burning. You can't put it out, no matter what it's the the love fire, </s><s>[INST] but it gets difficult. It does. It's funny the love fire. So you're saying the love fires all it takes to persevere to the difficulty. [/INST] Well, no, well that's a huge part of it. And also I contribute my my individual situation to uh in order to endure what the prison years is. My faith, </s><s>[INST] faith and guard Yes. [/INST] And friends who are unconditionally still loved me no matter what. </s><s>[INST] Yes. So she had love around [/INST] you and my Children. They, you know, and that was a real purpose to guide them and to love them and to help them become citizens. </s><s>[INST] What you roger, what advice would you give? [/INST] I just don't know how to do it. But I do know that you have to work on a relationship more and I've had problems. I mean we really </s><s>[INST] gotta get in fights. [/INST] Oh yeah, but not they don't let them laugh along, you know? But certainly you're so we're the same and yet we're so different </s><s>[INST] like little stuff. Little stuff. Yes. [/INST] And uh it might be big but I usually win her over, you know. But it's but anyhow, I just feel like Murray was always there. It was like she was my anchor. I was coming home, I was always coming home to her and the Children and you can see throughout my life I'm working on getting </s><s>[INST] there. Are you afraid for his life by the way? [/INST] Oh yes. Oh yeah, there are times. Yeah, but you know I had some, I had faith in him. He was an excellent pilot for example. I always said roger if the ship's going down, I'm jumping in the lifeboat with you because I know we're going to get to shore. You will save us. And so I had that. I have that faith in him. You know, I mean, he's he's a man, but yet he's the one you want to get into the </s>
<s>[INST] I often fail, but I try. And if you must skip them, please still check out our sponsors. I enjoy their stuff. Maybe you will too. This episode is brought to you by 8Sleep and its new Pod3 mattress, which I think of as a teleportation device into a land of dreams, a place where the mind goes to escape the space-time physics of this reality of the waking world. Anything is possible in a place of dreams. The darkness that lurks in the young age shadow [/INST] is possible. </s><s>[INST] The shadow, the hope, the triumph, symbolize this delight at the end of the tunnel is possible. All of it is possible. It's all up to you. I'm kind of somebody that likes both the good and the bad of dreaming. There's a cleansing aspect of a bad dream. You wake up freaking out a little bit, but then you realize how awesome this life is that whatever happened in the dream world is not real. It's a kind of dress rehearsal for a bad event that happens in reality, but it doesn't. It's like in a video game, you get to save, do a dangerous thing, screw it up, and then you get to load and try again. That's what a dream is. Anyway, I love dreaming. I love sleeping. I love naps. And an 8Sleep mattress is the best place to teleport into that dream world. Check them out and get special savings when you go to 8sleep.com slash flex. This show is also brought to you by NetSuite, an all-in-one cloud business management system. It manages financials, human resources, inventory, e-commerce, and many business-related details, all things that I have to start figuring out. I put up a job position for somebody to help you with financials. All of it needs so much help because running a business, any kind of business, whether it's a creative business or a robotics factory or any kind of AI software company, anything you do, has so many components. And I would say many of them don't involve any of the kind of cutting-edge engineering and design and brainstorming and innovation and research and all that kind of stuff. You have to do all the basic minutia, the glue that ties together people and makes the whole thing run. And I think you should use the best tool for that job. And NetSuite is something I can definitely recommend as a great tool. You can start now with no payment or interest for six months. Go to netsuite.com slash Lex to access their one-of-a-kind financing program. That's netsuite.com slash Lex. This show is also brought to you by ExpressVPN, my comrade, my friend, the piece of software that has accompanied me through darkness and light for many years, way before I had a podcast, way before I found my way. So I am still forever lost. And you, if you too are forever lost, perhaps it will also warm your heart as a dead mind. First of all, practically speaking, let's put the romantic stuff aside, you should be using a VPN on the internet. And ExpressVPN is the VPN I've used and can highly, highly, highly recommend. By the way, I apologize for the coarseness of my voice. I've been feeling a little bit under the weather, whatever the heck that expression actually means. There's always chat GPT that can ask the question, but I'm not going to, I'm just gonna go with it, gonna wing it. Gonna wing it is another funny expression, right? Wing it, what does that mean? Probably has to do with birds. And the fact that bird flight is a kind of chaotic process that's not amenable to clear dynamical system modeling that, for example, an airplane is. But let us return to the piece of software you should be using to warm your heart and to protect your privacy on the internet. Go to expressvpn.com slash Lexpod for an extra three months free is. This show is also brought to you by Inside Tracker, a service I used to track biological data that comes from my body. There's that song, It's My Party and I'll Cry If I Want To. And I used to think it said, It's My Body and I'll Cry If I Want To. I don't know what I thought that actually meant, but it's a good song, it's a silly song. It's my party and I'll cry if I want to, cry if I want to, cry if I want to. You would cry too if it happened to you. Anyway, speaking of which, we're going hard on the tangents today. I like data that comes from my body that is then used in machine learning algorithms to make decisions or recommendations of what I should do with said body. Lifestyle choices, diet, maybe in the future it'd be career advice, all kinds of stuff, dating, friends, anything, you know. But basically health stuff, medicine, I think, and that's the obvious way you should be figuring out what to do with your body is at least in large part based on the data that comes from your body. And that just wants, but many times, over and over and over and over. InsideTracker are pioneering the data collection, sort of the blood test, then can extract all kinds of information, give you advice. I highly recommend them. Get special savings for a limited time when you go to insidetracker.com slash Lex. This is a Lex Friedman podcast. To support it, please check out our sponsors in the description. [/INST] And now, dear friends, here's Manoas Callas. Good to see you, first of all, man. Lex, I've missed you. I think you've changed the lives of so many people that I know. And it's truly like such a pleasure to be back, such a pleasure to see you grow, to sort of reach so many different aspects of your own personality. Thank you for the love. </s>
<s>[INST] It's also fascinating how constraints somehow are essential for innovation. Um And the other thing you mentioned about engineering, I have a sneaking suspicion, maybe I over, you know, my my love is with engineering. So I have a sneaking suspicion that all the genius, a large percentage of the genius is in the tiny details of engineering. So like, I think we like to think our genius are the geniuses in the big ideas. There's I have a sneaking suspicion that like, because I've seen the genius of details of engineering details make uh make the night and day difference and I wonder if those kind of have a ripple effect over time. So that that too. So that's that's sort of taking the engineering perspective that sometimes that quiet innovation at the level of individual engineer or maybe at the small scale a few engineers can make all the difference that scales. Because we're doing, we're working on computers that are scaled across large groups that one engineering decision can lead to ripple effects, which is interesting to think about. [/INST] Yeah, I mean engineering, there's also kind of a historical, it might be a bit random because if you think of the history of how especially deep learning and neural networks took off feels like a bit random because GPS happened to be there at the right time for different purpose, which was to play video games. So even the engineering that goes into the hardware um and it might have a time like the time frame might be very different. I mean this the Gps were evolved throughout many years where we he didn't even, we're looking at that, right? So even at that level right there, that revolution, so to speak, um the ripples are like like we'll see when they stop, right? But in terms of thinking of why is this happening right? There's there's I think that when I try to categorize it in sort of things that might not be so obvious. I mean clearly there's a hardware revolution we are surfing thanks to that data centers as well. I mean data centers are where like I mean at google for instance obviously they're serving google but there's also now thanks to that and to have built such amazing data centers, we can train these models. Um software is an important one. I think if I look at the state of how I had to implement things to implement my ideas, how I discarded ideas because they were too hard to implement. Yeah, clearly the times have changed and thankfully we are in a much better software position as well. And then I mean obviously there's research that happens at scale and more people enter the field. That's great to see but it's almost enabled by these other things and last but not least is also data right, curating data sets, labeling, data sets, these benchmarks. We we think about maybe will will want to have all the benchmarks in one system but it's still very valuable that someone with the thought and time and the vision to build certain benchmarks. We've we've seen progress thanks to but we're gonna repurpose the benchmarks. That's the beauty of Atari is like we solved it in a way but we use it in gatto it was critical and I'm sure it's there's there's still a lot more to do thanks to that amazing benchmark that someone took the time to put even though at the time maybe, or you have to think what's the next, you know, iteration of architecture is, that's what may be the field recognizes. But we need to, that's another thing we need to balance in terms of the humans behind, we need to recognize all these aspects because they're all critical and we tend to, yeah, we tend to think of the genius, the scientist and so on. But I'm glad you're I know you have a strong engineering background but </s><s>[INST] also I'm a lover of data and it's a pushback on the engineering comment ultimately could be the creatives of benchmarks who have the most impact. Andre Capozzi, who you mentioned has recently been talking a lot of trash about Image Net, which he has the right to do because of how critical he is about how essential he is to the development and the success of deep learning around uh, Image Net. And you're saying that that's actually that benchmark is holding back the field because I mean, especially in his context on Tesla autopilot, that's looking at real world behavior of a system. It's, you know, there's something fundamentally missing about Image that that doesn't capture the real world Nous of things that we need to have data sets, benchmarks that have the impacted unpredictability, the edge cases, the, whatever the heck it is that makes the real world so calm so difficult to operate in, we need to have benchmarks with that. So, but just to think about the impact of image that as a benchmark and that really puts a lot of emphasis on the importance of a benchmark, both sort of internally a deep mind and as a community. So one is coming in from within like how do I create a benchmark for me to mark and make progress And how do I make benchmark for the community to mark and uh push uh progress. You you you have this amazing paper, you co authored a survey paper called emergent abilities of large language models has again the philosophy here that I'd love to ask you about, what's the intuition about the phenomena of emergence in neural networks transformers, Language [/INST] models, is </s><s>[INST] there a magic [/INST] threshold </s>
<s>[INST] P. C. I'm also excited to be working with cash app to support one of my favorite organizations called First, which is best known for their first robotics and lego competitions that seeks to inspire young students in engineering and technology fields all over the world. That's over 110 countries. 660,000 students, 300,000 mentors and volunteers and a perfect rating on charity Navigator, which means that donated money is used to maximum effectiveness when you sign up for cash up and use the promo Code lex podcast, You'll instantly receive $10 in cash up. Will also donate $10 to first, an amazing organization that I've personally seen, inspire girls and boys to learn to explore and to dream of engineering a better world. Don't forget to use the Code lex podcast when you download cash app from the app store or google play store today and now here's my conversation with diva Newman, You circumnavigated the globe on boat. So let's look back in history 500 years ago, Ferdinand, Magellan's crew was first to circumnavigate the globe But he died jake I think people don't know like halfway through and so did 242 of the 260 sailors that took that three year journey. What do you think it was like for that crew at that time heading out into the unknown to face? Probably likely death. Do you think they were filled with fear with excitement? [/INST] Probably not fear. I think in all of exploration, the challenge and the unknown. So probably wonderment. And then just when you're really are sailing the world's oceans, you have extreme weather of all kinds. When we were circumnavigating it was challenging. New dynamic. You really appreciate Mother Earth, you appreciate the winds and the waves. So back to Magellan and his crew, since they really didn't have a three dimensional map of of the globe of the earth when they went out, just probably looking over the horizon, thinking what's there, what's there? So I would say the challenge that had to be really important in terms of the team dynamics and that leadership had to be incredibly important team dynamics. How do you keep people focused on the mission? </s><s>[INST] So you think the psychology that's interesting. That's probably echoes of that in the space exploration stuff we'll talk about. So the psychology of the dynamics between the human beings on the mission is important. [/INST] Absolutely. for a mars mission. It's lots of challenges, technology. But you know, since I specialize and keep my astronauts alive, the psycho, social issues. The psychology of psychosocial team dynamics leadership. That's you know, we're all people, so that's gonna be, that's always a huge impact. One of the top three I think of any isolated, confined environment in any mission. That is really pretty extreme. </s><s>[INST] So your twitter handles data explorer. So when did you first fall in love with the idea of exploration? [/INST] That's a great question. Maybe as long as I can remember as I grew up in Montana in the Rocky Mountains, Helena in the capital. And so literally, you know, Mount Helen. It was my backyard was right up there. So exploring, being in the mountains, looking at caves, just running around, but always being in nature. So since my earliest memories, I think of myself as kind of exploring the natural beauty of the Rocky mountains where I grew up. </s><s>[INST] So exploration is not limited to any domain is just anything. So the natural domain of any kind going out to the woods into the place you haven't been? It's all exploration. [/INST] I think so yeah, I have a pretty all encompassing definition of exploration. What about </s><s>[INST] space exploration when we first captivated by the idea that we little humans could venture out into the space into the great unknown of space. [/INST] So it's a great year to talk about that, the 50th anniversary of Apollo 11s? I was alive during Apollo and specifically Apollo 11. I was five years old. And I I distinctly remember that I remember that humanity, I'm sure I probably didn't know their names at the time. You know, there's a real armstrong buzz Aldrin and never forget Michael Collins in orbit. No, those three men, uh you know, doing something that just seemed impossible, seemed impossible a decade earlier, even a year earlier. But the Apollo program really inspired me. And then I think it actually just taught me to dream to any impossible mission could be possible with enough focus. I'm sure you need some luck, but you definitely need the leadership. You need the focus of the mission. So, since an early age I thought of course people should be interplanetary. Of course, people, we need people on earth and we're gonna have people exploring space as well </s><s>[INST] that seemed obvious at that age. Of course, [/INST] it opened it up before we saw men on the moon. It wasn't obvious to me at all. But once we understood that, yes, absolutely astronauts, that's what they do. They explore. They go into space and they land on other planets or moons. </s><s>[INST] So, again, maybe a romanticized philosophical question, but when you look up at the stars knowing that, you know, there's at least 100 billion of them in the Milky Way Galaxy, Right, So we're really a small speck in this giant thing that's the visible universe. How does that make you feel about our efforts here. [/INST] I love the perspective. I love that perspective. I always open my public talks with a big Hubble space telescope. You mentioned looking out until you mentioned just now the solar system Milky Way because I think it's really important to know that we're just a small pale blue dot. We're really fortunate. We're on the best planet by far, life is fantastic. </s><s>[INST] You're confident this is the best plan. It. [/INST] I'm pretty sure it's the best plan. The best planet that we know of. I mean I searched my research is you know in mission worlds and when will we find life? I think actually probably the next decade we find probably past life. Probably the evidence of past life on MArs. Let's say </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] invented [/INST] new physics. I mean look at quantum, you know, look at quantum theory. So exactly. I mean we are always learning so we definitely don't know all the physics that exist too. But we're we still have to it's not science fiction. You know, we still have to pay attention to to physics in terms of our speed of travel for space flight. </s><s>[INST] So you were the Deputy administrator of Nasa during the Obama administration. There's a current Artemus program. That's what kind of crewed mission to the moon and then perhaps the MArs, what are you excited about their what are your thoughts on this program? What are the biggest challenges do you think of getting to the moon? Of landing to the moon once again and then the big step to the to mars? [/INST] Well, I love, you know, the moon program now, Artemus is definitely we've been in low earth orbit. I love low earth orbit to but I just always look at these three phases. So low earth orbit where we've been 40 years. So definitely time to get back to deep space. Time to get to the moon. There's so much to do on the moon. I hope we don't get stuck on the moon for 50 years. I really want to get to the moon, spent the next decade first with the lander than humans. There's just a lot to explore. But to me it's a big technology push. It's only three days away. So the moon is definitely the right place. So we kind of buy down our technology, we invest in specifically habitats, life support systems, We need suits. We really need to understand really how to live off planet. We've been off planet and low earth orbit. But still that's only 400 kilometers up, 250 miles. Right. So we get to the moon. It really is a great proving ground for the technologies and now we're in deep space radiation becomes a huge issue and to keep our astronauts were all alive. And I look at all of that investment for moon moon exploration to the ultimate goal, you know the horizon goals we call it to get people to MArs but we just don't go to MArs tomorrow right. We really need a decade on the moon. I think investing in the technologies learning making sure the astronauts are their health, you know, they're safe and well and also learning so much about institute research utilization. I. S are you in situ resource utilization is huge when it comes to exploration for the moon and MArs. So you need a test bed and to me it really is a lunar test bed. And then we use those same investments to think about getting people to Mars in the 20s 30s. </s><s>[INST] So developing sort of a platform of all the kind of research tools of all the what's the resource that can you speak to that? [/INST] Yeah. So I s are you for the moon? It's we'll go to the south pole and fascinating. We have images of it. Of course we know there's permanently shaded areas and like Shackleton crater and there's areas that are permanently in the sun. Well, it seems that there's a lot of water, ice water that's trapped in ice and the lunar craters. That's the first place you go why? Because it's water and when you want to try to could be fuel, you know, life support system. So you kind of get you go where the water is. And so when the moon is kind of for resources utilization But to learn how can we make the fuels out of the resources that are on the moon. We have to think about three D. Printing right. You don't get to bring all this mass with you. You have to learn how to literally live off the land. We need a pressure shell we need to have an atmosphere for people to live in. So all of that is going to bind down the technology during the investigation doing the science. What are the basically become lunar volatiles you know what is that ice on the moon? How much of it is there? What are the resources look like to me that helps us That's just the next step in getting humans to mars </s><s>[INST] it's cheaper and more effective to sort of develop some of these difficult challenges like solve some of these challenges. Practice developed tests and so on on the moon. Absolutely [/INST] absolutely. And people are going to love to get to the moon. You get to you have a beautiful earthrise. I mean you have the most magnificent view of earth being off planet. So it just makes sense. I think we're gonna have thousands lots of people hopefully tens of thousands in low earth orbit because low earth orbit it's a beautiful place to go and look down on the earth. But people want to return home. I think the the lunar explorers will also want to do round trips and you know, being on the moon three day trip Explorer to science also because the lunar day is 14 days and longer nights also 14 days. So in that 28 day cycle, you know, half of it is in light, half of it's in dark. So people would probably want to do a couple of weeks trips, a month long trips, not longer than that. </s><s>[INST] What you mean by people What people, [/INST] explorers. Yeah, astronauts are going to be civilians in the future to not all not all astronauts are going to be government astronauts actually when I was at now. So we changed, we actually got the law changed to recognize astronauts that are not only government employees. You know, Nasa astronauts or european space agency astronaut or Russian space agency that astronauts because of the big push we put in the private sector Astronauts essentially you're gonna be astronauts. You get over 100 km up and I think once you've done orbital orbital flight then you're an astronaut. So a lot of private citizens are going to become astronauts. </s><s>[INST] Do you think one day you might step foot on the moon. [/INST] I think you'd be good to go to the moon. I'll give that a shot mars I'm gonna that's my life's work to get the next generation to mars that's that's that's that's you or even younger than you. You know, my students generation will be the martian explorers. I'm just working to facilitate that. But that's not going to be me, </s><s>[INST] the moon is pretty good and it's a lot tougher. I mean it's still a really tough mission. It's [/INST] an extreme mission. Exactly. It's great for exploration but doable. But again, before Paula we didn't think getting humans to the moon was even possible. So we kind of made that possible. But we need to go back. We absolutely need to go back. We're investing in the heavy lift launch capabilities that we need to get there. We haven't had that since the Apollo days since the Saturn five. So now we have three options on the board. That's what's so fantastic. Nasa has its space launch system. SpaceX is going to have it. It's heavy capability. And Blue Origin is coming along too with heavy lift. So that's pretty fantastic. From where I said, I'm the Apollo program professor. Today I have zero heavy lift launch capability. I can't wait just in a few years. We'll have three different heavy lift launch capabilities. So that's pretty exciting. </s><s>[INST] You know, your heart is perhaps with Nasa but you mentioned SpaceX and Blue Origin. What are your what are your thoughts of space sex and the innovative efforts there from the sort of private company aspect. [/INST] They're great. They remember that the investments and SpaceX is government funding. It's Nasa funding is U. S. Air force funding just as it should be because you're betting on a company who is moving fast has new technology development. So I love it. So it was an accident really was under our public private partnerships. So necessarily the government needs to fund these, these startups. Now, SpaceX is no longer a startup but you know it's been at it for for 10 years. It's had some accidents learned a lot of lessons but it's great because it's the way you move faster and also some private industry folks and private businesses will take a lot more risk. That's also really important for the government. </s><s>[INST] What do you think about that culture at risk? I mean it's sort of Nasa and the government are exceptionally good at delivering sort of safe. Like there's a little bit more of a culture of caution and safety and sort of this kind of solid engineering and I think SpaceX well has the same kind of stuff, it has a little bit more of that startup field where they take the bigger risk. Is that exciting for you to see seeing bigger risks in this [/INST] kind of. Absolutely. And the best scenario is both of them working together because there's really important lessons learned, especially when you talk about human spaceflight safety, quality assurance, these things are the utmost importance, both aviation and space, when human lives are at stake. On the other hand, government agencies, Nasa can the european space agency, you name it, they become very bureaucratic pretty risk averse move pretty slowly. So I think the best is when you combine the partnerships from both sides, uh, industry necessarily has to push the government take some more risks that they're smart risk or actually gave an award at Nasa for failing smart be smart. </s><s>[INST] You [/INST] know, you kind of break open the culture say no, they don't look at Polo, that was a huge risk. It was done well. So there's always a culture of safety, quality assurance engineering, you know, at its at its best, but on the other hand, you want to get things done and you have to also get them, you have to bring the cost down for when it comes to launch. We really have to bring the cost down and get the frequency up. And so that's what the newcomers are doing. They're really pushing that. So it's a about the most exciting time that can imagine for for spaceflight. Again a little bit, it really is the democratization of space by opening it up. Not just because the launch capability, but the science we can do on a cube sat what you can do now for very, those used to be, you know, student projects that we would go through conceived design implement and think about what a small satellite would be now. They're the most, you know, these are really advanced instruments. Science instruments that are flying on little teeny cube sets that pretty much anyone can afford. So there's not a every nation, you know, every place in the world can fly a cube set And so that's </s><s>[INST] that [/INST] oh that is a uh this is called one you and says we measure in terms of units. So uh you know just in terms of I put both my hands here, that's one unit to unit so little small satellites. So cube SATs are for small satellites and we actually go by mass as well. You know small satellite might be 100 kg 200 kg. All well under 1000 kg cube SATs then are the next thing down from small SATs. You know basically you know kilos in tens of kilos, things like that but kind of the building blocks cubes has a fantastic design is kind of modular design so I can take a one U 11 unit of cube set and you know but what if I have a little bit more money and pay load I can fly three of them and just basically put a lot more instruments on it. But essentially think about something the size of a shoebox if you will uh you know that would be a cube set </s><s>[INST] and those how do those help empower you in terms of doing science in terms of doing experiments? [/INST] Oh right now they're getting back to private industry planet, the company is flying cube SATs and literally looking down on earth and orbiting or taking a picture if you will of Earth every day every 24 hours covering the entire earth. So in terms of earth observations, in terms of climate change, in terms of our changing earth, it's revolutionizing because they're affordable. We can put a whole bunch them up. Telecoms were all, you know, on our cell phones and GPS. We have our telecoms. But those used to be very expensive satellites providing that service. Now we can fly a whole bunch of modular cube sets. So it really is a breakthrough in terms of modularity as well as cost reduction. </s><s>[INST] So that's one exciting set of developments. Is there something else that you've been excited about reusable rockets perhaps that you've seen in the last few years? [/INST] Well the reusability you had other usability is awesome. It's just the best. Now we have to remember the shuttle was a reusable vehicle which shuttle is an amazing narrow space engineer in the shuttle is still just the most gorgeous, elegant, extraordinary design of the space vehicle. It was reusable, it just wasn't affordable. But they were usability of It was really critical because we flew it up. It did come back. So the notion of usability and I think absolutely now what we're doing with we, you know, the global we but with SpaceX and blue origin Setting, the rockets have recovering the first stages where if they can regain 70% cost savings, that's huge. And just seeing the control, you know, they can be in control and dynamics person. Just seeing that rocket come back and land, it never gets old. It's exciting every single time you look at it and think that's magic. So it's so cool. </s><s>[INST] Give me the landing is when I stand up. Start clapping. Just just to control. Yeah, yeah. [/INST] Just just algorithms to control outcomes and hitting that landing. It's, you know, it's gymnastics for for for rocket ships. But to see these guys stick a landing, it's just wonderful. So every time, like every time I see uh you know, the reusability and the rockets coming back and landing so precisely. It's really exciting. So, it is, it is actually, that's a game changer. We are in a new era of lower costs and lot the higher frequency and it's, it's the world, not just Nasa, it's many nations are really upping their frequency of launches. </s><s>[INST] You've done a lot of exciting research, design engineering on space suits. What does the space suit of the future look like? [/INST] Well, if I have anything to say about it, it'll be a very, it'll be a very tight fitting suit. We use a mechanical counter pressure to pressurize right directly on the skin. It seems that it's technically feasible. We're still at the research and development stage. We don't have a flight system, but technically it's feasible. So we do a lot of work in the materials, you know, what materials do we need to pressurize someone. What's the patterning we need. That's what our patents around the patterning kind of how we apply, this is a third of an atmosphere </s><s>[INST] just to sort of take a little step back. You have this incredible bio suit where it's tight fitting, so allows more mobility and so on. So maybe even take a bigger step back. Like what are the functions that are spaces should perform? [/INST] So start from the beginning, spacesuit is the world's smallest spacecraft. So I really that's the best definition I can give you right now. We fly gas pressurized suits, but think of developing and designing an entire spacecraft. So then you take all those systems and you shrink them around a person, provide him with oxygen to breathe, scrub out the carbon dioxide, make sure they have pressure, they need a pressure environmental event. So really the space is a shrunken, you know, spacecraft in its entirety has committed the same systems. Communications exactly. So you really thermal control a little bit of radiation, Not so much radiation protection, but thermal control, humidity, oxygen debris. So all those life support systems as well as the pressure production. So it's an engineering marvel. You know, the space suits that have flown because they really are entire spacecraft that a small spacecraft that we have around a person, but they're very massive, 140 kg. The current suit and they're not mobility suits. So since we're going back to the moon and mars, we need a planetary suit, we need a mobility suit. So that's where we've kind of flipped the design paradigm. I studied astronauts. I study humans in motion and if we can map that motion, I want to give you full flexibility, you know, move your arms and legs. I really want you to be like a olympic athlete in extreme explorer. I don't want to waste any of your energy. So we take it from the human design. So I take a look at humans, we measure them, we model them and then I say, okay, can I put a space suit on them that goes from the skin out? So rather than a gas pressurized shrinking that space craft around the person. So here's how humans perform. Can I design a space suit literally from the skin out? And that's what we've come up with mechanical counter pressure, some patterning and that way it can be order of magnitude less in terms of the mass and it should provide maximum mobility for the moon or mars. </s><s>[INST] What's mechanical counter pressure? Like how the heck can you even begin to create something that's tight fitting [/INST] so and </s><s>[INST] still doesn't protect you from the elements and so on. And the whole, the pressure thing. [/INST] That's the challenge is a big design chance we've been working on it for. So you can either put someone in a balloon. That's one way to do it as conventional. That's what I mean. That means the ballooning, that's the gas pressure I suit. So put someone in a balloon. It's only a third of an atmosphere To keep someone alive. So that's what the current system is. So depending on what units you think 30 killer Pasko's, you know, £4.. square. </s><s>[INST] So much less than the pressure that's on Earth. You can still want human alive with .3 and it's alive and happy, [/INST] alive and happy. And you know, you mix the gasses june here we're having this chat and we're both we're at one C level in boston and you know, one atmosphere. But suits are nitrogen to put a suit if we put someone to a third of an atmosphere. So for mechanical counter pressure now. So one way to do it with a balloon and that's what we currently have or you can apply the pressure directly to the skin. I only have to give you a third of an atmosphere right now, you and I are very happy and one atmosphere. So so you know, so if I put that pressure, a third of an atmosphere on you, I just have to do it consistently across all of your body and your limbs and it'll be a gas pressurized helmet doesn't make sense to shrink wrap the head, see the blue man group. That's a great, it's a great act. But we don't need, there's no benefits of like shrink wrapping. You put gas pressurized helmet because the helmet then the future of suits. You asked me about the helmet just becomes your information portal. So it will have augmented reality. You have all the information you need should have. You know the maps that I need. I'm on the moon. Okay well hey smart helmet then. Show me the map. Show me the topography. Hopefully it has the lab embedded too. If it has really great cameras, maybe I can see what that regular that's just lunar dust and dirt. What's that made of? We talked about the water. So the helmet then really becomes this information portal is how I see kind of the I. T. Architecture of the helmet is really allowing me to use all of my modalities of an explorer that I'd like to. So cameras voice over images. If it were really good it would kind of be would have lab capabilities as well. </s><s>[INST] Okay, so the pressure comes for the body comes from the mechanical pressure which is fascinating. What aspect when I when I look at bios, just the suits are working on sort of from a fashion perspective. They look awesome. Is that is that a small part of it too? [/INST] Oh absolutely. Because the teams that we work with of course I'm an engineer, there's engineering students, there's design students, there's architects. So it really is very much a multidisciplinary team. So sure colors, aesthetics, materials, all those things we pay attention to. So it's not just an engineering solution. It really is a much more holistic, is a suit. Your, you know, your dressing is, it's form fitting. So we really have to pay attention to all those things. And so that's the the design team that we work with and my partner get ready. You know, we're partners in this in terms of he comes from an architecture, industrial design background. So bringing those skills to bear as well, we team up with industry folks who are in athletic performance and designers. So it really is a team that brings all those skills together. </s><s>[INST] So what role does the space to play in our long term staying in MArs sort of exploring the doing all the work that astronauts do, but also perhaps civilians one day almost like taking steps towards colonization of MArs. What world does a space to play there? [/INST] So you always need life support system, pressurized habitat. And I'd like to say we're not going to MArs to sit around so you need a suit even if you land and have the land or you're not going there to stay inside. That's for darn sure. We're going there to search for the evidence of life. That's why we're going to MArs. So you need a lot of mobility. So for me, the suit is the best way to give the human mobility. We're always still gonna need rovers. We're gonna need robots. So for me explorations, always a suite of explorers, Some people are going to some of the suite of explorers or humans, but many are going to be robots, smart systems, things like that. But I look at it is kind of all those capabilities together make the best exploration team. </s><s>[INST] So let me ask, I love artificial intelligence. And uh I've also saw that you've enjoyed the movies space obviously in 2001, a space odyssey. Let me ask the question about how 9000 that makes a few decisions there that prioritizes the mission over the the astronauts. Do you think from a high philosophical question, uh do you think? How did the right thing of prioritizing the mission? [/INST] I think our artificial intelligence will be smarter in the future for a MARS mission is a great question of is that the reality isn't for a MARS mission, we need fully autonomous systems, we will get humans but they have to be fully autonomous. And that's a really important. That's the most important concept. Because you know, there's not gonna be a mission control on earth, you know, 20 minutes uh time. Like there's just no way you're gonna control so fully autonomous. So people have to be fully autonomous as well. But all of our systems as well. And so that's that's the big design challenge. So that's why we test them out on the moon as well when we have a okay a few seconds, three second time. Like you can test them out, we have to really get autonomous exploration down. You asked me earlier about Magellan Magellan and his crew. They left right. They were autonomous. You know they were autonomous they left and they were on their own to figure out that mission. Then when they hit land they have resources as institute resource utilization and everything else they brought with them. So we have to I think have that mindset for expression again back to the moon it's more the testing ground a proving ground with technologies. But when we get to MArs it's so far away that we need fully autonomous system. So I think that's that's where AI and autonomy come in. A really robust autonomy. Things that we don't have today yet. So they're on the drawing boards but we really need to test them out because that's that's what we're up against. </s><s>[INST] So fully autonomous, meaning like self sufficient. There still a role for the human in that picture. Do you think there will be a time when Ai systems just beyond doing fully autonomous flight control will also help or even take mission decisions? Like how did [/INST] that's interesting. It depends. I mean they're going to be designed by humans and as you mentioned, humans are always in the loop. We might be on Earth, we might be in orbit on MArs. Maybe the systems that Landers down on the surface of MArs. But yeah I think we're gonna get we are right now just on Earth based systems you know ai systems that are incredibly capable and you know, training them with all the data that we have now, you know, petabytes of data from earth? What I care about for the autonomy and ai right now we're applying it in research is to look at Earth and look at climate systems. I mean that's the it's not for mars to me today right now Ai is to eyes on Earth all of our space data compiling that using supercomputers. Because we have so much information and knowledge and we need to get that into people's hands. We need first there's an educational issue with both climate and our changing climate. Then we need to change human behavior. That's the big e so this next decade it's urgent. We take care of our own spaceship was just spaceship Earth. So that's uh to me where my focus has been for A. I systems using whatever is out there kind of imagining also what the future of situation is that the satellite imagery of Earth of the future, if you can hold that in your hands, that's gonna be really powerful. Well that helps people accelerate positive change for Earth and for us to live in balance with Earth. I hope so and kind of start with the ocean systems so oceans to land to air and kind of using all the space data. So it's a huge role for artificial intelligence to help us analyze the called curating the data using the data. It has a lot to visualizations as well. </s><s>[INST] Do you think in a weird dark question, do you think human species can survive if we don't become interplanetary in the next century or a couple of centuries? [/INST] Absolutely. We can survive. I don't think MArs is option B actually, so I think it's all about saving spaceship Earth and humanity. I simply put Earth doesn't need us, but we really need Earth. All of humanity needs to live in balance with Earth because Earth has been here a long time before we ever showed up and it'll be here a long time after. It's just a matter of how do we want to live with all living beings? You know, much more imbalance because we need to take care of the Earth and right now we're not. So that's the urgency. And I think it is the next decade to try to live much more sustainably live more in balance with Earth. I think the human species has a great long optimistic future, but we have to act it's urgent. We, you know, we have to change behavior. We we have to we have to realize that we're all in this together. It's just one blue bubble. It's for humanity. So when I think people realize that we're all astronauts, that's the great news is everyone is going to be an astronaut were all on. We're all astronauts of spaceship Earth and you know, again, this is our mission. This is our mission to take care of the planet </s><s>[INST] And yet as we explore out from our from our spaceship earth here out into the space. What do you think the next 50,200 years look like for space exploration? [/INST] I'm optimistic. So I think that will have lots of people, thousands of people, tens of thousands of people who knows, maybe millions in low earth orbit. That's just a place that we're gonna have people and actually some industry, manufacturing things like that. That that dream. I hope we realize getting people to the moon so I can envision a lot of people on the moon. Again, it's a great place to living, </s><s>[INST] living [/INST] probably visiting and living if you want to. Most people are gonna want to come back to Earth I think. But there'll be some people and it's not such a long it's a good view. It's a beautiful view. So I think that we will have, you know, many people on the moon as well. I think there'll be some people you told me well, you know, hundreds of years out. So we'll have people will be interplanetary for sure as a species. So I think we'll be on the moon. I think we'll be on mars venus. No, it's already a runaway greenhouse gas and not a great great place for science. You know, jupiter all within the solar system, great place for all of our scientific probes. I don't see so much in terms of human physical presence, will be exploring them. So we, we live in our minds there because we're exploring them and going on those journeys, but it's really our choice in terms of our decisions of how imbalanced, you know, we're going to be living here on the earth. </s><s>[INST] When do you think the first woman, first person will step on mars [/INST] uh steve on mars? Well I'm I'm going to do everything I can to make sure it happens in the twenties thirties 2020 2020 2025 2035 will be on the moon and hopefully with more people than us. But first with, you know, a few astronauts, it'll be global, international folks, but we really need those 10 years I think on the moon. And then so by the by later in the decade of the 20 thirties we'll have all the technology and know how and we need to get that, you know, human mission to mars then </s><s>[INST] live in exciting times. And David, thank you so much for leading the way and thank you for talking today. Thank [/INST] you my pleasure. </s><s>[INST] Thanks for listening to this conversation and thank you to our presenting sponsor cash app. Remember to use code lex podcast when you download cash app from the app store, google play store, you'll get 10 bucks, $10.10 dollars will go to first a stem education, non profit that inspires hundreds of thousands of young minds to learn at the dream of engineering our future. Thank you and hope to see you next time. [/INST] </s>
<s>[INST] it's sometimes very difficult, this is where vision is required to anticipate the unintended consequences and it seems like Mark Zuckerberg is not very good at that you've talked to so many great leaders in this world privately and publicly? What do you think makes a great leader of these tech companies is uh do you have an example like Ellen to you a great leader? He's also a controversial one, right? There's a, there's a love and hate controversial in the sense that there is, and I know a lot of people have worked with him for him, that there's also a love hate relationship. The hate comes from the fact that they get pushed extremely hard. It's, uh, it's a very competitive environment, but it's a positive one because it's, uh, there's a vision that's underlying is similar to the steve jobs thing. It has to do with back to our Michael Jordan discussion as well that there seems to be the, the demons involved in tension and just anxiety, all those kinds of things, [/INST] if you want to do great things, um, there will be some suffering. Uh, and you know, there'll be some pain and it's not easy if you want to change the world and then some people have this expectation that it's going to be easy. Um, and what you'll typically find for any great leader who is trying to do something super ambitious, like if you want to be like, if you're a rich guy and you start like a restaurant and you don't care about making money and people have made restaurants before, like you could be high fives and everybody can love you whatever, but if you want to change the world, you want to do something hard driving, there's going to be sacrificed involved? And so the problem is people are looking at something that is an olympic caliber sport or a navy seals, like effort. In other words, an effort that requires massive sacrifice. We would not look at somebody who wins a gold medal like Michael Phelps and say, oh my God, he had to get up at four a.m. Every day and he had to swim and he had to do an ice bath. Oh my God, that poor guy, he suffered, he was tortured. He people were super mean to him. They put him in an ice bath was like, no, he wanted to be the greatest swimmer of all time and he knew what the sacrifice entailed and that what happens in work in business is that people conflate like, well, I went to work to make a living to pay my bills vs. Michael Phelps approach to getting gold medals or Michael Jordan's or pick the person Ellen or Jeff Bezos. And when you look at the reviews of like a place like amazon, there was this incredible story in the new york times where people, I don't know if you remember it, this is the worst place you could ever work amazon and they, we talked to 200 people and they all told us, they all described for us in the new york times, a culture of cutthroat nous and brutality that has never before been seen. And then you see all these people who work for basis for 24 years from when they graduated with their NBA S until today and they've never left the company and they are ride or die forever and what you're seeing there is, there is a mismatch of people going to work in an extreme sport or an extreme endeavor, who should not do that. There are people who should go out into the rice fields and pick rice. And then there's another group of people who are samurai and who wield a sword and who take on missions that are dangerous. But if you're a rice picker and that's what you do and you feel safe, just, you know, getting a couple grains arise and put them in a basket cleaning it and then you know, whatever that that's valid work, no big deal. I'm not deriding and I'm sort of, but that is one group and then there's people who are samurai and you can, you cannot conflate the two, you cannot compare the two. And that's what is happening right now in business, Whenever you see these stories about this person at this company is like a tyrant and they're so horrible and they yelled at somebody like if you're in the field and you're taking the beach at Normandy and it's D day or you know, you gotta take the hill or you gotta whack Osama bin laden and you're the navy seals and like a rudder a rotor gets knocked off the back of the black Hawk. Like this is serious shit. Like don't do it if you're not serious. And if you're not serious about changing the world, why would you go work for Bezoza? Why would you go work for Elon musk? Don't do it. </s><s>[INST] Don't go work there. Uh, this is, this is uh, let me just sit back and enjoy the beauty of uh, all of that. That's music to my ears, but I'm not sure what to do with it because it is conflicting to a lot of the things I hear from the way you're supposed to kind of act and uh, I, I think in order to do great things, you have to, I always admired people that lose their shift a little bit because they're so passionate and, and like, you know, you know, apologize and all those kinds of things. But like there's a tension, there's a drama to the creative process when, especially in the early startup, you know, you're not, this is not like the work life balance idea doesn't even apply work life balance, ridiculous. It's [/INST] a ridiculous concept. Like the idea that there's like work life balance in a startup is ridiculous. If you're looking for work life balance, do not go to a startup or any kind of ambitious company, there is a series of places you can work in the world where you do not need to do anything more than what's put in front of you and you just put the round peg in the round hole in the square peg in a square hole pole and you go home and you get your like, you know, you get your little, you know, bits and grains of rice and you go heat them up and eat them. That's it. And then there's this other thing which is the extreme pursuit of changing the world and sacrificing and we have a generation of people or multi generations of people who are soft, they're just soft. I mean what is the big struggle we've had to deal with in America in our lifetimes like 9 11 and we didn't have the Vietnam War and then we had this like weird Iraq wars and Middle East wars that were kind of like a small number of people went and we sent drones like we have not had to sacrifice gen xers, you know, maybe the talent of boomers experience the Vietnam war regrettably. But you know, we've had a couple of generations now, three, I guess that just haven't had to suffer. And so were soft as americans were soft. And then you look at people in china and we're like, oh my God, these poor chinese people are living in these tiny cramped apartments, like they were living In like essentially Lean 2s in northern China with no running water or like one speaking of ice cold water for the entire village, like they're thrilled to be joining the middle class. Even if it's the bottom of the middle class, right? Uh they've taken hundreds of millions of people in china and moved them into the middle class. And we're like, oh my God, these people are suffering. You know, they're up to $4 an hour, three or $4 an hour in the factories there and they were just two decades ago at, you know, I don't know, it was probably 50 cents an hour, Something crazy like that. And now they've improved the quality of life there so much. Just like America did 200 years ago or 100 years ago, they've improved it so much in China that now they're getting out price for factories from Vietnam Sri Lanka Pakistan India and people are moving and people in China are moving the factories out of China into other countries because the Chinese are now outsourcing to Vietnam and other countries. So this is the way of the world, You know, people move up and they get a better lot in life for their families. And just in America we've gotten soft and there's a generation, how do people die in America now? Suicide, obesity, heart attacks anxiety. I mean, we're suffering from things that if you told people 100 years ago that the number, the top ways americans would die would be overeating and suicide. They'd be like what? You're literally killing yourself or eating yourself to death, that's what's happening in </s>
<s>[INST] just it was just walking down the hall and nobody paying attention and it's just like walking down this long hall and I'm like looking around is anyone like what's happening here? So presumably some kind of automation was doing the map. I mean the whole environment is probably really well mapped but it was just it gave me a picture of a world where robot is doing doing his thing wearing a couple hats, just going down the hall like getting some coffee or whatever. Like I don't know what it's doing, what's the mission. But I don't know for some reason that really stuck with me. You don't often see robots that aren't part of a demo or that aren't uh you know like with a semi autonomous autonomous vehicle, like directly doing a task. This was just chilling. Yeah. I don't know. [/INST] Well yeah. You know I mean we're at M. I. T. Like when I first got to M. I. T. I was like okay where's all the where's all the robots? And they were all like broken or like not damn going. So. Yeah. And and and what really excites me is that we're about to have that we're about to have so many moving wrote about to. Well it's coming, it's coming in our lifetime that we will just have robots moving around already. Seeing the beginnings of it there's delivery robots and some cities on the sidewalks and I just love seeing like the tick talks of people reacting to that because yeah, you see robot walking down the hall with a cowboy hat. Like what the, what is this? This is awesome and scary and kind of awesome and people either love or hate it. That's one of the things that I think companies are underestimating that people will either love a robot or hate a robot and nothing in between. So it's just again an exciting time to be alive. </s><s>[INST] Yeah. I think kids almost universally at least in my experience love them. Love legged robots. [/INST] If they're not like my, my son hates the remote because ours is loud. </s><s>[INST] Oh, that yeah, no, the legs. The legs [/INST] because </s><s>[INST] your son. Um, do they understand rumored to be a robot? [/INST] Oh yeah. My kids, that's one of the first words they learned. They know how to say beep boop and yes, they think the room as a robot. </s><s>[INST] Do they project intelligence out of the thing? [/INST] Well, we don't really use it around them anymore for the reason that my son is scared of it. </s><s>[INST] Yeah. [/INST] I think they would like even a Roomba because it's moving around on its own. I think kids and animals view it as an agent. </s><s>[INST] So what do you think if we just look at the state of the art of robotics? What do you think robots are actually good at today? So if we look at today, [/INST] you mean physical robots? </s><s>[INST] Yeah, physical robots, [/INST] wow. </s><s>[INST] Like what are you impressed by? So I think a lot of people, I mean that's what your book is about is have maybe a not a perfectly calibrated understanding of where we are in terms of robotics was difficult to robotics. What's easy in robotics? [/INST] Yeah, we're way behind where people think we are. So What's impressive to me. So let's see. 011 thing that came out recently was Amazon has this new warehouse robot and it's the first autonomous warehouse robot that can is safe for people to be around. And so like it's kind of most people, most people I think envision that our warehouses are already fully automated and that there's just like robots doing things. It's actually still really difficult to have robots and people in the same space because it's dangerous for the most part robots, you know, because especially robots that have to be strong enough to move something heavy, for example, they can really hurt somebody. And so until now a lot of the warehouse robots had to just move along like pre existing lines which really restrict what you can do. Um And so having I think that's that's one of the big challenges and one of the big like exciting things that's happening is that we're starting to see more Kobach ticks in industrial spaces like that where people and robots can work side by side and not get harmed. </s><s>[INST] Yeah. That's what people don't realize that the physical manipulation tasks with humans, it's not that the robots want to hurt you. I think that's what people are worried about. Like this malevolent robot gets them out of its own and wants to destroy all humans. Now. It's, you know, it's actually very difficult to know where the human is and to to respond to the human and dynamically and collaborate with them on a task, especially if you're something like an industrial robotic arm, which is extremely powerful. See this some of the some of those arms are pretty impressive now that you can just you can you can grab it, you can move it. So the collaboration between human robot and the factory setting is really fascinating. Um Do you think they'll take our jobs? [/INST] I don't think it's that simple. I think that there's a ton of disruption that's happening and will continue to happen. Um You know, I think speaking specifically of the amazon warehouses, that might be an area where it would be good for robots to take some of the jobs that are, you know, where people are put in a position where it's unsafe and they're treated horribly and you know, probably it would be better if a robot did that and amazon is clearly trying to automate that job away. So I think there's gonna be a lot of disruption, I do think that robots and humans have very different skill sets. So while a robot might take over a task, it's not gonna take over most jobs. Um I think just things will change a lot. Like I don't know one of the examples I have in the book is mining um So there you have this job that is very unsafe and that requires a bunch of workers and put them in unsafe conditions and now you have all these different robotic machines that can help make the job safer. And as a result now people can sit in these like air conditions, remote control stations and like control these autonomous mining trucks. And so that's a much better job but also they're employing less people now. So it's it's just a lot of I think from a bird's eye perspective, you're not going to see job loss, you're going to see more jobs created because that's I think the future is not robots just becoming like people and taking their jobs. The future is really a combination of our skills and then the supplemental skill set that robots have to increase productivity to help people have better, safer jobs too. Give people work that they actually enjoy doing and are good at. Um But it's really easy to say that from a bird's eye perspective and um ignore kind of the the rubble on the ground as we go through these transitions because of course specific jobs are going to get lost </s>
<s>[INST] Don't tell me you're gonna turn this [/INST] into a machine learning problem. So then you turn into a machine learning problem, And then you have a space of genetic algorithms and reinforcement learning and all these cool things. </s><s>[INST] Can you include that into the stack, into the modular stack? Yeah, yeah. Where does it sit? Where does it live? [/INST] Is it a separate thing or is it part of the compilation? Yeah, yeah. So you start from simple and predictable models. And so you can have full control and you can have coarse-grained knobs like nudged systems, so you don't have to do this. But if you really care about getting the best, last ounce out of a problem then you can use additional tools and they're the cool things you don't want to do this every time you run a model you want to figure out the right answer and then cash it and once you do that you can get you can say okay cool I can get up and running very quickly I can get good execution out of my system I can decide if something's important and if it's important I can go throw a bunch of machines at it and do a big expensive search ever the space using whatever technique I feel like its pretty up to to the problem, and then when I get the right answer, cool, I can just start using it. And so you can get out of this trade-off between, okay, am I gonna spend forever doing a thing, or do I get up and running quickly, and as a quality result, these are actually not in contention with each other if the system's designed to scale. </s><s>[INST] You started and did a little bit of a whirlwind overview of how you get 35,000X speed up or more over Python. Jeremy Howard did a really great presentation about sort of the basic, like, look at the code, here's how you get the speed up. Like you said, that's something we could, probably developers can do for their own code to see how you can get this gigantic speed up. But can you maybe speak to the machine learning task in general, how do you make some of this code fast and specific, like, what would you say is the main bottleneck for machine learning tasks? So are we talking about that mall matrix multiplication, how do you make that fast? [/INST] So, I mean, if you just look the Python problem, right, you can say, how do I make Python faster? There's been a lot of people that have been working on the, okay, how do I make Python 2X faster, 10X faster, or something like that, right? And there've been a ton of projects in that vein, right? Mojo started from the, what can the hardware do, like, what is the limit of physics? What is the speed of light, what is it? Like, how fast can this thing go? And then, how do I express that? Yeah, right. And so it wasn't well, it wasn't anchored relatively on make Python a little bit faster. It's saying cool I know what the hardware can do. Let's unlock that right now when you yeah </s><s>[INST] Yeah, just say how how gutsy that is to be in the meeting and as opposed to trying to see how do we get the improvement? [/INST] It's like what can the physics do? I Mean, maybe I'm a special kind of nerd, but you look at that. What is the limit of physics? How fast can these things go, right? When you start looking at that, typically it ends up being a memory problem. Mm-hmm. Right and so today Particularly with these specialized accelerators. The problem is that you can do a lot of math within them But yet you get bottleneck sending data back and forth to memory whether it be local memory or distant memory or disk or whatever It is and and that that bottleneck particularly is the training sizes get large as you start doing tons of inferences all over the place Like that becomes a huge bottleneck for people, right? So again, what happened is we went through a phase of many years where people took the special case and hand tuned it Tweaked it and tricked out and they knew exactly how the hardware worked and they knew the model and they made it they made it fast Didn't generalize and so you can make you know Resident 50 or some or Alex net or something inception v1 like you can you can do that, right because the models are small They fit in your head Right, but as the models get bigger more complicated as the machines get more complicated it stops working Right, and so this is where things like kernel fusion come in. So what is kernel fusion? This is this idea of saying let's avoid going to memory and let's do that by building a new hybrid Kernel and a numerical algorithm that actually keeps things in the accelerator instead of having to write all the way out to memory All right, what's happened with with these accelerators now is you get multiple levels of memory like in a GPU For example, you'll have global memory and local memory and like all these things If you zoom way into how hardware works the register file is actually a memory so the registers are like an L0 cache and so a lot of Taking advantage of the hardware ends up being full utilizing the full power in all of its capability and this has a number of problems, right one of which is again the complexity of disaster, right? There's too much hardware. Even if you just say let's look at The chips from one line of vendor like Apple or Intel or whatever it is Each version of the chip comes out with new features and they change things so that it takes more time or less time to do different Things and you can't rewrite all the software Whenever a new chip comes out, right? And so this is where you need a much more scalable approach and this is what mojo and what the Modular stack provides is it provides this infrastructure and the system for factoring all this complexity and then allowing people to express algorithms You talk about auto tuning for example Express algorithms in a more portable way so that when a new chip comes out you don't have to rewrite it all So to me like, you know, I kind of joke like what is a compiler? Well, there's many ways to explain that you convert thing a and thing B and you convert source code to machine code Like you can talk about many many Things that compilers do but to me it's about a bag of tricks It's about a system and a framework that you can hang Complexity it's a system that can then generalize and it can work on problems that are bigger than fit in one human's head Right. And so what that means what a good stack and what the modular stack provides is The ability to walk up to it with a new problem and it'll generally work quite well And that's something with a lot of machine learning infrastructure and tools and technologies don't have Typical state-of-the-art today as you walk up particularly if you're deploying if you walk up with a new model You try to push it through the converter and the converter crashes. That's crazy The state of ML tooling today it's not anything that a C programmer would ever accept, right? And it's always been this kind of flaky side of tooling that's never been integrated. Well, and it's been Never worked together and because it's not designed together. It's built by different teams It's built by different hardware vendors is built by different systems it's built by different internet companies They're trying to solve their their problems Right and so that means that we get this fragmented terrible mess of complexity </s>
