Jeff Hawkins: Thousand Brains Theory of Intelligence | Lex Fridman Podcast #25

The following is a conversation with Jeff Hawkins. He's the founder of the Redwood center for theoretical neuroscience in 2002 and Numenta 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 neocortex and propose artificial intelligence architectures, approaches and ideas that are inspired by the human brain. These ideas include hierarchical temporal memory from 2004 and new work the Thousands Brains 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 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 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 lexfriedman spelled F R I D. And now here's my conversation with Jeff Hawkins. 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?

So there's a clear answer to that question. My primary interest is understanding the human brain, no question about it. But 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. I actually believe that studying the brain is actually the fastest way to get to machine intelligence.

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

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. Let's discover the principles by how they work. Because intelligence isn't just some mechanism and it's not just some capabilities. It's like, okay, we don't even know where to begin on this stuff. 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 some of the things are going to be necessary, I believe, to create intelligent machines.

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 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. So the good old fashioned AI, the expert systems, 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. 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 going to go. There's a big, big gap there, huge gap. I think the quickest way of bridging that gap is to figure out how the brain does that. And then we can sit back and look and say, oh, which of these principles that the brain works on are necessary and which ones are not clear? We don't have to build this in. Intelligent machines aren't going to be built out of organic living cells. But there's a lot of stuff that goes on the brain that's going to be necessary.

So let me ask maybe, before we get into the fun details, let me ask maybe a depressing or 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?

Yeah, I don't believe that's the case. I have never believed that's the case. There's not been a single thing we've ever, humans have ever put their mind to. 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, Alon 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 to suggest this is the case. And I just never even consider that's a possibility. I would also say today we understand so much about the neocortex. 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. 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 going to be able to do this. This is not a problem anymore. Just takes time. Humans if ever puts their mind to. 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. Alan 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 to suggest this is the case. And I just never even consider that's a possibility. I would also say today we understand so much about the neocortex. 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. The pieces we don't know are clear to me. But the framework is all there and it's like, oh, okay, going to be able to do this. This is not a problem anymore. Just takes time and effort. But there's no mystery, a big mystery anymore.

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

Yeah, sure. A 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, only mammals have a neocortex in humans. In primates, it's very large. In the human brain, the neocortex occupies about 70, 75% of the volume of the brain. It's huge. And the old parts of the brain, there's lots of pieces there, there's a spinal cord and there's the brain stem and the cerebellum and the different parts of the basal ganglia and so on. In the old parts of the brain, you have the autonomic regulation, like breathing and heart rate. You have basic behaviors. So like walking and running are controlled by the old parts 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. And we associate with the neocortex all the things we think about as 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. That's like the rough division. 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. It gives you a system to study. 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. 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. A 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 a 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. And these evolve 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 Malcastle in 1978, I think it was, that the neocortex all works on the same principle. 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.

So the low level, the building blocks.

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

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

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 experiment was actually done by Morganka, sir.

Oh, boy.

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, person is 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 become. Does something else. It picks up another task. So, and it's, it's. So it's this, 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. It's called the common cortical algorithm, if you will. 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, then you understand what all these other cognitive functions are.

So if you were to sort of put neocortex outside of your book on intelligence, you look, if you wrote a giant tome, a textbook on the neocortex, 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?

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 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 neocortex and we publish our results and so on. So about three years ago we had a real breakthrough in this field, just 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 big. It's for the most part all correct. It's facts and experimental results and measurements and all kinds of stuff. But none of that has been really assimilated into a theoretical framework. Right. It's data without, in the language of Thomas Kuhn, the historian would be sort of a pre paradigm science. Lots of data, but no way to fit in together. I think almost all of that's correct. There's going to be some mistakes in there and for the most part there aren't really good cogent theories about 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, yeah, people just like scratching their heads wrong 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.

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

I don't think so. 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.

We'Ll get to that.

But, so I don't think it's. 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. 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, all this stuff you've collected, none of it makes sense. All these different things are just sort of around and then you're going to 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 personally feel like we passed that little thing about a couple years ago, well, that big thing a couple years ago, so we can talk about that. Time will tell if I'm right. But I feel very confident about it. That's what I'm willing to say it.

On tape like this, 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?

Yeah. So one of the things that neuroscientists just sort of missed for many, many years, and especially people who are 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 were 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 inputs completely. If I were to touch something like a coffee cup, as I move my fingers, the input changes. 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 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 is like. Vision is this 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. You won't understand the brain, nor will 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 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 that our experience is 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 and navigate and know how it's going on. That's what the memory referred to. And many people just, they were thinking about certain processes without memory at all. They're just processing things. And then finally the hierarchical component was a reflection to that. The neocortex, although it's just uniform sheet of cells, different parts of it project to other parts, which project 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 model, memory based and hierarchical processing. 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.

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

Yeah.

So in terms of time, how do you think of nature of time across different timescales? You mentioned things changing, sensory inputs changing every 10, 20 minutes. What about every few minutes, every few months and years?

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 start to for minutes, you know, so you could hold a certain perception activity for a certain period of time, but most of them don't last that long. If you think about your thoughts are 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. You have to store that. If I ask you what did you have for breakfast today? That is memory, you've built that into your model of the world. Now you remember that and that memory is in the, in the synapses, is basically in the formation of synapses. And so you're sliding into what you said different timescales. There's timescales of which we are understanding my language and Moving about and seeing things rapidly and over time. That's the timescales of activities of neurons. But if you want to get longer timescales, 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 store it for now.

So does memory also need to have. So the hierarchical aspect of reality is not just about concepts, it's also about time. Do you think of it that way?

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, then I'm at the coffee cup. I say, well, time is not an inherent property of the model I have of this cup. Whether it's a visual model or a 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 cell phone? My brain has learned a model of the cell phone. If you have a smartphone like this, and I say, well, this has time aspects to it. I have expectations when I turn it on, what's going to happen? What are. How long it's going to take to do certain things. If I bring up an app, what sequences. It's like melodies in the world. 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.

