What Most People Get Wrong About Evolution | Akarsh Kumar

I would just wanna clarify that evolution is anything but random. So artificial life is really about, like, understanding, like you said, life as it could be rather than life as as it is. We need to understand the space of all possible intelligences, the space of all possible life forms that can be.

Conway's Game of Life is a super famous simulation by John Conway where you have this grid of cells, this two d grid of cells, and they can either be on or off, alive or dead. That's it. And from this super, super simple world, it's like possibly the simplest possible thing you can think of.

You run this, you get insane amounts of complexity that no one would have thought it could do until you actually run it. You can do counterfactual analysis in other universes. In what worlds do we get this open ended creation of complexity and emergence, and in what worlds do we not get that?

Why does this physics, when you run it, it produces this amazing phenomenon. And when you run this physics, it doesn't do that. It produces just random noise.

Instead of hard coding a single simulation, you parameterize a space of simulations, which is much, much easier. Just simulate it, see what happens, plug it into a foundation model, and see what the foundation model thinks about what happened. There's 260,000 rules, and we've plotted all of them.

So we found that there's literally, like, a big island of solutions which are not open ended, and there's a small island of solutions where all of the coolest simulations lie. Some of them actually end up creating little patterns which move around that look like cells. This object, this cell like object, is exploiting the physics in a way to create a persisting object in this world.

Right? If you train them on calculus, they'll learn calculus. You don't have to train them on arithmetic first.

And it's such a weird alien way that we train these models. I really like to call them a statistical intelligence, and they're, like, basically perfect statistically. But this FER idea and this pick breeder line of work, it's basically like a different paradigm of intelligence that we're trying to study.

So it's a difference between, like, a statistical intelligence and a regularity based intelligence. And you can see this in, like, the pick breeder skulls. It's in the solutions, like, the neural circuits that we find.

The regularities are baked into the circuits. We wanted to see what would happen if you used LLMs to evolve basically small little assembly programs that compete against each other. So there's this programming game invented in, like, the nineteen eighties that people used to play.

It's called Core War. What my program needs to do in order to do that is it needs to basically inject an invalid operation in front of your program's execution thread. It's gonna halt your program by crashing it.

Your program will crash. And can we create, like, this open ended evolutionary arms race of programs from this? It's like Game of Thrones Turing edition.

Yeah. Yeah. Exactly.

That's a good way to put it. The LLM is not good at red code. If you just try to zero shot this language, it's terrible.

But if you do this evolution and you have this verifier, it turns out to be really good. Evolution is probably the most powerful algorithm that we know to solve, like, discrete combinatorial problems. If you solve, like, even one part of a puzzle and you hang on to that and you search for the other ones, you can turn your exponential search problem into a linear search problem.

We're basically trying to search for cellular automata, like neural cellular automata, which go from self replicating molecules, the cells floating in primordial soup to predator prey dynamics to alien animals roaming around. You can imagine that if you did this with a big particle simulation with, like, quadrillions of particles and you had the right foundation model and you searched for this sequence of events, then what would happen? Maybe you end up with some physics rule for this big particle system, which really does give you this entire sequence.

You get animals at them just like what happened in our universe. Right? The field of artificial life, I really think is, like, a very long term bet on intelligence.

What do you mean by that? So artificial life is really about, like, understanding, like you said, life as it could be rather than life as as it is. If we really just wanted to understand life on Earth and, like, how it is right now, we'd be studying biology.

Right? It's the same reason that we don't just study neuroscience to understand intelligence. We're...

Create AIs because we want a more mechanistic understanding. And not only that, but me personally, I like to... I'm gonna borrow this quote from Jeff Klune that I liked a lot.

It's like we really wanna understand... If we wanna claim that we understand intelligence or we understand life, we can't just talk about this specific form of life. We need to understand the space of all possible intelligences, the space of all possible life forms that can be, and only then can you talk about general principles for what governs intelligence or what governs life.

Right? You can't just look at one car and be like, this is how all cars are. Right?

That's the same way you can't just look at g t five and be like, all intelligences are like this. You can't just look at the human brain and be like, all intelligences are like this. There's a space of things, and we need to study the whole space.

If you look at how, like, humans learn and, like, animals are... They... And have, like, a natural curriculum.