<s>[INST] Also, if you want to work with our team or always hiring, go to luksfreedman.com slash hiring. And now, on to the full ad reads. As always, no ads in the middle. I try to make this interesting, but if you must skip them, please still check out our sponsors. I enjoy their stuff. Maybe you will too. This show is brought to you by Notion, a note-taking and team collaboration tool, my favorite note-taking and team collaboration tool. And they have a new feature, Notion AI, that I've been using and loving, and this thing is probably the best implementation of a system that uses a language model to generate text, because it integrates across the entirety of your note-taking process, and it adds just a giant number of small and big features that help you out, that save a lot of time, but also make everything more fun and creatively sort of inject ideas into your workflow. So just to list some features that can edit the voice and tone of the text you already wrote, so they can rewrite it in a different tone. They can make the text which I love. They can make it shorter or longer. Also, they can simplify the text, [/INST] which to me is at the core of the writing process </s><s>[INST] to support the learning. Make things as simple as possible, but not simpler, as Einstein said. And to have tools that give you ideas how to do that, not necessarily completely automate everything, but give you really powerful ideas on how to get 90% there. This is just brilliant. Also, if there's technical jargon, they can rewrite the text and explain it more simply. What else? They can obviously summarize the text. If you start writing, they can continue your writing. If you're having trouble starting to write and there's a blank page glaring back at you, they can generate based on a topic, a bunch of text to get you going. I mean, there's so many just amazing features. I love it when great, powerful language models or any idea in AI is then injected into a tool that's actually usable and useful and powerful across a number of use cases to a huge number of people. I mean, this is really, really, really exciting. Notion AI helps you work faster, write better, and think bigger, doing tasks that normally take you hours and just minutes. Try Notion AI for free when you go to notion.com slash Lex. That's all lowercase notion.com slash Lex to try the power of Notion AI today. This show is also brought to you by, indeed, a hiring website. I've used it, I continue to use it to hire folks for the teams I've been on, have led from engineering to creative. Everything requires a rigorous, systematic, artistic, all many adjectives I want to use, process to build up an amazing team because there's nothing more important to the success of an endeavor or the success of life or to just your contentment and happiness and joy and fulfillment and a source of meaning than the team that you take on hard challenges of life with, of work with. So you should use the best tools for the job. Of hiring, and you should take hiring very, very, very seriously. Don't overspend on hiring. Visit indeed.com slash Lex to start hiring now. That's indeed.com slash Lex. Terms and conditions apply. This show is also brought to you by MasterClass. $180 a year, gets you an all-access pass to watch courses from the best people in the world in their respective disciplines. One of the people I just recently talked to is Chris Voss. He is a former FBI hostage negotiator. Brilliant guy. Off the mic, I really enjoy talking to him. There is kindness, camaraderie, thoughtfulness, humor, wit, also a certain sort of cultural density and complexity, hailing from New York or whatever that rich, sexy accent is from. It's just really fun to listen to him, to listen to him discuss what he's really good at. That was true on the podcast, and that is very much true in his MasterClass, where he really systematically breaks down his ideas of what it takes to negotiate with terrorists, negotiate with hostage takers, negotiate with bank robbers, but I think the most important thing is negotiate in everyday life, to negotiate in business, relationships, all of that. It's just a really brilliant, concise, clear, actionable advice that he gives. And that's true for almost every single MasterClass they have, and you get access to all of them. Get unlimited access to every MasterClass and get 15% off an annual membership at masterclass.com. Lex. This is the Lex Friedman podcast. To support it, please check out our sponsors in the description. And now, dear friends, here's Sam Harris. What is more effective at making a net positive impact [/INST] on the world, empathy or reason? It depends on what you mean by empathy. There are at least two kinds of empathy. There's the cognitive form, which is, I would argue, even a species of reason. It's just understanding another person's point of view. You understand why they're suffering, or why they're happy, or you have a theory of mind about another human being that is accurate, and so you can navigate in relationship to them more effectively. And then there's another layer entirely, not incompatible with that, but just distinct, which is what people often mean by empathy, which is more a kind of emotional contagion, right? Like you feel depressed, and I begin to feel depressed along with you, because it's contagious, right? We're so close, and I'm so concerned about you, and your problems become my problems, and it bleeds through, right? Now, I think both of those capacities are very important, but the emotional contagion piece, and this is not really my thesis, this is something I have more or less learned from Paul Bloom, the psychologist who wrote a book on this topic titled Against Empathy. The emotional social contagion piece is a bad guide, rather often for ethical behavior and ethical intuitions. Oh boy. And so I'll give you the clear example of this, which is we find stories with a single, identifiable protagonist who we can effortlessly empathize with far more compelling than data, right? So if I tell you, this is the classic case of the little girl who falls down a well, right? This is somebody's daughter, you see the parents distraught on television, you hear her cries from the bottom of the well, the whole country stops. I mean, there was an example of this 20, 25 years ago, I think, where it was just wall to wall on CNN. This is just the perfect use of CNN. It was 72 hours of whatever it was of continuous coverage of just extracting this girl from a well. So we effortlessly pay attention to that. We care about it. We will donate money toward it. I mean, it's just, it marshals 100% of our compassion and altruistic impulse. Whereas if you hear that there's a genocide raging in some country you've never been to and never intended to go to, and the numbers don't make a dent and we find the story boring and will change the channel in the face of a genocide, right? It doesn't matter, and it literally, perversely, it could be 500,000 little girls have fallen down wells in that country and we still don't care, right? So it's, you know, many of us have come to believe that this is a bug rather than a feature of our moral psychology. And so the empathy plays an unhelpful role there. So ultimately, I think when we're making big decisions about what we should do and how to mitigate human suffering and what's worth valuing and how we should protect those values, I think reason is the better tool, but it's not that I would want to dispense </s>
<s>[INST] You mentioned collaboration, you've written about your collaboration with Amos Tversky That this is you writing the 12 or 13 years in which most of our work was joint for years of interpersonal and intellectual bliss. Everything was interesting. Almost everything was funny and there was a current joy of seeing an idea take shape so many times in those years. We shared the magical experience of one of us saying something which the other one would understand more deeply than the speaker had done contrary to the old laws of information theory. It was common for us to find that more information was received than had been sent. I have almost never had the experience with anyone else if you have not had it, you don't know how marvelous collaboration can be. So let me ask a bird. Perhaps a silly question. How does one find and create such a collaboration? That may be asking like how does one find love? But [/INST] yeah, you have to be lucky. And and and I think you have to have the character for that. Because I've had many collaborations, I mean none was as exciting as with atmosphere. But I've had and I'm having. It was very so it's a skill. I think I'm good at it, not everybody is good at it. And then it's the luck of finding </s><s>[INST] people who are also good at. It is their advice in a form for a young scientist who also seeks to violate this law of information theory. [/INST] I really think it's so much luck is involved. And you know, and those really serious collaborations, at least in my experience are a very personal experience. And I have to like the person I'm working with otherwise, you know, I mean there is that kind of a collaboration which is like an exchange a commercial exchange of giving this. You give me that. But the real ones our interpersonal there between people like each other and who like making each other think and who like the way that the other person responds to your thoughts. Uh You have to be lucky. </s><s>[INST] Yeah, I mean but I already notice about even just me showing up here, you have quickly started to digging in a particular problem I'm working on and already knew information started to emerge. It. Is that a process just the process of curiosity of talking to people about problems and seeing, [/INST] I'm curious about anything to do with ai and robotics and you know, and uh so and I knew you were dealing with that. So I was curious </s><s>[INST] just follow your curiosity jumping around and the psychology front, the dramatic sounding terminology of replication crisis. But really just the at times this this effect at the time studies do not are not fully generalize herbal. They [/INST] don't, you're being polite, it's worse than that. </s><s>[INST] But is it? So I'm actually not fully familiar. Didn't agree how bad it is. Right. So what do you think is the source? Where do you think? [/INST] I think I know what's going on actually. I mean I have a theory about what's going on and what's going on is that there is first of all a very important distinction between two types of experiments and one type is within subjects. So it's the same person has two experimental conditions and the other type is between subjects where some people have this condition of the people in that condition, they're different worlds. And between subject experiments much harder to predict and much harder to anticipate and the reason. Uh and they're also more expensive because you need more people. And it's it's just so between subject experiments is where the problem is, it's not so much and within subject experiments really between and there is a very good reason why the intuitions of researchers about between subject experiments are wrong. And that's because when you are a researcher, you're in a within subject situation, it is you are imagining the two conditions and you see the causality and you feel it. And but in between subject conditions, they don't they they see they live in one condition and the other one is just nowhere. So our intuitions are very weak about between subject experiments and that I think is something that people haven't realized. And and in addition because of that, we have no idea about the power of uh manipulations of experimental manipulations. Because the same manipulation is much more powerful when when you are in the two conditions, then when you live in only one condition. And so the experimenters have very poor intuitions about between subject experiments. And and there is something else which is very important, I think, which is that almost all psychological hypotheses are true. That is in the sense that, you know, directionally if you have a hypothesis that a really causes me that it's not true that causes the opposite be maybe a just has very little effect. But hypotheses are true mostly except mostly they're very weak. They're much weaker than you think when you are having images of. So the reason I'm excited about that is that I recently heard about uh huh Some some friends of mine who Uh they essentially funded 53 studies of behavioral change by 20 different teams of people with a very precise objective of changing the number of times that people go to the gym. But you know, and And the success rate was zero. Not one of the 53 studies work. Now, what's interesting about that is those are the best people in the field and they have no idea what's going on. So they are not calibrated. They think that it's going to be powerful because they can imagine it but actually just weak because you're focusing on on your manipulation and it feels powerful to you. There's a thing that I've written about that's called the focusing illusion that is that when you think about something, it looks very important, more important than it really </s>
<s>[INST] I'm actually quite surprised. I didn't know that it was born out of desire to implement our own ends and L C M's. It was that's fascinating. So you were actually one of the first people to really try to attempt to get the major architecture together. And it's also interesting that made me realize that that was a design decision at all is defining the model and code. Just I'm putting myself in your shoes whether the M O especially cafe was the most popular, [/INST] it was the most popular by far if I was </s><s>[INST] if I were Yeah, it I didn't like the whole thing but it makes more sense that you will put in a configuration file of the definition of a model. That's an interesting, gutsy move to stick with defining it in code just if you look [/INST] Back all the libraries were doing it as well. But it was definitely the more niche option. Yeah, Okay, Keras and then there are already scared us in March 2015 and it got you just very much from the start. So the deep learning community is very small at the time. Lots of people were starting to be interested in the SCM. So it was going to release it at the right time because it was offering an easy to use the same implementation exactly at the time where lots of your started to be intrigued by the capabilities of our linen uh on S one L. P. So it grew from there then I joined Google about six months later and that was actually completely unrelated to Cara's who actually joined research team working on image classification, mostly like computer vision. So I was doing computer vision research at google initially and immediately when I joined google, I was exposed to the early internal version of tensorflow and the way it appeared to me at the time and it was definitely the way it was at the time is that this was an improved version of piano. So I immediately knew I had to import keras to this new 10th of the thing and I was actually very busy as a nuclear as a new googler. Uh so I had not time to work on that, but then in november I think it was november 2015 tensorflow got released and it was kind of like my, my wake up call that hey, I had to actually go and make it happen. So in december I ported Caras to run onto offensive floor, but it was not exactly what it was more like a re factoring, where I was abstracting away all the back end functionality into one module so that the same code base could run on top of Metropole, back ends. Right? So on top of tensorflow or theano and for the next year Piano, you know, stayed as the default option. It was, you know, it was easier to use somewhat less biggie, it was much faster, especially when it came to our onions, but eventually, you know, tensorflow overtook it, right, </s><s>[INST] and doesn't flow the early tensorflow, a similar architectural decisions as Piano. So what is there was a natural, as a natural transition? [/INST] Absolutely. So </s><s>[INST] what I mean that still carries is a side almost fun project. [/INST] Right. Yeah, so it was not my job assignment was not, I was doing it on the side that so um and even though it grew to have, you know, a lot of fuses for deploying library at the time, like throughout 2016, but I wasn't doing it as my main job, so things started changing in, I think it must have been maybe october 2016, so one year later, so Rashad who has the lead intensive flaw, basically showed up one day in our building uh what I was doing like, so I was doing research and things like, so I did a lot of computer vision research, also collaborations with christians getting and deplaning for theory improving. It was some a really interesting research topic. And so Russia were saying, hey um we saw keras we like it, we saw that you had google, why don't you come over for like a quarter and, and and work with us and I was like, yeah, that sounds like a great opportunity, let's do it. And so I started working on integrating the Cara cpr into tensorflow more tightly. Um, so what ford up is a sort of like temporary tensorflow only version of keras that was in a tense for that country, bob for a while and finally moved to dance through core. And you know, I've never actually gotten back to my old team doing research. Well, </s><s>[INST] it's kind of funny that somebody like you who dreams of or at least sees the power of ai systems, that reason and they're improving, we'll talk about, has also created a system that makes the most basic kind of lego building that is deep learning, super accessible, super easy, so beautifully. So it's a, it's a funny irony that you're, there's both, you're responsible for both things, but uh, so tensorflow two point oh, it's kind of, there's a sprint, I don't know how long it will take, but there's a sprint towards the finish. What do you look, what are you working on these days? What are you excited about? What are you excited about in two point? Oh, eager execution, there's so many things that just make it a lot easier to work. What are you excited about and what's also really hard, what are the problems you have to kind of solve? [/INST] So I've spent the past year and a half working on tens of the two, it's been a long drawn here, I'm actually extremely excited about it, I think it's a great product. It's a delightful product, competitors for one, we met a huge progress. So on the correct side, what I'm really excited about is that, so, you know, previously chaos has been this very easy to use high level interface to do the planning. But if you wanted to, you know, uh, if you wanted a lot of flexibility, the keras framework, you know, was probably not the optimal way to do things compared to just writing everything from scratch. So in some way the framework was getting in the way and in terms of flow too, you don't have this at all actually, you have the usability of the high level interface, but you have the flexibility of this lower level interface and you have the spectrum of workflows where you can get more or less usability and flexibility tradeoffs depending on your needs, right? You can write everything from scratch and you get a lot of help doing so by, you know, sub classing models and writing because some train loops using eager execution, it's very flexible, it's very easy to the bug is very powerful, but all of these integrates seamlessly with higher level features up to, you know, the classic chaos workflows which are very psychically unlike and and uh, you know, ideal for data scientists, machine learning engineer type of profile. So now you can have the same framework offering the same set of apis that enable a spectrum of workflows to more or less durable, more or less high level that are suitable for profiles ranging from researchers to data scientists and everything in between. </s>
<s>[INST] Is that how you see problems yourself like that? That's actually an interesting point when you first are inspired by a certain idea that you maybe want to teach or visualize or just exploring your own. I'm sure you're captured by some possibility of magic of it. Do you read the work of others? Like do you go through the proof? Do you try to rediscover everything yourself? [/INST] So, um I think the things that I've learned best and have the deepest ownership of are the ones that have some element of rediscovery. The problem is that really slows you down and this is for my, for my part it's actually a big fault, like this is part of why I'm I'm not an active researcher, I'm not like at the depth of the field, a lot of other people are the stuff that I do learn. I try to learn it really well. Um but other times you do need to get through it at a certain pace, you do need to get to a point of a problem you're trying to solve. So obviously you need to be well equipped to read things uh without that reinvention component and see how others have done it, but I think if you choose a few core building blocks along the way and you say, I'm really going to try to approach this um before I see how this person went at it, I'm really going to try to approach it for myself, no matter what, you gain all sorts of in articulate herbal intuitions about that topic, which aren't going to be there. If you simply go through the proof, for example, you're going to be trying to come up with counter examples, you're going to try to come up with intuitive examples, all sorts of things where you're populating your brain with data and the ones that you come up with are likely to be different than the one that the text comes up with and that lends it a different angle. So that aspect also slowed Feinman down in a lot of respects. I think there was a period when like, the rest of physics was running away from him. Um but insofar as got it got him to where he was, uh I kind of resonate with that. I just I would I would be nowhere near because I'm not like him at all, but it's like a uh state to aspire to. </s><s>[INST] You know, just uh to look at a small point you made that you're not quote unquote active researcher. Do you hear swimming often and reasonably good depth about a lot of topics. Do you sometimes want to like dive deep? It's a certain moment and say like because you probably built up a hell of an amazing intuition about what is and isn't true within these worlds, do you ever want to just dive in and see if you can discover something new? [/INST] Yeah, I think one of my biggest regrets from undergrad is not having built better relationships with the professors I had there and I think a big part of success and research is that element of mentorship and people giving you the kind of scaffolding problems to carry along for my own like goals right now, I feel like um I'm pretty good at exposing math to others and like want to continue doing that for my personal learning. I are you familiar with the hedgehog Fox dynamic? I think this was either the ancient Greeks came up with it or it was pretended to be something drawn from the ancient Greeks that I don't know who to point it to, but they probably Mark Twain, it is that you've got two types of people are especially two types of researchers, there's the fox that knows many different things and then the hedgehog that knows one thing very deeply so like von neumann would have been the Fox, see someone who knows many different things, just very foundational. A lot of different fields. Einstein would have been more of a hedgehog thinking really deeply about one particular thing and both are very necessary for making progress. So between those two, I would definitely see myself like the fox where I'll try to get my paws and like a whole bunch of different things and at the moment I just think, I don't know enough of anything to make a significant contribution to any of them. But I do see value in um like having a decently deep understanding of a wide variety of things. Like most people who know computer science really deeply don't necessarily know physics very deeply, or many of the aspects like different fields and math, even let's say you have like an analytic number theory versus an algebraic number theory. Like these two things end up being related to very different fields, like some of them More complex analysis, some of them more like algebraic geometry. And then when you just go out so far as to take those adjacent fields, place one PhD student into a seminar of another ones. They don't understand what the other ones saying at all. Like you take the complex analysis specialist inside the algebraic geometry seminar, they're as lost as you or I would be. But I think going around and trying to have some sense of what this big picture is, certainly has personal value for me. I don't know if I would ever make like, new contributions in those fields, but I do think I could make new X positional contributions where there's kind of a notion of uh things that are known, but haven't been explained very well. </s>
<s>[INST] which is very important. But there's also something about mechanism that creates culture. So giving power to like a young student, ambitious student to have a tremendous impact on the progress of nuclear fusion creates a culture that actually makes progress more aggressively. Like you said, when seven nations collaborate, it gives more incentive to the bureaucracy to slow things down, to kind of have, let's first have a discussion and certainly don't give voice to the young, ambitious minds that are really pushing stuff forward. And there's something about like the private sector that rewards, encourages, inspires young minds to say in the most beautiful of ways, FU to the, to the boss, to say like, we'll make it faster, we'll make it simpler, we'll make it better, [/INST] we'll make it cheaper. To the boss. And sometimes that brashness doesn't bear out. That's an aspect that you just take a different risk profile as well too. But you're right. It's this, you know, of the, I mean, it was interesting, our own trajectory at the fusion center was like, we were pushed into this place by necessity as well too, because I told you we have, and we had operated for a long time, a Tokamak on the MIT campus, achieve these world records like a hundred million degree plasma and stuff. It's like, wow, this is fantastic. But, you know, somewhat ironically, I have to say is that, it was like, oh, but we're not, this isn't the future of fusion anymore. Like we're not, we're just gonna stop with small projects cause it's too small, right? So we should need, we need to really move on to these much bigger projects, cause that's really the future of fusion. And so it was defunded. And this basically put at risk, like we were going to essentially lose MIT in the ecosystem, really a fusion, both from the research, but also clearly important from the educational part of it. So we, you know, we pushed back against this, we got a lifeline, we were able to go, and it was in this, it was in this time scale that we basically came up with this idea. It's like, we should do this. And in the end, it was all of those, the people who were in the C level of the company were all literally students who got caught in that. They were PhD students at the time. So you talk about enabling another generation, it's like, yeah, there you go, right? </s><s>[INST] So, part gave a lifeline, a lifeline, gave fuel to the Fuzion at MIT, [/INST] that it continued. But a lifeline. A lifeline, gave fuel to the, the Fuzion at MIT that it continued. But it's way more than that. It wasn't just about like surviving for the sake of surviving, it was like, in the end for me, it became like this... I remember the moment, when you talk about these moments as a scientist. And we were just like, we were working so hard about figuring out like does this really with this really work like in his... it's complex. Like does the magnet work does the interaction with the plasma work? Does all these things work and it was just a grind push push push push and I remember the moment cuz I was sitting in my office and Brooklyn and there was just like I read like and I was in I don't know whatever the 20th or 40th slide or something into it and it was sort of that moment like it just came together and I like I got I couldn't even sit down, cause all it was just like, my wife was like, why are you walking around the apartment like this? Like I just couldn't, she, I said, it's going to work. Like, it's going to work, like holy. That moment of realization is like, kind of amazing. But it also brings the responsibility of making it work. </s><s>[INST] Yeah, how do you make it work? So you mean like that magic realization that you can have this, uh, this modern, uh, Madden technology and you can actually, like why do we need to work with either we can do it [/INST] here? Yeah, but it's interesting that Eater is, um, that one, one of, one of the reasons that like, that we started with a group of six of us at MIT and then once we got some funding through the, through the establishment of the company, it became a slightly larger, but in the end we had a rather small team. Like this was like a team of, you know, order of like 20 to 25 people design Spark in like a, like about two years, right? How does that happen? Well, we're clever, but you have to give Eater it's due here as well too. That again, this is an aspect always of the bootstrap up. Like I go back to the human genome project. So modern day genomics would not be possible without the underlying basis that came from setting that up. It had to be there. It had to be curiosity driven. Public program is the same with Eater, but we, because we had the tools that were there to understand Eater, we also had the tools to understand Spark. So we, we parlayed those in an extremely powerful way to be able to tell us about what was going to happen. So these things are never simple, right? It's like people look at this, go, oh, this means we should like, should we really have a public based program about fusion or should we have it all in the private? It's like, no, the answer is neither way, because in all these complex technologies, you have to keep pushing on all the fronts to actually get it there. </s>
<s>[INST] mean I got to push back on the those are just words. I mean I disagree with you. The the question points to a direction. The answer might be able to be more precise than the question because because just as you're saying there there's uh that we could be discovering certain characteristics and patterns that are associated with a certain type of matter microscopically speaking and that that we can then be able to post facto say this is let's assign the words life, this [/INST] kind of matter. I agree with that completely. That that's what that's uh but that's so it's not a disagreement. It's very frequent in physics that korean science that uh words that are in common use gets get refined and reprocessed into scientific terms that's happened for things like force and energy. Uh and so we're in a way we we find out what the useful definition is uh or symmetry for instance. And the common usage may be quite different from the scientific usage, but the scientific usage is special and takes on a life of its own and we find out what the useful version of it is, uh what the fruitful version of it is. So I do think so in that spirit, I think if we uh can identify states of matter or linked states of matter that can carry on processes of self reproduction and development uh and information processing, we should say we might be tempted to classify those as lang's as life. </s><s>[INST] Can I ask you about the craziest one which is uh the one we know maybe least about, which is consciousness. Is it possible that there are certain kinds of matter would be able to classify as um conscious meaning like? So there's uh the pants, I guessed right with the philosophers who kind of try to imply that all matter has some degree of consciousness and you can almost construct like a physics of consciousness. Do you? Um again, we're in such early days of this, but nevertheless it seems useful to talk about it. Is there some sense from a physics perspective to make sense of consciousness. [/INST] Is there? Well, again, consciousness is uh imprecise a very imprecise word and loaded with connotations that I think we should we don't want to start a scientific analysis that I don't think. Uh it's often been important in science to start with simple cases and work up uh consciousness, I think what most people think of when you talk about consciousness is okay, I'm what am I doing in the world? This is my experience of a rich experience, rich inner life and experience and where is that in the equations? And I think that's a great question, a great, great question. And actually, I think I'm gearing up to spend part of the, I mean, to try to address that in coming years. one </s><s>[INST] version of asking that question, just as you said now is what is the simplest formulation of that to study? I think I think [/INST] I'm much more comfortable with the idea of studying self awareness as opposed to consciousness because that that sort of gets rid of the mystical aura of the thing. And self awareness is uh in simple, you know, the uh I think uh contiguous at least with ideas about feedback. So if you have a system that looks at its own state and responds to it, that's the kind of self awareness, uh and more sophisticated versions could be like in information processing things, computers that look into their own internal state and do something about it. And I think that could also be done in neural nets, this is recurrent neural nets which are hard to understand and kind of a frontier that the uh so I think understanding those and gradually building up a kind of profound ability to unto uh conceptualize different levels of self awareness. What do you have to not know and what do you have to know? And when do you know that you don't know it or when do you know, What do you think? You know that you don't really know? And these uh I think uh clarifying those issues when we clarify those issues and get a rich theory around uh self awareness, I think the that will illuminate the questions about consciousness in a way that, you know, scratching your chin and talking about quality a and blah blah blah blah is never going to do. Well, </s><s>[INST] I also have a different approach to the whole thing. So there's from robotics perspective, you can engineer things that exhibit yes qualities of consciousness without understanding? Well, well the how things work and from that perspective you uh it's like a backdoor like enter through the psychology door precisely. [/INST] I think, yeah, I think </s><s>[INST] we're on we're on the [/INST] same wavelength here. I think that and let me just add one comment which is uh I think we should try to understand consciousness as we experience it uh uh as in evolutionary terms and ask ourselves why </s><s>[INST] why does it happen? This thing seems useful? Why is it useful? Why is it [/INST] useful? Uh We've got a conscious I watch here, interesting quest. Thank you Siri Okay, uh get back, I'll get back to you later. Uh And I think what we're gonna I'm morally certain that what's going to emerge from analyzing recurrent neural nets and uh robotic design and advanced computer design. Is that having this kind of looking at the internal state. Mhm. In a structured way that doesn't look at everything this guy has encapsulated, looks at highly processed information is very selective and makes choices without knowing how they're made. Is that there will also be an unconscious. I think that that is going to be turned out to be really essential to doing efficient information processing. And that's why it evolved because it's it's helpful and uh because brains come at a high cost. Yeah there has to be a good wife and there's a reason. Yeah they're rare in evolution. Uh And big brains are rare in evolution and they come at a big cost. You mean if you you they have high metabolic demands. Uh they require very active lifestyle. Warm bloodedness uh and take away from the ability to support metabolism of digestion. And so so it's it's uh it comes at a high cost. It has to it has to pay back. </s>
<s>[INST] I do ask myself of that like because I'm more in the tax base of constructing systems that prevent me from being corrupt because right now I'm all about love and all about those kinds of things, but I wonder you said like it just reveals the darkness. The problem is we might not be aware of our own darkness. I have the same feeling about money actually. I've been avoiding thinking about money. Like basically constructing my moral system, my moral compass around money, It's like the moment I feel a little too happy, but about the idea of owning some cool shiny thing. I started to think, okay, I'm not going to own that shiny thing because I'm afraid of the slippery slope of it. You ever think about that kind of stuff? Yeah, [/INST] the funny thing about our capitalist system is it's uh, it's um, it puts sort of profit motive above beauty. And you notice when you see certain cities, especially in the old days where like buildings used to be beautiful and uh now they're just like boxes, they throw a kid up and it's just for all profit margin. It's um, it's the illusion of permanence that, you know, it's like, oh, let me get as much money as they can be. Like, yeah, you know, my dad used to say, you know everyone, it's a cliche, but you can't take it with you. So it's kind of, it's comical to me that we're here trying to get this infinite amount like that where it's like Sisyphus we're all trying to climb this hill, but I mean the rock's gonna fall on us. So I think that's a healthy outlook. Yeah, my dad always used to say before he passed, you know, he would say, you can't, you have to survive, not only physically, but we have to survive emotionally. I think a lot of people forget about the emotional part of survival. You have to survive emotionally and humor and and and understanding reality in its objective context helps with that accepting reality as this ephemeral uh thing that urine is really just a part of, but not as significant as your ego wants you to believe is that is a start. That's a good foundation for surviving emotionally. </s><s>[INST] What's that mean? Surviving emotionally? Like [/INST] what's an ideal </s><s>[INST] life look like for you? You can't you [/INST] can't take things too seriously. You can't because they're ephemeral, they're not permanent. Nothing is permanent. Your bank accounts are permanent. Problems aren't permanent. Uh, nothing's permanent. Your abilities aren't permanent. Um Your memory is not permanent. You're you're you're getting hard is not permitted to curse on this or just go out there. You </s><s>[INST] can curse to your heart's content. Yeah. [/INST] Gender's not even permanent. More. I think I'm gonna I'm gonna change maybe and live my second half as another gender just to have on board with this gender. So it's like nothing is permanent. And so accepting that emotionally uh, is a good start to being more flexible. You gotta be flexible. Like my dad used to say anything to stiff snaps. You gotta, you know, it's a cliche. And people have said a bunch of different ways. But Bruce lee is right, man, be water be water. </s><s>[INST] Yeah. Makowski has this quote about love. That love is a fog that phase with the first light of reality. So he's a romantic, that guy. Uh but that even love is the thing that just doesn't last very long. Um you know, some people will disagree with that. Maybe morphs like like like water. It changes right? It might not be, might not be because he's mostly just loved like prostitutes I think. So it was kind of love, [/INST] no demand, no responsibilities. </s><s>[INST] Financial transaction. Yeah. Uh thermal has ever, you mentioned your dad, he passed away uh a year and a half ago. What did you learn from him? [/INST] I love my dad. My dad, I would say my dad was my, my hero. He was just, my dad really embodied those values and I think um for better or worse, it's made me who I am. He's he uh my dad was, was a painter, he was a lawyer. He was uh, he was, you know, a lieutenant in the military new yorker, new yorker born and bred Brooklyn. His dad, his dad, you know, surprise owned a diner. So that's, that's sort of the greek passport. That's the immigration passport for Greeks into America. And yeah, my dad played football. He just, my dad did what he wanted. He lived as he wanted at all costs and I think I got that from him for better or worse. I think it's hurt me in my pursuits. Uh, if you consider money and fame uh to be paramount. You know, I've always done what I wanted if I stopped wanting to do it, I just stopped doing it. I think I got that from my dad. So maybe for better or worse, that's what I learned from him. But that's a real currency. You know, feeling like you're in love with what you're doing when you're doing it. Maybe perhaps that's worth more than money. I don't know. You miss him. Yeah, every day. Every day. But I'm happy that uh He he got 91 years. It's very rare. I mean he smoked for 60 years. Talk about like a guy who was an outlier. He smoked like 60 years like packs. I mean, and he didn't die from that. He died. He had a prostate cancer, which is the way men should go. Your Dick should give out. It should start from the Dick. I mean we focus so much of our life on the Dick. That that's the way that's a successful life and that's why every man eventually gets prostate cancer because that is the universe's way is saying like the thing you focused on the most is you put the most energy into is the thing that's spent and it's going to your, your rotting is gonna start there. So that's a successful life and it just spread all over his body and he slowly died. I was with him when he died. And that meant a lot to me because me and my brother weren't talking at the time because we're Greeks. Uh we're talking again. But that's how it is. You've </s>
<s>[INST] So one of the magical things that perhaps makes him this earth quite unique is that it's home to conscious beings. So you mentioned consciousness perhaps is a small aside because we didn't really get specific to what, how we might do the alignment. Like you said, it's just a really important research problem. But do you think engineering consciousness into AI systems, this is a possibility. Is something that we might one day do or is [/INST] there something </s><s>[INST] fundamental to consciousness that is uh is there something about consciousness that is fundamental to humans and humans only? [/INST] I think it's possible. I think both consciousness and intelligence are information processing, certain types of information processing and that fundamentally it doesn't matter whether the information is processed by carbon atoms in the neurons and brains or by silicon atoms and so on in our technology. Yeah, some people disagree. This is what I think is a physicist and I uh </s><s>[INST] that consciousness is the same kind of you said consciousness is information processing, so meaning. You know, I think you had a quote or something like it's information ah knowing itself, that kind [/INST] of thing. I think consciousness, yeah. Is the way information feels when it's being processed, was people that makes ways we don't know exactly what those complex ways are. It's clear that most of the information processing in our brains does not create an experience, we're not even aware of it, right? Like for example, you're not aware of your heartbeat regulation right now, even though it's clearly being done by your body, right? It's just kind of doing its own thing when you go jogging. There's a lot of complicated stuff about how you put your foot down. We know it's hard. That's why robots used to fall over so much. But you're mostly unaware about it. Your brain just your ceo consciousness module. Just send an email. Hey, you know, I want to keep drawing along this path. The rest is on autopilot, right? Uh so most of it is not conscious, but somehow there are some of the information processing which is, we don't know what what exactly. I I think this is a science problem that I hope one day we'll have some equation for something. So we can be able to build a consciousness detector and say, yeah, here there is some consciousness here. There's not, oh don't boil that lobster because it's feeling pain or it's okay because it's not feeling pain right now, we treat this as sort of just metaphysics. Um but it will be very useful in emergency rooms to know if a patient has locked in syndrome and is conscious or if they are actually just out and in the future if you build a very, very intelligent helper robot to take care of you. You know, I think you'd like to know if you should feel guilty about shutting it down or or if it's just like a zombie going through the motions like a fancy tape recorder, right? And and once we can make progress on the science of consciousness and figure out what is conscious and what isn't, then we assuming we want to create positive experiences and not suffering will probably choose to build some machines that are deliberately unconscious that do you know, incredibly boring, repetitive jobs in a iron mined somewhere or whatever and maybe we'll cruise choose to create helper robots for the elderly that are conscious so so that people don't just feel creeped out that you know, the robot is just faking it when it acts like it's sad or happy. Okay. Said </s><s>[INST] elderly, I think everybody gets pretty deeply lonely in this world. And so there's a place I think for everybody to have a connection with conscious beings, whether they're human or otherwise, [/INST] but I know for sure that I would, if I had a robot, if I was going to develop any kind of personal emotional connection with it, I would be very creeped out if I knew it in intellectual level that the whole thing was just a fraud, you know, today you can buy little talking doll for a kid which will say things and the little child will often think that this is actually conscious and even real secrets to it that then go on the internet with lots of the creepy repercussions, you know, I would not want to be just hacked and tricked like this. If I was going to be developing real emotional connections with the robot, I would want to know that this is actually real, it's acting conscious, acting happy because it actually feels it and I think this is not sci fi, I think </s><s>[INST] it's possible to measure to come up with tools and they have to understand the science of consciousness you're saying is we'll be able to come up with tools that can measure consciousness and definitively say like this thing is experiencing the things it says, it's [/INST] experiencing kind of by definition, if it is a physical phenomena, information processing then and we know that some information processing is conscious and some isn't well then there is something there to be discovered with the methods of science Julia Tony has stuck his neck out the farthest and written down some equations for a theory. Maybe that's right, Maybe it's wrong, we certainly don't know. But I applaud that kind of efforts to sort of take this, say this, say this is not just something that philosophers can have beer and muse about, but something we can measure, we can study and coming being that back to us. I think what we would probably choose to do, as I said, is if we cannot figure this out, choose to make to be quite mindful about what sort of consciousness, if any, we put in different machines that we have, we and certainly not, we wouldn't want to make me should not be making much machines that suffer without us even knowing it, right? And if at any point someone decides to upload themselves like Ray Kurzweil wants to do, I don't know if you had him on your show, we agreed. </s>
<s>[INST] the local resident hometown resident, mr Elon musk, because anything to do with it, I do, I do tend to think you're absolutely right with all this political bickering. We shouldn't forget that what this age will be remembered by the incredible levels of innovation. I do, I do think the biotech stuff worries me more than anything because it feels like there's a lot of weapons that could be yet to be developed in that space. But I tend to believe that I'm excited about by two avenues. One is artificial intelligence, the kind of, the kind of systems will create in this digital space that you mentioned you were moving to and then the other, of course this could be the product of the Cold War. But I'm super excited by space exploration. Sure, there's a magic tour to humans beings [/INST] And we're getting back to it. I mean, we we were enthralled with it in the 50s and 60s when it was a cold war competition and then after the 70s we sort of gave up on it. And thanks to Elon musk and others were coming back to this issue and I think there's so much to be gained from the power of exploration. </s><s>[INST] Is there books or movies in your life long ago recently that had a big impact on you? Yes, this is something you [/INST] yes. Um, you know, my favorite novel, I always tell people this. I love reading novels, I'm a historian. Uh, and I think the historian and the novelist are actually, and the technology innovator are all actually one and the same. We're all storytellers. Storytellers and I met were all in the imagination space. And um, you know, I'm trying to imagine the world of the past to inform us in the present for the future. So one of my favorite novels that I read actually when I was in graduate school is Thomas Mann's Boudin Brooks and it's the story of a family in Lubeck in northern Germany living through the 19th century and the rise and fall of family cycles of life. Many things we've talked about in the last couple of hours cycles of life, um challenges of adjusting to the world around you. And it's just a very moving reflection on the limits of human agency and how we we all have to understand the circumstances were in and adjust to them. And there's triumph and tragedy in that it's a wonderful novel. It used to be a kind of canonical work, it's sort of fallen out now. It's a big, big novel. But uh, I'm very moved by that I'm very moved by told stories. Warren piece I assigned that every year to my students. That's a big, big book. But what tolstoy challenges is he challenges the notion that a napoleon can rule the world and we're all a little napoleons, right? We're all sort of thinking that we're going to do that. And he reminds us how much his contingency circumstance, it doesn't mean we don't have some control. </s><s>[INST] You've spoke to me a little bit of Russian. Where does that come from? So you're, you're appreciate ship tolstoy, but also your ability to speak a bit of Russian. [/INST] Where is that? Is that? So I speak in addition to english, I speak uh, reasonably well, depending on how much vodka I've had Russian and french and german. Um, I learned those, uh, for research purposes, I learned french actually, when I was in high school, Russian, when I was in college german, when I was in graduate school. Now I do have family on my mother's side. That's a Russian, jewish extraction. Um, but they were Yiddish speakers by the time, you know, I met them by the time they had gone through Germany and come to the United States have really gone through Poland and the United States, they were Yiddish speakers. So there's no one really in my family who speaks Russian, but I do feel a connection there, at least a long range personal connection. </s><s>[INST] Is there something to be said about the language and your ability to imagine history sort of when you study these different countries, your ability to imagine what it was like to be um a part of that culture part of that time? [/INST] Yes, language is crucial to understanding of culture and even if you learn the languages I have learning Russian and german and french, it's still not the same as also being a native speaker either as as you know. Um but I think language tells you a lot about mannerism about assumptions, the very fact that english doesn't have a formal you, but Russian has a formally right versus three, right, german has a formal Uz versus D. Right? So the fact that english doesn't have a formal, you tells you something about americans, right? That's just one example. Uh the fact that um you know that Germans have such a wider vocabulary for certain scientific concepts, then we have an english tells you something about the culture, right? Language is an artifact of the culture, The culture makes the language, </s>
<s>[INST] But is there some aspect of belief in the magic of this hand manifests quality of play. [/INST] So here's the thing, it's, you know, poker players, some have said it's it's unlucky to be superstitious, but we're all a little bit superstitious A little bit, you know, and so I don't know, maybe it is a case where when I have 10, 7, I feel somehow energetically that you know, I'm more likely to catch something which may actually make me more apt to be aggressive and confident in the hand, but but you really shouldn't let yourself do that. Like you're supposed to fall in love with any specific hands. </s><s>[INST] Yeah, but you know, uncertainty is ruthless, you know, the fact that it's a game of statistics, it it can be too painful for the human psychology. So maybe you have to hold onto certain superstitions because you know, I mean there's there's a cold absurdity to the fact that you can play up, you can play extremely well and still lose. I mean the actually this year you've played the what is it 50 days of world series of poker and it seems like at least from the perspective of me looking at it through the Internet, it seems like there's a lot of hands that you are like 70, 30, 80, 20 all in hands that you just did not, we're not going your way that can sort of break you mentally. [/INST] Yeah. One of the hardest things, especially about playing cash games and tournaments are different. One of the most difficult things about, you know, being a tournament player is resilience because more often than not, like, so if there's a tournament with 1000 people to win the tournament, you have to get all of the chips. That means there's one winner and 999 losers. So it's very rare that you actually like win all the chips. So you're essentially at some point in every tournament you play gonna deal with like really bad luck and disappointment. And sometimes those streaks can have you question yourself and be introspective about, Okay, so I think I'm 47 now, I think I've gotten better as time went on between distinguishing, Okay, am I losing right now because of bad luck or is it fundamentally decisions I'm making are not very good. Right. And that's one of the hardest things for anyone who plays poker to get to write, why am I losing? Am I losing because of my opponents being better? I'm not playing well or am I losing just because of luck? And because there's so much variance in poker, a lot of players can be confused with on both sides of the coin one guys winning and he thinks he's great. He's really not wait till the cards break. Even as we say, you know, </s><s>[INST] I think there's a lot of parallels to life as well, you don't, if you get screwed over over and over, it's hard to know if you're doing something wrong or if it's just bad luck. [/INST] I think they did a study. I remember it was like a study, it was supposedly related to gambling, but it was mice and they put them in a little maze and they go down these three tubes and they go down this one tube and there'd be cheese, right? And then they go down again cheese three times in a row, there was cheese there, right the next time there was an electric shock, they're not cheese. The rat went, you know, the mouse went to get zapped, he got zapped, okay, came back, he kept going back to get zapped until he died. Like he kept going because he found cheese there, he has one there. So he continued to go chase that win despite it being, you know, now all of a sudden, not worthwhile until until he died and essentially what they said was that is essentially how they compared it to like, you know, the gambling brain and how people think about gambling, </s><s>[INST] you're chasing the winds, you learn too much, You sort of over generalize the lessons learned from the times you've won. [/INST] Yeah, like beginner's luck can be detrimental. If you, if you have some early luck and you believe that this is just the way it's supposed to be forever. You know, it can put you in a delusional state where you know, you, you feel like I'm, I'm just great, but no, you're not, you're just lucky in the beginning. </s><s>[INST] I actually played poker once in Vegas, it was a it wasn't a tournament, but it was a kind of tournament like style. I already forgot what it was, but what I do remember is I had four of a kind. So the last hand I've ever played in poker was I got a four of a kind and there was uh a couple of others with really strong hands, so everybody went all in and I think you get some kind of bonus for getting four of a kind. [/INST] Yeah, </s><s>[INST] so it's something like this, I apologize if I don't know the details, but just remember winning a lot of money and I walked away from the table. I said I'm not playing poker again, this is great. [/INST] Because </s><s>[INST] I started to feel like this is your, I started to think even though I haven't really played poker at all that I'm good and I was a really dangerous feeling and everybody was really mad for walking away from the table. [/INST] One of the other things that I think is interesting about poker too is good is relative, right? So you could be the seventh best player in the whole world, like literally seven best player, but if you're playing with the other six, you're the sucker, you are, you are like the worst player in the game, right? So like there's a lot of players, for example, like the dan Bilzerian of the world, right? He's not a top level player like you know, these guys you see on tv, but he probably makes more money than they do because he plays with people that are far below his skill level. So part of the, part of the skill of being a poker player is finding situations where you're profitable, you know, regardless of your skill </s>
<s>[INST] I understand, I understand this. I understand this. But yes, there will be more such rooms, which is a beautiful place to be in the world. I'm terrifying, but mostly beautiful. So that might make you and a handful of folks the most powerful humans on Earth. Do you worry that power might corrupt you? [/INST] And this is just- But yes, there will be, for sure. Look, I think you want decisions about this technology and certainly decisions about who is running this technology to become increasingly democratic over time. We haven't figured out quite how to do this, but part of the reason for deploying like this is to get the world to have time to adapt and to reflect and to think about this, to pass regulation for institutions to come up with new norms for the people working out together. Like that is a huge part of why we deploy, even though many of the AI safety people you referenced earlier think it's really bad. Even they acknowledge that this is like of some benefit and certainly, but I think any version of one person is in control of this is really bad. So trying to distribute the power? I don't have and I don't want like any like super voting power or any special, you know, no control of the board </s><s>[INST] or anything like that open AI. [/INST] But AGI, if created, has a lot of power. How do you think we're doing, like, honest, how do you think we're doing so far? Do you think our decisions are? Like, do you think we're making things not better or worse, </s><s>[INST] what can we do better? What are the things I really like because I know a lot of folks that open AI. I think it's really like, is the transparency, everything you're saying, which is like, failing publicly, writing papers, releasing different kinds of information about the safety concerns involved, and doing it out in the open is great. Because especially in contrast to some other companies that are not doing that, they're being more closed. [/INST] That said, you could be more open. </s><s>[INST] Do you think we should open source GPT for? My personal opinion, because I know people at OpenAI, [/INST] is no. </s><s>[INST] What is knowing the people at OpenAI have to do with it? Because I know they're good people. I know a lot of people. I know they're good human beings. From a perspective of people that don't know the human beings, there's a concern. There's a super powerful technology [/INST] in the hands of a few that's closed. It's closed in some sense, but we give more access to it. If this had just been Google's game, I feel it's very unlikely that anyone would have put this API out. There's PR risk with it. I get personal threats because of it all the time. I think most companies wouldn't have done this. So maybe we didn't go as open as people wanted, </s><s>[INST] but we've distributed it pretty broadly. You personally, in OpenAI's culture, is not so nervous about PR risk and all that kind of stuff. You're more nervous about the risk of the actual technology and you reveal that. So the nervousness that people have is because it's such early days of the technology is that you will close off over time because it's more and more powerful. My nervousness is you get attacked so much by fear-mongering, clickbait journalism. [/INST] You're like, why the hell do I need to deal with this? I think the clickbait journalism bothers you </s><s>[INST] more than it bothers me. [/INST] No, I'm a third-person bother. I appreciate that. I feel all right about it. Of all the things I lose sleepover, </s><s>[INST] it's not high on the list. Because it's important, there's a handful of companies, a handful of folks that are really pushing this forward. They're amazing folks that I don't want them [/INST] to become cynical about the rest of the world. I think people at OpenAI feel the weight of responsibility of what we're doing. And yeah, it would be nice if journalists were nicer to us and Twitter trolls give us more benefit of the doubt. But I think we have a lot of resolve in what we're doing and why and the importance of it. But I really would love, and I ask this of a lot of people, not just if cameras are rolling, any feedback you've got for how we can be doing better. We're in uncharted waters here. Talking to smart people is how we figure out </s><s>[INST] what to do better. How do you take feedback? Do you take feedback from Twitter also? [/INST] Because there's the sea, the waterfall. My Twitter is unreadable, so sometimes I do. I can take a sample, a cup out of the waterfall. But I mostly take it from conversations like this. </s><s>[INST] Speaking of feedback, somebody you know well, you worked together closely on some of the ideas behind OpenAI's Elon Musk. You have agreed on a lot of things. You've disagreed on some things. What have been some interesting things you've agreed [/INST] and disagreed on, speaking of fun debate on Twitter? I think we agree on the magnitude of the downside of AGI and the need to get not only safety right, but get to a world where people are much better off </s><s>[INST] because AGI exists than if AGI had never been built. [/INST] What do you disagree on? Elon is obviously attacking us some on Twitter right now on a few different vectors, and I have empathy because I believe he is understandably so really stressed about AGI safety. I'm sure there are some other motivations going on too, but that's definitely one of them. I saw this video of Elon a long time ago, talking about SpaceX, maybe he's on some news show, and a lot of early pioneers in space were really bashing SpaceX and maybe Elon too. And Elon, he was visibly very hurt by that and said, you know, those guys are heroes of mine, and I sucks, and I wish they would see how hard we're trying. I definitely grew up with Elon as a hero of mine. You know, despite him being a jerk on Twitter or whatever, I'm happy he exists in the world, but I wish he would do more to look at the hard work </s>
<s>[INST] Well me who loves working all the time. All vacations. Fortification. Alright so okay so that gives us a sense of of duration and we can maybe also talk about longer and longer and longer duration uh as well. What are the hardest aspects of this of living in space for Many days? For let's say 100 days, 200 days maybe there's a threshold when it gets really tough. What are what are some stupid little things or big things that are very difficult for human beings to go through. [/INST] One big thing and one little thing and there's two classic problems that we're trying to solve in the space industry. One is radiation, it's not as much of a problem for us right now on the international space station because we're still protected by part of Earth's magnetosphere. But as soon as you get further out into space and you don't have that protection once you leave the Van allen belt area of the Earth and the, you know, cocoon around the earth, we have really serious concerns about radiation. The effect on human health, long term, that's the big one, the small one. And I say it's small because it seems mundane, but it actually is really big in its own way is mental health and how to keep people happy and balanced. And you were alluding to some of the psychological challenges of having humans together on missions and especially as we try to scale the number of humans in orbit or in space. So that's another big challenge is how to keep people happy and balanced and cooperating. </s><s>[INST] That's not an issue on Earth at all [/INST] at all. Okay, </s><s>[INST] so we'll talk about each of those in a, in a bit more detail but [/INST] let </s><s>[INST] me continue on the chain of dumb questions. What about food? What's a good food source for food and space and what are some sort of standard go to meals menus [/INST] right now, your go to menu is going to be mostly freeze dried every so often Nasa will arrange for a fun stunt or fresh food to get up to station. So they did bake Doubletree cookies with Hilton a couple of years ago, as I recall, I think sometime before the pandemic. But there's work actually in our lab at MIT Maggie Coblentz, one of my staff researchers is looking at the future of fermentation. Everybody loves beer, right? Beer and wine and kimchi and miso. These foods that have just been, you know, really important to human cultures for eons because we love the umami and the better flavor in them. But it turns out they also have a good shelf life if done properly. And they also have additional health benefit for the microbiome for probiotics and probiotics. So we're trying to work with Nasa and convince them to be more open minded to fermented food for long duration deep space missions that we think is one of the future elements in addition to in situ growing your own food. </s><s>[INST] Okay. This is, this is essential for the space party. Is the space beer? [/INST] Yes. Is the fermented product? Yes. </s><s>[INST] Okay, cool. In terms of water, what's a good source of drinkable water? Like where do you get water? Do you have to always bring it on board with you? And is there a compressed efficient way of storing it? [/INST] So to steal a line from charlie Bolden, who's the former Administrator of Nasa? Uh This morning's freshwater? Is yesterday's coffee. So you think about what that means? You drank the coffee </s><s>[INST] yesterday [/INST] through the body as the recycling system and then you drink what you peed out as um you know, clarified refined fresh water the next day. That is one source of water. Another source of water in the near neighborhood of our solar system would be on the moon. So water ice deposits, there's also water on mars. This is one of the big things that's bringing people to want to develop infrastructure on the moon is once you've gotten out of the gravity well of earth, if you can find water on the moon and refine it, you can either make it into propellant or drinkable water for humans. And so that's really valuable as a potential gateway out into the rest of the solar system to be able to get propellant without always having to ship it up from earth. </s><s>[INST] So how much water is there on mars? [/INST] That's a great question. I do not know. We </s><s>[INST] don't know the water the [/INST] caps I suspect nasa from all of the satellite um studies that they've done on MArs have a decent idea of what the water deposits look like. But I don't know to what degree they have characterized those. I </s><s>[INST] really hope there's life for traces of previous life on MArs. [/INST] This is a special spot in my heart because I got to work on Sherlock, which is the Astrobiology experiment that's on MArs right now, searching for. What they would say in a very cautious way is signs of past habitability. They want to be careful not to get people overly excited and say we're searching for signs of life. They're searching to see if there would have been organics on the surface of mars or water in certain areas that would have allowed for life to flourish. And I really love this prospect. I do think within our lifetimes will get a better answer about finding life in our solar system if it's there. If not on mars maybe Europa one of the icy Worlds. </s><s>[INST] So you like the you like Astrobiology this is part of part of the it's not just about human biology it's also other extraterrestrial alien biology. [/INST] Search for life in the universe. </s><s>[INST] Okay that's scary you excite you. [/INST] It excites me profoundly. </s><s>[INST] There's other alien civilizations potentially very different than [/INST] I think there's got to be some humility there. And certainly from science fiction we have plenty of reasons to fear that outcome as well. But I do think as a scientist it would be profoundly exciting if we were to find life especially in the near neighborhood of our solar system right now we would expect it to be most likely microbial life. But we have a real serious challenge in astrobiology which is it may not even be carbon based life. And all of our detectors we only know to look for D. N. A. Or RNA. How would you even build a detector to look for silicon based life or different molecules than what we know to be the fundamental molecules for life. </s>
<s>[INST] So not, yeah. Let me push back because yes, so I agree with you, but let me push back on a subtle point because I like to draw a difference between hard work and meritocracy because as a person who works really hard, like I work crazy hard, but I've also worked with a lot of people that are just much better than me. So hard work does not equal skill, good, productive. I just want to kind of draw that distinction, but I agree with you. I don't think our society rewards directly hard work or even high skilled. There's many examples at least we can see [/INST] that it does not do so. So we have an unequal distribution of talent, of course. So if we lived in a society in which there was some level of acceptable inequality and it's a normative kind of the question of how much we would say is acceptable, right, and that inequality was based on this unequal distribution of talent, then I think that would be fine with me, right? That would actually be a meritocracy. What I see in the US is often, okay, so if you are a upper middle class or rich kid and you get a good education, K through 12, out of those people, there will be some that work extra hard and go on to do incredible things or are very successful. And there'll be other people that do not, right? And decide for whatever reason or go down a different path. And you could say maybe among that group of the upper middle class, there is a meritocracy, right? But they're actually given those opportunities to make their own decisions and to fail. Whereas many, many other people, the vast majority of American society, I would say 60 plus percent, don't really get those opportunities to make those choices to begin with. And I would aspire to the type of world at least as a first step in which our only inequalities are based on our unequal, innate kind of distributions of talent. </s><s>[INST] Yeah, I guess a lot of people worry that when you have a socialist in any degree central planning or perhaps a collective of workers, that it won't result in that kind of meritocracy that you're talking about. But you're saying that no, [/INST] it's possible to have that kind of meritocracy. Think about it this way. The workers themselves are incentivized and are shaped by market forces too, right? They're trying to respond to consumer needs and preferences. They're trying to expand market share. They're trying to make money. So it requires no kind of leap into these people are gonna be more altruistic or whatever else. Even on purely bourgeois terms, the same way you would maybe justify getting competitive capitalist firms. I think you could justify this system as long as you think that people elected management can perform just as well. I think based on the experiences of cooperatives, we've seen that they can. And then at the state level, state bureaucracies have their own sort of sets of incentives, but in most systems that already have extensive state bureaucracies, these people at high levels are appointed or elected. They're held to certain standards. At the national level, a national government wants to maintain the tax revenue that they need to pay for school services. So we already, I think have incentive structures that you could say that some people might just, I think disagree with the normative thing of like, why would people have to own their own means of production, control their workplaces or whatever else? Why do we need this level of equality? Can't we just get by with our existing system, but just like make things a little bit easier for capitalists to make money or then everyone will benefit or whatever else. I mean, that's a normative question. And my vision of socialism, there'll be plenty of multiple parties with different views and perspectives, trying to either push us deeper into more radical forms of socialism, or on the other hand to kind of roll back to more capitalist forms of government. So I think that again, you can't try to make up a perfect system and try to implement it. You have to do it as a process democratically and so on. </s><s>[INST] So just philosophically in your gut, you're more concerned about the innate equal value of human beings versus the efficiency of this wonderful mechanism that we call human civilization at producing cool stuff. Just like a gut, if we were sitting at a bar, that's where the gut feeling you come with. Of course, your mind is open, [/INST] but you want to protect the equal value of humans. So I don't wanna fight the hypothetical. So I'll say equality. I am concerned with equality, but I don't think the two are necessarily always in tension. But also when you think about all the great things that human beings have produced, often I think people today just look at the end outcome. Like we go to the pyramids and we'll marvel at the pyramids and the human achievement that it took to make it happen. But we won't stop to think about all the suffering that went into the making of that thing. So I think we kind of lean in the opposite direction where we marvel at our achievements, but we don't often think about the suffering or exploitation that went into certain human achievements. would love a society in which we could marvel at things and not have to worry about the exploitation that was involved because there was no exploitation or oppression involved. There was just human ingenuity and creativity and </s><s>[INST] collaboration. And to degree which you may disagree to the degree there's a tension between the two at least give equal weight to the consideration of the suffering and don't just marvel at the beauty of the [/INST] equations to the degree there is a tension between the two. What Stalin did actually too it's not just capitalist what Stalin did was he sacrificed whole generations because he thought that he was building something for the future for future Russians to to enjoy and for future people of the world to to enjoy and actually that analogy that I just gave about the pyramids was was written by Karl Kotsky the German socialist anti-Stalinist critic when he was complaining about US journalists and others going to Russia in the 1930s and marveling at all the new industries you know how are these people blind to the </s>
