Lex Fridman Podcast - #177 – Risto Miikkulainen: Neuroevolution and Evolutionary Computation

Episode Date: April 19, 2021

Risto Miikkulainen is a computer scientist at UT Austin. Please support this podcast by checking out our sponsors: - The Jordan Harbinger Show: https://jordanharbinger.com/lex/ - Grammarly: https://grammarly.com/lex to get 20% off premium - Belcampo: https://belcampo.com/lex and use code LEX to get 20% off first order - Indeed: https://indeed.com/lex to get $75 credit EPISODE LINKS: Risto's Website: https://www.cs.utexas.edu/users/risto/ PODCAST INFO: Podcast website: https://lexfridman.com/podcast Apple Podcasts: https://apple.co/2lwqZIr Spotify: https://spoti.fi/2nEwCF8 RSS: https://lexfridman.com/feed/podcast/ YouTube Full Episodes: https://youtube.com/lexfridman YouTube Clips: https://youtube.com/lexclips SUPPORT & CONNECT: - Check out the sponsors above, it's the best way to support this podcast - Support on Patreon: https://www.patreon.com/lexfridman - Twitter: https://twitter.com/lexfridman - Instagram: https://www.instagram.com/lexfridman - LinkedIn: https://www.linkedin.com/in/lexfridman - Facebook: https://www.facebook.com/lexfridman - Medium: https://medium.com/@lexfridman OUTLINE: Here's the timestamps for the episode. On some podcast players you should be able to click the timestamp to jump to that time. (00:00) - Introduction (06:51) - If we re-ran Earth over 1 million times (10:08) - Would aliens detect humans? (12:46) - Evolution of intelligent life (16:31) - Fear of death (22:47) - Hyenas (26:12) - Language (29:43) - The magic of programming (35:43) - Neuralink (43:15) - Surprising discoveries by AI (46:49) - How evolutionary computation works (58:12) - Learning to walk (1:01:25) - Robots and a theory of mind (1:10:29) - Neuroevolution (1:20:47) - Tesla Autopilot (1:24:11) - Language and vision (1:29:53) - Aliens communicating with humans (1:35:29) - Would AI learn to lie to humans? (1:42:03) - Artificial life (1:46:56) - Cellular automata (1:52:32) - Advice for young people (1:57:09) - Meaning of life

The following is a conversation with Risto McAllin, a computer scientist at the University of Texas at Austin, and Associate Vice President of Evolutionary Artificial Intelligence at Cognizant. He specializes in evolutionary computation, but also many other topics in artificial intelligence, cognitive science and neuroscience. Quick mention of our sponsors, Jordan Harbourn to show, Grammarly, Bell Campo, and Indeed. Check them out in the description to support this podcast. As a side note, let me say that nature-inspired algorithms from end-call and optimization to generic algorithms to cellular automata

and neural networks have always captivated my imagination, not only for their surprising power in the face of long odds, but because they always opened up doors to new ways of thinking about computation. It does seem that in the long arc of computing history, running toward biology, not running away from it, is what leads to long-term progress. As usual, I'll do a few minutes of As Now. I try to make these interesting, but I give you time stamps, so if you skip, please still check out the sponsors by clicking the links in the description. It is the best way to support this podcast.

I'm fortunate to be able to be very selective of the sponsors we take on, so hopefully if you buy their stuff, which you should, you'll find value in it just as I have. This episode is sponsored by Jordan Harbinger Show. Go to Jordanharbinger.com slash Lex. You don't even need to buy stuff. It's free. It is beautiful. Subscribe to it. Listen. You won't regret it. He's a great interviewer, and I especially like his feedback for today's episodes, where his combination of fearlessness and thoughtfulness is especially on display. Touching topics of sex, corruption, mental disorders, hate, love, and everything between all my favorite topics.

Jordan has, in many ways, inspired me to keep pushing myself in these kinds of difficult conversations that I have on weird topics that sort of challenge me that are risky that I can get in trouble with and sort of walk through that fire, walk through it with grace. But at the same time, accepting the responsibility of the mistakes I make, and of course, I will make many mistakes. That is life. Again, go to JordanHarbinger.com slash Lex. It's how he knows I sent you. That's JordanHarbinger.com slash Lex. If you love this podcast, if you love podcast, listen to it. It's great. This show is also sponsored by Grammarly, a writing assistant tool that checks spelling,

grammar, sentence structure, and readability. Grammarly Premium, the version you pay for, and the one they hope you sign up for, offers a bunch of extra features. My favorite is the clarity check, which helps detect rambling chaos that many of us can descend into and I certainly do. If gremily can only process audio and detect mumbling, it would probably go into red alert mode, but that's talking. When I write, let's say the thing I aspire to when I write is simplicity. I think simplicity is beautiful. I think it's powerful in being able to communicate ideas, striving for simplicity forces you to

think deeply about a topic. It's not just that simplicity is a good metric for effective communication. is a good metric for effective communication. It's also just on a personal level, a great way to challenge yourself to think into understand a topic. Anyway, Grammarly is available on basically any platform in major sites and apps, like Gmail and Twitter and so on. Get 20% off Grammarly premium by signing up

at Grammarly.com slash Lex. That's 20% off at Grammy.com slash lex. Grammar by the way has two M's. In case this was something you were wondering about. This show is also sponsored by one of my favorite sponsors, Bell Campo Farms, whose mission is to deliver meat you can feel good about. Meat that is good for you, good for the animals, and good for the planet. Bell Campo animals graze on open pastures and seasonal grasses resulting in meat that is higher in nutrients and healthy fats and friends is delicious.

Bell Campo has been the best meat I've ever had at home. In fact, just for the fun of it, for the experience of planning a visit out there, maybe I'll videotape some parts of it, maybe not. It is going to be more expensive than store bought meat, but I honestly think both on the ethical side and the deliciousness side, it's worth it. Of course, under financial constraints we have to make tradeoffs in this life, but I think this is a worthy investment. Anyway, you can order Bell Campo Sustainably Raised Meets to be delivered straight to your door using code Lex at bellcampo.com slash Lex for 20% off for first time customers.

That's code Lex at bellcampo.com slash legs. If you order from them post on Instagram, tag me, hopefully I'll see it and it'll give me a good smile. So and in general for other sponsors and just any cool things going on in your life, if you tag me, I really appreciate it. It often puts a smile on my face.

So, the internet, I think in most cases, at least for me, can be an amazing place. This episode is also brought to you by Indeed, a hiring website. I've used them as part of many hiring efforts I've done for the teams I've led in the past. The main task is to quickly go from a huge number of initial applicants to a short list of great candidates. I'm going through the hiring process currently. I need a lot of help in more ways than one. I certainly need help with the video editor and all those kinds of things. There's a huge number of people that applied. I'm still very early in that process.

So if you're thinking about applying, you can still apply and I'll still get to you. When I look for people to work with, I'm really looking, hopefully, for somebody I can work with for a very long time, somebody who will help inspire me. Somebody's whose passion drives me to be more passionate and vice versa. I mean, what

else is left about if not working on a team with awesome people doing awesome things? Anyway, right now, get a free $75 credit at Indeed.com slash Lex. That's their best offer anywhere. Get it at Indeed.com slash Lex terms and conditions apply indeed.com slash Lex. This is the Lex Friedman podcast, and here is my conversation with Risto McCollinin. If we ran the Earth experiment, this funnily little experiment we're on, over and over and over and over a million times and watched the evolution of life as it pans out how much variation in the outcomes of that evolution do you think we would see. Now we should say that you are a computer scientist. That's actually not such a bad question for computer scientists because we are building

simulations of these things and we are simulating evolution and that's a difficult question to answer in biology but we can build a computational model and run it million times and actually answer that question. How much variation do we see when we simulate it? And that's a little bit beyond what we can do today. But I think that we will see some regularities and it to get a solution also a really long time to get started and then things accelerated really fast towards the end. But there are things

that need to be discovered and they probably will be over and over again like manipulation of objects, opposable thumbs and also some way to communicate. Maybe you're only like, why would you have speech? It might be some other kind of sounds and and decision-making, but also vision. I has evolved many times. Various vision systems have evolved. So we would see those kinds of solutions, I believe, emerge over and over again. They may look a little different, but they they get the job done. The really interesting question is would we have primates? Would we have humans? Or something that resembles humans? And would that be an apex of evolution after a while?

We don't know where we're going from here, but we certainly see a lot of tool use and building our constructing our environment. So I think that we will get that. We get some evolution producing some agents that can do that, manipulate the environment of the build. What do you think is special about humans? Like if you were running the simulation

and you observe humans emerge, like these like two makers, they start a fire and all of a sudden start running around building buildings and then running for president, all those kinds of things, what would be, how would you detect that? Because you're like really busy as the creator of this evolutionary system. So you don't have much time to observe like detective any cool stuff came up, right? How would

you detect humans? Well, you are running the simulation. So you also put in visualization and measurement techniques there. So if you are looking for certain things like communication, you'll have detectors to find out whether that's happening, even if it's a lot of simulation. I think that that's what we would do. We know roughly what we want, intelligent agents that communicate, cooperate, manipulate, and we would build

detections and visualizations of those processes. Yeah, and there's a lot of, we'd have to run it many times and we have plenty of time to figure out how we detect the interesting things. But also, I think we do have to run it many times because we don't quite know what shape those will take. And how a detector may not be perfect for them. Well, that seems really difficult to build the detector of intelligent or intelligent communication. Sort of, if we take an alien perspective observing Earth, are you sure that they would be able to detect humans as the special thing? Wouldn't they be already curious about other things? Earth. Are you sure that they would be able to detect humans as the special thing?