Okay, so it's, it's, it really is just a fourth dimension that's infused deeply. And you have to make sure that your models of intelligence incorporated. So, like you mentioned, the state of neuroscience is deeply empirical. A lot of data collection. It's, you know, that's. That's where it is. You mentioned Thomas Kuhn, right?

Yeah.

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 where string theory is.

Is that where it's a mixture of all those things? Although definitely where we are right now is 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 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. First of all, there are 100 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 supported. Let's keep going with that one. So the way I kind of view it, when we do our work, we come up, we look at all this empirical data, and 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. So every piece of empirical data is a constraint on a 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 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, a set of constraints, and even if you're working in one little part of the neocortex, 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. It's just mathematically almost impossible not to be. So that's the curse. And the advantage of what we have, the curse is 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. 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. We have people we've collaborated with. 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. New neuroscience experiments take a long time, years, although some people are doing that now, too. But between all of these things, I think it's a reasonable. It's actually a very, very good approach. We are blessed with the fact that we can test our theories out the yin yang here because there's so much unassimilar data. And we can also falsify our theories very easily, which we do often.

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

Yeah, I think that's the general nature of aha moments, and it's Copernicus. You could say the same thing about Darwin. You could say the same thing 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 when you were working on trying to discover the structure of the double helix, and when you came up with the structure, that ended up being 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. 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 it 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.

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

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 is 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 tea with him afterwards. He was interested in a different problem. He was focused on consciousness.

The easy problem. Right.

Well, 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. When he was director of the Cold Spring Harbor Laboratories, he was really behind moving in the direction of neuroscience there. He had a personal interest in this field. I have met with him numerous times. In fact, the last time was a little bit over a year ago. I gave a talk at Cold Spring Harbor Labs about the progress we were making in our work. It 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 to him was the director of the lab, Bruce Stillman. So these guys are in the front row of this auditorium. Nobody else in the auditorium wants to sit in the front row because there's Jim Watson, there's the director. And I gave a talk and then I had dinner with Jim afterwards. But there's a great picture of my colleague Subha Taya Madtuk, where I'm up there screaming the basics of this new framework. We have Jim Watson's on the edge of his chair. He's literally on the edge of his chair, intently staring up at the screen. When he discovered the structure of DNA, the first public talk he gave was at Cold Spring Harbor Labs. So, and there's a picture. There's a famous picture of Jim Watson standing at the whiteboard with. With an overhead thing pointing at something with. Holding a double helix with his pointer. And it actually looks a lot like the picture of me. So there was a sort of funny. There's air, I am talking about the brain, and there's Jim Watson staring Intently at it. And of course, there was, you know, whatever. 60 years earlier, he was standing, you know, pointing at the double helix.

And that's one of the great discoveries in, in all of, you know, whatever. Biology, science, all science is DNA. So. So it's funny that there's echoes of that in your presentation. Do you think in terms of evolutionary timeline and 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. From the birth of human, of life on Earth, how likely would we develop the mechanism of the neocorte?

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

Maybe correlated, maybe correlated, maybe not.

And we don't really have enough data to make a judgment about that. I would say definitely was a big leap. And I can tell you why I don't think it was just another incremental step. I'll get to that 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. Life formed on Earth billions of years ago. Whether it was introduced here or 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 multicellar cellular life, it took a long, long time to get the neocortex. And we've only had the New York text for a few hundred thousand years, so that's like nothing. So is it likely? Well, it 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 is A qualitative difference in all other evolutionary steps. I can try to describe that. You'd like, sure.

In which way?

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. We create music. Is there a really survival advantage to that? Maybe, maybe not. What about mathematics? Is there a real survival advantage to mathematics? Well, maybe you could stretch it. You can try to figure these things out. But mostly evolutionary history. Everything had immediate Survival advantages to it. I'll tell you a story which I like may or may not be true, but the story goes as follows. Organisms have been evolving since the beginning of life here on Earth and adding this complexity onto that, this sort of complexity onto that. And the brain itself is evolved this way. In fact, there's old parts and older parts and older, older parts of the brain that just keeps calming on new things and we keep adding capabilities. When 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 I think happens is that evolution took a mechanism, and this is in our recent theory, but it took a mechanism evolved a long time ago for navigating in the world, for knowing of where you are. These are the so called grid cells and place cells of an old part of the brain. And it took that mechanism for building maps of the world and knowing where you are in 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, concepts. Almost concepts, yes. And not just almost exactly. And it just started replicating this stuff. Right. You just think more and more and more of it. So we went from being sort of dedicated purpose neural hardware to solve certain problems that are important to survival, to a general purpose neural hardware that could be applied to all problems. And now it's escaped the orbit of survival. We are now able to apply it to things which we find enjoyment but aren't really clearly survival characteristics. And that it seems to only have happened in humans to a large extent. And so that's what's going on. We've sort of escaped the gravity of evolutionary pressure in some sense in the neocortex. And it now does things which that are really interesting. Discovering models of the universe which may not really help us, doesn't matter. How does it help us surviving knowing that there might be multiverses or 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.

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, let's not get Too quick.

Yeah, but, but you know, evolution works at one time frame and. Well, let's. Yeah, it's survival. If you think of survival of the phenotype, survival of the individual, 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.

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

Call it the Thousand Brain theory of intelligence.