They're like, I'm gonna learn and then this and then this. There's no other way. But if you look at how, like, our models are trained, you can train them on anything, and it'll just work.

And the question is a lot of people think that that's fine and that maybe it's better than how humans learn, and that's a possibility. It could be just be better. Right?

But there's reasons to believe that there is something fundamentally wrong or the universe doesn't work like that. The universe doesn't work like you can just learn anything at any given time. And thus, I think the fact that humans learn in the sequential order and evolution works in this path dependent way is the reason that it creates such nice regular structures in the representations that it uses.

the representations you learn are better. But how would you describe that in a kind of no nonsense way? What's the intuition?

The curriculum is not the only thing that matters because people have been doing curriculum learning in RL. And I was obsessed with curriculum learning in RL. I think the key thing is that...

I mean, this goes back to the why greatness cannot be planned lesson. You need, like, a serendipitous curriculum, which is not a preplanned, like, I'm gonna do this and this and this. It has to be much more serendipitous and embrace the chaos of our nature...

Of our... Of universe. Right?

It has to embrace this. You have to embrace idea that not just, like, going down this curriculum, but any possible curriculum which might lead me to somewhere interesting. So that's just a shout out to, like, you need serendipitous curriculums.

And to answer the question of why curriculums actually end up mattering, I think that's a fundamental question that that I'm really interested in answering. And I don't know, like, the short form answer for that, but it's like a fundamental property of our universe that if you wanna capture, as you like to say, the carve the universe and understand it by the joints. Right?

That's... Carve it up by the joints. I think in order to do that, you need to have this process of complexification where you build regularities on top of other regularities in this sequential way.

Alright? And I'm not exactly sure why it has to be like that, but I know that natural evolution works like that. And I know that a lot of theories like assembly theory, they work like that, like, from...

That's like a evolutionary theory in biochemistry and stuff. And human learning also works like that. It works in a sequential way.

So I'm not exactly sure why it works like that, but it definitely seems something like... It's something fundamental to our universe, and we need... Really need to understand that better.

Right? Yeah.

jump ahead. You actually need to synthesize these building blocks and you need to take the path. Yeah.

And one of the things I like whenever Ken explains his philosophy is that whenever p... Whenever he says like, oh, we need novelty search. We need this thing.

And people say, oh, but that's just like searching in the dark. That's like random. It's actually anything but random because randomness is, like, just doing random action.

Novelty, you know where... What you did before and you wanna avoid that. So I guess what you're saying is that if you wanna build...

If you wanna respect the path of where you previously came from, whether it's, like, by avoiding it via novelty or because you're respecting the symmetries that you learned along the way in a representation, you do need to respect it, and that gives you an idea. That get constraints where you can go. And I...

Question is, like, how much does that constrain you? There's a good chance it constrains you a lot, and it constrains you towards... In a right way towards the right path.

Right? That's why whenever I think about the FER hypothesis and this line of work, I really like looking at it through the lens of regularization. What...

Like like, people talk about a regularization in deep learning with, like, weight decay or some sort of other regularization mechanism, and I love that. I think everything is just regularization. The data is a form of regularization.

It regularizes, what... Like, do you need to model the world? That's a form of...

Like, it's like it's like basically molding the clay in a way that you need to model the world. L two regularization, like weight decay, is another form of that. Basically, it's saying you wanna find solutions with low weight norm.

Right? And then I think that this curriculum learning, basically, you wanna respect the symmetries, is just another form of regularization, But I think it's extremely, extremely, extremely strong regularization that you're subjecting this model to, and maybe it's the right regularization that we really, really need. And here's a quick refresher.

I think, is a completely different paradigm to doing it the statistical way. Exactly. Exactly.

And I think you said the right word. It's like a paradigm to understand intelligence. But this this FER idea and this pick breeder line of work, it's basically like a different paradigm of intelligence that we're trying to study.

We're not studying it from the standpoint of statistics. We're studying it from the standpoint of regularities. Right?

So it's a difference between, like, a statistical intelligence and a regularity based intelligence. And, I really like the idea of statistical intelligence. I think we did a good job, like, going down this path.

We should still go down this path, but we should also, not put all our eggs in one basket and really try to understand this other thing because there's lots of evidence that this other thing has lots of, potential here. Right? And it really ties into what all the criticisms of deep learning, they're basically talking about regularities.