Wouldn't they be already curious about other things? There's way more insects by body mass, I think, than humans by far, and colonies. Obviously dolphins is the most intelligent creature on Earth. We all know this. So it could be the dolphins that they detect. It could be the rockets that we seem to be launching. That could be the intelligent creature they detect. It could be some other trees. Trees have been here a long time. I just learned that sharks have been here 400 million years, and that's longer than trees have been here.

So maybe it's the sharks that go by age. Like there's a persistent thing. If you survive long enough, especially through the mass extinctions, that could be the thing your detector is detecting. Humans have been here for a short time, and we're just creating a lot of pollution, but so is the other creatures. So I don't know. Do you think you'd be able to detect humans? Like how would you go about detecting in that computational sense? maybe we can leave humans behind. In the computational sense, detect interesting things. You basically have to have a strict objective function by which you measure the performance of a system

or can you find curiosities and interesting things. Yeah, well, I think that the first measurement would be to detect how much of an effect you can have in your environment. So if you look around, we have cities, and that is constructed in Rhymns, and that's where a lot of people live, most people live. So that would be a good sign of intelligence that you don't just live in an environment, but you construct it to your liking.

And that's something pretty unique. I mean, there are certainly birds built nest, I know, but they don't build quite cities. Termites build Mounds and hives and things like that, but the complexity of the human Construction cities. I think would stand out even to an external observer. Of course, that's what a human would say. Yeah, and you know, you can certainly say that sharks are really smart because they've been around so long and they haven't destroyed their environment, which humans are about to do, which is not a very smart thing. But we'll get over it. I believe, and we can get over it by doing some construction that actually has been nine and maybe even enhances the resilience of nature.

So you mentioned the simulation that we run over and over might start, it's a slow start. So do you think how unlikely, first of all, I don't know if you think about this kind of stuff, but how unlikely is step number zero, which is the springing up, like the origin of life on earth. And second, how unlikely is the anything interesting happening beyond that. Sort of like the start that creates all the rich complexity that we see on earth today. Yeah. There are people who are working on exactly that problem from primordial soup. How do you actually get self-replicating molecules? And they are very close.

With a little bit of help, you can make that happen. So of course, we know what we want. So they can set up the conditions and try out conditions that are conducive to that. For evolution to discover that took a long time. For us to recreate it probably won't take that long. And the next steps from there, I think also with some handholding I think we can make that happen. But the evolution, what was really fascinating was eventually the runaway evolution of the brain

that created humans and created, well, also other higher animals. That was something that happened really fast. And that's a big question. Is that something replicable? It's just something that can happen. And if it happens, does it go in the same direction? That is a big question to ask.

Even in computational terms, I think that it's relatively possible to come up here, create an experiment where we look at the primordial soup and the first couple of steps of multicellular organisms even. But to get something as complex as the brain, we don't quite know the conditions for that. And how do you even get started and whether

we can get this kind of runaway evolution happening? From a detector perspective, if we're observing this evolution, what do you think is the brain? What do you think is the, let's say, what is intelligence? In terms of the thing that makes humans special, we seem to be able to reason, we seem to be able to communicate, but the core of that is this something in the broad category we might call intelligence. So if you put your computer scientist hat on, is there favorite ways you like to think about

that question of what is intelligence? like to think about that question of what is intelligence? Well, my goal is to create agents that are intelligent. Not to define what. And that is a bit of defining it. And that means that it's some kind of an object or a program that has limited sensory and effective capabilities interacting with the world and then also a mechanism for making decisions. So with limited abilities like that, can it survive? Survival is the simplest goal, but you could also give it other goals. Can it multiply? Can it solve problems that you give it?

That is quite a bit less than human intelligence. Animals would be intelligent, of course, with that definition. You might have even some other forms of life. Intelligence, in that sense, is a survival skill given resources that you have and using your resources so that you will stay around. Do you think death mortality is fundamental to an agent? So like there's I don't know if you're familiar, there's a philosopher named Ernest Becker

who wrote the denial of death. And his whole idea and there's folks, psychologists, cognitive scientists that work on tear management theory. And they think that one of the special things about humans is that we're able to sort of foresee our death, right? We can, we can realize not just as animals do sort of constantly fear in an instinctual sense, respond to all the dangers that are out there, but like understand that this right ends eventually. And that in itself is the most, is the force behind all of the creative efforts of human nature. That's the philosophy.

I think that makes sense. A lot of sense. I mean, I almost probably don't think of death the same way, but humans know that your time is limited and you want to make it count. And you can make it count in many different ways, but I think that has a lot to do with creativity and the need for humans to do something beyond just surviving. And now going from that simple definition to something that's the next level, I think that that could be the second level of definition. That intelligence means something, and you do something that stays behind you. That's more than your existence.

Something you create, something that is useful for others, is useful in the future, not just for yourself. And I think that's a nice definition of intelligence in a next level. And it's also nice, because it doesn't require that they are humans or biological. They could be artificial agents that are intelligence. They could achieve those kind of goals. So particular agent, the ripple effects of their existence on the entirety of the system is significant.

So like they leave a trace where there's like a, yeah, like ripple effects. It's the, but see then you go back to the butterfly with the flap of a wing. And then you can trace a lot of like nuclear wars and all the conflicts of human history, somehow connected to that one butterfly that created all the chaos. So maybe that's not, maybe that's a very poetic way to think that that's something we humans in a human-centric way. I want to hope we have this impact like that is the secondary effect of our intelligence. We've had that long lasting impact on the world, but maybe the entirety of physics in

the universe has a very long-lasting effect. Sure, but you can also think of it, what if, like, the wonderful life? What if you're not here? Well, somebody else do this. Is it something that you actually contributed because you had something unique to compute? That's a pretty high bar, though. Uniqueness. Yeah. So, you have to be more sorry to something to actually reach that level, nobody would have developed that. But other people might have solved this equation

if you didn't do it. But also within limited scope, I mean, during your lifetime or next year, you could contribute something that unique that other people did not see. And then that could change the way things move forward for a while. So I don't think we have to be more charged to be called intelligence, but we have this local effect

that is changing. If you weren't there, that would not have happened. And it's a positive effect, of course course you wanted to be a positive effect. Do you think it's possible to engineer in to computational agents a fear of mortality? Like does that make any sense? So there's a very trivial thing where it's like you can just code in a parameter, which is how long the life ends, but more of a fear of mortality like awareness of the way that things end and somehow encoding a complex representation of

that fear which is like maybe as it gets closer you become more terrified. I mean, there seems to be something really profound about the sphere that's not Currently incodable in a trivial way into our programs Well, I think you're you're referring to the emotion of fear something because we have cognitively We know that we have limited lifespan and most of us cope with it by just hey That's what the world is like and I make the most of it, but sometimes you can have a fear that's not healthy that paralyzes you, as you can do anything. And somewhere in between, they're not caring at all and getting paralyzed because of fear is a normal response,

which is a little bit more than just logic and it's emotion. So now the question is what good are emotions? I mean, they are quite complex and they are multiple dimensions of emotions and they probably do serve a survival function, heightened focus, for instance. And fear of death might be a really good emotion when you are in danger that you recognize it. Even if it's not logically necessarily easy to derive and you don't have time for that logical deduction, you may be able to recognize that situation is dangerous and this fear kicks in and you all of a sudden perceive the facts that are important for that.

And I think that's generally the role of emotions. It allows you to focus what's relevant for a situation. And maybe if your death plays the same kind of role, but if it consumes you and it's something that you think in normal life and you don't have to, then it's not healthy and then it's not productive. Yeah, but it's fascinating to think how to incorporate emotion into a computational agent.

It almost seems like a silly statement to make, but it perhaps seems silly because we have such a poor understanding of the mechanism of emotion, a fear of, I think at the core of it is another word that we know nothing about, but say a lot, which is consciousness. Do you ever, in your work, or like maybe on a coffee break, think about what the heck is

this thing consciousness, and is it at all useful in our thinking about AI systems? Yes, it is an important question. You can build representations and functions, I think, into these agents that act like emotions and consciousness, perhaps. So, I mentioned emotions being something that allow you to focus and pay attention, filter out what's important. Yeah, you can have that kind of a filter mechanism. And it puts you in a different state. Your computation is in a different state. Certain computation is in a different state. Certain things don't really get through another's heightened.

Now, you label that box emotion. I don't know if that means it's an emotion, but it acts very much like we understand what emotions are. And we actually did some work like that. Modeling hyenas who were trying to steal a kill from lions, which happens in Africa. I mean, hyenas are quite intelligent, but not really intelligent. And they have this behavior that's more complex than anything else they do.

They can bend together if there's about 30 of them or so. They can coordinate their effort so that they push the lions away from a kill. Even though the lions are so strong, they could kill a hyena by striking with a paw. But when they work together and precisely time this attack, the lions will leave and they get the kill. And probably there are some states, like emotions that the hyenas go through.

The first they call for reinforcements, they really want that kill, but there's not enough for them. So they vocalize and there's more people, more people. Mohyenas that come around. And then they have two emotions. They're very afraid of the lion. So they want to stay away, but they also have a strong affiliation between each other.

And then this is the balance of the two emotions. And also, yes, they also want to kill. So it's both repelled and attractive. And then, but then this affiliation eventually is so strong that when they move, they move together, they act as a unit, and they can perform that function. So there's an interesting behavior that seems to depend on these emotions strongly and makes it possible in the actions. And I think a critical aspect of that, the way you're describing is emotion there is a mechanism of social communication, of a social interaction. Maybe that maybe humans won't even be that intelligent. Or most things we think of as intelligent

wouldn't be that intelligent without the social component of interaction. Maybe much of our intelligence is essentially an outgrowth of social interaction. And maybe for the creation of intelligent agents we have to be creating fundamentally social systems. Yes, I strongly believe that's true. And yes,

the communication is multifaceted. I mean, they vocalize and call for friends, but they also rob against each other and they push and they do all kinds of gestures and so on. So they know not alone. And I don't think people act alone very much either, at least normal, most of the time. And social systems are so strong for humans that I think we built everything on top of these kind of structures. And one interesting theory around that, Biggest Theory, for instance, for language, for language origins, is that where did language come from? And it's a plausible theory that first came social systems

that you have different roles in a society. And then those roles are exchangeable. I scratch your back, you scratch my back, you can exchange roles. And once you have the brain structures that allow you to understand actions in terms of roles that can be changed, that's the basis for language, for grammar.

