Jeff Hawkins: Thousand Brains Theory of Intelligence

Jeff Hawkins is the founder of Redwood Center for Theoretical Neuroscience in 2002 and Numenta in 2005. In his 2004 book titled On Intelligence, and in his research before and after, he and his team have worked to reverse-engineer the neocortex and propose artificial intelligence architectures, approaches, and ideas that are inspired by the human brain. These ideas include Hierarchical Temporal Memory (HTM) from 2004 and The Thousand Brains Theory of Intelligence from 2017. If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter https://twitter.com/lexfridman, LinkedIn https://www.linkedin.com/in/lexfridman/, Facebook https://www.facebook.com/lexfridman, Medium https://medium.com/@lexfridman, or YouTube https://www.youtube.com/lexfridman where you can watch the video versions of these conversations.

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Lex Fridman?

  The following is a conversation with Jeff Hawkins. He's the founder of the Redwood Center for Theoretical Neuroscience in 2002 and Newmenta in 2005. In his 2004 book titled On Intelligence and in the research before and after, he and his team have worked to reverse engineer the neural cortex and propose artificial intelligence architectures, approaches, and ideas that are inspired by the human brain. These ideas include hierarchical temporal memory, HTM, from 2004, and new work, the thousands' brain's theory of intelligence, from 2017, 18, and 19. Jeff's ideas have been an inspiration to many who have looked for progress beyond the current machine learning approaches, but they have also received criticism for lacking

• 0:43Lex Fridman?

  a body of empirical evidence supporting the models. This is always a challenge when seeking more than small incremental steps forward in AI. Jeff is a brilliant mind, and many of the ideas he has developed and aggregated from neuroscience are worth understanding and thinking about. There are limits to deep learning as it is currently defined. Forward progress in AI is shrouded in a mystery. My hope is that conversations like this can help provide an inspiring spark for new ideas. This is the Artificial Intelligence Podcast. If you enjoy it, subscribe on YouTube, iTunes, or simply connect with me on Twitter at LexFriedman, spelled F-R-I-D. And now, here's my conversation with Jeff Hawkins.

• 1:43Lex Fridman?

  Are you more interested in understanding the human brain or in creating artificial systems that have many of the same qualities but don't necessarily require that you actually understand the underpinning workings of our mind?

• 1:57Speaker 01

  So, there's a clear answer to that question. My primary interest is understanding the human brain. No question about it. But...

• 2:06Speaker 01

  I also firmly believe that we will not be able to create fully intelligent machines until we understand how the human brain works. So I don't see those as separate problems. I think there's limits to what can be done with machine intelligence if you don't understand the principles by which the brain works. And so I actually believe that studying the brain is actually the fastest way to get to machine intelligence.

• 2:27Lex Fridman?

  And within that, let me ask the impossible question. How do you not define, but at least think about what it means to be intelligent?

• 2:35Speaker 01

  So I didn't try to answer that question first. We said, let's just talk about how the brain works and let's figure out how certain parts of the brain, mostly the neocortex, but some other parts too, the parts of the brain most associated with intelligence, and let's discover the principles by how they work. Because intelligence isn't just like some mechanism and it's not just some capabilities. It's like, okay, we don't even know where to begin on this stuff. And so now that we've made a lot of progress on this, after we've made a lot of progress on how the neocortex works, and we can talk about that, I now have a very good idea what's going to be required to make intelligent machines. I can tell you today, you know, some of the things are going to be necessary, I believe, to create intelligent machines.

• 3:19Lex Fridman?

  Well, so we'll get there. We'll get to the neocortex and some of the theories of how the whole thing works. And you're saying, as we understand more and more about the neocortex, about our own human mind, we'll be able to start to more specifically define what it means to be intelligent. It's not useful to really talk about that until...

• 3:38Speaker 01

  I don't know if it's not useful. Look, there's a long history of AI, as you know. And there's been different approaches taken to it. And who knows, maybe they're all useful. Right? So, you know, the good old fashioned AI, the expert systems, the current convolution neural networks, they all have their utility. They all have a value in the world, but I would think almost everyone agree that none of them are really intelligent in a sort of a deep way that humans are. And so it's just the question of how do you get from where those systems were or are today to where a lot of people think we're gonna go? And there's a big, big gap there, a huge gap. And I think the quickest way of bridging that gap

• 4:22Speaker 01

  is to figure out how the brain does that. And then we can sit back and look and say, oh, what's are these principles that the brain works on are necessary? And which ones are not? Clearly, we don't have to build this and telepath machines aren't gonna be built out of, you know, organic, living cells. But there's a lot of stuff that goes on the brain that's gonna be necessary.

• 4:42Lex Fridman?

  So let me ask maybe, before we get into the fun details, let me ask maybe a depressing or a difficult question. Do you think it's possible that we will never be able to understand how our brain works? That maybe there's aspects to the human mind, like we ourselves cannot introspectively get to the core? That there's a wall you eventually hit?

• 5:04Speaker 01

  Yeah, I don't believe that's the case. I have never believed that's the case. There's not have been a single thing we've ever, humans have ever put their minds to, that we've said, oh, we reached the wall. We can't go any further. People keep saying that. People used to believe that about life, you know? The lan vital, right? There's like, what's the difference between living matter and non-living matter? Something special, but you never understand. We no longer think that. So there's no historical evidence that suggests it's the case. And I just never even consider that's a possibility. I would also say, today, we understand so much about the near cortex. We've made tremendous progress in the last few years that I no longer think of it as an open question. The answers are very clear to me.

• 5:48Speaker 01

  And the pieces we know, we don't know are clear to me, but the framework is all there. And it's like, oh, okay, we're gonna be able to do this. This is not a problem anymore. It just takes time and effort. But there's no mystery, a big mystery anymore.

• 6:00Lex Fridman?

  So then let's get into it for people like myself who are not.

• 6:06Lex Fridman?

  Very well versed in the human brain, except my own. Can you describe to me at the highest level, what are the different parts of the human brain and then zooming in on the neocortex, the parts of the neocortex and so on, a quick overview?

• 6:21Speaker 01

  Yeah, sure. The human brain, we can divide it roughly into two parts. There's the old parts, lots of pieces, and then there's a new part. The new part is the neocortex. It's new because it didn't exist before mammals. The only mammals have a neocortex and in humans, in primates, it's very large. In the human brain, the neocortex occupies about 70 to 75% of the volume of the brain. It's huge. And the old parts of the brain are, there's lots of pieces there. There's the spinal cord and there's the brainstem and the cerebellum and the different parts of the basal ganglia and so on. In the old parts of the brain, you have autonomic regulation, like breathing and heart rate. You have basic behaviors, so like walking and running are controlled by the old parts

• 7:06Speaker 01

  of the brain. All the emotional centers of the brain are in the old part of the brain. So when you feel anger or hungry, lust or things like that, those are all in the old parts of the brain.

• 7:15Speaker 01

  And, and we associate with the neocortex, all the things we think about as sort of high level perception and cognitive functions, anything from seeing and hearing and touching things to language, to mathematics and engineering and science and so on. Those are all associated with the neocortex and they're certainly correlated. Our abilities in those regards are correlated with the relative size of our neocortex compared to other mammals. So that's like the rough division and you obviously can't understand the neocortex completely isolated, but you can understand a lot of it with just a few interfaces to the old parts of the brain. And so it, it gives you a system to study.

• 8:01Speaker 01

  The other remarkable thing about the neocortex compared to the old parts of the brain is the neocortex is extremely uniform. It's not visually or anatomically or it's very, it's like a, I always like to say, it's like the size of a dinner napkin, about two and a half millimeters thick. And it looks remarkably the same everywhere. Everywhere you look in that two and a half millimeters is this detailed architecture. And it looks remarkably the same everywhere. And that's across species, the mouse versus a cat and a dog and a human. Where if you look at the old parts of the brain, there's lots of little pieces do specific things. So it's like the old parts of our brain evolved like this is the part that controls heart rate and this is the part that controls this and this is this kind of thing and that's this kind of thing.

• 8:43Speaker 01

  And these evolved for eons, a long, long time, and they have their specific functions. And all of a sudden mammals come along and they got this thing called the neocortex. And it got large by just replicating the same thing over and over and over again. This is like, wow, this is incredible. So all the evidence we have, and this is an idea that was first articulated in a very cogent and beautiful argument by a guy named Vernon Malkesel in 1978, I think it was, that the neocortex all works on the same principle. So language, hearing, touch, vision, engineering, all these things are basically underlying or all built in the same computational substrate. They're really all the same problem.

• 9:28Lex Fridman?

  So at the low level, the building blocks all look similar.

• 9:30Speaker 01

  Yeah, and they're not even that low level. We're not talking about like neurons. We're talking about this very complex circuit that exists throughout the neocortex is remarkably similar. It is, it's like, yes, you see variations of it here and there, more of this cell, less and less, so on. But what Malkesel argued was, he says, you know, if you take a section of neocortex, why is one a visual area and one is an auditory area? Or why is, and his answer was, it's because one is connected to eyes and one is connected to ears.

• 10:01Lex Fridman?

  Literally, you mean just it's most closest in terms of number of connections to the sensor?

• 10:07Speaker 01

  Literally, if you took the optic nerve and attached it to a different part of the neocortex, that part would become a visual region. This actually, this experiment was actually done by Mergronka Sir.

• 10:17Lex Fridman?

  Oh, boy.

• 10:18Speaker 01

  In, in developing, I think it was lemurs, I can't remember what it was, some animal. And, and there's a lot of evidence to this. You know, if you take a blind person, a person who's born blind at birth, they, they're born with a visual neocortex. It doesn't, may not get any input from the eyes because of some congenital defect or something. And That region does something else. It picks up another task. So it's this very complex thing. It's not like, oh, they're all built on neurons. No, they're all built in this very complex circuit. And somehow, that circuit underlies everything. And so this is the... It's called the Common Cortical Algorithm, if you will.

• 11:02Speaker 01

  Some scientists just find it hard to believe. And they just say, I can't believe that's true. But the evidence is overwhelming in this case. And so a large part of what it means to figure out how the brain creates intelligence and what is intelligence in the brain is to understand what that circuit does. If you can figure out what that circuit does, as amazing as it is, then you can... Then you understand what all these other cognitive functions are.

• 11:26Lex Fridman?

  So if you were to sort of put neurocortex outside of your book on intelligence, if you wrote a giant tome, a textbook on the neurocortex, and you look maybe a couple centuries from now, how much of what we know now would still be accurate two centuries from now? So how close are we in terms of understanding?

• 11:46Speaker 01

  So I have to speak from my own particular experience here. So I run a small research lab here. It's like any other research lab. I'm the sort of the principal investigator. There's actually two of us and there's a bunch of other people. And this is what we do. We study the neurocortex and we publish our results and so on. So about three years ago, we had a real breakthrough in this field. It's a tremendous breakthrough. We've now published, I think, three papers on it. And so I have a pretty good understanding of all the pieces and what we're missing. I would say that almost all the empirical data we've collected about the brain, which is enormous, if you don't know the neuroscience literature, it's just incredibly...

• 12:29Speaker 01

  Big. And it's, it's for the most part, all correct. It's facts and, and experimental results and measurements and all kinds of stuff. But it, none, none of that has been really assimilated into a theoretical framework.

• 12:43Lex Fridman?

  Right.

• 12:44Speaker 01

  It's, it's data without, it's in the, in the language of Thomas Kuhn, the historian, would be a sort of a pre-paradigm science. Lots of data, but no way to fit it in together. I think almost all of that's correct. There's gonna be some mistakes in there. And for the most part, there aren't really good cogent theories about it, how to put it together. It's not like we have two or three competing good theories, which ones are right and which ones are wrong. It's like, nah, people are just like scratching their heads, throwing things, you know, some people have given up on trying to like figure out what the whole thing does. In fact, there's very, very few labs that we, that we do that focus really on theory and all this unassimilated data and trying to explain it. So it's not like we have, we've got it wrong. It's just that we haven't got it at all.

• 13:27Lex Fridman?

  So it's really, I would say, pretty early days in terms of understanding the fundamental theories, forces of the way our mind works.

• 13:36Speaker 01

  I don't think so. That, I would have said that's true five years ago. So, as I said, we had some really big breakthroughs on this recently, and we started publishing papers on this, so.

• 13:47Lex Fridman?

  So we'll get, we'll get to the.

• 13:50Speaker 01

  But, so I don't think it's, I, you know, I'm, I'm an optimist, and from where I sit today, most people would disagree with this, but from where I sit today, from what I know, it's not super early days anymore. We are, it's, it's, you know, the way these things go is it's not a linear path, right? You don't just start accumulating and get better and better and better. No, you got all this stuff you've collected, none of it makes sense, all these different things are just sort of around, and then you're gonna have some breaking points, all of a sudden, oh my God, now we got it right. That's how it goes in science. And I, I personally feel like we passed that little thing about a couple of years ago. All that big thing a couple of years ago. So we can talk about that. Time will tell if I'm right, but I feel very confident about it. That's why I'm willing to say it on tape like this.

• 14:31Lex Fridman?

  At least very optimistic. So let's, before those few years ago, let's take a step back to HTM, the Hierarchical Temporal Memory Theory, which you first proposed on Intelligence and went through a few different generations. Can you describe what it is, how it evolved through the three generations since you first put it on paper?

• 14:51Speaker 01

  Yeah, so one of the things that neuroscientists just sort of missed for many, many years, and especially people who were thinking about theory, was the nature of time in the brain. Brains process information through time. The information coming into the brain is constantly changing. The patterns from my speech right now, if you're listening to it at normal speed, would be changing on your ears about every 10 milliseconds or so, you'd have a change. This constant flow. When you look at the world, your eyes are moving constantly, three to five times a second, and the input's changing completely. If I were to touch something like a coffee cup, as I move my fingers, the input changes.

• 15:31Speaker 01

  So this idea that the brain works on time-changing patterns is almost completely, or was almost completely, missing from a lot of the basic theories like fears of vision and so on. It's like, oh, no, we're going to put this image in front of you and flash it and say, what is it? Convolutional neural networks work that way today, right? Classify this picture. But that's not what vision's like. Vision is this sort of crazy time-based pattern that's going all over the place, and so is touch and so is hearing. So the first part of hierarchical temporal memory was the temporal part. It's to say, you won't understand the brain nor you understand intelligent machines unless you're dealing with time-based patterns. The second thing was, the memory component of it was, is to say that we aren't just

• 16:15Speaker 01

  processing input, we learn a model of the world. And the memory stands for that model. We have to, the point of the brain, the point of the neocortex, it learns a model of the world. We have to store things, our experiences in a form that leads to a model of the world. So we can move around the world, we can pick things up and do things, navigate, know how it's going on. So that's, that's what the memory referred to. And many people just, they were thinking about like, certain processes without memory at all. They're just like processing things. And then finally, the hierarchical component was a reflection to, that the neocortex, although it's this uniform sheet of cells, different parts of it project to other parts which project

• 16:54Speaker 01

  to other parts. And there is a sort of a rough hierarchy in terms of that. So the hierarchical temporal memory is just saying, look, we should be thinking about the brain as time-based, you know, model memory-based and hierarchical processing. And, and that was a placeholder for a bunch of components that we would then plug into that. We still believe all those things I just said, but we now know so much more that I'm stopping to use the word hierarchical temporal memory yet because it's insufficient to capture the stuff we know. So again, it's not incorrect, but it's, I now know more and I would rather describe it more accurately.

