安德烈·卡帕西：特斯拉 AI、自動駕駛、Optimus、外星人與 AGI

Lex Fridman Podcast #333 – Andrej Karpathy: Tesla AI, Self-Driving, Optimus, Aliens, and AGI Machine transcription by Qwen3-ASR 0.6B (MLX, local, Apache-2.0). May contain recognition errors. The following is a conversation with Andre Capati, previously the director of AI at Tesla, and before that at Open AI and Stanford. He is one of the greatest scientists, engineers, and educators in the history of artificial intelligence. And now a quick few second mention of each sponsor. Check them out in the description. It's the best way to support this podcast. We got A Sleep for naps, BetterHelp for mental health, Fundrise for real estate investing, and Athletic Greens for nutrition. Choose wisely, my friends. And now on to the full ad reads. As always, no ads in the middle. I try to make this interesting, but if you skip them, please still check out our sponsors. I enjoy their stuff, maybe you will too. This episode is sponsored by A Sleep and its new Pod Three mattress. I am recording this in a hotel. In fact, given some complexities of my life, this is the middle of the night four a.m. I am sitting in an empty hotel room yelling at a microphone. This my friends, is my life. I do usually feel good about myself at four a.m. But not with two cups of coffee in me. And the reason I feel good is because I am going to go to sleep soon, and I've accomplished a lot. This is true today, except for the sleep soon part because I think I am going to an airport at some point soon. It doesn't matter. What matters is I am not even going to sleep here. And that's great because in a hotel I don't have an A Sleep bed that can cool itself. At home I do, and that's where I am headed. I am headed home. Anyway, check it out and get special savings when you go to a sleep dot com slash lex. This episode is also brought to you by BetterHelp spelled H E L P Help. I am a huge fan of talk therapy. I think of podcasting as a kind of talk therapy, so I am a huge fan of listening to podcasts. In fact, that's how I think of doing a podcast myself. I just get to have front row seats to the thing I love. And it's actually just the process of talking that reveals something about the mind. I think that's what good talk therapy is is guided by a professional therapist. It helps you reveal to yourself something about your mind. Just lay it all out on the table. So yeah, you should definitely use the best method of talk therapy, the best meaning the most accessible. At least to try it if not to make it a regular part of your life. That's what BetterHelp does. Check them out at BetterHelp dot com slash lex and save on your first month. This episode is also brought to you by Fundrise spelled F U N D R I S E. It's a platform that allows you to invest in private real estate. We live in hard times, folks, for many different reasons, but one of them is financial. And one way to protect yourself in difficult times is to diversify your investments. Private real estate is one of the things I believe you should diversify into. And when you do, you should use tools that look like they're made in the twenty-first century, which a lot of investment even like online. Investment websites and services seem to be designed by the same people that design the original ATMs. That's not the case with Fundrise. Super easy to use, accessible over one hundred fifty thousand investors use it. Their team vets and manages all their real estate projects. You can track your portfolio's performance on their website and see updates as properties across the country are acquired, improved, and operated. Anyway, check out Fundrise. It takes just a few minutes to get started at Fundrise dot com slash lex. This show is brought to you by Athletic Greens and it's AG One Drink, which is an all in one daily drink to support better health and peak performance. I have to be honest, I completely forgot to bring Athletic Greens with me as I am traveling now, and I miss it. It's not just good for my nutritional base and needs. It's good for my soul. It's part of the sort of the daily habit of life, and when you don't have that habit, the routine stuff is off. So it's good to just put that into your daily routine to make sure that you are getting the vitamins, the nutrition that you need, no matter the dietary, the workload, the athletic endeavors that you partaken. I don't know, it's kind of incredible, and yeah, that's what Athletic Greens is for me. They'll give you one month supply of fish oil when you sign up at Athletic Greens dot com slash lex. This is the lex Friedman podcast. To support it, please check out our sponsors. And now, dear friends, here is Andre Capati. What is a neural network, and why does it seem to do such a surprisingly good job of learning? What is a neural network? It's a mathematical abstraction of the brain. I would say that's how it was originally developed. At the end of the day, it's a mathematical expression and it's a fairly simple mathematical expression when you get down to it. It's basically a sequence of matrix multiplies, which everly dot products mathematically, and some nonlinearities thrown in, and so it's a very simple mathematical expression and it's got knobs in it. Many knobs, many knobs, and these knobs are loosely related to basically the synapses in your brain. They're trainable, they're modifiable, and so the idea is like we need to find the setting of the knobs that makes the neural net do whatever you wanted to do like classify images and so on. And so there is not too much mystery. I would say in it like you might think that basically don't want to indulge with too much meaning with respect to the brain and how it works. It's