And now you can start using symbols to refer to objects in the world, and you have this flexible structure. So there's a social structure that's fundamental for language to develop. Now, again, then you have language. So you can you can refer to things that are not here right now. And that allows you to then build all the good stuff about planning, for instance,

and building things and so on. So yeah, I think that very strongly humans are social, and that gives us ability to structure the world. But also, as a society, we can do so much more, because we don't, one person does not have to do everything. You can have different roles and together achieve a lot more. And that's also something we see in computational simulations today. We have multi-agent systems that can perform tasks, this fascinating demonstration, Mark Adorego, I think it was. These robots, little robots that had to navigate through an environment and there were things that dangers like maybe a big jasmine or some kind of groove, a hole, and they could not get across it.

But if they grab each other with their gripper, they form a robot that was much longer of the team. And this way they could get across that. So this is a great example of how together we can achieve things we could in otherwise, like the hyenas, you know, your loan they couldn't, but as a team they could. And I think humans do that all the time. We're really good at that. Yeah, and the way you describe the system of hyenas, it almost sounds algorithmic. Like the problem with humans is they're so complex, it's hard to think of them as algorithms. But with hyenas, there's a, it's simple enough There's a it's simple enough to where it feels like

at least hopeful that it's possible to create computational systems that mimic that. Yeah, that's exactly why why we looked at that as opposed to humans. Like I said, they are intelligent, but they are not quite as intelligent intelligent as say baboons, which would learn a lot and would be much more flexible. Hyenas are relatively rigid in what they can do. And therefore, you could look at this behavior like this is a breakthrough in evolution about to happen. Yes. That they've discovered something about social structures, communication, about cooperation,

and it might then spill over to other things too in thousands of years in the future. Yeah, I think the problem with baboons and humans is probably too much is going on inside the head, we won't be able to measure it if we're observing the system. With hyenas, it's probably easier to observe the actual decision making and the various motivations that are involved. Yeah, they are visible. And we can even quantify possibly their emotional state because they leave droppings behind. And there are chemicals there that can be associated with neurotransmitters.

And we can separate what emotional state might have, experienced in the last 24 hours. What to use the most beautiful speaking of hyenas. What to use the most beautiful nature inspired algorithm in your work that you've come across something maybe early on in your work or maybe today? I think it's evolution computation is the most amazing method. So what fascinates me most is that with computers,

is that you can get more out than you put in. I mean, you can write a piece of code, and your machine does what you told it. I mean, this happened to me in my freshman year. It did something very simple, and I was just amazed. I was blown away that it would get the number, and it would compute the result, and I didn't amazed. I was blown away that it would get the number and it would compute the result. And I didn't have to do it myself very simple.

But if you push that a little further, you can have machines that learn. And they might learn patterns. And already, say, deep learning neural networks, they can learn to recognize objects, sounds, patterns that humans have trouble with. And sometimes they do it better than humans, and that's so fascinating.

And now if you take that one more step, you get something like evolution algorithms that discover things, they create things. They come up with solutions that you did not think of. And that just blows me away. It's so great that we can build systems, algorithms, that can be in some sense smarter than we are, that they can discover solutions that we might miss. A lot of times it is because we have as humans,

we have certain biases, we expect the solutions to be a certain way, and you don't put those biases into the algorithms, so they are more free to explore. And evolution is just absolutely fantastic explorer. And that's what what really it's fascinating. Yeah, I think I gave me a fun of a bit because I currently don't mean kids, but you mentioned programs. I mean Do you have kids? Yeah, so maybe you could speak to this, but there's a magic to the creation of creative process like I With spot the the boss and dynamic spot, but really, any robot that I ever worked on, it just feels like the similar kind of joy I imagine I would have as a father, not the same perhaps level, but like the same kind of wonderment,

like that exactly this, which is like, you know what you had to do initially to get this thing going, let's speak on the computer side inside like what the program looks like, but something about it doing more than what the program was written on paper is like, that somehow connects to the magic of this entire universe, like that's like, I feel like I found God every time I like it's like, because you've really created something that's living, even if it's a separate. It has a life with its own, it has the intelligence of its own, it's beyond what you actually thought.

And that is, I think it's exactly spot on, that's exactly what it's about. You created something and has an ability to live its life and do good things. And you just gave it a starting point. So in that sense, I think that may be part of the joy, actually. But you mentioned creativity in this context, especially in the context of evolutionary computation. So we don't often think of algorithms as creative. So how do you think about creativity? Yeah. think of algorithms as creative. So how do you think about creativity? Yeah, algorithms absolutely can be creative. They can come up with solutions that you don't think about. I mean, creativity can be defined. A couple of requirements have to has to be new.

It has to be useful and it has to be surprising. And those certainly are true with say evolution computation discovering solutions. So maybe an example, for instance, we did a collaboration with MIT Media Lab, KELP Harvest Lab, where they had a hydroponic food computer, they called it, an environment that was completely computer controlled, nutrients, water, light, temperature, everything is controlled. Now, what do you do if you can control everything? Farmers know a lot about how to make plants grow in their own patch of land, but if you can control everything, it's too much. And it turns out that we don't actually know very much about it.

So we built a system, a velocity optimization system, together with a surrogate model of how plants grow and let this system explore recipes on its own. And initially, we were focusing on light, how strong, what wavelengths, how long the light was on. And we put some boundaries, which we thought were reasonable. For instance, that there was at least six hours of darkness, like night, because that's what we have in the world. And very quickly, the system evolution pushed all the recipes to that limit. We were trying to grow basil, and we had initially have some 200, 300 recipes, exploration as well as known recipes,

but now we are going beyond that. And everything was like pushed at that limit. So we look at it and say, well, we can easily just change it. Let's have it your way. And it turns out the system discovered that Basel does not need to sleep. 24 hours, lights on, and it will thrive. It will be bigger, it will be tastier.

And this was a big surprise, not just to us, but also the biologist in the team that anticipated that there's some constraints that are in the world for a reason it turns out that evolution did not have the same bias. And therefore, we discovered something that was creative. It was surprising, it was useful and it was useful, and it was new. That's fascinating to think about like the things we think that are fundamental to living

systems on earth today, whether they're actually fundamental or they somehow shape fit the constraints of the system and all we have to do is just remove the constraints. Do you ever think about, I don't know how much you know about brain computer interfaces in your link? The idea there is, you know, our brains are very limited. And if we just allow, we plug in, we provide a mechanism for a computer to speak with the brain. So you're there by expanding the computational power of the brain, the possibilities there, sort of from a very high level

of philosophical perspective, is limitless. But I wonder how limitless it is. Are the constraints we have, like, features that are fundamental to our intelligence? Or is it just like this weird constraint in terms of our brain size and skull and lifespan and Senses is just the weird little like a quirk of evolution and if we just open that up

Like add much more senses add much more computational power the intelligence will be will expand exponentially. Do you have a Do you have a sense about constraints, the relationship of evolution and computation to the constraints of the environment? Well, at first I'd like to comment on that, like changing the inputs to human brain. Yes, that would be great. And the flexibility of the brain, I think there's a lot of that. The eye experiments that are done in animals like Mikangasura, the MIT switching the auditory and visual information, going to the wrong part of the cortex and the animal was still able to hear and perceive the visual environment. And there are kids that are born with severe disorders and sometimes they have to remove half of the brain,

like one half, and they still grow up. They have the functions micro it to the other parts. There's a lot of flexibility like that. So I think it's quite possible to hook up the brain with different kinds of sensors, for instance. And something that we don't even quite understand will have today, on different kind of wavelengths or whatever they are. And then the brain can learn to make sense of

it. And that I think is this good hope that these prosthetic devices, for instance, work not because we make them so good and so easy to use, but the brain adapts to them and can learn to take advantage of them. And so In that sense, if there's a trouble, a problem, I think that brain can be used to correct it. Now, going beyond what we have today, can you get smarter? That's really much harder to do. Giving the brain more input, probably might overvalomate,

it would have to learn to filter it and focus, in order to use the information effectively and augmenting intelligence with some kind of external devices like that might be difficult, I think, but replacing what's lost, I think, is quite possible. Right. So our intuition allows us to sort of imagine that we can replace what's been lost, but expansion beyond what we have. I mean, we are already one of the most, if not the most intelligent things on the surface,

right? So it's hard to imagine if the brain can hold up with an order of magnitude greater set of information thrown at it, if it can do, if it can reason through that. Part of me, this is the russian thing, I think, is I tend to think that the limitations is where the the superpower is that you know immortality and huge increase in bandwidth of information

by connecting computers with the brain is not going to produce greater intelligence. It might produce lesser intelligence. So I don't know, there's something about the scarcity being essential to fitness or performance, but that could be just because we're so limited. Exactly. You make do with what you have, but you can't, you don't have to pipe it directly to the brain. I mean, we already have devices like phones where we can look up information at any point. Yeah. And that can make us more productive. You don't have to argue about, I don't know, what happened in that baseball game, whatever

it is, because you can look it up right away. And I think in that sense, we can learn to utilize tools. And that's what we have been doing for a long, long time. So, and we are already, the brain is already drinking from the water, fire hose, like vision. There's way more information in a vision that we actually present. So brain is already good at identifying what matters.