<s>[INST] Kind of breathing, coming to life for the first time. What does the pad look like? So there's a few interesting aspects of this. [/INST] What's up with the chopsticks and all of that? Yeah, so the launch pad is unique. I've never seen anything like it in the prior history of space flight. But it's a really simple launch stand. They basically have this almost looks like a stool, like a milking a cow stool thing, with a big giant. </s><s>[INST] Now I know you're from Iowa. [/INST] Yes, we all know what that stool looks like. We've all been sitting on that stool, milking a cow. With a giant hole in the middle, and that hole in the middle of that stool is where the rocket sits, and it sits on these launch clamps. And then next to it is the, so that's the orbital launch mount, and then next to it are the OLM some people will say, next to it is the orbital launch tower or the OLT. And that is not only integral to fueling up the upper stage, the upper stage has to have propellant lines run to it so that they can fill it with propellant and all that. But it also, they ended up making it so instead of having a big crane on site to stack the two on top of each other, they literally just use that tower as a crane. So the crane has these giant arms, lovingly called the chopsticks, or the whole system can be called Mechazilla. And that will grab onto, first it'll grab onto the booster, pick it up off of its transporter that transports it from the production site, lifts it up, puts it down onto the launch mount and then it will pick up the second stage or the upper stage Starship and plop it down on top of the booster and they did that for the first time last year. Actually I think it was like Valentine's last year it was the first time they used the chopsticks to stack it and now they're doing it quite frequently, but ultimately those chopsticks have to serve a second purpose. They're actually going to utilize If you say catch, it's not so much they're going to catch the booster with these chopsticks. It's not like it's a dad trying to catch a falling child. It's more that the booster and the Starship will someday land on those arms. They're more or less stationary. I'm sure there's some bit of adjustment that the arms will do, but more or less the rocket's going to propulsively land and get picked up by what's essentially two relatively small ball joints that hold the entire thing. It has to land very precisely on these mounts, then onto the launch mount. That's what's going to just place it back onto the stand </s><s>[INST] and allow it to be refueled and fly again. Fly again. [/INST] What's the idea of using the arms versus having a launch pad to land on? What's the benefit? You are basically removing the mass of what would be heavy landing legs, and you're putting kind of that landing infrastructure onto a ground system. You're not having to carry those landing legs into orbit. </s><s>[INST] It's also elevated off the ground. Is there some aspect to that where you don't have to [/INST] balance the thrust and all the... You can negate some of those, there's plume-plume interactions. There's the exhaust hitting concrete, and especially with a rocket this big, it's going to use three Raptor engines firing. If you have them firing really close to the ground, you're just going to absolutely destroy and crater the ground, and you're going to refurbish the ground and the landing pad every time, or have huge landing legs that are super long and tall to make it so it's elevated enough to not do that. Yeah, you're avoiding that whole mess by catching it high enough off the ground that you don't have to factor that in. </s><s>[INST] That's how many engines are involved in the landing part, is that three Raptor engines? [/INST] Well, we haven't actually... We haven't to date seen the exact landing sequence, so it might be something like at first, they might light up seven or something, or nine or something, some number to decelerate quickly without the same thing, and then shut it down to three or something for a little bit more granular control. Because unlike Falcon 9, Starship has enough engines and variability to actually... If it needed to hover to maybe more precisely align itself with the pad, it would have that capability. Especially having multiple engines. If you only have a single engine running, you can't really roll. Your roll axis, you can do pitch and yaw because the engine is like a rudder. It can move in two axes, so you can easily pitch and yaw of the vehicle. To actually induce roll along its vertical axis, you would either need auxiliary engines to roll it, or you'd need a pair of engines so they can be opposed and induce roll. By having two two or three running, they have all three axes of control that they would need, kind of like a broomstick, you know, and a bouncing broomstick on your hand. They can just move it over, and if they need to align it to those landing nubs, you know, on the landing arms and stuff like that, </s><s>[INST] then they can do that. Speaking of pitching yaw, the thing, so Starship flips on its belly flops, there's a interesting kind of maneuver on the way down to land. Can you describe that maneuver? [/INST] What's involved with that? Yeah, so this is definitely a first. I don't think anything's tried landing like this before, but the idea is when you're falling through the atmosphere, the atmosphere could actually do a lot of work for you. You know, you're moving quickly, something is falling from space, </s>
<s>[INST] So what do you think camping is thinking now? Was it, was it a mistake or [/INST] I'd like to know lex, I'd like you to be able to sit down with him across from this table here on your podcast and pose that same question him because we have no idea </s><s>[INST] there's a language barrier that's fascinating. By the way you, as a scholar of Stalin, do you think we'll ever break through the language barrier to china? Not ever, I apologize in the next few years because there is a gigantic cultural and language barrier between the west and the [/INST] china is a great civilization. China predates the United States by millennia, china's accomplishments are breathtaking, but china's also led by, let's be honest, a communist party monopoly, which engages in a lot of criminal behavior. Lex Tibet is Ukraine, Xinjiang is Ukraine Hong kong is Ukraine, let alone support for Putin, Ukraine. This is before we've even discussed Taiwan. And so now the Europeans are coming to see this and the americans are coming to understand this, that maybe trading with a regime like that and morally politically criminally Tibet Xinjiang Hong kong, How is that different from what Putin is doing in Ukraine? I'd be hard pressed to differentiate that ultimately, even though the analogies are not exact. And so the chinese, it's like that guy leon off the author of legality, the the great um memoir of the late soviet period, the end of the soviet union, you know that they they spend all this time and all these resources blackening our image, but we supply them with endless material to blacken our image. That's where she Jinping's regime is right now lex. And so they have a big dilemma on their side. It's a Western world and they've united the western world and and re awoken the rest and world to the fact that china is a threat to the values, the institutions and values of the West and that trade is not transforming china quite the opposite. We'll see if this endorse, maybe it doesn't endure. Maybe it's a fleeting moment. Maybe this is not an inflection point. Maybe the war in Ukraine ends more quickly than than we think and maybe like you said the chinese and the indians and the rest of them, the leaders there, they get their wish that it ends and the world moves on and forgets or says, let's try again to to resume our mutual understanding, our mutually beneficial trade and everything else. Maybe it's a passing phase we can't exclude that. I'm very poor at predicting the future. But the moment is not a good one for the chinese regime, let alone the fact that he's trying to impose An unprecedented in the modern era 3rd Term for himself as president in the fall at the next party congress becoming president for life, de facto a mao like figure. And he's now got to do that within this environment where he has damaged chinese grand strategy and damage the reputation of china and its relationships across the world. Maybe not permanently, but significantly in addition to the problems they have at home demography as you know, a middle income trap and then the regulatory insanity of chinese communist rule that we've seen with the tech companies that, you know, well, where they've destroyed all of that value with the blow up of their property sector because it was a massive bubble and that's still playing out. And this time it's the same meaning this time, it's not different when it comes to a property blowout. It has enormous effects on middle class balance sheets and their ability to to be to remain consumers and drive the economy, which is the model that they have to shift. So he's got a litany of challenges independent even of the fact that he cited with his pal Vladimir Putin and their bromance is costing china very, very significantly </s><s>[INST] if you close your eyes. [/INST] Yes, </s><s>[INST] And 100 years ago, 1922. And you think about the future, I wonder if you can hear the drums of war Predicting the 30s, predicting the Great Depression and the resentment that builds the economic resentment, the cultural resentment, the geopolitical resentment that builds at least the World [/INST] War Two. </s><s>[INST] It at least to me when I close my eyes, I can hear the drums of war that are still [/INST] ahead </s><s>[INST] of us. And it's possible that where there [/INST] 20 </s><s>[INST] 22 [/INST] will </s><s>[INST] Materialize in a similar way, as did 1922, [/INST] I have my eyes closed lex. </s><s>[INST] Do you hear anything? [/INST] And I sure hope that that's not what happens. But I'm looking in 1922, it's an epoch, I know well, and I don't see the future that unfolds. I would not have predicted it had I been alive then I see the war behind us. I see prosperity on the horizon. Yes, inflation in Germany and and some many other difficult issues, but there are more democracies now than there were before the war. And the old empires are gone and there's a cultural efflorescence and there's modernism in the arts and and there's women entering the public sphere. And there's all this fantastic new technology, like automobiles and I'm looking at the future from 1922. And and I'm not seeing the Great Depression and I'm not seeing World War Two and I'm not seeing the holocaust because I don't predict the future and nobody in 1922 could see that future, although I guess there were some clairvoyants who predicted it, but </s><s>[INST] but you're not one of them, [/INST] I'm not one of them. And but but this is what I know lex from studying history, What I know is stuff happens in other words, in other words, lex were watching Ukraine war right now and all of our attention is focused on that. And it's like the economists say in their textbooks, when their their powerful models are employed and there's this line that says all other factors held constant comma and then the model works and you get this really great result, it's very powerful predictor and analysis the model and and the whole game is all other factors held constant. So the Russia Ukraine war that we've been discussing and this could happen and that could happen. But you know what stuff could happen next. For example, the Israeli government could decide this summer that it's going to bomb Iran because no Israeli government will tolerate Iran acquiring a nuclear weapon. And since President trump exited unilaterally exited from the a multi power nuclear agreement, Iran is now much closer to the bomb than they were when they were still in when the United States was still in that agreement and you tell me the Israeli government that says sure it's fine, it's okay, Iran could get the bomb. And so maybe that happens and maybe that happens as early as this summer as Iran gets closer and closer and closer, maybe that guy in north Korea decides it's his time, just like his grandfather, Right in 1950 decided, you know, it's time, we're gonna quote, reunify, unquote the korean peninsula, maybe, I don't know, lex fill in the blank, something's gonna happen. It's not going to be what I predict, It's not going to be what I'm watching. It's gonna be obvious only after it happens. Not before. And then it's gonna upend the table and all of a sudden </s>
<s>[INST] Okay, so this okay, that makes a lot more sense. That's nice. So that you're trying to use sort of it's a probabilistic lee you're not, [/INST] you can't make a single particle collide with the single. So that's not an efficient way to do it. You'll be waiting a very long time to get anything. So </s><s>[INST] you're basically right to see, you're relying on probability to be that some fraction of them are going to collide and then, you know which it's a it's a swarm of the same kind of particle, [/INST] so it doesn't matter which ones hate each other. Exactly. I mean, that's not to say it's not hard. You've got a one of the challenges to make the collisions work is you have to squash these beams to very, very basic, their narrow where they are, the better because the higher chances of them colliding. If you think about two flocks of birds flying through each other, the birds are all far apart in the flocks, there's not much chance that they'll collide if they're all flying densely together and they're much more likely to collide with each other. So that's the sort of problem. And it's tuning those magnetic fields. Getting the family feels powerful after you squash the beams and focus them so that you get enough collisions. </s><s>[INST] That's super cool. Do you know how much software is involved here? I mean, it's sort of like um in the software world and it's fascinating. Uh this seems like it's a software is buggy and messy and so like you almost don't want to rely on software too much. Like if you do, it has to be like low level, like FORTRAN style programming. Do you know how much software is in the large Hadron collider. [/INST] I mean, it depends on which level a lot. I mean the whole thing is obviously computer controlled. So I mean, I don't know a huge amount about how the software for the actual accelerator works. Um but you know, I've been in the control center, so that's and there's this big control room, which is like a bit like a Nasa mission control with big banks, you know, desk where the engineers sit and they monitor the LHC because you obviously can't be in the tunnel when it's running, so everything's remote. Um I mean, one sort of anecdote about the sort of software side in 2000 and eight, when the LHC first switched on, they had this big launch event and then big press conference party to inaugurate the machine. And about 10 days after that, they were doing some tests and the dramatic event happened where a huge explosion basically took place in the tunnel that destroyed or damaged badly damaged about about half a kilometer of the machine. But the stories, the engineers are in the control room that day, they, one guy told me the story about, you know, basically all these screens they have in the control room started going red. So these alarms, like, you know, kind of software going off and then they assume that there's something wrong with the software because there's no way something this catastrophic could have could have happened. But I mean when I worked on, when I was a PhD student, one of my jobs was to help to maintain the software that's used to control the detector that we work on and that was, it is relatively robust. Not so you don't want it to be too fancy, you don't want to sort of fall over too easily. The more clever stuff comes when you're talking about analyzing the data and that's where they're sort of, you know, </s><s>[INST] are we jumping around too much? Do we finish with the standard model? We didn't we didn't we even started talking about quirks [/INST] we haven't talked about yet, We got to the messy zoo of </s><s>[INST] Particles. Let me uh let's go back there if it's okay, can you take us to the rest of the history of physics in the 20th [/INST] century? Sure, Okay, so 1960, you have this, you have these 100 or so particles. It's a bit like the periodic table all over again. So you've got like, like having 100 elements, it's sort of a bit like that and people try to start to try to impose some order. So, Murray gellman, his theoretical physicist America and from new york, he realizes that there are these symmetries in these particles that if you arrange them in certain ways they relate to each other. And he uses these symmetry principles to predict the existence of particles that haven't been discovered, which are then discovered in accelerators. So this starts to suggest there's not just random collections of crap, there's like, you know, actually some order to this underlying it A little bit later in 1960. Again, it's around the 1960s. Um He proposes along with another physicist called George zweig that these symmetries arise because just like the patterns in the periodic table arise because atoms are made of electrons and protons. That these patterns are due to the fact that these particles are made of smaller things and they are called quarks. So these are the particles are predicted from theory for a long time. No one really believes they're real. A lot of people think that there are kind of theoretical convenience that happen to fit the data, but there's no evidence, no one's ever seen a quark in any experiment. And lots of experiments done to try to find quarks to try to knock a quark out of her. So the idea of protons and neutrons are made of quarks, you should want to knock a quark out and see the quark. That never happens. And we still have never actually managed to do that. </s><s>[INST] We really [/INST] know. So the way, but the way that it's done in the end is this machine that's built in California at the stanford lab stanford linear accelerator, Which is essentially a gigantic three km long electron gun fires electrons almost speed of light at protons. And when you do these experiments, what you find is a very high energy, the electrons bounce off small hard objects inside the proton. So it's a bit like taking an X ray of the proton, you're firing these very light high energy particles and they're pinging off little things inside the proton that are like ball bearings if you like. So you actually that way they resolve that there are three things inside the proton which are quarks, The quarks that gell Mann and Zweig had predicted. So that's really the evidence that convinces people that these things are real. The fact that we've never seen one in an experiment directly, they're always stuck inside um other particles. And the reason for that is essential to do with the strong force. The strong force is the force that holds quarks together and it's so strong, it's impossible to actually liberate a quark. So if you try and pull a quark out of a proton, what actually ends up happening is that the you kind of create this that this spring like bond in the strong force, you imagine two quarks that are held together by a very powerful spring. You pull and pull and pull more and more energy gets stored in that bond, like stretching a spring and eventually the tension gets so great, the spring snaps and the energy in that bond gets turned into two new quarks that go on the broken ends. So you started with two quarks, you end up with four quarks. So you never actually get to take a clock out. You just end up making loads more quarks in the process. </s>
<s>[INST] Yeah, that's millions miles away besides physics. You also have poetry in your blood. So what has been your relationship to poetry? Music? What role did it play in your life? [/INST] Poetry a lot. But it is way later then then elementary school actually like music wise, you know, like all Teenagers, they're in love with music and it's just exactly the same now and 20 years ago and 30 years ago. Um, I would say at that time at that time we were all in love with one special group, which is beetles. Mm. And and what it was extremely later. It I wasn't 6th grade, 5th grade of the 60, 65, 66 and in soviet union beetles. They were forbidden. Believe me or not. It was absolutely strange but at the same time if something is forbidden, that's exactly what you laugh most. So I remember that for my big success in science, I was awarded. Who is going to the best of the best um, camps, pioneer camps, arctic in Crimea. And over there it was, it's international. So I met with, I lived together with a group people from friends because I was the only one kind of speaking fluently in french and uh, we just made trade. So we gave whatever we used to have and we got Beatles records. Beatles records. </s><s>[INST] That's the rebel and you're part of it. What about poetry? What when did you first I mean you've written a lot of culture. What poet? What maybe do you remember an early poem? You've written a bad one? [/INST] Good one. No, I started doing that late. So it was, I was in 7th grade I </s><s>[INST] think that's late writing poetry I thought [/INST] and writing poetry is a little bit related to when boys, they started looking at girls. It was a little bit different eyes. </s><s>[INST] We just love is somehow behind post even [/INST] not so much even love even just you know this imagination like uh, way far from reality is uh, it is romanticism. </s><s>[INST] Were you a serious poet or a funny pose because you have a lot of humor and with [/INST] that it's later. Yeah, but at that time I was extremely serious and extremely romantic which never ever after </s><s>[INST] that. But it's hard to imagine. [/INST] Yeah. But it is kind of a little bit like a childish romanticism or childish I mean you know that but but it was interesting enough that first poetry was actually almost immediately from my point. Very good. It's not like you know, you're doing something not good and then better and better and better. It's actually uh all the way opposite best stuff which I wrote. It was like 1/7 grade, well around more like eight and ninth grade. And I wrote a lot at that </s><s>[INST] time. Why do you think you were? So what does it mean? What does good poetry mean? That means it's not cheesy. It's beautifully worded and crafted and yes. And so where did that come from? Because most people, even great poets are terrible at first. So why why were you so clever quickly? Because most people know you as really clever? No, I mean Woodward's right. Very good words. So you're saying that was early on. You already had that. [/INST] Yes, I have no good answer. I just did. Comes from nowhere. Yeah, but my father insisted. Oh no, no, it was it was in circulation was it was actually to be honest. No, not so much connection. Uh but in Russian culture, romanticism? It is extremely important element. You know starting from 19th century romanticism. So just it was very popular. So either you are writing good poetry or bad poetry or you are an artist, you are like, you know, painting something. So, I have a lot of friends. They they were painting. </s><s>[INST] Do you remember a poetry? Do you remember a poem from that time that you've written by any chance? [/INST] Yeah, sure. I remember most of them by her. </s><s>[INST] Your mind, your mind reciting [/INST] uh, they're in the Russian, </s><s>[INST] Russian is good. As long as they're not in french [/INST] having french rolls. You want to me just to leave, </s><s>[INST] what do you think? What uh, what's comfortable? [/INST] You know, maybe I will read one poem, one poem which I like most from that period. And I'm not sure that I wrote something better after that. Well, it's a little bit cheesy. However, but not much. It's like a it's even not about girls, it's about music, </s><s>[INST] but still with a romantic, romanticized kind of with [/INST] very strong our medicine at was the result of me reading a book Para que Tenia que Tamara historia b china over capital Maestra. You're gonna chris laura. Actually, it's a story of a cat who found a book or like a notebook, but notebook. Mhm. Of people and he started reading about that and analyzing their life. So it's a life of people through the eyes of a very, very smart cat. So then I can read it in Russian. Right? I mean this poetry if you want, please, that would be great. Okay. Our abilities from Chrysler. Keep associated to Roswell? S koppel Mr. You gone Crazier budget plaque. It's the one you love us. Nobody has to be. This needs a french cafe global idea. And the woman noticed needs a little, I mean, the owner died in the mirror and cellist a pretty notice. Beattie snuck some keen only mirror share isn egret, what can you smoke? It's a real religion. Ou through the economic script coordinator. Don't, don't, I'm not sure. Ayala, paris smith, not Miriam. Senior it across the slush pile. See, Phyllis Gordon National Missouri chris lee. It was associated Roswell is koppel Mr again creates your bullet plaque. It's what? Leave us, </s><s>[INST] wow, that's good. [/INST] And it's like, uh, I would say that whatever I did later, it was, how </s>
<s>[INST] It's really important to say it's powerful enough to do training but in general just the incredible company that does both cloud and with the opposite of cloud. Offline computing systems, plug and play access to very powerful computation, specialized for machine learning. So you got all the Gpus you can possibly use. There you go. That's poetry. So it's good both for individual researchers and huge companies. [/INST] What </s><s>[INST] else can I say? You can check them out at lambda labs dot com slash lex. I just think it's great to support what they're doing for the machine learning community. Making it easy what they're doing for companies. They're interested in doing machine learning. Just making it easy. Making classy and sexy, love what they're doing. Glad there's people like that out there. This show is also brought to you by Inside Tracker, a service I used to track biological data. They have a bunch of plans, most of which include a blood test. That gives you a lot of information they can use to make decisions about your health have algorithms. Machine learning algorithms that analyze that data that includes your blood data, DNA data and fitness tracker data that comes from your body, right? This is very specific to your body and gives you a clear picture of what you need to do. [/INST] This </s><s>[INST] is obviously what should be done in the 21st century combined with my conversation with de from deepmind about the future of sort of science of biological applications of machine learning medical applications of machine learning is so so so exciting and being able to make these large scale machine learning systems that give you advice based on your specific individual data. That's really, really exciting. Just even outside of it being beneficial to your life, I think you should also consider supporting them for this big mission that's gonna help a lot of people So go to Inside Tracker dot com slash lex and for a limited time you get special savings for being a listener. This show is also brought to you by indeed hiring website. I've used them as part of many hiring efforts I've done for the teams I've led, especially engineering teams, but all kinds of teams, they have tools like indeed instant match giving you quality candidates with resumes that indeed fit your job description immediately. I'm actually currently looking for translators and over doubles to help me with some of the projects I'm doing here in Ukrainian and Russian, I speak the languages, but I want to have like a strong team that brings out the best from these people and it's all a fascinating new challenge and I want to hire the best people in the world to help me. I want to connect the world and language is a barrier that separates us. And so I'm looking to hire people to help me and probably tweet about it. All that kind of stuff anyway, indeed is a tool definitely used to help me find great folks for only a limited time, indeed has a special offer for the listeners of this podcast. Check it out and indeed dot com slash flex. This show is also brought to you by Express VPN, you should know friends that the I. S. P. S. The internet service providers can still track you even if you use basic protection like incognito mode on chrome, they can still get your data as I travel whether it's watching shows on netflix or just protecting your privacy on the internet from all the I. S. P. S. And everybody who wants to collect your data or just in general as you travel to different parts of the world and you want to read different kinds of news. I mean VPN is essential and my favorite VPN has always been for many, many years. Express VPN with a big sexy button that just works super fast. Works on any device, any operating system, at least any that I know of including my favorite operating system. You can go check them out at Express VPN dot com slash lex pod for an extra three months free. I've been using it for many years. Why don't you join me friend in this journey that's protected at least in part with a good V P. M. This episode is also brought to you by on it, a nutrition supplement and fitness company. They make Alpha Brain. Perhaps you've heard of it. I don't take it every day but I do take it often when I have uh an especially serious kind of difficult deep work session when I'm preparing for certain difficult conversations. I mean this is particularly for engineering if I'm unsure how I'm going to solve the different design parts, especially early on in the design stage of the project. But I also think of conversations as a kind of design and so in trying to sort of visualize the big picture of a conversation and zooming into very specific parts of a conversation, I have to really think hard and and for that alpha Brain can be a big boost, so I'll take it in those cases, helps clear the mind, helps maintain focus, sleep and and I gotta say power now, so of course are really essential. But on top of that, something like Alpha Brain really helps. You can check them out at lex Friedman dot com slash on it to get a special discount. This is the lex Friedman podcast to support it, please check out our sponsors in the description and now dear friends, here's martin Reese In your 2020 scientific American article you write that quote today, we know that the universe is far bigger and stranger than anyone suspected. So what do you think are the strangers, maybe the most beautiful or maybe even the most terrifying things lurking out there in the cosmos? [/INST] Well, of course we're still groping for any detailed understanding of the remote parts of the universe, but of course what we've learned in the last few decades is really two things. First we've understood that the universe had an origin about 13.8 billion years ago in a so called Big Bang, a hot, dense state whose very beginnings are still shrouded in mystery. And also we've learned more about the extreme things in it, black holes, neutron stars, explosions of various kinds. And one of the most potentially exciting discoveries in the last 20 years, mainly in the last 10, has been the realization that most of the stars in the sky are orbited by retinues of planets just as the sun is orbited by the Earth and the other familiar planets. And this of course makes the night sky far more interesting. What you see up there are just points of light, but their planetary systems and that raises the question, could there be life out there? And so that is an exciting problem for the 21st century. So </s><s>[INST] when you see all those lights out there, you immediately imagine all the planetary worlds that are around them and they potentially have all kinds of different lives, living organisms, life forms or, well in history that we [/INST] don't know at all, we know that these planets are there. We know that they have masses and orbits rather like the planets of our solar system, but we don't know at all if there's any life on any of them. I mean, it's entirely logically possible that life is unique to this. Earth doesn't exist anywhere. On the other hand, it could be that the origin of life is something which happens routinely given conditions like the young earth, in which case there could be literally billions of places in our galaxy where some sort of biosphere has evolved and settling where the truth lies between those two extremes is a challenge for the coming decades. </s><s>[INST] So certainly we're either lucky to be here or very, very, very lucky to be here. [/INST] I guess </s><s>[INST] that's the difference. Uh where do you fall your own estimate? Your own guests on this question? Are we alone in the universe do you think? [/INST] I think would be foolish to give any firm estimate because we just don't know. And that's just an example of how we are, depending on greater observations. And also, incidentally, in the case of life, we've got to take account of the fact that, as I always say to my scientific colleagues, biology is a much harder subjects than physics, and most of the universities we know about to be honest with my physics, but we've got to remember that even the smallest living organism, an insect is far more complicated with layer on their complexity than the most complicated star or galaxy. You </s><s>[INST] know, that's the funny thing about physics and biology. The dream of physicists in the 20th century, and maybe this century is to discover the theory of everything. And there's a sense by that, once you discover that theory, you will understand everything if we unlock the mysteries of how the universe works. Would you be able to understand how life emerges from that fabric of the universe that we understand? [/INST] I think the phrase theory of everything is very misleading because it's used to describe a theory which unifies the three laws of micro physics, electricity, magnetism, the weak interaction with gravity. So it's important step forward for particle physicists. But the lack of such a theory doesn't hold up any other scientists. Anyone doing biology or most of physics is not held up at all through not understanding sub nuclear physics. They're held up because they're dealing with things that are very complicated and that's especially true of anything biological. So what's holding up biologists is not a lack of a so called theory of everything. It's the inability to understand things which are very complicated. </s><s>[INST] What do you think? We'll understand first how the universe works or how the human body works deeply like from a fundamental deep level? [/INST] Well, I think perhaps we can come back to it later that there are only limited prospects of ever being able to understand with unaided human brains. The most fundamental theories linking together all the forces of nature. I think that may be a limitation of the human brains. But I also think that we can perhaps aided by computer simulations understand a bit more of the complexity of nature. But even understanding a simple organism from the atom up is very, very difficult and I think extreme reduction ists have a very misleading perception. They tend to think that in a sense we are all solutions for his equation etcetera. But that isn't the way we'll ever understand anything. It may be true that we are reductions in the sense that we believe that that's the case. We don't believe in any special life force in living things. But nonetheless, no one thinks that we can understand a living thing by solving schrodinger's equation to take an example, which isn't as complicated. Lots of people study the flow of fluids like water, why waves break, why flows go turbulent things like that. This is a serious branch of applied mathematics and engineering. And in doing this you have concepts of viscosity, turbulence and things like that. Now you can understand quite a lot about how water behaves and how waves break in terms of those concepts, but the fact that any breaking wave is a solution of schrodinger's equation for tens of 30 particles. even if you could solve that, which you clearly can't would not give you any insight. So the important thing is that every science has its own irreducible concepts in which you get the best explanation. So it may be in chemistry, things like valence in biology, the concepts in cell biology and in ecology, there are concepts like imprinting etcetera and in psychology there are other concepts. So in a sense the sciences are like a tall building where you have basic physics the most fundamental then the rest of physics and chemistry then cell biology etcetera. All the way up to the I guess economist in the penthouse and all that. We have that and that's true in a sense but it's not true that it's like a building in that it's made unstable by an unstable base. Because if your chemist biologist, an economist you're facing challenging problems but they're not made any worse by uncertainty about sub nuclear physics. </s><s>[INST] And at every level. Just because you understand the rules of the game or have some understanding of the rules of the game doesn't. I mean you know what kind of beautiful things that game creates [/INST] right? So if you interested in birds and how they fly then things like imprinting the baby and the mother and all that and things like that are what you need to understand. You couldn't even in principle solve this vertical equation how an albatross wanders for thousands of miles of the southern ocean and comes back and then coughs up food for its young. That's something we can understand in a sense and predict the behavior. But it's not because we can solve it on the atomic scale. </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] and the new methods of machine learning actually love raw data. The kind that astronomy provides organized, structured, raw data. [/INST] Well indeed, because the reason they really have a benefit over us is that they can learn and think so much faster. That's how they can learn to play chess and go, that's how they can learn to diagnose lung cancer better than the radiologist because they can look at 100,000 scans and if in a few days. Whereas no human radio sees that many a lifetime. </s><s>[INST] There's still magic to the human intelligence, to the intuition to the common sense reasoning. Well, [/INST] we hope so </s><s>[INST] for now. What, what, what is the new book that you mentioned? [/INST] The book is called? If science is to Save us, it's coming out in september um and it's on the um well the big challenges of science um you know climate dealing with biosafety and dealing with cyber safety. And also it's got chapters on the way science is organized universities and academies, et cetera. And and the the ethics of science and uh </s><s>[INST] perhaps [/INST] and limits. Yes. </s><s>[INST] Well, let me actually just stroll around the beautiful and the strange of the universe. Over 20 years ago you hypothesized that we would solve the mystery of dark matter by now. So unfortunately we didn't [/INST] yet </s><s>[INST] um First what is dark matter and why has it been so tough to figure out? [/INST] Well, I mean we learned that Galaxies and other large scale structures which are moving around but um prevention flying apart by by gravity would be flying apart if they only contain the stuff we see if everything in them was shining and to understand how Galaxies formed and why they do remain confined. The same size. One has to infer that is about five times as much stuff producing gravitational forces than the total amount of stuff in the gas and stars that we see. And that stuff is called dark matter. Leading name. It's not dark, it's just transparent et cetera. And the most likely interpretation is that it's a swarm of microscopic particles which have no electric charge and the very small cross sector for hitting each other and hitting anything else. So they swarm around and we can we can attack their collective effects. And when we do computer simulations of how Galaxies form and evolve and how they emerged from the Big Bang, then we get a nice consistent picture. If we put in five times as much mass in the form of these mysterious dark particles and for instance, it works better if we think they're not interacting particles than if you think there are gas, which would have shockwaves and things. So we know something about the properties of these, but we don't know what they are. And the disappointment compared to my guests 20 years ago is that particles answering this description have not yet been found. It was thought that the big accelerator, the large Hadron collider at cern is the world's biggest might have found a new class of particles which would have been the obvious candidates and it hasn't. And some people say, well, dark matter can't be there etcetera. But what I would argue is that there's a huge amount of parameter space that hasn't been explored. There are other kinds of particles called axons which behave slightly differently, which are good candidates. And there's a factor of 10 powers of 10 between the heaviest particles that could be created by the large Hadron collider and the heaviest particles, which, on theoretical grounds could exist without turning into black holes. There's a huge amount of possible particles which could be out there as remnants of the Big Bang, which we wouldn't be able to text so easily. So the fact that we've got new constraints on what the dark matter could be doesn't diminish my belief that it's there in the form of particles, because we've only explored a small fraction of parameter space. </s><s>[INST] So there's this search you're literally upon an unintended are searching in the dark here in this giant parameter space of possible particles you're searching for. I mean, there could be all kinds of particles [/INST] could be and there's some, it may be very, very hard to detect. But I think we can hope for um some new theoretical ideas because one point which perhaps you'd like to discuss more is about the very early stage of the Big Bang. And the situation now is that we have a outlined picture for how the universe has evolved from the time when it was expanding in just a nanosecond right up to the present. And we could do that because after nanosecond, the physics of the material is in the same range that we can test in the lab after another second, the particles moving around like those in the large Hadron collider if you wait for one second there rather like in the centers of the hottest stars and nuclear actions produce hydrogen helium, etcetera, which fit the data. So we can with confidence extrapolate back to when the universe was a nano second old indeed, I think we can do with as much confidence as anything. A geologist tells you about the early history of the earth and that's huge progress in the last 50 years. But any progress puts in sharper focus new mysteries. And of course the new mysteries in this context are why is the universe expanding the way it is? Why does it contain this mixture of atoms and dark matter and radiation? And why does it have the properties that allow galaxy to form, being fairly smooth but not completely smooth? And the answer to those questions generally believed to lie in a much much earlier stage of the universe when conditions were much more extreme and therefore far beyond The stage where we have the foot holding experiments. Very theoretical. And so we don't have a convincing theory. We just have ideas until we have something like string theory or some other clues to the cultural universe. That's going to remain speculative. So there's a big gap. And to say a big gap is if we take the observable universe to a bit more than 10 billion light years. Then when the universe was a nanosecond old, that would have been squeezed down to the size of our solar system or compressed into that volume. But the times we're talking about when the key properties of the universe were first imprinted were times when that entire universe was squeezed down to the size of a tennis ball or baseball if you prefer and to emerge from something microscopic. So it's a huge extrapolation. And it's not surprising that since it's so far from our experimental range of detect ability, we are still groping for ideas. </s><s>[INST] But you think first theory will reach into that place and then experiment will perhaps one day catch up simulation. [/INST] In a sense, it's a combination. I think what we hope for is that uh there'd be a theory which applies to the early universe but which also has consequences which we can test in our present day universe. Um like um discovering my neutrinos exist or things like that. And that's the thing which I mentioned, we maybe have a bit of a I to help us to calculate, but but I think the hope would be that we will have a theory which applies under the very, very extreme early stages of the universe, but which gains credibility and gains confidence because it also manages to account for otherwise unexplained features of the world and what people call the standard model of particle physics where lots of undetermined numbers. So it may help with that. </s><s>[INST] So we're dancing between physics and philosophy a little bit. But what do you think? What do you think happened before the Big Bang? So this seems this feels like something that's out of the reach of science. [/INST] It's out of the reach of present science because science develops and as the front is advance, then new problems come into focus that couldn't leave been postulated before. I mean if I think of my own career when I was a student, the evidence for the Big Bang was pretty weak, whereas now it's extremely strong but we are now thinking about the the reason why the universe is the way it is and all that. So I would put all these things we just mentioned in the category of speculative science and I don't see a bifurcation between that and philosophy. But of course to answer your question, if we do want to understand the very early universe, then we've got to realize that it may involve even more counterintuitive concepts than quantum theory does because it's a condition even further away from everyday world than quantum theory is. And remember our lives our brains evolved haven't changed much since our ancestors roamed the african savanna and looked at the everyday world. And it's rather amazing that we've been able to make some sense of the quantum micro world and the cosmos. But there may be some things which are beyond us. And certainly as you implied there things that we don't yet understand at all. And of course one concept we might have to jettison is the idea of three dimensions of space and time. Just ticking away a lot of ideas. I mean I think Stephen Hawking had an idea that talking about what's what happened before the Big Bang, it's like asking what happens if you go north of the North Pole, you know, it's somehow closes off, that's just one idea, I don't like that idea, but that's a possible one. Um and uh and so we just don't know what happened at the very beginning of the Big Bang, where there many big bangs rather than one, et cetera, and those are issues which we may be able to get some foothold on from some new theory, um but even then we won't be able to directly test the theories, but I think it's a heresy to think you have to be able to test every prediction of a theory that be given another example. Um We take seriously what Einstein's theory says about the inside of black holes, even though we can't observe them, because that theory has been vindicated in many other places in cosmology and black holes, gravitational waves and all those things. Um Likewise, if we had a theory which explains some things about the early history of our Big bang in the present universe, then we would take seriously the inference if it predicted many big bangs, not one, even though we can't predict the other ones, so the example is that we can take seriously a prediction if it's the consequence of the theory that we believe on other grounds, we don't need to be able to detect another big bang in order to take it seriously, </s><s>[INST] It may not be a proof, but it's a good indication that this is the direction where the truth lies. [/INST] Yeah. If the theory is getting confidence in other way, </s><s>[INST] Yes. Where do you sense do you think there's other universes besides our own, [/INST] the sort of well defined theories that make assumptions about the physics at the relevant time and this time incidentally is 10 to the power minus 36 seconds or earlier than that. This tiny sliver of time. And there are some theories famous bone due to Andrea Lynn day, the Russian cosmologist now at stanford called eternal inflation, which did predict an internal production of new big Bangs as it were and that's based on specific assumptions about the physics. But those assumptions of course are just hypotheses which are vindicated, but there are other theories which only predict one big bang. So I think we should be open minded and not dogmatic about these. These options until we do understand the relevant physics. But there are these different scenarios are very different ideas about about this. But I think all of them have the feature that physical reality is a lot more extensive than what we can see through our telescope. I think even the most conservative astronomers would say that because we can see with our telescopes to a sort of horizon which is about Depending on how you measure it maybe 15 billion light years away or something like that. But that horizon of observations is no more physical reality than the horizon around you, if you're in the ocean and looking looking out at your horizon, there's no reason to think that the ocean ends just beyond your horizon, and likewise, there's no reason to think that the aftermath of our Big Bang ends just at the boundary of what we can see. Indeed, there are quite strong arguments that it probably goes on about 100 times further. It may even go on so much further that all combinatorial czar replicated and there's another set of people like us sitting in a room like this, </s><s>[INST] every possible combination of [/INST] Yeah, that that could happen, that's not logically impossible, but but I think many people would accept that it does go on and contain probably a million times as much stuff as what we can see within the horizon. </s><s>[INST] The [/INST] reason for that incidentally, is that if we look as far as we can in one direction and in the opposite direction, Then the conditions don't differ by more than one part in 100,000. So that means that if we're part of some finite structure, The gradient across the part we can see is very small. And so that suggests that it probably does go on a lot further. And the best estimates say it must go on at least 20 times further </s><s>[INST] is that exciting or terrifying to you. Just the spans of it all the wide everything that lies beyond the horizon. That example doesn't even hold for Earth's, it goes way way farther and on top of that just to take care of metaphor further with the on the ocean. While we're on top of this ocean, not only can we not see beyond the horizon, we also don't know much about the depth of the ocean [/INST] nor </s><s>[INST] the actual mechanism of observation that's in our head. You [/INST] know? I think the is all those points you make. Yes, Yes. But but I think uh even even the solar system's pretty vast by human standards. And so I don't think the perception of this utterly vast cosmos need have any deeper impact on us and just realizing that we are very small on the scale of the external world. </s><s>[INST] Yeah. It's humbling though. It's humbling in depending where your ego is. It's humbling and well if you very [/INST] humble indeed it may make a difference. But most of us, I don't think it makes the most difference. And well there's a more general question of course about whether um the human race is such is something which is very special or if on the other hand, it's just one of many such species elsewhere in the universe or indeed existing at different times in our universe. </s><s>[INST] It to me it feels of almost obvious that the universe should be full of alien life, perhaps dead alien civilizations, but just the vastness of space. And it just feels wrong to think of Earth as somehow special. It sure as heck doesn't look that special when you the more we learn, the less specialist seems [/INST] well. I mean I don't agree with that as far as life is concerned because remember that we don't understand how life began here on earth. We don't understand. Although we know there is an evolution of simple life to complex life. We don't understand what caused the transition between complex chemistry and the first replicating metabolizing entity we call alive. That's the mystery and serious physics and chemistry now thinking about it, but we don't know. So we therefore can't say was it a rare fluke which would not have happened anywhere else? Or was it something which involves the process would have happened in any other planet where conditions were like they were in the young earth. So we can't say that now. Um I think many of us would indeed bet that probably some kind of life exists elsewhere. But even if you accept that then um many contingencies going from simple life too present day life. And some biologists like Stephen jay Gould thought that if you re round evolution you'd end up with something quite different. Maybe not an intelligent species. So the contingencies in evolution may militate against the emergence of intelligence even if life gets started lots of places. So I think these are still completely open questions and that's why it's such an exciting time now that we are starting to be able to address these. I mean I mentioned the fact that the origin of life is a question that we may be able to understand and serious people are working on it. Usually put in the sort of too difficult box ever knew was important, but they didn't know how to tackle it or what exponents to do. But it's not like that now and that's partly because of clever experiments. But I think most importantly because we are aware that we can look for life in other places, Other places in our solar system and of course on the exoplanets around other stars and within 10 or 20 years I think two things could happen which would be really, really important. We might with the next big telescope be able to image some of the earth like planets around other stars. </s><s>[INST] Image get [/INST] Well actually let me caveat that it takes 50 years to get a resolved image but try to detect the light because now of course these exoplanets are detected by their effects on the parent star. They either of course that their parents start to dim slightly when they transit across in front of it. And so we see the dips or Their gravitational pull makes the star wobble a bit. So most of the 5000 plus planets that have been found around other stars. They've been found indirectly by their effect in one of those two ways on the parents do </s><s>[INST] a pretty good job of estimating size, all those kinds of [/INST] the size and the mass you can estimate, but but detecting the actual light from one of these actual planets hasn't really been done yet. Exactly one or two very, very, very bright. Big planets </s><s>[INST] like James Webb telescope. [/INST] James Webb may do this, but even better will be the european ground based telescope called Unimaginatively the extremely large telescope which has a 39 m diameter mirror 39 m later on sheets of glass and that will collect enough light from one of these exoplanets around a nearby star and to be able to separate out its light from that of the star, which is a millions of times brighter. And get the spectrum of the planet and see if it's got oxygen or chlorophyll and things in it. So that that that will come. James Webb may may make some some steps there. But I think we can look forward to learning quite a bit in the next 20 years because I like to say. Supposing that is looking at the solar system, then they see the Son as an ordinary star. They see the Earth as in Carl Sagan's lies fraser pale blue dot lying very close in the sky to its star, our sun and much much much fainter. But if they could observe that dot, they could learn quite a bit, they could perhaps get respectively of the light and find the atmosphere, they'd find the shade of blue is slightly different depending on whether the pacific ocean or land mass of Asia was facing them. So they could infer the length of the day and the two oceans and continents and maybe something about the seasons and the climate. And that's the kind of Calculation, calculation and inference we might be able to draw within the next 10 or 20 years about other exoplanets and and evidence of some sort of biosphere on one of them would of course be crucial and it would rule out the Still logical possibility that life is unique. But there's another way in which this may happen the next 20 years. People think there could be something swimming under the ice of Europa and enceladus and probes are being sent to maybe not quite go under the ice, but detect the spray coming coming out to see if there's evidence for organics in that. And if we found any evidence for an origin of life that happened in either of those places, that would immediately be important. Because if life has originated twice independently in one planter system, the solar system, that would tell us straight away, it wasn't a rare accident and must have happened billions of times in the galaxy at the moment, we can't rule out it being unique and incidentally, if we found life on MArs, then that would still be ambiguous because people have realized that this early life could have got from MArs to Earth or vice versa on meteorites. So if you found life on MArs, then some skeptics could still say if it's a single origin. But I think </s><s>[INST] europe is far enough [/INST] far enough away. So that's why that would be, especially, it's </s><s>[INST] always the skeptics that ruined a good party. But [/INST] we need them. Of course </s><s>[INST] we need them at the party. We need some skeptics at the party. But boy, would that be so exciting to find life on one of the moons? [/INST] That would just be any kind of vegetation or life? Um, the question of the aliens of science fiction is a different matter, </s><s>[INST] intelligent aliens. Yeah, But if you have a good indication that there's life elsewhere in the solar system, that means life is everywhere. And that that's I don't know if that's terrifying or what that is, because if life is everywhere, why is intelligent life not everywhere? Why? I mean, you've talked about that most likely alien civilizations. If they are out there, they would likely be far ahead of us. The ones that would actually communicate with us and that, um, again, one of those things that is both exciting and terrifying, you've mentioned that they're likely not to be of biological nature. [/INST] Well, I think that's important. Of course. Again, it's speculation, but uh, in speculating about intelligent life. And I, I think the search seriously. In fact I chair the committee that the Russian american investor yuri milner supports looking for intelligent life is putting $10 million a year into better equipment and getting time on telescopes to do this. And so I think it's worthwhile. Even though I don't hold my breath for success, it's very exciting. But that does lead me to wonder what might be detected. And I think, well, we don't know, we've got to be open minded about anything. We have no idea what it would be. And so any anomalous objects or even some strange shiny objects in the solar system or anything we've got to keep our eyes open for. But I think if we ask what about a planet like the earth where evolution had taken more of the same track then, as you say, it wouldn't be synchronized. If it had lagged behind, then of course it would not have got to advanced life, but it may have had a head start. It may have formed on a planet around an older star. Okay, But then let's ask what would see? It's taken nearly four billion years from the first live to us. And we've now got this technological civilization which could make itself detectable to any alien live aliens out there. But I think most people would say that this civilization of flesh and blood creatures in the collective civilization may not last more than a few 100 years more. I think that the people may, some people would say that it will kill itself off. But I'm more optimistic and I would say that what we're going to have in </s><s>[INST] future [/INST] is no longer the slow Darwinian selection, but we're going to have what I call secular intelligent design, which will be humans designing their progeny to be better adapted to where they are. And if they go to mars or something somewhere, they're badly adapted and they want to adapt a lot and so they will adapt. But there may be some limits to what can be done with flesh and blood. And so they may become largely electronic, download their brains and have and be electronic. And if they're electronic then what's important is that they're near immortal and also they won't leslie want to be on the planet with an atmosphere or gravity. They may go off into the blue yonder and they if they're near immortal, they won't be daunted by interstellar travel taking a long time. And so if if we looked at what would happen on the earth in the next millions of years, then there may be these electronic entities which have been sent out and are now far away from the earth but still sort of burping away in some in some fashion to be detected. And so this this therefore leads me to think that if there was another planet, Richard evolved like the earth and was ahead of us, it wouldn't be synchronized so we wouldn't see a flesh and blood civilization, but we would see these electronic progeny as it were? And then this raises another question because there's a famous argument against there being lots of aliens out there, which is that they would come and invade us and eat us or something like that. You know, that's a common idea which family is attributed have been the first to say. Um and I think there's a escape clause to that because these entities would be say that they evolved by second intel to design designed by their predecessors and then designed by us. And uh Whereas Darwinian selection requires two things. It requires aggression and intelligence. This future intel design may favor intelligence because that's what they were designed for, but it may not favor aggression. And so these future entities, they may be um sitting deep thoughts, thinking deep thoughts, um and not being at all expansionist. So they could be out there and we can't refute their existence in the way the family paradoxes supposed to refute their existence because these would not be aggressive or expansionist? </s><s>[INST] Well, maybe evolution requires competition, not aggression. And I wonder if competition can take forms that are non expansionary. So you can still have fun competing in the space of ideas which may be primarily [/INST] will be philosophers perhaps. Yeah, </s><s>[INST] in a way. Right. It's uh it's an intellectual exercise versus a sort of violent exercise. So what is this civilization on mars look like? So do you think we would more and more, you know, maybe start with some genetic modification and then move to basically cyborgs, increasing integration of electronic systems, computational systems into our bodies and brains. [/INST] This is a theme of my other new book out this year, which is called The End of Astronauts And </s><s>[INST] co [/INST] written with my old friend colleague from Berkeley Don Goldsmith. And it's really about the role of human spaceflight versus sort of robotic spaceflight. And just to summarize what it says, it argues that the practical case for sending humans into space, it's getting weaker all the time as robots get better and more capable Robots 50 years ago couldn't do anything very much. But now they could assemble big structures on space or on space or on the moon. And they could probably do exploration. Present ones on Mars can't actually do the geology but future Ai will be able to do the geology and already they can dig on Mars. And so if you want to do exploration of Mars and of course even more of and sell the Europa, we could never send humans, we depend on robots And they're far far cheaper because to send a human to Mars requires feeding them for 200 days on the journey there and bringing them back and neither of those are necessary for robots. So the practical case for humans is getting very, very weak and if humans go it's only as an adventure really. And so the line in our book is that </s><s>[INST] human [/INST] space flight should not be pursued by Nassau or public funding agencies because it has no practical purpose, but also because it's specially expensive if they do it because they would have to be risk averse in launching civilians into space. I could illustrate that by noting that the shuttle Was launched 135 times and it had two spectacular failures which each killed seven people in the crew and it had been mistakenly presented as safe for civilians and there was a woman schoolteacher killed in one of them and it was a big natural trauma and they tried to make it safer still. But if you launch into space, just the kind of people prepared to accept that sort of risk. And of course test pilots and people who go hang gliding and Go to the South Pole etc are prepared to accept a 2% risk, at least for a big challenge. Then of course you do it more cheaply. And that's why I think human spaceflight should be left to the billionaires and their sponsors because then the taxpayers aren't paying and they can launch simply those people who are prepared to accept high risks space adventure, not space tourism and we should cheer them on. And as regards where they would go, then low Earth orbit I suspect can be done quite cheaply in future, but going to mars, which is very, very expensive and dangerous for humans. The only people who would go would be these adventurers maybe on one way trip, like some of the early polar explorers and Magellan and people like that, you know, and we will cheer them on and I expect. And I've always hoped that by the end of a century there will be a small community of such people on mars living very uncomfortably, far less comfortably than at the South Pole or the bottom of the ocean or top of Everest, but they will be there um and they won't have a ticket, but they'll be there. Um Incidentally, I think it's a dangerous delusion to think as Elon musk has said that we can have mass emigration from the earth to mars to escape the earth's problems today disillusioned because it's far easier to deal with climate change on earth than to terra form mars to make it probably habitable to humans and there's no planet B for the risk averse people. But for these crazy adventurers then you can imagine that they would be trying to live on mars as as great pioneers and by the end of century then there will be huge advances compared to the present in two things. First in in understanding genetics, so as to genetically redesign one's offspring and secondly to use cyborg techniques to implant some something in our brain or indeed think about downloading etcetera. And those techniques will one hopes be heavily regulated on Earth on Prudential's and ethical grounds and of course we are pretty well adapted to the Earth, so we don't have the incentive to do these things in the way they were there. So our argument is that it will be those crazy pioneers on MArs using all these scientific advances which will be controlled here away from the regulators. They will transition into a new post human species. And so if they do that, and if they transition into something which is electronic eventually, because there may be some limits, the capacity of flesh and blood, brains anyways, then those electronic entities may not want to stay on the planet, like mars, they may want to go away. And so they'll be the precursors of the future evolution of life and intelligence coming from the earth. And of course there's one point which perhaps astronomers are more aware of that. Most people, most people are aware that we are the outcome of four billion years of evolution. Most of them nonetheless probably think that we humans are somehow the culmination the top of the tree. </s><s>[INST] But you [/INST] know, astronomers could believe that because astronomers know that the Earth is 4.5 billion years old. The sun has been shining for that length of time, but the sun has got six billion years more to go before it flares up and engulf the inner planets. So the sun doesn't halfway through his life. Um and the expanding universe goes on far longer, Still, maybe forever. And I'd like to quote woody Allen who said eternity is very long, especially towards the end. So, so we shouldn't think of ourselves as maybe even the halfway stage in the emergence of cosmic complexity. And so these entities who are post curses, they will go beyond the solar system. And of course, even if there's nothing else out there already, then they could populate the rest of the galaxy </s><s>[INST] and maybe eventually meet the others who are out there expanding as well, expanding, populating with