• 17:33Lex Fridman?

  Yeah. So you're basically, we could think of HTM as emphasizing that there's three aspects of intelligence that are important to think about, whatever the, whatever the eventual theory converges to.

• 17:44Speaker 01

  Yeah.

• 17:45Lex Fridman?

  So in terms of time, how do you think of nature of time across different time scales? You mentioned things changing, sensory inputs changing every 10, what about every few minutes, every few months and years?

• 17:58Speaker 01

  Well, if you think about a neuroscience problem, the brain problem, neurons themselves can stay active for certain periods of time. There are parts of the brain where they stay active for minutes, you know, so you could hold a certain perception or activity for a certain period of time, but not, most of them don't last that long. And so if you think about your thoughts or the activity of neurons, if you're going to want to involve something that happened a long time ago, even Just this morning, for example, the neurons haven't been active throughout that time. So you have to store that. So if I ask you, what did you have for breakfast today? That is memory. That is, you've built it into your model of the world now. You remember that.

• 18:41Speaker 01

  And that memory is in the, in the synapses, is basically in the formation of synapses. And so it's, you're sliding into what, you know, you said different time scales. There's time scales on which we are like, understanding my language and moving about and seeing things rapidly over time. That's the time scales of activities of neurons. But if you want to get in longer time scales, then it's more memory. And we have to invoke those memories to say, oh, yes, well, now I can remember what I had for breakfast because I stored that someplace. I may forget it tomorrow, but I'd stored for now.

• 19:14Lex Fridman?

  So does memory also need to have?

• 19:19Lex Fridman?

  So the hierarchical aspect of reality is not just about concepts. It's also about time. Do you think of it that way?

• 19:26Speaker 01

  Uh, yeah, time is infused in everything. It's like, you really can't separate it out. If I ask you, what is the, what is your, you know, how's the brain learn a model of this coffee cup here? I have a coffee cup, an American coffee cup. I say, well, time is not an inherent property of this, of this, of the model I have of this cup, whether it's a visual model or tactile model. I can sense it through time, but the model itself doesn't really have much time. If I asked you, if I said, well, what is the model of my cellphone? My brain has learned a model of the cellphones. If you have a smartphone like this. And I said, well, this has time aspects to it. I have expectations when I turn it on, what's going to happen, what, what are, how long it's going to take to do certain things. If I bring up an app, what sequences.

• 20:10Speaker 01

  And so I have, and it's like melodies in the world, you know, melody has a sense of time. So many things in the world move and act, and there's a sense of time related to them. Some don't, but most things do actually. So it's sort of infused throughout the models of the world. You build a model of the world, you're learning the structure of the objects in the world, and you're also learning how those things change through time.

• 20:37Lex Fridman?

  Okay, so it's, it really is just the fourth dimension that's infused deeply. And you have to make sure that your models of intelligence incorporate it.

• 20:49Lex Fridman?

  Like you mentioned, the state of neuroscience is deeply empirical. A lot of data collection. It's a, you know, that's, that's where it is. You mentioned Thomas Kuhn, right?

• 20:59Speaker 01

  Yeah.

• 21:01Lex Fridman?

  And then you're proposing a theory of intelligence and which is really the next step, the really important step to take. But why, why is HTM or what we'll talk about soon, the right theory? So is it more in this, is it backed by intuition? Is it backed by evidence? Is it backed by a mixture of both? Is it kind of closer to where string theory is in physics? Where there's mathematical components which show that, you know what? It seems that this, it fits together too well for it not to be true, which is what where string theory is. Is that where?

• 21:45Speaker 01

  It's a mixture of all those things, although definitely where we are right now, it's definitely much more on the empirical side than let's say, string theory. The way this goes about, we're theorists, right? So we look at all this data and we're trying to come up with some sort of model that explains it, basically. And there's, unlike string theory, there's this vast more amounts of empirical data here that I think than most physicists deal with. And so our challenge is to sort through that and figure out what kind of constructs would explain this. And when we have an idea, you come up with a theory of some sort, you have lots of ways of testing it.

• 22:25Speaker 01

  First of all, I am, you know, there are a hundred years of assimilated, unassimilated empirical data from neuroscience. So we go back and read papers and we say, oh, well, did someone find this already? We can predict X, Y, and Z. And maybe no one's even talked about it since 1972 or something, but we go back and find that and we say, oh, either it can support the theory or it can invalidate the theory. And we say, okay, we have to start over again. Oh, no, it's supportive. Let's keep going with that one. So the way I kind of view it, when we do our work. We come up, we, we look at all this empirical data and it's, it's what I call it as a set of constraints. We're not interested in something that's biologically inspired. We're trying to figure out how the actual brain works.

• 23:08Speaker 01

  So every piece of empirical data is a constraint on a theory. In theory, if you have the correct theory, it needs to explain every pin, right? So we have this huge number of constraints on the problem, which initially makes it very, very difficult. If you don't have many constraints, you can make up stuff all the day. You can say, oh, here's an answer on how you can do this, you can do that, you can do this. But if you consider all biology as a set of constraints, all neuroscience as a set of constraints, and even if you're working in one little part of the neurocorps, for example, there are hundreds and hundreds of constraints, these are empirical constraints, that it's very, very difficult initially to come up with a theoretical framework for that. But when you do, and it solves all those constraints at once, you have a high confidence that you got something close to correct.

• 23:52Speaker 01

  It's just mathematically almost impossible not to be. So that's the, the curse and the advantage of what we have. The, the curse is we have to solve, we have to meet all these constraints, which is really hard. But when you do meet them, then you have a great confidence that you've discovered something. In addition, then we work with scientific labs. So we'll say, oh, there's something we can't find, we can predict something, but we can't find it anywhere in the literature. So we will then, we have people we collaborated with will say, sometimes they'll say, you know what, I have some collected data, which I didn't publish, but we can go back and look at it and see if we can find that, which is much easier than designing a new experiment. You know, neuroscience experiments take a long time, years.

• 24:36Speaker 01

  So although some people are doing that now too. So, but between all of these things, I think it's a reasonable, it's actually a very, very good approach. We, we are blessed with the fact that we can test our theories out to yin yang here because there's so much unassimilated data. And we can also falsify our theories very easily, which we do often.

• 24:57Lex Fridman?

  It's kind of reminiscent to whenever that was with Copernicus. You know, when you figure out that the sun is at the center of the solar system as opposed to Earth, the pieces just fall into place.

• 25:11Speaker 01

  Yeah, I think that's the general nature of aha moments. And it's Copernicus, it could be, you could say the same thing about Darwin. You could say the same thing about, you know, about the double helix. That people have been working on a problem for so long and have all this data and they can't make sense of it, they can't make sense of it. But when the answer comes to you and everything falls into place, it's like, oh my gosh, that's it. That's got to be right. I asked both Jim Watson and Francis Crick about this. I asked them, you know, when you were working on trying to discover the structure of the double helix, and when you came up with the sort of, the structure that ended up being

• 25:56Speaker 01

  correct, but it was sort of a guess, you know, it wasn't really verified yet, I said, did you know that it was right? And they both said, absolutely. Said, we absolutely knew it was right. And it doesn't matter if other people didn't believe it or not, we knew it was right, they'd get around to thinking and agree with it eventually, anyway. And that's the kind of thing you hear a lot with scientists who really are studying a difficult problem. And I feel that way too about our work.

• 26:23Lex Fridman?

  Have you talked to Crick or Watson about the problem you're trying to solve, of finding the DNA of the brain?

• 26:32Speaker 01

  Yeah. In fact, Francis Crick was very interested in this in the latter part of his life. And in fact, I got interested in brains by reading an essay he wrote in 1979 called Thinking About the Brain. And that was when I decided I'm going to leave my profession of computers and engineering and become a neuroscientist, just reading that one essay from Francis Crick. I got to meet him later in life. I spoke at the Salk Institute and he was in the audience and then I had a tea with him afterwards. You know, he was interested in a different problem. He was focused on consciousness.

• 27:08Lex Fridman?

  The easy problem, right?

• 27:12Speaker 01

  I think it's the red herring and so we weren't really overlapping a lot there. Jim Watson, who's still alive, is also interested in this problem and he was, when he was director of the Colsping Harvard Laboratories, he was really sort of behind moving in the direction of neuroscience there. And so he had a personal interest in this field. And I have met with him numerous times. And in fact, the last time was a little bit over a year ago, I gave a talk at Colsping Harvard Labs about the progress we were making in our work. And it

• 27:53Speaker 01

  was a lot of fun because he said, well, you wouldn't be coming here unless you had something important to say, so I'm going to go attend your talk. So he sat in the very front row. Next in was the director of the lab, Bruce Stillman. So these guys are in the front row of this auditorium, right? So nobody else in the auditorium wants to sit in the front row because there's Jim Watson and there's the director. And I gave a talk and I had dinner with Jim afterwards. But there's a great picture of my colleague, Soubhata Madhuk, where I'm up there sort of screaming the basics of this new framework we have. And Jim Watson's on the edge of his chair. He's literally on the edge of his chair, like intently staring up at the screen. And when he discovered the structure of DNA, the first

• 28:38Speaker 01

  public talk he gave was at Colsping Harvard Labs. And there's a picture, there's a famous picture of Jim Watson standing at the whiteboard with an overhead thing, pointing at something, holding a double helix with his pointer. And it actually looks a lot like the picture of me. So there was sort of funny, there's Ari, I'm talking about the brain, and there's Jim Watson staring intently at it. And of course, there with, you know, whatever, 60 years earlier, he was standing, you know, pointing at the double helix.

• 29:00Lex Fridman?

  It's one of the great discoveries in all of, you know, whatever, biologists, science, all science with DNA. It's funny that there's echoes of that in your presentation.

• 29:10Speaker 01

  Yeah.

• 29:11Lex Fridman?

  Do you think in terms of evolutionary timeline in history, the development of the neocortex was a big leap? Or is it just a small step? So like if we ran the whole thing over again, from the birth of life on Earth, how likely would we develop the mechanism of the neocortex?

• 29:31Speaker 01

  Okay, well, those are two separate questions. One, was it a big leap? And one was how likely it is. Okay. They're not necessarily related.

• 29:39Lex Fridman?

  Maybe correlated.

• 29:40Speaker 01

  Maybe correlated, maybe not. And we don't really have enough data to make a judgment about that. I would say definitely it was a big leap. And I can tell you why. I think, I don't think it was just another incremental step. I'll get that in a moment. I don't really have any idea how likely it is. If we look at evolution, we have one data point, which is Earth. Right? Life formed on Earth billions of years ago. Whether it was introduced here or it created here, or someone introduced it, we don't really know. But it was here early. It took a long, long time to get to multicellular life. And then for multicellular life, it took a long, long time to get the neocortex. And we've only had the neocortex for a few hundred thousand years. So that's like nothing. Okay.

• 30:24Speaker 01

  So is it likely? Well, certainly isn't something that happened right away on Earth. And there were multiple steps to get there. So I would say it's probably not something that would happen instantaneously on other planets that might have life. It might take several billion years on average. Is it likely? I don't know. But you'd have to survive for several billion years to find out. Probably. Is it a big leap? Yeah, I think it's, it is a qualitative difference than all other evolutionary steps. I can try to describe that if you'd like.

• 30:56Lex Fridman?

  Sure, in which way?

• 30:58Speaker 01

  Yeah, I can tell you how. Pretty much. Let's start with a little preface. Many of the things that humans are able to do do not have obvious survival advantages precedent. You know, we create music. Is that, is there a really survival advantage to that? Maybe, maybe not. What about mathematics? Is there a real survival advantage to mathematics? You can stretch, you can try to figure these things out, right? But up, but mostly evolutionary history, everything had immediate survival advantages to it. So I'll tell you a story, which I like, may, may not be true.

• 31:41Speaker 01

  But the story goes as follows. Organisms have been evolving for, since the beginning of life here on Earth. And adding this sort of complexity onto that, and this sort of complexity onto that. And the brain itself is evolved this way. In fact, there's an old parts and older parts and older, older parts of the brain that kind of just keeps coming on new things and we keep adding capabilities. And we got to the neocortex. Initially, it had a very clear survival advantage in that it produced better vision and better hearing and better touch and maybe so on. But what, what I think happens is that evolution discovered, took, took a mechanism, and this is in our recent theories, but it took a mechanism evolved a long time ago for navigating in the world, for knowing where you are.

• 32:26Speaker 01

  These are the so-called grid cells and place cells of an old part of the brain. And it, it took that mechanism for building maps of the world and knowing where you are on those maps and how to navigate those maps, and turns it into a sort of a slimmed down, idealized version of it. And that idealized version could now apply to building maps of other things. Maps of coffee cups, and maps of phones, maps of, you know, mathematics. Concepts, almost. Concepts, yes. And not just almost, exactly. And, and so you, and it just started replicating this stuff, right? You're just thinking more and more and more. And so we went from being sort of dedicated purpose neural hardware to solve certain

• 33:07Speaker 01

  problems that are important to survival, to a general purpose neural hardware that could be applied to all problems. And now it's, it's escaped the orbit of survival. It's, we are now able to apply it to things which we find enjoyment. You know, but aren't really clearly survival characteristics. And that it seems to only have happened in humans to the large extent. And so that's what's going on where we sort of have. We've sort of escaped the gravity of evolutionary pressure in some sense in the near cortex. And it now does things which not that are really interesting, discovering models of the universe, which may not really help us.

• 33:52Speaker 01

  It doesn't matter. How does it help us surviving, knowing that there might be multiverses? Or not, there might be, you know, the age of the universe or how do, you know, various stellar things occur? It doesn't really help us survive at all, but we enjoy it. And that's what happened.

• 34:06Lex Fridman?

  Or at least not in the obvious way. Perhaps it is required. If you look at the entire universe in an evolutionary way, it's required for us to do interplanetary travel and therefore survive past our own sun. But you know what? Let's not get too.

• 34:20Speaker 01

  Yeah, but you know, evolution, it works at one timeframe. It's survival. If you think of survival of the phenotype, survival of the individual.

• 34:29Lex Fridman?

  Exactly.

• 34:29Speaker 01

  It that what you're talking about there is spans well beyond that. So there's no genetic. I'm not transferring any genetic traits to my children that are going to help them survive better on Mars.

• 34:42Lex Fridman?

  Right. Totally different mechanism. That's right. So let's get into the new, as you've mentioned, this idea, the, I don't know if you have a nice name, thousand.

• 34:51Speaker 01

  We call it the thousand brain theory of intelligence.

• 34:53Lex Fridman?

  I like it. So can you, can you talk about the, the, this idea of spatial view of concepts and so on?