And that, we can switch that from vision to some other wavelength or some other kind of modality, but I think that the same process principles probably still apply. But also indeed, this ability to have information more accessible and more relevant, I think, can enhance what we do. I mean, kids today at school, they learn about DNA. I mean things that we're discovered just a couple of years ago and they it's already common knowledge and we are building on it and we don't see a problem where where there's too much information that we can absorb and learn. Maybe people become a little bit more narrow in what they know they are in one field. But this information that we have accumulated,

it is passed on and people are picking up on it and they are building on it. So it's not like we have reached a point of saturation. We have still this process that allows us to be selective and decide what's interesting. I think still works, even with the more information we have today. Yeah, it's fascinating to think about Wikipedia becoming a sensor.

So the firehose of information from Wikipedia, is like you integrated directly into the brain to where you're thinking. Like you're observing the world with all of Wikipedia directly piping into your brain. So like when I see a light, I immediately have like the history of who invented electricity, like integrated very quickly into. So just the way you think about the world might be very interesting if you can integrate that kind of information. What are your thoughts if I could

ask on the early steps on the neural link side? I don't know if you got a chance to see, but there's a monkey playing pawn. Yeah, through the brain computer interface. And the dream there is sort of you're already replacing the thumb. Essentially, that you would use to play video game. The dream is to be able to increase further the interface by which you interact with the computer. Are you impressed by this? Are you worried about this? What are your thoughts as a human? I think it's wonderful. I think it's great that we could do something like that. There are devices that read your EEG, for instance, and humans can learn to control things

using just their thoughts in that sense. And I don't think it's that different. I mean, those signals would go to limbs, they would go to thumbs. Now, the same signals go to a sensor to some computing system. It still probably has to be built on human terms, not overwhelm them, but utilize what's there.

And sense the right kind of patterns that are easy to generate. But oh, I think it's really quite possible and wonderful and could be very much more efficient. Is there, so you mentioned surprising being a characteristic of creativity? Is there something you already mentioned a few examples, but is there something that jumps out at you as was particularly surprising from the various evolutionary computation systems you've worked on, the solutions that were come up along the way, not necessarily the final solutions, but maybe things that were even discarded. Is there something that just jumps the mind? It happens all the time. I mean, evolution is so creative, so good at discovering solutions

you don't anticipate. A lot of times they are taking advantage of something that you didn't think was there, like a bug in the software. There's a great paper, the community put it together about surprising anecdotes about evolution of computation. A lot of them are indeed in some software environment. There was a loophole or bug and the system utilizes that. By the way, for people who want to read it, it's kind of on the read. It's called the surprising creativity of digital evolution, a collection of anecdotes from

the evolutionary computation and artificial life research communities, and there's just a bunch of stories from all the seminal figures in this community. You have a story in there that released to you at least on the Tic Tac Toe Memory Bomb. So can you, I guess, describe that situation if you think that's still? Yeah, that was quite a bit smaller scale than our base that doesn't need to sleep, surprise. But it was actually done by students in my class in a neural nets evolution computation class.

There was an assignment. It was perhaps a final project where people built game playing AI, it was an AI class. And it was for TikTok to our five in a row in a large board. And this one team evolved an neural network to make these moves. And they set it up, the evolution, they didn't really know what would come out, but it turned out that they did really well, evolution actually won the tournament. And most of the time when it won, it won because the other teams crashed.

And then we look at what was going on was that evolution discovered that if it makes a move that's really, really far away, like millions of squares away. The other teams, the other programs, this expanded memory in order to take that into account until they run out of memory and crash. And then you've been a tournament by crossing all your opponents. I think that's quite a profound example, which is probably applies to most games from a even a game theoretic perspective that sometimes to win, you don't have to be better within the rules of the game.

You have to come up with ways to break your opponent's brain if it's a human. Like not through violence, but through some hack where the brain just is not... You're basically... how would you put it? You're going outside the constraints of where the brain is able to function. Yeah, expectations of your opponent. This was even Kasparov pointed out that when Deep Blue was playing against Kasparov, that it was not playing the same way as Kasparov expected. This has to do with not having the same biases.

That's really one of the strengths of the AI approach. Yeah. Can you at a high level say, what are the basic mechanisms of evolutionary computation, algorithms that use something that could be called an evolutionary approach? I can't as it work. What are the connections to the, it's what are the echoes of the connection to is biological. A lot of these algorithms really do take motivation from biology, but they are caricatures. You try to essentialize it and take the elements that you believe matter. So in evolutionary computation, it is the creation of variation and then the selection upon that. So the creation of variation, you have to have some mechanism

that allow you to create new individuals that are very different from what you already have. That's the creativity part. And then you have to have some way of measuring how well they are doing and using that measure to select who goes to the next generation and you continue. So first, you also have some kind of digital representation of an individual that can be then modified. So I guess humans in biological systems have

DNA and all those kinds of things. You have to have similar kind of encodings in a computer program. Yes, and that is a big question. How do you encode these individuals? So there's a genotype which is that encoding and then a decoding mechanism which gives you the phenotype which is the actual individual that then performs the task and in an environment can be evaluated how good it is. So even that mapping is a big question then how do you do it? But typically the representations are either they are strings of numbers or they are some kind of trees, those are something that we know very well in computer science and we try to do that. DNA in some sense is also a sequence and it's a strain.

So it's not that far from it, but DNA also has many other aspects that we don't take into account necessarily like this folding and interactions that are other than just the sequence itself. And lots of that is not yet captured, and we don't know whether they are really crucial. Evolution, biological evolution has produced wonderful things, but if you look at them, it's not necessarily the case that every piece is irreplaceable and essential. There's a lot of baggage because you have to construct it. And it has to go through various stages. And we still have appendix, appendix, and we have tailbones,

and things like that that are not really that useful. If you try to explain them now, it would make no sense. It would be very hard. But if you think of us as productive evolution, you can see where they came from. They were useful at one point perhaps and no longer are, but they're still there. So that process is complex and your representation should support it.

And that is quite difficult if we are limited with strings or trees, and then we are pretty much limited what can be constructed. And one thing that we are still missing in evolution competition in particular is what we say in biology, major transitions, so that you go from for instance single cell to multicell organisms and eventually societies. There are transitions of level of selection and level of what a unit is. And that's something we haven't captured in evolution competition yet. Does that require a dramatic expansion of the representation?

Is that what that is? Most likely it does, but it's quite, we don't even understand it in biology very well where it's coming from. So it would be really good to look at major transitions in biology, try to characterize them a little bit more in detail, what the processes are. How does a unit, a cell, is no longer evaluated alone. It's evaluated as part of a community, or organism.

Even though it could reproduce, now it can't alone. It has to have the environment. So there's a push to another level, at least the selection. And how do you make that jump to the next level? How do you make the jump as part of the algorithm? Yeah. Yeah. So we haven't really seen that in computation yet. And there are certainly attempts to have open-ended evolution. Things that could add more complexity and start selecting at a higher level, but it is still not quite the same as going from single to multi to society for instance and biology.

So, so there essentially would be as opposed to having one agent, those agent all of a sudden spontaneously decided to then be together and then your entire system would then be treating them as one agent. Something like that. Some kind of weird merger, but also, so you mentioned, I think you mentioned selection. So basically, there's an agent and they don't get to live on if they don't do well. So there's some kind of measure of what doing well is and isn't. And does mutation come into play at all in the process and what the world does

it serve? Yeah, so again, back to what the computational mechanisms of evolution computation are. So the way to create variation, you can take multiple individuals to, usually, but you could do more. And you exchange theot of the representation. You do some kind of recombination, it could be crossover, for instance, in biology you do have DNA strings that cut and put together again. We could do something like that. And it seems to be that in biology, the crossover is really the workhorse the crossover is really the workhorse in biological evolution. In computation, we tend to rely more on mutation.

And that is making random changes into parts of the chromosome. You can try to be intelligent and target certain areas of it and make the mutations also follow some principle. Like you collect statistics of performance and correlations and try to make mutations you believe are going to be helpful. That's where evolution competition has moved in the last 20 years. I mean, evolution competition has been around for 50 years, but a lot of the reason success comes from mutation comes from comes from using statistics. It's like the rest of machine learning based on statistics. We use similar tools to guide evolution and computation. And in that sense, it has diverged a bit

from biological evolution. And that's one of the things I think we could look at again, having a weaker selection, more crossover, large populations, more time, and maybe a different kind of creativity would come out of it. We are very impatient in evolution competition today. We want answers right now, right quickly. And if somebody doesn't perform, kill it. And biological evolution doesn't work quite that way. And more patient.

Yes, much more patient. Yes, much more patient. So I guess we need to add some kind of mating, some kind of like dating mechanisms, like marriage may be in there. So do, uh, into our algorithms to improve the combination mechanisms as opposed to all mutation during all of the work. Yeah, and many ways of being successful, you know, usually in Evers competition we have one goal.

Play this game really well compared to others, but in biology there are many ways of being successful. You can build niches, you can be stronger, faster, larger, or smarter, or eat this or eat that. So there are many ways to solve the same problem survival, and that then breeds creativity. And it allows more exploration. And eventually you get solutions that are perhaps more creative, rather than trying to go from initial population directly,

or more or less directly to your maximum fitness, which you measure, that's just one metric. So in a broad sense, before we talk about newer evolution, do you see evolutionary computation as more effective than deep learning in certain contexts, machine learning broadly speaking, maybe even supervised machine learning. I don't know if you want to draw any kind of lines and distinctions and borders where they rub up against each other kind of thing, or one is more effective than the other in the current state of things. Yes, of course, they are very different than they

address different kinds of problems. The deep learning has been really successful in domains where we have a lot of data. That means not just data about situations, but also what the right answers were. So labeled examples, or they might be predictions, it might be weather prediction, where the data itself becomes labels, what happened, what the weather was today,

and what it will be tomorrow. So they are very effective, deep learning methods on that kind of tasks. But there are other kinds of tasks where we don't really know what the right answer is. Game playing for instance, but many robotics tasks and actions in the world, decision-making and axiopractical applications like treatments and care or investment in stock market. Many tasks are like that. We don't know and we'll never know what the optimal answer is where.