expanded capacity for life and intelligence, all those kinds of things. [/INST] Well, they might but again, all better off because I can't conceive what they'd be like. They won't, they won't be a green green men and women with eyes on stalks. You know, maybe something quite different, We just don't know. But there isn't any question actually which comes up when I sometimes spoken to audiences about this topic, but the question of consciousness and self awareness because going back to philosophical questions whether an electronic robot would be a zombie or would it be conscious and self aware. And I think there's no way of answering this empirically and some people think that consciousness and self awareness is an emergent property and any sufficiently complicated networks that there would be others say, well, maybe it's something special to the flesh and blood that were made of, we don't know and in a sense, this may not matter to the way things behave because we they could be zombies and still behave as though they were intelligent. But remember after one of my talks, someone came up and said, wouldn't it be sad if these future entities which were the main intelligence in the universe, had no self awareness? So there was nothing which could appreciate the wonder and mystery of the universe and the beauty of the universe in the way that we do. And so it does perhaps affect one's perspective of whether you welcome or deplore this possible future scenario depending on where you think the future post human entities are conscious and have an aesthetic sense or whether they're just zombies. </s><s>[INST] And of course you have to be humble to realize that self awareness may not be the highest form of being, that humans have a very strong ego and a very strong sense of identity, like personal identity connected to this particular brain. It's not so obvious to me that that is somehow the the highest achievement of a life form. That maybe this kind [/INST] of, it's </s><s>[INST] possible that uh well, I think from an alien perspective, when you look at earth, it's not so obvious to me that individual humans are the atoms of intelligence. It could be the entire organism together the collective intelligence. And so we humans think of ourselves as individuals, we dress up, wear ties and suits and we give each other prizes. But in reality the intelligence, the things we create that are beautiful, emerges from our interaction with each other. And that may be where the intelligence is ideas jumping from one person to another over generations. [/INST] Yes, but we have experiences where we can appreciate beauty and wonder and all that. And uh zombie may not have those experiences. </s><s>[INST] Yeah. Or it may have a very different, We have a very black and white harsh description of like a philosophical zombie zombie. That could be just a very different way to experience. Uh, and you know, in terms of the explorers that colonized MArs, I um, I mean there's several things I want to mention, one it's just at a high level to me that's one of the most inspiring things humans can do is reach out into the unknown. That's in the space of ideas in the space of science, but also the explorers [/INST] and </s><s>[INST] that inspires people here on earth more. I mean it did in there, you know, when going to the moon or going out to space in the 20th century that inspired a generation of scientists, I think that also [/INST] could </s><s>[INST] be used to inspire a generation of new scientists in the 21st century by reaching out towards mars. So in that sense, I think what Elon musk and others are doing is actually quite inspiring. It's [/INST] not, it's </s><s>[INST] not a recreationally thing. It's actually has a deep humanitarian purpose of really inspiring the world. And then on the other one to push back on your thought. You know, I don't think Elon says we want to escape earth's problems. It's more that we should allocate some small percentage of resources to have a backup plan. And because you yourself have spoken about and written about all the ways we, clever humans destroy ourselves, [/INST] and </s><s>[INST] I'm not sure, it does seem when you look at the long arc of human history, it seems almost obvious that we need to become a multi planetary species over a period. If we are to survive many centuries, it seems that [/INST] as </s><s>[INST] we get clever and clever with the ways we can destroy ourselves, earth is going to become less and less safe. Um, so in that sense, this is one of the things, you know, people talk about climate change and that we need to respond to climate change and that's a long term investment we need to make, but it's not really long term, it's a span of decades. I think what Ellen is doing is a really long term investment. We should be working on multi planetary colonization. Now, if we were to have it ready five centuries from now. And so taking those early steps and then also there's something happens when you're, when you go into the unknown and do this really difficult thing, you discover something very new. You discover something about robotics or materials engineering or nutrition or neuroscience or human relations or political systems that actually work well with you, you discover all those things, so it's worth the effort to go out there and uh try to become cyborgs. Yeah, [/INST] no, I agree with that. I think the only different point I'd make is that this is going to be very expensive if it's done in a risk averse way. And that's why I think we should be grateful to the billionaires if they're going to sort of foster these opportunities for thrill seeking risk takers who we can </s><s>[INST] Yeah, by the way, I should push back on the billionaires because there's sometimes a negative connotation to the word billionaire. It's not a billionaire, it's a company versus government because governments are billionaires and trillion airs. It's not it's not the wealth, it's the capitalist uh imperative. So uh which I think deserves a lot more praise than people are giving it. I'm I'm troubled by this sort of criticism, like it's billionaires playing with toys for their own pleasure. I think what some of these companies like SpaceX and Blue Origin are doing is some of the most inspiring engineering and even scientific work ever done in human history. [/INST] No, I agree. I think that people have made the greatest wealth are people who have really been mega benefactors. I mean, I think, you know, some </s><s>[INST] of them, some of [/INST] them, yes, some of them, but but but those who who founded google and all that and and even amazon their their their their beneficiaries then they're quite different category in my view from those who just shuffle around money or or or crypto coins and things like that, who are </s><s>[INST] not yet. [/INST] But I think if they use their money in these ways that's fine. But I think it's true that the far more money is owned by us, collectively as taxpayers. But I think the fact is that in a democracy, um there'd be big resistance to exposing human beings to very high risks if in a sense, we share responsibility for it. </s><s>[INST] And [/INST] that's that's the reason I think we've done much more cheaply by by by these private funders. </s><s>[INST] That's an interesting hypothesis, but I have to push back. I don't know if it's obvious why Nasa spends so much money and takes such a long time to develop the things I was doing so before Elon musk came along. Because I would love, I would love to live in a world where government actually uses taxpayer money to get some of the best engineers and scientists in the world and actually work across governments, Russia china United States, european union together to do some of these big projects. It's strange that Ellen is able to do this much cheaper much faster. It could have to be do with risk aversion. You're right, but I think it's [/INST] it's the it's that it's that he had all the the whole assembly within this one building as it were rather than depending on a supply chain. But I think it's also that he had a Silicon valley culture and younger people. Whereas the big aerospace companies Boeing and Lockheed martin, they had people who were left over from the Apollo program in some cases and so they weren't quite so lively and indeed quite apart from the controversial issues of the future of human spaceflight. In terms of the next generation of big rockets. Then the one that musk is going to launch for the first time this year, huge one is going to be far far cheaper than the one that Nasa has been working on the same time. And that's because it will have a reusable first stage and it's going to be great. It can launch over 100 tons into Earth orbit and instead that's going to be make it feasible to do things that I used to think we're crazy like having solar energy from space. That's no longer so crazy if you can do that. And also for science because its nose cone could contained within it, something as big as the entire unfurled James Webb telescope mirror and have a big telescope much more cheaply if you can launch it all in one piece. And so it's going to be hugely beneficial to science and to any practical use of space to have these cheaper rockets that are far more completely reusable anyways Nasa had. So I think mosques are a tremendous service to the space exploration and the whole space technology through these rockets </s><s>[INST] certainly. Plus it's some big sexy rocket. It's just great engineering. [/INST] Of course, yeah. It's </s><s>[INST] like looking at a beautiful big bridge that humans are capable of descendants of apes are capable to do something so majestic. [/INST] And also the way they land coming down at this bar. That's amazing. </s><s>[INST] It's both controls engineering. It's um increasing sort of intelligence in these rockets but also great propulsion engineer materials uh, on your ship. And it just inspires. It just inspires so many people [/INST] know I'm entirely with you on that. </s><s>[INST] So would it be exciting to you to see a human being stepped foot on mars in your lifetime? Yes. [/INST] I think it's unlikely in my lifetime since I'm I'm so ancient but but I think this essentially is going to happen And I think that that will indeed be exciting. And I hope there will be a small community by the end of the century. But as I say, I think they may go with one way tickets or accepting the risk of of of no return. So they've got to be people like that. And I still think it's going to be hard to persuade the public to send people when you say straight out that they may never come back. But of course the Apollo astronauts, they took a high risk And in fact in in my previous book, I quote the speech that has been written for Nixon to be read out if Neil armstrong got stuck on the moon. And it was written by one of his, his advisor's very eloquent speech, you know about how they have come to a noble end et cetera. But of course there was a genuine risk at that time, but that may have been accepted. But clearly the crashes of the shuttle were not acceptable to the american public Even when they were told that this was only a 2% risk given how often they launched it. And so that's what leads me to think that it's got to be left to the kind of people who are prepared to take these risks. And and II think think of America event was a guy called Steve Fossett who was aviator, did all kinds of crazy things, you know, and then the guy who fell super sonically um with the parachute from very high altitude, all these people, we all cheer them on, they extend the bounds of humanity. But I don't think the public would be so happy to fund them. </s><s>[INST] And I mean I disagree with that. I think if we change the narrative we should change the story. [/INST] I think, </s><s>[INST] I think there's a lot of people because the public is happy to fund folks in other domains that take bold giant risks. First of all military for example military [/INST] uh </s><s>[INST] I think this is in the name of science especially if it's sold correctly. I sure as I would go up there with the risk with that, I would, I would take a 40% chance risk of [/INST] death </s><s>[INST] for something that's, can [/INST] I might want to be even older than I am </s><s>[INST] now. I guess what I'm trying to communicate is there's all, there's a lot of people on earth that's a nice feature and I'm sure there's going to be a significant percentage or some percentage of people that are, they take on the risk for the adventure. So, and I, I particularly love that that risk of adventure when taking on inspires people and just the ripple effect that has across the generation, especially among the young minds is perhaps immeasurable. But you're thinking, um, [/INST] yeah, </s><s>[INST] that sending humans should be something we do less and less sending humans to space. That it should be primarily an effort. The work of space exploration should be done primarily by robots. [/INST] Well, I think it can be done much more cheaply obviously on, on mars and no one is thinking of sending humans to Enceladus or Europa, the outer planets. And the point is we will have much better robots because let's take an example, you've seen these pictures of the moons of Saturn and the picture of Pluto and the comet taken by probes and, and cassini spent 13 years going around Saturn and its moons after seven year boys and those are all based on 19 nineties technology? And if you think of how smartphones have advanced in the 20 years since then, just think how much better one could do instrumented some very small sophisticated probe that could send dozens of them to explore the outer planets. And that's that's the way to do that because no one thinks you can send humans that far and that I would apply the same argument to to mars and if you want to assemble big structures, like for instance, radio astronomers would like to have a big radio telescope on the far side of the moon. So it's away from the Earth's background artificial radio waves. And that could be done by assembling using robots without people. So, on the moon and on mars, I think everything that's useful can be done by machines, much more cheaper than by humans. Do </s><s>[INST] You know the movie 2001? A Space Odyssey? [/INST] Of course, yes. </s><s>[INST] You [/INST] must be too young to have seen that when he came out. Obviously </s><s>[INST] I remember [/INST] when he came out, you </s><s>[INST] saw when he came out [/INST] Yeah, </s><s>[INST] 60 when it was 60 [/INST] uh in </s><s>[INST] The 60s, it's still probably [/INST] me. </s><s>[INST] The greatest ai movie ever made. One of the great space movies ever made. So [/INST] Well, </s><s>[INST] Let me ask you philosophical questions since we're talking about robots exploring space. Do you think how 9000 is good or bad. So for people who haven't watched this computer system makes a decision to uh basically prioritize the mission that the ship is on over the humans that are part of the mission, um Do you think hal is good or evil? [/INST] If you ask you? Probably in that context, it was probably good. But I think you're raising what is of course very much active issue in everyday life about the extent to which we should entrust any important decision to a machine. And there again, I'm very worried because I think if you are recommended for an operation or not given parole from prison or even denied credit by your bank, you feel you should be entitled to an explanation. It's not enough to be told that the machine has a more reliable record on the whole than humans have of making these decisions. You think you should be given reasons you could understand. And that's why I think the present societal trend to uh take away the humans and leave us in the hands of decisions that we can't contest is a very dangerous one. I think we've got to be very careful of the extent to which ai which can handle lots of information actually makes the decisions without oversight and I think we can use them as a supplement, but to take the case of radiology and cancer. I mean, it's true that the radiologist hasn't seen as many x rays of council lungs as the machine. So the machine can certainly help. But you want the human to make the final decision. And I think that's true in most of these instances. But if we turn a bit to the short term concerns with robotics, I think the big worry of course is the effect it has on people's self respect and their labor market. And I think my solution would be that we should arrange the tax more heavily the big international conglomerates which use the robots and use that tax to a fund decently paid dignified posts of the kind where being a human being is important above all carers for old people, teachers, assistance for young gardens in public parks and things like that. And if the people who are now working in mind numbing jobs in amazon warehouses or in telephone call centers automated. But those same people are given jobs where being a human is an asset, then that's a plus plus situation. And so that's the way I think that we should benefit from these, these technologies um take over the mind numbing jobs and you use machines to make them more efficient but enable the people so displaced to do jobs where we do want a human being. I mean most people when they're, when they're old, the rich people if they have the choice, they want human carers and all that don't, they may want robots to help with some things empty bedpans and things like that. But they want real people and certainly in this country, I think even worse in America and the care of old people is completely inadequate and it needs just more human beings to help them cope with everyday life and look after them when they're sick. And uh and so that seems to me the way in which the money raised in tax on these big companies should be deployed. </s><s>[INST] So that's in the short term. But if you actually just look, the fact is where we are today to long term future in 100 years, it does seem that there is some significant chance that the human species is coming to an end in his pure biological form is going to be greater and greater integration to genetic modification than cyborg type of creatures. And so you have to think all right, well we're gonna have to get from here to there and that process is going to be painful and that you know how there's so many different predictions that take us from one place to another. It does seem that we need to deeply respect humanness and humanity. Basic human rights, human welfare like happiness and all that kind of [/INST] No, absolutely. And that's why I think we ought to try and slow down the application of these human enhancement techniques and cyborg techniques for humans. For just that reason. I mean that's why I want to lead into people on mars let them do it. But that's just the reason </s><s>[INST] they're people too okay for people to I tend to, you know, [/INST] but they are poorly adapted to where they are. That's why they need modification. Whereas were adapted to the earth quite well. So we don't need these modifications. We're happy to be humans living in in the environment where our ancestors lived. So we don't have the same same motive. So I think there's a difference but I agree we don't want drastic change is probably in our lifestyle and that indeed is a worry because some things are changing so fast. But I think I'd like to inject a note of caution. If you think of the way Progress in one technology goes, it goes in a sort of spurred, it goes up very fast and then it levels off. Let me give you two examples. One we've had already a human space flight at the time of the Apollo program was only 12 years after Sputnik one. I was alive then and I thought it would only be 10 or 20 years further before there were footprints on Mars. But as we know, for reasons we could all understand, um that was and still remains the high point of human space exploration, but that's because it was funded for reasons superpower rivalry, accused public expense. But let me give you another case. Um civil aviation. Um if you think of the change between 1919 when that is all cock and brown's first transatlantic fight to 1979. The first flight of the Jumbo jet is a big change. It's more than 50 years since 1969. And we still have jumbo just more or less the same. So that's an example of something which developed fast. And to take another analogy, we've had huge developments in mobile phones but I suspect the iPhone the iPhone 24 may not be too different from the iPhone 13 because they develop, but then they saturate and then maybe some new innovation takes over in stimulating economic growth. </s><s>[INST] Yeah. So it's that uh, we have to be cautious about being too optimistic and we have to be cautious about being too cynical. I think that is optimistic [/INST] is begging the question. I mean, do we want this very rapid change? </s><s>[INST] Right. So first of all, there's some degree to which technological advancement is, is something is a force that can't be stopped. And so the question is about directing it versus stopping it. It [/INST] Can be sort of slow, slow but human spaceflight, there could have been footprints on Mars if if America had gone on spending 4% of the federal budget on the project after they were very good reasons. But um, and we could, we could have had supersonic flight but Concord came and went during the 50 years. But </s><s>[INST] the reason it didn't progress is not because we realized it's not good for human society. The reason it didn't progress is because it could make uh sort of from a capitalist perspective, it couldn't make, uh, there was no short term or long term way for it to make money. So for me it [/INST] isn't, but that's the same mistake. It's local society. </s><s>[INST] I don't think everything that makes money is good for society and everything that doesn't make money is bad for society. Right? That's a, that's a difficult, that's a difficult thing. We're always contending with. When we look at social networks, it's not obvious, even though they make a tremendous amount of money, that they're good for society, especially how they're currently implemented with the advertisement and engagement maximization. So that's the constant struggle. [/INST] You know, I agree with many </s><s>[INST] innovations are [/INST] damaging. Yes. </s><s>[INST] Yes. Well, [/INST] but I would have thought that supersonic flight was something that will benefit only a tiny </s><s>[INST] elite, [/INST] huge expense and environmental damage. That was obviously something which was very glad not to have, in my opinion. </s><s>[INST] Yeah, But perhaps there was a way to do it where it could benefit the general populace. If you were to think about airplanes. Once you think that in the early days, airplanes would have been seen as something that can surely only benefit 1% at most of the population as opposed to a much larger percentage there. There's, there's another aspect of capitalist system that's able to drive down costs, once you get the thing kind of going, so that, you know, we get together maybe with taxpayer money and get the thing going at first and once it gets going, companies step up and drive down the cost and actually make it so that blue collar folks can actually start using the, so it's that's again the double edged sword of human civilization that some technology hurts us, some benefits us and we don't know ahead of time, we can just do our best and [/INST] gap between what could be done and what we collectively decide to do. </s><s>[INST] Yes. [/INST] In the, in the term, you could push forward some developments um, faster than we do. Let </s><s>[INST] me ask you in your book on the future prospects for humanity. You imagine a time machine that allows you to send a tweet length message to scientists in the past, like the Newton. Um what tweet would you send? That's an interesting thought experiment. What message would you send to Newton about what we know today? Well, [/INST] I think he'd love to know that there were planets around other stars. He'd he'd like to know that </s><s>[INST] that would really blow his mind. [/INST] He'd like to know that everything was made of atoms. He'd like to know that if he looked a bit more carefully through his prisms and looked at light, not just from the sun, but from From some flames, he might get the idea that different substances emitted light of different different colors and he might have been twigged to discover some things that had to wait two or 300 years could have given those clues. I think </s><s>[INST] it's kinda, it's fascinating to think to look back at how little he understood people at that time, understood about our [/INST] world </s><s>[INST] and [/INST] certainly about the cosmos because of course, </s><s>[INST] if [/INST] You think about astronomy then until about 1850, um astronomy was a matter of the positions of how the stars and the planets moved around. Of course that goes back a long way, but Newton understood why the planets moved around in ellipses, but he didn't understand why the solar system was all in a plane, what we called the ecliptic. And he didn't understand it. No one did till the mid 19th century, what the stars are made of, I mean, they were thought to be made of some fifth essence, not earth, air, fire and water, like everything else. And it was only after 18 50 when people did use prisms were precisely to get to get spectrum, that they realized that the sun was made of the same stuff as the earth and indeed the stars were. And it wasn't till 1930 the people I knew about nuclear energy and knew what kept the sun shining for for so long. So it was quite late that some of these key ideas came in, you know, which would completely transform Newton's views and of course the entire scale of the of the galaxy and the rest of the universe came later, </s><s>[INST] what he would have thought about the Big Bang or even just general relativity, gravity, just just him and Einstein talking for for a couple of weeks, would he be able to make sense of space time and the curvature of space time and [/INST] well, I think given a quick course, I mean he was sort of uh if one looks back, he he was really a unique intellect in a way, you know, and uh he said that he thought better than everything everyone else by thinking on things, continually thinking very deep thoughts and so he was utterly remarkable intellect obviously. But of course scientists aren't all like that. I think it's the one thing that interested me having spent a life among scientists is what a variety of mindsets and mental styles they have and well, just a contrast Newton and Darwin Darwin said and correct as he, that he thought he just had a as much sort of common sense and reasoning power as the average lawyer. That's probably true because his ability was to sort of collect data and think through things deeply. That's quite different kind of thinking from what was involved in a Newton or someone doing abstract mathematics, </s><s>[INST] I think in the 20th century, the coolest, Well, there's the theory, but from a astronomy perspective black holes is one of the most fascinating entities to have been through theory and through experiment to have emerged [/INST] obviously, I agree it's an amazing story that um well of course what's interesting is Einstein's reaction, because of course, although as you know, we now accept this is one of the most remarkable predictions of Einstein's theory, he never took it seriously, even believed it, although it was a consequence of uh A solution of these equations, which someone discovered just a year off his theory, Sword Shield, but he never took it seriously, and others did. But then of course, well this is something that I've been involved in actually finding evidence for black holes and that's come in the last 50 years. And so now there's pretty compelling evidence that they exist um as the remnants of stars or big ones in the centers of Galaxies, and we we understand uh what's the, what's going on? We have ideas on how they form, and of course gravitation waves have been detected and that's an amazing piece of technology, </s><s>[INST] ligo is one of the most incredible engineering f all time. [/INST] That's an example where the engineers deserve the most of the credit because the precision is well, as I said, it's like measuring the thickness of a hair and traditions of alpha, centauri. </s><s>[INST] Yeah, it's incredible. 10 [/INST] To -21. </s><s>[INST] So maybe actually if we step back, what are black holes, what do we humans understand about black holes and what still [/INST] Einstein's theory extended by people like Roger Penrose tells us that black holes are in a sense of other, simple things, basically, because they are solution of Einstein's equations and the thing that was shown in the 19 sixties by roger Penrose in particular and by a few other people, was that a black hole when it forms and settles down, is defined just by two quantities, its mass and its spin. So they're actually very standardized objects. It's amazing that objects as standardized as that can be so big and can lurk in the solar system and so that's the situation for a ready forms, black hole. But the way they form obviously is very messy and complicated. Um and uh one of the things that I've worked on a lot is what the phenomena are, which are best attributed to black holes and what may lead to them and all that and which </s><s>[INST] can you explain to that? So what what what are the different phenomena that detail black hole? Let's let's talk about it. [/INST] Okay, well, </s><s>[INST] so Yes. [/INST] Okay, okay, Well, I mean, I think one thing that only became understood really in the 19 fifties I suppose and beyond was how stars evolved differently, depending on how heavy they are. This is the sun burns highs into helium and then managed to run out of that contract to be a white dwarf and we know how long that will take about 10 billion years all together for its lifetime. But big stars burn up their fuel more quickly and more interestingly because when they've turned into helium, they then get even hotter so they can fuse helium into carbon and go up the periodic table and then they eventually explode when they have an energy crisis and they blow out that person's material, which as a digression is crucially important because all the atoms inside our bodies were synthesized inside a star, A star that lived and died more than five billion years ago before our services informed. And so we have inside us atoms made in 1000 different stars all over the Milky way. And that's an amazing idea. And my predecessor Fred Hoyle in 1946 was the first person to suggest that idea. And that's been borne out. That's a wonderful idea. So that's how massive stars explode and they leave behind something </s><s>[INST] which is [/INST] Very exotic and of two kinds, one possibility a neutron star. And these were first discovered in 1967-68. These are stars a bit heavier than the sun, which are compressed to an amazing density. So the whole mass of more than the Sun's mass is in something about 10 miles across. So they're extraordinary dense. The exotic physics. And and they they've been studied in immense detail and they've been real laboratories because the good thing about astronomy apart from explore what's out there, is to use the fact that the cosmos has provided us with a lab far more extreme conditions that we could ever simulated. So we learned lots of basic physics from looking at these objects and that's been two neutron stars. But for black holes, that's even more true because the bigger stars when they collapse, they leave something behind in the center, which is too big to be a stable by two or four neutron star becomes a black hole. And we know that there are lots of black holes weighing about 10 or up to 50 times as much as the sun, which are the remnants of stars. They were detected 1st 50 years ago when the black hole was orbiting around another star and grabbing material from the other star which swirled into it and gave us x rays. So the X rays astronomers found these objects orbiting around an ordinary star and emitting X ray radiation very intensely varying all of a sudden short timescale. So something very small and dense was giving that radiation that was the first evidence for black holes. But then the other thing that happened was realizing that there was a different class of monster black holes in the centers of Galaxies and these are responsible what's called quasars, which is when something in the center of the galaxy is grabbing some fuel and outshines all the 100 billion stars. Also in the rest of the galaxy, </s><s>[INST] giant beam light. [/INST] And in many cases it should be, it should be, it should be </s><s>[INST] is that that's got to be the most epic thing the universe produces is quasars. [/INST] Well, it's it's a debatable, but quasars maybe or maybe a gamma ray burst or something. But there they are remarkable and that they were a mystery for a long time. And there were things I worked on in my younger days. So </s><s>[INST] even though they're so bright, they're still a mystery. And [/INST] but I wouldn't say I </s><s>[INST] only see them [/INST] a little mystery now. I think we do understand basically what's going on, how </s><s>[INST] we're quasars discovered. [/INST] Well, they were discovered when astronomers found things that looked like stars and that they were small enough to be a point like not resolved by a telescope but outshone an entire galaxy. And yes, but but then they realized that what they were, they were uh object which we now know black holes and they were black holes were capturing gas and that gas was getting very hot, but it was producing far more energy than all the stars added together. And it was the energy of the black hole That was lighting up all the gas in the galaxy. So, you've got a spectrum of it. So this was something which was realized from the 1970s onwards. And as you say, the other thing we've learned is that they often do produce these jets squirting out, which can be detected in in all wave band. So there's now a picture </s><s>[INST] black hole generating jets of light in the center of most Galaxies. Do we know? Do you ever since? If every galaxy has one of these big big boys, big black holes, [/INST] most Galaxies have big black holes, they vary in size, The one in our galactic center. </s><s>[INST] Do we know much about ours? [/INST] We do, yes, we we know it weighs about as much as four million suns, which is less than some of the several billion other Galaxies. And but we know this isn't very bright or conspicuous and that's because not much is falling into it at the moment. If a black hole is isolated, then of course it doesn't radiate it. Only all that radiates is gas swirling into it which is very hot or has magnetically </s><s>[INST] that's only radiating the thing. It's murdering or consuming however you put it. [/INST] Yeah, that's right. And so so it's thought that our galaxy may have been bright bright at some time in the past. But now that's when the black hole forms or grew but but now it's not capturing very much gas. And so it's it's rather it's rather faint and detected indirectly and by a fairly weak radio mission. And and so I think the answer to your question is that we suspect that most Galaxies have a black hole in them. So that means that some stays in their lives or maybe one or more stages. They went through a phase of being like a quasar where that black hole captured gas and became very, very bright. But for the rest of the lives, the black holes are fairly quiescent because there's not much gas falling into them. </s><s>[INST] And so this universe of ours is sprinkled a bunch of Galaxies and giant black holes was [/INST] like </s><s>[INST] very large number of stars orbiting these black holes and then planets orbiting likely, it seems like planets orbiting almost every one of those stars. [/INST] And </s><s>[INST] just this beautiful universe of ours. What happens when Galaxies collide when these two big black holes collide? Is that well, [/INST] what would happen? Is that well? And I should say that this is going to happen near us one day, but not for four billion years because the Andromeda galaxy, which is the biggest galaxy near to us, it is about three million light years away, which is a big disk galaxy black holders hub rather like our Milky Way and that's uh in falling towards us because they're both in a common gravitational potential. Well, and that will collide with our galaxy in about four billion years. </s><s>[INST] It'll be, it'll be maybe it'll be lesser collision and more of a dance because it'll be like a swirling situation [/INST] swirling, but eventually it will be to be a merger that they go through each other and then merge. In fact the nice movies to be made of this, you know, computer simulations and it will go through. Um and then um there's a black hole in the sense of diameter and our galaxy and the galax, the black holes will settled towards the center, then they will orbit around each other very fast and then they will eventually merge and that will produce a big burst of gravitational waves. Very big burst </s><s>[INST] that an alien civilization with a ligo like detector will be able to detect Yes [/INST] and in fact well but we can detect these with their lower frequencies than the ways that will be detected by ligo. So there's a space interferometer which can detect these about it's about one cycle per hour Rather than about a 100 </s><s>[INST] cycles per second, [/INST] the ones that detected. But that that will happen. But thinking back to what will happen in four billion years to any of our descendants, they'll be okay because the two disk Galaxies will merge. It will end up as a sort of amorphous elliptical galaxy but the stars won't be much closer together than they are now. It'll still be just twice as many stars in the structure almost as big. And so the chance of another star colliding with our son would still be very small because </s><s>[INST] there's actually a lot of space [/INST] between. Indeed, </s><s>[INST] yes. The [/INST] chance of a star getting close enough to affect our solar system's orbit is small and it won't change that very much so that we could be reassured </s><s>[INST] a heck of a starry sky though. Well [/INST] it won't make much different teams of that actually would </s><s>[INST] look kind of beautiful when you're swirling or going so slowly. [/INST] But they're far away. So twice as many stars in the sky. Yeah but </s><s>[INST] the pattern changes. The [/INST] pattern will change a bit and there won't be The Milky Way with the Milky Way across the sky is because we are looking in the disc of our galaxy and you lose that because the disk will be disrupted and it will be a more sort of spherical distribution. And of course many Galaxies are like that. Um and that's probably because they have been through mergers of this kind. </s><s>[INST] If we survive four billion years, we would likely be able to survive beyond that. What what's the other thing on the horizon for humans? Uh in terms of the sun burning out all those kinds of interesting cosmological threats to our civilization? [/INST] Well, I think on the cosmological timescale because it won't be humans because </s><s>[INST] something else, even [/INST] if evolution is going no faster than Darwinian and I would like it will be faster Darwin in the future. Then we're thinking about six billion years before the sun dies. So any entities watching the death of the sun, if they're still around, they'll be as different as much as we are from slime mold or something, you know, far more different still, if they become electronic. So on that time scale we just can't predict anything. But I think going back to um to the human timescale then we've talked about whether there'll be people on mars by the end of a century. And even in his long perspective then indeed, this century is very special because it may see the transition between purely flesh and blood entities to those which are sort of cyborgs. And that'll be an important transition in in biology and complexity in this century. But of course the other importance and this has been the theme of a couple of my older books is that this is the first century when one species, namely our species, has the future of the planet in his hands. And that's because of two types of concerns. One is that there are more of us where more demanding of energy and resources and therefore we are for the first time changing the whole planet through climate change, loss of biodiversity and all those issues. This has never happened in the past because having enough humans have been much in power. So this is uh an effect that's obviously is how on everyone's agenda now and rightly so because we've got to ensure that we leave heritage that isn't eroded or damaged to future generations. And so that's one class of threats. But there's another thing that worries me, perhaps more than many people seem to worry. And that's the threat of misuse of technology. And this is particularly because technologies empower even small groups of malevolent people or indeed in careless people to create some effect which could cascade globally and take an example, um a dangerous pathogen or pandemic. I mean, my worst nightmare is that there could be um some small group that can engineer a virus to make it more virulent or more transmissible than a natural virus. This is so called gain of function experiments which were done on the flu virus 10 years ago and can be done for others. Um and of course we now know from Covid 19 that our world is so interconnected That a disaster in one part of the world can't confines of that past was spread globally. So it's possible for a few dissidents with expertise in biotech could create a global catastrophe of that kind. And also I think we need to worry about very large scale disruption by cyber attacks. In fact, I quote in one of my books, a 2012 report from the American Pentagon about the possibility of a state level cyber attack on the electricity grid in Eastern United States, which is, it could happen. And it says that at the end of this chapter that this would merit a nuclear response. It's pretty scary possibility. That was 10 years ago. And I think now what would have needed a state actor then could be done perhaps by a small group in fire by ai. And so there's obviously been a an arms race between the cybercriminals and the cybersecurity people not clear which side is winning. But the main point is that as we become more dependent on more integrated systems, then we get more vulnerable and uh and and so we have the knowledge then the misuse of that knowledge becomes more and more of a threat and that's a bio and cyber are the two biggest concerns. Um and and if we depend too much on ai and complex systems then just breakdowns, it may be that they break down. And even if it's innocent breakdown, then maybe pretty hard to mend it and just think how much worse the pandemic would have been if we'd lost the internet in the middle of it. It was we depended more than ever for communication, everything else on on the internet and zooms and all that. Um and if that had broken down and that would have made things far worse. And those are the kinds of threats that we, I think need to be more energized and politicians need to be more energized to minimize. And one of things I've been doing the last year through being a member of our part of our parliament is sort of, I have to instigate a committee to think more on better preparedness for extreme technological risks and things like that. So there are concern in my mind that we've got to make sure that we can benefit from these advances but safely, because the stakes are getting higher and the benefits are getting great as we know huge benefits from computers, but also huge downsides as well. </s><s>[INST] And one of the things this war in Ukraine has shown, one of the most terrifying things outside of the humanitarian crisis is that at least for me, I realized that the human capacity to initiate nuclear war is greater than I thought. I thought the lessons of the past have been learned. It seems that we hang on the brink of nuclear war with this conflict, like every single day with just one mistake or bad actor or [/INST] the </s><s>[INST] actual leaders of the particular nations launching a nuclear strike and all hell broke breaks loose. So then add into that picture, cyber attacks and so on. They can lead to confusion and chaos. And then out of that confusion, um, calculations are made such that uh a nuclear launches A nuclear weapon is launched. And it's and then you're talking about, I mean, I don't direct probably, of humans on earth are dead instantly. And then the rest, I mean, it's basically 99% of the human population is wiped out in the period of well, it's not [/INST] that bad, but we are devastating for civilization of course. And of course you were quite right that this could happen very quickly because of um, you know, information coming in and there's a there's hardly enough time for human collected and careful thought. And there have been recorded cases of false alarms, several where um, where have been suspected attacks from the other side. And fortunately they've been really to be false alarms soon enough. But this could happen. And there's a new class of threats actually, which in our center in Cambridge people are thinking about, which is that the commander control system Of the nuclear weapons and the submarine fleet and all that is now more automated and could be subject to cyber attacks. And that, that's a new threat which didn't exist 30 years ago. And so I think indeed, it's we're in a sort of scary world I </s><s>[INST] think. [/INST] And it's because things happen faster and human beings aren't in such a direct and immediate control because so much is delegated to machines and also because the world is so much more interconnected, then some local event can cascade globally in a way I never could in the past and much faster. </s><s>[INST] Yeah, it's a double edged sword because the interconnectedness brings, uh, um, brings a higher quality of life across a lot of metrics. [/INST] Yeah, it can do. But of course there again, I mean if you think of supply chains where we get stuff from around the world and um, one lesson we've learned is that there's a trade off between resilience and efficiency and his resilient to have an inventory and stock and to depend on local supplies where it's more efficient to have long supply change. But the risk there is that a break in one link in one chain Can screw up car production and this has already happened in the pandemic. So there's a trade off and there are other examples. I mean, for instance, the other thing we learned was that it may be efficient to have 95% of your hospital intensive care beds occupied all the time, which has been the UK situation. Whereas to do what the Germans do and always keep 20% of them free for an emergency is really a sensible precaution. And so I think we've probably learned a lot of lessons from COVID-19 and they would include rebalancing the trade off between resilience and efficiency </s><s>[INST] Boy. The fact that COVID-19 a pandemic that could have been a lot, a lot worse, brought the world to its knees anyway. It [/INST] could be far worse in terms of its a fatality rate of </s><s>[INST] fatality rate. Yes. [/INST] Yeah. So </s><s>[INST] the fact that that I mean revealed so many flaws in our human institutions. [/INST] Yeah. Yeah. And I think I'm rather pessimistic because um I do worry about the bad actor or a small group who can produce catastrophe. And if you imagine someone with access to the kind of equipment that's available in university labs or industrial labs and they could create some dangerous pathogen, then even one such person is too many. And how can we stop that? Because it's true that you can have regulations. I mean academies are having meetings etcetera about how to regulate these new biological experiments, et cetera, make them safe. But even if you have all these regulations then enforcing regulations is pretty hopeless. We can't enforce the tax laws globally. We can't enforce the drug laws globally. And so similarly, we can't readily enforce the laws against people doing these games experiments, even if all the governments say they should be prohibited. And so my my line on this is that all nations are going to face a big trade off between three things. We value freedom, security and privacy. And I think um, different nations will make that choice differently. Um, the chinese would give up privacy and have more security, if not more liberty, but I think um in in our countries, I think we're going to have to give up more privacy. </s><s>[INST] That's a really interesting trade off. But there's also something about human nature here where I personally believe that all humans are capable of good and evil. And there's some aspect to which we can fight this by encouraging people incentivizing people towards the better angels of their nature. So, uh, in order for a small group of people to create to engineer deadly pathogens, you have to have people that for whatever trajectory took them in life, wanting to do that kind of thing. And if we can aggressively work on a world that sort of sees the beauty and everybody and encourages the flourishing of everybody in terms of mental health, in terms of meaning, in terms of all those kinds of things, that's one way to fight the development of of weapons that can lead to atrocities. [/INST] Yes, and I completely agree with that and to reduce the reason why people feel embittered, but of course we've got a long way to go to do that, because if you look at the present world, um nearly everyone in Africa has reason to feel embittered because their economic development is lagging behind most of the rest of the world. And the prospects of getting out of the poverty trap is is rather bleak, especially as the population grows, because for instance, they can't develop like the Eastern tigers by chief manufacturing because robots are taking that over so that they will naturally feel embittered by the inequality. And of course, what we need to have is some sort of mega version of the marshall plan that helped europe in the post World War two era to enable Africa to develop that will be not just an altruistic thing for europe to do, but in our interest, because otherwise Those in Africa will feel massively disaffected. And indeed it's a manifestation of the excessive inequality, the fact that the 2000 richest people in the world have enough money to double the income of the bottom billion. And that's uh you know, an indictment of the ethics of the world. And this is where I, my friend Steven Pinker and I have had some contact, we wrote joint articles on bio threats and all that. Um but he writes these books being very optimistic about quoting figures about how um life expectancy has gone up, infant hotel has gone down, literacy has gone up and all those things, and he's quite right about that. Um and so he says the world's getting getting better. Do </s><s>[INST] you disagree with your friends to Pinker? [/INST] Well, I mean, I agree with those facts. Okay, But but I think he misses he misses out part of the picture because there's a new class of threats which hang over us now, which didn't hangovers in the past. And I would also question whether we have collectively improved our ethics at all, because let's think back to the Middle Ages, it's truth, as Pinker says, the average person was in a more miserable state than they are today, on average, for all the reasons he quantifies, that's fine. </s><s>[INST] But [/INST] in the Middle Ages there wasn't very much that could have been done to improve people's lot in life because of lack of knowledge and lack of science etcetera. So the gap between the way the world was, it was pretty miserable and the way the world could have been, it wasn't all that much better, was fairly narrow. Whereas now the gap between the way the world is and the way the world could be is far far wider and therefore I think we are ethically more at fault in allowing this gap to get wider than it was in medieval times. And so I would very much question disputes the idea that we are ethically um in advance of our predecessors </s><s>[INST] that's collected a lot of interesting hypotheses in there. And I don't, there it's a it's a fascinating question of how much is the size of that gap between the way the world is in the way the world could be, is a reflection of our ethics. Or maybe sometimes it's just a reflection of a very large number of people. Uh like maybe it's a technical challenge to. It's not just [/INST] a political systems, </s><s>[INST] political systems like how many and we're trying to figure this thing out. Like there's 20th century tried this thing that sounded really good on paper of collective, the communism type of things. It's like turned out at least the way that was done there, at least atrocities and the suffering and the murder of tens of millions of people. Okay, so that didn't work. Let's try democracy. And that seems to have a lot of flaws, but it seems to be the best thing we've got so far. So we're trying to figure this out as our technology has become more and more powerful, have the capacity to do a lot of good to the world, but also, unfortunately, have the capacity to destroy the entirety of the human civilization. [/INST] And I think it's social media generally, which makes it harder to get a a sort of moderate consensus because in the old days when people got their news filtered through responsible journalists in this country, the BBC and they made newspapers, et cetera, they would muffle the crazy extremes, whereas now, of course there there on the internet and if you click and then you get something more extreme. And so I think we are seeing a sort of dangerous polarization which I think is going to make all countries hard at the governor that something we find pessimistic about. </s><s>[INST] So to push back it is true that brilliant people like you highlighting the limitations of social media is making you realize the stakes and the failings of social media companies, but the same time they're revealing the division. It's not like they're creating it, they're revealing it in part. And so that puts a lot of uh that puts the responsibility into the hands of social media and the opportunity in the hands of social media to alleviate some of that division. So it could in the long arc of human history result. So bringing some of those divisions and the anger and the hatred to the surface so that we can talk about it. And as opposed to disproportionately promoting it actually just surfacing it so we can get over. [/INST] You're assuming that the fat cats are more public spirited than the politicians. And I'm not sure about that. </s><s>[INST] I think there's a lot of money to be made in being publicly spirited. I think there's a lot of money to be made in increasing the amount of love in the world despite the sort of public perception that all the social media companies heads are interested in doing is making money. I think that may be true, but I just personally believe people being happy is a hell of a good business model and so making as many people happy, helping them flourish in a long term way. That's a lot of ways to make that's a good way to make. [/INST] I think guilt and shame are good motives to make you behave better in future. </s><s>[INST] Okay, so most [/INST] experience </s><s>[INST] for maybe in the political perspective, certainly case, but it does make sense now that we can destroy ourselves with nuclear weapons with engineered pandemics and so on, that the aliens would show up that if I was the um you know, had a leadership position, maybe as a scientist or otherwise in an alien civilization and I would come upon earth, I would try to watch from a distance, do not interfere and I would start interfering when these life forms start becoming quite have the capacity to be destructive. And so, I mean, it is an interesting question when people talk about Ufo sightings out and all those kinds of things that at least [/INST] benign? </s><s>[INST] Yes, I mean they benign, almost curious, almost. Um partially as with all curiosity partially selfish to try to observe. Is there something interesting about this particular evolutionary system? Because I'm sure even to aliens, earth is a curiosity [/INST] Yeah, very special stage, </s><s>[INST] perhaps [/INST] in this century is very </s><s>[INST] special among [/INST] The 45 million centuries, the Earth experienced already. So it is a very special time where they should be specially interested. But I think going back to the politics and the other problem is getting People who have short term concerns to care about the long term by the long term. I now mean, just looking 30 years or so ahead, you know, I know people who've been scientific advisors to governments and things and they may make these points, but of course they don't have much traction because, as we know very well, any politician has an urgent agenda of very worrying things to deal with. And so they aren't going to prioritize these issues which are longer, longer term unless immediate and don't just concern their constituents, that they concern distant parts of the world. And so I think, I think what, what we have to do is to enlist charismatic individuals, convert the public, because if the if the politicians know the public care about something climate change as an example, then they will make decisions which take cognizance of that. Um, and I think for that to happen, then we do need some public individuals who are respected by everyone, um, and to have a high profile and in the climate context, I would say that I've mentioned four very desperate people who've had such a big effect in the last few years. One is Pope Francis, the others, David Attenborough, the others, Bill Gates and the others greater Thornburgh. And those four people have certainly had a big shift in public opinion and uh and even change the rhetoric of business, although how deep that is, I don't know, and so, but but but but politicians can't let these issues drop down off the agenda, um if there's a public clamor and it needs people like that to keep the public clamor going </s><s>[INST] to push back a little bit. So, those four are very interesting and I have deep respect for them. They have, except David Attenborough. Uh David Attenborough is really, I mean, everybody loves him. I mean, I can't say, but, you know, Bill Gates and Greta, there is that they also create a lot of division [/INST] and </s><s>[INST] this is a big problem. So it's not just charismatic, I put that responsibility actually in the scientific community [/INST] and yeah, </s><s>[INST] uh and the politicians, so we need the charismatic leaders and their rare, when you look at human history, those are the ones that make a difference. Those are the ones that um not the ride, they inspire the populace to think long term the JFK we do will go to the moon in this decade. Not because it's easy, but because it is hard, there's no discussion about like um short term political gains or any of that kind of stuff uh in in the vision of going to the moon, going to mars or taking on gigantic uh projects are taking on world hunger or taking on climate change or uh the education system, all those things that require long term significant investment that requires. [/INST] It's hard to find those people. And and incidentally, I think another problem which is a downside of social media is that of younger people. I know um the number who would contemplate a political career has gone down because of the pressures on them and their family from social media. Um it's a hell of a job now. Um and so I think we are all losers because the quality of people who choose that path is um is really dropping. And as we see by the quality of those who are in these compositions </s><s>[INST] that said, I think the civil lining there is the quality of the competition Actually is inspiring because it's it's it shows to you that there's a dire need of leaders, which I think would be inspiring to young people to step into the whole great leaders are not afraid of a little bit of a little bit of fire on social media. So, if you have, you have a 20 year old kid now, a 25 year old kid is seeing how the world respond, respond to the pandemic, Seeing the geopolitical division over the war in Ukraine, seeing the brewing war between the west and china, we need create leaders and there's a hunger for them and the time will come when, when, when they step up. I I I I believe that, but also to add to your list of four, he doesn't get enough credit. I've been defending him in this conversation. Elon musk in terms of the fighting climate change, but he also has led to a lot of division, but we need more David Edinburgh. Yeah, [/INST] No, no, I mean I'm a fan. Um, </s><s>[INST] definitely. I [/INST] Mean I've heard him described as the 21st century Brunel for his innovation and that that's true. But um, whether he's an ethical inspiration, I don't </s><s>[INST] know. Yeah, he has a lot of fun on twitter. Well, let me ask you to put on your wise sage. Hat, what advice would you give to young people today? Maybe they're teenagers in high school, maybe early college. What advice would you give to a career or have a life they can be proud of? [/INST] Yes, Well, I'd be very diffident really about offering any any wisdom, but I think, I think they should, they should realize that uh, the choices they make at that time are important and from the experience of, I've had many friends, many people don't realize that opportunities open until it's too late. They somehow think that some opportunities are only open to a few privileged people and they don't even try and and that they could succeed. But if I focus on people working in some professor I know about like science, I would say pick an area to work in where new things are happening, where you can do something that the old guys never had a chance to think about. Don't go into a field that's fairly stagnant because then it won't be much to do or you'll be trying to tackle the problems that the old guys got stuck on. And so I think in science I can give people good advice that they should pick us up subject where there are exciting new developments and also of course something which suits their style because even within science, which is just one profession, there's a big range of style between the sort of solitary thinker, the person does fieldwork, the person who works in a big team etcetera and whether you like computing or mathematical thought etcetera. So pick some subject that suits your style and where things are happening fast and be prepared to be flexible. That's what I'd say, really </s><s>[INST] keep your eyes open for the opportunity throughout. Like you said, go to a new field, go to the field with new cool stuff is happening. You just keep your eyes open. [/INST] That's platitudinous. But I think most of us, I include myself in this, didn't realize these sorts of things too late. </s><s>[INST] Yeah, I think this applies way beyond science. Um what do you make of this finite nous of our life? Do you think about death? Do you think about mortality? Do you think about your mortality? And are you afraid of death? [/INST] Well I mean I'm not afraid because I I think I'm lucky. I feel lucky to last as long as I have. Um and uh and to have been fairly lucky and um in my life in many respects compared to most people. So I feel very fortunate. This reminds me of this current emphasis on living much longer than the so called Altos laboratories which have been set up by billionaires. Um This one in san Francisco, one in uh La Hoya I think and one in Cambridge and then they're funded by these guys who when young wanted to be rich and now they're rich. They want to be young. Again they won't find that quite so easy. And do we want this? I don't know if there was some elite that was able to do much longer than others not to be a really fundamental kind of inequality. And I think if it happened to everyone then that might be an improvement. It's not so obvious. But I think um for my part I think to have lived as long as most people and had a fortunate life is all I can expect a lot to be grateful for. Those are all past issues. </s><s>[INST] Well, I am incredibly honored that you sit down with me today. I thank you so much for life of exploring some of the deepest mysteries of our universe and um of our humanity and thinking about our future with existential risks that are before us. Um it's it's a huge honor martin that you sit with me and I really enjoyed it and [/INST] well thank you lex I thought we couldn't go on for as long as this could have gone much longer. </s><s>[INST] Exactly, thank you so much. Thank you for listening to this conversation with martin Rees to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Martin Rees himself. I'd like to widen people's awareness of the tremendous time span lying ahead for our planet and for life itself. Most educated people are aware that were the outcome of nearly four billion years of Darwinian selection, but many tend to think that humans are somehow the culmination. Our son, however, is less than halfway through its lifespan, will not be humans who watch their son's demise six billion years from now. Any creatures that then exist will be as different from us as we are from bacteria or amoeba. Thank you for listening. I hope to see you next time [/INST] </s>
<s>[INST] not, acid mushroom and that's it. Uh and also edibles. But that's, there's some psychedelic properties to them. But um, but yeah, mushroom mushrooms uh, several times and always had an incredible experience. Exactly the kind of experience you're referring to, which is if it's true that language constrains our experience. It felt like I was removing some of the constraints because even just the most basic things were beautiful in the way that I wasn't able to appreciate previously like trees and nature and so on. [/INST] Yeah. And the experience of coming down is an is an experience of encountering the futility of capturing what you just saw a moment ago in words right? Like especially if you have any part of your your self concept and your ego program is to be able to capture things in words. And if you're a writer or a poet or or a scientist is someone who wants to just encapsulate the profundity of what just happened the the total fatuous nous of that enterprise when you really have gotten when you have taken a whopping dose of psychedelics and you begin to even gesture at describing it to yourself so that you could describe it to others. It's just it's like trying to you know thread a needle using your elbows. I mean it's like you're you're trying something they can't it's like the beer gesture proves its impossibility. Uh And it's um So yeah so that I mean that for me that that suggests just empirically on the first person side that it's possible to put yourself in a in a condition where it's clearly not about language structuring your experience and your having much more experience than you you tend to. So the primacy of languages primary for some things, but ah it's it's certainly primary for certain kinds of concepts and certain kinds of semantic understandings of the world. But it's uh it's clearly more to mind than the conversation we're having with ourselves or that we can have with others, </s><s>[INST] can we go to that world of psychedelics for for a bit. Sure. Where do you think? Uh So joe Rogan apparently and many others uh meet apparently elves when they on D. M. T. A lot of people report this kind of creatures that they uh and again it's probably the failure of language to describe that experience. But Dont is an interesting one. There's uh as you're aware there's a bunch of studies going on on psychedelics psychedelics currently. M. D. M. A. Um uh psilocybin and uh john Hopkins and much other places. But D. M. T. They all speak of as like some extra super level of a psychedelic. Yeah. Do you have a sense of where it is? Our mind goes on ah in second on psychedelics but in in D. M. T. Especially. [/INST] Well unfortunately I haven't taken Gmt. </s><s>[INST] So unfortunately unfortunately unfortunately unfortunately [/INST] uh although it's I presume it's in my body as it is in uh everyone's brain and in many many plants apparently but I've wanted to take it I haven't had an opportunity that was presented itself that where it was obviously the right thing for me to be doing. Ah But you know for those who don't know D. M. T. Is is often touted as the most intense psychedelic and also the shortest acting you smoke it and it's it's basically a 10 minute experience where a or a three minute experience within like a 10 minute window Uh that when you're really down after 10 minutes or so. Um And Terence McKenna was a big proponent of DMG, that was, that was his, you know, the center of the bullseye for him psychedelically apparently. Um and it does, it is characteristics seems for many people by this phenomenon which is which is unlike virtually any other psychedelic experience, which is your your it's not just your perception being broadened or changed its you according according to Terence McKenna feeling fairly unchanged but catapulted into a different circumstances. You have been shot elsewhere and find yourself in relationship to other entities of some kind. So the place is populated with things that seem not to be your mind. </s><s>[INST] So it does feel like travel to another place because you're on change yourself [/INST] according again, I just have this on the authority of the people who have described their experience, but it sounds like it's it's pretty common, it sounds like it's pretty common for people not to have the full experience because it's apparently pretty unpleasant to smoke. So it's getting enough on board in order to get shot out of the cannon uh and land among the what mechanic called uh self transforming machine elves um that appeared to him like jeweled faberge egg like self dribbling basketballs that were handing him uh completely un interpret herbal reams of profound knowledge. Um it's a, it's an experience I haven't had, so I just have to accept that people have had it. Um I would just point out that our minds are clearly capable of producing apparent others on demand, that are totally compelling to us, right? There's no there's no limit to our ability to do that. As anyone who's ever remembered a dream kind of test every night we go to sleep. Some of us don't remember dreams very often, but um some dream vividly every night and just think of how insane that experiences. I mean, you've forgotten where you were, right? That's the strangest part of this is psychosis, right? You're you have you have lost your mind, you have lost your connection to your episodic memory or even your expectations that reality won't undergo wholesale changes a moment after you have closed your eyes, right? Like you're you're in bed, you're, you know, watching something on netflix, you're waiting to fall asleep and then the next thing that happens to you is impossible. And you're not surprised, right? You're talking to dead people, you're hanging out with famous people, your your uh someplace you couldn't physically be, you can fly. And even that's not surprising, right? So if you have lost your mind, but relevantly for this, </s>