Like, whenever people talk about, like, we need symbolic processing, whenever we... The way we need geometric deep learning, we need more inductive biases, and people have, like, all these different fields. There's whole different fields on, like, what we need.

Right? And they're all forms of adding regularities and symmetries to the system. And what I really like about this FER approach is I like to think about it as, like, it's like a automatic symmetry learning algorithm.

Right? Because, so I have... I love you.

I have an example I like to say. People like CNNs because they're translation invariant. Right?

People like transformers because they're permutation invariant, and they encode certain symmetries. And that's great. I mean, we need permutation invariant for set operations.

Right? But can you code in, like, lighting invariance into your model? Like, lighting invariance.

Like, if you want your CNN or image model to be invariant to whether it's a nighttime or daytime, there's no equation in the world that'll probably get you there. Maybe there is in the future, but that's impossible for me to imagine that you could come up with a mathematical, like, inductive bias that's gonna guarantee that. Right?

So what you really need is some sort of data driven symmetry learning thing that automatically respects it, and it forms neural circuits which are naturally have that inductive bias built in. Right? And you can see this in, like, the pick breeder skulls.

It's like the neural... It's not that the inductive bias is in the hypothesis space of things we're searching for. It's in the solutions, like the neural circuits that we find.

The regularities are baked into the circuits.

Yeah. So I want to touch on one key point that you said that you said it's not grounded in our world. Right?

And that's one of the... My favorite things about artificial life is that you can ground it however you want to in whatever artificial world you want to. Right?

So people often think about artificial life as this. It's only talking about life. The reason I like it, because there's a subfield in artificial life called artificial chemistry.

It's about just changing... Instead of using, like, the normal hydrogen helium, you can change how they interact and see what happens. Right?

So that's the power of artificial life. You can do counterfactual analysis in other universes. Right?

And I really like this idea because artificial life is not only about life, but it's also about studying, like, what happens in general in, like, artificial physics, artificial chemistries. Can we study the emergent properties in each of these different universes? When...

In what universe... These are the questions that I really wanna focus my research agenda around is that in what, like, worlds do we get this open ended creation of complexity and emergence, and in what worlds do we not get that? And why is it...

And this is the key question is why is this parameter? Why does this physics, when you run it, it produces this amazing phenomenon? And when you run this physics, it doesn't do that.

It produces just random noise or something. Right? And that was the key reason I actually, worked on automated search for artificial life as ASIL work is because I wanted to answer that exact question, directly.

But ASIL was trying to basically parameterize a space of intelligences, find the good ones, find the bad ones, and just do simple stuff like interpolate between them and just see what happens. Right? Interpolate the parameter space between them and run the simulation for each intermediate point and just see what happens.

Just simple scientific analysis like that. Yeah. And another thing that jumps out to me is that you get these convergent patterns and rule your space.

What do you mean by that?

But they might also be hints of just something else. They could be shadows. I I kind of agree with you because in my ASIL work, I I span the space of all possible two d cellular automata, for example.

Right? And in my case, I had a lot of diversity. In one world, a glider looked like a Conway's game of Life Glider.

In another world, the the minimal glider looked like a train going down the tracks. Right? So...

And it, like, didn't... It left, like, a long path. So in different worlds, it can be different.

But I guess what you're talking about is that when they're all the same in all the different worlds, that points to something fundamental about, like, not only the world that you're in, but, like, not only a rule that you're in, like, the rule that you're operating on, but, like, the entire substrate that you're working in. Maybe all possible rules in that substrate have this type of thing.

So, I can start off with, the linear one. I... I'll start with the simplest one, Conway's Game of Life.

So Conway's Game of Life is a super famous, simulation by John Conway where you have this grid of cells, this two d grid of cells, and they can either be on or off, alive or dead. That's it. And, basically, it has super simple rules.

Like, if I'm dead and three of my neighbors in, like, my eight... I have eight neighbors. If three of them are alive and I'm dead, then I come to life, right, as a act of, like, just coming to life.

And there's, like, rules like that. There's, like, two or three rules like that, and it's, like, super simple rules, and that's it. That's it.