And there you need different kinds of approaches. Re-enforcement learning is one of those. Re-enforcement learning comes from biology as well. Agents learn during their lifetime. They bury and sometimes they get sick and then they don't and get stronger. And then that's how you learn. And evolution is also a mechanism like that by the different time scale because you have a population, not an individual during a lifetime, but an entire population as a whole can

discover what works. And there you can afford individuals that don't work out. Everybody dies and you have a next generation and it will be better than the previous one. So that's the big difference between these methods they apply to different kinds of problems. And in particular, there's often a comparison that's kind of interesting and important between reinforcement learning and evolution of computation. And initially, reinforcement learning was about individual learning during the lifetime.

And evolution is more engineering. You don't care about the lifetime. You don't care about all the individuals that are tested. You only care about the final result. The last one, the best candidate that evolution produced. In that sense, they also applied to different kinds of problems. Now, that boundary is starting to blur a bit.

You can use evolution as an online method and reinforcement learning to create engineering solutions, but that's still roughly the distinction. From the point of view, what algorithm you want to use, if you have something where there is a cost for every trial, reinforcement learning might be your choice. Now if you have a domain where you can use a surrogate, perhaps, so you don't have much

of a cost for trial. And you want to have surprises. You want to explore more broadly than this population-based method is perhaps a better choice because you can try things out that you wouldn't afford when you're doing a reinforcement. There's very few things as entertaining as watching either evolution, computation, or reinforcement learning, teaching a simulated robot to walk. I maybe there's a higher level question they can be asked here, but do you find this whole space in applications in the robotics? Interesting for evolution and computation? Yeah, very much. And indeed, that's the fascinating videos of that. And that's

actually one of the examples where you can contrast the difference. So between reinforcement learning and reinforcement learning evolution. Yes. So if you have a reinforcement learning agent, it tries to be conservative because it wants to walk as long as possible and be stable. But if you have evolution in computation, it can afford these agents that go haywire. They fall flat on their face and they could take a step and then they jump and then again fall flat. And eventually what comes out of that is something like falling that's controlled. And you take another step and another step and you're no longer fall instead you run,

you go fast. So that's a way of discovering something that's hard to discover step by step incrementally because you can afford these evolutionist dead ends, although they are not entirely dead ends in the sense that they can serve as stepping stones. When you take two of those, put them together, you get something that works even better. And that is a great example of this kind of discovery.

Yeah, learning to walk is fascinating. I talk quite a bit to Rostadirarko's MIT. There's a community of folks who just roboticists who love the elegance and beauty of movement and walking by petal robotics is beautiful but also exceptionally dangerous in the sense that like you're constantly following essentially if you want to do elegant movement. And the discovery of that is, I mean, it's such a good example of that the discovery of a good solution sometimes requires a leap of faith and patience and all those kinds of things. I wonder what other spaces where yet to discover those kinds of things in.

Yeah, yeah. Yeah, and another interesting direction is learning for virtual creatures learning to walk. We did a study in simulation, obviously, that you create those creatures, not just their controller, but also their body. So you have cylinders, you have muscles, you have joints and sensors, and you're creating creatures that look quite different. Some of them have multiple legs.

Some of them have no legs at all. And then the goal was to get them to walk, to walk, to run. And what was interesting is that when you evolve the controller together with the body, you get movements that look natural because they are optimized for that physical setup. And these creatures, you start believing them, that they are alive because they walk in a way that you would expect somebody with that kind of a set up to walk. Yeah, there's something subjective also about that, right? I've been thinking a lot about that, especially in the human robot interaction context. You know, I mentioned Spot, the Boston Dynamics robot.

There is something about human robot communication. Let's say let's put it in another context. Something about human and dog context, like a living dog. There's a dance of communication. First of all, the eyes, you both look at the same thing and you dog communicate with their eyes as well. If you and a dog want to deal with a particular object, you will look at the person, the dog will look at you and then look at the object and look back at you, all those kinds of things. But there's also just the elegance of movement. I mean, there's the, of course, the tail and all those kinds of mechanisms of communication., and all seems natural and often joyful. And for robots to communicate that is really difficult how to figure that out

because it's almost seems impossible to hard code in. You can hard code it for a demo purpose, or something like that. But it's essentially choreographed. Like if you watch some of the Boston and NS videos where they're dancing, all of that is choreographed. Like if you watch some of the Boston and Annas videos where they're dancing, all of that is choreographed by human beings. But to learn how to, with your movement, demonstrate a naturalness and elegance, that's fascinating. Of course, in a physical space, that's very difficult to do, to learn the kind of at scale that you're referring to. But

the hope is that you could do that in simulation and then transfer it into the physical space if you're able to model the robots efficiently naturally. Yeah. And sometimes I think that it requires a theory of mind on the side of the robot that they understand what you're doing because they themselves are doing something similar. And that's a big question too. We talked about intelligence in general and a social aspect of intelligence. And I think that's what is required

that we humans understand other humans because we assume that they are similar to us. We have one simulation we did a while ago, Ken Stanley did that, Two robots that were competing, simulation, like you said. They were foraging for food, to gain energy. Then, when they were really strong, they would bounce into the other robot and win if they were stronger. We watched evolution discover more and more complex behaviors.

They first went to the nearest food and then they started to plot a trajectory so they get more, get more, but then they started to pay attention what the other robot was doing. And in the end, there was a behavior where one of the robots, the most sophisticated one, sends to other food pieces where and identified that the other robot was close to

two of a very far distance and there was one more food nearby. So it faked, that's now I'm using anthropomorphized terms, but it made a mood towards those other pieces in order for the other robot to actually go and get them. Because it knew that the last remaining piece of food was close and the other robot would have to travel a long way, lose its energy, and then lose the whole competition. So there was like emergence of something like a theory of mind, knowing what the other robot would do, guided towards bad behavior in order to win.

So we can get things like that happen in simulation as well. But that's a complete natural emergence of a theory of mind. But I feel like if you add a little bit of a place for a theory of mind to emerge like easier, then you can go really far. I mean, some of these things with evolution, you know, you add a little bit of design in there, it'll really far. I mean, some of these things with evolution, you know, you add a little bit of design in there, it'll really help. And I think, I tend to think that a very simple theory of mind will go a really long way for cooperation between agents and certainly for

human robot interaction. Like, it doesn't have to be super complicated. I've gotten a chance to, in the autonomous vehicle space to watch vehicles interact with pedestrians or pedestrians interact with vehicles in general. I mean, you would think that there's a very complicated theory of mind thing going on, but I have a sense, it's not well understood yet, but I have a sense it's pretty dumb. Like it's pretty simple.

There's a social contract there where between humans, a human driver and a human crossing the road where the human crossing the road trusts that the human in the car is not going to murder them. And there's something about, again, back to that mortality thing. There's some dance of ethics and morality that's built in, that you're mapping your own morality into the person in the car. And even if they're driving at a speed where you think if they don't stop, they're going to kill you. You trust that if you step in front of them, they're going to hit the brakes, and there's that weird dance that we do, that I think is a pretty simple model, but of course, it's very difficult to introspect what it is.

And autonomous robots in the human robot interaction context have to build that current robots are much less than what you're describing. They're currently just afraid of everything. They're more, they're not the kind that fall and discover how to run. They're more like, please don't touch anything. Don't hurt anything. Stay as far away from humans as possible.

Treat humans as ballistic objects that you can't, that you do with a large spatial envelope, make sure you do not collide with. That's how, like I mentioned mentioned Elon Musk thinks about autonomous vehicles. I tend to think autonomous vehicles need to have a beautiful dance between human and machine, where it's not just the collision avoidance problem, but a weird dance. Yeah, I think that these systems need to be able to predict what will happen, what the other agent is going to do, and then have a structure of what the goals are and whether those predictions

actually meet the goals. And you can go probably pretty far with that relatively simple setup already. But to call it a theory of mind, I don't think you need to. I mean, it doesn't matter whether pedestrian has a mind, it's an object, and we can predict what we will do, and then we can predict what the states will be in the future, and whether they are desirable states. Stay away from those that are undesirable

and go towards those that are undesirable. So, that's a relatively simple, functional approach to that. Where do we really need the theory of mind? Maybe when you start interacting and you're trying to get the other agent to do something and jointly, so that you can jointly collaboratively achieve something, then it becomes more complex. Well, I mean, even with the pedestrians, you have to have a sense of where their attention,

actual attention in terms of their gaze is, but also like, attention. There's this vision science people talk about the Salatana, just because I'm looking at it doesn't mean I'm paying attention to it. So figuring out what is a person looking at? What is the sensory information they've taken in? And the theory of mind piece comes in is what are they actually attending to cognitively and also what are they thinking about? Like what is the computation that are performing? And you have probably maybe a few options for the pedestrian crossing.

It doesn't have to be, it's like a variable with a few discrete states, but you have to have a good estimation which of the states that brain is in for the pedestrian case and the same is for attending with a robot if you're collaborating to pick up an object, you have to figure out is the human like, there's a few discrete states that the human could be in, you have to, you have to predict that by observing the human.