really just a complicated mathematical expression with knobs and those knobs need a proper setting for it to do something desirable. Yeah, but poetry is just a collection of letters with spaces, but it can make us feel a certain way, and in that same way when you get a large number of knobs together whether it's in a inside the brain or inside a computer they seem to. They seem to surprise us with with their power. Yeah, I think that's fair. So basically, I am underselling it by a lot because you definitely do get very surprising emergent behaviors out of these neural nets when they're large enough and trained on complicated enough problems like say for example the next word prediction in a massive data set from the internet. And then these neural nets take on pretty surprising magical properties. Yeah, I think it's kind of interesting how much you can get out of even very simple mathematical formalism. When your brain right now is talking, is it doing next word prediction, or is it doing something more interesting? Well, it's definitely some kind of a generative model that's a GPT like and prompted by you. Yes, so you are giving me a prompt and I am kind of like responding to it in a generative way. And by yourself, perhaps a little bit like are you adding extra prompts from your own memory inside your head. Well, definitely feels like you are referencing some kind of a declarative structure of like memory and so on, and then. You are putting that together with your prompt and giving away some. How much of what you just said has been said by you before? Nothing basically right. No, but if you actually look at all the words you've ever said in your life and you do a search, you'll probably said a lot of the same words in the same order before. Yeah, could be. I mean, I am using phrases that are common, etc. But I am remixing it into a pretty sort of unique sentence at the end of the day. But you are right, definitely. There is like a ton of remixing. Why you didn't you? It's like Magnus Carlson said, "I am rated twenty nine hundred whatever, which is pretty decent." I think you are talking very you are not giving enough credit to neural nets here. Why do they seem to? What's your best intuition about this emergent behavior? I mean, it's kind of interesting because I am simultaneously underselling them, but I also feel like there is an element to which I am over like it's actually kind of incredible that you can get so much emergent magical behavior out of them despite them being so simple mathematically. So I think those are kind of like two surprising statements that are kind of juxtaposed together. And I think basically what it is is we are actually fairly good at optimizing these neural nets, and when you give them a hard enough problem, they are forced to learn very interesting solutions in the optimization, and those solution basically have these emergent properties that are very interesting. There is wisdom and knowledge in the knobs, and so this representation that's in the knobs. Does it make sense to you intuitively? The large number of knobs can hold a representation that captures some deep wisdom about the data it has looked at. It's a lot of knobs. It's a lot of knobs, and somehow you know so speaking concretely, one of the neural nets that people are very excited about right now are are GPTs, which are basically just next word prediction networks. So you consume a sequence of words from the internet and you try to predict the next word. And once you train these on a large enough data set, they you can basically prompt these neural nets in arbitrary ways and you can ask them to solve problems and they will. So you can just tell them you can you can make it look like you are trying to solve some kind of a mathematical problem and they will continue what they think is the solution based on what they've seen on the internet and very often those solutions look very remarkably consistent, look correct potentially. Do you still think about the brain side of it? So as neural nets is an abstraction or mathematical abstraction of the brain, do you still draw wisdom from from the biological neural networks or even the bigger question? So you are big fan of biology and biological computation. What impressive thing is biology doing to you? The computers are not yet that gap. I would say I am definitely on I am much more hesitant with the analogies to the brain than I think you would see potentially in the field. And I kind of feel like certainly the way neural networks started is everything stemmed from inspiration of the brain, but at the end of the day the artifacts that you get after training they are arrived at by a very different optimization process than the optimization process that gave rise to the brain. And so I think I kind of think of it as a very complicated alien artifact. It's something different. Sorry, the the neural nets that we're training. Okay, they are complicated alien artifact. I do not make analogies to the brain because I think the optimization process that gave rise to it is very different from the brain. So there was no multi agent self play kind of setup, and evolution. It was an optimization that is basically a what amounts to a compression objective on a massive amount of data. Okay, so artificial neural networks are doing compression, and biological neural networks are not to survive and are not really doing anything. They're they're an agent in a multi agent self play system that's been running for a very very long time. That said, evolution has found that it is very useful to to predict and have a predictive model in the brain, and so I think our brain utilizes something that looks