<s>[INST] So there's some kind of invisible momentum that some people like Einstein or opening eyes plugging into, that's anybody else can also plug into, and ultimately, that wave takes us into a certain [/INST] Direction. That's right, that's right, that's right. And, you know, this kind of seems to play out in a bunch of different ways that there's some exponential that is being written and that the exponential itself, which one it is, changes think about Moore's law. An entire industry set its clock to it for 50 years like how can that be right? How is that possible? And yet somehow it happened. And so I think you can't hope to ever invent something that no one else will, maybe you can change the timeline a little bit, but if you really want to make a difference. I think the thing that you really have to do, the only real degree of freedom you have is to set the initial conditions under which the technology is born. And so you think about the internet Right? There are lots of other competitors trying to build similar things and the Internet one. And that the initial conditions where there is created by this group that really valued people being able to be, Uh, you know, anyone being able to plug in this very academic mindset of being open and connected. Um, and I think that the Internet for the next 40 years really played out that way. Um, you know, maybe today things are starting to shift in in a different direction, but I think that those initial conditions were really important to determine the next 40 years worth of progress. </s><s>[INST] That's really beautifully put. So, another example of that, I think about, you know, I recently looked at it, I looked at Wikipedia the formation of Wikipedia and I wonder what the internet would be like if Wikipedia had ads. You know, there's an interesting argument that why they chose not to make it put advertisement on Wikipedia. I think it's uh, I think Wikipedia is one of the greatest resources we have on the internet. It's extremely surprising how well it works and how well it was able to aggregate all this kind of good information. And essentially the creator Wikipedia, I don't know, there's probably some debates there, but set the initial conditions and now it carried itself forward. That's really interesting. So you're, the way you're thinking about A G. I. Or artificial intelligence is you're focused on setting the initial [/INST] conditions for for the progress. That's </s><s>[INST] right. That's powerful. Okay, so look into the future, if you create an A G. I. System, like one that can ace the turing test natural language, what do you think would be the interactions you would have with it? What do you think are the questions you would ask? Like what would be the first question you would ask? It hurt [/INST] him. That's right. I think that at that point if you've really built a powerful system that is capable of shaping the future of humanity, the first question that you really should ask is how do we make sure that this plays out well? Um and so that's actually the first question that I would ask, a powerful A Gi system. So </s><s>[INST] you wouldn't ask your colleague, you wouldn't ask, like Elia, you would ask the Gi system, [/INST] We've already had the conversation with Ilya right? And everyone here and so you want as many perspectives and uh piece of wisdom as you can for answering this question. So I don't think you necessarily defer to whatever you're powerful system tells you, but you use it as one input to try to figure out what to do, but and I guess fundamentally what it really comes down to is if you built something really powerful and you think about think about for example the creation of uh shortly after the creation of nuclear weapons right? The most important question the world was what's the world we are going to be like how do we set ourselves up in a place where we're gonna be able to survive as a species with a G. I think the question is slightly different, right? That there is a question of how do we make sure that we don't get the negative effects? But there's also the positive side, right? You imagine that you know like like what will a G. I. B. Like what will be capable of? And I think that one of the core reasons that an A. G. I can be powerful and transformative is actually due to technological development, right? If you have something that's capable as capable as a human and that it's much more scalable that you absolutely want that thing to go read the whole scientific literature and think about how to create cures for all the diseases, right? You wanted to think about how to go and build technologies to help us create material abundance and to figure out societal problems that we have trouble with. Like how we're supposed to clean up the environment and you know maybe you want this to go and invent a bunch of little robots that will go out and be biodegradable and turn ocean debris into harmless molecules and I think that that that positive side is something that I think people miss sometimes when thinking about what an A. G. I. Will be like. Um And so I think that if you have a system that's capable of all of that, you absolutely want advice about how to make sure that we're using your your capabilities in a positive way for humanity. </s>
<s>[INST] And the only way you find that out is by doing a bunch of [/INST] doing a bunch of stuff and refining it. </s><s>[INST] That's hilarious. Yeah, that's brilliant. Um, so in terms of the career path of leaping into the startup world and launching a startup, what does it take to successfully found a startup to have a chance to succeed and maybe how you decide uh, to take that leap? Is there sort of having founded, having been part of many, the ones, many of some of the most successful, the ones ever, uh what's what's it take to take that leap? May believe your job a cushy job at a company and do the startup, [/INST] what does it take? It takes belief in yourself. That's the first thing, belief that you can do it not. But hopefully with mirrors or mentors around your coaches around you to make sure, you know, you're not crazy. It's a crazy smart idea, but you're not crazy and you're just working on something as a, like a lone madman or woman. You know, you have a great idea and like I said, great ideas chase you. You can in this world. There are so many people who have more ideas than they have time to implement. I used to be like that. I would like, oh my God, have this idea, this idea and you do, you try to do all of them. But the best ideas are the ones that you can really focus on and you, you shut out all those other things and you bring them other ideas into the thing you're trying to do. So I try to run away from a great idea and then it stalks me. It hunts you down because you're like, that's gonna have this problem. I'm going to put it aside and then all of a sudden, uh, you know, a few days later, oh, I think I know how to solve that problem or I talk to somebody and you just always kind of niggling around the edges of it and then at some point it's like, it just becomes, it becomes like this black hole that just sucks you and you're like, I can't think about anything else, but this, it's almost like a relationship in the world, right? You know, when you have it with you find your partner, you know, you're like, wait something and then your channel and then all of a sudden it just, it comes together, right? It's kind of like that </s><s>[INST] ultimately achieve folk, see I'm different, I just dive right in. I [/INST] used to do that too. I used to dive right in. </s><s>[INST] Yeah, [/INST] but I learned that you need to run away from run away from it. And so it chases you because it makes you think harder about that the story, </s><s>[INST] this is not dating advice we're [/INST] talking about, but </s><s>[INST] ultimately, so you have achieve uh focus on it. But you also said I so believe in yourself. So it's not necessarily even the idea is the human that believe in the human being, [/INST] you have to believe in yourself and the idea that you have, because if you don't have that belief, then you can't project that to other people to say join the team. </s><s>[INST] Uh Let me let me ask you, because you mentioned mentors and you've talked about having had incredible mentors in your life. You're also a mentor to a very large number of people. What does it take to find a mentor? How do you how do you find a great mentor? [/INST] Usually they also find you, </s><s>[INST] Is it like with the ideas? [/INST] No, no, no, no. What happens is you're in the right you have a community around you okay. And because you've been building a network because you can't do it alone so you have to create this network around you and of relationships that don't it's not transactions but relationships over time that you really cherish and people you talk to okay and you share vulnerable or nascent ideas with or crazy opinions with and then you argue them through but you start to see resonate and it's it's not about age, it's just about this connection right? I have mentors obviously when I was young all my mentors were older and as I get older I have mentors who are younger than me or the same age right? They're not all just older. Right? And so it's about that connection. It's about being on that same wavelength. But they also they can counterbalance </s><s>[INST] you. [/INST] They compliment you in some way. Like my best mentors had nothing to do with technology. They didn't know anything about </s><s>[INST] technology [/INST] right? The way we know it they were all about human nature and they could reflect that and help me get more human focused and more empathetic because I was so detailed in the technology I needed to see from other perspectives. But then they wanted to learn more about the technology right? Or they thought that this idea was so great that it should exist now. Let's work together on that. So it's really they have to find you and you have to find them and that's by sharing. You just don't go and look it up on, you know, on the internet and say who the best manners in the world, it just doesn't work that way. </s><s>[INST] So form a network of people and see where I mean, it's like finding relationships, finding love, all that kind [/INST] of friendship. </s><s>[INST] Uh venture capitalist money, do vcs help or hurt a business in general. So like in those early stages in the chase of developing a V. One just what's the constructive and destructive power of money in the development of a brilliant idea and the deployment of the brilliant idea. [/INST] I have seen brilliant venture capitalists, I have seen horrible ones, ones that care about their LPS more than they care about the entrepreneurs, of course everyone's in it. You know, at the end of the day, especially venture capital, they have to give a return to their, their limited partners, the people who invest in money that they, you know, that they have to shepherd that money and make sure it's watched over properly. But when there's not a balance a pushback in a venture capitals between what the LP needs and what the entrepreneur needs and that the entrepreneur might be trying really hard. But if they don't see the VC doesn't see the exit is going to happen in two years and they just leave them hanging when it's there's no the value exchange is only money and not mentorship or ideas or other things when there's not a relationship, but really a transaction that's when money is toxic because you can get money everywhere. Maybe it's a little harder today after, you know, over the last month. But you can still find people with money who are on that, who want to enable your mission and can be mentors. Not always not all of them, but some of them can be mentors, but they they're on your side. Then it's incredibly powerful because it's not just one plus one equals two, right? It's something bigger than that because then they can bring their networks of people and their networks of companies and other people they worked with that might want to join your your your mission, right? That's the kind of venture capitalists and and smart money that's out there, right? But you have to build a relationship. People go, oh look at that valuation. Oh, it's the brand name of the VC. That that's investing me. No, it boils down to who's that partner and how experienced are they don't just give me the brand, Give me the person because that's the person I'm gonna be interacting with. </s>
<s>[INST] just two humans doing something together. Yeah. And the healthcare system and the legal system should not get in the way of that. I mean, there's liability and all these kinds of things that can get in the way of the humanness. I mean, some of that is justified, you have to be careful, you have to make sure there's a responsible, [/INST] but a little too much can destroy the humanness. I'll use it where I don't usually say something is insane, like it's not consistent with sanity. Yeah. And the presence of the legal system, look, I'm all for, of course, physicians have to be held to be responsible and everybody makes mistakes and people have to be accountable for their mistakes. I understand all of that, but what we see now, it's so absurd that all like everyone is frightened, right? Everyone is frightened and then just looking to like, how do I slot into the box, check the boxes of what I'm supposed to do and not get in trouble? You know, people get sued because someone was at that hospital and that doctor touched their care. It happens in the VA system, it happens in other systems too. So you might've touched their care and no one's even saying you did anything wrong, but they say the next person did. Oh, someone settled on your behalf and now you have a malpractice ding and maybe you can't get a license somewhere else. Like doctors are terrified and they're terrified for good reason because the same society that has given doctors in many ways too much power over time and treated doctors maybe too much like God's now is I think enacting some of society's anger and envy out on the physicians. Even the idea that like a person would know what medicine, like I saw a couple of TV commercials, give me this. It's like, it's interesting, right? Because even if, let's say I take myself out of it, it doesn't feel good obviously, but it takes about, it's like, wow, like I went to school for like eight years for this and you don't even wanna hear my opinion, right? You're not taking good care of yourself, right? It doesn't mean you should think my opinion is gospel because I said it, but people then don't have an understanding of like, what is expertise? What do people learn? How can people help us understand and make better decisions? It kind of goes out with the wash and then the position of the expert, I mean, a lot has been written about this, right? It gets diminished over time, very much to our own peril. And then often with aggression in the medical world, </s><s>[INST] coming back towards the alleged expert of the league. Yeah, expertise is a tricky one. It's such a tricky thing because a couple with expertise, the attention is this arrogance that can come with expertise. The arrogance can make the expert feel like they're more of an expert and it's a vicious cycle. And then the arrogance in the current, in the 21st century, especially with the internet, the arrogance can completely force the public to distrust the expert because all they see is the arrogance versus the expertise. So ultimately you have to have, I think the greatest experts and masters I know are the ones that have a complete humility. Humility and gratitude. And gratitude. Leave this back. Which is usually a really good sign [/INST] that somebody is at the top of their field. And they'll acknowledge that they don't know everything. </s><s>[INST] Which is hilarious, right? So like the best experts I know are the ones that will say that they don't know, [/INST] they would not call themselves an expert. Right, right. It's very confusing. Or know that they know a lot but don't know the answer to this. You see that a lot in medicine. That person knows they're an expert surgeon but they also acknowledge they don't know if this is the right time to operate. That's how you get to the best answer instead of someone who is an expert </s><s>[INST] and always knows the answer. Right. Yep. If we actually rewind to the beginning of our conversation, we talked about, you mentioned something I wanted to return to. So there's layers that are, there's an emergent novelty. And you mentioned that we as human beings and we introspect on our own mind, we really can't know most of it. Which of course makes me think of this, the unconscious mind, the subconscious mind and Carl Jung. How much is hiding there in the shadows? You've investigated a lot of trauma. How much is there in our mind that's not directly accessible to us? Like what can you say maybe philosophically about how much is there [/INST] lurking in the Jungian shadow? I think there's a tremendous amount there. But I wouldn't, I don't immediately go to an ominous perspective, right? Because if it's lurking there, right, it can come get us, right? And to some extent that's true, right? Because the seeds of evil are there if we want to plant and nurture them. You think good things can't lurk? </s><s>[INST] I guess so, I guess so. I was being poetic. But you're right, you're absolutely right. And the Jungian shadow is supposed to not just be dark things, it's supposed to be everything. [/INST] It's supposed to be a lot of positive things as well, yeah. Right. Which I think brings us to self-knowledge, to truth. Where I think the opposite of envy, narcissism, sociopathy, I do think is all rooted in truth. It's both the truth of the good things about us or the ways we're not blameable, blameworthy for the things we're blaming ourselves for, et cetera. But the self-knowledge and the truth and getting away from the reflex of anger, frustration, envy, shame, what I think happens then is all of that underneath the surface. If we look at like the consciousness is the top of the iceberg, you know, outside the top. Say, well, outside the water. So is what's underneath like shifting and it can pull the top under, right? Or is it supporting the top? And really I believe is honesty, truth, self-knowledge, humility, gratitude, all this simple stuff. Good mental health is always consistent with simplicity. You know, humility, gratitude are easy things to say, like we know what that is, right? We understand what that is. Soothing envy by having immense power and subjugating others is getting very, very complicated. Right. What that is and how that plays out. So if we are in touch with ourselves, if we're honest with ourselves, if we own what's ours, we don't try and own what's not ours, right? What happens then is something isn't waiting inside of us to sort of jump us with some new fact of self or challenge of self, right? Then I think what happens are phenomena like intrinsic learning, like the way that so much happens inside of us automatically, right? How people who have high levels of expertise know the answer to complex questions more rapidly, right? It doesn't take them longer to think through it, but they have more knowledge to think through. It's that more happens rapidly and unconsciously. So they know the more complex answer more quickly and readily, right? And we can build that in ourselves, not just in terms of factual knowledge, but in terms of how we respond to things, right? If I make a mistake, do I respond with reflexive shame, right? If I see someone has something I'd like, how do I respond? We're more in accord with ourselves. And then the automaticity in us is serving us better. </s>
<s>[INST] and then he left and that's how can we take it? And then I got hired and I was in the group, can we take a slight tangent on the on this topic of it sounds like maybe you could speak to the bigger picture. It sounds like you're quite self critical, who Charles. No, you, I think I can I can do better. I can do better. I'll try me again. I'll do better. But yeah, that was like a like a three out of 10 response. Uh let's try to work it up to five and six. Uh You know, I remember Marvin Minsky said uh on a video interview, something that the key to success in academic research is to hate everything you do. Uh for some reason I think I followed that because I hate everything. He's done a good line. That's a that's a keeper. But what do you do find that resonates with you at all in how you think about talks and so [/INST] on? I would say it differently. It's </s><s>[INST] not [/INST] that's such an M I. T. View of the world. So I remember I remember talking about this one as a student. You know, you were basically told I will clean it up for the purpose of the podcast. Uh My workers crap, My work is crap. My workers crap, my workers crap. Then you like, go to a conference or something like everybody else's work is crap. Everybody else's work is crap. And you feel better and better about it relatively speaking and then you sort of keep working on. I I don't hate my work that resonates with me. Yes. I've never hated my work, but I have I have been dissatisfied with it and I think being dissatisfied being okay with the fact that you've taken a positive step, the derivative is positive. Maybe even the second derivative is positive. That's important because that's a part of the hope, right? But you have to. But I haven't gotten there yet. If that's not there, That I haven't gotten there yet, then, you know, it's hard to, it's hard to move forward. I think. So, I by that, which is a little different from hating everything that you do. </s><s>[INST] Yeah, I mean, there's there's things that I've done that I like better than I like myself. So it's separating me from the work essentially. So I think I am very critical of myself, but sometimes the work I'm really excited about and sometimes I think it doesn't happen [/INST] right away. So I found the work that I've liked, that I've done most of it. I liked it in retrospect more when I was far away from it in time, </s><s>[INST] I have to be fairly excited about it to get done, [/INST] No excited at the time, but then happy with the result, but years later, or even Michael back, you know what, that actually turns out that turned out to matter or oh, gosh, It turns out I've been thinking about that. It's actually influenced all the work that I've done since without realizing it. That's smart. Yeah, that guy had a future. Yeah, I think so, yeah. So I think there's something to it. I think there's something to the idea you gotta, you know, hate what you do. But it's not quite hate, it's just being unsatisfied and different people motivate themselves differently. I don't happen to motivate myself with self loathing. I have been to motivate myself and something else. </s><s>[INST] So you're able to sit back and be proud of in retrospect of the work you've done [/INST] well and it's easier when you can connect it with other people because then you can be proud of them </s><s>[INST] people. [/INST] And then the question is still safely hate </s><s>[INST] yourself. It's [/INST] win win, Michael or at least win lose, which is what you're looking for, </s><s>[INST] wow, there's so many levels. Uh, so how did you actually meet? Meet? So my, the way I think about it is because we didn't do much research together at age 20, but, but then we all got laid off. So that was the other way, sorry to interrupt. But that was like one of the most magical places historically speaking. Uh [/INST] they did not appreciate what they had </s><s>[INST] and how do we uh I feel like there's a profound lesson in there too. How do we get it? Like what was, why was it so magical? It's just a coincidence of history or is there something special about some really good managers and people who really believed in machine learning as this is going to be important. Um, let's get the people who are thinking about this in creative and, and insightful ways and put them in one place and [/INST] star. But even beyond that, right, it was, it was Bell labs at its heyday and even when we were there, which I think was passed it and to be clear, </s><s>[INST] he's gotten to be at Bell labs. I never got to be at Bell labs joined after [/INST] That should have been 91 as a grad student. So I was there for a long time. Um, every summer twice </s><s>[INST] I worked for companies that had just stopped being the last Bell core and then 18 T labs, so Bell labs was several locations or for the researchers, like definitely Jerseys involved somehow. They're all in Jersey. [/INST] Yeah, they're all over the place, but they were in a couple places in Murray Hill was the labs place. Um, so </s><s>[INST] you, you had, you had an office in Murray Hill at one point in your career? [/INST] Yeah, I played ultimate frisbee on the cricket pitch at Bell Labs in Murray Hill. And then it became 18 T labs when split off with loose during what we call try best picture supposed to be better than Michael </s><s>[INST] kearns. Ultimate frisbee. [/INST] Yeah, yeah. </s>
<s>[INST] So do you think that kind of processes possible for us humans? So we live in a three dimensional world maybe with the time component for dimensional. And then math allows us to uh to go high into high dimensions comfortably and explore the world from those perspectives. Yeah. Like is it possible that the universe is uh many more dimensions than the ones we experience as human beings. So if you look at uh the you know, especially in physics theories of everything, uh physics theories that try to unify general relativity and quantum field theory, they seem to go to high dimensions to work stuff out through the tools of mathematics. Is it possible? So like the two options are one is just a nice way to analyze a universe, but the reality is is as exactly we perceive. It is three dimensional. Or are we just seeing, Are we those flat land creatures? They're just seeing a tiny slice of reality. And the actual reality is many, many, many more dimensions Than the three Dimensions We Perceive? [/INST] Oh I certainly that's possible. Um Now, how would you figure out whether it was true or not is another question. Um And I suppose what you would do as with anything else that you can't directly perceive is um you would try to understand what affect the presence of those extra dimensions out there would have on the things we can perceive, like what else can you do, right? And in some sense, if the answer is they would have no effect, then maybe it becomes like a little bit of a sterile question. Because what question are you even asking? Right? You can kind of posit however many entities that </s><s>[INST] is it possible to into it, how to mess with the other dimensions while living in a three dimensional world? That seems like a very challenging thing to do. We the reason flatland could be written Is because it's coming from a three dimensional writer. [/INST] Yes, But but what happens in the book, I didn't even tell you the whole plot, what happens is the square is so excited and so filled with intellectual joy by the way, maybe to give the story from context? You asked like, is it possible for us humans to have this experience of being transcendent, transcendental, jerked out of our world? So we can sort of truly see it from above? Well, Edwin Abbott, who wrote the book, certainly thought so, because Edwin Abbott was a minister. So the whole christian subtext of this book, I had completely not grasped reading this as a kid that it means a very different thing. Right? It's sort of a theologian is saying like, oh, what if a higher being could like pull you out of this earthly world you live in so that you can sort of see the truth and like really see it uh from above as it were. So that's one of the things that's going on for him. And it's a testament to his skill as a writer that his story just works whether that's the framework you're coming to it from or not. Um but what happens in this book and this part, now looking at it through a christian lens, it becomes a bit subversive. Is the square is so excited about what he's learned from the sphere and the sphere explains him like what a cube would be, oh, it's like you but three dimensional and the square is very excited and the square is like, okay, I get it now. So like now do you explain to me how just by reason I can figure out what a cube would be like, like a three dimensional version of me, Like let's figure out what a four dimensional version of me would be like. And then this year is like, what the hell are you talking about the fourth dimension? That's ridiculous. Like there's three dimensions like that somebody there are, I can see like, I mean it's a sort of comic moment where the sphere is completely unable to conceptualize that there could actually be yet another dimension. So that takes a religious allegory to like a very weird place that I don't really understand theologically, </s><s>[INST] but it's a nice way to talk about religion and myth in general as perhaps us trying to struggle with us meaning human civilization, trying to struggle with ideas that are beyond our cognitive capabilities. [/INST] But it's in fact not beyond our capable, it may be beyond our cognitive capabilities to visualize a four dimensional cube. Tesseract to some like to call it or a five dimensional cube or a six dimensional cube, but it is not beyond our cognitive capabilities to figure out how many corners a six dimensional cube would have. That's what's so cool about us. Whether we can visualize it or not, we can still talk about it, we can still reason about it. We can still figure things out about it. That's amazing. </s><s>[INST] Yeah. If we go back to this first of all to the mug. But to the example you give in the book of the straw, how many holes does the straw have? And you listener may try to answer that in your own head. Yeah, [/INST] I'm gonna take a drink while everybody thinks about </s><s>[INST] it. We can give you a slow step. Is it uh 01 or two or more than that? Maybe maybe you get very creative. But uh it's kind of interesting to each dissecting each answer as you do in the book. It's quite brilliant. People should definitely check it out. But if you could try to answer it now, like think about all the options and why they may or may not be right. [/INST] Yeah, that's one of its one of these questions where people on first hearing it think it's a triviality and they're like well the answer is obvious and then what happened? Have you ever asked a group of people? This something wonderfully comic happens. Which is that everyone's like well it's completely obvious and then each person realizes that half the person to other people in the room have a different obvious answer for the way they have. And then people get really heated. People are like I can't believe that you think it has two holes are like I can't believe that you think it has one. And then you know you really like people really learn something about each other and people get heated. </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] organizations that extensively U. C. Plus plus. Yes because it's basically all individuals or individuals. I mean it's uh it's a bunch of people in the room deciding the design of a language based on which a lot of the world's systems run. [/INST] Right? Well I think most people would agree it's better than if I decided it or better than if a single organization like H and C decides it. I don't know if everyone </s><s>[INST] agrees to that. By the way. Bureaucracies have their critics to. [/INST] Yes there that look standardization is not pleasant. It's it's it's horrifying </s><s>[INST] democracy. [/INST] But we exactly as Churchill says democracy is the worst way except for all the others, right? And it's I would say the same reform standardization. But anyway so we meet and we we have these votes and that determines what the standard is. A couple of years later we extended this so it became worldwide we have standards organizations that are active in currently 15 to 20 countries and another 15-20 are sort of looking and voting based on the rest of the work on it. And we meet three times a year. Next week I'll be in cologne Germany uh spending a week doing centralization and we'll vote out the committee draft of C plus last 20 which goes to the National Standards Committee is for comments and requests for changes and improvements. Then we do that and there's a second set of votes where hopefully everybody votes in favor. This has happened several times. The first time we finished, we started in the first technical meeting was in 1990. The last was in 98. We voted it out. That was the standard that people used till 11 or a little bit past 11. Um and it was an international standards. All the countries voted in favor. Um It took longer with 11, I'll mention why, but all the nations voted in favour. Uh and we work on the basis of consensus that is, we do not want something that passes 60 40 because then we're good in case you get dialects and opponents and people complain too much. They all complain too much. But basically </s><s>[INST] it has [/INST] no real effect. The standards has been obeyed. They have been working to make it easier to use many compilers, many computers and all of that kind of stuff. And so the first that it was traditional with I. S. O. Standards to take 10 years. We did the first one in eight, brilliant. Uh and we thought we were going to do the next one and six because now we're good at it right. It took 13. </s><s>[INST] Yeah, it was named O [/INST] X. It was named O X. </s><s>[INST] Hoping that you would at least get it within the single within the arts the single day. [/INST] I I thought we would get I thought would get 6, 7 or eight. </s><s>[INST] The confidence of youth. [/INST] That's right. Well, the point is that this was sort of like a second system effect. That is we now knew how to do it. And so we're going to do it much better and we've got more ambitious and it took longer. Furthermore, There is this tendency because it's a 10 year cycle or each doesn't matter just before you're about to ship somebody has a bright idea. And so we really, really must get that in. We we did that successfully with the STL. We got the standard library that gives us all the STL stuff that that basically, I think it saved Plus Plus it was beautiful. </s><s>[INST] Uh [/INST] and then people tried it with other things and it didn't work so well they got things in, but it wasn't as as dramatic and it took longer and longer and longer. So after C plus plus 11, which was a huge improvement. And what basically what most people are using today, we decided ever again. And so how do you avoid those slips? And the answer is that you ship more often so that If you if you if you have a slip on a 10 year cycle By the time you know it's a slip, there's 11 years till you get it. Now with a three year cycle There is about 34 years till you get it. Like the delay between feature freeze and shipping. So you always get one or two years more. And so we shipped 14 on time. We shipped 17 on time and we ship We will ship 20 on time. It's it will happen. And furthermore this allow this gives a predictability that allows the implement urz, the compiler implementer is the library implementer. They have a target and they deliver on it. 11 took two years before most compilers were good enough 14, Most compilers were actually getting pretty good in 14, 17. Everybody shipped in 17. We are going to have At least almost everybody ship almost everything in 20. And I know this because they're shipping in 19, predictably this is good, delivery on time is good. And so yeah, </s><s>[INST] that's great. That's how it works. There's a lot of features that came in in C Plus plus 11. There's a lot of features at the birth of C Plus plus that were amazing and ideas with concepts in 2020. What to you is the most just just to you personally. Beautiful or mm just you sit back and think, wow, that's just nice clean feature of C Plus plus. [/INST] I have written two papers for the history of Programming languages conference which basically ask me such questions and I'm writing a third one which I will deliver at the History of Programming Languages conference in London next year. So I've been thinking about that and there is one clear answer constructors and instructors the way a constructor can establish the environment for the use of the of its hype for an object and the destructor that cleans up any messes at the end of it. That is the key to C Plus plus. That's why we don't have to use garbage collection. That's how we can get predictable performance. That's how you can get the minimal go ahead in many, many cases and have really clean types. It's the idea of constructive destructive pairs. Sometimes it comes out under the name R I Ai. Resource acquisition is initialization which is the idea that you grab resources and the constructor and release them in destructor. Um It's also the best example of why I shouldn't be in advertising. I get the best idea and I call it resource acquisition is initialization. Um not the greatest naming I've ever heard. </s>
<s>[INST] You have to actually do some research here, wow that as another level of depth. That's awesome. Okay, so [/INST] okay, so say lex is playing. Yeah, one of his songs, he shows up </s><s>[INST] What's your favorite Hendrix song with, [/INST] Oh that's a hard one, I like castles in the sand, it's a sad one, but I like it. </s><s>[INST] So I'm playing something. Yes. And [/INST] I was saying boom, just like Elvis does for people, Hendrick shows up, all right, and then you're amazed and that tells you something that's very, very significant and he says you need to tell other people this. Okay, So then like, </s><s>[INST] okay, yes, [/INST] and you start and because people believe you and because you are a person of um, you know, credibility, people believe you. And so all of a sudden movement starts okay, and it's the Hendrix movement, it's Hendricks two or something like that, you know, we call it something the next iteration of Hendrix, right? Hendricks lives, but he lives is this vibration And only lex can like, you know, can manifest this vibration. Okay, so like this is, this is how religion start, you know, excuse your audience who are religious, I'm actually practicing catholic. So um this is how religion start. They start with first off, a contact experience, not, I mean not all of them, but a good portion of them. Um Peep, some person has an experience that's transcendent sacred to them and they go and they tell other people and then those people tell other people and then something gets written about it. Okay, And then it becomes because it's a charismatic movement, people become affected by it and if if too many people are affected by it um an institution steps in and tries to control the narrative. Uh so this is what you call the beginning of a religion or a myth, a very powerful myth. And so it's almost like a star, a Star is Born. </s><s>[INST] Okay. Yeah. We say institution. Do you mean some other organization that's already powerful? You don't want to become overpowered by this new movement? [/INST] Yes, absolutely. </s><s>[INST] Usually governments [/INST] usually. Yeah. So I have a couple examples. I used the example of the christian church in my book because I'm most familiar with the history of Christianity and you know, Christianity, you know, was started by this jewish man and it was a movement that you know, he was a very powerful charismatic person, other people believed in him and then his followers talked about him and then other than, you know, usually early christians before does 300s were generally people who were disenfranchised because he had a pretty radical idea that, you know, humans should have dignity. And this was pretty radical during that time. So women who didn't have dignity and you know, slaves who didn't have dignity at the time um convert to Christianity in droves. And so what happened was that all of a sudden um it became this belief system that was undercurrent and then Constantine who was an elite had an experience and made Christianity the state religion by that time there were different forms of Christianity probably hundreds of them well most likely and Constantine and the people who were powerful with him decided that their idea this is the Council of Nicaea now decided that there was one form and they call it universal the one form of Christianity and this should be it. And so they kind of took out all the other denominations of Christianity in different forms of it. So you can see that a very very powerful set of beliefs put a culture on fire. Right. And so how did they had to deal with that fire somehow. And so they narrative ized it, they decided how do we interpret this and they interpreted it as they wished. But that wasn't the only interpretation of Christianity. Have another example. I'm in the catholic church a lot of times and I'm gonna use the example of uh Faustina. Um she's um she's a nun and she's polish and um I think it was in the early 20th century, if not the 18 hundreds that she had a very powerful uh many experiences actually of of jesus and she saw jesus with rays coming out of his life, his heart. And basically she called his Divine Mercy. And it became a devotion in Poland and it spread the catholic church was not, not into this at all. Okay. And so they did everything they could to try to suppress festina's influence which was growing and growing and growing and growing okay. And so they were very successful in trying to keep her quiet and she died. Okay. Years later, john paul the second polish sainted her and created the divine mercy devotion, which is worldwide now and millions and millions of people. But do you see how they, they, you know, completely </s><s>[INST] controlled, so fascinating that it uh that it just starts with a single. So like you said, contact experience, experience is the key word, is your sense that those experiences are legitimate. So it's not [/INST] yes, </s><s>[INST] artificially constructed. [/INST] I think for the most part, they're legitimate experiences that people have, Why would someone want to put themselves through what they go through? Like why would jesus want to get crucified? I mean, that's a pretty nasty way to die. Um you know, why would Faustina bringing this upon herself, the people that I meet who said that they've seen UFOs and that most of them don't want to be known because of the ridicule that goes along with it. So I honestly think that, you know, there are people who are maybe not stable and would like the attention, but for the most part, normal people don't want this attention. </s>
<s>[INST] And we're part of creating one of the most incredible things humans have ever created. So yes, there is the science. That's the fermi thing. Right? Uh [/INST] The instrument </s><s>[INST] and the instrument. The instrument is a magical creation, not just by a human by a collection of humans. The collaboration is uh That's yes, that's humanity at his best. I do hope I do hope we last quite a bit longer. But if we don't. Mhm this is a good thing to remember humans by at least they built that thing. It's pretty impressive. Barry this is an amazing conversation. Thank you so much for wasting your time in explaining so many things. So well, I appreciate your time today. [/INST] Thank you. </s><s>[INST] Thanks for listening to this conversation with barry Barish. To support this podcast. Please check out our sponsors in the description And now let me leave you some words from Warner Heisenberg, a theoretical physicist and one of the key pioneers of quantum mechanics. Not only is the universe stranger than we think it is stranger that we can think. Thank you for listening and hope to see you next time. Mhm. [/INST] </s>
<s>[INST] Uh, [/INST] although to be fair, some of those museums parks and not are pretty rusty and, and dangerous, </s><s>[INST] but that, that, that kind of propaganda, I guess what I'm playing the Devil's advocate is like it's comforting and it's useful, but it does seem that that naturally leads to an abuse of power, [/INST] But it's not, how can it be used correctly? No. one person has the intellect for the mind to understand the entirety of an economy, let alone every individual field of interest. </s><s>[INST] Well, for example, you can have an artificial intelligence system that understands the the entirety of your [/INST] affect. Just complete change the masks lift. Yes. You can have an artificial intelligence. </s><s>[INST] Uh, but like the question is, can that, I mean like the human version of that is like you can hire a lot of experts, right? You can be an extremely good manager and [/INST] since everything is dynamic, it's not gonna, they're not gonna have the data to kind of manage it. </s><s>[INST] Well, it seems that there's a like what George Washington allegedly did. It seems like most humans are not able to fire themselves. You're, you're not able to like, yeah, ultimately be a check in your own power. But that's not if I was like, if I was creating a human, it's like that's not an obvious bug of the system that we would not be able to fire ourselves to to know. And we have, I mean, it seems like that's something you have to know Always like that's something I often wonder is like, am I wrong about this? [/INST] Well, this is what we talked about earlier. What are the safety valves to make sure that okay if I am incorrect or my knowledge is finite. Plato's cave kind of thing. What mechanisms are in place that my mistake or limited information is going to have deleterious consequences. North Korea does not really have that. And as a result they had polio in the 90s. </s><s>[INST] So there is uh you're you write about it straight but there's a humor to it because it's a absurd, the evil place. I suppose a bunch of people I asked, I asked uh I said that I'm talking to you and a bunch of past questions uh here from the [/INST] plebs you asked me before we start recording. I specifically said no, it was in my contract. </s><s>[INST] Uh Yeah, you gave I gave you all the pink skittles or whatever. Uh but they think, you know Pink, I'm trolling Michael. Let me explain to you how that works. Uh People should go uh malice that locals dot com which can sign up and uh pay I think the membership fees several $1000. It's very it's not, it's not. Yeah, but the service is excellent. You get a coat with it. Uh But yeah, I went there posted a lot of really brilliant people that people should join that community. If you find uh Michael interesting or if you just want to go and say why he's wrong. It's a great place to have that. That [/INST] I assure </s><s>[INST] you. Uh yeah, a lot of really kind people. So anyway, the there's a bunch of people asked that we should talk about humor. So pretend hypothetically speaking that I'm a robot asking you to explain humor to me. What? So dear reader. I mean, there's a humor, there's, there's your so wonderfully dance between serious, dark topics and then seriously dark humor. Can you try to uh if you were to write like a, I don't know, Wikipedia article, maybe a book about your philosophy of humor? What do you think is the role of humor in all of this? [/INST] A joke is like a baby. You can't dissect it and then put it back together and expect it to work. Trust me on this one. Despite no matter how you carve that thing up, it's not gonna be working the next day and you need it to. So those little sneakers with those hands. Um I don't know that humor is something that is a very explainable people. There's something called clap ter where this is like the worst kind of humor where people applaud because they agree with what you're saying as opposed to laughter? Well that's still, that's that's a kind of poetry reading. Yeah, the drag queens do that too. Um, I think they have the nails this, you laugh. It's a visceral reaction when someone on twitter is insisting, you know that's not funny. You're not in a position to make that claim. And let's let's go, let's go back to north Korea. I had a refugee I knew and he went to high school here and he was talking his buddies and they said um, hey, remember when we were kids, we had Pokemon and he goes, oh yeah, except instead of Pokemon, I watched my dad starved to death, which is the truth now. Who are you, who are any of us to tell him not to make that joke? I don't know what it's like watching anyone including my dad uh starved to death and my dad's fatty, so he's not going hungry anytime soon. Um so it's very bizarre to me when people feel comfortable precluding others from making jokes especially, and I think this is a very jewish thing like this kind of gallows humor, especially when it's laughing about a personal uh loss or experience that they've had humor is a great way to mitigate um uh, pain and suffering. But it's also, I think this is why it's a jewish thing is it's a black thing when you are a marginalized community or poorer. It's free uh telling stories, telling jokes or songs, you don't have to have money, but you can have joy and happiness and I think that's why you find it so much more in kind of lower status communities. Then you're finding like wasps who are notoriously humorless. </s>
<s>[INST] can be a dreamer and you can be a dreamer in a rural little village and then that has ripple effects throughout the entire country, young kids growing up, you know, I want to be the next [/INST] X </s><s>[INST] whatever and it doesn't have to be, you know, the next steve jobs that, that seems really far far away [/INST] all levels. It's at all levels. You you create local heroes because because, because representation matters right, so and we are so badly in need of that. And so, um, so that's what all the things that have been stolen from us as long as things remain the same. So lex once I found out that basically at the end of the day, the answer is economic freedom and that when it comes to that the indexes economic indexes that measure that whether it's the doing business index ranking of the World Bank or the fraser, economic freedom index of the Heritage Foundation. When you look at all of those um indexes and others, what do they have in common one after another. They show you that it is harder to do business in almost anywhere in africa than it is per se, anywhere in Scandinavia. So it is telling you that Scandinavian nations that socialist americans tend to love so much and take as an example over there too, they're showing you that they don't understand what's going on really in Scandinavia, that Scandinavia is more capitalist, Scandinavian nations are more capitalist than almost any sub Saharan african nations. </s><s>[INST] Ultimately, the political systems actually don't even matter nearly as much as the private sector being able to operate the machinery of capitals. [/INST] There you go. There you go, There you go. And it's almost like, like I said, it's almost like its own little widget within, within it, you can have whatever type of society you want to practice you want to exercise at whatever level you want to. But if you're serious about becoming a low amid a middle to high income nation, there is no other pathway that we know of at this point. And you know what made me super excited about that beyond Having finally found my answer, I have to tell you when I found that answer, I literally fell to my knees, it was the type of feeling that, you know, if something is not well with you, whoever it's physical or mental, something is not well you're not well and you go around and you go to the so called specialist, some of them, you know, but you you're going around for years, going around trying to get help for your ailment and here we don't know here they tell you things that you can't tell why, but you just know it's not true and it's it's going on for years after year after year. And finally you meet this one person and boom, it's there not only the liberation, but also this whole new world that comes with it, You know, I'm still I'm still ill, but guess what? There's a path forward. We know that I'm gonna have a lot of work to do. But there's hope. Yeah, </s><s>[INST] you're the beacon of hope actually for a lot of people in that part of the world. And that's those beacons are actually really necessary. So not only is there hope, but you can become, I mean the beacon for your people, your your your home, this this power that you see that you feel all around to become uh to escape the feeling of being trapped. Is there a device you can give to people that to uh young girls and boys dreaming somewhere in africa how to change the world. [/INST] That's right. And by the way, I want to say there are bigger beacons, There are better beacons than me. I just happened to be someone who has the chance of talking to you right now. Uh and one of my goals is to open the same doors that were opened for me because together our voice, there's such amazing stories out there and um so bigger Beacons, better Beacons out there. one thing here for me, the reason why I do what I'm doing right now and it's almost to the point of self destructing my own health. I feel invested with such the mission of I have been afforded the truth. So it is my moral duty to try to take it around. I know I sound people sometimes I say when I listen to it, I feel like I'm I'm talking to a to a priest and I'm like because the gospel received. So anyway, but the thing is lex who tells you these things to this day, when they talk about the poverty of Africa, what do they talk about? Their sitting there telling you? Oh yes, because of Cronyism is because of race, racism is because of imperialism is because they're stealing, you know, raw material, blah, blah blah. Is any of those called, you know, like guilty to some level of where we are today, one of maybe part of the reason where we are today, maybe, maybe is that the only reason or the overwhelming reasons No, is that unsurmountable. Absolutely not. So for me don't stay in that place of um, that steals and robs you of your agency. So, so I think it's important for people to get the right diagnosis as to why we are where we are. Because what you and I just talked about the mainstream does not talk about this when they even talk about africa in terms that, you know, are not the usual suspect of, oh, famine is building over there, wars building over here. Oh, we're having Ebola is coming all of that stuff. Even when they were talking about the monkey pox, which at first, you know, um, in this wave, it started with white people in europe. Well even in many newspapers, you pull out it's black people with monkeypox on their on their skin. I'm like, wait a second. This time around, we did not start with us. So why are you always showing us when it's right now happening to white people? You know? So, so all of that is happening. So for me, the thing is We, the world simply right now does not have the right diagnosis as to why this continent right now, despite all of its riches, because Lord knows it's got riches. Starting with its young population, 75% of the population of my country is below the age of 25 years old. So when we're talking, I know we're talking about, you know, repopulation. You know, it's important we're gonna have to go for that, Maybe you'll get me going about convention. I don't know. But anyway, um, so here my point is a we need the right diagnosis as to why this continent is the poorest continent in the world despite its which is starting with its young people over natural resources, diversity in land, people, cultures, languages, everything that make that make for great ingredient for for awesomeness. Despite all of that, we are the poorest region in the world. People need to know that the reason why that is It's because we also happen to be the most overrated, overregulated region in the world at the end of the day with Africa as and I dare to say Africa here and treated as one. We are 54 countries. 55 depending how you count. Yet. We almost for a tiny minority of these countries. We almost all lack one of the most crucial freedoms that they are. If you are serious about prosperity building, we lack economic freedom </s>
<s>[INST] of our daily activities. So we all become the builders of cathedrals. Correct. Yeah, and we follow intellectual pursuits, artistic pursuits. I wonder how that really changed at a scale of several billion people, everybody playing in the space of ideas [/INST] and the space of creations. So ideas, maybe for some of us, maybe you and I are in the job of ideas, but other people are in the job of experiences. Are there people in the job of emotions, of dancing, of creative artistic expression, of skydiving, and you name it. So basically, again, the pew of human diversity is exactly that, that what rocks my boat might be very different from what rocks other people's boat. And what I'm trying to say is that maybe AI will allow humans to truly not just look for, but find meaning, and you don't need to work, but you need to keep your brain at ease. And the way that your brain will be at ease is by dancing and creating these amazing movements, or creating these amazing paintings, or creating, I don't know, something that sort of changes, that touches at least one person out there that sort of shapes humanity through that process. And instead of working your mundane programming job, where you hate your boss, and you hate your job, and you say, you hate that darn program, et cetera, you're like, well, I don't need that. I can offload that, and I can now explore something that will actually be more beneficial to humanity, </s><s>[INST] because the mundane parts can be offloaded. I wonder if it localizes all the things you've mentioned in all the vocations. So you mentioned that you and I might be playing in the space of ideas, but there's two ways to play in the space of ideas, both of which we're currently engaging in. So one is the communication of that to other people. It could be a classroom full of students, but it could be a podcast. It could be something that's shown on YouTube and so on. Or it could be just the act of sitting alone and playing with ideas in your head. Or maybe with a loved one, having a conversation that nobody gets to see. The experience of just sort of looking up at the sky and wondering different things, maybe quoting some philosophers from the past and playing with those little ideas. And that little exchange is forgotten forever, but you got to experience it, and maybe it's basically engaging. I wonder if it localizes that exchange of ideas, for that with AI, it'll become less and less valuable to communicate with a large group of people, that you will live life intimately and richly [/INST] just with that circle of meat bags that you seem to love. So the first is, even if you're alone in a forest, having this amazing thought, when you exit that forest, the baggage that you carry has been shifted, has been altered by that thought. When I bike to work in the morning, I listen to books and I'm alone, no one else is there. I'm having that experience by myself. And yet in the evening, when I speak with someone, an idea that was formed there could come back. Sometimes when I fall asleep, I fall asleep listening to a book. And in the morning, I'll be full of ideas that I never even process consciously, I'll process them unconsciously. And they will shape that baggage that I carry that will then shape my interactions, and again, affect ultimately all of humanity in some butterfly effect, minute kind of way. So that's one aspect. The second aspect is gatherings. So basically you and I are having a conversation which feels very private, but we're sharing with the world. And then later tonight, you're coming over and we're having a conversation that will be very public with dozens of other people, but we will not share with the world. So in a way which one is more private? The one here or the one there? Here there's just two of us, but a lot of others listening. There a lot of people speaking and thinking together and bouncing off each other. And maybe that will then impact your millions of audience through your next conversation. And I think that's part of the beauty of humanity. The fact that no matter how small, how alone, how broadcast immediately or later on something is, it still percolates through the human psyche. </s><s>[INST] Human gatherings all throughout human history, there's been gatherings, there's been gatherings. I wonder how those gatherings have impacted the direction of human civilization. Just thinking of, in the early days of the Nazi party, it was a small collection of people gathering. And the kernel of an idea, in that case an evil idea, gave birth to something that actually had a transformative impact on all human civilization. And then there's similar kind of gatherings that lead to positive transformations. This is probably a good moment to ask you and a bit of a tangent, but you mentioned it. You put together salons with gatherings, small human gatherings, with folks from MIT, Harvard, here in Boston, friends, colleagues. [/INST] What's your vision behind that? So it's not just MIT people, it's not just Harvard people. We have artists, we have musicians, we have painters, we have dancers, we have cinematographers, we have so many different diverse folks. And the goal is exactly that, celebrate humanity. What is humanity? Humanity is the all of us. It's not the anyone's subset of us. And we live in such an amazing, extraordinary moment in time where you can sort of bring people from such diverse professions, all living under the same city. You know, we live in an extraordinary city where you can have extraordinary people who have gathered here from all over the world. So my father grew up in a village in an island in Greece that didn't even have a high school. To go get a high school education, he had to move away from his home. My mother grew up in another small island in Greece. They did not have this environment that I am now creating for my children. My parents were not academics. They didn't have these gatherings. So I feel so privileged as an immigrant to basically be able to offer to my children the nurture that my ancestors did not have. So Greece was under Turkish occupation until 1821. My dad's island was liberating in 1920. So like they were under Turkish occupation for hundreds of years. These people did not know what it's like to be Greek, let alone go to an elite university or be surrounded by these extraordinary humans. So the way that I'm thinking about these gatherings is that I'm shaping my own environment and I'm shaping the environment that my children get to grow up in. So I can give them all my love. I can give them all my parenting, but I can also give them an environment as immigrants that sort of, we feel welcome here. My wife grew up in a farm in rural France. Her father was a farmer. Her mother was a school teacher. Like for me and for my wife to be able to host these extraordinary individuals that we feel so privileged, so humbled by is amazing. And I think it's celebrating the welcoming nature of America, the fact that it doesn't matter where you grew up. And many, many of our friends at these gatherings are immigrants themselves. I grew up in Pakistan in all kinds of places around the world that are now able to sort of gather in one roof as human to human. No one is judging you for your background, for the color of your skin, for your profession. It's just everyone gets to raise their hands and ask ideas. </s>
<s>[INST] For people just listening, there's a bit of hard slapping. That's fine. [/INST] That could be considered a strike. That's fine, yeah. That could be considered a strike. It's fine, there was just a lot of electric atmosphere in the room. So now, things settle down a little bit, but here's where things get interesting. Andre throws the whole tactical game out the window right from the start. He goes for the takedown, Gordon doesn't try to fight the takedown because it's in his interests to go to the ground. But I love this about Andre. He's literally like, fuck you, kid. Let's see how good your ground game is. So he shoots the takedown and Gordon accepts it obviously because it's to his advantage to accept it. But I love the fact that Andre was like, I'm not even going to try and stall this out. I'm just going to bang. There it is. So he's like, okay, let's see what you got, kid. They say you're good on the ground. Let's see what you fucking got. And I love that about Andre. Unfortunately, he's </s><s>[INST] entered the hornet's nest now. What happened there real quick? Because that was very fast. [/INST] Gordon immediately went into Ashigurami. Not just any Ashigurami, but Ashigurami was holding both </s><s>[INST] legs. There's an open guard and he scooted forward. Oh, wow. That's really nice. [/INST] So he splits the legs, now he dominates the space between the knees. So there's a guaranteed </s><s>[INST] straight Ashigurami here. He split the knees against Andre Gavao, like effortlessly right there. [/INST] So already Gordon's in his preferred domain now. So he's starting to off balance his opponent. He's looking for a reaction to get heel exposure. He does get heel exposure. Andre does a good job of monitoring the feet to try and reduce the breaking pressure. But the brute fact is it's in Gordon's realm now. This is where he has all the advantage. And the match is going to be 20 minutes in Gordon's realm. That's going to be a very, very tall order. </s><s>[INST] Was there a moment here, again, Gordon's on the legs? Are you impressed that Andre was able to [/INST] get out from this? I don't know. I would expect this. Andre's been preparing for this for two years. And remember, Andre has gone against some of the greatest leg lockers in grappling before and prevailed. So he's not naive. He knows how to defend himself. The big problem is that he's going to create defensive reactions, which lead into other aspects of Gordon's game, in particular </s><s>[INST] back exposure. So here, Ashigurami goes to a single leg type of position where Gordon runs [/INST] to Andre's back. Now he has to return him to the mat. The most efficient way to do so is always courtesy of foot sweeping. So he pulls out a diashihirai from the back to sweeping down to the mat. And now Gordon's on top. And this is a serious problem for any grappler in the world. Once </s><s>[INST] Gordon gets top position, he's just relentless. But just getting Andre Guevara's good, just [/INST] getting the guard back, all of that is great. There's also a sense here in which Gordon is </s><s>[INST] pacing it too, just to physically fatigue an opponent. So he's passing the guard, [/INST] but not rushing it. Now what Gordon's looking for here is complete chest to chest contact. He's getting very close to it now, and once he gets chest to chest, an opponent in top position, past one of his opponent's knees, it's going to be awfully, awfully difficult for an opponent to </s><s>[INST] recover. What is he waiting for here? Is this pressure here? And over time, he just wears you [/INST] out. And over time, he just wears you out. Yeah, it's part of a campaign of attrition, of pressure, over time. Now he's creating a situation where he's either going to get back exposure or mount exposure. Either way is pretty much fatal when you're dealing with Gordon. Andre </s><s>[INST] elected to go the route of back exposure. Now, Gordon got the body triangle is on his back. [/INST] Now, there's one physical problem here. Andre Galvan has a neck like a ball and he has a very short and very thick neck. So, penetrating under the chin for a strangle can be a real problem. He also has extremely well-developed shoulders and upper arms. So, when the head comes down and the shoulders go up, there's very little real estate to work with with regards to your strangle holds. So, Gordon in time will trap one of his opponent's arms with his legs in order to take away one of those strong defensive arms. There you can see the arm has been trapped and now he can start working towards the strangle. And now here it's still difficult. It's still difficult, but things are looking good. There's still considerable amount of time left on the clock. Gordon as well ahead on points. So, all the pressure, all the tactical pressure now is on Andre. You'll see the critical penetration of the jaw with the wrist. Now, Gordon elects for a one-handed strangle. Andre fought very bravely, but a strangle, it doesn't matter how brave you are. </s><s>[INST] And where does the strangle actually happen in terms of... it felt like the strangle was at the blade of the, it wasn't even fully sunk in, so [/INST] where is is that like a full calm is like a four-handed joke. There's a sense in which, once you get underneath, you know the inevitable. Because again, the inevitable, you're feeling the inevitable. It's like a to go back to the chest analogy. It's like </s>
<s>[INST] problem. Yeah, there's actually quite a lot of ways that I can introduce misery into the push ups and the running, get creative including um you know, even just like stuff outside of the running, like taking freezing cold showers, those kinds of things, just introducing random kind of chaos into the indiana system um or having conversations with people as an introvert, it's terrifying more podcasts more podcasts, uh so um now starting uh the training and uh Zach you've been kind enough to also kind of be willing to help me out throughout this process. So I look forward to where that goes. It's kind of fascinating um on the diet side, you're one of one of the many things that make you fascinating is you've played with diet as well and your um someone famous, I would say for doing low carb, we're playing with low carb or meat based diets. Can you describe the potential, like how you're thinking about that has evolved and the potential beneficial role of a carnivore diet or keto diet or a meat based diet in training as an ultra marathon runner. [/INST] Yeah, and I think like where a lot of times things get confusing for people here is the context of it, to where it's like they want an answer as to what do I eat for endurance sport, It's like, well, endurance sport is quite wide ranging as we've talked about many times here. So there's going to be differences, I think in just like what you want to maybe necessary prioritize uh, both for the event, you're doing in the intensity that's required for training that's required for that event and then also the individual component to where I think this one often gets overlooked, where we tend to say like, well we've got all these olympic medalists at the marathon and below distance who are, you know, eating a moderate to high carbohydrate diet. So everyone needs to do that if they want to reach their potential in, you know, say the three K to the marathon and you know, in a perfect world, maybe that would be true, but there's a lot of other variables that often get forgotten then that could positively or negatively impact that decision choice. So I think dr Jeff Volek has done a great job of kind of highlighting this in the sense that, you know, when he works with people, he works with people in the health sphere as well as the performance fear And you know, he's one of the main guys at Verte Health who's uh they've got like a 60% success rate with working with folks with the type two diabetes To reverse their type two diabetes. Uh and I mean that's an astounding. When you, when you think of just any nutritional protocol, it's access rate, they're all incredibly low. They're very, very low and the big difference with his is the coaching aspect of it. Like they give support. So these people like have someone to turn to when they make a mistake or if they're thinking about doing something differently or they don't know what to do rather than just kind of throwing, throwing it all up in the air and quitting. They have a resource there and that's probably a big reason why that's the success rate that they have with that is they put those support mechanisms in place, that picture needs to be carried into the performance world or the running world to where, you know, we may have just identifying that uh, you know, olympic distance athletes that can tolerate a very large portion of their diet comes from carbohydrate is gonna just, it's gonna filter those ones towards the olympics, filter those towards interesting. Yeah. And that doesn't mean that like, uh, if we would have taken, say the gold medals in the five K and put them on a low carb diet, they'd run faster. They probably wouldn't because we may have already selected that that person is thriving on carbohydrate. Uh, what I would be interested in is like, you have, let's say we have some with equal talent but got weeded out along the way potentially because for whatever reason they just weren't able to tolerate, like both the training and the nutrition requirements that they're being told to do. </s><s>[INST] So the coaches kind, there's a culture where the coaches would really push a carb heavy diet and that, that in itself would do the filtering process of people that are not, it was filled out to people that are not able to tolerate carbs as part of their training. [/INST] I mean, I might be an example of this actually where, you know, you take someone where, uh, they forever reason the carbs aren't working for them. Like it's unsustainable for them to continue that path or if they do, they might have a shortened career So they might be able to eke out a few really good years. But then, you know, they're not gonna be the person, they were like, wow, that persons 38 they're still competing at the olympics type of a person. Uh, and you know, you, you put them on a low carb diet, uh, if you can control everything else, like, the entire lifestyle is based around training and racing, then, uh, you know, they may still have better potential by introducing carbohydrates at a higher level, but if that's not gonna, if that's not going to be sustainable for them as a person, then, you know, what's the point? Kind of at that? Unless they want to be like a kind of a spark in the pan, so to speak, </s><s>[INST] I just feel good eating meat performance wise. [/INST] Well, I think there's that group too. </s><s>[INST] And they may [/INST] just not be the olympians. </s>