And that seems like a machine learning problem to figure out what's, how the human is, what's the human up to? It's not as simple as sort of planning, just because they move their arm, means the arm will continue moving in this direction. You have to really have a model of what they're thinking about and what's motivation behind the movement of the arm.

Here we are talking about relatively simple, physical actions, but you can take that the higher levels, also like to predict what the people are going to do. You need to know what their goals are, what are they trying to, are they exercising, are they trying to get summer, but even higher level I mean you are predicting what people will do in their career, what their life themes are, do they want to be famous, rich or do good. And that takes a lot more information, but it allows you to then predict their actions what choices they might make.

So how does evolution and computation apply to the world of neural networks? Because I've seen quite a bit of work from you and others in the world of neural evolution. So maybe first, can you say, what is this field? Yeah, a new revolution is a combination of neural networks and evolution computation in many different forms, but the early versions were simply using evolution as a way to construct a neural network instead of, say, stochastic gradient descent or back propagation. Because evolution can evolve these parameters, weight values in a neural network,

just like any other string of numbers, you can do that. And that's useful because some cases, you don't have those targets that you need to backpropagate from. And it might be an agent that's running a maze or a robot playing a game or something. You don't, again, you don't know what the right answer is, as you don't have backpap, but this way you can still evolve

a neural net. And neural networks are really good at this task because they recognize patterns and they generalize, interplayed between known situations. So you want to have a neural network in such a task, even if you don't have the supervised targets. So that's a reason and that's a solution. And also more recently, now when we have all this deep learning literature, it turns out

that we can use evolution to optimize many aspects of those designs. The deep learning architectures have become so complex that there's little hope for as little humans to understand their complexity and what actually makes a good design. And now we can use evolution to give that design for you. And it might mean optimizing hyper parameters like the depth of layers and so on, or the topology of the network, how many layers, how they connected, but also other aspects like what activation functions you use where in the network during the learning process, or what loss function you use.

You could generate that, even data augmentation. All the different aspects of the design of a deep learning experiments could be optimized that way. So that's an interaction between two mechanisms. But there's also when we get more into cognitive science and the topics that we've been talking about, you could have learning mechanisms at two-level time scales. So you do have an evolution that gives you baby neural networks that then learn during their lifetime. And you have this interaction of two time scales.

And I think that can potentially be really powerful. Now, in biology, we are not born with all our faculties. We have to learn. We have a developmental period. And humans, it's really long. And most animals have something. And probably the reason is that evolution, a DNA, is not detailed enough or plentiful enough to describe them.

We can't describe how to set the brain up. But we can, evolution can decide on a starting point and then have a learning algorithm that will construct the final product. And this interaction of intelligent, well, evolution that has produced a good starting point for the specific purpose of learning from it, with the interaction of the environment. That can be a really powerful mechanism for constructing brains and constructing behaviors. I like how you walk back from intelligence.

So optimize starting point maybe. Yeah. Okay. There's a lot of fascinating things to ask here. And this is basically this dance between your networks and evolution and computation could go into the category of automated machine learning to where you're optimizing whether it's hyperparameters

of the topology or hyperparameters taken broadly. But the topology thing is really interesting. I mean, that's not really done that effectively or throughout the history of machine learning has not been done. Usually there's a fixed architecture, maybe there's a few components you're playing with, but to grow a neural network essentially, the way you grow in it, organisms, really fascinating space, how hard is it, do you think, to grow a neural network?

And maybe what kind of neural networks are more amenable to this kind of idea than others. I've seen quite a bit of work on recurrent neural networks. Is there some architectures that are friendly than others? And is this just a fun, small scale set of experiments? Or do you have hope that we can be able to grow powerful neural networks?

I think we can. And most of the work up to now is taking architectures that already exist that humans have designed and try to optimize them further. And you can totally do that. A few years ago, we did an experiment. We took a winner of the image captioning competition and the architecture.

And just broken into pieces and took the pieces and and that was our search base. See if you can do better and we indeed could, 15% better performance by just searching around the network design that humans had come up in, for millennials and others. So, but that's starting from a point that humans have produced. But we could do something more generally, it doesn't have to be that kind of network. The hard part is just, the couple of challenges, one of them is to define the search space. What are your elements and how you put them together?

And the space is just really, really big. So you have to somehow constrain it and have some hun hunch of what will work because otherwise everything is possible. And another challenge is that in order to evaluate how good your design is, you have to train it. I mean, you have to actually try it out and that's currently very expensive, right?

I mean, deep learning networks may taste the train while imagining having a population of 100 and have to run it for a hundred generations. It's not yet quite feasible computationally. It will be, but also there's a large carbon footprint and all that. I mean, we're using a lot of computation for doing it. So intelligent methods and intelligent, I mean, we have to do some science in order to figure out what the right representations are and right operators are and how do we evaluate them without having to fully train them. And that is where the current research is and making progress in all those fronts. Yes, there are certain architectures that are more amenable to that approach, but also I think we can create our own architecture and all representations that are even better at that.

Do you think it's possible to do like a tiny baby network that grows into something that can induce state of the art, like even the simple data set of the chemist, and just it just grows into a gigantic monster that's the world's greatest handwriting recognition system. Yeah, there are approaches like that, Esteban Real and Cochlear, for instance, that work done evolving a small network and then systematically expanding it to a larger one. Your elements are already there and scaling it up will just give you more power. So again, evolution gives you that starting point. Yes. And then there's a mechanism that gives you the final result and a very powerful approach.

But you could also simulate the actual growth process. And I said before, evolving a starting point and then evolving or training the network, there's not that much work that's been done on that yet. We need some kind of a simulation environment so there are interactions at will. The supervised environment doesn't really, it's not as easily usable here.

Sorry, the interaction between neural networks. Yeah, the neural networks that you're creating, interacting the world, and learning from these sequences of interactions, perhaps communication with others. That's awesome. We would like to get there, but just the task of simulating something is at that level, it's very hard.

It's very difficult. I love the idea. I mean, one of the powerful things about evolution on earth is predators and prey emerged. And like, there's just like, there's bigger fish and smaller fish and it's fascinating to think that you could have neural networks competing against each other, one neural network being able to destroy another one. There's like wars of neural networks competing to solve the M-niss problem. I don't know.

Oh, don't know. Yeah, yeah, yeah. And we actually simulated also that's prepared to pray and it was interesting what happened there with but but many logic bonded this and K whole composer zoologist. So we had again, we had simulated hyenas, simulated zebra's. Nice. And initially, you know, the hyenas just tried to hunt them. And when they actually stumbled upon the zebra, they ate it and were happy. And then the zebra's learned to escape. And the hyenas learned to team up. And actually two of them approached in different directions. And now the zebra's then next step, they generated a behavior where they split in different directions.

Just like, actually Gazelles do in when they are being hunted. They confuse the predator by going in different directions. That emerged. And then more hyenas joined and kind of circled them. And then when they circled them, they could actually hurt the zebras together and eat multiple zebras. So there was an arms race of predators and prey, and they gradually developed more complex behaviors, some of which we actually do see in nature. And this kind of co-evolution, that's competitive co-evolution, it's a fascinating topic,

because there's a promise or possibility that you will discover something new that you don't already know you didn't build it in It came from this arms race. It's hard to keep the arms race going. It's hard to have reads enough simulation That that supports all of these complex behaviors, but at least for several steps, we've already seen it in this breath of the brain scenario. First of all, it's fascinating to think about this context in terms of evolving architectures. So I've studied Tesla Autopilot for a long time. It's one particular implementation of a NEI system that's operating in the real world. I find it fascinating because of the scale at which it's used out in the real world. And I'm not sure if you're familiar with that system much,

but, you know, Andre Kapati leads that team on the machine learning side. And there's a multitask network, multi-headed network, where there's a core, but it's trained on a particular task and there's a bunch of different heads that are trained on that. Is there some lessons from evolution in computation or neuro-evolution that could be applied to this kind of multi-headed beast that's operating in the real world? Yes. It's a very good problem for neuro-evolution. And the reason is that when you have multiple tasks,

they support each other. So let's say you're learning to classify x-ray images to different pathologies. So you have one task is to classify this disease and another one this disease and another one this one. And when you're learning from one disease, that forces certain kinds of internal representations and embeddings, and they can serve as a helpful starting point for the other tasks.

So you are combining the wisdom of multiple tasks into these representations, and it turns out that you can do better in each of these tasks when you're learning simultaneously other tasks than you would by one task alone. Which is a fascinating idea in itself, yeah. Yes, and people do that all the time. I mean, you use knowledge of domains that you know in new domains, and certainly, no network can do that. When your evolution comes in is that,

what's the best way to combine these tasks? Now, there's architectural design that allows you to decide where and how the embeddings, the internal representations are combined, and how much you combine them. And there's quite a bit of research on that, and my team, Elliot Mayerson, has worked on that, in particular, like, what is a good internal representation that supports multiple tasks?

And we're getting to understand how that's constructed and what's in it, so that it is in a space that supports multiple different heads, like you said. And that, I think, is fundamentally how biological intelligence works as well. You don't build a representation just for one task. You try to build something that's general general not only so that you can do better in one task or Multiple tasks, but also future tasks and future challenges. So you learn the structure of of the world And and that helps you in all kinds of future future challenges And so you're trying to design a representation that will support an arbitrary set of tasks in a particular sort of class of problem Yeah support an arbitrary set of tasks in a particular sort of class of problem. Yeah, and also it turns out, and that's again the surprise that Elliott found, was that those

tasks don't have to be very related. You know, you can learn to do better vision by learning language or better language by learning about DNA structure. No, somehow the world. It rhymes. The world rhymes even. Yes, very, very disparate fields. I mean, on that small topic, let me ask you, because you've also on the competition, you're a science side, you worked on both language and vision. You worked on both language and vision. What's the connection between the two? What's more, maybe there's a bunch of ways to ask this, but what's more difficult to build from an engineering perspective

and evolutionary perspective, the human language system or the human vision system or the equivalent of in the AI space, language and vision or is it the best, is the multitask idea that you're speaking to that they need to be deeply integrated? Yeah, absolutely. The learning both at the same time, I think, is a fascinating direction in the future.