• 35:00Speaker 01

  Yeah. So can I just describe sort of the, there's an underlying core discovery, which then everything comes from that. It's a very simple. This is really what happened. We were deep into problems about understanding how we build models of stuff in the world and how we make predictions about things. And I was holding a coffee cup just like this in my hand. And I had my finger was touching the side, my index finger. And then I moved it to the top. And I was gonna feel the rim at the top of the cup. And I asked myself a very simple question. I said, well, first of all, let's say, I know that my brain predicts what it's gonna feel before it touches it. You can just think about it and imagine it. And so we know that the brain's making predictions all the time.

• 35:44Speaker 01

  So the question is, what does it take to predict that? Right? And there's a very interesting answer. First of all, it says, the brain has to know it's touching a coffee cup. It has to have a model of a coffee cup. It needs to know where the finger currently is on the cup, relative to the cup. Because when I make a movement, it needs to know where it's going to be on the cup after the movement is completed, relative to the cup. And then it can make a prediction about what it's gonna sense. So this told me that the neocortex, which is making this prediction, needs to know that it's sensing it's touching a cup. And it needs to know the location of my finger relative to that cup, in a reference frame of the cup. It doesn't matter where the cup is relative to my body. It doesn't matter its orientation. None of that matters. It's where my finger is relative to the cup.

• 36:27Speaker 01

  Which tells me then that the neocortex is, has a reference frame that's anchored to the cup. Because otherwise, I wouldn't be able to say the location, and I wouldn't be able to predict my new location. And then we quickly, very instantly, you can say, well, every part of my skin could touch this cup. And therefore, every part of my skin's making predictions. And every part of my skin must have a reference frame that it's using to make predictions. So, the big idea is that throughout the neocortex, there are, everything is being stored and referenced in reference frames. You can think of them like X, Y, Z reference frames, but they're not like that. We know a lot about the neural mechanisms for this. But the brain thinks in reference frames.

• 37:11Speaker 01

  And as an engineer, if you're an engineer, this is not surprising. You'd say, if I wanted to build a CAD model of the coffee cup, well, I would bring it up in some CAD software, and I would assign some reference frame, and say, this features at this locations, and so on. But the fact that this, the idea that this is occurring throughout the neocortex, everywhere. It was a novel idea. And then a zillion things fell into place after that, a zillion. So now, we think about the neocortex as processing information quite differently than we used to do it. We used to think about the neocortex as processing sensory data and extracting features from that sensory data, and then extracting features from the features, very much like a deep learning network does today. But that's not how the brain works at all.

• 37:53Speaker 01

  The brain works by assigning everything, every input, everything, to reference frames, and there are thousands, hundreds, thousands of them active at once in your neocortex. It's a surprising thing to think about, but once you sort of internalize this, you understand that it explains almost every, all the, almost all the mysteries we've had about this, about this structure. So, one of the consequences of that is that every small part of the neocortex, say a millimeter square, and there's 150,000 of those, so it's about 150,000 square millimeters. If you take every little square millimeter of the cortex, it's got some input coming into it, and it's gonna have reference frames where it's assigned that input to. And each square millimeter can learn complete models of objects. So, what do I mean by that?

• 38:38Speaker 01

  If I'm touching the coffee cup, well, if I just touch it in one place, I can't learn what this coffee cup is, because I'm just feeling one part. But if I move it around the cup, and touch it at different areas, I can build up a complete model of the cup, because I'm now filling in that three-dimensional map, which is the coffee cup. I can say, oh, what am I feeling at all these different locations? That's the basic idea, it's more complicated than that. But, so through time, and we talked about time earlier, through time, even a single column, which is only looking at, or a single part of the cortex, which is only looking at a small part of the world, can build up a complete model of an object. And so, if you think about the part of the brain which is getting input from all my fingers, so there's, they're spread across the top of your head here, this is the somatosensory cortex, there's columns associated of all the different areas of my skin.

• 39:23Speaker 01

  And what we believe is happening is that all of them are building models of this cup, every one of them. Or things, not they're not all building, not every column or every part of the cortex builds models of everything, but they're all building models of something. And so you have, so when I, when I touch this cup with my hand, there are multiple models of the cup being invoked. If I look at it with my eyes, there are again, many models of the cup being invoked because each part of the visual system, the brain doesn't process an image. That's, that's a misleading idea. It's just like your fingers touching the cup. So different parts of my retina are looking at different parts of the cup. And thousands and thousands of models of the cup are being invoked at once. And they're all voting with each other, trying to figure out what's going on.

• 40:06Speaker 01

  So that's why we call it the thousand brains theory of intelligence, because there isn't one model of a cup. There are thousands of models of this cup. There are thousands of models of your cell phone and about cameras and microphones and so on. It's a distributed modeling system, which is very different than the way people have thought about it.

• 40:21Lex Fridman?

  So that's a really compelling and interesting idea. I have two first questions. So one, on the ensemble part of everything coming together, you have these thousand brains. How, how do you know which one has done the best job of forming?

• 40:35Speaker 01

  Great question. Let me try to explain. There's a problem that's known in neuroscience called the sensor fusion problem.

• 40:41Lex Fridman?

  Yes.

• 40:42Speaker 01

  And so the idea is there's something like, oh, the image comes from the eye. There's a picture on the retina and it gets projected to the neocortex. Oh, by now it's all spat out all over the place and it's kind of squirrely and distorted and pieces are all over the, you know, it doesn't look like a picture anymore. When does it all come back together again? Right? Or you might say, well, yes, but I also, I also have sounds or touches associated with the cup. So I'm seeing the cup and touching the cup. How do they get combined together again? So this is called the sensor fusion problem, as if all these disparate parts have to be brought together into one model someplace. That's the wrong idea. The right idea is that you got all these guys voting. There's auditory models of the cup, there's visual models of the cup, there's tactile models of the cup.

• 41:25Speaker 01

  There are one, in the vision system, there might be ones that are more focused on black and white, ones focusing on color. It doesn't really matter. There's just thousands and thousands of models of this cup. And they vote. They don't actually come together in one spot. Just literally think of it this way. Imagine you have these columns are like about the size of a little piece of spaghetti. Okay. Like a two and a half millimeters tall and about a millimeter in wide. They're not physical like, but you can think of them that way. And each one's trying to guess what this thing is they're touching. Now, they can, they can do a pretty good job if they're allowed to move. Over touched, so I can reach my hand into a black box and move my finger around an object and if I touch enough spaces, I go, "Okay, now I know what it is." But often, we don't do that. Often, I can just reach and grab something with my hand all at once, and I get it. Or if I had to look through the world through a straw, so

• 42:10Speaker 01

  I'm only invoking one little column, I can only see a part of something because I have to move the straw around, but if I open my eyes, I see the whole thing at once. So what we think is going on is all these little pieces of spaghetti, if you will, all these little columns in the cortex are all trying to guess what it is that they're sensing. They'll do a better guess if they have time and can move over time, so if I move my eyes, I move my fingers. But if they don't, they have a poor guess. It's a probabilistic guess of what they might be touching. Now imagine they can post their probability at the top of a little piece of spaghetti. Each one of them says, "I think," and it's not really a probability distribution, it's more like a set of possibilities. In the brain, it doesn't work as a probability distribution, it works as more like what we call a union. So you could say, and one column says, "I think it could be a coffee cup, a soda can,

• 42:55Speaker 01

  or a water bottle." And another column says, "I think it could be a coffee cup, or a telephone, or a camera," whatever, right? And all these guys are saying what they think it might be. And there's these long-range connections in certain layers in the cortex. So there's some layers in some cell types in each column send their projections across the brain, and that's the voting occurs. And so there's a simple associative memory mechanism, we've described this in a recent paper, and we've modeled this, that says they can all quickly settle on the only, or the one best answer for all of them. If there is a single best answer, they all vote and say, "Yep, it's gotta be the coffee cup." And at that point, they all know it's a coffee cup. And at that point, everyone acts as if it's the coffee

• 43:39Speaker 01

  cup. "Yep, we know it's a coffee," even though I've only seen one little piece of this world, I know it's a coffee cup I'm touching, or I'm seeing, or whatever. And so you can think of all these columns are looking at different parts, in different places, different sensory input, different locations, they're all different. But this layer that's doing the voting, that's, it solidifies. It's just like, it crystallizes and says, "Oh, we all know what we're doing." And so you don't bring these models together in one model, you just vote, and there's a crystallization of the vote.

• 44:05Lex Fridman?

  Great. That's at least a compelling way to think about.

• 44:10Lex Fridman?

  About the way you form a model of the world. Now, you talk about a coffee cup. Do you see this, as far as I understand, you are proposing this as well, that this extends to much more than coffee cups?

• 44:23Speaker 01

  Yeah.

• 44:25Speaker 01

  It does.

• 44:25Lex Fridman?

  Or at least the physical world. It expands to the world of concepts.

• 44:30Speaker 01

  Yeah, it does. And well, first, the prima facie evidence for that is that the regions of the neocortex that are associated with language or high-level thought or mathematics or things like that, they look like the regions of the neocortex that process vision, hearing and touch. They don't look any different. Or they look only marginally different. And so one would say, well, if Vernon Mountcastle, who proposed that all the parts of the neocortex are doing the same thing, if he's right, then the parts that are doing language or mathematics or physics are working on the same principle. They must be working on the principle of reference frames. So that's a little odd thought. So hmm. But of course, we had no prior idea how these things happen. So let's go with that.

• 45:13Speaker 01

  And we, in our recent paper, we talked a little bit about that. I've been working on it more since. I have better ideas about it now. I'm sitting here, I'm very confident that that's what's happening. And I can give you some examples to help you think about that. It's not we understand it completely, but I understand it better than I've described it in any paper so far. So, but we did put that idea out there. It says, okay, this is, it's a good place to start, you know? And the evidence would suggest it's how it's happening. And then we can start tackling that problem one piece at a time. Like, what does it mean to do high-level thought? What does it mean to do language? How would that fit into a reference framework?

• 45:50Lex Fridman?

  Yeah, so there's a, I don't know if you could tell me if there's a connection, but there's an app called Anki that helps you remember different concepts. And they talk about like a memory palace that helps you remember completely random concepts by trying to put them in a physical space in your mind and putting them next to each other.

• 46:09Speaker 01

  It's called the method of Loki.

• 46:10Lex Fridman?

  Loki, yeah. For some reason, that seems to work really well.

• 46:13Speaker 01

  Yeah.

• 46:14Lex Fridman?

  Now, that's a very narrow kind of application of just remembering some facts.

• 46:17Speaker 01

  But that's a very, very telling one.

• 46:19Lex Fridman?

  Yes, exactly. So this seems like you're describing a mechanism why this seems to work.

• 46:25Speaker 01

  So basically, the way, what we think is going on is all things you know, all concepts, all ideas, words, everything you know, are stored in reference frames. And, and so if you want to remember something, you have to basically navigate through a reference frame, the same way a rat navigates to a maze, and the same way my finger navigates to this coffee cup. You're moving through some space. And so if you have a random list of things you would ask to remember, by assigning them to a reference frame, you already know very well, let's say your house. Right, and the idea of the method of loci is you can say, "Okay, in my lobby, I'm going to put this thing, and then, and then the bedroom, I put this one. I go down the hall, I put this thing." And then you want to recall those facts, or recall those things, you just walk, mentally, you walk through your house.

• 47:10Speaker 01

  You're mentally moving through a reference frame that you already had. And that tells you, there's two things that are really important about that. It tells us the brain prefers to store things in reference frames, and that the method of recalling things, or thinking, if you will, is to move mentally through those reference frames. You could move physically through some reference frames, like I could physically move through the reference frame of this coffee cup. I can also mentally move through the reference frame of the coffee cup, imagining me touching it. But I can also mentally move my house. And, and so now we can ask ourselves, "Are all concepts stored this way?" There was some recent research using human subjects in fMRI, and I'm going to apologize for not knowing the name of the scientist who did this.

• 47:53Speaker 01

  But what they did is they, they put humans in this fMRI machine, which was one of these imaging machines. And they, they gave the humans tasks to think about birds. So they had different types of birds, and birds that looked big and small, and long legs, and long legs, things like that. And what they could tell from the fMRI, was a very clever experiment. You could tell when humans were thinking about the birds, that the birds, that the, the knowledge of birds was arranged in a reference frame, similar to the, the ones that are used when you navigate in a room. That, these are called grid cells, and there, there are grid cell-like patterns of activity in the neocortex when they do this. So that it's a very clever experiment, you know. And what it basically says that even when you're thinking about something abstract and you're

• 48:38Speaker 01

  not really thinking about it as a reference frame, it tells us the brain is actually using a reference frame and it's using the same neural mechanisms. These grid cells are the basic same neural mechanisms that we we propose that grid cells, which exist in the in the old part of the brain, the anteroinic cortex, that that mechanism is now similar mechanism is used throughout the near cortex. It's the same nature preserve this interesting way of creating reference frames. And so now they have empirical evidence that when you think about concepts like birds, that you're using reference frames that are built on grid cells. So that's that's similar to the method of loci, but in this case, the birds are related. So that makes they create their own reference frame, which is consistent with bird space. And when you think about something, you go through that, you I you can make the same example, let's take a math mathematics, right?

• 49:23Speaker 01

  Let's say you want to prove a conjecture. Okay, what is a conjecture? A conjecture is a statement you believe to be true, but you haven't proven it. And so it might be an equation. I want to show that this is equal to that. And you have a point, you have some places you start with. You say, well, I know this is true and I know this is true. And I think that maybe to get to the final proof, I need to go through some intermediate results. What I believe is happening is literally these equations or these points are assigned to a reference frame, a mathematical reference frame. And when you do mathematical operations, a simple one might be multiply or divide, but you might be a Laplace transform or something else. That is like a movement in the reference frame of of the math.

• 50:04Speaker 01

  And so you're literally trying to discover a path from one location to another location in a space of mathematics. And if you can get to these intermediate results, then you know your map is pretty good and you know you're using the right operations. Much of what we think about is solving hard problems is designing the correct reference frame for that problem, figuring out how to organize the information and what behaviors I want to use in that space to get me there.

• 50:32Lex Fridman?

  Yeah, so if you dig in on the idea of this reference frame, whether it's the math, you start a set of axioms to try to get to proving the conjecture. Can you try to describe, maybe taking a step back, how you think of the reference frame in that context? Is it the reference frame that the axioms are happy in? Is it the reference frame that might contain everything? Is it a changing thing?

• 50:56Speaker 01

  You have many, many reference frames. In fact, the way the theory, the thousand brain theory of intelligence says that every single thing in the world has its own reference frame. So every word has its own reference frames. And we can talk about this. The mathematics work out, this is no problem for neurons to do this.

• 51:12Lex Fridman?

  But how many reference frames does a coffee cup have? It's on a table.