<s>[INST] Alright, you keep telling yourself that, what do you think? What do you think was feeling that when he was playing a 13 year old magnus like yeah, as [/INST] much as it's a beauty of the sport that any age can be brilliant, any demographic, anything. Um I feel like when you're adult and you're paired against the kid, it's just hard not to let it get to you and it depends maybe if they're a really sweet kid, but most times I play kids they're just really arrogant and but I don't think they do it intentionally because their kids, </s><s>[INST] I mean there is a certain etiquette thing where like you say yawning and in general your [/INST] kids, there's no etiquette. </s><s>[INST] Yeah. Yeah [/INST] the kids traumatized me too, I was playing in Vegas and it was not even my opponent, it was the board next to me And the kid was at least 10 years old made 12 max and he's playing against an adult and he takes out his hand and he starts doing a fake phone to which the kids studying sitting across diagonally picks up their banana and starts talking like it's a phone and they're just mouthing words while their two adult opponents are thinking intensely at the game. And then I see the adult look up, look at the kid just making banana phone and his eyes as he size </s><s>[INST] Yeah and they're not even doing for trash talking. [/INST] There's just bored, bored kids. Yes exactly. </s><s>[INST] What was the because you play a bunch of people for for your channel what was the most like memorable, what's the most fun, most intense. There's a bunch of fun ones you played kids before some trash talking kids that [/INST] sounds great. They trash talk kids </s><s>[INST] nothing like [/INST] Losing a 12 year old who then starts doing a fortnite dance. </s><s>[INST] Yeah so that that actually happened. [/INST] That did happen. He he is you know a very young master I think he became master when he was like nine years old or something and he's very good at chess and doing a lot of training but he's also incredibly good at trash talking and he beat me one game and he stood up and he started doing the Fortnite dance. </s><s>[INST] So [/INST] you know you got to just swallow your pride in those moments. </s><s>[INST] What is that culture of like street chess players. It seems seems pretty interesting like um I don't know that seems to be celebrating the beauty of the game, it's the trash talking but also having fun with it but also taking it seriously and you've done a few of those good in new york [/INST] and Union Square Park. What </s><s>[INST] was that like? [/INST] It's such a unique place. I haven't seen it anywhere else in the U. S. Where people are just professional chess hustlers even if they're not necessarily, you know a top player, but they play chess every single day. And so many of them learn chess by themselves and never had a professional coach. So they are quite good at it. They're also very tight knit. They all know each other and it's a very social thing where you're not just playing chess, it's the experience of getting to know this person who's very much a personality and they talk to you, they could I give you tips or they can be really chatty and talk to you during. So it's a chess experience rather than just playing a game. </s><s>[INST] Do you tell them like what your rating is or do you just let people just like both, Do you discover how good they actually the person actually, [/INST] initially I loved going and not telling people my rating and just surprising them and winning games, but now we've gone so many times that they just know us so we can't get away with it anymore. One time actually I don't know if I should share this, but one time we dressed up as the grandmothers and we had prosthetics on our face and I think they still recognized us. </s><s>[INST] Yeah, it's probably the other components like probably the trash talk and all that. [/INST] It was actually, no, it was funny. We were talking like grandmothers but it was the way I held, it was the way I </s><s>[INST] talk. [/INST] We're not bringing, </s><s>[INST] okay, what were your names or the code names? [/INST] Oh my God. I think it was Edna. Edna and I had a really, I can't remember the other one but it was embarrassing because we were walking so slowly and Andrea dropped her cane or something at one point then people in the park, they would have to help her. We felt like, but it was funny because they didn't know it was us until he saw the way I reached for my pond and he said the way you held your pond, I knew it was you. It was like such a snitch thing. That was what blew the grandma cover. </s><s>[INST] Uh Yeah. Do you have a style of how you play physically? I didn't [/INST] think we did until grandma went to play chess. But yeah, I've never thought about that and I think our style is just trash talking now like style is very, if you're talking about style on and youtube and twitch we definitely have a distinctive style. </s><s>[INST] What's that? What's your distinctive [/INST] but but not going too far. No no definitely that's definitely going to if it's us two against each other so we, we trash talk each other so hard and I love looking at Andrea and watching her little nose scrunch up that she's annoyed and the satisfaction I get when that happens. </s><s>[INST] How many times do you play against each other on online publicly? I think I've seen a couple of games [/INST] played a lot of times. We try not to do it too often because it's repetitive but every now and then when we haven't done it for a while we'll go at it again, </s>
<s>[INST] And it's more beautiful and attractive at the same time. So how hard is it to get the humanoid robot Atlas to do some of the things it's recently been doing? Let's forget the flips and all of that. Let's just look at the running. Maybe you can correct me, but there's something about running. I mean, that's not careful at all. That's you're falling forward. You're jumping forward and are falling. [/INST] So how hard is it to get that right? Our first humanoid, we needed to deliver natural looking walking. We took a contract from the army. They wanted a robot that could walk naturally. They wanted to put a suit on the robot and be able to test it in a gas environment. And so they wanted the motion to be natural. And so our goal was a natural looking gate. It was surprisingly hard to get that to work environment. But we did build an early machine. We called it Petman prototype. It was the prototype before the Petman robot. And it had a really nice looking gate where it would stick the leg out. It would do heel strike first before it rolled onto the toes. You didn't land with a flat foot. You extended your leg a little bit. But even then it was hard to get the robot to walk where when you were walking that it fully extended its leg and essentially landed on an extended leg. And if you watch closely how you walk, you probably land on an extended leg but then you immediately flex your knee as you start to make that contact. And getting that all to work well took such a long time. In fact, I probably didn't really see the nice natural walking that I expected out of our humanoids until maybe last year. And the team was developing on our newer generation of Atlas some new techniques for developing a walking control algorithm. And they got that natural looking motion as sort of a byproduct of just a different process they were applying to developing the control. So that probably took 15 years, 10 to 15 years to sort of get that from the Petman prototype was probably in 2008 and what was it, 2022. </s><s>[INST] Last year that I think I saw a good walking on Atlas. If you could just like link on it what are some challenges of getting good walking? So is it, is this partially like a hardware like actuator problem? Is it the control? Is it the artistic element of just observing the whole system operating in different conditions together? I mean, is there some kind of interesting quirks or challenges you can speak to like the heel strike [/INST] or all these kinds of things? Yeah, so one of the things that makes the like this straight leg a challenge is you're sort of up against a singularity a mathematical singularity where when your leg is fully extended it can't go further the other direction. There's only, you can only move in one direction. And that makes all of the calculations around how to produce torques at that joint or positions makes it more complicated. And so having all of the mathematics so it can deal with these singular configurations is one of many challenges that we face. And I'd say in the, in those earlier days again we were working with these really simplified models. So we're trying to boil all the physics of the complex human body into a simpler subsystem that we can more easily describe in mathematics. And sometimes those simpler subsystems don't have all of that complexity of the straight leg built into them. And so what's happened more recently is we're able to apply techniques that let us take the full physics of the robot into account and deal with some of those strange situations like the straight leg. </s><s>[INST] And I'd say in the leg. So is there a fundamental challenge here that it's maybe you can correct me but is it under actuated? [/INST] Are you falling? Under actuated is the right word, right? You can't push the robot in any direction you want to, right? And so that is one of the hard problems </s><s>[INST] of like a locomotion. [/INST] And you have to do that for natural movement. It's not necessarily required for natural movement. It's just required, you know, we don't have a gravity force that you can hook yourself onto to apply an external force in the direction you want at all times, right? The only external forces are being mediated through your feet and how they get mediated depend on how you place your feet. And, you know, you can't just, you know, God's hand can't reach down and push </s><s>[INST] in any direction you want, you know, so. Is there some extra challenge to the fact that Alice is such a big robot? [/INST] There is. Humanoid form is attractive in many ways, but it's also a challenge in many ways. You have this big upper body that has a lot of mass and inertia, and throwing that inertia around increases the complexity of maintaining balance. And as soon as you pick up something heavy in your arms, you've made that problem even harder. And so in the early work in the Leg Lab and in the early days at the company, we were pursuing these quadruped robots, which had a kind of built-in simplification. You had this big rigid body and then really light legs. So when you swing the legs, the leg motion didn't impact the body motion very much. All the mass and inertia was in the body. But when you have the humanoid, that doesn't work. You have big, heavy legs. You swing the legs, it affects everything else. And so dealing with all of that interaction </s>
<s>[INST] and that's the ground, [/INST] that is what makes it possible for anything to be intelligible at all. If we lived outside of communities, if we lived in a world where there were no social norms at all, nothing would mean anything, nothing would have any significance, nothing would be regular in the way that things need to be regular in order for there to be departures or manifestations of that regularity. Uh so, so community norms are crucial, but there are also always updating, we place um we have some responsibility for what they are and the way in which they are updating themselves. And yet we didn't never choose it to be that way. So, those norms are somehow giving significance to us in a way that that were implicated in we have some relation to and all that gets covered over. If you think of us as efficient resources to be optimized. </s><s>[INST] Is that a conflicting view that we are resources to be optimized? That is that somehow deeply conflicting with the fact that there is a ground that we stand on. [/INST] Absolutely. So what Heidegger thinks is that this is this he calls this the supreme danger of the technological age, is that without ever having chosen it without ever having decided it, this is the way we understand what it is to be us. But he thinks that um it's also, he says, quoting hold early in the 18th century German poet, he says in in the Supreme Danger lies the saving possibility. So what does that mean? It means that we this is the this is the understanding that we've been thrown into that we've been given. It's the gift that was given to us. It's supremely dangerous. If we let ourselves live that way, we'll destroy ourselves. But it's also the saving possibility because if we recognize that we never chose that, that it was given to us, but also we were implicated in it's being given and we could find a way to supersede it that it's the ground, but it's also up datable. He calls the ground the groundless ground. It's it's not like an entity which is there solid stable? Like God whose eternal and non changing is always updating itself. And we're always involved in it's being updated but were only involved in it in the right way if we listen like miles Davis. </s><s>[INST] So optimization is not a good way to live life. [/INST] If you thought that it was obviously clear that that was the relevant value. So obviously clear that it never even occurred to you to ask whether it was right to think that, then you would be in danger. </s><s>[INST] Yeah, got it. So yeah, there is some in this modern technological age in the full meaning of the word technology that's updated to actual modern age with a a lot more technology going on. It does feel like like colleagues of mine in tech space actually are somehow drawn to that optimization as if that's going to save us as if the thing that truly weighs us down is um, the inefficiencies. [/INST] Exactly. And I think if you think about other, other contexts, like what, what are the moments when I mean we're unique in this respect. This, this period in history is unlike any previous. No, nobody ever felt that way right? But think about. But it's also true that nobody, no previous period in history was nihilistic. So our condition is tied up. That sort of thing is meant to be a response to the felt lack of a ground. And so no, no previous epic in history felt that way. They didn't have our problem but think so. So they, it was much more natural to them to experience moments in ways that feel um unachievable for us, what we were calling. Moments of aliveness before. Think about where the context in which they felt them, they weren't efficient. Optimized context. Think about the Greeks. If you ever read home rate is a bizarre world back there. But one of the things that's bizarre is that they're so unmotivated by efficiency and optimizing that the only thing that seems to run through all of the different greek cultures is the idea that if some stranger comes by, you better take care of them Because Zeus is the, is the God of Strangers and Zeus will be angry. That's what they say right, but what is it? How does it manifest itself? Odysseus. He's trying to get home and he gets shipwrecked on an island and you know, he's trying to figure out how he's been at sea for 10 days. He's starving, he's bedraggled. And he sees uh now Cisa, the princess who is beautiful and he's like, boy, I better you know, I don't know, get some clothes or something like, I don't want them to beat me up and kill me. And so so she takes him to the palace. They have three days of banquets and festivals before they even ask his name. It's like here's a stranger. Our job is to celebrate the presence of a stranger because this is where significance lies now, we don't have to feel that way. But but but the idea that that's one of the places where significance could lie is pretty strongly at odds with the idea that our salvation is going to come from optimization and efficiency. Maybe something about the way we live our lives will have that integrated into it. Um, but it's, but it's at odds with other, other moments. </s>
<s>[INST] They just provide this incredible note taking tool for the masses, but they provided to businesses, especially small businesses and startups to sort of actually help them get uh real stuff done and provide value and then they can pay for that value. So if you're a startup you should definitely check them out and get started for free at notion dot com. This episode is also brought to you by better help spelled H E L P help. I think they're a sponsor on a lot of my favorite podcast, which is awesome because it makes me feel like we're in this together. So it's great that better help us supporting all of these amazing podcasts. Anyway, I'm a huge fan of talk therapy, which is what they do. You can connect online with a licensed professional therapist in under 48 hours. The conversation is a great way to of opening up your mind without resistance [/INST] and just </s><s>[INST] seeing what comes out and it's fun to see whatever lurks there in your shadow, in the darkness of your shadow and the subconscious and unconscious mind. [/INST] It's </s><s>[INST] great for you. It's good to do talk therapy to help a little bit at least bring the beautiful puzzle of it to the light, check them out at better help dot com slash lex and save on your first month. The show is also brought to you by blink ist my favorite app for learning new things. They got nonfiction books, thousands of them and they condense them down into 15 minute chunks you can read or listen to by the way, this isn't to save time. I guess you save time. There's this obsession in this world of being in a hurry. A lot of people listen to podcasts at like incredibly high speeds. I admire those people. I give them props, but I'm just not that person. I like to sit [/INST] on </s><s>[INST] a sentence on a word sometimes on a silence for a long time and think and in that way blinking isn't about at least to me about saving time? It's about actually revealing something powerful about a nonfiction book that you may otherwise miss? So I think even if you read the book, it's just a good supplement to the book, reading experience before after to remind yourself to preview it. To select which books you want to read in full, all that kind of stuff. You can claim a special offer now for savings at blink ist dot com slash lex. This is Alex Friedman podcast to support it. We check out our sponsors in the description and now your friends. Here's nick Lane. Let's start with. Perhaps the most mysterious, the most interesting question that we little humans can ask of ourselves. How did life originate on earth? [/INST] You could, you could ask anybody working on the subject and you'll get a different answer from all of them. They will be pretty passionately held opinion's and their opinions grounded in science. Um, but they're still really at this point, their opinion because there's so much stuff to know that all we can ever do is get a kind of a small slice of it. And it's the context which matters. So I can give you my answer. My answer is from a biologist's point of view that has been missing from the equation over decades, which is well, what does life do on earth? What what why is it this way? Why is it made of cells? Why is it made of carbon, why does it, why is it powered by electrical charges on membranes? There's all these interesting questions about cells that if you then look to see, well, is there an environment on earth on the early Earth, four billion years ago, it kind of matches the requirements of cells? Well, there is one, there's a very obvious one. It's basically created by whenever You have a wet rocky planet, you get these hydrothermal vents which generate hydrogen gas in bucket loads and electrical charges on kind of cell like pores that can can drive the kind of chemistry that life does. So it seems so beautiful and so, so obvious um that I've spent the last 10 years or more trying to do experiments. It turns out to be difficult. Of course, everything is more difficult than you ever thought it was going to be. But it looks, I would say more true rather than less true over that 10-year period. I think I have to take a step back every now and then and think, hang on a minute, where's this going? I'm happy, it's going in a sensible direction and I think then you have these other interesting dilemmas. I mean, I'm often accused of being too focused on life on Earth to kind of narrow minded and inward looking. You might say I'm think I'm talking about carbon. I'm talking about cells and maybe you or plenty of people can say to me ah Yeah, but life can be anything. I have no imagination. Maybe they're right. But unless we can say why life here is this way. And if those reasons are fundamental reasons or if they're just trivial reasons then we can't answer that question. Um So so I think they're fundamental reasons and I think we need to worry about them. </s><s>[INST] Yeah. There might be some deep truth to the puzzle here on earth that will resonate with other puzzles elsewhere that will um solving this particular puzzle will give us that deeper truth. So what to this puzzle, you said, vents hydrogen wet so chemically, what is the potion here? How important is oxygen? You wrote a book about this? [/INST] Yeah. And I actually just came straight here from a conference where I was chairing a session on whether oxygen matters or not in the history of life, of course it matters, but it matters most of the origin of life to be not there. Um as I see it, we have this. I mean like life is made of carbon basically primarily organic molecules with carbon carbon bonds and the building block the lego brick that we take out of the air or take out of the oceans is carbon dioxide and to turn carbon dioxide into organic molecules we need to strap on hydrogen and so we need and this is basically what life is doing its hydrogen ating carbon dioxide is taking the hydrogen that bubbles out of the earth in these hydrothermal vents and it sticks it on C. 02. And and it's kind of really as simple as that um actually thermodynamic lee. There's the thing that I find most troubling is that you if you do these experiments in the lab, the molecules you get are exactly the molecules that we see at the heart of biochemistry in the heart of life. </s>
<s>[INST] I worry about that and that's part of the thing that you're talking about is people that build the technology had to be thinking about ethics have to be thinking about access and all those things and not not just a small small subset. Let me ask some philosophical slightly romantic questions. People to listen to this we'll be like here he goes again. Okay. Do you think do you think one day we'll build an Ai system that we a person can fall in love with and it would love them back. Like in the movie her for [/INST] example. Yeah. Although she kind of didn't fall in love with him or she fell in love with like a million other people, something like that. </s><s>[INST] So you're the jealous type I see. So we humans [/INST] at the job so I do believe that we can design systems where people would fall in love with their robot with their um Ai partner. Um That I do believe because it's actually and I don't I don't like to use the word manipulate but as we see there are certain individuals that can be manipulated if you understand the cognitive science about it. Right. </s><s>[INST] Right. So I mean if you could think of all close relationship and love in general as a kind of mutual manipulation that dance the human dance manipulation is a negative connotation. Uh [/INST] I don't like to use that particularly. </s><s>[INST] I guess another way the phrases you're getting at is it could be algorithm a ties or something. It could be a [/INST] relationship building part can Yeah, I mean just think about it there we have and I don't use dating sites but from what I heard there are some individuals that have been dating that have never saw each other. Right? In fact there's a show I think that tries to like weed out fake people. Like there's a show that comes out right? Because like people start faking like what's the difference of that person on the other end being an ai agent. Right? And having a communication and you building a relationship remotely like there's no reason why that can't happen </s><s>[INST] in terms of human robot interaction. So what role you've kind of mentioned with data, emotion being can be problematic if not implemented? Well I suppose what role does emotion and some other human like things the imperfect things come into play here for good human robot interaction and something like love. [/INST] Yeah. So in this case and you had asked can an ai agent love a human back. Um I think they can emulate love back. Right. And so what does that actually mean? It just means that if you think about their programming they might put the other person's needs in front of theirs in certain situations, right? You look at think about it as return on investment. Like was my return on investment as part of that equation, That person's happiness, you know has some type of you know algorithm waiting to it. And the reason why is because I care about them, right? That's the only reason, right? Um But if I care about them and I show that then uh my final objective function is length of time of the engagement, right? So you can think of how to do this actually quite easily. And so </s><s>[INST] but that's not love. [/INST] Well so that's the thing. Um It I think it emulates love because we don't have a classical definition of love, </s><s>[INST] right? But and we don't have the ability to look into each other's minds to see the algorithm. [/INST] And </s><s>[INST] I mean I guess what I'm getting at is is it possible that especially if that's learned, especially if there's some mystery and black box nature to the system, how is that? You know, how is it any different? How is any different in terms of sort of if the system says I'm conscious I'm afraid of death and it does indicate that it loves you another way to sort of phrase. Be curious to see what you think. Do you think there will be a time when robots should have rights? You've kind of phrase the robot in a very roboticist way and just a really good way, but saying, okay, well there's an objective function and I could see how you can create a compelling human robot interaction experience that makes you believe that the robot cares for your needs and even something like loves you. But what if the robot says, please don't turn me off? What if the robot starts making you feel like there's an entity of being a soul there? Right? Do you think there will be a future? Hopefully you won't laugh too much at this, but where they do ask for rights [/INST] so I can see a future if we don't address it in the near term where these agents as they adapt and learn could say, hey, this should be something that's fundamental. Um I hopefully think that we would address it before it gets to that point. </s><s>[INST] You think you think that's a bad future is like, what is that a negative thing where they ask were being discriminated against? [/INST] I guess it depends on what role have they attained at that point. Right? And so if I think about </s><s>[INST] now careful what you say because The robots, 50 years from now, I'll be listening to this and you'll be on TV is saying this is what robotics is used to believe. [/INST] Well, right. And so this is my and as I said, I have a biased lens uh and and my robot friends will understand that. Um but so if you think about it um and I actually put this in kind of the as a roboticist, you don't necessarily think of robots as human with human rights, but you could think of them either in the category of property or you can think of them in the category of animals, right? And so both of those have different types of of rights. So animals have their own rights as a living being, but you know, they can't vote, they can't write uh they they can be euthanized but as humans, if we abuse them, we go to jail like right? So they do have some rights that protect them, but don't give them the rights of like citizenship. And then if you think about property property, the Wrights are associated with the person, right? So if someone vandalizes your property or steals your property, like there are some rights but is associated with the person who owns that. If you think about it back in the day and if you remember we talked about, you know how society has changed, women were property right? They were not thought of as having rights, they were thought of as property of </s>
<s>[INST] And now here's my conversation with Manolis callous, You mentioned Leonard Cohen and the song Hallelujah as a beautiful song. So what are the three songs you draw the most meaning from about life? [/INST] Don't get me started. So there's really countless songs that have marked me that have sort of shaped me in periods of joy, periods of sadness. My son likes to joke that I have a song for every sentence he will say because very often I will break into a song with the sentence you'll say, my wife calls me the radio because I can sort of recite hundreds of songs that have really shaped me. So it's very, it's gonna be very hard to just pick a few. So I'm just gonna tell you a little bit about my song transition as I've grown up in Greece. It was very much about as I told you before, the misery, the poverty, but also overcoming adversity. So some of the songs that I have really shaped me are had dyslexia for example, is one of my favorite singers in Greece. And then there's also really just old traditional songs that my parents used to listen to like one of them is uh the moon pollution, eos which is basically oh if I was rich and the song is painting this beautiful picture about all the noises that you hear in the neighborhood, his poor neighborhood, the train going by the priest walking to the church and the kids crying next door and all of that. And he says with all of that, I'm having trouble falling asleep and dreaming if I was rich and then he was like, you know, break into that. So it's the juxtaposition between the spirit and the sublime and then the physical and the harsh reality, it's just not having troubles, not, not not being miserable. So basically rich to him just means out of my misery basically. Uh and then also being able to travel, being able to sort of be the captain of a ship and you know, see the world and stuff like that. So it's just such beautiful imagery. </s><s>[INST] So many of the greek songs just like the poetry we talked about, they acknowledge the cruelty, the difficulty of life but our longing for a better life. That's exactly [/INST] right. And another one is the whole oh yeah and this is one of the songs that has like a fast and joyful half and a slow and sad half and he goes back and forth between them and it's like the whole Seneca dragoons. He's so poor basically uh it's the state of being poor. I don't I don't even know if there's a word for that in english. And then fast part is to reassume mega Lawson came up. So and then it's like, oh you know, um basically like the state of being poor and misery, you know for you write all my songs etcetera. And then the fast part is in your arms, grew up and suffered and you know, stood up and you know, rose um men with clear vision, it's called concept of taking on the world with nothing to lose because you've seen the worst of it. This imagery of still occupy paris Apoula Harasta, chorizo palazzo is describing the young men as cypress trees. And that's probably one of my earliest exposure to a metaphor to sort of you know, this very rich imagery. And I love about the fact that I was reading a story to my kids the other day and it was dark and my daughter who's six is like, oh can I please see the pictures and Jonathan who's um eight. So some of my daughter Cleo is like, oh let's look at the pictures and my son Jonathan, he's like, but Cleo, if you look at the pictures, it's just an image if you just close your eyes and listen, it's a video brilliant. It's beautiful. And he's basically showing just how much more the human imagination has besides just a few images that the book will give you. And then another one, oh gosh, this one is really like miserable. It's called Stupid really to Griffo. And it's basically describing how vigorously we took on our life and we pushed hard towards the direction that we then realized what is the wrong one. And again, these songs give you so much perspective. There's no songs like that in english that. Well, basically, you know, sort of just smack in the face about sort of the passion and the force and the drive and then it turns out we just follow the wrong life and it's like, wow, okay, all right. So that, that's like before 12. So, so you know, growing up in sort of this horrendously miserable, you know, sort of view of romanticism of, you know, suffering. Um, so then my preteen years is like learning english through songs. So basically, you know, listening to all the american pop songs and then memorizing them vocally before I even knew what they meant. So, you know, Madonna and Michael Jackson and all of these sort of really popular songs and you know, George, Michael and uh, just songs that I would just listen to the radio and repeat vocally. And eventually as I started learning english, I was like, oh wow, this thing I've been repeating. I know I now understand what it means without really listening to it, but just with re repeating, it was like, oh again, Michael Jackson's Man in the Mirror is uh, teaching you that it's your responsibility to just improve yourself if you want to make the world a better place, they can look at yourself and make the change this whole concept of again, I mean all of these songs, you can listen to them shallowly or you can just listen to them and say, oh, there's a deeper meaning here. And I think there's a certain philosophy of of song as a way of touching the psyche. So if you look at regions of the brain, people have lost their language ability because they have an accident in that region of the brain can actually sing because it's exactly the symmetric region of the brain. And that again, teaches you so much about language evolution and sort of the duality of musicality and you know, rhythmic patterns and eventually language. </s>
<s>[INST] So, look, I assume is a big part of this. [/INST] Yeah, for sure. I mean, there's just so many variables that are uncontrollable on this type of an experience. Just because I mean, you go over this year as maybe you hit a storm, you know, you try to time it. Most people do it in, start in september so you can, can get over the mountain passes without a big storm coming through. Uh but they also get to the east coast before it's like the middle of winter. So like september early september start is kind of ideal. But you can, you know, I mean, Pete was very fortunate from a weather standpoint. I think he made one big mistake, we had a little too aggressive beginning, had to take a full day off. So he actually averaged from a moving day standpoint closer to 75 miles per day. Um but yeah, I mean there's gonna be things that I can't prepare for, won't know it's going to happen, you know, a lot of that will get a lot of the logistical stuff will get leaned on with the crew. So that's I mean that's the hardest part right now is just like getting all that put together where it's like okay, I need to have the RV ready, I need to have all the stuff, we need to have the places figured out where we're going to stop and and the people that can, you know, dedicate that much time to an activity like that. You know, there's a lot of moving parts even before you start the adventure itself. What </s><s>[INST] are you see, you're, you're taking the san Francisco to new york. When are you doing the run [/INST] september 1st is when, you know, barring anything like catastrophic between now </s><s>[INST] and that's really exciting, but I mean it's incredible. So you probably have a bunch of people just randomly running with you, are people going to be tracking where you're located? [/INST] Yeah, so I'll be documenting everything because I mean my hope is that I'm doing it primarily to raise awareness for fight for forgotten just in Rennes charity. Uh, but with that said, I think I am capable of uh, if I have a good experience, uh, you know, chasing the record or going after the record or at least getting close to it. So, </s><s>[INST] so you're going to try to beat this record? [/INST] Yeah, I'm gonna, I'm gonna go out with it. I'm going to structure the process in a way that leaves that door open is the way I would describe it. I'm gonna try not to do anything that would potentially put in a situation where that becomes the primary goals, just because I want to make sure that the reason I decided to do in the first place was for fight for the forgotten. So I want to make sure that I don't end up two thirds the way across the country with a broken leg and like, hey guys guess the donation buttons turned </s><s>[INST] off, so focus on like don't sacrifice that, that goal, but also there is a community aspect to it that I feel like, are you going to, I mean, so you're going to document and post, but are you going to also, is there a safety perspective here? It's like the forest gum thing, you might have large numbers of crowds that run along with you for a while [/INST] worried </s><s>[INST] about that kind of thing. [/INST] I wouldn't say I'm worried about, I mean I think there's probably, there's remote enough spots along the way where you'll get some alone time or more likely. I don't necessarily mind if people want to jump in, there will be some people that will definitely want to do that and they can come in and but the reality is like, it's probably not going to be a scenario where there's like, You know, 40 people following me at all times. You </s><s>[INST] say that now. [/INST] You never know. Wait for this podcast. </s><s>[INST] Yeah. And then if joe finds out you're doing this, then we're really in trouble. All right. So I mean, what are the things that you think will be the hardest for you and also like how do you train for this kind of thing? Um, and what yeah, one of the hardest things you anticipating, How do you train for them. [/INST] Yeah. So the way I'm looking at this is, it's much less about performance from the traditional sense where I need to be able to be X fit. I think I need to be injury proof. That's what's going to be a detriment if you think about it. Like if I managed to average nine minute mile pace for a day, that would be 80 miles in a 12 hour time frame. So I'll easily have 12 hours of moving time per day. Um Nine minute pace I think is slow enough. That is not an unreasonable clip. So like when you, I mean obviously there's things that slow you down or I'll probably take walking breaks, you know, stopping breaks, you have to stay on top of nutrition. That's the other big thing too. I'm, you know, probably like anywhere between 10 to 15,000 calories a day, which is, you know, I can probably count on my hand a couple of occasions where I've eaten that much in my life. So now I got to do that for six plus weeks in a row </s><s>[INST] and saying, you don't want to have any stomach problems trying to minimize the amount of stomach problems. Would you estimate about 12 to 13 to 14 hours of running every day? [/INST] Yeah, that's probably like from from the first step to the last step, it'll probably be somewhere around like, say, 14 hours, 13 hours or something like that would be a pretty good estimate </s>
<s>[INST] there's unfortunately sadly a lot of people that look up to you, [/INST] that is a horrible thing, but life is a nightmare. </s><s>[INST] Uh if you were to give them advice, young young folks, people in college, maybe even high school, but people in their twenties about what to do with their life, whether it's career, whether it's just life in general. What would you say, ignore [/INST] everyone make a few good friends truly have honest conversations with yourself about your, what, when do you feel the most alive? Figure that out when and how do you feel the most alive? Figure that out. Try to figure out a job or a career that can replicate that feeling. Um, don't listen to anyone, Don't listen to your parents. Don't listen to the gurus on the internet. Don't listen to me. Don't listen to anyone figure out you know where you feel the most alive. Where do you feel excited? Where do you, where does your pulse quicken? What do you feel matters when you're in a situation? Do you feel like it matters? What situation was that? What got you excited? What thing did you walk into where you looked around and were taken back and you're like, wow, this is amazing. And I'm filled with awe. If you can figure out a life where you, you, you can excite yourself. You might not use drugs or alcohol or a sex addiction or gambling or irresponsibility. You might not have to get your fucking kicks in very destructive places if you can get them in a productive place. We've </s><s>[INST] got to you have a pretty weaving like that's full of uh mistakes and so on. Many mistakes. Is that our mistakes a bug or feature. Like do you recommend embrace the mistakes? Make, make a bunch of them [/INST] depends what they are, right? So you had the full spectrum. I've had a lot, but a lot of mine could have sunk, made like their sound like fun when I talk about them, but they actually could have sunk me and they were all part of what made me funny, but I don't know. I would never tell anyone else to just like their life on fire and hope it works out on the other end. It would be pretty irresponsible. But hey, at the end of the day, it's like you're gonna, we get there's, you know, I think one of my themes is that there's too much we give the power. We think we have to, the power of choice has been elevated on our society to an unhealthy degree. I think people are, I think you could, you could get really good at something, but you're born with a certain aptitude. It might be to be a dealmaker. Might be to be an athlete, it might be to be an artist. It might be to be a romantic and just fall in and out of love in and out of love in and I love, it might be to be like a world traveler like, but whatever you are, I think you are, I think that there's something about you that makes you something and if you can figure it out and then you're not going to be good at it per se. But if you're, if you're an athlete, it might not mean that you're going to be a great athlete in the history, but it might mean you're the best coach anyone's ever had or you're the person that you know builds a local scene for young athletes or whatever. If you are a really good deal maker, it doesn't mean you're gonna be warren Buffett, but it might mean you're somebody who enjoys making deals all the time and things like that. Like if you're an entertainer, it might mean that you are an entertainer. It might mean that you are in the world of entertainment because you love it so much that if you lack the skill set to really pursue it on on a degree, you just want to be like, there's there's a there's a thing inside of you that makes you what you are. I think I look at certain people and I know you were born to be that thing. You know, the whole purpose is to find it. I was a juror on that murder trial on a murder trial in Long Island and the woman who is the D. A. I'm like you were born to do this, you were born to put murderers away and this guy killed the mother of his Children and he's a bad guy. But like I was like you are really good at what you do. She has a strong belief in whatever heard moral code is and what justice and ethics are and she wants to communicate that to people. She was very good uh, at doing what she did. I don't know the facts of the case. I didn't really listen, he seemed guilty but just voted guilty, but she didn't really listen to her. But I heard the shape of her mouth was very bovine like account it conferred a certain level of expertise that I enjoyed. </s><s>[INST] It was funny. I mean you could see your half joking, you can often see that people just this, they found their place, they found their role, they found their thing and that's kind of the purpose of life and once you are in a place that seems sticky like the place that seems right, you know, that's one of the problems with the generation that you're speaking to is there's always a feeling like I should keep exploring, keep exploring, but it's okay to stay in a place that you follow that works [/INST] Yeah. And and listen sometimes the best place you'll find is like one point people are like, when did you feel really excited and alive? It's like doing nothing. You know, like that's the other thing. It's like some people gonna be like, I feel really excited and alive and I'm laying in my backyard in a hammock and I just wanted the simplest life and not have to do much and I don't like doing anything and I love laying around and go, wow this guy looks good today. Bill Gates because this guy was good today. Let's shoot a missile into it. He wants to do ship, right? So it's like in between that and nothing is you can find something </s>
<s>[INST] do it. So it's [/INST] all about the context and </s><s>[INST] the situation. Um, [/INST] for example, working </s><s>[INST] in Northern Yemen, you [/INST] couldn't film for </s><s>[INST] five minutes if you [/INST] didn't have paperwork because you'd be taken away. So you have </s><s>[INST] to make sure you have all those permissions [/INST] ahead of time. 50 ft from Syria. </s><s>[INST] Um, I would love to talk at least a little bit about this film. Um First, can you high level, can you tell what this documentary is about? Yeah, [/INST] it was early in </s><s>[INST] um the Syrian [/INST] uprising and um we returned to the Syrian </s><s>[INST] Turkish border with a Syrian [/INST] american orthopedic surgeon who </s><s>[INST] is volunteering [/INST] operating on </s><s>[INST] refugees as they float across the border from Syria into Turkey. [/INST] Um, and it was an attempt at the time before. A lot of films had come out about the conflict to um really show again </s><s>[INST] um [/INST] the effects of the war on civilians. Um, you've heard </s><s>[INST] me echoed that sentiment [/INST] multiple times now, </s><s>[INST] but it it, you [/INST] know, people knew there was there was a major conflict in Syria, but didn't really understand the form that that was taking and the impact it </s><s>[INST] was having. And [/INST] so we we embedded into </s><s>[INST] the at the [/INST] time. It was the only </s><s>[INST] clinic [/INST] in Turkey that was </s><s>[INST] sanctioned by the Turkish [/INST] government um to </s><s>[INST] treat Syrian refugees. [/INST] Um, and so we filmed there with surgeons </s><s>[INST] as they operated [/INST] on more victims. </s><s>[INST] And we [/INST] also went into Syria into some of the camps as well. </s><s>[INST] So in this film [/INST] there's a man </s><s>[INST] who crosses the border every day to retrieve the wounded and fair them [/INST] safety and care. </s><s>[INST] And you also mentioned [/INST] about heroism </s><s>[INST] in the United States. Um, can you tell me [/INST] about this man and </s><s>[INST] just people like him, like what's the heroic [/INST] action in </s><s>[INST] some of these places that you've visited? [/INST] So, in that instance, you know, I thought of him as </s><s>[INST] the Turkish Schindler, right? [/INST] Because he was human being who um of </s><s>[INST] his own volition [/INST] volition. And no one was paying him to do this. </s><s>[INST] But [/INST] he was spending much of his time. He was just a local businessman who really saw the need in the camps </s><s>[INST] Right across the border, 10-K [/INST] away, and </s><s>[INST] and and he [/INST] saw the medical need in particular, </s><s>[INST] and how [/INST] hard it was to get people in desperate medical conditions across the border where there was a </s><s>[INST] clinic just [/INST] right across the border. But because of the security and the layers of security, um, they couldn't get out by themselves. So he </s><s>[INST] took it upon himself [/INST] as a Turkish person to build relationships with the Turkish guards, which was relatively easy. And </s><s>[INST] then he [/INST] built relationships with sort of the guards in the no man's land between </s><s>[INST] the Syrian guards [/INST] and sort of those who lived in the middle area. And then also with the Syrian guards at </s><s>[INST] the camp [/INST] and he would drive out there daily and bring them food, </s><s>[INST] right? [/INST] Talk him up and build relationships. And so every day he would bring these guards food and build relationships with them. And what that meant was eventually right. He had this </s><s>[INST] avenue of [/INST] access to and from the camps </s><s>[INST] and so he started using [/INST] it and </s><s>[INST] he would [/INST] dr this avenue of </s><s>[INST] access [/INST] through the three layers of guards each day and then they would open the gates for him </s><s>[INST] because he had made [/INST] himself trustworthy in their eyes. And he would receive </s><s>[INST] the [/INST] most desperate medical cases that were coming from all over Northern Syria, right to </s><s>[INST] receive medical treatment. [/INST] And he would, </s><s>[INST] as you see in the film, he [/INST] would ferry them into the back of </s><s>[INST] his car, right? [/INST] And then drive them to </s><s>[INST] the hospital [/INST] where they would receive operations and then </s><s>[INST] he would [/INST] bring them back if they wanted after </s><s>[INST] they had healed and [/INST] recovered back to Syria. If they wanted to return at post recovery and you know, he didn't get paid </s><s>[INST] for that, he [/INST] was spending his own money to do it because he saw </s><s>[INST] other human beings [/INST] in need and </s><s>[INST] it's like we were talking about [/INST] earlier, </s><s>[INST] that's heroic, [/INST] right? That's selfless. That's that's aspirational for me, right? Here's here's someone who is spending their time on the planet doing something of value </s><s>[INST] and good to other human [/INST] beings. </s><s>[INST] I mean, if you [/INST] draw parallels to Schindler, </s><s>[INST] I feel like [/INST] the fascinating thing </s><s>[INST] about [/INST] Schindler's that </s><s>[INST] he's [/INST] kind of a flawed human </s><s>[INST] and it's not the kind of human that does these [/INST] things usually, but you just </s><s>[INST] can't help it. [/INST] And that's like the basic humanity, </s><s>[INST] despite [/INST] who </s><s>[INST] you are, the basic [/INST] humanity shines through. I think that, you know, the whims of </s><s>[INST] war test [/INST] people in those ways, </s><s>[INST] right? They, they [/INST] ask of you things that you may not </s><s>[INST] even [/INST] know we're going </s><s>[INST] to be asked of you and [/INST] then it speaks to who, who you are fundamentally as a human being. They </s><s>[INST] reveal who you are as a [/INST] human being. Just as you </s><s>[INST] said. [/INST] Um </s><s>[INST] let me ask a kind of stupid technical [/INST] question </s><s>[INST] about publications and movies [/INST] and so on. I've been um </s><s>[INST] recently [/INST] becoming good friends with thomas Tall </s><s>[INST] who was the producer, his [/INST] company legendary, finding some </s><s>[INST] of the big sort of blockbuster [/INST] films and so on. And so </s><s>[INST] obviously money is part [/INST] of filmmaking. That's </s><s>[INST] interesting. But also the release of movies [/INST] and me as a consumer, </s><s>[INST] you know, [/INST] with netflix, with Youtube, </s><s>[INST] you know, [/INST] that's one </s><s>[INST] of the reasons I'm a huge fan of [/INST] Youtube is, </s><s>[INST] it's like out [/INST] in the open access, especially historical access, </s><s>[INST] like over time, [/INST] you can look back </s><s>[INST] years later if you pay some money, you can watch some of the great films ever made. [/INST] Um </s><s>[INST] Youtube hulu netflix, I don't know what other services that are. HBO paramount plus paramount plus. Um [/INST] anyway, there's </s><s>[INST] all these platforms [/INST] Spotify </s><s>[INST] now. [/INST] It's uh, I understand they want to </s>
<s>[INST] well can I have to proceed carefully here because it's a complicated topic. Um so she took the call and you kind of, you're kind of saying that bro, she basically erased credit, you know, pretending you didn't exist in some kind of in a certain sense. Let me phrase it this way. I've uh as a as a research scientist at MIT I've had an especially just part of a large set of collaborations. I've had a lot of students come to me and talk to me about ideas perhaps less interesting than what we're discussing here in the space of A. I that I've been thinking about anyway in general with everything I'm doing with robotics people uh would have told me a bunch of ideas that I'm already thinking about. The point is taking that idea. See this is different because the idea is more power in the space that we're talking about here in robotics is like your idea means ship until you build it like so the engineering world is a little different but there's a kind of sense that I probably forgot a lot of brilliant ideas have been told to me. Do you think she pretended you don't exist? Do you think she was so busy that she kind of forgot? You know, she has like the stream of brilliant people around her that there's a bunch of ideas that are swimming in the air and you just kind of forget people that are a little bit on the periphery, on the idea generation. Like or is it some mix of both. [/INST] Uh it's not a mix of both. Um I know that because we corresponded, she put a graduate student on this work. He emailed me excitedly when the results came in. So there was no ambiguity about what had happened. What's more. When I went to publish my work, I actually sent it to carol in order to get her feedback because I wanted to be a good collaborator to her. And she absolutely Pandit made many critiques that were not valid. But it was clear at that point that she became an antagonist and none of this adds that she couldn't possibly have forgotten the conversation. Um I believe I even sent her tissues at some point in in part not related to this project, but as a favor, she was doing another project that involved telomeres and she needed samples that I could get a hold of because of the Museum of Zoology that I was in. So this was not a one off conversation. I certainly know that those sorts of things can happen, but that's not what happened here. This was a relationship that existed and then was suddenly cut short at the point that she published her paper by surprise without saying where the hypothesis had come from and began to be a opposing force to my work. </s><s>[INST] Is there there's a bunch of trajectories that could have taken through life. Do you think about the trajectory of being um a researcher of then going to war in the space of ideas of publishing further papers along this line. I mean, that's often the dynamic of that fascinating space is you have a junior researcher with brilliant ideas and a senior researcher that that starts out as a mentor that becomes a competitor. That that happens. But then the way two, it's an almost an opportunity to shine is to publish a bunch more papers in this place that did to tear it apart to dig into like really uh make it a war of ideas. Did you consider that possible trajectory? I [/INST] did a couple of things to say about it. One this work was not central for me. I took a year on the telomere project because something fascinating occurred to me and I pursued it and the more I pursued it, the clearer it was there was something there, but it wasn't the focus of my graduate work and I didn't want to become a telomere researcher. What I want to do is to be an evolutionary biologist who upgrades the toolkit of evolutionary concept so that we can see more clearly how organisms function and why. And telomeres was a proof of concept, right? That paper was a proof of concept that the toolkit in question works. Um as for the need to pursue it further, I think it's kind of absurd and you're not the first person to say maybe that was the way to go about it. But the basic point is look, the work was good. The it turned out to be highly predictive, frankly, the model of sin essence that I presented is now widely accepted and I don't feel any misgivings at all about having spent a year on it said my piece and moved on to other things which frankly I think are bigger. Um I think there's a lot of good to be done and it would be it would be a waste to get overly narrowly focused. </s><s>[INST] There's so many ways through the space of science and the most common ways to just published a lot. Published a lot of papers, these incremental work and exploring the space kind of like ants looking for food. You're tossing out a bunch of different ideas. Some of them could be brilliant breakthrough ideas nature, some of their more confidence kind of publications, all those kinds of things. Did you consider that kind of path and science? [/INST] Of course I considered it. But I must say the experience of having my first encounter with the process of peer review be this story which was frankly a debacle from one end to the other. With respect to the process of publishing it did not, it was not a very good sales pitch for trying to make a difference to publication. And I would point out part of what I ran into and I think frankly part of what explains carol's behavior is that in some parts of science there is this dynamic where p is parachutists, their underlings. And if you're very, very good, uh you rise to the level or one day, instead of being parachutist, you get two parachutists, others. Now I find that scientifically despicable and it wasn't the culture of the lab I grew up in at all my lab. In fact, the P. I. Dick alexander who is now gone, but who was an incredible mind and a great human being. He didn't want his graduate students working on the same topics he was on, not because it wouldn't have been useful and exciting, but because in effect, he did not want any confusion about who had done what, because he was a great mentor. And the idea was actually a great mentor is not stealing ideas and you don't want you don't want people thinking that they are. So anyway, my point would be um I wasn't up for being parachutist. I don't like the idea that if you are very good, you get parachutist until it's your turn to parasitism. Others that doesn't make sense to me. Um A crossing over from evolution into cellular biology may have exposed me to that. That may have been par for the course, but it doesn't make it acceptable. And I would also point out that my work falls in the realm of synthesis. My work generally takes evidence accumulated by others and places it together in order to generate hypotheses that explain sets of phenomena that are otherwise intractable and I am not sure that that is best done with narrow publications that are read by few. And in fact, I would point to the very conspicuous example of Richard Dawkins, who I must say I've learned a tremendous amount from and I greatly admire Dawkins has almost no publication record in the sense of peer reviewed papers in journals. What he's done instead is done synthetic work and he's published it in books which are not a peer reviewed in the same sense. And frankly, I think there's no doubting his contribution to the field. So my sense is if Richard Dawkins can illustrate that one can make contributions to the field without using journals as the primary mechanism for distributing what you've come to understand that it's obviously a valid mechanism and it's a far better one from the point of view of accomplishing what I want to accomplish. </s>
<s>[INST] So there's a fixed number, there's there's a fixed frequency of blocks. And so if you want to increase the number of transactions per second, you want to increase the size of the blocks, huge blocks allow you to shove in a lot of transactions. Right? Small blogs don't, so that's what you mean, like constraining the system. So what's the benefit of a small block size for transactions? Uh, when you can squeeze in only a small number of transactions and what's the benefit of a huge block size where you can squeeze in a lot of transactions? [/INST] Well, it really comes down to the way you think about the system. So a lot of people wanted Bitcoin to be Visa scale. So to have blocks sufficiently large that you could accommodate a Visa level scale of transactions. So </s><s>[INST] which is many orders of magnitude more transactions? [/INST] That's right. I mean, preposterously larger in terms of data throughput than Bitcoin offers up or at least it used 244 MB of space per day. And your average transactions 350 bytes. So you know, you could add a push to 4, 500,000 transactions a day, which is not many. So if you wanted to get to Visa scale you'd have to increase blocks. Obnoxiously large. The small blockers claimed that this would overwhelm the ability of any regular person to ingest that data and stay current at the state of the ledger to rebroadcast to replay all those transactions to ensure that the protocol rules are valid. So basically the small block your contention is that you eliminate the trust looseness of the system by pushing a ton of data through the system because only one or two industrial heavy duty nodes would ever be able to run the protocol at that point. </s><s>[INST] So by the way, in the civil war, the two sides is as you're calling them the small blocker. And the big blocker sides. And so that takes us back to the uh the thing that you mentioned that a regular computer could be a node and with a big with big blocks, that's no longer going to be the case. So just the number of transactions is going to blow up the size of the Blockchain that every full node has the store. And so then as opposed to a regular mom and pop type of node, you're going to have to have data centers. So they're going to have to be owned by large organizations is going to have to be very few of them. And that's how you centralize the control over this whole uh operation. So the big blocker, yes, it allows you to be Visa and do a huge number of transactions, but it becomes centralized and small blocker is you cannot actually do kind of merchant style transactions but you get the decentralized benefit. [/INST] Well, I don't even think the big block approach would allow you to be Visa frankly, because there's effectively one note of the Visa network. Right. Um, so you don't really need to maintain this peer to peer architecture at all. Um and the amount of data you have to push through the network to reach visa scales are really preposterous amount. I mean, and we have now evidence for what happens when you try and scale up as a Blockchain and do 10 million transactions a day, which is still not visa scale right? You know, I've, I've, you know, seen what it's like to operate those nodes and it's not pretty. So there are totally genuine computer science physical limits. Um because it's a, it's a broadcast network. Everyone has to be aware of every transaction. And that model which gives you the trust looseness, the nice guarantees where everyone is an equal peer on the network, everyone has audited the full history of the transactions. That model falls apart under stress. So the small block of vision is that ultimately you would scale in a layered approach with the base layer transactions being settlement style transactions and, you know, payments happening at the other layers basically. </s><s>[INST] Is that universally agreed upon or like to a large degree agreed upon that the small blockers have one and is in this debate. Well, where would you put the current state of affairs? [/INST] There was a wave of competing Bitcoin implementations in starting in 2015 with Bitcoin. XT Actually, Gavin Anderson, who is the guy that Satoshi handed the reins to when Satoshi left, Gavin supported this large block block proposal. Uh And so that was that didn't achieve consensus and then the respect quite unlimited. And then later on, there is a genuine hard fork where the small blockers couldn't or the large blockers couldn't push through their proposals on Bitcoin itself. So they just created a competing version of Bitcoin. So </s><s>[INST] by the way, uh maybe you can comment on, but sort of hard fork versus a soft fork. A hard fork is when it's not no longer compatible. What's the right way to put it? They can't operate on the same block chain. They say we're the same protocol. [/INST] Yeah, so there's a few ways to define them and it's pretty gets controversial as well, but um, 11 way to define it as a hard fork is a expansion of protocol rules and the soft fork is a shrinking of protocol </s><s>[INST] rules. That's an interesting way to fight. It's [/INST] not very intuitive, so I don't like that way. Um Another way is that a hard work is backwards incompatible, whereas soft work is in theory backwards compatible. So in August 2017 basically the large blockers had had enough and they said we're going to hard fork Bitcoin, we're going to create a clone, an alternative version of Bitcoin which has the same shared history as Bitcoin itself, but you completely fork it and you create a new future and uh but you know everybody that had a balance on Bitcoin at the time also had a balance on the alternative coin. Bitcoin cash. And so that was really, </s>
<s>[INST] Well, Scott Aaronson who's now here at Ut Austin, he used to be at MIT Puts the probability of P&P not equal to NP at 3%. He put, you know, I always love it when you ask. It's very rare in science in and academics because you're because most folks are humble in in the face of the mystery of the uncertainty of everything around us to have the both the humor and the guts to say um like what are the chance that there is um aliens in our galaxy, intelligent alien civilizations? As opposed to saying, I don't know, it could be, you know, it could be zero, it could be depending on the factors saying it's 2.5 [/INST] percent. There's </s><s>[INST] something very pleasant about just having a it's the it's the number thing. Uh Its power to the number. It's just like 42. It's like why 40? I don't know. But it's a powerful number and then everything, this is the power of the human psychology is once you have the number 42, it's not that the number has meaning, but because it's placed in a book with humor around it, it has the meme effect of actually creating reality. I mean, you could say that 42 has a strong contribution of helping us colonize Mars because it created it gave the whatever existential crisis too many of us, including Elon Musk when he was young. You know, reading a book like that and then the now 42 is not part of his humor. He doesn't shut up [/INST] about joking </s><s>[INST] about and that humor is spreading through our minds and somehow this like silly number just had an effect in that same way. After scott told me like the 3% chance, it's stuck in my head and I think it's been having a ripple effect and everybody else the believing that p is not equal to np Scott Adams is a joke saying is three is make is actually motivating a large number of researchers to work on [/INST] It. It's very high for the potential impact, but then 3% is not </s><s>[INST] That high because it's only, you know, it's like we're not very good. I feel like humans are only able to really think about like 1% 50 and we kind of, I think a lot of people around 3% up to 50%. Like in our minds, like three [/INST] it could happen, it could happen and it </s><s>[INST] could happen is like yeah, [/INST] like half the time it'll probably happen. </s><s>[INST] So we're not very good at that. That's that's the other thing with the pandemic is uh we're not the exponential growth that we also talked about offline is uh something that we can't quite into it and that's something we probably should if we were to predict the future to anticipate the future and to understand how to create technologies that let us sort of control the future. Can I ask you for some recommendations? Uh Maybe for books or movies in your life long ago when you were a baby po or today? Um that you found insightful or you learned you learned a lot from, you would recommend to others. [/INST] Yeah. So I think I don't necessarily have an exact name of these old things, but I was generally inspired by stories true or fictional of campaigns, you know, like for example like The Lord of </s><s>[INST] the Rings. That's a container, [/INST] right? But the thing that always inspired me was it could be possible for somebody who's crazy enough to go up against adversity after adversity after adversity and it succeeds. I mean, those are false if those are fictitious. But I also spent a lot of time I guess reading about I don't know, I was interested somehow in like World War Two history for whatever reason, that's a campaign which is much more brutal. But nevertheless the idea of difficulty strategy uh fighting even when things in that in that case it was really fighting but just pushing on even when things are difficult, I guess these are these are the kinds of general stories that made me I guess want to work on things that would be hard and where it could be a campaign, it could be that you work on something for a year, multiple years because that was the point. </s><s>[INST] It starts with a single person. That that's that's the interesting thing I've obviously been, don't shut up about it recently about World War Two, especially on the Hitler side and the Stalin side, some of that has really affected my own family, that the roots of my family very much. But it's interesting to think um that it was just an idea and one person decided to do stuff and it just builds and builds and builds and you can truly have an impact in the world, both uh horrendous and and uh like exceptionally positive and inspiring. So yeah, that's uh it's like it's uh agency of us individuals, sometimes we think we're just reacting to the world, but we have the full power to actually change the world. [/INST] Is </s><s>[INST] there advice you can give to young folks? We talked, we give a bunch of advice in middle school high school mathematics, Is there more general advice you would give about how to succeed in life, how to learn for high school students, for college students, career [/INST] or life in general. So I think the first one would be to make sure that you're learning to invent and to make sure you're not just learning how to mimic because a lot of times you learn how to do X by watching somebody do X. And then repeating X. Many times with different inputs. I've just been very generic in explaining this, but I guess this is just my own attitude towards the world. I didn't like ever following anyone's directions exactly. Even if you told me that this is the way to do your homework is to write in pencil, I would say, but I think that is nice. Let's try, right? So I've been that kind of a funny person. Um but I do encourage that if you can learn how to invent as your core skill then you can do a lot. But then the second piece that comes with that is something I learned from my PhD Advisor PhD Advisor, which was well make sure that what you're working on is big enough. And so in that sense I usually advise to people once they have learned how to invent uh ideally don't just try to settle for something comfortable, try to see if you can aim for something which is hard which might involve a campaign which might be important, which might make a difference. And it's more of I guess rather than worrying what if you didn't achieve that there's also the regret of what if I didn't try that, that's how I operate, I don't operate based on, did I succeed or fail? It was hard anyway if I did this. No vid thing and the whole thing failed. But I feel terrible. No, it's a very hard problem. But what I have had the regret of not jumping in. Yes. So it's that different mentality of don't worry about the failing part as much of the make sure you give yourself the shot at those potentially unbounded opportunities. </s>