So we have data sets where there's visual component, as well as verbal descriptions, for instance, and now where you can learn a deeper representation, a more useful representation of a ball. But it's still an interesting question of which one is easier. I mean, recognizing objects or even understanding sentences that's relatively possible, but where it becomes, where the challenges are,

is to understand the world. Like the visual world, the 3D, what are the objects doing and predict them, what will happen, the relationships. That's what makes vision difficult. And language, obviously, it's what is being said, what the meaning is. And the meaning doesn't stop at who did what to whom. There are goals and plans and themes. And you eventually have to understand the entire human society and history in order to understand the sentence very much fully.

There are plenty of examples of those kinds of short sentences when you bring in all the world knowledge to understand it. And that's the big challenge. Now, we are far from that, but even just bringing in the visual world together with the sentence will give you already a lot deeper understanding of what's happening. And I think that that's where we're going very soon. I mean, we've had image net for a long time, and now we have all these text collections, but having both together and then learning a semantic understanding of what is happening. I think that

will be the next step in the next few years. You're starting to see that with all the work with transformers, the AI community started to dip their toe into the idea of having language models that are now doing stuff with images with vision and then connecting the two. I mean right now it's like these little explorations were literally dipping the toe in, but like maybe at some point we'll just like dive into the pool and it'll just be all seen as the same thing. I do still wonder what's more fundamental or their vision is whether we don't think about vision correctly, maybe the fact

because we're humans and we see things beautiful and so on, and because we have cameras that take in pixels as a 2D image that we don't sufficiently think about vision as language, you know, maybe Champsky is right all along. That vision is fundamental to uh, sorry, that language is fundamental to everything. To even cognition, to even consciousness. The base layer is all language, not necessarily like English, but some weird abstract representation the linguistic representation. Yeah. Well, early we talked about the social structures, and that may be what's underlying the language. That's the more fundamental part, and then language has been added on top of that.

Language emerges from the social interaction. Yeah, that's a very good guess. We are visual animals, though. A lot of the brain is today dedicated to vision, and also when we think about various abstract concepts, we usually reduce that to vision and images. And that's, you know, go to a whiteboard, you draw pictures of very abstract concepts.

So we tend to resort to that quite a bit. And that's a fundamental representation, probably possible that it predated language even animals, a lot of that don't talk, but they certainly do have vision. And language is interesting development from, from mass education, from eating, you develop an organ that actually can produce sound, the manipulate them. Maybe that was an accident, maybe that was something that was available, and then allowed us to do the communication.

Or maybe it was gestures, sign language. Could that be in the original proto-language? We don't quite know, but the language is more fundamental than the medium in which it's communicated. And I think that it comes from those representations. communicated. And I think that it comes from those representations. Now, in current world, they are so strongly integrated. It's really hard to say which one is fundamental. You'll look at the brain structures and even visual cortex, which supposed to be very much just vision. Well, if you are thinking of semantic concepts, thinking of language, visual cortex

lights up. It's still useful even for language competitions. So there are common structures underlying them. So you utilize what you need. And when you are understanding a scene, you're understanding relationships. Well, that's not so far from understanding relationships between words and concepts. So I think that that's how they are integrated. Yeah, and there's dreams and once it closed our eyes, there's still a world in there somehow operating and somehow possibly the visual system somehow integrated into all the... I tend to enjoy thinking about aliens

and thinking about the sad thing to me about extraterrestrial intelligent life that if it was, if it visited us here on earth, or if we came on Mars and, or maybe another other solar system and other galaxy one day, that us humans would not be able to detect it or communicate with it or appreciate, like it'd be right in front of our nose and we were too self-obsessed to see it. That's self-obsessed, but our our tools, our frameworks of thinking would not detect it as a good movie arrival.

And so on, we're Steven Wolfram and his son, I think, were part of developing this alien language of how aliens would communicate with humans. They ever think about that kind of stuff where if humans and aliens would be able to communicate with each other, like if we met each other at some, okay, we could do a setty, which is communicating from across a very big distance, but also just us, you know, if you did a podcast with an alien, do you think we'd be able to find a common language and a common methodology of communication? I think from a computational perspective, the way to ask that is,

is you have very fundamentally different creatures, agents that are created, would they be able to find a common language? Yes, that's, I do think about that. I mean, I think a lot of people who are in computing an AI in particular, they got into it because they were fascinated with science fiction and all of these options. I mean, start, generate it, all kinds of devices that we have now, they envision. It's true. First, and it's a great motivator. The think about things like that.

and it is a great motivator to think about things like that. And so one, and again, being a computational scientist and trying to build intelligent agents, what I would like to do is have a simulation where the agents actually evolved communication. Not just communication, we've done that, people have done it many times, they communicate, they signal, and so on, but actually develop a language.

And language means grammar, it means all these social structures and on top of that grammatical structures. And we do it under various conditions, and actually try to identify what conditions are necessary for it to come out. And then we can start asking that kind of questions. Are those languages that emerge in those different, similar environments? Are they understandable to us?

Can we somehow make a translation? We can make it a concrete question. So machine translation of evolved languages, and so like languages that evolve come up with can we translate like I have a Google translate for the evolved languages. Yes, and if we do that enough we have perhaps an idea what an alien language might be like the space of where those languages can be because we can set up their environment differently. can be because we can set up their environment differently. They doesn't need to be gravity. You can have all kinds of societies can be different. They may have no predators. They may have, or everybody's a predator, all kinds of situations.

And then see what the space possibly is where those languages are and what the difficulties are. They'll be really good actually to do that before the aliens come here. Yes, it's good practice. On the similar connection, you can take of AI systems as aliens, is there a ways to evolve a communication scheme for, there's a field you can call it like explainable AI, for AI systems to be able to communicate.

So you evolve a bunch of agents, but for some of them to be able to communicate. So you evolve a bunch of agents, but for some of them to be able to talk to you also. So to evolve away for agents to be able to communicate about their world to us humans, do you think that there's possible mechanisms for doing that? We can certainly try. And if it's an evolution of competition system,

for instance, you reward those solutions that are actually functional, that communication makes sense, it allows us to together, again, achieve common goals. I think it's possible. But even from that paper that you mentioned, the anecdotes, it's quite likely also that the agents learn to lie and fake and do all kinds of things like that.

I mean, we see that in even very low level, like bacterial evolution, there are cheaters. And who's to say that what they say is actually what they think? But that's one thing that there would have to be some common goal so that we can evaluate whether that communication is at least useful. You know, they may be saying things just to make us feel good or get us to do what we want, whatever, not turn them off or something. But so we would have to understand their internal representations much better to really make sure that translation is critical. But it can be useful. And I think it's possible to do that. There are examples where visualizations

are automatically created so that we can look into the system and the language is not that far from it. I mean, it is a way of communicating and logging what you're doing in some interpretable way. I think you're fascinating topic, yeah, to do that. You make me realize that it's a good scientific question where their lying is an effective mechanism for integrating yourself and succeeding in a social network and a social in a world that is social. I tend to believe that honesty and love

are evolutionary advantages in an environment where there's a network of intelligent agents, but it's also very possible that dishonesty and manipulation and even violence, all those kinds of things might be more beneficial. That's the old open question about good versus evil. But I don't know if it's a hopeful, maybe I'm delusional, but it feels like karma is a thing, which is like long term agents they're just kind to others.

Sometimes for no reason, we'll do better. In a society that's not highly constrained on resources. It's like people start getting weird and evil towards each other and bad when the resources are very low relative to the needs of the populace, especially at the basic level like survival shelter, food, all those kinds of things. But I tend to believe that once you have those things established, then well, not to believe, I guess I hope that AI systems will be honest. But it's fun. It's scary to think about the touring tests. AI systems that will eventually pass the touring test will be ones that are exceptionally

good at lying. That's a terrifying concept. I mean, I don't know. First of all, from somebody who studied language and obviously are not just a world expert in AI, but somebody who joins us about the future of the field. Do you hope, do you think there will be human level or superhuman level intelligences in the future that we eventually build?

Well, I definitely hope that we can get there. One, I think important perspective is that we are building AI to help us. It is a tool like cars or language or communication. AI will help us be more productive. That is always a condition. It's not something that we build and let run. It becomes an entity of its

own that doesn't care about us. Now, of course, really find the future maybe that might be possible, but not in the foreseeable future when we are building it. And therefore, we always in a position of limiting what it can or cannot do. And the, your point about lying is very interesting. Even in this high-nature society, for instance, when a number of these high-nature bands together and they steal a risk and steal the kill, they're always high-nature that hang back. And don't participate in that risky behavior but they walk in later and join the party after the kill and there are even some that may be ineffective and cause others to have harm. So and like I said, even bacteria cheat and we see it in biology, there's always

some element on opportunity. If you have a society, in order for society to be effective, you have to have this corporation and you have to have trust. And if you have enough of agents who are able to trust each other, you can achieve a lot more. But if you have trust, you also have opportunity for cheaters and liars. And I don't think that's ever going to go away. There will be hopefully a minority so that they don't get in the way. And we studied in these high-end simulations, like what the proportion needs to be before it's no longer functional. And you can point out that you can tolerate a few cheaters and a few liars,

and the society can still function. And that's probably going to happen when we build these systems that autonomously learn. The really successful ones are honest because that's the best way of getting things done. But there probably are also intelligent agents that find that they can achieve their goals by bending the rules or cheating. So there could be a huge benefit to as opposed to having fixed AI systems, say we build an AGI system and deploying millions of them, that are exactly the same. There might be a huge benefit to introducing sort of from like an evolution in competition perspective, a lot of variation.

introducing sort of from like an evolution competition perspective a lot of variation. Yeah, sort of like diversity in all its forms is beneficial even if some people are assholes or some robots are assholes So like it's beneficial to have that because I Because you can't always a priori. I know what's good. What's bad? But And there's that there's a fascinating. Absolutely. Diversity is the bread and butter. I mean, if you're running on a location, you see diversity is the one fundamental thing you have to have. And absolutely, it's also, it's not always good diversity.