like that as a part of it, but it has a lot more you know gadgets and gizmos and value functions and ancient nuclei that are all trying to like make you survive and reproduce and everything else and the whole thing through embryogenesis is built from a single cell. I mean it's just the code is inside the DNA and it just builds it up like the entire organism. It's totally crazy. Head and legs, yes, and like it does it pretty well. It may not be possible, so there is some learning going on. There is some, there is some, there is some kind of computation going through that building process. I mean, I don't know where. If you were just to look at the entirety of history of life on Earth, where do you think is the most interesting invention? Is it the origin of life itself? Is it just jumping to eukaryotes? Is it mammals? Is it humans themselves Homo sapiens? The the origin of intelligence or highly complex intelligence? Or is it all just a continuation of the same kind of process? Certainly, I would say it's an extremely remarkable story that I am only like briefly learning about recently. All the way from actually like you almost have to start at the formation of Earth and all of its conditions and the entire solar system and how everything is arranged with Jupiter and Moon and the habitable zone and everything, and then you have an active Earth. That's turning over material, and and then you start with a biogenesis and everything. So it's all like a pretty remarkable story. I am not sure that I can pick like a single unique piece of it that I find most interesting. I guess for me as an artificial intelligence researcher, it's probably the last piece. We have lots of animals that you know are are not building technological society, but we do, and it seems to have happened very quickly. It seems to have happened very recently, and something very interesting happened there that I don't fully understand. I almost understand everything else kind of I think intuitively, but I don't understand exactly that part and how quick it was. Both explanations would be interesting. One is that this is just a continuation of the same kind of process. There is nothing special about humans. That would be deeply understanding that would be very interesting. That we think of ourselves as special, but it was obvious all it was already written in in the code that you would have. Greater and greater intelligence emerging, and then the other explanation which is something truly special happened something like a rare event, whether it's like crazy rare event like a space Odyssey. What would it be? See if you say like the invention of fire. Or the as Richard Rangham says, the beta males deciding a clever way to kill the alpha males by collaborating and so just optimizing the collaboration the really the multi agent aspect of the multi agent and that really being constrained on resources and trying to survive. The collaboration aspect is what created the complex intelligence, but it seems like it's a natural outgrowth of the evolution process. Like what what could possibly be a magical thing that happened like a rare thing that would say that humans are actually human level intelligence is actually a really rare thing in the universe. Yeah, I am hesitant to say that it is rare. By the way, but it definitely seems like it's kind of like a punctuated equilibrium where you have lots of exploration and then you have certain leaps sparse leaps in between. So of course, like origin of life would be one you know DNA, sex, eukaryotic system, eukaryotic life, the endosymbiosis event where the Archean ate little bacteria, you know just the whole thing and then of course emergence of consciousness and so on. So it seems like definitely there are sparse events where massive amount of progress was made, but yeah, it's kind of hard to pick one. So you don't think humans are unique? Got to ask you, how many intelligent alien civilizations do you think are out there, and is their intelligence different or similar to ours? Yeah, I've been preoccupied with this question quite a bit recently. Basically, the Fermi paradox and just thinking through, and and the reason actually that I am very interested in the origin of life is fundamentally trying to understand how common it is that there are technological societies out there. In space, and the more I study it, the more I think that there should be quite a few, quite a lot. Why haven't we heard from them? Because I agree with you, it feels like I just don't see why what we did here on Earth is so difficult to do. Yeah, and especially when you get into the details of it, I used to think origin of life was very. It was this magical rare event, but then you read books like for example Nick Lane, The Vital Question, Life Ascending, etc. And he really gets in and he really makes you believe that this is not that rare. Basic chemistry. You have an active Earth and you have your alkaline vents and you have lots of alkaline waters mixing with the sea ocean and you have your proton gradients and you have the little porous pockets of these alkaline vents that concentrate chemistry. And basically, as he steps through all of these little pieces, you start to understand that actually this is not that crazy. You could see this happen on other systems, and he really takes you from just a geology to primitive life, and he makes it feel like it's actually pretty plausible. And also like the origin of life didn't was actually fairly fast after formation of Earth. If I remember correctly, just a few hundred million years or something like that after basically when it was possible life actually arose, and so that makes me feel like that is not