That's that's come... That's all you need to know. Then you start off with a, grid of, like, random, dead or alive cells, or you can start off with some pattern that humans have created, and you just run this simulation over many, many time steps.

And from this super, super simple world, it's like possibly the simplest possible thing you can think of, you run you get insane amounts of complexity that no one would have thought about... That thought it could do until you actually run it. And now people are like, there's whole Discord servers.

I'm actually in one of them where people try to, go through and they just share what they found. They're like, oh, I found this cool spaceship that also... That, that's a repeating pattern that repeats every 64 time step, and it moves at this speed.

And I really love this community because they call, like, the glider how fast it moves. I think it's at, like, a certain speed. Right?

And they realize that there's, like, a speed of causality in this system, which is, like, one cell per time step. That's, like, the speed at which information can propagate. So they call that the speed of light c, and then they they use their gliders, and they're like, this goes at c over 16 speed.

Right? Just like in real physics, how people talk about this kind of stuff. So it really is like an artificial universe, and people...

A lot of people seem to think it's like a toy system. But I guess the point of it is that it's toy enough that we can study it. If it were super complex in our real world, then we wouldn't be able to study it.

Right? And... But I do think it's a very interesting quest.

That's one of my quest is to create more compelling universes, which are capture... Like, Conway's cap... Conway's Game of Life, they capture some properties of our universe, like emergence and this idea that you can build up global patterns from local interactions.

But there's other stuff you wanna capture too. Right? Like, the idea of, like, self organization and, open ended evolution.

So a lot of my research is on trying to find simulations which have all those properties that we care about. And that was the point of ASIL again. Yeah.

So then how structured is a space?

does it trans... You know, is it like a wormhole where you get transported into a completely different part of the space? Or does it make some commensurate small change in the emergent, like a high level domain?

Yeah. Exactly. That's a great, great question, and this is one of the things I really wanna study.

So in the initial state of Game of Life, yes, it's very, very chaotic. In Conway's Game of Life, let's talk about that specifically. It's very, very chaotic.

I've had examples where you change one cell... Like, one pixel in, like, the 64 by 64 grid. And beforehand, I actually use this in one of my talks.

It's like it basically runs forever. It's just like... It's just...

Not forever. I shouldn't say forever, but, like, for, like, tens of thousands of steps, it just keeps on moving. Right?

And it just, like, keeps on doing interesting stuff. You change this one thing, it stops... It basically halts into an oscillating pattern in, like, less than a 100 steps.

So it's, like, in the initial state, yeah, it's very, very chaotic. But the interesting thing is that this is not necessarily true for all simulations. And in ASIL, we are really interested in searching over the physics, like, the actual rules that dictate the dynamical system, like, what I call the physics.

What we've been talking about is is the initial state. Right? Yeah.

But there's two things, initial state of physics. And if you do it in the physics, Game of Life seems to be a little more robust as in if you change, like, one... There's basically 18 possible rules you can toggle on or off.

And if you change one of them, it doesn't impact it too much in my experience. But there are some exceptions to that where... Yeah.

Very interesting. So... And and talk about some of the other simulators as well.

So one of the... So I can go through a list of the ones we used in our paper. In Linea by Bert Chan, and he basically created this continuous generalization of Game of Life, which generalizes to, like, three channels, and as you can dictate them to RGB.

And they're basically just like a continuous, differential equation update rule that dictates how they operate. So I think that one's really cool.

across my screen. And then the cool, also another cool one is the Neurocellular TomDA. Yeah, by Movinsav.

an image. So like a gecko. Yeah.

Yeah. Yeah. Yeah.

And to build on top of that, I guess it's like, you don't really wanna learn the intelligence. You wanna learn the process which grows the intelligence sort of. Right?

Yes. It's similar to that. I mean, that's one of the reasons that deep learning took off in the first place because we're not hard coding these...

All this knowledge about we know about the world. We're letting it learn from the data itself. Right?

But there's other problems to that maybe. But... Yeah.

Going back to the neural cellular the... Just for the audience, it's basically just like you have the cellular TOMDA. But what if you made this three...

Basically, the dynamics rule is like this mapping from a three by three patch into one cell. Right? That's what the dynamics rule tells you to...