• 51:16Speaker 01

  Let's say, you ask, how many reference frames could the column in my finger that's touching the coffee cup have? Because there are many, many, there are many, many models of the coffee cup. So the coffee, there is no model of a coffee cup. There are many models of a coffee cup. And you could say, well, how many different things can my finger learn? Is this the question you want to ask? Imagine, I say, every concept, every idea, everything you've ever know about that you can say, I know that thing, has a reference frame associated with it. And what we do when we build composite objects, we assign reference frames to point another reference frame. So my coffee cup has multiple components to it. It's got a limb, it's got a cylinder, it's got a handle. And those things have their own reference frames, and they're assigned to a master reference

• 52:01Speaker 01

  frame, which is called this cup. And now I have this numenta logo on it. Well, that's something that exists elsewhere in the world. It's its own thing, so it has its own reference frame. So we now have to say, how can I assign the numenta logo reference frame onto the cylinder or onto the coffee cup? So it's all, we talked about this in the paper that came out in December of this last year. The idea of how you can assign reference frames to reference frames, how neurons could do this.

• 52:27Lex Fridman?

  So, well, my question is, even though you mention reference frames a lot, I almost feel it's really useful to dig into how you think of what a reference frame is. I mean, it was already helpful for me to understand that you think of reference frames as something there is a lot of.

• 52:42Speaker 01

  Okay, so, let's just say that we're gonna have some neurons in the brain, not many actually, 10,000, 20,000 are gonna create a whole bunch of reference frames. What does it mean? What is a reference frame? First of all, these reference frames are different than the ones you might be used to. We know lots of reference frames. For example, we know the Cartesian coordinates, X, Y, Z, that's a type of reference frame. We know longitude and latitude, that's a different type of reference frame. If I look at a printed map, it might have columns A through M and rows, you know, 1 through 20, that's a different type of reference frame. It's a kind of a Cartesian coordinate reference frame. The interesting thing about the reference frames in the brain, and we know this because

• 53:24Speaker 01

  these have been established through neuroscience studying the entorhino cortex. So I'm not speculating here, okay? This is known neuroscience in an old part of the brain. The way these cells create reference frames, they have no origin. So, what it's more like, you have a point, a point in some space, and you, given a particular movement, you can then tell what the next point should be. And you can then tell what the next point would be, and so on. You can use this to calculate how to get from one point to another. So how do I get from my house to my home? Or how do I get my finger from the side of my cup to the top of the cup? How do I get from the axioms to the conjecture?

• 54:09Speaker 01

  So it's a different type of reference frame? And I can, if you want, I can describe in more detail, I can paint a picture, how you might wanna think about that.

• 54:16Lex Fridman?

  It's really helpful to think, it's something you can move through.

• 54:18Speaker 01

  Yeah.

• 54:19Lex Fridman?

  But is it helpful to think of it as spatial in some sense? Or is there something that's more...

• 54:26Speaker 01

  No, it's definitely spatial. It's spatial in a mathematical sense.

• 54:30Lex Fridman?

  How many dimensions? Can it be crazy number of dimensions?

• 54:32Speaker 01

  Well, that's an interesting question. In the old part of the brain, the entorhino cortex... They studied rats. And initially, it looks like, oh, this is just two dimensional. It's like the rat is in some box in the maze or whatever. And they know where the rat is using these two dimensional reference frames to know where it is in the maze. We said, OK, but what about bats? That's a mammal, and they fly in three dimensional space. How do they do that? They seem to know where they are, right? So this is a current area of active research. And it seems like somehow the neurons in the entorhino cortex can learn three dimensional space. We just, two members of our team, along with Yila Fett from MIT, just released a paper this, literally last week.

• 55:16Speaker 01

  It's on BioArchive, where they show that you can, if you, the way these things work, and I won't get, unless you want to, I won't get into the detail. But grid cells can represent any n-dimensional space. It's not inherently limited. You can think of it this way. If you had two dimensional, the way it works is you had a bunch of two dimensional slices. That's the way these things work. There's a whole bunch of two dimensional models. And you can just, you can slice up any n-dimensional space with two dimensional projections. So, and you could have one dimensional models. So there's nothing inherent about the mathematics about the way the neurons do this, which constrain the dimensionality of the space, which I think was important. So obviously, I have a three dimensional map of this cup.

• 56:00Speaker 01

  Maybe it's even more than that, I don't know. But it's a clearly three dimensional map of the cup. I don't just have a projection of the cup. But when I think about birds, or when I think about mathematics, perhaps it's more than three dimensions. Who knows?

• 56:12Lex Fridman?

  So in terms of each individual column building up more and more information over time, do you think that mechanism is well understood? In your mind, you've proposed a lot of architectures there. Is that a key piece? Or is it, is the big piece, the thousand brain theory of intelligence, the ensemble of it all?

• 56:33Speaker 01

  Well, I think they're both big. I mean, clearly, the concept, as a theorist, the concept is most exciting. Right?

• 56:39Lex Fridman?

  A high level of concept.

• 56:40Speaker 01

  A high level of concept. This is a totally new way of thinking about how the neocortex works. So that is appealing. It has all these ramifications. And with that, as a framework for how the brain works, you can make all kinds of predictions and solve all kinds of problems. Now, we're trying to work through many of these details right now. Okay, how do the neurons actually do this? Well, it turns out, if you think about grid cells and place cells in the old parts of the brain, there's a lot that's known about them, but there's still some mysteries. There's a lot of debate about exactly the details, how these work and what are the signs. And we have that still, that same level of detail, that same level of concern. What we spend here, most of our time doing, is trying to make a very good list of the things we don't understand yet. That's the key part here. What are the constraints? It's not like, oh, this thing seems to work, we're done. No, it's like, okay, it kind of works,

• 57:25Speaker 01

  but these are other things we know it has to do, and it's not doing those yet. I would say we're well on the way here. We're not done yet. There's a lot of trickiness to this system, but the basic principles about how different layers in the neocortex are doing much of this, we understand. But there's some fundamental parts that we don't understand as well.

• 57:46Lex Fridman?

  So what would you say is one of the harder open problems? Or one of the ones that have been bothering you?

• 57:52Speaker 01

  Oh.

• 57:53Lex Fridman?

  Keeping you up at night the most?

• 57:54Speaker 01

  Oh, well, right now, this is a detailed thing that wouldn't apply to most people, okay? But you want me to answer that question?

• 58:00Lex Fridman?

  Yeah, please.

• 58:02Speaker 01

  We've talked about, as if, oh, to predict what you're going to sense on this coffee cup, I need to know where my finger is going to be on the coffee cup. That is true, but it's insufficient. Think about, my finger touches the edge of the coffee cup. My finger can touch it at different orientations.

• 58:17Lex Fridman?

  Right.

• 58:18Speaker 01

  I can rotate my finger around here. And that doesn't change. I can make that prediction somehow. So it's not just the location. There's an orientation component of this as well. This is known in the old parts of the brain too. There's things called head direction cells, which way the rat is facing. It's the same kind of basic idea. So if my finger were a rat, you know, in three dimensions, I have a three-dimensional orientation, and I have a three-dimensional location. If I was a rat, I would have a, you might think of it as a two-dimensional location, a two-dimensional orientation, a one-dimensional orientation. Like, just which way is it facing? So how the the two components work together? How it is that I I combine orientation, the orientation of my sensor,

• 59:00Speaker 01

  as well as the the the location is a tricky problem. And I think I've made progress on it.

• 59:09Lex Fridman?

  So at a bigger version of that, so perspective is super interesting, but super specific.

• 59:14Speaker 01

  Yeah, I warned you.

• 59:16Lex Fridman?

  No, no, that's really good. But it's there's a more general version of that. Do you think context matters? The fact that we are in a building in North America that that we in the day and age where we have mugs? I mean, there's all this extra information that you bring to the table about everything else in the room that's outside of just the coffee cup.

• 59:40Speaker 01

  Of course it is.

• 59:41Lex Fridman?

  How does it get connected, do you think?

• 59:43Speaker 01

  Yeah, and that is another really interesting question. I'm going to throw that under the the rubric or the the name of attentional problems. First of all, we have this model. I have many, many models.

• 59:54Lex Fridman?

  So first, and also the question, does it matter? Because.

• 59:56Speaker 01

  Well, it matters for certain things. Of course it does. Maybe what we think of as a coffee cup in another part of the world is viewed as something completely different. Or maybe our logo, which is very benign in this part of the world, it means something very different in another part of the world. So those things do matter. I think the thing, the way to think about it is the following, or one way to think about it, is we have all these models of the world. Okay. And we model, we model everything. And as I said earlier, I kind of snuck it in there. Our models are actually, we we build composite structures. So every object is composed of other objects, which are composed of other objects, and they become members of other objects. So this room has chairs and a table and a room and walls and so on. Now we can just arrange them in these things in a certain way.

• 1:00:40Speaker 01

  You go, oh, that's in the namenta conference room. So.

• 1:00:46Speaker 01

  And what we do is when we go around the world and we experience the world, by walking to a room, for example, the first thing I do is like say, "Oh, I'm in this room." Do I recognize the room? Then I can say, "Oh, look, there's a table here." And by attending to the table, I'm then assigning this table in a context of the room. Then I say, "Oh, on the table, there's a coffee cup." "Oh, and on the table, there's a logo." And in the logo, there's the word "dementa." "Oh, and look, in the logo, there's the letter E." "Oh, and look, it has an unusual serif." And it doesn't actually, but pretend it does.

• 1:01:16Speaker 01

  So, the point is, your attention is kind of drilling deep in and out of these nested structures.

• 1:01:24Speaker 01

  And I can pop back up and I can pop back down. I can pop back up and I can pop back down. So, when I attend to the coffee cup, I haven't lost the context of everything else, but it's sort of, there's this sort of nested structure.

• 1:01:35Lex Fridman?

  So, the attention filters the reference frame information for that particular period of time?

• 1:01:40Speaker 01

  Yes, it basically, moment to moment, you attend to subcomponents, and then you can attend to subcomponents to subcomponents.

• 1:01:46Lex Fridman?

  And you can move up and down that?

• 1:01:48Speaker 01

  You can move up and down that. We do that all the time. You're not even, now that I'm aware of it, I'm very conscious of it. But until, but most people don't even think about this. You know, you just walk in a room and you don't say, "Oh, I looked at the chair, and I looked at the board, and I looked at that word on the board, and I looked over here. What's going on?" Right?

• 1:02:03Lex Fridman?

  So, what percentage of your day are you deeply aware of this? And what part can you actually relax and just be Jeff?

• 1:02:09Speaker 01

  Me personally, like my personal day?

• 1:02:10Lex Fridman?

  Yeah.

• 1:02:11Speaker 01

  Unfortunately, I'm afflicted with too much of the former.

• 1:02:17Lex Fridman?

  Unfortunately, they are unfortunate.

• 1:02:19Speaker 01

  Yeah.

• 1:02:19Lex Fridman?

  You don't think it's useful?

• 1:02:21Speaker 01

  Oh, it is useful, totally useful. I think about this stuff almost all the time. And one of my primary ways of thinking is when I'm in sleep at night, I always wake up in the middle of the night, and then I stay awake for at least an hour with my eyes shut in sort of a half-sleep state, thinking about these things. I come up with answers to problems very often in that sort of half-sleeping state. I think about my bike ride, I think about my walks. I'm just constantly thinking about this. I have to almost schedule time to not think about this stuff, because it's very, it's mentally taxing.

• 1:02:54Lex Fridman?

  Are you, when you're thinking about this stuff, are you thinking introspectively, like almost taking a step outside of yourself and trying to figure out what is your mind doing right now?

• 1:03:02Speaker 01

  I do that all the time, but that's not all I do. I'm constantly observing myself. So as soon as I started thinking about grid cells, for example, and getting into that, I started saying, oh, well, grid cells can have my place of sense in the world. You know, that's where you know where you are. And it's interesting, you know, we always have a sense of where we are unless we're lost. And so I started at night when I got up to go to the bathroom, I would start trying to do it completely with my eyes closed all the time. And I would test my sense of grid cells. I would, I would walk, you know, five feet and say, okay, I think I'm here. Am I really there? What's my error?

• 1:03:31Lex Fridman?

  Yeah.

• 1:03:31Speaker 01

  And then I would calculate my error again and see how the errors accumulate. So even something as simple as getting up in the middle of the night to go to the bathroom, I'm testing these theories out. It's kind of fun. I mean, the coffee cup is an example of that, too. So I think, I find that these sort of everyday introspections are actually quite helpful. It doesn't mean you can ignore the science. I mean, I spend hours every day reading ridiculously complex papers. That's not nearly as much fun, but you have to sort of build up those constraints and the knowledge about the field and who's doing what and what exactly they think is happening here. And then you can sit back and say, okay, let's try to piece this all together. Let's come up with some, you know, I'm very, in this group here, people, they know they do, I do this all the time.

• 1:04:15Speaker 01

  I come in with these introspective ideas and say, well, have you ever thought about this? Now watch, well, this, all do this together. And it's helpful. It's not, if you, as long as you didn't, you don't, if you, all you did was that, then you're just making up stuff, right? But if you're constraining it by the reality of the neuroscience, then it's really helpful.

• 1:04:34Lex Fridman?

  So let's talk a little bit about deep learning and the successes in the applied space of neural networks. Ideas of training model on data and these simple computational units, neuron, artificial neurons that with backpropagation have statistical ways of being able to generalize from the training set onto data that's similar to that training set. So where do you think are the limitations of those approaches? What do you think are its strengths relative to your major efforts of constructing a theory of human intelligence?

• 1:05:11Speaker 01

  Yeah. Well, I'm not an expert in this field. I'm somewhat knowledgeable, so, but I'm not.

• 1:05:16Lex Fridman?

  Some of it is in just your intuition. What are your?

• 1:05:18Speaker 01

  Well, I have, I have a little bit more than intuition, but I just want to say like, you know, one of the things that you asked me, do I spend all my time thinking about neuroscience? I do. That's to the exclusion of thinking about things like convolutional neural networks. But I try to stay current. So, look, I think it's great, the progress they've made. It's fantastic. And as I mentioned earlier, it's very highly useful for many things. The models that we have today are actually derived from a lot of neuroscience principles. There are distributed processing systems and distributed memory systems, and that's how the brain works. They use things that we might call them neurons, but they're really not neurons at all. So we can just, they're not really neurons. They're distributed processing systems. And the nature of hierarchy that came also from neuroscience. And so there's

• 1:06:03Speaker 01

  a lot of things, the learning rules, basically, not backprop, but other, you know, sort of heavy anti-.

• 1:06:08Lex Fridman?

  I'd be curious to say, they're not neurons at all. Can you describe in which way, I mean, some of it is obvious, but I'd be curious if you have specific ways in which you think are the biggest differences.

• 1:06:19Speaker 01

  Yeah, we had a paper in 2016 called "Why Neurons Have Thousands Of Synapses", and if you read that paper, you'll know what I'm talking about here. A real neuron in the brain is a complex thing. Let's just start with the synapses on it, which is the connection between neurons. Real neurons can everywhere from 5 to 30,000 synapses on them. The ones near the cell body, the ones that are close to the soma, the cell body, those are like the ones that people model in artificial neurons. There's a few hundred of those, maybe. They can affect the cell, they can make the cell become active. 95% of the synapses can't do that. They're too far away. So if you activate one of those

• 1:07:02Speaker 01

  synapses, it just doesn't affect the cell body enough to make any difference.

• 1:07:05Lex Fridman?

  Any one of them individually?