the constraint that is not the limiting variable and that life should actually be fairly common. And then you know where the drop-offs are is very is very interesting to think about. I currently think that there is no major drop-offs basically, and so there should be quite a lot of life. And basically, what it where that brings me to then is the only way to reconcile the fact that we haven't found anyone and so on is that we just can't we can't see them, we can't observe them. Just a quick brief comment: Nick Lane and a lot of biologists I talk to, they really seem to think that the jump from bacteria to more complex organisms is the hardest jump. The eukaryotic life, basically, yeah, which I don't I get it they're much more knowledgeable than me about like the intricacies of biology, but that seems like crazy because how much how many single cell organisms are there, like and how much time you have. Surely it's not that difficult. Like in a billion years, it's not even that long. Of a time really, just all these bacteria under constrained resources battling it out. I am sure they can invent more complex. Like I don't understand, it's like how to move from a hello world program to like like invent a function or something like that. I don't. Yeah, so I don't. Yeah, so I am with you. I just feel like I don't see any. If the origin of life, that would be my intuition. That's the hardest thing, but if that's not the hardest thing because it happened so quickly, then it's got to be everywhere. And yeah, maybe we're just too dumb to see it. Well, it's just we don't have really good mechanisms for seeing this life. I mean, by what how? So I am not an expert just to preface this, but just from what I think about it. Who's I want to meet an expert on alien intelligence and how to communicate? I am very suspicious of our ability to to find these intelligences out there and to find these Earth like radio waves for example are are terrible. Their power drops off as basically one over r squared. So I remember reading that. Our current radio waves would not be the ones that we are broadcasting would not be measurable by our devices today. Only like was it like one tenth of a year away like not even basically tiny distance because you really need like a targeted transmission of massive power directed somewhere for this to be picked up on long long distances and so I just think that our ability to measure is is not amazing I think there's probably other civilizations out there and then the big question is why don't they build nanomim probes and why don't they interstellar travel across the entire galaxy and my current answer is it's probably interstellar travel is like really hard you have the interstellar medium if you want to move at close to the speed of light you're going to be encountering bullets along the way because even like tiny hydrogen atoms and little particles of dust are basically have like massive kinetic energy at those speeds and so basically you need some kind of shielding you need you have all the cosmic radiation it's just like brutal out there it's really hard and so my thinking is maybe interstellar travel is just extremely hard and you have billions of years to build hard it feels like it feels like we're not a billion years away from doing that it just might be that it's very you have to go very slowly potentially as an example through space right as opposed to close to the speed of light so I'm suspicious basically of our ability to measure life and I'm suspicious of the ability to just permeate all of space in the galaxy or across galaxies and that's the only way that I can I can currently see a way around it yeah it's kind of mind blowing to think that there is trillions of intelligent alien civilizations out there kind of slowly traveling through space to meet each other and some of them meet some of them go to war some of them collaborate or they're all just independent they are all just like little pockets I don't know well statistically if there's like if it's there's trillions of them surely some of them some of the pockets are close enough together some of them happen to be close yeah in close enough to see each other and then once you see once you see something that is definitely complex life like if we see something yeah we're probably going to be severe like intensely aggressively motivated to figure out what the hell that is and try to meet them what would be your first instinct to to try to like at a generational level meet them or defend against them or what would be your instinct as a president of the United States and a scientist I don't know which hat you prefer in this question yeah I think the the question it's really hard I will say like for example for us we have lots of primitive life forms on Earth next to us we have all kinds of ants and everything else and we share space with them and we are hesitant to impact on them and to we are we're trying to protect them by default because they are amazing interesting dynamical systems that took a long time to evolve and they are interesting and special and I don't know that you want to destroy that by default and so I like complex dynamical systems that took a lot of time to evolve I think I'd like to I'd like to preserve it if I can afford to and I'd like to think that the same would be true about the galactic resources and that they would think that we're kind of incredible interesting story that took time it took a few billion years to unravel and you don't want to just destroy it I could see two aliens talking about Earth right now and saying I'm I'm a big fan of complex dynamical systems so I think it it was a value to preserve these and it