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

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 my finger was touching the side, my index finger, and then I moved it to the top and I was going to feel the rim at the top of the cup. 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 going to feel before it touches it. You can just think about it and imagine it. We know that the brain's making predictions all the time. The question is, what does it take to predict that? 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 going to 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. Which tells me then that the neocortex 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. Then we quickly, very instantly can say, well, every part of my skin could touch this cup, and therefore every part of my skin is making predictions. And every part of my skin must have a reference frame that it's using to make predictions. The big idea is that throughout the neocortex, everything is being stored and referenced in reference frames. You can think of them like XYZ 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. 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 location 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. The brain works by assigning everything, every input, everything to reference frames. And there are thousands, hundreds and thousands of them active at once in your neocortex. It's a surprising thing to think about. But once you internalize this, you understand that it explains almost all the mysteries we've had 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 going to have reference frames where it's assigned that input to each square millimeter can learn complete models of objects. What do I mean by that? 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. 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 it's only looking at a small part of the world, can build up a complete model of an object. If you think about the part of the brain which is getting input from all my fingers, they're spread across the top of your head here. This is the somatosensory cortex. There's columns associated all the different areas of my skin. What we believe is happening is that all of them are building models of this cup. Every one of them or things. 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. 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 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. 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 to 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 way people have thought about it.

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 do you know which one has done the best job of forming the great question?

Let me try explain. There's a problem that's known in neuroscience called the sensor fusion problem. And so the idea is something like, oh, the image comes from the eye. There's a picture on the retina and it gets projected through 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. 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, it's 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 get all these guys voting. There's auditory models of the cup, there's visual models of the cup, those tactile models of the cup. 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 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 or touching. Now, they can do a pretty good job if they're allowed to move over, touch. I could 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 I'm only invoking one little column. I can only see part of something because I have to move the straw around. But if I open my eyes, I see the whole thing at once. 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 if I move my eyes and 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 little piece of spaghetti. Each one of them says, I think. 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. You could say. And one column says, I think it could be a coffee cup, soda can or a water bottle. Another column says, I think it could be a coffee cup or telephone or camera or whatever. 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 cells, types in each column send the projections across the brain and that's the voting occurs. 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 got to be the coffee cup. At that point, they all know it's a coffee cup. And at that point everyone acts as if it's the coffee cup. We know it's a coffee cup. 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, 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.

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

Yeah, it does.

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

Yeah, it does. And well, first, the primary face 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 and 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 in the cortex 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. But of course we had no prior idea how these things happen. So let's go with that. And 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 very confident that that's what's happening. And I can give you some examples that help you think about that. It's not. We understand it completely, but I understand it better than I've described in any paper so far. But we did put that idea out there. Says, okay, it's a good place to start, you know, and the evidence would suggest that'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 frame framework?

Yeah, so there, 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, they talk about like a memory palace that helps you remember completely random concepts by sort of trying to put them in a physical space in your mind and putting them next to each other.

Called the method of loci.

Loci.

Yeah.

For some reason that seems to work really well.

Yeah.

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

But that's not. But that's a very, very telling one. Okay.

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

So, 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. If you want to remember something, you have to basically navigate through a reference frame the same way a rat navigates to a mave and the same way my finger rat navigates to this coffee cup. We're moving through some space. If you have a random list of things you were asked to remember by assigning them to a reference frame, you already know very well to see your house. 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 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, 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 room, the coffee cup, imagining me touching it. But I can also mentally move my house. Now we can ask yourself, are all concepts stored this way? There was some recent research using human subjects, an fmri and I'm going to apologize for not knowing the name of the scientist who did this. But what they did is they put humans in this FMRI machine, which is one of these imaging machines. And they gave the humans tasks to think about birds. So they had different types of birds and birds that look big and small, and long necks and long legs, things like that. And what they could tell from the FMRI was a very clever experiment. Get to tell when humans were thinking about the birds, that the birds, the knowledge of birds was arranged in a reference frame similar to the ones that are used when you navigate in a room. These are called grid cells and there are grid cell like patterns of activity in the neocortex when they do this. It's a very clever experiment. And what it basically says that even when you're thinking about something abstract and you're 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 mechanism that we propose, that grid cells, which exist in the old part of the brain, the entorhinal cortex, that that mechanism is now similar mechanism is used throughout the neocortex. It's the same nature preserve. This interesting way of creating reference frames. 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 similar to the method of loci. But in this case the birds are related, so they create their own reference frame which is consistent with bird space. And when you think about something, you go through that, you can make the same example. Let's take a math, mathematics. Let's say you want to prove a conjecture. What is a conjecture? A conjecture is a statement you believe to be true but you haven't proven. Might be an equation. I want to show that this is equal to that. 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. When you do mathematical operations, a simple one might be multiply or divide, but you might be able to laplace, transform, or something else that is like a movement in the reference frame of the math. You are literally trying to discover a path from one location to another location in a space of mathematics. 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.

Yeah. So if you dig in an 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 take a step back, how you think of the reference frame in that context is, 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?

So you have many, many reference frames. I mean, 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.

But how many reference frames does the coffee cup have? Well, it's on a table.

Let's say you could ask how many reference frames could the column in my finger that's touching the coffee cup. Half, because there are many, many copy. There are many, many models of the coffee cup. So the coffee. There is no model of 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 rim, 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 frame which is called this cup. And now I have this memento 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 sign the name, 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.

So my question is, even though you mentioned reference frames a lot, I almost feel it's really useful to dig into how you think, 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.

Okay, so let's just say that we're going to have some neurons in the brain, not many, actually 10,000, 20,000, are going to create a whole bunch of reference frames. What does it mean? What is a reference frame in this case? 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 xyz. 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 one through 20. That's a different type of reference frame. It's a Cartesian reference frame. The interesting thing about the reference frames in the brain, and we know this because these have been established through neuroscience studying the entorhinal cortex. So I'm not speculating here. This is known neuroscience in an old part of the brain. The way these cells create reference frames, they have no origin. So what is more like you have a point, a point in some space, and 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? So it's a different type of reference frame. And if you want, I can describe in more detail, I can paint a picture. How you might want to think about that.

It's really helpful to think it's something you can move through. But is it helpful to think of it as spatial in some sense? Or is there something.

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

How many dimensions can it be? Crazy number of dimensions.