• 1:07:06Speaker 01

  Any one of them individually, or even if you do a mass of them. What real neurons do is the following. If you activate, or you get 10 to 20 of them, active at the same time, meaning they're all receiving an input at the same time. And those 10 to 20 synapses, or 40 synapses, are within a very short distance on the dendrite, like 40 microns, a very small area. So if you activate a bunch of these right next to each other at some distant place, what happens is it creates what's called a dendritic spike. And the dendritic spike travels through the dendrites and can reach the soma, or the cell body.

• 1:07:44Speaker 01

  Now, when it gets there, it changes the voltage, which is sort of like gonna make the cell fire, but never enough to make the cell fire. It's sort of what we call, it says we depolarize the cell, you raise the voltage a little bit, but not enough to do anything. It's like, well, good as that. And then it goes back down again. So we proposed a theory, which I'm very confident in basics are, is that what's happening there is those 95% of those synapses are recognizing dozens to hundreds of unique patterns. They can write, you know, about 10, 20 synapses at a time. And they're acting like predictions. So the neuron actually is a predictive engine on its own. It can fire when it gets enough, what they call proximal input from those ones near the cell fire,

• 1:08:28Speaker 01

  but it can get ready to fire from dozens to hundreds of patterns that it recognizes from the other guys. And the advantage of this to the neuron is that when it actually does produce a spike, an action potential, it does so slightly sooner than it would have otherwise. And so what good is slightly sooner? Well, the slightly sooner part is it, there's it, all the neurons in the, the excitatory neurons in the brain are surrounded by these inhibitory neurons. And they're very fast, the inhibitory neurons, these baskets all. And if I get my spike out a little bit sooner than someone else, I inhibit all my neighbors around me. Right? And what you end up with is a different representation. You end up with a representation that matches your prediction. It's a sparsa representation, meaning it's fewer neurons are active,

• 1:09:12Speaker 01

  but it's much more specific. And so we showed how networks of these neurons can do very sophisticated temporal prediction, basically. So this, summarize this. Real neurons in the brain are time-based prediction engines. And there's no concept of this at all in artificial, what we call point neurons. I don't think you can mail the brain without them. I don't think you can build intelligence without them because it's where a large part of the time comes from. It's, these are predictive models and the time is, there's a prior in a prediction and an action. And it's inherent through every neuron in the near cortex. So I would say that point neurons sort of model a piece of that, and not very well at that either.

• 1:09:57Speaker 01

  But, you know, like, for example, synapses are very unreliable. And you cannot assign any precision to them. So even one digit of precision is not possible. So the way real neurons work is they don't add these, they don't change these weights accurately like artificial neural networks do. They basically form new synapses. And so what you're trying to always do is, is detect the presence of some 10 to 20 active synapses at the same time as opposed, and they're almost binary. It's like, because you can't really represent anything much finer than that. So these are the kind of dishes, and I think that's actually another essential component because the brain works on sparse patterns and all that, all that mechanism is based on sparse patterns.

• 1:10:40Speaker 01

  And I don't actually think you could build art, real brains or art, machine intelligence without incorporating some of those ideas.

• 1:10:47Lex Fridman?

  It's hard to even think about the complexity that emerges from the fact that the timing of the firing matters in the brain, the fact that you form new, new synapses and the, I mean, everything you just mentioned in the past.

• 1:11:00Speaker 01

  You can't, but trust me, if you spend time on it, you can get your mind around it. It's not like, it's no longer a mystery to me.

• 1:11:06Lex Fridman?

  No, but, but sorry, as a function, in a mathematical way, it's, can you get it, start getting an intuition about what gets it excited, what not?

• 1:11:15Speaker 01

  Yeah, it's not as easy as, there are many other types of neural networks are, that are more amenable to pure analysis. You know, especially very simple networks, you know, oh, I have four neurons and they're doing this, can we, you know, describe the mathematically what they're doing type of thing. Even the, the complexity of convolutional neural networks today, it's sort of a mystery, they can't really describe the whole system. And so it's different. My colleague Subhati Ahmad, he did a nice paper on this. You can get all this stuff on our website if you're interested. Talking about sort of the mathematical properties of sparse representations. And so we can't, what we can do is we can show mathematically, for example, why 10 to

• 1:11:59Speaker 01

  20 synapses to recognize a pattern is the correct number, is the right number you'd want to use. And by the way, that matches biology. We can show mathematically some of these concepts about the show why the brain is so robust to noise and error and fallout and so on. We can show that mathematically as well as empirically in simulations. But the system can't be analyzed completely. Any complex system can't. And so that's out of the realm. But there is, there is mathematical. Benefits and intuitions that can be derived from mathematics. And we try to do that as well. Most of our papers have a section about that.

• 1:12:39Lex Fridman?

  So I think it's refreshing and useful for me to be talking to you about deep neural networks. Because your intuition basically says that we can't achieve anything like intelligence with artificial neural networks.

• 1:12:52Speaker 01

  Well, not in their current form.

• 1:12:53Lex Fridman?

  Not in the current form.

• 1:12:54Speaker 01

  Sure, we can do it in the ultimate form, sure.

• 1:12:56Lex Fridman?

  So let me dig into it and see what your thoughts are there a little bit. So I'm not sure if you read this little blog post called Bitter Lesson by Rich Sutton recently. He's a reinforcement learning pioneer. I'm not sure if you're familiar with him. His basic idea is that all the stuff we've done in AI in the past 70 years. He's one of the old school guys.

• 1:13:19Lex Fridman?

  The biggest lesson learned is that all the tricky things we've done don't, you know, they benefit in the short term. But in the long term, what wins out is a simple, general method that just relies on Moore's law. On computation getting faster and faster.

• 1:13:36Speaker 01

  This is what he's saying. This is what has worked up to now.

• 1:13:39Lex Fridman?

  This what has worked up to now. That if you're trying to build a system, if we're talking about, he's not concerned about intelligence. He's concerned about system that works in terms of making predictions on applied narrow AI problems. Right, that's what this discussion is about. That you just try to go as general as possible and wait years or decades for the computation to make it actually.

• 1:14:06Speaker 01

  Is he saying that as a criticism? Or is he saying this is a prescription of what we ought to be doing?

• 1:14:10Lex Fridman?

  Well, it's very difficult. He's saying this is what has worked. And yes, a prescription, but it's a difficult prescription because it says, all the fun things you guys are trying to do. We are trying to do. He's part of the community. He's saying it's only going to be short term gains. So this all leads up to a question, I guess, on artificial neural networks and maybe our own biological neural networks. Is, do you think if we just scale things up significantly? So take these dumb artificial neurons, the point neurons, I like that term. If we just have a lot more of them, do you think some of the elements that we see in the brain? May start emerging.

• 1:14:54Speaker 01

  No, I don't think so. We can do bigger problems and of the same type. I mean, it's been pointed out by many people that today's convolutional neural networks aren't really much different than the ones we had quite a while ago. We're just, they're bigger and trained more and we have more labeled data and so on.

• 1:15:12Speaker 01

  But I don't think you can get to the kind of things I know the brain can do and that we think about as intelligence by just scaling it up. So that may be, it's a good description of what's happened in the past, what's happened recently with the reemergence of artificial neural networks. It may be a good prescription for what's going to happen in the short term.

• 1:15:34Speaker 01

  But I don't think that's the path. I've said that earlier. There's an alternate path. I should mention to you, by the way, that we've made sufficient progress on our, the whole cortical theory in the last few years, that last year we decided to start actively pursuing how do we get these ideas embedded into machine learning? That's again, being led by my colleague, Subitabh Mon. And because he's more of a machine learning guy, I'm more of a neuroscience guy. So this is now our new, this is, I wouldn't say our focus, but it is now an equal focus here. Because we, we, we need to proselytize what we've learned

• 1:16:14Speaker 01

  and we need to show how it's beneficial to, to, to the machine learning. So we're putting, we have a plan in place right now. In fact, we just did our first paper on this. I can tell you about that. But, you know, one of the reasons I want to talk to you is because I'm trying to get more people in the machine learning community to say, like, I need to learn about this stuff. And maybe we should just think about this a bit more, about what we've learned about the brain. And what are those team at NAMET, what have they done? Is that useful for us?

• 1:16:41Lex Fridman?

  Yeah. So is there elements of all the cortical theory, that things we've been talking about that may be useful in the short term?

• 1:16:48Speaker 01

  Yes, in the short term, yes.

• 1:16:49Lex Fridman?

  This is the, sorry to interrupt, but the, the open question is, it certainly feels from my perspective that in the long term, some of the ideas we're talking about will be extremely useful.

• 1:17:00Speaker 01

  Yeah.

• 1:17:00Lex Fridman?

  The question is whether in the short term.

• 1:17:02Speaker 01

  Well, this is a, always what we, I would call the entrepreneur's dilemma. So you have this long-term vision. Oh, we're going to all be driving electric cars or we're all going to have computers or we're all going to, whatever. And you're at some point in time and you say, I can see that long-term vision. I'm sure it's going to happen. How do I get there without killing myself, you know, without going out of business?

• 1:17:23Lex Fridman?

  Yeah.

• 1:17:23Speaker 01

  That's the challenge. That's the dilemma. That's the really difficult thing to do. So we're facing that right now. So ideally, what you'd want to do is find some steps along the way that you can get there incrementally. You don't have to like throw it all out and start over again. The first thing that we've done is we focus on the sparse representations. So just in case you don't know what that means, or some of the listeners don't know what that means. In the brain, if I have like 10,000 neurons, what you would see is maybe 2% of them active at a time. You don't see 50%, you don't see 30%, you might see 2%. And it's always like that.

• 1:17:59Lex Fridman?

  For any set of sensory input?

• 1:18:00Speaker 01

  It doesn't matter of anything. It doesn't matter of any part of the brain.

• 1:18:04Lex Fridman?

  But which neurons differs? Which neurons are active?

• 1:18:08Speaker 01

  Yeah, so let's say I take 10,000 neurons that are representing something. They're sitting there in a little block together. It's a teeny little block in there, 10,000 neurons. And they're representing a location, they're representing a cup, they're representing the input from my sensors. I don't know, it doesn't matter. It's representing something. The way the representations occur, it's always a sparse representation. I mean, it's a population code. So which 200 cells are active tells me what's going on. It's not, individual cells aren't that important at all. It's the population code that matters. And when you have sparse population codes, then all kinds of beautiful properties come out of them. So the brain uses sparse population codes. And we've written and described these benefits in some of our papers. So they give this tremendous robustness to the systems.

• 1:18:54Speaker 01

  You know, brains are incredibly robust. Neurons are dying all the time and spasming and synapses falling apart and, you know, all the time. And it keeps working. So what Sybuthai and Louise, one of our other engineers here, have done.

• 1:19:09Speaker 01

  I've shown they're introducing sparseness into convolutional neural networks. Now, other people are thinking along these lines, but we're going about it in a more principled way, I think. And we're showing that if you enforce sparseness throughout these convolutional neural networks in both the act, which sort of which neurons are active and the connections between them, that you get some very desirable properties. So, one of the current hot topics in deep learning right now is these adversarial examples. So, you know, I can give me any deep learning network and I can give you a picture that looks perfect and you're going to call it, you know, you're going to say the monkey is, you know, an airplane. That's a problem. And DARPA just announced some big thing. They're trying to, you know, have some contest for this.

• 1:19:53Speaker 01

  But if you, if you enforce sparse representations here, many of these problems go away. They're much more robust and they're not easy to fool. So, we've already shown some of those results. It was just literally in January or February, just like last month, we did that. And you can, I think it's on BioArchive right now or on ICRI, you can read about it. But, so that's like a baby step. Okay? That's take something from the brain. We know, we know about sparseness. We know why it's important. We know what it gives the brain. So, let's try to enforce that on to this.

• 1:20:25Lex Fridman?

  What's your intuition why sparsity leads to robustness? Because it feels like it would be less robust.

• 1:20:31Speaker 01

  Why, why would you feel the rest robust to you?

• 1:20:34Lex Fridman?

  So, it, it just feels like if the fewer neurons are involved, the more fragile the representation.

• 1:20:43Speaker 01

  Yeah, but I didn't say there was lots of few. I said, let's say 200. That's a lot.

• 1:20:47Lex Fridman?

  It's still a lot.

• 1:20:48Speaker 01

  Yeah. So, here's an intuition for it. This is a bit technical, so for, you know, for engineers, machine learning people, this would be easy, but other listeners, maybe not. If you're trying to classify something, you're trying to divide some very high dimensional space into different pieces, A and B, and you're trying to create some point where you say all these points in this high dimensional space are A and all these points in this high dimensional space are B.

• 1:21:14Speaker 01

  And if you have points that are close to that line, it's not very robust. It works for all the points you know about, but it's it's not very robust because you can just move a little bit and you've crossed over the line. When you have sparse representations, imagine I pick, I have, I'm going to pick 200 cells active out of, out of 10,000. Okay. So I have 200 cells active. Now let's say I pick randomly another, a different representation, 200. The overlap between those is going to be very small, just a few. I can pick millions of samples randomly of 200 neurons, and not one of them will overlap more than just a few. So one way to think about it is if I want to fool one of these representations to look like one of those other representations,

• 1:21:59Speaker 01

  I can't move just one cell or two cells or three cells or four cells. I have to move 100 cells. And that makes them robust.

• 1:22:09Lex Fridman?

  In terms of further, so you mentioned sparsity.

• 1:22:12Speaker 01

  What would be the next thing?

• 1:22:13Lex Fridman?

  Yeah.

• 1:22:14Speaker 01

  Okay, so we have, we picked one. We don't know if it's going to work well yet. So again, we're trying to come up incremental ways to moving from brain theory to add pieces to machine learning, current machine learning world and one step at a time. So the next thing we're going to try to do is is sort of incorporate some of the ideas of the 1,000 brains theory, that you have many, many models and that are voting. Now that idea is not new. There's a mixture of models has been around for a long time. But the way the brain does is a little different and and the way it votes is different and the kind of way it represents uncertainty is different.

• 1:22:53Speaker 01

  So we're just starting this work, but we're going to try to see if we can sort of incorporate some of the principles of voting or principles of 1,000 brain theory, like lots of simple models. That talk to each other in a very certain way. And can we build more machines, the systems that learn faster and also, well, mostly are multimodal and robust to multimodal type of issues?

• 1:23:24Lex Fridman?

  So one of the challenges there is, you know, the machine learning, computer vision community has certain sets of benchmarks, sets of tests based on which they compete. And I would argue, especially from your perspective, that those benchmarks aren't that useful for testing the aspects that the brain is good at or intelligent. They're not really testing intelligence. They're very fine.

• 1:23:48Speaker 01

  Yeah.

• 1:23:49Lex Fridman?

  And it's been extremely useful for developing specific mathematical models, but it's not useful in the long term for creating intelligence. So you think you also have a role in proposing better tests?