basically are a video game they watch or show a TV show that they watch yeah I think you would need like a very good reason I think to to destroy it like why don't we destroy these ant farms and so on it's because we're not actually like really in direct competition with them right now we do it accidentally and so on but there's plenty of resources and so why would you destroy something that is so interesting and precious well from a scientific perspective you might probe it you might interact with it lately you might want to learn something from it right so I wonder there's could be certain physical phenomena that we think is a physical phenomenon but it's actually interacting with us to like poke the finger and see what happens I think it should be very interesting to scientists other alien scientists what happened here um and you know it's a what we're seeing today is a snapshot basically it's a it's a result of a huge amount of computation of over like billion years or something like that so it could have been initiated by aliens this could be a computer running a program like when okay if you had the power to do this when you okay for sure at least I would I would pick a Earth-like planet that has the conditions based my understanding of the chemistry prerequisites for life and I would seed it with life and run it right like yeah wouldn't you 100 percent do that and observe it and then protect I mean that that's not just a hell of a good TV show it's it's a good scientific experiment yeah and that it is it's physical simulation right maybe maybe the evolution is the most like actually running it is the most efficient way to understand computation or to compute stuff or to understand life or you know what life looks like and what branches it can take it does make me kind of feel weird that we're part of a science experiment but maybe it's everything's a science experiment inside does that change anything for us for a science experiment I don't know two descendants of apes talking about being inside of a science I'm suspicious of this idea of like a deliberate panspermia as you described it sort of I don't see a divine intervention in some way in the in the historical record right now I do feel like the story in these in these books like Nick Lane's books and so on sort of makes sense and it makes sense how life arose on Earth uniquely and yeah I don't need a I need I don't need to reach for more exotic explanations right now sure but NPCs inside a video game don't don't observe any divine intervention either and we might just be all NPCs running a kind of code maybe eventually they will currently NPCs are really dumb but once they're running GPTs maybe they will be like hey this is really suspicious what the hell so you famously tweeted it looks like if you bombard Earth with photons for a while it can emit a rooster so if like in hitchhiker's guide to the galaxy we would summarize the story of Earth so in in that book it's mostly harmless what do you think is all the possible stories like a paragraph long or sentence long that Earth could be summarized as once it's done its computation so like all the possible full if Earth is a book right yeah probably there has to be an ending I mean there's going to be an end to Earth and it could end in all kinds of ways it can end soon it can end later what do you think are the possible stories well definitely there seems to be yeah you're sort of it's pretty incredible that these self replicating systems will basically arise from the dynamics and then they perpetuate themselves and become more complex and eventually become conscious and build a society and I kind of feel like in some sense it's kind of like a deterministic wave that you know that kind of just like happens on any you know any sufficiently well arranged system like Earth and so I kind of feel like there's a certain sense of inevitability in it and it's really beautiful and it ends somehow right so it's a it's a chemically a diverse environment where complex dynamical systems can evolve and become more more further and further complex but then there's a certain um what is it there's certain terminating conditions yeah I don't know what terminating conditions are but definitely there's a trend line of something and we're part of that story and like where does that where does it go so you know we're famously described often as a biological bootloader for AI's and that's because humans I mean you know we're an incredible biological system and we're capable of computation and you know and love and so on but we're extremely inefficient as well like we're talking to each other through audio it's just kind of embarrassing honestly that we're manipulating like seven symbols serially we're using vocal chords it's all happening over like multiple seconds it's just like kind of embarrassing when you step down to the frequencies at which computers operate or are able to operate on and so basically it does seem like synthetic intelligences are kind of like the next stage of development and I don't know where it leads to like at some point I suspect the universe is some kind of a puzzle and these synthetic AI's will uncover that puzzle and solve it and then what happens after right like what because if you just like fast forward Earth many billions of years it's like it's it's quiet and then it's like turmoil you see like city lights and stuff like that and then what happens at like at the end like is it like a it's it or is it like a calming is it explosion is it like Earth like open like a giant because you said emit roosters like will it start emitting like like a giant number of like satellites yeah it's some kind of a crazy