Well, that's an interesting Question. In the old part of the brain, the entorhinal 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 whether the rat is using these two dimensional reference frames and know where it is in the maze. We said, okay, well what about, 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 there's, this is a current area of active research and it seems like somehow the, the neurons in the entorhinal cortex can learn three dimensional space. Two members of our team, along with ILAFET from MIT just released a paper this literally last week. It's on BioRxiv, where they show that you can, the way these things work. And unless you want to, I won't get into the detail. But grid cells can represent any N dimensional space. It, there's, it's, 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 and with two dimensional projections, the number of dimensions. Well, that's an interesting question. In the old part of the brain, the entorhinal 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 whether the rat is using these two dimensional reference frames and know where it is in the maze. We said, okay, well what about, what about bats? That's a mammal and they fly in three dimensional space. How do they so, and you could have one dimensional model. So there's nothing inherent about the mathematics about the way the neurons do this, which, which constrain the dimensionality of the space, which I think was important. So obviously I have a three dimensional map of this cup. Maybe it's even more than that, I don't know. But it's 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?

So in terms of each individual column building up more and more information over time, do you think that mechanism is well understood to do that?

They seem to know where they are. Right. So there's this is A current area of active research. And it seems like somehow the rep.

The in your mind you've proposed a lot of architectures.

There is that neurons in the entorhinal cortex can learn three dimensional space.

We just key piece. Or is it is the big piece the thousand brain theory of intelligence. The ensemble of it all.

Well I think they're both two members of our team along with El Fett from MIT just released a paper this literally last week. It's on Bio Archive where I mean clearly the concept as a theorist, the concept is most exciting, right? We want a little concept, a high level concept. This is a totally new way of thinking about how the near characteristics work. 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 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 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 so ons. 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, but these are other things we know it has to do and it's not doing those yet. I would say we're. Well 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 model. 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 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.

So what would you say is obviously.

I have a three dimensional map of this cup. Maybe it's even more than that, I don't know.

But one of the harder open problems or one of the ones that have been bothering you keeping you up at night the most.

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?

Yeah, please.

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 in a 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?

So in terms of each individual column building up more and more information over time, do you think that mechanism is well understood?

Different orientations, Right. I can rotate my finger around here and that doesn't change. I can make that prediction. And 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 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 three dimensional. 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 two components work together, how it is that I. I combine orientation, my. The orientation of my sensor 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?

Well, I think they're both big. I mean clearly the concept, as a theorist, the concept is most exciting as well as the location is a tricky problem and I think I've made progress.

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

Yeah, I warned you.

No, no, no, it's really Good. But 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.

Right. The high level concept. This is a totally new way of thinking about how the New York 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 room that's outside of just the coffee cup. How does it get.

Yeah. So connected, do you think? Yeah. And that is another really interesting question. I'm going to throw that under the rubric or the name of attentional problems. First of all, we have this model. I have many, many models.

And also the question, does it matter? Because.

Well, it matters for certain things. Of course it does. Maybe what we think of that 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 way to think about is the following. One way to think about it is we have all these models of the world, okay. And we model everything. And as I said earlier, I kind of snuck it in there. Our models are actually. We build composites 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 so ons. And we have that still that same level of detail, the 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 posit structure. 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 a walls and so on. Now we can just arrange them in these things a certain way and go, oh, that's in the mentor conference room. 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 like say, oh, I'm in this room. Do I recognize the room? Then I can say, oh, look, there's a table here. By attending to the table, I'm then assigning this table in the context of the room. Next on the table there's a. It's like, okay, it kind of works. 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.

So what would you say is coffee cup.

Oh, and on the table there's a logo. And in the logo there's the word dementia. Oh, look, in the logo there's the letter E. Oh, look, it has an unusual serif and it doesn't actually, but pretend it does serif. So the point is, you're attention is kind of drilling deep in and out of these nested structures. And I can pop back up and I can pop back down. I can pop back up and I can pop that down. So when I attend to the coffee cup, I haven't lost the context of everything else. But. But it's sort of. There's this sort of nested structure.

So the attention filters the reference frame formation for that particular period of time.

Yes, it basically a moment to moment. You attend the subcomponents and then you can tend to subcomponents. To subcomponents.

And you can move up and down.

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, but most people don't even think about this. You know, you don't. You just walk in a room and you don't say, oh, I looked at the chair and I looked at the board and looked at that word on the board and I looked over here, what's going on? Right.

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

Me personally, like my personal day. Yeah, unfortunately, I'm afflicted with too much of the former.

Fortunately or unfortunately?

Yeah.

You don't think it's useful?

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 on my bike, riding, about on 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.

Are you, when you think 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?

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 have my place of sense in the world. 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? And then I would calculate my error again and see how the errors could accumulate. So even something as simple as getting up in the middle 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, I'm, I'm very, in this group here, people, they know, they do. I do this all the time. I come in with these introspective ideas and say, well, have you ever thought about this? Now watch. Well, let's all do this together and it's helpful.

It's not if it is one of the harder open problems.

As long as you just. 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.

So let's talk a little bit about deep learning and the success. Are one of the ones that have been bothering you keeping up at night the most.

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?

Yeah, please.

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 coffee cup.

This is in the applied space of neural networks. The ideas of training model on. On data and these, these simple computational units, neuron artificial neurons that with back propagation 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.

That is true, but it's insufficient. Think about my finger touches the edge of the coffee cup. My finger can touch it.

The limitations of those approaches. What do you think are his strengths relative to your major efforts of constructing a theory of human intelligence?

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

But some of it is in just your intuition. What are your.

Well, I have. I have a little bit more than intuition. Different orientations. Right. I can rotate my finger around here and that doesn't change. I can make that prediction. And 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. But I just want to say 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 is the same kind of basic idea. So if my finger were a rat in three dimensions, I have a three works. They Use things that we. 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. And the nature of hierarchy that came also from neuroscience. And so there's a lot of things the learning rules basically not back prop but other 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. You know so heavy intelligence. I'll be.