• 1:24:03Speaker 01

  Yeah, this is a very, you've identified a very serious problem. First of all, the tests that they have are the tests that they want, not the tests of the other things that we're trying to do, right? You know, what are the, so on. The second thing is sometimes these, to be competitive in these tests, you have to have huge data sets and huge computing power. And so, you know, and we don't have that here. We don't have it as well as other big teams and big companies do. So there's numerous issues there. You know, we come out, you know, we're, our approach to this is all based on, in some sense, you might argue elegance. We're coming at it from like a theoretical base that we think, oh my God, this is so, this is so clearly elegant, this is how brains work, this is what intelligence is.

• 1:24:48Speaker 01

  But the machine learning world has gotten in this phase where they think it doesn't matter, doesn't matter what you think, as long as you do, you know, 0.1% better on this benchmark, that's what, that's all that matters. And, and that's a problem. You know, we have to figure out how to get around that. That's, that's a challenge for us. It's, it's one of the challenges that we have to deal with. So I agree, you've identified a big issue. It's difficult for those reasons, but you know.

• 1:25:14Speaker 01

  Part of, you know, part of the reasons I'm talking to you here today is I hope I'm gonna get some machine learning people to say, I don't wanna read those papers. Those might be some interesting ideas. I'm tired, I'm tired of doing this 0.1% improvement stuff, you know?

• 1:25:24Lex Fridman?

  Well, that's, that's why I'm here as well, because I think machine learning now as a community is at a place where the next step is, um, needs to be orthogonal to what has received success in the past.

• 1:25:37Speaker 01

  You see other leaders saying this, machine learning leaders, you know, Jeff Hinton with his capsules idea. Uh, many people have gotten up to say, you know, we're gonna hit road map, maybe we should look at the brain, you know, things like that. So, um, hopefully that thinking will occur organically, and then, then we're in a nice position for people to come and look at our work and say, well, what can we learn from these guys?

• 1:25:59Lex Fridman?

  Yeah, MIT is just launching a billion dollar computing college that's centered around this idea, so.

• 1:26:05Speaker 01

  Is it on this idea of what, of a?

• 1:26:07Lex Fridman?

  Well, the idea that, uh, you know, the humanities, psychology, neuroscience have to work all together to get to, uh, build the AI.

• 1:26:15Speaker 01

  Yeah, I mean, Stanford just did this human centered AI thing. I'm a little disappointed in these initiatives because, you know, they're, they're focusing on sort of the human side of it, and it could very easily slip into how humans interact with, um, intelligent machines, which is nothing wrong with that, but that's not, that is orthogonal to what we're trying to do. We're trying to say, like, what is the essence of intelligence? I don't care. In fact, I wanna build intelligent machines that aren't emotional, that don't smile at you, uh, that, you know, that aren't trying to tuck you in at night.

• 1:26:48Lex Fridman?

  Yeah, there, there is that pattern that you, uh, when you talk about, uh, understanding the humans is important for understanding intelligence, you start slipping into topics of ethics, or, um, yeah, like you said, the interactive elements as opposed to, no, no, no, let's zoom in on the brain, study, study what the human brain, the baby, the...

• 1:27:07Speaker 01

  Let's study what a brain does, and then we can decide which parts of that we wanna recreate in some system. But do you have that theory about what the brain does? What's the point? You know, it's just, you're gonna be wasting time, I think.

• 1:27:19Lex Fridman?

  Right. Just to break it down on the artificial neural network side, maybe you could speak to this on the, on the biologic neural network side, the process of learning versus the process of inference. Maybe you can explain to me, is there a difference between, you know, in artificial neural networks, there's a difference between the learning stage and the inference stage.

• 1:27:39Speaker 01

  Yeah.

• 1:27:39Lex Fridman?

  Do you see the brain as something different? One of the, one of the big distinctions that people often say, I don't know how correct it is, is artificial neural networks need a lot of data. They're very inefficient learning.

• 1:27:50Speaker 01

  Yeah.

• 1:27:51Lex Fridman?

  Do you see that as a correct distinction from the, the biology of the human brain? That the human brain is very efficient? Or is that just something we deceive ourselves with?

• 1:28:00Speaker 01

  No, it is efficient, obviously. We can learn new things almost instantly.

• 1:28:04Lex Fridman?

  And so what elements do you think?

• 1:28:06Speaker 01

  Yeah, I can talk about that. You brought up two issues there. So remember I talked early about the constraints? We, we always feel, well, one of those constraints is the fact that brains are continually learning. That, that's not something we said, oh, we can add that later. That's something that was upfront, had to be there from the start. And made our problems harder. But we showed, going back to the 2016 paper on sequence memory, we showed how that happens. How do brains infer and learn at the same time? And our models do that. And they're not two separate phases or two separate sets of time. I think that's a big, big problem in AI, at least for many applications, not for all. So I can talk about that.

• 1:28:50Speaker 01

  There are some, it gets detailed. There are some parts of the neocortex in the brain where actually what's going on, there's these, there's these, with these cycles, they're like, you know, cycles of activity in the brain. And there's very strong evidence that you're doing more of inference on one part of the phase and more of learning on the other part of the phase. So the brain can actually sort of separate different populations of cells are going back and forth like this. But in general, I would say that's an important problem. We have, you know, all of our networks that we've come up with do both. And it's, they're learning, continuous learning networks. And you mentioned benchmarks earlier. Well, there are no benchmarks about that.

• 1:29:28Lex Fridman?

  Exactly.

• 1:29:29Speaker 01

  So, so we, you know, we have to like, you know, we get in our little soapbox and hey, by the way, we, you know, this is important, you know, and here's a mechanism for doing that. But then, you know, but until you can prove it to someone in some, you know, commercial system or something, it's a little harder.

• 1:29:43Lex Fridman?

  So yeah, one of the things I had to linger on that is in some ways to learn the concept of a coffee cup, you only need this one coffee cup and maybe some time alone in a room with it.

• 1:29:54Speaker 01

  Well, the first thing is, I, when I, imagine I reach my hand into a black box and I'm reaching, I'm trying to touch something.

• 1:29:59Lex Fridman?

  Yeah.

• 1:30:00Speaker 01

  I don't know upfront if it's something I already know, or if it's a new thing.

• 1:30:03Lex Fridman?

  Right.

• 1:30:04Speaker 01

  And I have to, I'm doing both at the same time. I don't say, oh, let's see if it's a new thing. Oh, let's see if it's an old thing. I don't do that. As I go, my brain says, oh, it's new or it's not new. And if it's new, I start learning what it is. So, and by the way, it starts learning from the get go, even if it's going to recognize it. So they're, they're not separate problems. And so that's the thing. The other thing you mentioned was the fast learning. So I was just talking about continuous learning, but there's also fast learning. Literally, I can show you this coffee cup and I say, here's a new coffee cup. It's got the logo on it. Take a look at it. Done. You're done. You can predict what it's going to look like, you know, in different positions. So I can talk about that, too.

• 1:30:45Lex Fridman?

  Yeah.

• 1:30:46Speaker 01

  In the brain, the way learning occurs, I mentioned this earlier, but I'll mention it again, the way learning occurs, I'm, imagine I have a section of a dendrite of a neuron. And I want to learn, I'm going to learn something new. I'm just, doesn't matter what it is, I'm just going to learn something new. I, I need to recognize a new pattern. So what I'm going to do, I'm going to form new synapses. New synapses, we're going to rewire the brain onto that section of the dendrite. Once I've done that, everything else that neuron has learned is not affected by it. Now, that's because it's isolated to that small section of the dendrite. They're not all being added together like a point neuron. So if I learn something new on this segment here, it doesn't change any of the learning that occur anywhere else in that neuron.

• 1:31:31Speaker 01

  So I can add something without affecting previous learning. And I can do it quickly. Now, let's talk, we can talk about the quickness, how it's done in real neurons. You might say, well, doesn't it take time to form synapses? Yes, it can take maybe an hour to form a new synapse. We can form memories quicker than that, and I can explain that happens too, if you want. But it's getting a bit neurosciency.

• 1:31:55Lex Fridman?

  That's great, but is there an understanding of these mechanisms at every level?

• 1:31:59Speaker 01

  Yeah.

• 1:31:59Lex Fridman?

  So from the short-term memories and the forming

• 1:32:04Speaker 01

  Well, so this idea of synaptogenesis, the growth of new synapses, that's well described, is well understood.

• 1:32:10Lex Fridman?

  And that's an essential part of learning.

• 1:32:12Speaker 01

  That is learning.

• 1:32:13Lex Fridman?

  That is.

• 1:32:14Speaker 01

  Learning, okay. You know, back, you know, going back many, many years, people, you know, was, what's his name? The psychologist proposed, Hebb, Donald Hebb. He proposed that learning was the modification of the strength of a connection between two neurons. People interpreted that as the modification of the strength of a synapse. He didn't say that. He just said there's a modification between the effect of one neuron and another. So synaptogenesis is totally consistent with Donald Hebb said. But anyway, there's these mechanisms, the growth of new synapses. You can go online, you can watch a video of a synapse growing in real time. It's literally, you can see this little thing going boop. It's pretty impressive.

• 1:32:54Lex Fridman?

  Yeah.

• 1:32:54Speaker 01

  So that's, those mechanisms are known. Now, there's another thing that we've speculated and we've written about, which is consistent with non-neuroscience, but it's less proven. And this is the idea, how do I form a memory really, really quickly? Like instantaneous. If it takes an hour to grow a synapse, like, that's not instantaneous. So there are, there are types of synapses called silent synapses. They look like a synapse, but they don't do anything. They're just sitting there. It's like, if an action potential comes in, it doesn't release any neurotransmitter. Some parts of the brain have more of these than others. For example, the hippocampus has a lot of them, which is where we associate most short-term memory with.

• 1:33:35Speaker 01

  So what we speculated, again in that 2016 paper, we proposed that the way we form very quick memories, very short-term memories, or quick memories, is that we convert silent synapses into active synapses. It's going, it's like saying a synapse has a zero weight and a one weight. But the long-term memory has to be formed by synaptogenesis. So you can remember something really quickly by just flipping a bunch of these guys from silent to active. It's not like, it's not from point one to point one five. It's like, doesn't do anything till it releases transmitter. And if I do that over a bunch of these, I've got a very quick short-term memory. So I guess the lesson behind this is that most neural networks today are fully connected.

• 1:34:18Speaker 01

  Every neuron connects every other neuron from layer to layer. That's not correct in the brain. We don't want that. We actually don't want that. It's bad. You want a very sparse connectivity so that any neuron connects to some subset of the neurons in the other layer, and it does so on a dendrite by dendrite segment basis. So it's a very parcolated out type of thing. And that then learning is not adjusting all these weights, but learning is just saying, okay, connect to these 10 cells here right now.

• 1:34:46Lex Fridman?

  In that process, you know, with artificial neural networks, it's a very simple process of back propagation that adjusts the weights. The process of synaptogenesis.

• 1:34:56Speaker 01

  Synaptogenesis.

• 1:34:57Lex Fridman?

  Synaptogenesis.

• 1:34:58Speaker 01

  It's even easier.

• 1:34:59Lex Fridman?

  It's even easier.

• 1:35:00Speaker 01

  It's even easier. Back propagation requires something that really can't happen in brains. This back propagation of this error signal, that really can't happen. People are trying to make it happen in brains, but it doesn't happen in brains. This is pure Hebbian learning. Well, synaptogenesis is pure Hebbian learning. It's basically saying, there's a population of cells over here that are active right now, and there's a population of cells over here active right now. How do I form connections between those active cells? And it's literally saying, this guy became active, these 100 neurons here became active before this neuron became active. So form connections to those ones. That's it. There's no propagation of error, nothing. All the networks we do, all the models we have work on, almost completely on Hebbian learning, but.

• 1:35:44Speaker 01

  In on dendritic segments and multiple synapses at the same time.

• 1:35:49Lex Fridman?

  So now that's returned the question that you already answered, and maybe you can answer it again. If you look at the history of artificial intelligence, where do you think we stand? How far are we from solving intelligence? You said you were very optimistic.

• 1:36:03Speaker 01

  Yeah.

• 1:36:04Lex Fridman?

  Can you elaborate on that?

• 1:36:05Speaker 01

  Yeah, you know, it's always the crazy question to ask. Because, you know, no one can predict the future.

• 1:36:11Lex Fridman?

  Absolutely.

• 1:36:12Speaker 01

  So I'll tell you a story. I used to, I used to run a different neuroscience institute called the Red Bull Neuroscience Institute. And we would, we would hold these symposiums and we'd get like 35 scientists from around the world to come together. And I used to ask them all the same question. I would say, well, how long do you think it'll be before we, we understand how the neurocortex works? And everyone went around room and they had introduced a name and they have to answer that question. So I got, the typical answer was 50 to 100 years. Some people would say 500 years. Some people said never. I said, why are you, why are you a neuroscientist?

• 1:36:46Speaker 01

  It's good pay.

• 1:36:49Speaker 01

  It's interesting. So, you know, but it doesn't work like that. As I mentioned earlier, these are not, these are step functions. Things happen and then bingo, they happen. You can't predict that. I feel I've already passed a step function. So if I can do my job correctly over the next five years,

• 1:37:07Speaker 01

  then, meaning I can proselytize these ideas, I can convince other people they're right. We can show that other people or machine learning people should pay attention to these ideas. Then we're definitely in an under 20 year timeframe. If I can do those things. If I, if I'm not successful in that, and this is the last time anyone talks to me and no one reads our papers and, you know, and I'm wrong or something like that, then, then I don't know. But it's, it's not 50 years. It's, it, you know, it'll, it'll, you know, the same thing about electric cars. How quickly are they going to populate the world? Well, it probably takes about a 20 year span. It'll be something like that, but I think if I could do what I said, we're starting it.

• 1:37:48Lex Fridman?

  And of course, there could be other, you said step functions, it could be

• 1:37:54Lex Fridman?

  everybody gives up on your ideas for 20 years and then all of a sudden, somebody picks it up again. Wait, that guy was on to something.

• 1:38:00Speaker 01

  Yeah, so that would be, that would be a failure on my part, right? You know?

• 1:38:03Lex Fridman?

  Yeah.

• 1:38:03Speaker 01

  Think about Charles Babbage. You know, Charles Babbage, he's the guy who invented the computer back in 18 something. 1800s and everyone forgot about it until, you know, 100 years later and say, hey, this guy figured this stuff out a long time ago. You know, but he was ahead of his time. I don't think, you know, like, as I said, I recognize this is part of any entrepreneur's challenge. I use entrepreneur broadly in this case. I'm not meaning like I'm building a business trying to sell something. I mean, like, I'm trying to sell ideas. And this is the challenge as to how you get people to pay attention to you. How do you get them to give you positive or negative feedback? How do you get the people actively based on your ideas? So, you know, we'll see how well we do on that.

• 1:38:46Lex Fridman?

  So, you know, there's a lot of hype behind artificial intelligence currently. Do you, as, as you look to spread the ideas that are of neural cortical theory, the things you're working on? Do you think there's some possibility we'll hit an AI winter once again?

• 1:39:03Speaker 01

  Yeah, certainly, certainly a possibility. No question about it.

• 1:39:06Lex Fridman?

  You worry about?

• 1:39:06Speaker 01

  Yeah, well, I guess, do I worry about it? I haven't decided yet if that's good or bad for my mission.