explosion and we're living we're like we're stepping through a explosion and we're like living day to day and it doesn't look like it but it's actually if you I saw a very cool animation of Earth and life on Earth and basically nothing happens for a long time and then the last like two seconds like basically cities and everything and the lower orbit just gets cluttered and just the whole thing happens in the last two seconds and you're like this is exploding this is state of explosion so if you play yeah yeah if you play at a normal speed yeah it will just look like an explosion it's a firecracker we're living in a firecracker where it's going to start emitting all kinds of interesting things yeah and then so explosion doesn't it might actually look like a little explosion with with lights and fire and energy emitted all that kind of stuff but when you look inside the details of the explosion there's actual complexity happening where there's like yeah human life or some kind of life we hope it's not a destructive firecracker it's kind of like a constructive firecracker all right so given that I think hilarious this guy it is really interesting to think about like what the puzzle of the universe is did the creator of the universe give us a message like for example in the book contact Carl Sagan there's a message for humanity for any civilization in digits in the expansion of pi in base 11 eventually which is kind of interesting thought maybe maybe we're supposed to be giving a message to our creator maybe we're supposed to somehow create some kind of a quantum mechanical system that alerts them to our intelligent presence here because if you think about it from their perspective it's just say like quantum field theory massive like scalar tachyon like thing and like how do you even notice that we exist you might not even be able to pick us up in that simulation and so how do you how do you prove that you exist that you're intelligent and that you're part of the universe so this is like a Turing test for intelligence from Earth like the creator is I mean maybe this is like trying to complete the next word in a sentence this is a complicated way of that like Earth is just is basically sending a message back yeah the puzzle is basically like alerting the creator that we exist or maybe the puzzle is just to just break out of the system and just you know stick it to the creator in some way basically like if you're playing a video game you can you can somehow find an exploit and find a way to execute on the host machine any arbitrary code there's some for example I believe someone got a Mario a game of Mario to play pong just by exploiting it and then creating a basically writing writing code and being able to execute arbitrary code in the game and so maybe we should be maybe that's the puzzle is that we should be find a way to exploit it so so I think like some of these synthetic AI's will eventually find the universe to be some kind of a puzzle and then solve it in some way and that's kind of like the end game somehow do you often think about it as a as a simulation so as or the universe being a kind of computation that has might have bugs and exploits yes yeah I think so is that what physics is essentially I think it's possible that physics has exploits and we should be trying to find them arranging some kind of a crazy quantum mechanical system that somehow gives you buffer overflow somehow gives you rounding error in the floating point yeah that's right and like more and more sophisticated exploits like those are jokes but that could be actually very close yeah we'll find some way to extract infinite energy for example when you train reinforcement learning agents in physical simulations and you ask them to say run quickly on the flat ground they'll end up doing all kinds of like weird things in part of that optimization right they'll get on their back leg and they'll slide across the floor and it's because the optimization the reinforcement learning optimization on that agent has figured out a way to extract infinite energy from the friction forces and basically their poor implementation and they found a way to generate infinite energy and just slide across the surface and it's not what you expected it's just a it's sort of like a perverse solution and so maybe we can find something like that maybe we can be that little dog in this physical simulation the the cracks or escapes the intended consequences of the physics that the universe came up with we'll figure out some kind of shortcut to some weirdness yeah and then but see the problem with that weirdness is the first person to discover the weirdness like sliding on the back legs that's all we're going to do yeah it very quickly becomes everybody does that thing so like the the paperclip maximizer is a ridiculous idea but that very well could be what then we'll just we'll just all switch that because it's so fun well no person will discover it I think by the way I think it's going to have to be a some kind of a super intelligent AGI of a third generation like we're building the first generation AGI you know third generation yeah so the the bootloader for an AI that AI will be a bootloader for another AI yeah and then there's no way for us to introspect like what that might even I think it's very likely that these things for example like so you have these AGIs it's very likely for example they will be completely inert I like these kinds of sci-fi books sometimes where these things that are just completely inert they don't interact with anything and I find that kind of beautiful because they probably they've probably figured out the meta game of the universe in some way