<s>[INST] which of the directions do you find most exciting [/INST] trouble </s><s>[INST] space travel. So you haven't really explored space travel in your work, you've said, you said something like if you had unlimited amount of money. I think I read it. I am a that you would make like a multiyear series space wars or something like that. So what, what is it that excites you about space exploration? [/INST] Well, because if we have any sort of long term future, it's that it just simply is that if energy and matter are linked up in the way we think they're linked up, we'll run out if we don't move so we gotta move and but but also how can we not? It's, it's built into us to, to do it or die trying. I was on easter Island um a few months ago, which is as I'm sure, you know, in the middle of the pacific and difficult for people to have got to, but they got there and I did think a lot about the way those boats must have set out into something like space. It was the ocean and and how sort of fundamental that was to the way we are. And um it's the one that most excites me because it's the one I want most to happen. It's the thing, it's the place where we could get to as humans, like in a way I could live with us never really unlocking fully unlocking the nature of consciousness, I'd like to know, I'm really curious, but if we never leave the solar system and if we never get further out into this galaxy or maybe even Galaxies beyond our galaxy, that that would that feel sad to me because um because it's so limiting. </s><s>[INST] Yeah, there's something hopeful and beautiful about reaching out any kind of exploration, reaching out across earth centuries ago and then reaching out into space. So, what do you think about colonization of MArs? So go to MArs. Does that excite you the idea of a human being stepping foot on MArs? [/INST] It does, it absolutely does. But in terms of what would really excite me, it would be leaving the solar system inasmuch as that. I just think I think we already know quite a lot about MArs and but yes, listen, if it happened, that would be I hope I see it in my lifetime. I really hope I see in my lifetime it would be a wonderful thing </s><s>[INST] without giving anything away. But the series begins with the use of quantum computers. A new series does begins with the use of quantum computers to simulate basic living organisms. Or actually, I don't know if it's quantum computers are used, but basic living organism simulated on the screen is really cool. Kind of demo [/INST] Yeah, that's right. They're using Yes, they are using a quantum computer to simulate a nematode. Yeah. </s><s>[INST] So, returning to our discussion of simulation or thinking of the universe is a computer. Do you think the universe is deterministic. Is there a free will. [/INST] So with the qualification of what do I know? Because I'm a layman, right lay person, </s><s>[INST] but with big imagination. [/INST] Thanks with that qualification? Uh yeah, I think the universe is deterministic and I see absolutely, I cannot see how free will fit into that. So, so yes, deterministic, no free will, that would be my position. </s><s>[INST] And how does that make you feel? [/INST] It partly makes me feel that it's exactly in keeping with the way these things tend to work out, which is that we have an incredibly strong sense that we do have free will. Um uh and just as we have an incredibly strong sense that time is a constant and uh turns out probably not to be the case. So we're definitely in the case of time. But the problem I always have with free will is that it gets, I can never seem to find the place where it is supposed to reside. </s><s>[INST] And yet you explore [/INST] just very, very but we have something we can call free will, but it's not the thing that we think it is, </s><s>[INST] but free world. So do you what we call free world [/INST] is what we call it, is the illusion of it. And that's </s><s>[INST] a subjective experience of the, [/INST] which is a useful thing to have. And it partly it partly comes down to, although we live in a deterministic universe, our brains are not very well equipped to fully determine the deterministic universe. So we're constantly surprised and feel like we're making, snap decisions, decisions based on imperfect information? So that feels a lot like free will. It just isn't it would be my that's my </s><s>[INST] I guess so in that sense you're sort of sense is that you can unroll the universe forward or backward and you will see the same thing and you mean that notion? [/INST] Yeah, sort of sort of but yeah, sorry, go ahead. </s><s>[INST] I mean that notion is a bit uncomfortable to think about that. It's could you can roll it back and and forward and [/INST] if you were able to do it, it would certainly have to be a quantum computer, something that worked in a quantum mechanical way in order to understand the quantum mechanical system I guess. But </s><s>[INST] and so that enrolling there might be a multiverse thing where there's a bunch of branching. [/INST] Well exactly, because it wouldn't follow that every time you roll it back or forward, you get exactly the same result, </s><s>[INST] which is another thing that's hard to wrap your [/INST] mind around. So Yeah, but that yes, but essentially what you just described that the yes, forwards and yes, backwards, but you might get a slightly different results, very different results. </s>
<s>[INST] I mean, this is something we talked about, I think last time. So there's these effects at different levels that happened. You said at a single cell level, you're trying to see things that happened due to certain perturbations and then, so it's not just like a puzzle of probation and disease. It's probation then effect at a cellular level than at an organ level thereby. Like how do you disassemble this into, like what your group is working on? You're basically taking a bunch of the heart problems in the space. How do you break apart a difficult disease uh and break it apart into problems that you into puzzles that you can now start solving. [/INST] So there's a struggle here. Computer scientists love hard puzzles and they're like, oh I want to, you know, build a method that just involved the whole thing, computational and, you know, that's very tempting and it's very appealing. But biologists just like to decouple that complexity experimentally, to just like peel off layers of complexity experimentally. And that's what many of these modern tools that, you know, my group and others have both developed and used the fact that we can now figure out tricks for peeling off the layers of complexity by testing one cell type at a time or by testing one cell at a time and you can basically say what is the effect of this genetic variant associated with Alzheimer's on human brain. Human brain sounds like, oh, it's an organ of course, just go one organ at a time. But human brain has of course, dozens of different brain regions and within each of these brain regions, dozens of different cell types and every single type of neuron every single type of glial cell between astrocytes, illegal, dangerous sites, micro glia between all of the mural cells and the vascular cells and the immune cells that are co inhabiting the brain between the different types of excitatory and inhibitory neurons that are interacting with each other between different layers of neurons in the cortical layers. Every single one of these has a different type of function to play in cognition, in interaction with the environment, in maintenance of the brain in energetic needs, in feeding the brain with blood with oxygen, in clearing out the debris that are resulting from the super high energy production of cognition in humans. So all of these things are basically um potentially deacon vulnerable, computational E but experimentally you can just do single cell profiling of dozens of regions of the brain across hundreds of individuals across millions of cells. And then now you have pieces of the puzzle that you can then put back together to understand that complexity. </s><s>[INST] I mean, first of all, I mean the human brain, the cells in the human brain are the most Okay, maybe I'm romanticizing it, but cognition seems to be very complicated. So uh separating into the function, Breaking Alzheimer's down to the cellular level seems very challenging. Is that basically you're trying to find a way that some probation and genome results in some obvious major dysfunction in the cell. You're trying to find something like that. [/INST] Exactly. So, so what does human genetics do? Human genetics basically looks at the whole path from genetic variation all the way to disease. So human genetics has basically taken thousands of alzheimer's cases and thousands of controls matched for age for sex for, you know, environmental backgrounds and so and so forth. And then look at that map where you're asking, what are the individual genetic perturbations and how are they related to all the way to Alzheimer's disease? And that has actually been quite successful. So we now have more than 27 different los I these are genomic regions that are associated with Alzheimer's at this end to end level. But the moment you sort of break up that very long path into smaller levels, you can basically say from genetics, what are the epa genomic alterations at the level of gene regulatory elements where that genetic variant perturbed the control region nearby. That effect is much larger. </s><s>[INST] You mean much larger in terms of its down the line impact [/INST] or its much larger in terms of the measurable effect. This A VS. B variants is actually so much cleanly defined when you go to the shorter branches because for one genetic variant to affect Alzheimer's that's a very long path. That basically means that in the context of millions of these six million values that every one of us carries, that one single nucleotide has a detectable effect all the way to the end? I mean, it's just mind boggling that that's even possible, but indeed crazy. But indeed there are such </s><s>[INST] effects. So the hope is or the most scientifically speaking, the most effective place where to detect the alteration that results in diseases earlier on in the pipeline as early as possible. [/INST] It's a trade off if you go very early on in the pipeline. Now each of these epic genomic alterations. For example, this enhancer control region is active maybe 50%, which is a dramatic effect. Now you can ask, well, how much does changing one regulatory region in the genome in one cell type changed disease? Well, that path is now long. So if you instead look at expression, the path between genetic variation in the expression of one gene goes through many enhancer regions and therefore it's a subtler effect at the gene level. But then now you're closure because One gene is acting, you know, in the context of only 20,000 other genes As opposed to one enhancer acting in the context of two million other enhancers. So you basically now have genetic mp genomic, the circuit train transcript atomic the gene expression level. And then cellular. Where you can basically say, I can measure various properties of those cells. What is the calcium influx rate when I have the genetic variation. What is the synaptic density, What is the electric impulse conductivity? And so and so forth. So you can measure things along these path to disease. And you can also measure end of fema types. You can basically measure, you know, um your brain activity. You can do imaging in the brain. You can basically measure, I don't know the heart rate, the polls, the lipids, the amount of blood he created and so and so forth. And then through all of that you can basically get at the path to causality, the path to disease. </s>
<s>[INST] And it took a really long time. It [/INST] took two billion </s><s>[INST] years and it [/INST] hasn't happened since to the best of our knowledge. So it looks as if it's genuinely difficult and if you think about it then from from from just an informational perspective you think bacteria have got they structure their information differently. So a bacterial cell has a small genome, you might have 4000 genes in it. But a single e coli cell has access to about 30,000 genes potentially it's got a kind of meta genome where other E coli out there have got different gene sets and they can switch them around between themselves and so you can generate a huge amount of variation. And you know they've got more of an e coli meta genome is larger than the human genome. We have 20,000 genes or something. So and they've had four billion years of evolution to work out what can I do and what can't I do with this meta genome? And the answer is you're stuck, you're still bacteria. So they have explored genetic sequence space far more thoroughly than new characters ever did because they've had twice as long at least. And they've they've they've got much larger populations and they never they never got around this problem. So why can't they? It seems as if you can't solve it with information alone. So what's the what's what's the problem? The problem is structure if if if sells if the very first cells needed an electrical charge on their membrane to grow and in bacteria it's this it's the outer membrane that surrounds the cell which is electrically charged, you try and scale that up and you've got a fundamental design problem. Not an engineering problem. And there are examples of it and what we see in all these cases is what's known as extreme polyp Lloyd which is to say they have tens of thousands of copies of their complete genome which is energetically hugely expensive. And you end up with a large bacteria with no further development. What you need is to incorporate these electrically charged power packed units inside with their control units intact and for them not to conflict so much with the host cell that it all goes wrong. Perhaps it goes wrong more often than not. And then you change the topology of the cell. Now you don't necessarily have any more DNA than a giant bacterium with extreme polyp Lloyd. But what you've got is an asymmetry, you now have a giant nuclear genome. We're surrounded by lots of subsidiary energetic genomes that do do all the the the control units that are doing all the all the all the all the all the control of energy generation. </s><s>[INST] Could this have been done gradually or does it have to be done? The power pack has to be all intact and ready to go. And [/INST] I mean it's a kind of step change in the possibilities of evolution. But it doesn't happen overnight. It's going to still require multiple multiple generations. So it could take you know it could take millions of years. It could take shorter times. There's another thing I would like to put the number of steps and try and work out what's required at each step. And we we are trying to do that with sex for example. You can't have a very large genome unless you have sex at that point. So what are the changes to go from bacterial recombination to eukaryotic recombination? What what do you need to do? Why do we go from passing around bits of D. N. A. As if it's loose change to fusing cells together, lining up the chromosomes, recombining across the chromosomes and then going through two rounds of cell division to produce your your gametes, all your carrots do it that way. So again, you know why switch what are the drivers here? So there's a lot of there's a lot of times a lot of evolution. But as soon as you've got cells living inside another cell, what you've got is a new design. You've got new potential that you didn't have before. </s><s>[INST] So the cell living inside another cell that design allows for better storage of information, better use of energy, more delegation. Like a hierarchical control of the whole thing. And then and then somehow that leads to ability to have multi cell organisms. [/INST] I'm not sure that you have hierarchical control necessarily. But you you've got a system where you can you can have a much larger information storage depot in the nucleus. You can have a much larger genome and that allows multicellular charity. Yes because it allows you </s><s>[INST] it's [/INST] A it's a funny thing you to have to have an animal where I have you know 70% of my genes switched on in my brain and a different 50% switched on in my liver or something? You've got to have all those genes in the egg cell at the very beginning? And you've got to have a program of development which says, okay you guys switch off those genes and switch on those genes and you guys you do that. But all the genes are there at the beginning. That means you got to have a lot of genes in one cell and you've got to be able to maintain them. And the problem with bacteria is they don't get close to having enough jeans in one cell. So they would, if you were to try and make multicellular organism from bacteria, you bring different types of bacteria together and hope they'll cooperate. And the reality is they don't </s><s>[INST] that's really, really tough to do coming in. We [/INST] know they don't because there doesn't exist. </s>
<s>[INST] Well, it's a foreign case study, right? But okay, so that's really well put. So like gold was sticky. Once it was accepted, the network effects, the winner take all took over. And here's a fundamentally different kind of like analog versus digital is a leap in technologies. And you're suggesting that there may not be, there's unlikely to be other leaps of that [/INST] kind into a whole nother kind of space of technologies. I would argue that Bitcoin, it's kind of like the ideological synthesis of gold, taking the monetary properties of gold and combining them with the internet itself. And in doing so, it has essentially perfected the properties of money, right? You can't get more divisible, durable, recognizable, portable, or scarce than Bitcoin. So Satoshi has kind of... He left a no design space for a superior technology to intercede and out-compete Bitcoin at this point, now that it's established liquidity in the network. </s><s>[INST] Far superior technology, right? [/INST] Yeah, but it's a combination of the tech itself and the social layer. In the social layer. </s><s>[INST] That is coalesced to it. In the social layer. That is coalesced to it. You can't separate those two out. They're all connected and then the political as well. But the portability for example, that's the... Another way to phrase is the... What What is it, the scaling? So the number of transactions, that's the limitation for Bitcoin that many argues a feature, many argues a bug. You have a bunch of cryptocurrency technologies that are able to achieve much higher, much faster frequency of transactions, much more transactions, you know, all that kind of stuff. What are your thoughts on that? You know, the low level of transactions that's possible with Bitcoin. Do you think that's a feature? [/INST] Do you think that's a bug? That's right. Necessary for security, actually. And even these other crypto assets that settle more quickly, they settle with less assurance of finality. So Nick Carter has a great piece on this actually called, it's the settlement assurance is stupid. It's really good. Where the gist of it is that there is more work being done in each block of Bitcoin, that it is less vulnerable to reversion. So it's giving you higher degrees of assurance that your settlement or your trade has occurred with finality, whereas other blockchains are much more vulnerable. And again, with Bitcoin, the evolutionary path of money with gold is that it was first used as a collectible. It then became used as a store value. After it had stored enough value, it began to be used as a medium of exchange. And then finally, when it was used widely enough as a medium of exchange, it becomes a unit of account. We actually start to think in the money. Bitcoin's following a similar path. So started out as kind of a collectible. Today, I would argue it's a store value, one of the most effective store value we've ever seen. So that evolutionary path that Bitcoin's following is similar to gold. First, a collectible, today is store value. To be an effective store value, It has to optimize for supply cap. That has to be the first, and this is all Bitcoin really needs to do to be successful, by the way. Exactly what it's been doing for 12 years, virtually flawlessly, which is keep creating a block every 10 minutes and keep enforcing a supply cap of 21 million. As long as those two things hold, it is sound money, the ultimate sound money, the most inflation resistant money there's ever been. It's actually completely immune. It's taken unexpected inflation to 0%. We know with perfect certainty what Bitcoin supply will ever be. For it to be used more broadly as a medium of exchange, it can't make trade-offs at the base layer to increase its portability, for instance, even though portability is maybe kind of a misnomer because Bitcoin has extremely high portability, just doesn't have extremely high transaction throughput. So we could say you can move it pretty quickly anywhere in the world as long as you're willing to bid up for the block space, but you can't satisfy all the world's economic volume. You can't do 300 million transactions per second like you can on a centralized database like Visa. But Bitcoin needs to be this, it has to be a store value first before it can be a medium of exchange. So it has to protect the supply cap first before making any trade-offs for that. And I would argue that that's why Bitcoin is so rigid, is that it's optimized for survivability and optimized for that supply cap, and it's pushing experimentation and other features that would increase its transaction throughput to higher layers. So I think Lightning Network is something that's very interesting. It's still early, but there's a lot of throughput already being used on the Lightning Network. And it makes some slight trade-offs in terms of the trust minimization of Bitcoin. You end up trusting these smart contracts instead to move the Bitcoin, but you pick up nearly unlimited transaction throughput. So that's how biology evolves, that's how the internet evolved, it evolves in layers. So I think Bitcoin, you can sort of conceive of it as the latest layer to the internet, and it's one that preserves this store value property better than any asset we've ever </s><s>[INST] had. Let me ask sort of a critical question of if you're wrong about your statements about Bitcoin, you find out years from now that you were wrong, what would that look like? What would be the things that make you realize you were wrong, likely ideas or crazy out there ideas? [/INST] Do you think about this kind of stuff all the time? </s>
<s>[INST] Yeah. What's, what are some secrets, words of wisdom you can say for how to be successful online and all the, everything you've learned. You're kind of like the, the Mr. Beast of comedy, just innovating constantly in terms of how to promote stuff, in terms of how to present stuff across the different social media and across YouTube, podcasts, all that stuff. [/INST] I think the number one thing is, don't be afraid to suck. No one sees the shit that sucks. Doesn't get views. You just gets forgotten. Yeah, gets forgotten. The good stuff they remember, and then that's all they bring up. The stuff that sucks just goes away, and they're like, oh yeah, did you do that? I don't even think I saw that. Fuck it, who cares? Yeah. You know, it's like, I watched, one of my favorite stories about this is a guy named Sean Patton. I was explaining Instagram stories to him and Ari and Mark Norman. And I was explaining that you can set now sell tickets on Instagram stories. It was a back when they swiped up instead of tap the button to swipe up. And they didn't understand it. And I said, let me show you. And I put up tickets for sale. And I said, you know, hey, guys, swipe up. And then I just showed him in 10 minutes. Look, there's not many people swiped up. There's 145 people. It's a lot of people to buy tickets for a fucking comedy club. And they were like, whoa. And they're like, what do you do stories about? I go, fucking anything. Who gives a shit? Just anything. And some things work, some things don't. And I watched Sean Patton, shout out to Sean Patton, try for about 15 minutes to do an Instagram story about his cup of tea. He was making cup of tea and he was making and he kept going, hey, okay, hold on, hold on. I was filming him from the couch. I was filming all these. The whole thing. Yeah. I filmed every single one of my like 15 different stories of him trying to do that. I had 145,000 views on each story. He never posted it. He never posted it. And I was like, I was like, man, if he had just posted that one, he never posted anything in his stories. That one, 145, 5,000 people would have gone to his story to see that cup of tea being made and see which one he finally went with. And so sometimes I think the biggest mistake you can make is just not doing it. Just do it. Just post it. Turn the camera on. The idea will show up. And that's the number one thing. Just turn the camera on and it'll come up. You'll figure it out. </s><s>[INST] Do you do multiple takes or no? [/INST] Maybe I do three like and I'm talking even like in the dance video I did where I did the hip-hop dance. I did two takes on that With what I had the marching band come to my house. I did two takes on that Once you start doing more takes you lose the fun of it. I think and and then the fun ones I mean my favorite one I've ever done without a doubt my favorite promo I've ever done is I needed they added a second show in some city and, uh, and, and they added a second show like Friday and Saturday and our third show. And I said, I, they just told me, I was like, fuck, I'm leaving like tomorrow. I need to sell tickets. So I said, real quick, girls meet me outside and lands like girls are doing homework. I go to take five seconds. I put on a speedo. I got the American flag. I gave Isla the hose. I gave land the leaf blower and I gave Georgia the drone. And I just had Georgia drone it back to reveal the leaf blower and the mist you were seeing was coming from Isla and Leanne. I'm going to speed it with American flag. I have Bob Seager playing rambling, gremlin man. And that night, Larry, the cable guy texted me and he goes, this is fucking genius. And I was like, it was just, and it was just like, yo, just let's just shoot something. Who gives a fuck? like just shoot something just just just say something and and and put a little just do a little movement into it and and those are my back and that was I used to be I watched a bunch of my promo clips back from back in the day I used to be really good now it's like I'm promoting so fucking many things I'm just like I'm almost like I'm exhausted my promotions yeah because you know the the wall can dry up in terms of ideas Yeah. And it's like, how many times am I going to show a picture of my ass? My ass sells really good. Whatever my ass is on Instagram, fucking million views guaranteed. A million views. Your ass. And it's an active post. Like people are like, I did the best one I did the other day was where I superimposed my ass on my front and it just looked beautiful. No views. Oh, so you got reported. Oh, I see. It looked like a front vagina. </s><s>[INST] Oh, is that what it was? [/INST] Yeah, I think so, but like, but yeah, my ass, like I'm at a place right now where I am promoting. I'll be promoting this movie. I'll be promoting this movie until it goes to a streamer. I'll be promoting it shamelessly. I'm proud of it. I had a great time shooting it. It's in theaters. It'll be on video on demand. It'll be on a streamer. I'm sure I don't know, but I'm sure I'm promoting fully loaded my summer festival with 19 different comics. I'm promoting the tops off world tour That starts again this fall. I'm promoting my cruise the fully loaded cruise. I'm promoting red rocks. I'm promoting so many things That today was the very first time in my career Where I said in January, I'm gonna take a break. I'm gonna take a break and go like Hey man, let's get your resting heart rate down. Let's get some sleep. Let's maybe take off like three months from drinking. Let's just really slow it down and also not think, when you're thinking in promo all the time, it can be a little exhausting. I mean, you think it's exhausting to look at my feet. It's exhausting to be my feet. I'm my feet. </s>
<s>[INST] mean? Like a definitive, [/INST] well they took it away and gave me a bag of weed instead and I cried my eyes out for </s><s>[INST] days and days and days, you know, [/INST] and then you know as a, and my dad said we're going to exchange it back in a little bit. So you keep the little gun, you know, the one that you shoot the ducks with. So I'm like, okay, I'm keeping the gun. So sometimes it's going to come back. But if they exchanged the gun as well for some sugar or something, I was so pissed. I was like, I didn't want to eat for days after that. I'm like, I don't want your food keeping my Nintendo. Um, that was extremely traumatic. Um, but you know, I was happy that that was my only traumatic experience. You know, my dad had to actually go to trial novel with a bunch of 20 year old. He was 20 when he went to Chernobyl and that was right after the explosion. No one knew anything. The whole crew, he went with all of them are dead now. I think there was this one guy still, wow, that was still alive for this last few years. I think he died a few years ago now. My dad somehow luckily got back earlier than everyone else, but just the fact that that was the, and I was always like, well how did they send you? I was only, I was just born, you know, you had a newborn talk about paternity leave. They're like, but that's who they took because they didn't know whether you would be able to have kids when you come back. So they took the ones with kim so him with some guys want to And I just think, you know me. And when I was 20, I was so sheltered from any problems would serve in life. And then my dad um His 21st birthday at the reactor, You work three hours a day, you sleep the rest. And yeah, so I played with a lot of toys from Chernobyl. What are your </s><s>[INST] memories of Chernobyl in general? Like bigger context? You know, because of that HBO show is the world's attention turned to it once again. Like what are your thoughts about your novel? The Russia screw that one up. Like, you know, there's probably a lot of lessons about our modern times with data about coronavirus and all that kind of stuff. It seems like there's a lot of misinformation, there's a lot of people kind of trying to hide whether they screwed something up or not. As it's very understandable. It's very human, very wrong probably. But obviously Russia was probably trying to hide that. They screwed things up. Like what are your thoughts about that time? Personal and general. [/INST] I mean, I was born when the explosion happened. So actually a few months after. So of course, I don't remember anything apart from the fact that my dad would bring me tiny toys plus like plastic things that would just go crazy haywire when you put the bigger thanks to it. My mom was like just nuclear about that. Um it was like what do you bring age? I'll do that. She was a nuclear, very nice, well done was uh, but yeah, but the tv show was just phenomenal. Yeah, definitely. First of all, it's an incredible how, um, that was made, not by the Russians but someone else, but capturing so well everything about the, in, about, about our country. Um, it felt a lot more genuine than most of the movies and tv shows that are made now in Russia, just so much more genuine. And most of my friends in Russia were just complete all about the, with the show, but I think that good of a job, they did a phenomenal, but the apartments, </s><s>[INST] there's something just [/INST] design. I mean Russians can't do that, you know, but you, you, you see everything and it's like, wow, that's exactly how it was. </s><s>[INST] So I don't know that show, I don't know what to think about that because it's british accents, british actors of a person, I forgot who created the show. I'm not, but I remember reading about him and he's not, he doesn't even feel like, like there's no Russia in his history. [/INST] No, he did like super bad or some like, or like, uh, I don't know whatever that thing about the bachelor party in Vegas, uh, number four and five or something, we're the ones that he </s><s>[INST] worked, but he, it made me feel really sad for some reason that if a person obviously a genius could go in and just study and just be uh extreme attention to detail that can do a good job. It made me think like why don't other people do a good job with this? Like about Russia? Like there's so little about Russia, there's so few good films about the Russian side of World War Two. Uh I mean there's so much interesting evil and not and beautiful Moments in the history of the 20th century in Russia. That feels like there's not many good films on from the Russians. You would expect something from the Russians. [/INST] Well they keep making this propaganda movies now unfortunately, trainable was such a perfect tv show I think capturing really well, it's not about like given the set design, which was phenomenal, but um just capturing all the problems that exist now with the country and like um focusing on the right things. Like if you build the whole country on a lie, that's what's going to happen and that's just this very a simple kind of thing. </s><s>[INST] Yeah. And did you have your dad talked about it to you like his thoughts on the experience. [/INST] He never talks. It's this kind of Russian man that just my husband was american and he asked him a few times like you know, Igor, how did you, but why did you say yes or like why did you decide to go? You could have said no, not go to your novel, why would like a person to Yeah, that's what you do. You cannot say no. It's just, it's like a Russian way. It's the Russian don't talk that much there. Downsides and upsides for that. </s>
<s>[INST] Wait, what? Oh, interesting. [/INST] So no ambiguities, it's logically consistent. </s><s>[INST] Yeah, Lojban. [/INST] But can you still have fun in it? You can get very- Can you write poetry or what? There's people who actually write poetry in Lojban. I'm gonna switch to that and start tweeting in it. Yeah, there you go. So there's a lot there and they're just fun to study and think about. And, unfortunately, if you go down that rabbit hole, you'll spend way, way too much time and there's diminishing returns. Now, the second question you asked was one on theoretical computer science to I guess engineering. Philosophy, no, no, no. </s><s>[INST] Can you write poetry or what? I'm gonna switch to that and start tweeting and philosophy. No, no, no, no. First step, you said, humans and computers. So theoretical computer science is theory of the computer And philosophy is the theory of the human. And then we can dissect different stuff about the computer, but in terms of these two worlds of the theory of the human, which is philosophy and the theory of the computer, which is computer science, what do you think is the difference? As we try to bridge that gap, as you mentioned, what's going to be the biggest challenge? Like can we formalize love? Can we formalize music, art, poetry, all that kind of stuff, [/INST] or is that a human nonsense that we need to get rid of? No, I don't think it's human nonsense at all. I mean, there's even attempts to create algorithmically generated music. And the question is, is love just strictly a chemical phenomena? Is there something like metaphysical about it or transcendent of some sort of formal system? I mean, computer science is just saying, hey, we have this notion of computing. We have this brain that we've constructed, this formal system that we've built. And given that we have it, what can we do with it? And so some people worry about the roots of the tree of knowledge. The great Yigdrasil of computer science, they worry about the roots of say, how far can we grow them and let's keep adding these new models of computation. And other people worry about the trunk of the tree, and some people worry about the leaves of the tree. And the more advanced the field gets the closer and closer it gets to the people who constructed it. Us. We have better image processing. have better ways of handling speech-to-texts. And we have better ways of computers understanding the intent of what a human being is saying. And then the question is, well, how will a computer understand love or poetry or music? Well, it will understand it the same way we understand it. You have to get a computer to grow up to a point where it can learn the way we learn, or as close to it as possible, then you just expose it to the things that we were exposed with. And then at some point, the computer will start creating things. So the question is, well, Well, how do you quantify creativity? And I have no clue about that. </s><s>[INST] But it's a- You make it into an NFT and see how much it excels for. That's one way. Yeah. But basically, yeah, there's so much of it is subjective. And that's a fascinating whole area of, that I'm fascinated with is human-robot interaction is, how do we create compelling experiences that are subjectively compelling? Whether it's art or just two humans talking or two humans interacting in some kind of way to maximize the richness of the subjective experience. And I think that could be an optimization problem that could be solved. We're solving it all the time. Human civilization is constantly trying to, we're constantly trying to impress each other. When we're younger, trying to get laid, whatever, fall in love, impress your boss at work by all the awesome stuff you do. I mean, we're trying to optimize that problem. [/INST] That's purely, for the most part, it's subjective. Yeah, right, right, right. Did you ever watch Blade Runner 2049? Yes. Yeah, did you remember the whole relationship between Joy and Kay? Did she really love him, the hologram or not? </s><s>[INST] Was it fake love or real love? Yes, fake it till you make it is my view on love. No comment from Charles. So let's go to the difference between theoretical computer science and software engineering. Or I don't know if you draw a distinction, but if we look into this computer world now, is there a difference between theory, things you can say formally, and the pragmatic implementation of that theory into actual systems that people use. Which I guess we'll call software engineering. [/INST] So, the engineer they're obsessed with the domain of what do you want to accomplish and who are you accomplishing it for? So they live in the world of people if they're good engineers. And they say okay, what's the experience? How are we going to use this? Why are we going to do this? What's the commercial application? What's the non-commercial application? and you collect all these business requirements. And once you've done all of that, the better job you do, the more self-evident it is of how do we apply the toys and tools of computer science and other such things to actually resolve that. And the point of theoretical computer science from the software engineering domain is it can tell you kind of where your guardrails are. It won't make perfect programs and there's no such thing as that, but rather it can give you a good notion and sense that your program has some desirable properties. Like maybe you can prove that it can terminate if you're dealing with total programs or maybe you can prove you'll never have a buffer overflow or you'll demote divide by zero somewhere or something like that. Some event won't occur that'll cause a catastrophic failure in your system. But there's always this combinatorial explosion between what you can test and think about and what you can actually code. So the stuff on the left-hand side lives in a different cardinality, a different universe. There's something significantly larger there. And the tools on the right-hand side, we have property-based testing and these SAT solvers. We have all this great stuff here in formal methods land and computer science theory land, but there's only a small subset of things that they actually give you good answers about. So the balance of the two things is basically saying, well, what do you care about and what are you okay throwing away? That's the art of engineering and building these types of things. So, you know, cryptocurrencies, we deal with these complex distributed systems that have cryptography and game theory and Byzantine actors. So the balance there is saying, okay, what can't fail in that system? And that's the kind of stuff that you want to apply as heavy a tool set as you can, because when that stuff fails, you either have the loss of billions of dollars, privacy, or potentially even life, depending on how these systems get adopted. But then other things, you know, what can fail? Is it okay if the block doesn't get made every now and then? Is it okay if your latency goes up or your network suddenly becomes as synchronous and you disconnect from it and you have to restart the computer or something like that? That's probably okay. It's an inconvenience and burden to the user. And if you actually try to chase that tail, you'll end up spending 10 years chasing phantoms and ghosts. And meanwhile, the whole world moves on. So it's really figuring out those balance of the two. And what's really beautiful is that the formal methods tools have gotten so much better over the last 20 years in particular, mostly because of incredibly high investments from Microsoft and Google and big universities, because these guys are building these gargantuan systems. If you look at the Googleplex or what Amazon has or others, and they have so much value, so many users, so many things going on, and no person can keep that in their head. And so you're talking about systems may have 10 million lines of code, 15 million lines of code, millions of nodes connecting, faulty processes happening all the time, hackers breaking in on a regular basis. So when you're trying to model all of that, trying to ask yourself, what formal guarantees and properties can I get to simplify this system as much as possible? So instead of the applications of formal methods slowing you down, in many cases, it actually massively reduces your debugging time and your ability to find where errors occur. In some cases, you can't find where errors occur inside these massive concurrent systems. And you say, well, where are cryptocurrencies going? We're talking about just the same thing. But we're talking about a much more hostile operating environment where instead of it running in a pristine data center in California somewhere, it's running on your cell phone. It's running on your mom's phone. It's running your dad's phone. It's running on some computer in Mongolia that may have good internet on Tuesday but not any other day. So when you live in that kind of environment, you really do need to think carefully about a whole new class of protocols. And then you need to think carefully about a whole new class of tools and techniques to test the reliability of those systems. And you need to separate the world and say, what is high assurance and cannot fail? Because if it fails, people lose money. And what is low assurance? And it's okay if that falls apart. The other thing I'll mention is there are perverse financial incentives in our industry. Because the reality is when something blows up, the people who built those things that blow up usually get paid upfront. So what they're focusing on is time to market, speed to market and getting tokens out and getting them liquid. And then people come in, they buy it. But if there's an innocent bug in some DeFi protocol, it'll probably be discovered six months later or something like that. </s>
<s>[INST] And that's a kind of immortality is ideas that you've invented living on long after you in the minds of others and humans are ultimately not, are like meat vehicles that carry ideas for a brief for just a few years may not be the important thing. It might be the ideas that we carry with us and invent new ones. Like we get a bunch of baby ideas in our head, We borrow them from others and then maybe we invent a new one and then you one might have a life of its own. And it's fun. It's fun to think about that idea of living from many centuries to come unless we destroy ourselves, but maybe a, I will borrow it and we'll remember Poe as like that one human that, that that helped us out before we of course killed him and the rest of human civilization On that note. Well this is a huge honor. You're one of the great educators I've ever gotten a chance to interact with. So it's it's truly an honor that you would talk with me today. It means especially a lot that you would travel out to Austin to talk to me. It really means a lot. So thank you so much. Keep on inspiring. And I'm one of your many, many students. Thank you so much for talking today. [/INST] Thank you. Thank you. It's actually a real honor for me to talk to you and to get this chance to have this really intellectual conversation through all of these topics. Thanks bro, </s><s>[INST] Thanks for listening to this conversation with pasta and lo and thank you to Jordan's harbored the show on it. Better help eight sleep and element check them out in the description to support this podcast. And now let me leave you with some words from Isaac Newton. I can calculate the motion of heavenly bodies but not the madness of people. Thank you for listening. I hope to see you next time [/INST] </s>
<s>[INST] When did you know you have this? Oh right here, [/INST] I I actually panicked um right about here </s><s>[INST] was maybe his head to come out [/INST] my hand, I tore the muscle in my palm because I was pulling so hard that I'm like he may not that Yeah, because he is my hand just going to give out beforehand and then he were right on this edge, right? So like if we roll a little bit outside and I still don't have it like that raft could stop it and then I felt him tapping and </s><s>[INST] oh that he is his heartbroken, I felt surprised there it is [/INST] the relief olympic olympic final and he knew he knew he lost an olympic medal right there because he already knew that the japanese guy was gonna be his bronze that he never beats </s><s>[INST] see the But also he probably in his head, I was confident that he would be in the final, correct and so like this, he almost is surprised. Yeah, it's not supposed to happen this way [/INST] and it's the second time it's happened. Mhm </s><s>[INST] and that's how you became an olympic medalist man, that must be a great feeling, that must be a great feeling right here. Just like all the years of injuries, all of it as as fans that watch this too. It's like holy shit, he actually did it. [/INST] It's a packed stadium to not one empty seat </s><s>[INST] man. So uh what were you thinking here? Just focus on the next match. Yeah, [/INST] it took me maybe like a minute or so to like decompress and then like get back to my normal state for the final. </s><s>[INST] So the final is against the the Russian here. What can you say about your mindset? You're saying the exact same thing thing Travis stevens olympic champion. [/INST] I will not be denied because I had felt like in London and throughout the years I felt like I kept getting robbed so I made sure and my mantra had that little bit at the end to reassure myself that like they are not going to control the outcome of today, I'm going to control the outcome. </s><s>[INST] What did you know about the Russian [/INST] everything. Um and I I honestly, I thought I had won the olympics right now and I still do think that today just like mentally when you think about it that I've won like yeah, he threw me but it was like a one in a million chance that that worked for him. </s><s>[INST] All right, come on. So, so it's not like you feel lucky to be in the final. It's like [/INST] you can't remember, I'm I'm anticipating the goal like I'm past that </s><s>[INST] like their confidence in the way you're moving in the way you're [/INST] Yeah, like I have his sleeve, he's not breaking it like still walking him down, still going forward like um I knew exactly how I was going to beat him and I developed a plan because when I was getting ready for Rio, we brought in a lot of the top Japanese players that weren't invited to the camp for the national team to boston. So I had four people, three of them were on the national team, one of them had one The universities in Japan all at 81 kg. I only got thrown once during camp for a month. Like I was I was ready. Mhm. I just fucking slipped. </s><s>[INST] Where does it happen? [/INST] Right when he threw me? So if you let this play out really quick, there's a point right here where I'm going to come around his back and I'm kind of gonna just Yokosuka to me, which means like a lateral drop and I'm going to bring him down to the floor which isn't a throw right here. It's more of like a takedown right? I'm trying to get him to the ground because I want to burn him. He doesn't do any waza So I'm just gonna keep burning him and you can see that like I get really close here. He just went a little too far to his side during this exchange. And like he's running oh my God. Mhm. </s><s>[INST] He's very wiry for an 81 KK player. Yeah there's not much like muscle on him [/INST] but he uses his length and his leverage very well. And you can see like I'm really burning the clock here, like I'm owning these exchanges more than I'm owning the Tachi waza ones, the ones in your feet. </s><s>[INST] So you weren't trying to necessarily submit him here or are like really hard or like um pin um You're trying to break him a bit. [/INST] I'm doing both. I'm being overly physical. Um And a lot of the B. J. J. People who are watching this like they're like oh well I would have done this, I would have done that. You've got to think like if that referee who's repping the judo side of it, looks at it for a couple of seconds and like uh he's not really moving, they'll stop it. </s><s>[INST] Yeah so you're like you understand judo, yeah what's called Nowata gone work like well you because you're really showing it to the ref [/INST] yes, you have to show movement and progression. I heard the forehead. Like see I threw that hand in. They're kind of hard ripping it across his face just because </s><s>[INST] the I gotta I gotta tell you there's a calm. Well no he does look a little a little broken but the Russians have like this calmness [/INST] they're pretty good at. Well don't forget they've competed like this for a long time. Yeah, it's all he knows and this is where I lose it, see how my knee hit the ground. My knee wasn't supposed to touch the ground, I was supposed to sit to my hip to bring him down. Something happened where my knee touched and it didn't happen in the first one. It just happened there. It's like that we never should have been in that predicament. Yeah. And that's that's one of the things where when you're looking at, you know, sports for anybody who's trying to improve, you have to, when you're, when you're trying to improve, you've really got to ignore the ends of the spectrum, right? The the autopsies and they got lucky and you only focus on the middle. Like the technique I was doing was perfectly sound. It just happened that the one upsy happened on the stage, it shouldn't have happened on and there's no, there's no amount of drilling that will ever like prevent that from happening. </s>
<s>[INST] You founded the payment system Braintree in 2007 That acquired Venmo in 2012 in that in that same year was acquired by paypal, which is now ebay, can you tell me the story of the vision and the challenge of building an online payment system and just building a large, successful business in general, [/INST] I discovered payments by accident As I was when I was 21. I I just returned from Ecuador living in extreme poverty for two years and I came back to the U. S. And I was shocked by the opulence and of the United States and I just thought this is, I couldn't believe it and I decided I wanted to try to spend my life helping others. Like that was the that was the life objective that I thought was worthwhile to pursue versus making money and whatever the case may be for its own right. And so I decided that moment that I was going to try to make Enough money by the age of 32, never have to work again. And then with some abundance of money, I could then choose to do things that might be beneficial to others but may not meet the criteria of being a standalone business. And so in that process I started a few companies, had some small successes, had some failures. In one of the endeavors, I was up to my eyeballs in debt. Things were not going well and I needed a part time job to pay my bills. And so I one day I saw in the paper in Utah where I was living the 50 richest people in Utah and I e mailed each one of the assistants and said, you know, I'm young, I'm resourceful, I'll do anything. I just want to, I'm entrepreneurial. I try to get a job that would be flexible and no one responded and then I interviewed at a few dozen places, nobody would even give the time of day like you wouldn't want to take me seriously. And so finally I it was a monster dot com that I saw this job posting for credit card sales, door to door commissioner, I did not know this story, This is great. I love the head drop. That's exactly right. So it was </s><s>[INST] the low points to which we go and [/INST] like so I I responded and you know the person made an attempt at suggesting that they had some kind of standards that they would consider hiring, but it's kind of like if you could fog a mirror, Like come and do this because 100% Commission. And so I started walking up and down the street in my community selling credit card processing. And so what you learn immediately and doing that is if you, you walk into a business first of all, the business owner is typically there and you walk in the door and they can tell by how your address or how you walk whatever their pattern recognition is and they just hate you immediately. It's like stop wasting my time. I really am trying to get stuff done. I don't want to do a sales pitch. So you have to overcome the initial get out and then once you engage when you say there were credit card processing, the person's like I already hate you because I have been taking advantage of dozens of times because you all are weasels. And so I had to figure out an algorithm to get past all those different conditions because I'm still working on my other startup for the majority of my time doing this part time. And so I figured out that the industry really was built on people uh on the seat basically people promising things that were not reality. And so I walk into a business and say look I will give you $100. I put $100 bill and say I'll give you $100 for three minutes of your time. If you don't say yes to what I'm saying, I'll give you $100. And then he usually crack a smile and say ok what you got for me son. And so I sit down, I just opened my book and I'd say here's the credit card industry, here's how it works. Here are the players, here's what they do here is how they deceive you. Here's what I am. I'm no different than anyone else. It's like you're going to process your credit card, you get the money in the account, you're just going to get a clean statement, you can have someone who answers the call when someone asked and you know just like the basic like you're okay and people started saying yes and then of course I went to next business and be like, you know joe and susie and whoever said yes to and so I built the social proof structure and I became the number one sales person out of 400 people nationwide doing this and I have worked half time still doing so their startup and </s><s>[INST] that's a brilliant strategy by the way, it's very well, very well strategized and executed. [/INST] He did it for nine months. And at the time my customer base was making was generating around I think was sick, if I remember correctly, $62,500 a month where the overall revenues, I thought, Wow, that's amazing. If I Built that as my own company, I would just make $62,000 a month of income passively with these merchants processing credit cards set up. And so uh, that's when I thought I'm going to create a company. And so then I started Braintree and the idea was the online world was broken because Paypal had had been acquired by Ebay around I think 19 2099 or 2000. And Ebay had not innovative much with Paypal. So it basically sat still for seven years as the software world moved along and then authorize dot net was also accompanied with relatively stagnant. So you basically had software engineers who wanted modern payment tools, but there were none available for them. And so they just dealt with software they didn't like. And so with Braintree, I thought the entry point is to build software that engineers will love. And if we can find the entry point via software, make it easy and beautiful and just a magical experience and then provide customer service on top of that. It was easy. That would be great. What was really going after for that was it was Paypal. They were the only company and payments making money because they, because they had the relationship with the bay early on, People created a Paypal account. They fund their account with their checking account versus their credit cards. And then when they use Paypal to pay a merchant, Paypal, how the cost of payment of zero versus if you have coming from a credit card, you have to pay the bank the fees. So Paypal's margins were 3% on a transaction versus a typical payments company, which may be a nickel or a penny or a dime or something like that. And so I, a new Paypal really was the model to replicate. But a bunch of companies had tried to do that. They tried to come in and build a two sided marketplace. So get consumers to fund the checking account, the merchants to accept it. But they all failed because building a two sided marketplaces very hard at the same time. So my plan was, I'm going to build a company and get the best merchants in the whole world to use our service Then in year five, I'm going to have, I'm going to acquire a consumer payments company and I'm going to bring the two together and </s>
<s>[INST] has crashed, right? By the way, yeah, there's a plot that shows on the x axis percent white, and on the y axis of the different companies. And the tech companies are basically below 50% white, and all the different media tech journalism companies are all way above, you know, 70 80 90 90 plus percent white, and [/INST] hypocrisy, ladies and gentlemen, I mean, again, I'm not the kind of person who thinks white is an insult. But these guys are. And they are the wokest whites on the planet, right? It's like </s><s>[INST] ridiculous, right? I you know, it's like, anyone, anyone who's homophobic, anyone who's that it feels like it's a personal thing that they're struggling with. Maybe the journalists are [/INST] actually the ones who are racist. Well, actually, you know, it's funny, you say that because there's this guy, am Rosenthal, okay. And you know, on his gravestone was quote, we kept the he kept the paper straight, right? And actually, he essentially went and this is managing editor of the New York Times for almost, you know, from 69 to 77, executive editor from </s><s>[INST] 77 86. And it was a history. Lord. Yeah, it was a history. [/INST] Lord history of basically keeping, you know, gay reporters out. So essentially, the way I think about it is, New York Post reported that, just just just to talk about this for a second, because it's so insane. All right. New York Post reported and I've got some of this in the book. Okay, but </s><s>[INST] a a broad Rosenthal, managing editor of the New York Times from 1969 to 1977, executive editor from 1997 to 1986. His gravestone reads he kept the paper straight. [/INST] And then here's G here on this, he kept the paper straight. As it happens, Rosenthal's in tourist homophobe, he made it a specific policy to paper not to use term gay, he denied a plum job to a gay man for being gay, he minimized AIDS crisis. So, like, you know, the thing about this is, this is not like a one off thing. Okay. The New York Times literally won a Pulitzer for choking out the Ukrainians for helping starve 5 million Ukrainians to death and now has reinvented themselves as like a cheerleader to stand with Ukraine, right? They were for, you know, a Rosenthal's homophobia before they were against it, right? They were like, if you look saw the link, I just paste it in. Okay. During BLM, you know, it's credibly reported that I haven't seen this refuted, the family that owns the New York Times were slaveholders. Somehow that stayed out of 1619 and BLM coverage, right? Say we're literally getting the profits from slavery to help bootstrap, you know, the what was the times or, you know, went into it. They actually did this article on like the compound interest of slaveholders in Haiti and how much they owed people, right? If you apply that to how much money they made off of slaves. I mean, can anyone name one of Salzburg or slaves? Like, can we humanize that? Put a face on that show exactly, you know, who who lost such that he may win, right? And so you stack this up and it's like, you know, for the Iraq War before they were against it. And it's like, yeah, sure, Bush, you know, did a lot of bad stuff there. But they also reported a lot of negative, you know, not negative coverage, like false coverage, right about WMD is like, you know, the whole truth, military. And so it's like this amazing thing where if some of the most evil people in history are the historians if the, you know, they actually ran this ad campaign in the 2017 time period called the truth. So giant Orwellian billboards, right, which say, you know, the truth is essential here, </s><s>[INST] it looks like this. This was when? This was just a few years ago, 2017. This is in New York. A billboard by the New York Times reads, the truth is hard to know. The truth is hard to find. The truth is hard to hear. The truth is hard to believe. The truth is hard to accept. The truth is hard to deny. The truth is more important now than ever. All right, this is like, [/INST] yeah, this is 1984 type of stuff. Yeah, now here's the thing. Do you know what other? Truth. Yeah. Big. Truth, period. Big white board. So, okay, what other national newspaper proclaimed itself the truth in constantly, every day. You know this one actually. Oh, you mean Pravda? Yeah. There you go. That's right. What is it? What's the Soviet translation? What's the Russian </s><s>[INST] translation of Pravda is? Pravda is truth. Yeah. Sorry, that didn't even connect to my head. Yes. [/INST] Yeah, truth. Unironically, huh? And again, it just so happens that- </s><s>[INST] Is this an onion article? [/INST] Listen, I didn't know. Pravda, at least you're a communist, these guys have figured out how to get charged people $99 a year or whatever it is for the truth. Wow, that's actually even amazing. The corporate truth. When you stack all that up, basically legacy media has delegitimize themselves. Every day that those quote investigative journalists don't investigate Salsberger shows that they are so courageous as to investigate your boss, but not their own. Ta-da. Total mass drop. That's just obvious. Now, once you realize this and every influencer who's coming up, every creator realizes, okay, well, that means I have to think about these media corporations as competitors. They are competitors. They are competitors for advertisers and influencers. They will try basically what the media corporations did partially successfully during the 2010s is they sort of had this reign of terror over many influencers, where they'd give them positive coverage if they supported sort of the party line and negative coverage if they didn't. But now the soft power has just dropped off a cliff and many kinds of tactics that establishment journalists do, one way of thinking of them is like as a for-profit Stasi. Why? Because they may stalk you, dox you, surveil you. They can literally put two dozen people following somebody around for a year and that's not considered stalking. That's not considered spamming. They are allowed to do this and make money doing this. Whereas if you so much as criticize them, oh my God, it's an attack on the free press, blah, blah, blah. But you are the free press and I'm the free press. We're the free press. Again, it goes back to the decentralized, the free speech is not like some media corporations thing. It's everybody's right. And what actually happened with social media, what they're against, is not that it is an attack on democracy, is that it's the ultimate democracy because people have a voice now that didn't used to have a voice. It's saying freedom of the press belongs to those that won one, right? Never argue with the man who buys ink by the barrel. In a real way, the entire things that were promised to people, freedom of speech, free markets, like a beggar's democracy, oh yeah. You can have freedom of speech, but not freedom of of reach, because you're just talking to yourself in your living room in, you know, Buffalo, New York, right? You maybe you can get gather some friends around, you didn't have the licenses to get, you know, like a TV broadcast license, radio license, you know, the resources to buy a newspaper, you didn't have practical reach or distribution. Okay. What happened was all these people in the US and around the world suddenly got voices, and they were suddenly saying things that the establishment didn't want them to say. And so that's what this counter decentralization is meant both in the US and in China, this crackdown. But it's as if like a stock went up like 100x and then drop like 30%. All the de platforming stuff. Yes, it's bad. Okay, it's, um, it's it's a it's a rearward move. But in the long arc, I think we're going to have more speech, I think the counter decentralization may succeed in China, but I don't think it's going to succeed outside it because you you're trying to retrofit speech and thought controls onto an ostensibly free society, right? Now that check got cash, people actually have a voice, it's not going to be taken away from them very easily. Right? So how does this relate to my advice to young kids? Once you have that context, right? Once you realize, hey, look, Apple didn't like do deals with Blackberry, okay, Amazon didn't collaborate or give free content to Barnes and Noble. Netflix was not going and you know, socializing with employees of blockbuster. These employees of establishment media corporations are your competitors. Okay, they are out for clicks. They are out for money. They will, if they literally choke out the Ukrainians before making themselves into champions of the Ukrainian cause, they'll basically do anything, you know. And so it once you realize that you're like, okay, I need to build my own voice. Okay, if you're resilient, you're, you know, Nigerian, you're in the Midwest or the Middle East, right? If you're, you know, Japanese, you know, whatever, wherever you are, you need to build your own voice, because outsourcing that voice to somebody else, and having it put through the distorting filter, which maximizes the clicks of the distorting kind of thing, is just not going to be in one's own interest. You don't have to, you know, even agree with everything I'm saying, or even all of that to just be like, well, look, I'd rather speak for myself, I'd rather go direct if I could speak unmediated in my own words, right? Because the choice of words is actually very important, right? So that's the second big thing, you need to and this is the thing that took me a long time to understand, okay, because I always got the importance of math and science. And in fact, I would have been probably just a career academic or mathematician in another life, you know, maybe statistician, something like that, electrical engineer, etc. But the importance of creating your own content and telling your own stories. If, if you don't tell your own story, the story will be told for you, right? The sort of flip of winners, right? History is if you do not write history, you will not be the winner, you must write a history. Okay, as kind of a funny way of, you know, putting it, right? Yeah, chicken and egg. Yeah, contra positive, right? And now what does that mean, practically, okay? So in many ways, the program that I'm laying out is to build alternatives, peaceful alternatives to all, you know, legacy institutions, right? To obviously to the Fed, right, with with Bitcoin, to Wall Street, with defy and with Ethereum, and so on, to academia, with the ledger of record and the on chain reproducible research that we talked about to media with decentralized social media decentralized AI, you can melt Hollywood with this, okay, melt the RIA melt the MPAA. I mean, there's there's some good people there. But everybody should have their own movies, you know, there's people should be able to tell their own stories and not just wait for it to be cast through Hollywood and how it was just making remakes anyway, okay, so you can tell original stories, and you can do so online, and you can do so by hitting a key and the production values will be there now that the AI content creation tools are out there. I mentioned disrupting or replacing or building alternatives to the Fed, to Wall Street, to academia, to media, I mentioned to Wikipedia, right? There's things like golden, there's things like, there's a bunch of web three ish Wikipedia competitors that are combining with AI and crypto for property rights. There's you'll also need alternatives to all the major tech companies. That's that was the list that went through with, you know, decentralized, search and social, and messaging and operating systems and even the crypto phone. Okay. And then finally, you need alternatives to us political institutions and more generally, and Chinese political institutions. And what are those that's that's where the network state comes in. And the fundamental concept is, if, as I mentioned, only 2% of the world can become president of the United States about the number of Americans who are, you know, native born and over 35, and so on and so forth. But 100% world can become president of their own network state. What that means is, um, and this kind of related to those two points, right? If you're an individual, you're good at engineering and you're good at content creation, okay, like somebody like Jack Dorsey, for example, or or Mark Anderson, actually, a lot of the founders are actually quite good at both nowadays, you look Bezos, he's actually funny on Twitter, when he allows himself to be he's, you know, you don't become a leader of that caliber without having, you know, some of both, right? If you've got some of both, um, now, no matter where you are, what your ethnicity is, what your nationality is, whether you can get a US visa, you can become president of a network state. And what this is, it's a new path to political power that does not require going through either the US or the Chinese establishment, you don't have to wait till you're 75. You don't have to become a gerontocrat, or spout the party line, and so on. The V one of this is like, folks like, you know, Francis Suarez, or Nate McKelly of El Salvador. But, you know, Suarez is a great example where, while not a full sovereign or anything like that, he has many ways, and maybe is the skills of a tech CEO, we just put up a, you know, a call on Twitter, and helped build Miami recruited all these people from all over. And wasn't the two party system, but the end city system, he just helped build the city by bringing people in. Okay. And that's, and when I say Suarez is a V one, I, you know, I love Francis Suarez, I love what they're doing. Um, the next iteration of that is to actually build the community itself, rather than just kind of taking an existing Miami, you're building something that is potentially the scale of Miami, but as a digital community. And how many people is that? Well, like the Miami population is actually not that large. It's like 400 something 1000 people, you could build a digital community like that. So if you have the engineering, and you have the content creation, and you build your own distribution, you own your own thing, you can become essentially a new kind of political leader, where you just build a large enough online community, that can crowdfund territory, and you build your vision of the good. </s>