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

Yeah. We had a paper in 2016 called why Neurons have thousands of Synapses. And it. And if you read that paper you'll. You'll know what I'm talking about here. A real neuron in the brain is how it is that I combine orientation the orientation of my sensor complex thing. Let's just start with the synapses on it which is a connection between neurons. Real neurons can everywhere from 5,30,000 synapses on them. The ones near the cell body, the ones that are close to the soma of the cell body. Those are like the ones that people model in artificial neurons. There's a few hundred of those. Maybe they can as well as the location is a tricky problem. And I think I've made progress on.

It so at a bigger version of that. So perspective is super interesting and 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 synapses it just doesn't affect the cell body enough to make any difference.

Any one of them individually.

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 they. You know you get.

But super specific.

Yeah, I warned you. No no, no.

It's really good.

But it's 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 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 the dendritic spike.

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 and dendritic spike travels through the dendrites and can reach the soma or the cell body. Now when it gets there, it changes the voltage, which is sort of like going to 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 information that you bring to the table about everything else in the.

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 10, 20 synapses at a time. And they're acting like predictions. So the neuron actually is a predictive.

Engine on its own room that's outside of just the coffee cup. How does it get.

Yeah. So connected, do you think? Yeah. And that is another really interesting question. I'm going to throw that under the rubric or the name of attentional problems. First of all, we have this model. I have many, many models. It can fire when it gets enough, what they call proximal input from those ones near the cell fire. 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 in 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 does it all the neurons in the excited.

And also the question does it matter? Because.

Well, it matters for certain things. Of course it does. Maybe what we think about as a coffee, neurons in the brain are surrounded by these inhibitory neurons and they're very fast. The inhibitory neurons, these basket cells. And up 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 way to think about it is the following. One way to think about it is we have all these models of the world. If I get my spike out a little bit sooner than someone else, I inhibit all my neighbors around me. What you end up with is a different representation. You end up with a representation that matches your prediction. It's a sparser representation, meaning it's fewer neurons are active, but it's much more specific. We showed how networks of these neurons can do very sophisticated temporal prediction. Basically summarize this. Real neurons in the brain are. And we model everything. And as I said earlier, I kind of snuck it in there. Our models are actually we, we build time based prediction engines and, and they, and there's no concept of this at all in artificial, what we call point neurons. I don't think you can build a brain without them. I don't think you can build intelligence because it's the, it's where large part of the time comes from. It's, it's. These are predictive posit 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 a walls and so on. Now we can just arrange them in these things a certain way and go, oh, that's in the mentor conference room. The models and the time, there's a prior and a prediction and an action, and it's inherent through every neuron in the neocortex. I would say that point neurons sort of model a piece of that and not very well at that either. But 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 and what we do is when we go around the work is 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 detect the presence of some 10 to 20 active synapses at the same time, as opposed to world. When we experience the world by walking to a room, for example, the first thing I do, I 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 dentist. 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. And I think that's actually another essential component because the brain works on sparse patterns and all that mechanism is based on sparse patterns. And I don't actually think you could build real brains or Machine intelligence without incorporating some of those ideas. Assigning this table in the context of the room. Oh, on the table there's a.

If you 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, and I mean everything you just mentioned in the past, you can trust me.

Coffee cup. Oh, and on the table there's a logo. And in the logo there's the word no menta. Oh, look, in the logo there's a. The letter E. Oh look. It has an unusual serif and it doesn't actually, but pretend it does. So the point is you, your attention is kind of drilling. 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.

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 and what kind of representation.

Not as easy as there's many other types of neural networks are that are more amenable to pure analog. Deep in and out of these nested structures. And I can pop back up and I can pop back down, I can pop back up and I can pop back down just this, you know, especially very simple networks, you know, oh, I have four neurons and so I, when I attend to the coffee cup, I haven't lost the context of everything else. But, but it's sort of, there's this sort of nested structure.

So the attention filters the reference frame formation for that particular period of time.

Yes, it basically a moment to moment, you attend the sub components and then you can attend the subcomponents to subcomponents.

And you can move up and down that.

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 most people don't even think about this. They're doing this. Can we describe them mathematically, what they're doing type of thing. Even the complexity of convolutional neural networks today, it's a mystery. They can't really describe the whole system. It's different. My colleague Subutan Ahmad, he did a nice paper on this. You can get all this stuff on our website, if you're interested. Talking about the mathematical properties of sparse representations. What we can do is we can show mathematically, for example, why 10 to 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. Walk in a room and you don't say, oh, I looked at the chair and I looked at the board and looked at that word on the board and I looked over here, what's going on. Right. Simulations. But the system can't be analyzed completely. Any complex system can, so that's out of the realm. But 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. That.

So I think it's represented your day. Are you deeply aware of this? In what part can you actually relax and just be. Jeff, refreshing and useful for me to be talking to you about deep neural networks? Because your intuition basically says, like my personal day.

Yeah, unfortunately, I'm afflicted with too much.

Of the former that we can't achieve anything like intelligence with artificial neural networks.

Well, not in their current form.

Not in the current form.

Sure. We can do it in the ultimate form. Sure.

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. I. I think unfortunately they are unfortunate.

Yeah.

So you don't think it's useful?

Oh, it is useful. Totally useful. I think about this stuff almost all the time. And I met one of my primary button 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. The. 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. On computation getting faster and faster.

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

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 and 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.

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

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 is saying it's, 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 yarns. 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?

No, I don't think so. We can do bigger problems 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 just, they're bigger and trained more and we have more label data and so on. 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 the ways of thinking is when I'm asleep 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 on my bike ride, I think about on walks. I'm just constantly thinking about this. I have to almost schedule time 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, 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 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 Subataimad 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 need to proselytize what we've learned and we need to show how it's beneficial to the machine learning. So we have a plan in place right now. In fact, we just did our first paper on this. I could tell you about that, but 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 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 nmenta, what have they done? Is that useful for us?

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

Yes. In the short term? Yes.

This is the. Sorry to interrupt the. The open question. Is it. It certainly feels from my perspective that in the long term, some of the ideas we've been talking about will be extremely useful. The question is whether in the short term.