• 1:39:14Lex Fridman?

  That's true. That's very true because it's almost like you need the, the winter to refresh the palate.

• 1:39:20Speaker 01

  Yeah, it's so, it's like, I want, here's what you want to have it is, you want like, to the extent that everyone is so thrilled about the current state of machine learning and AI and they don't imagine they need anything else, it makes my job harder.

• 1:39:35Lex Fridman?

  Right.

• 1:39:36Speaker 01

  If, if everything crashed completely and every student left the field and there was no money for anybody to do anything and it became an embarrassment to talk about machine intelligence and AI, that wouldn't be good for us either. You want, you want sort of the soft landing approach, right? You want enough people, the senior people in AI and machine learning say, you know, we need other approaches. We really need other approaches. We're damn, we need other approaches. Maybe we should look to the brain. Okay, let's look to the brain. Who's got some brain ideas? Okay, let's, let's start a little project on the side here, trying to do brain idea related stuff. That's the ideal outcome we would want. So I don't want a total winter and yet I don't want it to be sunny all the time either.

• 1:40:14Lex Fridman?

  So what do you think it takes to build a system with human level intelligence? Where once demonstrated, you would be very impressed? So does it have to have a body? Does it have to have the C word we used before, consciousness? As an entirety, in a holistic sense?

• 1:40:35Speaker 01

  First of all, I don't think the goal is to create a machine that has human level intelligence. I think it's a false goal. Back to Turing, I think it was a false statement. We want to understand what intelligence is, and then we can build intelligent machines of all different scales, all different capabilities. You know, a dog is intelligent. I don't need, you know, that'd be pretty good to have a dog, you know? But what about something that doesn't look like an animal at all, in different spaces? So my thinking about this is that we want to define what intelligence is, agree upon what makes an intelligent system. We can then say, okay, we're now going to build systems that work on those principles, or some subset of them, and we can apply them to all different types of problems. And the kind, the idea, it's not computing.

• 1:41:17Speaker 01

  We don't ask, if I take a little, you know, little one-chip computer, I don't say, well, that's not a computer because it's not as powerful as this, you know, big server over here. No, not because we know that what the principles of computing are, and I can apply those principles to a small problem or to a big problem. And same, intelligence needs to get there. We have to say, these are the principles. I can make a small one, a big one, I can make them distributed, I can put them on different sensors, they don't have to be human-like at all. Now, you did bring up a very interesting question about embodiment. Does it have to have a body? It has to have some concept of movement. It has to be able to move through these reference frames I talked about earlier. Whether it's physically moving, like I need, if I'm going to have an AI that understands coffee cups, it's going to have to pick up the coffee cup and touch it and look at it with its eyes and hands, or something equivalent to that.

• 1:42:02Speaker 01

  If I have a mathematical AI, maybe it needs to move through mathematical spaces. I could have a virtual AI that lives in the internet, and its movements are traversing links and digging into files, but it's got a location that it's traveling through some space. You can't have an AI that just takes some flash thing input, you know, we call it flash inference, here's a pattern, done. No, it's movement, movement pattern, movement pattern, movement pattern, attention, digging, building, building structure, figuring out the model of the world. So some sort of embodiment, embodiment, whether it's physical or not, has to be part of it.

• 1:42:42Lex Fridman?

  So self-awareness in the way to be able to answer where am I?

• 1:42:45Speaker 01

  You're bringing up self-awareness, that's a different topic, self-awareness.

• 1:42:47Lex Fridman?

  No, the very narrow definition of self, meaning knowing a sense of self enough to know where am I in the space where it's interesting?

• 1:42:56Speaker 01

  Yeah, basically, the system, the system needs to know its location, or each component of the system needs to know where it is in the world at that point in time.

• 1:43:04Lex Fridman?

  So, self-awareness and consciousness, do you think, one, from the perspective of neuroscience and neurocortex, these are interesting topics, solvable topics, do you have any ideas of what, why the heck it is that we have a subjective experience at all?

• 1:43:20Speaker 01

  Yeah, I have a lot of fun with it.

• 1:43:22Lex Fridman?

  And is it useful, or is it just a side effect of us?

• 1:43:24Speaker 01

  It's interesting to think about. I don't think it's useful as a means to figure out how to build intelligent machines. It's, it's something that systems do, and we can talk about what it is, that are like, well, if I build a system like this, then it would be self-aware. Or, you know, if I build it like this, it wouldn't be self-aware. So that's a choice I can have. It's not like, oh my God, it's self-aware, you know, I can't turn, I heard an interview recently with this philosopher from Yale, I can't remember his name, I apologize for that. But he was talking about, well, if these computers are self-aware, then it would be a crime to unplug them. And I'm like, oh, come on, you know, that's not, you know, I unplug myself every night, I go to sleep. What, is that a crime? You

• 1:44:04Speaker 01

  know, I plug myself in again in the morning, there I am. So, you know, people get kind of bent out of shape about this. I have very definite, very detailed understanding or opinions about what it means to be conscious and what it means to be self-aware. I don't think it's that interesting a problem. You've talked about Christoph Koch, you know, he thinks that's the only problem. I didn't actually listen to your interview with him, but I know him and I know that's the thing.

• 1:44:31Lex Fridman?

  Well, he also thinks intelligence and consciousness are disjointed. So I mean, it's not, you don't have to have one or the other. So he is.

• 1:44:38Speaker 01

  I just agree with that. I just totally agree with that.

• 1:44:41Lex Fridman?

  So where's your thoughts on consciousness? Where does it emerge from? Because it is.

• 1:44:44Speaker 01

  So then we have to break it down into two parts. Okay. Because consciousness isn't one thing. That's part of the problem with that term is it means different things to different people. And there's different components of it. There is a concept of self-awareness. Okay? That can be very easily explained. You have a model of your own body. The neocortex models things in the world and it also models your own body. And, and then it has a memory. It can remember what you've done. Okay? So it can remember what you did this morning, can remember what you had for breakfast and so on. And so I can say to you, okay, Lex, were you conscious this morning when you, you know, had your, you know, bagel? And you'd say, yes, I was conscious.

• 1:45:25Speaker 01

  Now, what if I could take your brain and revert all the synapses back to the state they were this morning? And then I said to you, Lex, were you conscious when you ate the bagel? And he said, no, I wasn't conscious. I said, here's a video of eating the bagel. And he said, I wasn't there. I have no, that's not possible because I was, I must have been unconscious at that time. So we can just make this one-to-one correlation between memory of your body's trajectory through the world over some period of time, a memory, and the ability to recall that memory is what you would call conscious. I was conscious of that. It's self-awareness. And, and any system that can recall, memorize what it's done recently and bring that back and invoke it again would say, yeah, I'm aware. I remember what I did.

• 1:46:05Lex Fridman?

  Yep.

• 1:46:05Speaker 01

  All right. I got it. That's an easy one, although some people think that's a hard one. The more challenging part of consciousness is this is one that's sometimes used by the word qualia. Which is, you know, why does an object seem red? Or what is pain? And why does pain feel like something? Why do I feel redness? Or why do I feel painness? And then I could say, well, why does sight seems different than hearing? You know, it's the same problem. It's really, you know, these are all just neurons. And so how is it that, why does looking at you feel different than, you know, hearing you? It feels different, but there's just neurons in my head. They're all doing the same thing. So that's an interesting question. The best treatise I've read about this is by a guy named O'Regan, O'Regan.

• 1:46:50Speaker 01

  He wrote a book called, um, Why Red Doesn't Sound Like a Bell. It's a little, um, it's not, it's not a trade book easy to read, but it, and, and it's an interesting question. Take something like color. Color really doesn't exist in the world. It's not a property of the world. Property of the world that exists is light frequency. And that gets turned into, we have certain cells in the retina that respond to different frequencies, different than others. And so when they enter the brain, you just have a bunch of axons that are firing at different rates. And from that, we perceive color. But there is no color in the brain. I mean, there's, there's no color coming in on those synapses. It's just a correlation between some, some, some axons and some property of frequency. And that isn't even color itself.

• 1:47:35Speaker 01

  Frequency doesn't have a color. It's just a, it's just what it is. So then the question is, well, why does it even appear to have a color at all?

• 1:47:43Lex Fridman?

  Just as you're describing it, there's, seems to be a connection to those ideas of reference frames. I mean, it just feels like consciousness having the subject, assigning the feeling of red to the actual color or to the wavelength is useful for intelligence.

• 1:48:04Speaker 01

  Yeah, I think that's a good way of putting it. It's useful as a predictive mechanism or useful as a generalization idea. It's a way of grouping things together to say, it's useful to have a model like this.

• 1:48:13Lex Fridman?

  Yes.

• 1:48:15Speaker 01

  Think about the, there's a well-known syndrome that people who've lost a limb experience called phantom limbs. And what they claim is they can have their arm is removed, but they feel their arm. They not only feel it, they know it's there.

• 1:48:31Lex Fridman?

  Yeah.

• 1:48:32Speaker 01

  They, it's there. I can, I know it's there. They'll swear to you that it's there. And then they can feel pain in their arm and they'll feel pain in their finger. And if they move their, they move their nonexistent arm behind their back, then they feel the pain behind their back. So this whole idea that your arm exists is a model of your brain. It may or may not really exist. And just like, but it's useful to have a model of something that sort of correlates to things in the world so you can make predictions about what would happen when those things occur. It's a little bit of a fuzzy, but I think you're getting right towards the answer there. It's useful for the model of, to express things certain ways that we can then map them into these reference frames and make predictions about them. I need to spend more time on this topic. It doesn't bother me.

• 1:49:15Lex Fridman?

  Do you really need to spend more time?

• 1:49:16Speaker 01

  Yeah.

• 1:49:17Lex Fridman?

  It does feel special that we have subjective experience, but I'm yet to know why.

• 1:49:23Speaker 01

  I'm just, I'm just personally curious. It's not, it's not necessary for the work we're doing here. I don't think we need to solve that problem to build intelligent machines at all, not at all.

• 1:49:32Lex Fridman?

  But there is sort of the silly notion that you described briefly, that doesn't seem so silly to us humans is, you know, if you're successful building intelligent machines, it feels wrong to then turn them off. Because if you're able to build a lot of them, it feels wrong to then be able to, you know, to turn off the...

• 1:49:54Speaker 01

  Well, why? But just, let's, let's break that down a bit. As humans, why do we fear death? There's, there's two reasons we fear death. Well, first of all, I'll say when you're dead, it doesn't matter at all. Who cares? You're dead. So why do we fear death? We fear death for two reasons. One is because we are programmed genetically to fear death. That's a, that's a survival and propaganda genes thing. And we also are programmed to feel sad when people we know die. We don't feel sad for someone we don't know dies. There's people dying right now, they don't even come say it. I don't feel bad about them because I don't know them. But if I knew them, I'd feel really bad. So again, this are, these are old brain genetically embedded things that we fear death. Outside of those, those uncomfortable feelings.

• 1:50:40Speaker 01

  There's nothing else to worry about.

• 1:50:42Lex Fridman?

  Well, wait, hold on a second. Do you know the Denial of Death by Becker?

• 1:50:46Speaker 01

  No.

• 1:50:47Lex Fridman?

  You know, there's a thought that death is,

• 1:50:52Lex Fridman?

  you know, our whole conception of our world model kind of assumes immortality. And then death is this terror that underlies it all. So like,

• 1:51:04Speaker 01

  Well, some people's world model, not mine.

• 1:51:06Lex Fridman?

  But, okay, so what Becker would say is that you're just living in an illusion. You've constructed an illusion for yourself because it's such a terrible terror. The fact that

• 1:51:16Speaker 01

  What's the illusion?

• 1:51:17Lex Fridman?

  The illusion that death doesn't matter. You're still not coming to grips with

• 1:51:21Speaker 01

  The illusion of what? That death is?

• 1:51:23Lex Fridman?

  Uh, going to happen.

• 1:51:25Speaker 01

  Oh, like it's not gonna happen?

• 1:51:26Lex Fridman?

  You're, you're actually operating. You haven't, even though you said you've accepted it, you haven't really accepted the notion you're gonna die, is what you say. So it sounds like,

• 1:51:36Lex Fridman?

  it sounds like you disagree with that notion. I mean,

• 1:51:38Speaker 01

  Yeah, yeah, totally. I, I, like, I,

• 1:51:40Lex Fridman?

  So death is not such an important

• 1:51:42Speaker 01

  Every night I go to bed, it's like dying.

• 1:51:44Lex Fridman?

  A little deaths.

• 1:51:45Speaker 01

  It's, it's a little death. And if I didn't wake up, it wouldn't matter to me. Only if I knew that was gonna happen, it wouldn't be bothersome. If I didn't know it was gonna happen, how would I know? Then I would worry about my wife. So imagine, imagine I was a loner and I lived in Alaska. And I lived out there and there was no animals. Nobody knew I existed. I was just eating these roots all the time. And nobody knew I was there. And one day I didn't wake up. Where, what, what pain in the world would there exist?

• 1:52:13Lex Fridman?

  Well, so most people that think about this problem would say that you're just deeply enlightened or are completely delusional.

• 1:52:22Lex Fridman?

  But I would say, I would say that's a very enlightened way to see the world. Is, that's the rational one as well.

• 1:52:31Speaker 01

  Rational, that's right.

• 1:52:32Lex Fridman?

  But the fact is, we don't, um, I mean, we really don't have an understanding of why the heck it is we're born and why we die and what happens after we die.

• 1:52:42Speaker 01

  Well, maybe there isn't a reason, maybe there is. So I'm interested in those big problems too, right? You know, you, you interviewed Max Tegmark, you know, and those people like that, right? I'm interested in those big problems as well. And, um, In fact, when I was young, I made a list of the biggest problems I could think of. First, why does anything exist? Second, why did we have the laws of physics that we have? Third, is life inevitable? And why is it here? Fourth, is intelligence inevitable? And why is it here? I stopped there because I figured if you can make a truly intelligent system, that would be the quickest way to answer the first three questions.

• 1:53:19Speaker 01

  I'm serious.

• 1:53:20Lex Fridman?

  Yeah.

• 1:53:20Speaker 01

  And so I said, my mission, you know, you asked me earlier, my first mission is to understand the brain, but I felt that is the shortest way to get to true machine intelligence. And I want to get to true machine intelligence because even if it doesn't occur in my lifetime, other people will benefit from it because I think it'll occur in my lifetime, but you know, 20 years, you never know. And but that will be the quickest way for us to, you know, we can make super mathematicians, we can make super space explorers, we can make super physicists' brains that do these things and that can run experiments that we can't run. We don't have the abilities to manipulate things and so on. But we can build intelligent machines that do all those things and with the ultimate goal of finding out the answers to the other questions.

• 1:54:05Lex Fridman?

  Let me ask you another depressing and difficult question, which is, once we achieve that goal of creating, no, of understanding intelligence, do you think we would be happier, more fulfilled as a species?

• 1:54:21Speaker 01

  Understanding intelligence or understanding the answers to the big questions?

• 1:54:24Lex Fridman?

  Understanding intelligence.

• 1:54:25Speaker 01

  Oh, totally, totally. It would be a far more fun place to live.

