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> |
End of preview. Expand
in Dataset Viewer.
Intro
This dataset(1K) formats an existing podcast dataset (64bits/lex_fridman_podcast_for_llm_vicuna) for llama 3 chat model fine tuning. It represents a compilation of audio-to-text transcripts from the Lex Fridman Podcast. The Lex Fridman Podcast, hosted by AI researcher at MIT, Lex Fridman.
Problems
There might be some minor issues during the transcribe phase.
Next Step
Use whisper to directly load the podcast and transcribe it in this format.
- Downloads last month
- 2