Well, this is always what 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, without going out of business? 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 throw it all out and start over again. The first thing that we've done is we focus on these sparse representations to not think about this stuff because it's mentally taxing.

When you think 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?

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, so just, 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 for any.

Set of sensory inputs.

It doesn't matter of anything, just matter. Any part of the brain.

But which neurons differs, which neurons are active? Yeah.

So let me put, let's say I take 10, 10,000 neurons that are representing something. They're sitting there in a block together. It's a teeny little block in around 10,000 neurons and they're representing a location, they're representing a cop, they're representing the input from my sensors. I don't know, it doesn't matter at all. It's representing something. The way the representations occur. It's always a sparse representation, meaning 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. 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. Brains are incredibly robust. Neurons are dying all the time and spasming and synapses falling apart and all the time. And it keeps working. So what Subutai and Louise, one of our other engineers here, have done, I've shown they're introducing sparseness into convolution 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 neurons are active and the connections between them, that you get some very desirable properties. One of the current hot topics in deep learning right now are these adversarial examples. So you give me any deep learning network and I can give you a picture that looks perfect and you're going to call it, you're going to say the monkey is an airplane. That's a problem. And DARPA just announced some big thing. They were trying to have some contest for this. But 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 just literally in January or February, just like last month we did that. I think it's on Biorxiv right now or on Archive. You can read about it. But so that's like a baby step, okay? That's taking 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 onto this.

What's your intuition? Why sparsity leads to robustness.

And getting into that, I started saying, oh, well, grid cells 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?

Yeah.

And then I would calculate my error again and see how the errors can accumulate. So even something as simple as getting.

Because it feels like it would be less robust.

Why, why would you feel the rest of the bus to you?

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

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

There's still a lot.

Yeah. So here's an intuition for it. This is a bit technical. So for engineers, machine learning people, this will be easy. But 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. 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 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 10,000. So I have 200 cells active. Now let's say I pick randomly 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. I can't move just one cell or two cells or three cells or four cells. I have to move 100 cells cells.

And that makes them robust in terms of further. So you mentioned sparsity.

What would be the next thing?

Yeah.

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 with incremental ways the 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 sort of incorporate some of the ideas of the Thousand Brains theory that you have many, many models that are voting now. That idea is not new. There's a mixture of models that has been around for a long time. But the way the brain does is in the middle of night to go to the bathroom. I'm testing these theories out a little different. The way it votes is different and the kind of way it represents uncertainty is different. So we're just starting this work but we're going to try to see if we can incorporate some of the principle. It's fun. The coffee cup is an examp 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 a voting or principles of Thousand Brain Theory. Like lots of simple models that talk to each other in a very certain way. And can we build more machines, systems that learn faster and also. Well, mostly are multimodal and robust to multimodal type of issues.

So one of the challenges there is 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. A very fine.

Yeah.

And has been extremely useful for developing specific mathematical models but it's not useful in the long term for creating intelligence.

So yeah.

You think you also have a role in proposing better tests.

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 test of the other things that we're trying to do. Right. So on the second thing is sometimes to be competitive in these tests you have to have huge data sets and huge computing power and we don't have that here. We don't have it as well as other big teams that big, big companies do. So there's numerous issues there. We come at it. Our approach to this is all based on, in some sense, you might argue, elegance. We're coming at it from a theoretical base that we think, oh my God, this is so clearly elegant. This is how brains work. This is what intelligence is. 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 0.1% better on this benchmark. That's all that matters. And that's a problem. You know, we have to figure out how to get around that. That's a challenge for us. That's one of the challenges we have to deal with. So it's much fun, but you have to sort of build up those constraints and the knowledge about the field and who's. I agree, you've identified a big issue. It's difficult for those reasons. But, you know, part of the reasons I'm talking to here today is I hope I'm going to get some machine learning people to say, read those papers. Those might be some interesting ideas. I'm showing 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, I'm, I'm very in this group here. People, they know, they do this, I do that. I'm tired of doing this 0.1% improvement stuff, you know, well, this all the time. I come in with these introspective ideas and say, well, have you ever thought about this? Now watch. Well, this all do this.

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

You see other leaders saying this. Machine learning leaders, you know, Jeff Hinton with his capsules idea, many people have gotten up saying, you know, we're going to hit road. Maybe we should look at the brain, you know, things like that. So hopefully that thinking will occur organically. And 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?

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

Is it on this idea of what?

Well, the idea that the humanities, psychology, neuroscience have to work all together to get to build the ass.

Yeah, I mean, Stanford just did this human centered AI thing. I'm a little disappointed in these initiatives because. Yeah, you know, they're focusing sort of the human side of it and it can very easily slip into how humans interact with 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 want to build intelligent machines that aren't emotional, that don't smile at you, that, you know, that aren't trying to tuck you in at night.

Yeah, there is that pattern that you, when you talk about understanding humans is important for understanding intelligence, that you start slipping into topics of ethics or. Yeah, like you said, the interactive elements as opposed to. No, no, we have to zoom in on the brain study. Study what? The human brain, the baby, the.

Let's study what a brain does.

Does.

And then we can decide which parts of that we want to recreate in some system. But until you have that theory about what the brain does, what's the point? You know, it's just. You're going to be wasting time, I think. Right.

Just to break it down. On the artificial neural network side, maybe you can speak to this. On the biological neural network side, the process of learning versus the process of inference. Maybe you can explain to me together.

And it's helpful. It's not.

Is there a difference between. In artificial neural networks, there's a difference between the learning stage and the inference stage. 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.

As long as you just, you don't. 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.

So let's talk a little bit about deep learning and the success. A lot of data. They're very inefficient learning. 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?

No, it is efficient. Obviously we can learn new things almost instantly.

And so what elements do you think?

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's not Something we said, oh, we can add that later. That's something that was upfront, had to be there from the start, 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? Our models do that. 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. 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 cycles, they're like 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 set with different populations of cells or going back and forth 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.

Exactly.