• 1:54:30Lex Fridman?

  You think so?

• 1:54:30Speaker 01

  Oh, yeah, why not? I mean, you know, just put aside this, you know, Terminator nonsense and just think about, you can think about, we can talk about the risks of AI if you want.

• 1:54:43Lex Fridman?

  I'd love to, so let's talk about.

• 1:54:44Speaker 01

  But I think the world would be far better knowing things. We're always better than know things. Do you think it's better, is it a better place to live in that I know that our planet is one of many in the solar system and the solar system is one of many in the galaxies? I think it's a more, I dread, I used to, I sometimes think like, God, what would it be like to live 300 years ago? I'd be looking up at the sky, going, I can't understand anything. Oh, my God, I'd be like going to bed every night going, what's going on here?

• 1:55:06Lex Fridman?

  Well, I mean, in some sense, I agree with you, but I'm not exactly sure. So I'm also a scientist, so I have, I share your views, but I'm not, we're like rolling down the hill together.

• 1:55:19Speaker 01

  What's down the hill? I feel like we're climbing a hill.

• 1:55:21Lex Fridman?

  Whatever.

• 1:55:22Speaker 01

  We're getting, we're getting closest to enlightenment.

• 1:55:24Lex Fridman?

  Whatever.

• 1:55:26Lex Fridman?

  We're climbing, we're getting pulled up a hill by our curiosity.

• 1:55:29Speaker 01

  We are putting, our curiosity is pulling, we're pulling ourselves up the hill by our curiosity.

• 1:55:33Lex Fridman?

  Yeah, Sisyphus was doing the same thing with the rock.

• 1:55:35Speaker 01

  Yeah, yeah, yeah.

• 1:55:37Lex Fridman?

  But, okay, our happiness aside, do you have concerns about, you know, you talk about Sam Harris, Elon Musk, of existential threats of intelligent systems?

• 1:55:48Speaker 01

  No, I'm not worried about existential threats at all. I, there are, there are some things we really do need to worry about. Even today's AI, we have things we have to worry about. We have to worry about privacy and about how it impacts false beliefs in the world. And, and we have real problems that, and things to worry about with today's AI. And that will continue as we create more intelligent systems. There's no question, you know, the whole issue about, you know, making intelligent armaments and weapons is something that really we have to think about carefully. I don't think of those as existential threats. I think those are the kind of threats we always face and we have to face them here and, and, and we have to deal with them. The, I, we can, we could talk about what people think are the existential threats, but when I hear people talking about them, they all sound hollow to me.

• 1:56:33Speaker 01

  They're, they're based on ideas, they're based on people who really have no idea what intelligence is. And, and if, if they knew what intelligence was, they wouldn't say those things. So those are not experts in the field, you know?

• 1:56:46Lex Fridman?

  So, yeah, so there's two, right? There's, so one is like super intelligence. So a system that becomes far, far superior in reasoning ability than us humans.

• 1:56:59Speaker 01

  And how is that an existential threat?

• 1:57:02Lex Fridman?

  Then, so there's a lot of ways in which it could be. One way is us humans are actually irrational, inefficient, and get in the way of, of.

• 1:57:16Lex Fridman?

  Not happiness, but whatever the objective function is of maximizing that objective function.

• 1:57:20Speaker 01

  Yeah.

• 1:57:20Lex Fridman?

  And super intelligent.

• 1:57:21Speaker 01

  The paperclip problem and things like that.

• 1:57:23Lex Fridman?

  But so the paperclip problem, but with a super intelligent.

• 1:57:25Speaker 01

  Yeah, yeah, yeah. So we already faced this threat in some sense. They're called bacteria. These are organisms in the world that would like to turn everything into bacteria. And they're constantly morphing. They're constantly changing to evade our protections. And in the past, they have killed huge swaths of populations of humans on this planet. So if you want to worry about something that's going to multiply endlessly, we have it. And I'm far more worried in that regard. I'm far more worried that some scientists in a laboratory will create a supervirus or a super bacteria that we cannot control. That is a more existential step. Putting putting an intelligent thing on top of it actually seems to make it less existential to me.

• 1:58:10Speaker 01

  It's like it's it limits its power. It limits where it can go. It limits the number of things it can do in many ways. A bacteria is something you can't you can't even see. So that's only one of those problems.

• 1:58:20Lex Fridman?

  Yes, exactly. So the the other one, just in your intuition about intelligence, when you think about intelligence of us humans, do you think of that as something? If you look at intelligence on a spectrum from zero to us humans, do you think you can scale that to something far superior?

• 1:58:39Speaker 01

  Yeah.

• 1:58:39Lex Fridman?

  All the mechanisms we've been talking about.

• 1:58:41Speaker 01

  Let me I want to make another point here, Lex, before I get there.

• 1:58:43Lex Fridman?

  Sure.

• 1:58:44Speaker 01

  Intelligence is the neocortex. It is not the entire brain. If I the goal is not to be make a human. The goal is not to make an emotional system. The goal is not to make a system that wants to have sex and reproduce. Why would I build that? If I want to have a system that wants to reproduce and have sex, make bacteria, make computer viruses. Those are bad things. Don't do that. Those are really bad. Don't do those things. Regulate those. But if I just say, I want an intelligent system, why does it have to have any of the human-like emotions? Why does it even care if it lives? Why does it even care if it has food? It doesn't care about those things. It's just, you know, it's just in a trance thinking about mathematics, or it's out there just trying to build the space fort on Mars.

• 1:59:28Speaker 01

  It's a, that's a choice we make. Don't make human-like things. Don't make replicating things. Don't make things that have emotions. Just stick to the neocortex.

• 1:59:37Lex Fridman?

  So that's a view, actually, that I share, but not everybody shares, in the sense that you have faith and optimism about us as engineers of systems, humans as builders of systems, to not put in stupid things.

• 1:59:51Speaker 01

  So this is why I mentioned the bacteria one. Because you might say, well, some person's gonna do that. Well, some person today could create a bacteria that's resistant to all the known antibacterial agents. So we already have that threat. We already know this is going on. It's not a new threat. So just accept that, and then we have to deal with it, right? Yeah. So my point, it has nothing to do with intelligence. Intelligence is a separate component that you might apply to a system that wants to reproduce and do stupid things. Let's not do that.

• 2:00:23Lex Fridman?

  Yeah, in fact, it is a mystery why people haven't done that yet. My dad is a physicist believes that the reason, for example, nuclear weapons haven't proliferated amongst evil people. So one belief that I share is that there's not that many evil people in the world that would use, whether it's bacteria or nuclear weapons, or maybe the future AI systems, to do bad. So the fraction is small. And the second is that it's actually really hard, technically. So the intersection between evil and competent is small.

• 2:01:00Speaker 01

  Yeah. And by the way, to really annihilate humanity, you'd have to have, you know, sort of the nuclear winter phenomenon, which is not one person shooting, or even 10 bombs. You'd have to have some automated system that detonates a million bombs, or whatever many thousands we have.

• 2:01:16Lex Fridman?

  So extreme evil combined with extreme competence.

• 2:01:19Speaker 01

  And despite building some stupid system that would automatically, you know, Dr. Strangelove type of thing, you know. I mean, look, we could have some nuclear bomb go off in some major city in the world. I think that's actually quite likely, even in my lifetime. I don't think that's a likely thing, and it'll be a tragedy. But it won't be an existential threat. And it's the same as, you know, the virus of 1917, whatever it was, you know, the influenza. These bad things can happen, and the plague and so on. We can't always prevent it. We always try, but we can't. But they're not existential threats until we combine all those crazy things together in one form.

• 2:01:57Lex Fridman?

  So on the spectrum of intelligence from zero to human, do you have a sense of whether it's possible to create several orders of magnitude, or at least double that of human intelligence, talking about neural cortex?

• 2:02:12Speaker 01

  I think it's the wrong thing to say double the intelligence. Break it down into different components. Can I make something that's a million times faster than a human brain? Yes, I can do that. Could I make something that is, has a lot more storage than a human brain? Yes, I could do that. More cop is a comp. Can I make something that attaches to different sensors than a human brain? Yes, I can do that. Could I make something that's distributed? So these people, we talked earlier about the different neural cortex voting. They don't have to be co-located. Like, you know, they could be all around the place. I could do that, too. Those are the levers I have. But is it more intelligent? Well, it depends what I train it on. What is it doing?

• 2:02:51Lex Fridman?

  Well, so here's the thing. So let's say larger neural cortex, and or whatever size that allows for higher and higher hierarchies to form, we're talking about reference frames and concepts.

• 2:03:06Speaker 01

  So I could, could I have something that's a super physicist or a super mathematician? Yes.

• 2:03:09Lex Fridman?

  And the question is, once you have a super physicist, will they be able to understand something? Do you have a sense that it will be orders of like us compared to ants?

• 2:03:19Speaker 01

  Could we ever understand it?

• 2:03:20Lex Fridman?

  Yeah.

• 2:03:21Speaker 01

  Most people cannot understand.

• 2:03:26Speaker 01

  General relativity.

• 2:03:27Lex Fridman?

  Right.

• 2:03:28Speaker 01

  It's a really hard thing to get. I mean, you know, you can paint it in a fuzzy picture, stretchy space, you know?

• 2:03:33Lex Fridman?

  Yeah.

• 2:03:34Speaker 01

  But the field equations to do that and the deep intuitions are really, really hard. And I've tried, I'm unable to do it. It's easy to get, you know, it's easy to get special relative, but general relative, man, that's too much. And so we already live with this to some extent. The vast majority of people can't understand actually what the vast majority of other people actually know. We're just, either we don't have the effort to, or we can't, or we don't have time, or just not smart enough, whatever. So, but we have ways of communicating. Einstein has spoken in a way that I can understand. He's given me analogies that are useful. I can use those analogies for my own work and think about, you know, concepts that are similar. It's not stupid.

• 2:04:18Speaker 01

  It's not like he's existing some other plane and has no connection with my plane in the world here. So that will occur. It already has occurred. That's what my point of this story is. It already has occurred. We live with it every day. One could argue that when we create machine intelligence that think a million times faster than us, that it'll be so far, we can't make the connections. But, you know, at the moment, everything that seems really, really hard to figure out in the world, when you actually figure it out, it's not that hard. You know, we can, almost everyone can understand the multiverses. Almost everyone can understand quantum physics. Almost everyone can understand these basic things, even though hardly anybody, people could figure those things out.

• 2:04:55Lex Fridman?

  Yeah, but really understand.

• 2:04:57Speaker 01

  But you don't need to really, only a few people really don't understand.

• 2:05:00Lex Fridman?

  You need to only understand the, the projections, the sprinkles of the useful insights from that.

• 2:05:07Speaker 01

  That was my example of Einstein, right?

• 2:05:08Lex Fridman?

  Right.

• 2:05:09Speaker 01

  His general theory of relativity is one thing that very, very, very few people can get. And what if we just said those other few people are also artificial intelligences? How, how bad is that?

• 2:05:17Lex Fridman?

  In some sense, they are, right?

• 2:05:19Speaker 01

  Yeah, they say already. I mean, Einstein wasn't a very normal person. He had a lot of weird quirks. And so, so the other people who work with him. So, you know, maybe there already were sort of this astral plane of intelligence that we live with it already. It's not a problem. It's still useful and, you know.

• 2:05:36Lex Fridman?

  So do you think we are the only intelligent life out there in the universe?

• 2:05:40Speaker 01

  I would say that intelligent life...

• 2:05:44Speaker 01

  Has and will exist elsewhere in the universe, I'll say that. There is a question about contemporaneous intelligence life, which is hard to even answer when we think about relativity and the nature of spacetime. You can't say, "What exactly is this time someplace else in the world?" But I think it's, you know, I do worry a lot about the filter idea, which is that perhaps intelligent species don't last very long. And so, we haven't been around very long. And as a technological species, we've been around for almost nothing, you know, what, 200 years, something like that. And we don't have any data, a good data point on whether it's likely that we'll survive or not. So, do I think that there have been intelligent life elsewhere in the universe? Almost certain, of course.

• 2:06:29Speaker 01

  In the past, in the future, yes. Does it survive for a long time? I don't know. This is another reason I'm excited about our work, is our work meaning the general world of AI. I think we can build intelligent machines that outlast us. You know, they don't have to be tied to Earth, they don't have to, you know, I'm not saying they're recreating, you know, aliens, I'm just saying, if I asked myself, and this might be a good point to end on here, if I asked myself, you know, "What's special about our species?" We're not particularly interesting physically, we're not, we don't fly, we're not good swimmers, we're not very fast, we're not very strong, you know? It's our brain, that's the only thing.

• 2:07:12Speaker 01

  And we are the only species on this planet that's built a model of the world that extends beyond what we can actually sense. We're the only people who know about the far side of the moon and the other universes and, I mean, other galaxies and other stars and about what happens in the atom. There's no, that knowledge doesn't exist anywhere else, it's only in our heads. Cats don't do it, dogs don't do it, monkeys don't do it, it's just on, and that is what we've created that's unique. Not our genes, it's knowledge. And if I asked me, "What is the legacy of humanity?", what should our legacy be? It should be knowledge. We should preserve our knowledge in a way that it can exist beyond us. And I think the best way of doing that, in fact, you have to do it, is it has to go along with intelligent machines to understand that knowledge.

• 2:07:54Speaker 01

  That's a very broad idea, but we should be thinking, I call it a state planning for humanity. We should be thinking about what we want to leave behind when as a species, we're no longer here. And that will happen sometime, sooner or later, it's gonna happen.

• 2:08:08Lex Fridman?

  And understanding intelligence and creating intelligence gives us a better chance to prolong?

• 2:08:14Speaker 01

  It does give us a better chance to prolong life, yes. It gives us a chance to live on other planets, but even beyond that, I mean, our solar system will disappear one day. Just give it enough time, so I don't know, I doubt we will ever be able to travel to other things. But we could tell the stars, but we could send intelligent machines to do that.

• 2:08:34Lex Fridman?

  So you have a, you have an optimistic, a hopeful view of our knowledge of the echoes of human civilization living through the intelligent systems we create?

• 2:08:45Speaker 01

  Oh, totally. Well, I think the intelligent systems we create are in some sense the vessel for bringing them beyond Earth. Or making them last beyond humans themselves, so.

• 2:08:56Lex Fridman?

  How do you feel about that, that they won't be human, quote unquote?

• 2:09:00Speaker 01

  Who cares? It's not, but human, what is human? Our species are changing all the time. Human today is not the same as human just 50 years ago. It's, what is human? Do we care about our genetics? Why is that important? As I point out, our genetics are no more interesting than a bacterium's genetics. It's no more interesting than, you know, a monkey's genetics. What we have, what's unique and what's valuable is our, is our knowledge, what we've learned about the world. And that is the rare thing, that's the thing we want to preserve. It's, who cares about our genes?

• 2:09:31Lex Fridman?

  It's the knowledge.

• 2:09:32Speaker 01

  It's the knowledge.

• 2:09:33Lex Fridman?

  That's a really good place to end. Thank you so much for talking today.

• 2:09:36Speaker 01

  Ah, it was fun.