How do you go from one time step to the next? And, basically, what they do there is they just replace this with a small neural network that dictates this. So that gives you a whole space of possible physics rules that you can search over.

So I really like neural cell automata. And I can briefly go over the next two, the Boyd's and the particle life. Yeah.

Boyd's is like the super seminal algorithm inspired by how fish and how birds flock in nature. Because if you look at... I actually just went to the Osaka Aquarium, and I was watching these videos...

The... Not these videos. I've seen this fish fish in person, and they were, like, always together.

And there's, like, a whale shark coming out behind them, and they just, like, steered to the left a little bit. And I was like, how did they know how to do that? Because each fish, they...

And only one of them knew about the whale shark, and it tugged the other ones to the left. And the other ones all kind of just realized, oh, we should all go there. It's an example of collective intelligence in nature.

Right? So Boyd's is basically an inspiration of that where you have these, like, bird like objects which flow through two d or three d space, and they have super simple rules where they just look at the neighbors. Like, I have my neighbor to the left and to the right, and I basically...

Let's just say I have, like, four neighbors that I can see. Right? I'm just gonna make a decision on whether to go left or right based on where their positions are.

That's it. And if you made the right decision and you're all making the same decision, you can get the emergent flocking behavior that we see in nature. And...

Yeah. So what we did is we just, like, parameterized this with a small neural network and just searched over this decision making network, this... With this decision making.

If if the Boyds make different decision rules, how does the global behavior of the collective change according to local decision rules that they're making? Particle life is super cool because in grid based simulations, it feels like this... It's like this spatial thing, but particle life is basically saying that we're gonna have this three d Euclidean space or two d Euclidean space, and we're just gonna throw particles at it.

Just like just like just vanilla particles. But their physics rule is not gonna be like, you know, Newtonian mechanics or something like that. It's just gonna be whatever we want it to be.

Right? So in this case, in particle life, I I I was inspired by Thomas Moore. He has this great YouTube videos on this type of thing.

Is basically, you have this set of particles, and each particle can take on one of six types. Right? And these are dictated by their colors.

And then what you can have is that you have the six by six matrix, which tells you how do different types of particles interact with each other. So it could be that red and red repel, but red and orange attract, and orange and green, they, are neutral. Right?

And you have the six by six matrix, and if you change the values of this physics matrix, this this is the physics of the world again. Right? Or you can call it the periodic table or whatever you wanna call it.

As you change this physics, how do the actual... How does the simulation change? Right?

Some of them are super bland and boring, and I don't wanna look at them. But some of them, they're, like, evolving and moving and doing interesting things. And some of them actually end up creating little patterns which move around that look like cells.

So you can literally see them. They have, like, a cell barrier, which is like this red coating. And inside, they'll have, like, purple and yellow in a triangle, and that's like its insides.

And it's it's... Basically, this is a simulation. This object, this cell like object is exploiting the physics in a way to create a persisting object in this world.

Right? And you just interviewed Blaze. So this idea that life is just the I...

Persistence. Right? It's just that idea that, like, life is basically about persistence.

These organisms are just trying to figure out how do we persist into the next time frame, and they've exploited the laws of physics in order to do so. Yeah. And Blaise was saying that this persistence is kind of like a natural...

You is know, was talking about these natural convergent phenomena.

Yeah. The the emergence of persistence is very fascinating. It doesn't happen in all simulations.

It only happens in some. But I think this points to the broader point about what life is and what the second law of thermodynamics tells us. There's a generalization to persistence, which is this...

I like... This at least how I have a... In a...

My mental model of how I think about it is the second law of thermodynamics and life and persistence, they all basically are saying... And evolution, I should say. They're all saying the same thing.

They're talking about what exists right now and what is likely to exist in the future. So the second law of thermodynamics is saying that you're more likely to go towards higher entropy states. Right?

That's just like... If you look at the macrostates and microstates of any simulation, that's how it operates. But if you look at it from the standpoint of evolution, what is more likely to exist in the future?

It's self replicators because they'll naturally exist more often in the future versus non self rep... Self replicators. So they're really...

People make it out to be like, oh, life is like fighting entropy. They're really two sides of, like, the same idea of persistence or what is likely to exist in the future. Yeah.

Fascinating.

So you're saying, I want to have a principled way for searching this space. Yeah. We used it in three different ways.