So, so we, you know, we have to like, you know, we get 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, and you know, but until you can prove it to someone in some, you know, commercial system or something, it's a little harder.

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 this is in the applied space of neural networks, the ideas of training model and some time alone in a room with it.

Well, no, the first things is I, when I imagine I reach my hand into a black box and I'm reaching, I'm trying to touch something.

Yeah. I don't data and these simple computational units, neuron artificial neurons that would back propagation statistical ways of being able to generalize from the training set onto no.

Upfront if it's something I already know or if it's a new thing 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. I, 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. And by the way, it starts learning from the get go, even if it's going to recognize it. So 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. In the brain, the way learning occurs. I mentioned this earlier, but I'll mention again the way learning occurs. 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 need to recognize a new pattern. What I'm going to do is 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. That's because it's isolated to that small section of the dendrite. They're not all being added together like a point neuron. If I learn something new on this segment here, it doesn't change any of the learning that occur anywhere else in that neuron. So I can add something without affecting previous learning. 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 too if you want, but it's getting a bit neuroscience y.

That's great. But is there an understanding of these mechanisms at every level?

Yeah.

So from the short term memories and the forming. Well, so data that's similar to that training set. So where do you think are this.

Idea of synaptogenesis, the growth of new synapses? That's well described as well understood.

And that's an essential part of learning.

That is learning.

That is learning.

Okay, you know, back, you know, the.

Limitations of those approaches. What do you think are his strengths.

Going back Many, many years people, you.

Know, was relative to your major efforts of constructing a theory of human intelligence.

Yeah, well, I'm not an ex's 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. Expert in this field. I'm somewhat knowledgeable, so. But I'm of.

It is in just your intuition. What are your.

Well, I have. I have a little bit more than intuition. 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 synapse. 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, right. It's pretty impressive. 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 known neuroscience, but it's less proven. This is the idea. How do I form a memory really, really quickly, like instantaneously? If it takes an hour to grow a synapse, that's not instantaneous. 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 neurotransmitters. 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 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 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 from 0.1 to 0.15. It's like doesn't do anything to release this transmitter. If I do that over a bunch of these, I've got a very quick short term memory. I guess the lesson behind this is that most neural networks today are fully connected. 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 parcel at it out type of thing. Then learning is not adjusting all these weights, but learning is just saying, okay, connect to these 10 cells here right.

Now in that process with artificial neural networks. It's a very simple process, back propagation that adjusts the weights. The process of synaptogenesis. Synaptogenesis, it's even easier.

But. 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 even easier.

It's even easier. Back propagation requires something we that really can't happen in brain. 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 fantastic. And as I mentioned earlier, it's very highly useful for many things. The models that we have today, this is pure Hebbian learning. What 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 almost completely on Hebbian learning, but on dendritic segments and multiple synapses at the same time.

So now let's return 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. Can you elaborate on that?

Yeah, you know, it's always the crazy question to ask because, you know, no one can predict the future. Absolutely. So I'll tell you a story. I used to. I used to run a different neuroscience institute called the Redwood Neuroscience Institute. And 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 understand how the neocortex works? And everyone went around the 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 a neuroscientist? Because they're going to find it's good pay, it's interesting, but it doesn't work like that. As I mentioned earlier, 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, then, meaning I can proselytize these ideas, I can convince other people to write, we can show that other people, machine learning people should pay attention to these ideas. Then we are definitely in an under 20 year time frame. If I can do those things, if I'm not successful in that and this is the last time anyone talks to me and no one reads our papers and I'm wrong or something like that, then I don't know. But it's actually derived from a lot of neuroscience principles. They're 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 a lot of things, the learning rules basically not back prop, but other not 50 years. It'll. You know, the same thing about electric cars. How quickly are they going to populate the world? It probably takes about a 20 year span. It'll be something like that. But I think if I can do what I said, we're starting it.

And of course there could be other. You said step functions. It could be everybody gives up on your ideas for 20 years and then all of a sudden somebody picks it up again. Wait, that guy was onto something.

Yeah, so that would be. That would be a failure on my part. Right. You know.

Yeah.

Think about Charles Babbage. You know, Charles Babbage is 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. Yeah, 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, 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 to. People act differently based on your ideas. So we'll see how well we do on that.

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

Yeah, certainly. It's certainly a possibility.

No question about worry about.

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

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

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, you know, so heavy, I'll be.

I'd be curious to say they're not neurons at all. Can you just.

I. And they don't imagine they need anything else. It makes my job harder.

Right.

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, to talk about machine intelligence and AI. That wouldn't be good for us either. 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. 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 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.

So what do you describe in which way? I mean, it's. Some of it is obvious, but I'd be curious if, if you have specific ways in which you think are the biggest differences?

Yeah. We had a paper in 2016 called why Neurons have Thousands of Synapses. And it. And if you read that paper, you'll know what I'm talking about here. A real neuron in the brain is.

I 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?

First of all, I don't think the goal is to create a machine that is 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 idea, it's like computing. 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, no, because we know that what the principles of computing are. And I can apply those principles to a small problem into 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. Complex thing. Let's just start with the synapses on it, which is a connection between neurons, real neurons, 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 own. With its eyes and hands or something equivalent to that. 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 in everywhere, from 5 to 30,000 synapses on them. The ones near the cell body, the ones that are close to the soma or the cell body 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. We call it flash inference. Here's a pattern done. No, it's movement, moving pattern. Movement, pattern, moving pattern. Attention, digging, building structure. Just figuring out the model of the world. Those are like the ones that people model in artificial neurons. There's a few hundred of those. Maybe they can sort of embodiment. Embodiment. Whether it's physical or not has to be part of it.

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

You bring up self. That's a different topic. Self awareness.

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

Yeah, basically 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.

So self awareness and consciousness, do you think one from the perspective of neuroscience and neocortex, 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?

Yeah, I have a lot of is.

It useful or is it just a side effect of us?