<s>[INST] those are, those two are so fascinating because it's coming from Russia. I don't know if that's where I got it or if it's just my own predisposition as I always loved. The there's two ways to get you to want to pin yourself. One is to making it so painful not to pin yourself that you pin yourself or whatever and the other is it's sort of like Bruce lee water flows, make it so easy to pin yourself. So it's technique, it's like the elegance, the ease of movement. This is the city of brothers, uh, Bossier city ev ah like the, just the elegance, the efficiency of [/INST] L. A. Watching these guys, you know, this incredible satellite brothers are massive and uh, and </s><s>[INST] also the past so [/INST] caveat a little bit that like if you're, if you're approaching this from a Russian perspective, Russians are quite truthful about things, especially when it comes to something like combat. They just, this is how it is and this is how it's going to be. Yes and honesty is what I really like about catch wrestling because I find that we given any opportunity for us to be dishonest for any number of reasons we're gonna, especially if it's a dishonesty towards a positive, right? Like, oh well, you know, it's all technique and it's all this and it's the gentle art of blah Bro. I have rolled with 80cc world champions, you know, some of the best you have ever heard of. There ain't a lot of gentleness when it comes to like, oh yeah, they wanted to sweep you and you said no and then you did said no again and then you said no and attack their leg, it ceases to be all that gentle because at the end of the day, these dudes are strong as hell, they're flexible. They're all, I mean there the difference between the athleticism and the the ability to actually win is a pretty wide gap. The athleticism shows up, but then there's all that other extra and part of that is meanness and, and pain and getting what you need out of it proceed. </s><s>[INST] There is a philosophical difference in the way is thought, because [/INST] I think some of it is just they just in denial, like, oh, people will, they like to people like to espouse a lot of things this theory and then it's like, okay, let me watch. You're not doing anything about what you said right now. In fact, you're doing the opposite. You're you're literally hurting that guy because your shift ain't working in the way that you'd like it to. So you're having to use strength, you're having too much one of my favorites, like, oh, you're using too much strength. And it's like, well, hold on, do we want people not to use strength at this point to understand more of mechanics? Or are you trying to tell people if they use strength at all, uh, that there's somehow bad at what they do because, you know, it's not my fault. You're not stronger than, </s><s>[INST] you know, speaking of something else? That's uh [/INST] that's I tend to think what it comes down to is the strength is fine until you beat me with it, then it </s><s>[INST] sucks. Okay, so strength is another thing I'm thinking about more like anger. Oh, so like a lot [/INST] of angry guys, you did too. I know that. </s><s>[INST] Really? Okay, okay, but let's talk about, let's talk about their only the highest level of competition. There's a book called Wrestling tough. There's a really good book that I've encountered in my life. A few, especially in wrestling people who really try to find a way to use anger to get really angry at their opponent, not like stupid anger, but just like [/INST] intense pointed uh, anger, uh, distilled into something that you can use fuel. </s><s>[INST] And like, I remember the story, I don't know why I read, it might be wrestling tough, where a person was imagining that their opponent just rape their mother raped their girlfriend or something like that to, to create this like method acting thing in their head to be like to snap them out of this polite interaction of usual, like athletic convention and like really go to the [/INST] primitive design of necessity. So my anecdote for this was I was sitting with uh backstage before a fight, not my fight and I'm working with this guy and the student is, this is this is the world champion guy and he competed at the highest levels. Uh, any, he looks at me and he goes, you know, you ever get nervous before fights? I looked at and I went, no, I don't and he just looks at me. He's like funk man, I'm sooner, you know, how do you do it man? You know, I wish I could be like you and I said, you know what, that doesn't mean that what I'm doing is better. It's just what is necessary for me. It's the way I am. And I told him, so this anecdote goes into another anecdote. This is a family guy episode I guess uh where some, another famous high level guy told me about this experience with world champion boxer in Japan and this guy would get insanely nervous and worked up and anxious before his matches and he hated it and hated it and hated it. And so he wanted to get rid of that feeling. So he went to a hypnotist for a bunch of sessions and managed to, and he goes in and the next fight cool as a cucumber and doesn't perform and loses. And so what I said, going back to anecdote, one was, you know, whatever is necessary for you to get yourself in the best state of being right now to compete. Whatever that may be, it could be absolute stress and fear. It could be, anger could be calmness, it could be whatever. But there is a, but there is a, there's a state at which you need to begin to do your best </s>
<s>[INST] Yeah, it's for us that like final Air or some particular layer is very important. The one that tells us that it's our dog or like it's a cat or a dog. But, you know, each layer is probably equally as important in the grand scheme of things. Like there's no reason why the cat versus dog is more important than the lower level activations. It doesn't really matter. I mean, all of it is just this beautiful stacking on top of each other and we humans live in this particular layers. For us. For us it's useful to to survive to to use those cat versus dog predator versus prey, all those kinds of things. It's fascinating that it's all continues. But then you then ask, you know, the history of artificial intelligence you ask, are you able to introspect and convert the very things that allow us to tell the difference the cat and dog into uh logic into formal logic. That's been the dream, I would say that's still part of the the dream of symbolic ai and um I've recently talk to Doug Leonard who created psych and that's that's a project that lasted for many decades and still carries a sort of dream in it, right? Um we still don't know the answer, right? It seems like connection is um is really powerful, but it also seems like there's this building of knowledge. So [/INST] how do we </s><s>[INST] how do you square those two? Like do you think the connections can contain the depth of human knowledge and the depth of what uh Dave Rummelhardt was thinking about of understanding? [/INST] Well that remains the $64 question. And um </s><s>[INST] with inflation that [/INST] Number, </s><s>[INST] dollars, maybe [/INST] It's a $64 billion uh uh you know, I think that um yeah, from the emergent aside which, you know, uh I placed myself on. So I I used to sometimes tell people I was a radical eliminated connection ist because I didn't want them to think that I wanted to build like anything into the machine. But I don't like the word eliminated, I've uh anymore because it makes it seem like it's wrong to think that there is this emergent level of understanding and um I disagree with that. So I think you know, I would call myself an a radical emergent ist uh connection ist rather than eliminated connection ist right? Because I want to acknowledge that that these higher level kinds of aspects of our cognition are are real, but they're not, they don't they don't exist as such. And so there was an example that Doug Hofstadter used to use that I thought was helpful in this respect. Just the idea that we can think about sand dunes as entities and talk about like how many there are even. Um but we also know that a sand dune is a very fluid thing. It's it's it's a it's a it's a pile of sand that is capable of moving around under the wind and and and um you know, reforming itself in somewhat different ways and and if we think about our thoughts is like sand dunes as being things that you know emerged from uh just the the way all the lower level elements sort of work together and are constrained by external forces, then we can we can say yes, they exist as such, but they also, you know, we shouldn't treat them as completely monolithic entities that we we can understand without understanding sort of all of the stuff that allows them to change in the ways that they do and that's where I think the connection ist feeds into the into the cognitive, it's like, okay, so if the under if the substrate is parallel distributed connection ist um then it doesn't mean that the contents of thought isn't you know like abstract and symbolic and but it's more fluid maybe than uh is easier to capture with a set of logical </s><s>[INST] expressions. Yeah, that's a heck of a sort of thing to put at the top of a of a resume radical emergen ist connection ist. So there is just like you said, a beautiful dance between that between the machinery of intelligence, like the neural network side of it and the stuff that emerges. I mean the stuff that emerges seems to be um I don't know, I don't know what that is that it seems like maybe all of reality is emergent. What I what I think about this has made most distinctly rich to me when I look at cellular Tamina look a game of life that from very, very simple things, very rich, complex things emerge that start looking very quickly like organisms that you forget that forget how the actual thing operates, they start looking like that moving around, they're eating each other. Some of them are generating offspring. You forget very quickly. And it seems like maybe it's something about the human mind that wants to operate in some layer of the emergent and forget about the mechanism of how that emergency happens. So it's just like you are in your radicalness. I'm uh also it seems like unfair to eliminate the magic of that emergent? Like eliminate the the fact that that the emergence is real. [/INST] Yeah, no, I agree. I'm not that's why I got rid of eliminated. </s><s>[INST] Right? Yeah. [/INST] Because it seemed like that was trying to say that, you know, it's all completely like </s><s>[INST] an illusion of some kind of, well, [/INST] it, you know, who knows whether there isn't, there aren't some illusory characteristics there. Um, and and I think that philosophically, um, many people have have confronted that possibility over time, but, but uh, it's still important to, um, you know, accept it as magic, right? So, you know, I think of Fellini in this context. I think of others who have appreciated uh, the role of magic of actual trickery in creating illusions that that move that move us. You know, And Plato was onto this too. It's like somehow or other these shadows, you know, give rise to something much deeper than that. And that's that's so, you know, we won't try to figure out what it is. We'll just accept it as given that that that occurs. And um, you know, but he was still on to the magic of </s>
<s>[INST] a unit test will catch it in some way. Yeah, in my private code, I have asserts everywhere. There's something pleasant to me, pleasurable to me about sort of the dictatorial rule of like, like, this should be true at this point. In too many times, I've made mistakes that shouldn't have been made. And I would assume I wouldn't be the kind of person that would make that mistake, but I keep making that mistake. Therefore, an assert really catches me, really helps all the time. So my code, I would say like 10 to 20% of my private code just for personal use is probably [/INST] asserts. And they're active comments. It's one of those things that in theory, they don't make any difference to the program. And if it was all operating the way you expected it would be, then they will never fire. But even if you have it right and you wrote the code right initially, then circumstances change. The world outside your program changes. And in fact, that's one of the things where I'm kind of fond in a lot of cases of static array size declarations where I went through this period where it's like, okay, now we have general collection classes, we should just make everything variable. Because I had this history of in the early days, you get doom, which had some fixed limits on it, then everybody started making crazier and crazier things, and they kept bumping up the different limits, this many lines, this many sectors. And it seemed like a good idea, well, we should just make this completely generic, it can go kind of go up to whatever. And there's cases where that's the right thing to do. But it also, the other aspect of the world changing around you is it's good to be informed when the world has changed more than you thought it would. And if you've got a continuously growing collection, you're never going to find out you might have this quadratic slowdown on something where you thought, oh, I'm only ever going to have a handful of these, but something changes, and there's a new design style, and all of a sudden, you've got 10,000 of them. So I kind of like in many cases, picking a number, some nice round power of two number, and setting it up in there and having an assert saying it's like, hey, you hit the you hit this limit, you should probably think are the choices that you've made around all of this still relevant, if somebody's using 10 times more than you thought </s><s>[INST] they were those things that in theory, they don't Yeah, this code was originally written with this kind of worldview, with this kind of set of constraints, you were you were thinking of the world in this way. If something breaks, that means you got to rethink the initial stuff. And it's nice for it to afford to afford to do that. Is there any stuff like keyboard or [/INST] or monitors or monitors? Barely pedestrian on a lot of that where I did move to triple monitors, like in the last several years ago, I had been dual monitor for a very long time. And I am. And it was one of those things where probably years later than I should have, I'm just like, well, the video cards now generally have three output ports, I should just put the third monitor up there. That's been a that's been a pure win. I've been very happy with that. But no, I don't have fancy keyboard or mouse </s><s>[INST] or anything. The key things is, the key things is an ID that has helpful debuggers has helpful [/INST] tools. So it's not the Emacs VIM route and then Diet Coke. So I did spend, you know, I spent I had one of my week long retreats where I'm like, okay, I'm going to make myself use is actually classic VI, which I know people will say you should never have done that. You should have just used them directly. But, you know, I gave it the good try. It's like, okay, I'm being in kind of classic Unix developer mode here. And I worked for a week on it. I used Anki to like teach myself the different little key combinations for things like that. And in the end, it was just like, all right, this was kind of like my Civil War reenactment phase, you know, it's like I'm </s><s>[INST] going out there doing it like they used to in the old days. And it was kind of fun. So many people [/INST] right now screaming as they're listening to this. So again, the out is this was not modern VIM, </s><s>[INST] but still, yes, I was very happy to get back to my visual studio at the end. Yeah, I'm actually, I struggle with this a lot, because there's a Kinesis keyboard and I use Emacs primarily. And I feel like I can exactly as you said, I can understand the code, I can navigate the code. There's a lot of stuff you can build within Emacs with using Lisp, you can customize a lot of things for yourself to help you introspect to code, like to help you understand the code and visualize different aspects of the code, you can even run debuggers. But it's it's work. And the world moves past you and the better and better ideas are constantly being built and that that puts a kind of I need to take the same kind of retreat as you're talking about but now I'm still fighting [/INST] the civil war I need to kind of move into the 21st century and it does seem like the world is or a large chunk of the world is moving towards visual studio code which is kind of interesting to me against the JavaScript ecosystem on the one hand and IDs are one of those things that you want to be infinitely fast you want them to just kind of immediately respond and like I mean heck I've got there's someone I know I'm an old school game dev guy that still uses visual studio six and on a modern computer everything is just absolutely instant on something like that because it was made to work on a computer that's 10,000 or 100,000 times slower so just everything happens immediately and all the modern systems just feel you know they feel so crufty when it's like oh why is this refreshing the screen and moving around and updating over here and something blinks down there and you should update this and there's you know there there are things that we've lost with that incredible flexibility but I have lots of people get tons of value from it and I am super happy that that seems to be winning over even a lot of the old vim and emacs people that they're kind of like hey visual studio codes may be you know not so bad I am that may be the final peacekeeping solution where everybody is reasonably happy with something like that. </s>
<s>[INST] Okay, so, I mean on that topic, let me ask you to play Devil's advocate. Is it possible for you to imagine, Look, years from now and looking at your book ah in which ways might your ideas be wrong? [/INST] Oh, I worry about this all the time. Um, </s><s>[INST] yeah. Still useful. [/INST] Yeah, Yeah. I think there's, you know, um, I can I can best relate it to like, things I'm worried about right now. So we talked about this voting idea, It's happening. There's there's no question it's happening. But it could be far more uh, there's there's enough things I don't know about it that it might be working in the ways differently. I'm thinking about the kind of what's voting, who's voting? You know, where our representations. I talked about like, you have 1000 models of the coffee cup like that. That could turn out to be wrong because it may be Maybe there are 1000 models that are sub models, but not really a single model. The coffee cup. I mean, there's things, these are all sort of on the edges, things that I I present is like, oh, it's so simple and clean. Well, it's not that it's always gonna be more complex. And um, and there's parts of the theory which I don't understand the complexity well, so I think, I think the idea that the brain is a distributed modeling system is not controversial at all. Right. That's not that's well understood by many people. The question then is our each cortical column, an independent modeling system. Um, I could be wrong about that. Um, I don't think so, but I worry about it. </s><s>[INST] My intuition, not even thinking why you could be wrong is the same intuition I have about any sort of physicists like string theory that we as humans desire for a clean explanation. And 100 years from now. Uh, intelligence systems might look back at us and laugh at how we try to get rid of the whole mess by having simple explanation when the reality is, it's it's way messier and in fact, it's impossible to understand. You can only build it. It's like this idea of complex systems and sell your Tamara. You can only launch the thing. You cannot understand it. [/INST] Yeah, I think that, you know, the history of science suggests that's not likely to occur. Um, the history of science suggests that as a theorist and we're theorists. You look for simple explanations, right, fully knowing that whatever simple explanation you're gonna come up with is not going to be completely correct. I mean, it can't be, I mean, it's just it is more complexity, but that's the role of theorists play. They sort of give you a framework in which you now can talk about a problem and figure out, okay, now we can dig in more details. The best frameworks stick around while the details change. You know, again, you know, the classic example is Newton and Einstein, right. You know, um Newton's theories are still used, they're still valuable, they're still practical, they're not like wrong, just they've been </s><s>[INST] refined. Yeah, but that's in physics, it's not obvious by the way. It's not obvious for physics either, that the universe should be such, that amenable to these [/INST] simple, but it's so far it appears to be as far as we can tell. </s><s>[INST] Uh Yeah, I mean, but as far as we can tell, and but it's also an open question whether the brain is amenable to such clean theories, that's the not the brain, but intelligence. [/INST] Well, I don't know, I would take intelligence just say, you know, um well, okay, um the evidence we have suggests that the human brain is a at the one time extremely messy and complex, but there's some parts that are very regular and structured. That's why we started the new york cortex it's extremely regular in its structure and unbelievably so, and then I mentioned earlier, the other thing is it's universal abilities, it is so flexible to learn so many things we don't, we haven't figured out what I can't learn yet, We don't know, but we haven't figured out yet, but he learns things that it never was evolved to learn. So those give us hope. Um, that's why I went into this field because I said, you know, this regular structure, it's doing this amazing number of things. There's gotta be some underlying principles that are common and other scientists have come up with the same conclusions. Um, and so it's promising, it's promising and um, and that's and whether the theories play out exactly this way or not, that is the role that theorists play. And so far it's worked out well, even though, you know, maybe, you know, we don't understand all the laws of physics, but so far it's been pretty damn useful. The ones we have, our theories are pretty useful. </s><s>[INST] You mentioned that we should not necessarily be at least to the degree that we are worried about the existential risks of artificial intelligence, relative to human risks from human nature being existential risk. What aspect of human nature worries you the most in terms of the survival of the human species, [/INST] I mean I'm disappointed in humanity's humans, I mean all of us, I'm one, so I'm disappointed myself too. Um it's kind of a sad state, there's there's two things that disappoint me. One is how it's difficult for us to separate our rational component of ourselves from our evolutionary heritage, which is, you know, not always pretty, you know, um, rape is a, is an evolutionary good strategy for reproduction. Murder can be at times too, you know, making other people miserable at times is a good strategy for reproduction. It's just, and it's just, and so now that we know that and yet we have this sort of, you know, you and I can have this very rational discussion talking about, you know, intelligence and brains in life and some, so it seems like it's so hard. It's just a big transition, forget humans, all humans to, to make the transition from like, let's pay no attention to all that ugly stuff over here. Let's just focus on the incident. What's unique about humanity is our knowledge and our intellect. </s>
<s>[INST] But the causal graph is, is, I don't know, it's kind of an observation. It's not enforced. It's just emergent from, well, it's a feature of, okay, so what it is characteristic, [/INST] I guess, the way events happen. Well, it's a, it's a feature of, okay. So what it is characteristic, I guess, right. Right. It's an event can't happen until its input is ready. Right. And so that creates this, this network of causal relationships. And that's, that's the causal graph. And the thing that the next thing to realize is, okay, we, when you're going to observe what happens in the universe, you have to sort of make sense of this causal graph. So, and you are an observer who yourself is part of this causal graph. And so that means, so let me give you an example of how that works. So, so imagine we have a really weird theory of physics of the world, where it says that this updating process, there's only going to be one updated every moment in time. And there's this can be like a Turing machine. Who has a little head that runs around and just is always just updating one thing at a time. So you say, you know, I have a theory of physics and the theory of physics says there's just this one little place where things get updated, you say, that's completely crazy, because, you know, it's plainly obvious that things are being updated, sort of, you know, at the same, but the fact is that the thing is that if I'm talking to you, and you seem to be being updated as I'm being updated, but, but, if there's just this one little head, that's running around updating things, I will not know whether you've been updated or not until I'm updated at the same time. So in other words… that if you draw this causal graph of the causal relationship between the updateings in you and the updates in me, it'll still be the same causal graph. Whether even though the underlying sort of story of what happens is, oh, there's just this one little thing and it goes and updates in different places in the universe. </s><s>[INST] Is that clear or is that a hypothesis? Is that clear that there's a unique causal graph? [/INST] If there's causal invariance there's a unique causal graph. </s><s>[INST] So it's okay to think of what we're talking about as a hypergraph and the operations on it as a kind of Turing machine with a single head, like a single guy running around updating stuff. Is that safe to intuitively think of it this way? [/INST] Let me think about that for a second. Yes, I think so. I think there's nothing. It doesn't matter. I mean, you can say, okay, there is one, the reason I'm pausing for a second is that I'm wondering, well, when you say running around, depends how far it jumps </s><s>[INST] every time it runs away. Yeah, that's right. But I mean, like, one operation. Yeah, you can think of it as one operation. It's easier for the human brain to think of it that [/INST] way, as opposed to simultaneous… Well maybe. Yeah, you can think of it as one operation. Okay, but the thing is, that's not how we experience the world. What we experience is, we look around, everything seems to be happening at successive moments in time everywhere in space. And that's partly a feature of our particular construction. I mean, that is, the speed of light is really fast compared to, you know, we look around, you know, I can see maybe a hundred feet away right now. You know, it's the, my brain does not process very much in the time it takes light to go a hundred feet. </s><s>[INST] The brain operates at a scale of hundreds of milliseconds or something like that. I don't [/INST] know. And speed of light is much faster and speed of light is much faster. Right. You know, light goes in a billionth of a second light has gone a foot. So it </s><s>[INST] goes a billion feet every second. There's certain moments through this conversation where I imagine the absurdity of the fact that there's two descendants of apes modeled by a hypergraph that are communicating with each other and experiencing this whole thing as a real time simultaneous update with, I'm taking in photons for you right now, but there's something much, much deeper going on right here. It does have a, it's paralyzing sometimes just to remember that right here. Yes. To remember that. Right. No, I mean, you know, yes, yes, no, as a small, as a small little tangent, I just remembered that we're talking about, I mean, this, about the [/INST] fabric of reality. Right. So we've got this causal graph that represents the sort of causal relationships between all these events in the universe. That causal graph kind of is a representation of space time, but our experience of it requires that we pick reference frames. This is kind of a key idea. Einstein had this idea that what that means is we have to say, what are we going to pick as being the sort of what we define as simultaneous moments in time? So for example, we can say, you know, we, we set, how do we set our clocks? You know, if we've got a spacecraft landing on Mars, you know, do we say that, you know, what, what time is it landing at? Was it, you know, even though there's a 20 minute speed of light delay or something, you know, what time do we say it landed at? How do we, how do we set up sort of time coordinates for the world? And that turns out to be that there's kind of this arbitrariness to how we set these reference frames that define sort of what counts as simultaneous. And what is the essence of special relativity is to think about reference frames going at different speeds and to think about sort of how they assign what counts as space, what counts as time and so on. That's all a bit technical, but the basic bottom line is that the, this causal invariance property, that means that it's always the same causal graph independent of how you slice it with these reference frames, you'll always sort of see the same physical processes go on. And that's </s>
<s>[INST] experiment with different hyperparameters on it. Really building up intuition by doing ML [/INST] experiments of different kinds. The next big thing though is I decided that I was going to take some investor money because I have an overactive sense of responsibility about other people's money. A lot of my push and my passionate entreaties for things at Meta are like, I don't want Zuck to have wasted his money investing in Oculus. I want it to work out. I want it to change the world. I want it to be worth all of this time, money, and effort going into it. And I expect that it's going to be like that with my company. It's a huge forcing function in this investment. Investors that are going to expect something of me. Now, we've all had the conversation that this is a low-probability long-term bet. It's not something that there's a million things I could do that I would have line of sight on the value proposition for. This isn't that. I think there are unknown unknowns in the way, but it's one of these things that it's hyperbole, but it's potentially one of the most important things humans ever do. And it's something that I think is within our lifetimes, if not within a decade, to happen. So yeah, this is just now happening like term sheet, like the ink is barely, </s><s>[INST] virtual ink is barely dry on this. It's dry. I mean, as I mentioned to you offline, like somebody I admire and somebody you know, Andre Karpathy, I think the two of you, different trajectories in life, but approach problems similarly in that he causes stuff from scratch up all the time. And he's created a bunch of little things outside of, even outside the course at Stanford that had been tremendously useful to build up intuition about stuff, but also to help people. And they're all in the realm of AI. Do you see yourself potentially doing things like this or built, you know, not necessarily solving a gigantic problem, but on the journey, on the path to that, that building up intuitions and sharing code or ideas or systems that give inklings of AGI, [/INST] but also kind of are useful to people in some way. So yeah, first of all, Andre is awesome. I learned a lot when I was going through my larval phase from his blog posts and his Stanford course and, you know, super valuable. I got to meet him first a couple of years ago when I was first kind of starting off on my gentleman scientist bit. And just a couple months ago, when he went out on his sabbatical, he stopped by in Dallas and we talked for a while and I had a great time with him. And then when I heard he actually left Tesla, I did, of course, along with a hundred other people say, Hey, if you ever want to work with me, it would be an honor. So he thinks that he's going to be doing this educational work, but I think someone's going to make him an offer. He can't </s><s>[INST] refuse before he gets too far along on it. Oh, his current interests, his education is like, yeah, he's a special mind. Is there something you could speak to what makes him so special? [/INST] So you understand. He was very much a programmer's programmer that was doing machine learning work rather than it's a different feel than an academic where you can see it in paper sometimes where somebody, that's really a mathematician or a statistician at heart and they're, they're doing something with machine learning. But I, you know, Andre's about getting something done and you could see it in, like all of his earliest approaches to- it's like, okay, here's how reinforcement learning works. Here's how recurrent neural networks work. Here's how transformers work. Here's how I am crypto works. And I am, and yeah, it's just, he's a hacker's, you know, one of his old posts was like a hacker's guide to machine learning. And, you know, he deprecated that and said, don't really pay attention to what's in here. But it's that thought that carries through in a lot of it where it is that back again to that hacker mentality and the hacker ethic with what he's doing and sharing all of it. </s><s>[INST] Correct. Yeah. And a lot of his approach to a new thing, like you said, larva stage is, [/INST] let me code up the simplest possible thing to build up intuition about it. Yeah. Like I say, I sketch with structs and things when I'm just thinking about a problem. </s><s>[INST] I'm thinking in some degree of code. You are also among many things, a martial artist, both judo and jujitsu. How has this helped make you the person you are? [/INST] So, I mean, I was a competent club player in judo and grappling. I mean, I was, you know, by no means any kind of a superstar, but it was, I went through a few phases with it where I did some, I, when I was quite young, a little bit more when I was 17, I am. And then I got into it kind of seriously in my mid thirties and, you know, I went pretty far with it and I was, you know, pretty good at some of the things that I was doing. And I did appreciate it quite a bit where, I mean, on the one hand, it's always if you're going to do exercise or something, it's a more motivating form of exercise. You know, if someone is crushing you, you are motivated to, to do something about that, to up your attributes and be better about getting out of that, but there's also that sense that I was not a sports guy. I did do wrestling in junior high and I often wish that I think I would have been good for me if I'd carried that on into high school and had a little bit more of that. I mean, it's like I filch a little bit of wrestling vibe with always going on about embracing the grind and that push that I associate with the wrestling team that in hindsight, I wish I had gone through that and push myself that way. But even getting back into Judo and Jiu-Jitsu in my mid-30s as usually the old man on the mat with that, there was still the sense that working out with the group and having the guys that you're beating each other up with it, but you just feel good coming out of it. I can remember those driving home aching in various ways and just thinking it's like, oh, that was really great. And it's mixing with a bunch of people that had nothing to do with any of the things that I worked with. Every once in a while, someone would be like, oh, you're the Doom guy. But for the most part, it was just different slice of life, a good thing. And I made the call when I was 40. That's like, maybe I'm getting a little old for this. I had separated a rib and tweaked a few things and I got out without any really bad injuries and was like, have I dodged enough bullets? Should I hang it up? I went back, I've gone a couple of times in the last decade trying to get my kids into it a little bit. I didn't really stick with any of them, but it was fun to get back on the mats. I really hurts for a while when you haven't gone for a while, but I still debate this pretty constantly. My brother's only a year younger than me and he's going kind of hard in jujitsu right now. He won a few medals at the last tournament he was at and I was thinking, yeah, I guess we're in the executive division if you're over 50 or over 45 or something. It's not out of the question that I go back at some point to do some of this, but again, I'm just reorganizing my life around more focus, probably not going to happen. I'm pushing my exercise around to give me a longer uninterrupted intellectual focus time, pushing it to the beginning or the end of the game. I'm running and stuff like that, walking. Yeah, I got running in </s>
<s>[INST] Yeah. So in its inner an inner voice or an outer voice, whether it's it could be spiritual, religious too with God or some other components of the environment outside of you or just your own voice. Do you have a do you have an answer there? [/INST] So, okay, so that I have an answer and through, you know, the long period of time of thinking and searching, even searching through outsides right? You know, voices are factors outside of me so that I have and I have come to the conclusion and realization that it's you yourself that defines the meaning of life. </s><s>[INST] Yeah, that's a big burden though, isn't it? Um [/INST] Yes, yes, yes and no. Right? So then you have the freedom to define it. And and another question is like, what does it really mean by the meaning of life? Right. Um and also whether the question even makes sense. </s><s>[INST] Absolutely. And you said it somehow distinct from happiness. So, meaning is something much deeper than just any kind of emotional, any any kind of contentment or joy or whatever, it might be much deeper. And then you have to ask what is deeper than that, what is, what is there at all? And then the question starts being silly, [/INST] right? And also you can see it's deeper, but you can also say it's a shallow depending on how people want to define the meaning of their life. So for example, most people don't even think about this question then the meaning of life to them? It doesn't really matter that much. And also whether knowing the meaning of life, um, whether it actually helps you will have to be better or that helps your life to be happier. Um, these actually are often questions. It's not </s><s>[INST] of course most questions open. I tend to think that just asking the question, as you mentioned as you've done for a long time is the only that there is no answer and asking the question is a really good exercise. I mean I have this for me personally, I've had kind of feeling that creation is uh like for me has been very fulfilling and it seems like my meaning has been to create and I'm not sure what that is. Like. I don't have a single enough kids. I'd love to have kids. But I also sounds creepy. But I also see sort of sexy programs. I see programs as little creations. I see robots as little creations. Uh, I think I think those are those are those bring and then ideas theorems and and our creations and those somehow intrinsically like you said, bring me joy. And I think they do to a lot of at least scientists, but I think they did a lot of people. So that to me if I had to force the answer to that, I would say creating new things. Yeah. Yourself [/INST] For you, For me, For me, </s><s>[INST] for me, I don't I don't know, but like you said that it keeps changing, Is there some answer that [/INST] some people they can, I think they may say it's experience, right? Like there are many of life uh they just want to experience to the richest and fullest they can and a lot of people do take that path. </s><s>[INST] Yes, seeing life is actually a collection of moments and then trying to make the richest possible set fill those moments with the richest possible experiences, [/INST] right? And for me, I think certainly we do share a lot of similarity here, like the creation is also really important for me, even from, you know, the things that are they talked about um even like you know writing papers and these are our creations as well. Um and I have not quite about whether that is really the meaning of my life, like in a sense also that maybe like what kind of things should you create? That so many different things that you can create? Um and also you can say another view is maybe growth is, it's related but different from experience, growth is also maybe type of meaning of life is just you try to grow every day to try to be a better self every day and uh and also ultimately we are here is part of the overall evolution, the right, the world is evolving, it's funny, </s><s>[INST] isn't it funny that the growth seems to be the more important thing than the thing you're growing towards. It's like, it's not the goal, it's the journey to it sort of, it's almost, it's almost when you submit a paper, it's a there's a sort of depressing element to it, not to submit a paper, but when that whole project is over, I mean there's there's a gratitude, there's a celebration and so on. But uh, you're usually immediately looking for the next thing for the next step, right? It's not it's not that satisfied at the end of, it is not the satisfaction is the hardship, the challenge you have to overcome the growth through the process, it's some somehow probably deeply within us the same thing that drove that drives the evolutionary process is somehow within us with everything. The the way the way we see the world since you're thinking about this, So you're still in search of an answer. [/INST] I mean yes and no, in a sense that I think for people who really dedicate time to search for the answer to ask the question, what is the meaning of life? It does not actually bring you </s><s>[INST] happiness? [/INST] Yeah, it's a question um we can say right, like whether it's a well defined question and and on the uh but on the other hand, given that you get to answer it yourself, you can define it yourself then. Sure that I can just, you know, give it uh an answer and in that sense, Yes, it can help. Um like like we discussed, if you say, oh then my meaning of life is to create, to grow. Then then yes, then I think they can help, but how do you know that that is really the meaning of life and the meaning of your life? It's like there's no way for you to really answer the question. </s>
<s>[INST] That's that's fascinating framing like the more deadly and transmissible the disease, the stronger the incentive to install it in a positive sense. The in the in the good feedback loop sense. That's a really good example. It's a really good way to frame it because with covid it was not as deadly as uh as potential pandemics could've been viruses could have been. So it's sometimes muddled with how we think about it. But yeah, this is a really good framing if if the virus was a lot more deadly, you want to create a system that has a set of incentives that it quickly suppresses the population where everybody is using it and it's contributing in a positive way to the system. [/INST] Exactly. And actually that point you just made I don't take credit for that observation. There was another person I talked to who pointed out that it's very interesting that this feedback loop is even more effective when the disease is my worse. And that's actually not a bad characteristic to have in your feedback loop if you're trying to help civilization keep running. </s><s>[INST] Yeah, it's a really it's in this dynamic like people figure out, they dynamically figure out how bad the disease is, the more it spreads and the deadlier it is as people observe it. As long as the spread of information like uh semantic information, natural language information is closely aligned with the reality of the disease, which is a whole lot of the conversation. Right? We that's we might maybe we'll chat about that how we sort of make sure there's not misinformation when there's accurate information. But that aside, Okay, so this is a really nice property. [/INST] Right? And and and just going on on that actually, just talking more about what that could do and why we are so excited about it. It's that not only would people want to install it, what would they do if you start to see that this disease is getting closer and closer. We surveyed informally people, but they said as we saw it getting closer, we would hide we would try to not have contacts. But now you notice what this has just achieved. The whole goal on this whole exercise was you got the people who might be sick and you got everyone else set A. And set B. That is the people who might be six that be as everyone else. And for the entirety of the past, uh contact tracing approaches, you try to get set A to do things that might not be to their liking or there will because that's removing them from society. Yes, we found out that there's two ways to separate sunday from should be. You can also let the people at set B at the fringe of such a attempt to remove themselves from this interface. It's just it's the symmetry of A. And B. Separation. Everyone was looking at A. We look at B and suddenly be is in their incentive to do so </s>
<s>[INST] There's an idea of power play. You described a training and general problem solving, this kind of way of looking for the unsolved problems. [/INST] Yeah, </s><s>[INST] can you describe that idea a little further? [/INST] It's another very simple idea. So normally what you do in computer science, you have you have some guy who gives you a problem and then there is a huge search space of potential solution candidates and you somehow try them out and you have more less sophisticated ways of moving around in that search space until you finally found a solution which you consider satisfactory. That's what most of computer science is about. Power plane just goes one little step further and says that's not only search for solutions to a given problem, but let's search too pairs of problems and their solutions where the system itself has the opportunity to phrase its own problem. So, we are looking suddenly at pairs of problems and their solutions or modifications of the problems over that is supposed to generate a solution to that new problem and this additional degree of freedom allows us to build career systems that are like scientists in the sense that they not only try to solve, try to find answers to existing questions nor there as a free to pose their own questions. So if you want to build an artificial scientists, we have to give it that freedom and power play is exactly doing that. </s><s>[INST] So that's that's the dimension of freedom that's important to have. But how do you, how hard do you think that how multi dimensional and difficult the space of them coming up with your questions is so it's as it's one of the things that as human beings we consider to be the thing that makes this special, the intelligence that makes it special is that brilliant insight that can create something totally new. [/INST] Yes. So now let's look at the extreme case, let's look at the set of all possible problems that you can formally describe which is infinite, which should be the next problem that a scientist or a power play is going to solve. Wow, it should be the easiest problem that goes beyond what you already know. So it should be the simplest problem that the current problems all of that you have, which can already solve 100 problems that he cannot all yet by just generalizing. So it has to be new. So it has to require a modification of the problem solver, such that the new problem solvers can solve this new thing, but the only problem solver cannot do it. And in addition to that, we have to make sure that the problem solver doesn't forget any of the previous solutions. And so by definition, power play is now trying always to search and this pair of in in in the set of pairs of problems and problems over modifications for a combination that minimize the time to achieve these criteria. So it's always trying to find the problem which is easiest to add to the repertoire. </s><s>[INST] So just like grad students and academics and researchers can spend their whole career in a local minima, stuck trying to come up with interesting questions but ultimately doing very little. Do you think it's easy in this approach of looking for the simplest unsolvable problem to get stuck in a local minima is not never really discovering new uh you know, really jumping outside of the 100 problems very solved in a genuine creative way. [/INST] No, because that's the nature of power Play, that it's always trying to break its current generalization abilities by coming up with a new problem which is beyond the current horizon. Just shifting the horizon of knowledge a little bit out there, breaking the existing rules such as the new thing becomes solvable, but wasn't solvable by the old thing. So like adding a new axiom, um like what google did when he came up with these new sentences, new theorems that didn't have a proven the formal system, which means you can add them to the repertoire, hoping that that they are not going to damage the consistency of the whole thing. </s><s>[INST] So in the paper with the amazing title formal theory of creativity, fun and intrinsic motivation, you talk about discovery as intrinsic reward. So if you view humans as intelligent agents, what do you think is the purpose and meaning of life for us? Humans is you've talked about this discovery? Do you see humans as an instance of power play agents? [/INST] Yeah, so humans are curious and that means they behave like scientists, not only the official scientists, but even the babies behave like scientists and they play around with their toys to figure out how the world works and how it is responding to their actions and that's how they learn about gravity and everything. And yeah, in 1990 we have the first systems like that. We just try to play around with the environment and come up with situations that go beyond what they knew at that time and then get a reward for creating these situations and then becoming um more general problems all of us and being able to understand more of the world. So yeah, I think in principle that um yeah, that that curiosity, strategy or more sophisticated versions of whether justice crime, they are what we have built in as well. Because evolution discovered that's a good way of exploring the unknown world and a guy who explores the unknown world has a higher chance of solving problems that he needs to survive in this world. On the other hand, those guys who were too curious, they were weeded out as well. So you have to find this tradeoff evolution found a certain trade off. Apparently in our society, there are a certain percentage of extremely exploitative guys. And it doesn't matter if they die because many of the others are more conservative. And and and so yeah, it would be surprising to me if if that principle of artificial curiosity Mhm wouldn't be present in almost exactly the same form here </s>
<s>[INST] do 100 podcasts in a row on COVID. It makes no sense. You think in part audience capture can explain that? [/INST] I absolutely think it can. I absolutely think it can. </s><s>[INST] For example, do you feel pressure to not admit that you made a mistake on COVID or made a mistake on Trump? I'm not saying you feel that way, but do you feel this pressure? So you've attacked audience capture within the way you do stuff, so you don't feel as much pressure from the audience, but within your own ego. [/INST] I mean, again, the people who think I'm wrong about any of these topics are going to think, okay, you're just not admitting that you're wrong, but now we're having a dispute about specific facts. There are things that I believed about COVID or worried might be true about COVID two years ago that I no longer believe or I'm not so worried about now and vice versa. I mean, things have flipped, certain things have flipped upside down. The question is, was I wrong? So here's the cartoon version of it, but this is something I said probably 18 months ago and it's still true. When I saw what Brett was doing on COVID, let's call it two years ago, I said, even if he's right, even if it turns out that ivermectin is a panacea and the mRNA vaccines kill millions of people, he's still wrong right now. His reasoning is still flawed right now. His facts still suck right now and his confidence is unjustified now. That was true then, that will always be true then and not much has changed for me to revisit any of my time points along the way. Again, I will totally concede that if I had teenage boys and their schools were demanding that they'd be vaccinated with the mRNA vaccine, I would be powerfully annoyed. I wouldn't know what I was going to do and I would be doing more research about myocarditis and I'd be badgering our doctors and I would be worried that we have a medical system and a pharmaceutical system and a healthcare system and a public health system that's not incentivized to look at any of this in a fine-grained way and they just want one blanket admonition to the entire population. Just take the shot, you idiots. I view that largely as a result, a panicked response to the misinformation explosion that happened and the public, the populist resistance animated by misinformation that just made it impossible to get anyone to cooperate. Part of it is, again, a pendulum swing in the wrong direction, somewhat analogous to the woke response to Trump and the Trumpist response to woke. A lot of people have just gotten pushed around for bad reasons, but understandable reasons. But yes, there are caveats to things have changed about my view of COVID. But the question is, if you roll back the clock 18 months, was I wrong to want to platform Eric Topol, a very well-respected cardiologist on this topic or Nicholas Christakis to talk about the network effects of whether we should close schools. He's written a book on COVID. He's network effects or his wheelhouse, both as an MD and as a sociologist. There was a lot that we believed we knew about the efficacy of closing schools during pandemics, during the Spanish flu pandemic and others. But there's a lot we didn't know about COVID. We didn't know how negligible the effects would be on kids compared to older people. </s><s>[INST] My problem, I really enjoyed your conversation with Eric Topol, but also didn't. He's one of the great communicators in many ways on Twitter, distillation of the current data. I hope I'm not overstating it, but there is a bit of an arrogance from him that I think could be explained by him being exhausted, by being constantly attacked by conspiracy theory, like anti-vaxxers. To me, the same thing happens with people that start drifting to being right-wing, is to get attacked so much by the left, they become almost irrational and arrogant in their beliefs. I felt your conversation with Eric Topol did not sufficiently empathize with people that have skepticism, but also did not sufficiently communicate uncertainty we have. Many of the decisions you made, many of the things you were talking about were saying, there's a lot of uncertainty, [/INST] but this is the best thing we could do now. Well, it was a forced choice. You're going to get COVID. Do you want to be vaccinated when you get it? That was always, in my view, an easy choice. And it's up until you start breaking apart the cohorts and you start saying, okay, wait a minute, there is this myocarditis issue in young men. Let's talk about that. Before that story emerged, it was just clear that if it's not knocking down transmission as much as we had hoped, it is still mitigating severe illness and death. And I still believe that it is the current view of most people competent to analyze the data, that we lost something like 300,000 people </s><s>[INST] unnecessarily in the US because of vaccine hesitancy. But I think there's a way to communicate with humility about the uncertainty of things that would increase the vaccination rate. [/INST] I do believe that it is rational and sometimes effective to signal impatience with certain bad ideas and certain conspiracy theories and certain forms of misinformation. </s><s>[INST] I think so. I just think it makes you look like a douchebag most times. [/INST] Well, certain people are persuadable, certain people are not persuadable, but it's not enough. It's the opportunity cost. Not everything can be given a patient hearing. You can't have a physics conference and then let people in to just trumpet their pet theories about the grand unified vision of physics when they're obviously crazy or when they're obviously half crazy. You begin to get a sense for this when it is your wheelhouse, but there are people who declare their irrelevance to the conversation fairly quickly without knowing that they have done it. And the truth is, I think I'm one of those people on the topic of COVID. It's never that I felt, listen, I know exactly what's going on here. I know these mRNA vaccines are safe. I know exactly how to run a lockdown. No, this is a situation where you want the actual pilots to fly the plane. We needed experts who we could trust. And insofar as our experts got captured by all manner of things, I mean, some of them got captured by Trump. Some of them were made to look ridiculous just standing next to Trump while he was bloviating about whatever. It's just going to go away. There's just 15 people in a cruise ship and it's just going to go away. There's going to be no problem. Or it's like when he said, many of these doctors think, I understand this better than them. They're just amazed at how I understand this. And you've got doctors, real doctors, the heads of the CDC and NIH standing around just ashen faced while he's talking. All of this was deeply corrupting of the public communication of science. And then again, I've banged on about the depredations of wokeness. The woke thing was a disaster. I still is a disaster. But it doesn't mean that... But the thing is, there's a big difference between me and Brett in this case. I didn't do a hundred podcasts on COVID. I did like two podcasts on COVID. The measure of my concern about COVID can be measured in how many podcasts I did on it. It's like once we had a sense of how to live with COVID, I was just living with COVID. Like, okay, if you get vaxxed or don't get vaxxed, wear a mask or don't wear a mask, travel or don't travel. You've got a few things to decide, but my kids were stuck at home on iPads for too long. I didn't agree with that. It was obviously not functional. I criticized that on the margins, but there was not much to do about it. But the thing I didn't do is make this my life and just browbeat people with one message or another. We need a public health regime where we can trust what competent people are saying to us about what medicines are safe to take. And in the absence of that, craziness is going to put... Even in the presence of that craziness is going to proliferate given the tools we've built, but in the absence of that, it's going to proliferate for understandable reasons and that's gonna, it's not gonna be good next time when something orders of magnitude more dangerous hits us. And that's, I spent a little, insofar as I think about this issue, I think much more about next time than this time. </s>
<s>[INST] The following is a conversation with Noam Chomsky his second time in the podcast. This episode is focused on the war in Ukraine And it is a departure from the way I usually do this podcast in several ways. Gnome is a strong and healthy 93 year old. But this conversation is remote. To be cautious. It is brief. Only one hour, [/INST] it </s><s>[INST] is more of an interview than a conversation due to the limitations of our audio and video connection. I decided it's best to get gnomes clear thoughts on this war and the complicated geopolitics of today and the rest of the 21st century that is unrolling before us with our decisions and actions fully capable of either helping humanity flourish or unleashing global destruction and suffering. As a brief aside perhaps you know this but let me mention that I traveled to Ukraine and saw heard felt things that are haunting and gave me a lot to think about because of that. I've been really struggling to edit the videos I recorded, I hope to finish it soon. I'm sorry for these delays and I'm especially sorry to the people there who gave me their time, their story, their heart. Please be patient with me. I hope you understand. And now a quick few second mention of each sponsor check them out in the description is the best way to support this podcast. We got skip for email inside tracker for longevity on it for supplements and blankets for nonfiction, choose wisely. My friends and now onto the flat reads as always no ads in the middle because I hate those. They break the flow of the conversation. Some of my favorite podcasts do them. It is what it is, that's life, I deal with it. But now because I have some control over where the ads or a lot of control where the ads and this podcast go, even if I lose money, I care not my friends. I am first and foremost just a fan of podcasts. So um I get to do this podcast in the way that I like to listen to podcasts as a fan. So there it is. But if you skip the sponsors which I make super easy for you apparently, um please to check out the sponsors. I enjoy their stuff. Maybe you will too. It really is the best way to support this podcast. This show is brought to you by Skiff a private end to end encrypted email. I just read like a blog post about them somewhere. This is not a very kind of informative had read, I read a blog post about skip how they're revolutionizing um a lot of aspects of email that they're doing incredible [/INST] job. I've been </s><s>[INST] using skip for a while for document collaboration for email. They got all kinds of features. Fast search. You can do custom domains for the email and you can migrate from whatever the email service you use like gmail proton mail or outlook. Man, it's been a while since I opened up outlook. I used it for a while for the most shady of emails but I think outlook um is used quite a lot in the sort of business sector in the professional sector. So if you're one of those folks you should uh move upgrade to the NTN encryption and really easy, powerful accessible interfaces gift. So sign up at dot com slash lex that S K I F F dot com slash lex. This show is also brought to you by Inside Tracker a service I used to track biological data, they got blood data, D. N. A data, fitness tracker data, all that kind of stuff. They shove it all in into a machine learning algorithm and then make predictions for what you should be doing with your life. Of course in a way that protects your privacy in the way that gives you control over that data. But I would love it if some of the aspects of my life were all integrated to where I can have an advisor, how I should allocate my effort throughout the day in order to be most optimal, how to maximize my well being, how to manage things like social media access. I just feel like [/INST] my </s><s>[INST] body has a lot of data about my well being and the software I use doesn't have access to any of that data. It just seems like those two things should be connected and inside Tracker is really pushing towards that direction of using data from your body to give lifestyle changes advice [/INST] for </s>
<s>[INST] What about the rediscovery or like the Discovery of the Little Lights? Um, uh, in the darkness. So you, the book, I think you've brilliantly describe the dark parts of your journey. Uh, but maybe can you talk about how you were able to rediscover the lights [/INST] they came in many ways? And the way you'd like to think about it is like grief as an ocean. He was tiny islands of the little like, like the little lights and eventually that ocean gets smaller and smaller and the islands like become continents with lakes. So initially be like the Children laughing one day or my colleagues at work who rallied around me and would take me away from my darkness to work on the project. Later on, it turned out to be a group of women my age, all widows, all with Children in my town. And it would be, even though it was a bit morose getting together? Um still very joyful at the same time, </s><s>[INST] What was the journey of rediscovering love like for you? So re finding I mean is there some by way of advice or insight about how to uh how to rediscover the beauty of life [/INST] Of Life? It's A Hard one. I think you just have to stay open to being positive and just to get out there. </s><s>[INST] Do you still think do you still think about your own mortality? So you mentioned that that was the thing that you would meditate on is the question when it was right there in front of you. But do you still think about [/INST] it? I think I will after talking to you know, it's not really something I think about. I mean I do think about the search for another earth and will, will I get there. Will I be able to conclude my search? And is there one like as time goes by that window to solve that problem gets smaller, </s><s>[INST] what would bring you again? I apologize if this makes concrete the fact that life is finite. But what what would bring you joy if we discovered while you're still here, [/INST] we'll bring me joy finding another earth and earth like planet around a sun like star. Knowing that there's at least one or more out there been able to see water that it has signs of water and being able to see some gasses that don't belong. So I know that the search we'll continue after I'm gone enough to fuel the next generation. </s><s>[INST] Uh so just like opening the door and there's like this glimmer of hope. Uh what do you think it will take to realize that? I mean we've talked about all these interesting projects, Star Shade especially, but is there something that you're particularly kind of Hopeful about in the next 10, 20 years that might give us that that exact glimmer of hope that there's earthlike planets out there. [/INST] I have to I stand behind star shade in all cases. So, but there is this other kind of feel that I that everyone is involved in because Star shade is hard, births are hard. But there are, there's another category of planet star type that's easier. And these are planets orbiting small red dwarf stars. They're not earth like at all. Think like Earth cousin instead of Earth twin, there's a chance that we might establish that some of those have water and signs of life on them that's nearer term than Star shade. And we're all working hard on that too. </s><s>[INST] Let me ask by way of recommendations. I think a lot of people are curious about this kind of stuff what three books, technical or fiction or philosophical or anything really had an impact on your life and and or you would recommend. Besides, of course your book. Mhm [/INST] There's one book I wish everyone could read. I'm not sure if you've read it. It's actually a Children's book, like a young adult book. It's called the Giver. </s><s>[INST] Yes. Uh [/INST] And it is a book that kids in school read now. And I'm only </s><s>[INST] sorry that's not that's wow, sorry that that caught me off guard. Uh So when I first came to this country, I didn't speak much. It's really what made me I had a profound impact on my life and I have a really important moment because they give it to kids. Like I think middle school, I think you have something like [/INST] that. I'm so surprised you've even heard of this </s><s>[INST] book. So they but like it's the value of giving the right book to a person at the right time uh was because it's very accessible. [/INST] Do we want to share what the story is without spoiling it? </s><s>[INST] Yeah, you can without spoiling right? [/INST] What follows this boy in this very utopian society that's like perfect. It's been all clean cut and made perfect actually. And as he kind of comes of age, he starts realizing something's wrong with his world. And so it's part of that question, are we going to evolve this? I mean this isn't what's there, but it made me wonder, you know, are we evolving to a better place? Is there a day when we can eliminate poverty and hunger and crime in sickness in this book. They pretty much have in a society that the boys in It sort of follows him and he becomes the chosen one too be like a receiver, the givers, the old wise man who retain some of the harshness of the outside world so that he can advise the people as the sort of boy comes of age and has chosen for the special role. He finds the world isn't what he expects and I don't know about you, but it was so profound for me because it jolts you out of reality. It's like, oh my God, what am I doing here? I'm just going with the flow with my society. How do I think outside the box in the confines of my society, which surely carries negative things with it that we don't realize today. </s>