potentially they're they're doing something completely beyond our imagination and they don't interact with simple chemical life forms like why would you do that so I find those kinds of ideas compelling what's their source of fun what are they what are they doing what's the source of pleasure solving in the universe but inert so can you define what it means inert so they escape the interaction with us as in they will behave in some very like strange way to us because they're they're beyond they're playing the meta game and the meta game is probably say like arranging quantum mechanical systems in some very weird ways to extract infinite energy solve the digital expansion of pi to whatever amount they will build their own like little fusion reactors or something crazy like they're doing something beyond comprehension and not understandable to us and actually brilliant under the hood what if quantum mechanics itself is the system and we're just thinking it's physics but we're really parasites on on or not parasite we're not really hurting physics we're just living on this organism's this organism and we're like trying to understand it but really it is an organism and with a deep deep intelligence maybe physics itself is the the the organism that's doing the super interesting thing and we're just like one little thing yeah ant sitting on top of it trying to get energy from it we're just kind of like these particles in a wave that I feel like is mostly deterministic and takes universe from some kind of a big bang to some kind of a super intelligent replicator some kind of a stable point in the universe given these laws of physics you don't think as Einstein said God doesn't play dice so you you think it's mostly deterministic there's no randomness in the thing I think is deterministic oh there's tons of well I'm I'm I want to be careful with randomness pseudo random yeah I don't like random I think maybe the laws of physics are deterministic yeah I think they're deterministic you just got really uncomfortable with this question do you have anxiety about whether the universe is random or not this is a source what's there's no randomness it's you say you like goodwill hunting it's not your fault Andre it's not your fault man um so you don't like randomness yeah I think it's unsettling I think it's a deterministic system I think that things that look random like say the collapse of the wave function etc I think they're actually deterministic just entanglement and so on and some kind of a multiverse theory something something okay so why does it feel like we have a free will like if if I raise the hand I chose to do this now what that doesn't feel like a deterministic thing it feels like I'm making a choice it feels like it okay so it's all feelings it's just feelings yeah so when RL agent is making a choice is that um it's not really making a choice the choices are all already there yeah you're interpreting the choice and you're creating a narrative for for having made it yeah and now we're talking about the narrative it's very meta looking back what is the most beautiful or surprising idea in deep learning or AI in general that you've come across you've seen this field explode and grow in interesting ways just what what cool ideas like like we made you sit back and go small big or small well the one that I've been thinking about recently the most probably is the the transformer architecture so basically neural networks have a lot of architectures that were trendy have come and gone for different sensory modalities like for vision audio text you would process them with different looking neural nets and recently we've seen this this convergence towards one architecture the transformer and you can feed it video or you can feed it you know images or speech or text and it just gobbles it up and it's kind of like a bit of a general purpose computer that is also trainable and very efficient to run on our hardware and so this paper came out in 2016 I want to say attention is all you need attention is all you need you criticize the paper title in retrospect that it wasn't it didn't foresee the bigness of the impact that it was going to have yeah I'm not sure if the authors were aware of the impact that that paper would go on to have probably they weren't but I think they were aware of some of the motivations and design decisions behind the transformer and they chose not to I think expand on it in that way in a paper and so I think they had an idea that there was more than just the surface of just like oh we're just doing translation and here's a better architecture you're not just doing translation this is like a really cool differentiable optimizable efficient computer that you've proposed and maybe they didn't have all of that foresight but I think it's really interesting isn't it funny sorry to interrupt that that title is memeable that they went for such a profound idea. They went with a. I don't think anyone used that kind of title before, right? Attention is all you need. Yeah, it's like a meme or something. Yeah, it's not funny that one. Like maybe if it was a more serious title, it wouldn't have the impact. Honestly, I yeah there is an element of me that honestly agrees with you and prefers it this way. Yes. If it was too grand, it would over promise and then under deliver potentially. So you want to just meme your way to greatness. That should be a T-shirt. So you you tweeted the transformer is a magnificent neural network architecture because it is a general purpose differentiable computer. It is simultaneously expressive in the forward pass, optimizable via back propagation gradient descent and efficient high parallelism compute