So at a high level before that, I guess the field of artificial life, I think it's a very cool field, but often people, like, only, like, simulate single simulations, and they try to draw conclusions from it. And and I I feel like it's cool, but, like, you really need to be studying the space of simulations. Right?

So I think our algorithm, what it does is, basically, you... Instead of hard coding a single simulation, you parameterize a space of simulations, which is much, much easier. Basically, it's a difference between coding up the periodic table.

Like, how does each element interact with each element versus just saying that there's gonna be, like, a 100 elements, and I don't know how they interact. You figure it out, telling the algorithm to search for it automatically. So it's a much easier problem to just say there's a 100 elements.

Right? So once you have this space of simulations that you have described, then you can just search for what you want in automatic way using a foundation model. And the reason I like ASIL is because it captures this principle of computational irreducibility.

You don't need to know what this physics rule is gonna do and try to predict which one is the best one. Just simulate it, see what happens, plug it into a foundation model, and see what the foundation model thinks about what happened, and then go back. And the key thing is that here, you're letting the simulation unroll, and you're not having, like...

You're not trying to predict what's gonna happen. Right? So you're kind of embracing this idea of chaos and computational reducibility.

And there's, like, two reasons it's better because one is just easier to specify what you want. You can just be like, I want a cat. I don't need to, like, have a picture of a cat and supervise it in, like, a pixel wise manner.

I can just say I want a cat in, like, a general way. Right? That's one way.

But importantly, it also makes the optimization and the search much easier because it's really dang hard to find a self organizing rule that creates this particular image of this particular cat. That's, like, really... If you do that in Conway's Game of Life, that's not gonna happen.

But if you just say, oh, I don't want that specific cat. I just want a cat. Give me any cat.

That's a much easier space of things that satisfy that problem, so it's much easier to search for. And we experienced this firsthand that in, like, Conway in the open ended simulation, we're not searching for particular configurations of states that we want. We're just saying we want some open ended simulation.

It can be open ended in however it wants to be. As long as the foundation model thinks it's open ended, it... It'll work...

It'll do. And the cool thing about... I wanna say, the reason we use foundation models is not just because it's, like, the newest and greatest thing that you can use.

It's because we really care about what a human thinks about these simulation because it's really hard to describe what complexity is, what emergence is, what does it mean to have a very interesting system. It's like you can't really mathematize that really easily. And if you did and you optimize for those simulations, you'll find, like, Goodhart's Law.

You'll find something that you asked for, but not something that you wanted. Right? So what we really want is what a human thinks about this in this subjective vague way.

And we can't put a human in the loop because that's, like, too expensive. So what's the next best thing is you try to find a representation space which matches that of a human. And there's a lot of evidence statistically, at least, statistically, that these foundation models are matching human representations from a...

that's a good question. So you're basically asking... Let's talk about the Boyd's one.

You're basically saying, is the decision making rule of each Boyd, is it an impostor or is it, the real thing that gives you the real, thing. Right? Yeah.

And and what would an impostor mean in in this simulator? Yeah. That's a great question.

So I think the idea of impostor is... I like to ground this idea in its performance on future tasks and how how how it adapts to things we want it to adapt to. That's, that's how I like to coin that.

I don't really like to ground it in modularity or something specific like that. I like to ground it in set of future tasks.

Yeah. In this case, they're pretty robust to that sort of thing. But in this case, I mean, it could be that, like, like, small changes.

I guess what I'd call you... You can imagine that if these boys were really UFR or, like, good... Nicely factored, then small changes to their network change the global behavior of the collective in, like, nice ways where it goes from a spiral to, like, triangles or something.

Maybe not triangles, but some other cool shape. But in this case, they don't do that. They actually degrade.

If you sweep the parameters, then they become basically kind of random. So in that way, it kind of is a impostor version of this spiral. Exactly.

Exactly. And the thing is, in this case, they're evaluated on and they're expected to maintain... Persist into the future of this simulation.

So in that way, they're very, very well structured because they are able to persist indefinitely. You could run this simulation probably for, like, millions of time steps, and they'll still be doing what they're doing. Yeah.

But if you wanna... Them to do something else, then they, like, make a triangle by sweeping some weights, then they would fail in that way. And...