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 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 if I built it like this, it wouldn't be self aware. So that's a choice I could have. It's not like, oh my God, it's self. Aware. 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 and affect the cell. They can make the cell become active 95% of the cinema. I'm like, oh, come on. I unplug myself every night. I go to sleep. Is that a crime? I plug myself in again in the morning. I'm there I am. People get kind of bent out of shape about This I have 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 absence can't do that. They're too far away. So if you activate one of those synapses, it just doesn't affect the cell body enough to make that interesting. A problem you've talked about, Christoph Koch. You know any difference?

Any one of them individually.

Any one of them individually, or even if you do a mass of them. 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.

He also thinks intelligence and consciousness are disjoint. So I mean it's not. You don't have to have one or the other. So he is.

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

So where's your, your thoughts and cautions? Where does it emerge from?

What, what we, what, what real neurons do is the following. If you activate or they, you know.

You get because it is.

So then we have to break it down to the 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 then it has a memory. It can remember what you've done, 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 had your bagel? And you'd say, yes, I was conscious. 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 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 of it and the ability to recall that memory is what you would call conscious. I was conscious of that self awareness 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. 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 one that sometimes used, going by the word equalia, 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 why, you know, 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. 10 to 20 of them active at the same time, meaning they're all received. So that's an interesting question. The best treatise I've read about this is by a guy named o'. Regan. He wrote a book called why Red Doesn't Sound Like a Bell. It's a little. It's not a trade book. Easy to read. It's an interesting question, keeping an input at the same time. And those 10 to 20 synapses, or 40 synapses, within a very short distance on the dendrite, 40 microns, a very small area. So if you activate a bunch of these right next to each other at some distant place, 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, what happens is it creates what's called a dendritic spike. There's no color coming in on those synapses. It's just a correlation between some axons and some property of frequency. And that isn't even color itself. Frequency doesn't have a color. It's just what it is. So then the question is, well, why does it even appear to have a.

Color at all, just as you're describing it? There 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.

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. Think about. 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, not only feel it, they know it's there. It's there, 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 in their finger and if they move their, they move their non existent 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, but it's useful to have a model of something that 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 an dendritic spike travels through the dendrites and can reach the soma or the cell body. Now when it gets there it changes the voltage which is sort of like going to make the cell fire but never enough to make the cell fire. 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.

Do you really need to spend more time?

Yeah.

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

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 I need to solve that problem to build intelligent machines at all. Not at all.

But there is sort of the, the silly notion that you describe briefly that doesn't seem so silly to us humans is you know, if you're successful building.

Intelligent sort of what we call it says we depolarize the cell, you raise the voltage a little bit but not enough to do anything thing.

It's like well, good 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.

Well, why. But this big. 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 survival and propagating the 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 just come say. And 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, these are old brain, genetically embedded things that we fear death. There's. Outside of those, those uncomfortable feelings, there's nothing else to worry about.

Well, wait, hold on a second. Do you know the Denial of Death by Becker? Dental? You know, there's a thought that death is, you know, our whole conception of our world model kind of assumes immortality and that death is this terror that underlies it all. So, like.

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

But okay, so what, 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 what is the illusion? The illusion that that doesn't matter. You're still not coming to grips with.

The illusion of what?

That death is going to happen.

It's not going to happen.

You're a mat. You're actually operating. You haven't. Even though you said you've accepted it, you haven't really accepted unless you're going to die is what he was saying. So it sounds like you disagree with that notion.

Yeah, yeah, totally. 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 and 20 synapses at a time. And they're acting like I. Every night I go to bed, it's.

Like dying little deaths.

It's. It's a little death. And, and if I didn't wake up, it wouldn't matter to me. Only if I knew that was going to happen, would it be bothersome if I didn't know it was going to happen. How would I know? No, 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's no animals like predictions. So the neuron actually is a predictive engine on its own. 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. What pain in the world would there exist?

Well, so most people that think about this problem would say that you're just deeply enlightened or are completely delusional. But I would say that that's very enlightened. Enlightened way to see the world is that that's the rational one.

I think it's rational. That's right.

But the, the fact is we don't, 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.

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 there's people like that, right? I mentioned those big problems as well. 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 will be the quickest way to answer the first three questions. It can fire when it gets enough, what they call proximal input from those ones near the cell, fire. 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 in action potential, it does so slightly sooner than it would have otherwise. I'm serious.

Yeah.

And so I said, and my mission, you know, you asked me earlier, my first mission is 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. But that would 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.

Let me ask you another depressing and difficult question which is once we achieve.

That goal and so what good is slightly sooner? Well, the slightly sooner part is it. It does it all the neurons in the excited.

Do you. Of creating. No, of understanding intelligence. Do you think we would be happier, more fulfilled as a species to understand.

Intelligence or understanding the answers to the big questions?

Understanding intelligence.

Totally. Totally. It'd be far more fun place to live.

You think so?

Oh yeah. Why not? I mean, you know, just put aside this, you know, Terminator nonsense and, and, and, and just think about. You can think about. We can talk about the risk of AI if you want.

I'd love to. So let's talk about.

But I think the world will be far better knowing things. We always. Better than know things. Do you think it's better. Is it a better place to world 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 galaxy. I think it's a more. I. I dread. I used to. I sometimes think like God, what would be like 300 years ago, I'd be looking up the sky. I can't understand anything. Oh my God. I'd be like going to bed every night going, what's going on here?

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

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

Whatever.

We're getting. We're getting closer to enlightenment and you're going down.

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

We are put. Our poliosity is we're pulling ourselves up the hill by our curiosity.

Yeah, Sisyphus was doing the same thing with the rock. But okay. Our happiness aside, do you have concerns about. You know, you talk about Sam Harris, Elon Musk of existential threats of intelligence.

No, I'm not worried about existential threats at all. 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 we have real problems and things to worry about with today's. AI Neurons in the brain are surrounded by these inhibitory neurons, and they're very fast, the inhibitory neurons, these basket cells. And that will continue as we create more intelligent systems. There's no question, the whole issue about making intelligent armament.