But but they're... To be fair, they're not trained to do that in the first place. They're not...

Their evolutionary lineage doesn't. There's no reason for them to want to have to do that. Right?

So I wanna point out to, like, we had this figure in our paper, which showed, like, what the future of this possible direction of searching for simulations via foundation models could look like. And we had this fun example. I have it pulled up right here.

The bottom one is particularly fascinating. We're basically trying to search for cellular automata, like neural cellular automata, which go from self replicating molecules. So cells floating in primordial soup to predator prey dynamics to alien animals roaming around.

And this is just like a like a fun, toy example that we use. In this case, the cellular automata just memorized that sequence of frames. But you can imagine that if you did this with a big particle simulation with, like, quadrillions of particles and you have the right foundation model and you searched for this sequence of events, then what would happen?

Yeah. Yeah. It's a good point because the performance of these foundation models for this type of tasks, it's like...

It it it will be flawless. Right? Because this is the exact type of things where you only care about the output behavior.

You don't care about its internal representation. You don't care about creativity in a sense, because the humans are the ones kinda injecting those prompts. And you're using this, like, statistical intelligence to bootstrap, like, a real natural gin...

Like, organic particle simulation, which should have all the properties of our real world. Right? Yeah.

But did you see similar things in the space where these properties that we're talking about, like, existed in a sliver of this computational space? Yeah, definitely. So if you mean the...

Let's... In the computational space, I guess we can talk about the laws of physics. That's your space.

Right? In that way, definitely. I mean, I have this...

I have it pulled up right here. Found simulations which are basically in... They...

That look more open ended than Conway's Game Life. Yeah. That one.

That exact one. Yeah. Basically, we found simulations which are more open ended than Game of Life.

Right? But we wanted to go further than that and ask, what is the space of possible rules look like? What rules are open ended?

What rules are not? Right? So if you scroll down to in the paper, we had this graph right here where we basically tried to plot all possible rules.

There's 260,000 rules, and we plotted all of them. We colored them. We...

What we did, we we ran the rules. We put this image into clip and plotted this clip space in two d, but we colored each of the points based on how open ended they are. So we found that there's literally, like, a big island of solutions which are not open ended, and there's a small island of solutions where all of the coolest simulations lie.

So in that way, I mean, this graph kind of outlines exactly what we're talking about is the space of possible simulations, and we wanna find what part of this space is like that. Yeah. And you can see that there's like this...

There's like different islands. There's like one big island and like one smaller island and one tiny island with like one simulation that's very different from all the rest of them and its behavioral properties.

Yeah. Yeah. So that's that's the grand question.

Right? That's like... That's how I like to go about it.

So the field of artificial life, I really think is, like, a very long term bet on artificial... On intelligence. But there's two caveats.

One, they're still interesting to study because they give you lots of insights about our universe and emergence and all these other scientifically, scientific things that we still care about even if we don't create intelligence. But second of all, I think Ken talks about this a lot, is that we don't really need to simulate every possible particle at a lower level and get everything to bootstrap. What we really wanna do is create an abstraction of natural evolution and an abstraction of these simulations and may...

And find abstraction, which is one, ultra efficient that we can run-in ten years from now. And, two, it gives this abstraction the right way where you get what you want, which is intelligent, general intelligence. And that is a open problem, and that's one of my research agendas is finding the principles that we extract from natural evolution, artificial life in order to create better AI systems.

We wanted to see what would happen if you used LLMs to evolve, basically, small little assembly programs that compete against each other. So I can give you some background. So there's this, programming game invented in, like, the nineteen eighties that people used to play.

It's called Core War. And, basically, the idea is it's... There's, like, this assembly like language called RedCode.

And how it goes down is I create an assembly program, you create an assembly program, and everyone creates an assembly program. We put them into a virtual machine, and we put them in the memory address of this virtual machine in a random location, and we just let the machine go. It's just gonna run the programs, and they can do whatever they want.

It's like a Turing complete language, and the goal is that my program will be the last one to run. So what I need... What my program needs to do in order to do that is it needs to basically inject an invalid operation in front of your program's execution thread.

And when it does that, it's gonna halt your program by crashing it. Your program will crash. And then then my program will be the last one running, and I will win this game.

And so in order to do this, you need to basically... Your program needs to defend itself against other people attacking it and attack other people. So it's like this really cool game that you can just run.

And what we did was we saw that people have been making these war... Human warriors for such a long time. We asked what would happen is...

If we launched LLMs to evolve these programs and have them compete against each other, And can we create, like, this open ended evolutionary arms race of programs from this? That's amazing. So it's like Game of Thrones touring edition.

Yeah. Yeah. Exactly.

That's a good way to put it. Yeah. Yeah.

Well well well tell me more.

How... What was the population size? And how did you set this thing up?

Yeah. So the actual algorithm is really, really simple. So what we do is we start off with a program.

This can be a human program, or you can be, like, just the LLM generator program. And then you basically just optimize a program with an LLM as the mutation operator in an evolutionary loop to beat this program. So you just try to do that, and we actually ended up using MapElites because the space that you're optimizing is very deceptive.

It's very nonlocal. If you just do a vanilla gradient descent... Not gradient descent.

Greedy genetic algorithm, it won't work. You need to use MapElites. But then we end up with a warrior.

These are programs that are called warriors in CoreWar. You end up with a warrior that beats your initial warrior. Then what you can do is optimize a third warrior to beat both of these two, and then you can optimize a fourth warrior to beat these three.

And you just keep on doing this, and you end up with a long sequence of warriors. Right? And then the question is, like, where does this, like, adversarial, like, rounds of evolution?

Where does it take you? And one of the cool results I get was... Because we have two main results is the first one is in this first round of training, we can already beat, like, 96% of a dataset of human warriors.

There's, like, a dataset of, like, 300 human warriors. We can beat 96% of them just by using an LLM to evolve them. And, importantly, the LLM is not good at red code.

If you just try to zero shot this language, it's terrible. If you do best of ends... Best of end sampling, it's terrible.

But if you do this evolution and you have this verifier, it turns out to be really good. This is the same lesson from alpha evolve. Right?

These LLMs are not good at zero shotting certain kinds of proofs and stuff. But if you let them evolve with a verifier in the loop, they can be really, really powerful. That speaks to the power evolution and the priors from the model.

But the second result that we have that I'm the most excited about, it turns out if you do this rounds of evolution, right, then these warriors that you end up with, more, further down the line, they become more and more general as in they're more likely to beat human warriors that they haven't seen before. So, I think that's a pretty cool result. But, even more than that, the cooler part is is if we we have this vector describing the behavior of these warriors, just like their behavioral characteristics, and we can get into details of how we, measure the behavior, but we have this vector.

The variance in the behavior of these warriors goes down as you increase the number of rounds. So that kinda means that they're getting more general, and they're trending towards, like, kind of, like, reducing variance. So they're kind of behaviorally becoming, like, a single generalist warrior.

At least that's what the trend is towards. Exactly. And I think, people in AI have noticed tend to think of evolution in general as this very dumb naive algorithm that you use when you can't do gradient descent.

Right? And they basically call it just random search. And I would just wanna clarify that evolution is anything but random.

It's anything but random, and evolution is probably the most powerful algorithm that we know to solve, like, discrete combinatorial problems where you need to basically get pieces of the puzzle right before you get the whole thing right. And the selection mechanism in evolution is really, really underrated. Because if you solve, like, even one part of a puzzle and you hang on to that and you search for the other ones, you can turn your exponential search problem into a linear search problem.

So in that way, evolution is a really, really powerful algorithm, but all it needs is your mutations to be good, like, 1% of the time. Right? If you just do this with, like, naively in, like, program space and just involve...

I think there was a cool paper from, like, the before LLM era of AI, like, I think AutoML zero, where they did program search, but with random mutations. And that's, like, really hard to get working properly because there's, like, literally around a 0% chance that any mutation will be give you some useful code. But LLMs, sure, they can't give you a 100% success, but they can give you way more than 1%.

So then you can basically... It... Whenever you are successful, you can hang on to that achievement and build on top of it.

And that's what gives this combination of evolution plus LLMs a lot, like, a significant more amount of power than if you just do LLMs by themselves. It's not even close. Akash Kumar, it's been an absolute honor having you on the show.

Awesome. Thanks for having me. Yeah.

It's been amazing. This was a great conversation. Yeah.