It may be something that can be destructive. We had in these high simulations, we have high in this, it's just suicidal. They just run and get killed. But they form the basis of those who actually are really fast, but stop before they get killed and eventually turn into this mob. So there might be something useful there if it's recombined with something else. So I think that as long as we can tolerate some of that, it may turn into something better. You may change the rules because it's so much more efficient to do something that was actually against the rules before. And we've seen society change over time, quite a bit along those lines.

There were rules in society that we don't believe are fair anymore, even though they were considered proper behavior before. So things are changing. And I think that in that sense, I think it's a good idea to be able to tolerate some of that, some of that cheating because eventually we might turn into something better. So, yeah, I think this is a message to the trolls and the assholes of the internet that you two have a beautiful purpose in this human ecosystem. So, I appreciate you very much. In water quantities. In water quantities.

So, there's a whole field of artificial life. I don't know if you're connected to this field if you pay attention. Do you think about this kind of thing? Is there an impressive demonstration to you of artificial life? Do you think of the agency you work within the evolutionary computation perspective as life? And what do you think this is headed? Like is there interesting systems that will be creating more and more

that make us redefine maybe rethink about the nature of life? Different levels of definition and goals there. I mean, at some level, out of life can be considered a little multi-agent systems that build a society that, again, achieves a goal, and it might be robots that go into a building and clean it up or after earthquake or something. You can think of that as an artificial life problem, in some sense.

Or you can really think of it, artificial life as a simulation of life, and a tool to understand what life is and how life evolved in Earth. And I guess in an artificial life conference, there are branches of that conference sessions of people who really worry about molecular designs and the start of life, like I said, primordial soup where eventually you get something self replicating. And they are really trying to build that. So it's a whole range of topics. And I think that artificial life is a great tool to understand life. And there are questions like sustainability, species. We're losing species, how bad is it? Is it natural? Is there a tipping point?

And where are we going? I mean, like the hyena evolution, we may have understood that there's a pivotal point in their evolution. They discovered cooperation and coordination. You know, artificial light simulations can identify that. And maybe encourage things like that. So, and also, societies can be seen as a form of life itself. I mean, we're not talking about biological evolution, evolution of societies. Maybe some of the same phenomena emerge in that

domain and having artificial life simulations and understanding could help us build better societies. Yeah, and thinking from a mean perspective of Richard Dawkins, that maybe the organisms, ideas of the organisms, not the humans in these societies, that from, it's almost like reframing what is exactly evolving. Maybe the interesting the humans aren't the interesting thing as the contents of our minds is the interesting thing and that's what's multiplying and that's actually multiplying and evolving in a much faster time scale and that maybe has more power on the trajectory of life on earth than this biological evolution.

Yes. They have a lot of these ideas? Yes. And it's fascinating, I guess it before, that we can keep up somehow biologically. We go all to a point where we can keep up with this meme evolution, literature, internet. We understand DNA and we understand fundamental particles. We didn't start that way. I mean, that was a year ago,

and we haven't evolved biologically very much, but somehow our minds are able to extend. And there for AI can be seen also as one such step that we created and it's our tool, and it's part of that meme evolution that we create, even if our biological evolution does not progress as fast. And us humans might only be able to understand so much.

We're keeping up so far, or we think we're keeping up so far, but we might need AI systems to understand. Maybe like the physics of the universe is operating like a strength theory. Maybe it's operating on much higher dimensions. Maybe we're totally because of our cognitive limitations and not able to truly internalize the way this world works.

And so we're running up against the limitation of our own minds, and we have to create these next-level organisms like AI systems that would be able to understand, really understand what it means to live in a multi-dimensional world that's outside of the 40 mentions, the three of space and one of the time. And the translation, and generally we can deal with the world even if you don't understand all the details, we can use computers. Yes. Even though we don't, most of us don't know all the structures that's underneath or drive a car.

I mean, there are many components, especially new cards that you don't quite fully know, but you have the interface, you have an abstraction of it that allows you to operate it and utilize it. And I think that that's perfectly adequate and we can build on it. And AI can be a play a similar role. I have to ask about beautiful artificial life systems or evolution competition systems, cellular automata to me. Like, I remember it was a game changer for me early on in life when I saw Conway's Game of Life who recently passed away, unfortunately.

It's beautiful. How much complexity can emerge from such simple rules. I just don't, somehow that simplicity is such a powerful illustration, and also humbling because it feels like I personally, from my perspective, understand almost nothing about this world, because my intuition fails completely how complexity can emerge from such simplicity.

Like my intuition fails, I think, because of the biggest problem I have. Do you find systems like that beautiful? Do you think about cellular trauma? Because cellular trauma don't really have many other artificial life systems. Don't necessarily have an objective, maybe that's a wrong way to say it. It's almost like it's just evolving and creating. And there's not even a good definition of what it means to create something complex and interesting and surprising. All those words that you said, is there some of those systems you find beautiful? Yeah, and similarly, evolution does not have a goal.

It is responding to current situation. And survival then creates more complexity. And therefore, we have something that we perceive as progress. But that's not what evolution is inherently said to do. And yeah, that's not what evolution is inherently said to do. And yeah, that's really fascinating while how a simple set of rules or simple mappings can, from such simple mappings, complexity can emerge.

So to question of emergence and self-organization and the game of life is one of the simplest ones and very visual and therefore it drives home the point that it's possible that non-linear interactions and And this kind of Complexity can emerge emerge from them and biology and evolution is along the same lines. We have simple representations DNA if you really think of it, it's not that complex. It's a long sequence of them, there's lots of them,

but it's a very simple representation and similar evolution of computation, whatever string or tree representation we have and the operations, the amount of code that's required to manipulate those, it's really, really little. And of course, game alive, you're unless. So how complex the emerges from such simple principles, that's absolutely fascinating.

The challenge is to be able to control it and guide it and direct it so that it becomes useful. And like game alive is fascinating to look at and evolution, all the forms that come out is fascinating, but can we actually make it useful for us? And efficient, because if you actually think about each of the cells in the game of life as a living organism, there's a lot of death that has to happen to create anything interesting. And so I guess the questions for us humans that are mortal in their life and quickly, we

want to kind of hurry up and make sure we make sure we take evolution the trajectory that is a little bit more efficient than the alternatives. Yeah and that touches upon something we talked about earlier that evolution competition is very impatient. Yeah. We have a goal we want it right away versus biology has a lot of time and deep time and weak pressure and large populations. One great example of this is the novelty search. So evolution and computation, where you don't actually specify a fitness goal, something that is your actual thing that you want, but you just reward solutions that are different from what you've seen before. Nothing else. And you know what, you actually discovered things that are interesting and useful

that way. Can Stanley and Joel Emendet, this one study where they actually tried to evolve walking behavior on robots. And that's actually we talked about earlier where your robot actually failed in all kinds of ways and eventually discovered something that was a very efficient walk. And it was because they rewarded things that were different that you were able to discover something. And I think that this is crucial because in order to be really different from what you already have, you have to utilize what is there in a domain to create something really different. So you have encoded the fundamentals of your world, and then you make changes to those fundamentals you get further away.

So that's probably what's happening in these systems of emergence, that the fundamentals are there, and when you follow those fundamentals, you get into points and some of those are actually interesting and useful. Now, even in that robotic worker simulation there was a large set of garbage, but among them there were some of these gems. And then those are the ones that somehow you have to outside recognize and make useful.

But these kind of productive systems, if you code them the right kind of principles, I think that they encode the structure of the domain, then you will get to these solutions and you discover it. It feels like that might also be a good way to live life. So let me ask, do you have advice for young people today about how to live life or how to succeed in their career or forget career, just succeed in life. Form an evolution in competition perspective. Yes, yes, definitely.

Explore, diversity, exploration, and individuals, take classes in music, history, philosophy, individuals, take classes in music, history, philosophy, you know, math, engineering, see connections between them, travel, you know, learn a language. I mean, all this diversity is fascinating and we have it at our fingertips today. It's possible. You have to make a bit of an effort because it's not easy. But the rewards are wonderful. Yeah, there's something interesting about an objective function of new experiences. So try to figure out what is the maximally new experience I could have today. So that novelty, optimizing for novelty for some period of time might be very interesting way to sort of

Maximally expand the sets of experience if you had and then ground from that perspective Like what you what will be the most fulfilling trajectory through life. Of course the flip side of that This is where I come from again, maybe Russian. I don't know. But the choice has a choice as a detrimental effect, I think, at least for my mind, where scarcity has an empowering effect. So if I sort of, if I have very little of something, and only one of that something, I will appreciate it deeply, until I came to Texas recently, and I've been picking out on delicious, incredible meat. I've been fasting a lot, so I need to do that again. But when you fast for a few days, the first taste of a food is incredible. So the downside of exploration is that,

for somehow, maybe you can correct me, but somehow you don't get to experience deeply any one of the particular moments, but that could be a psychology thing. That could be just a very human peculiar flaw. Yeah, I didn't mean that you superficially explore. I mean, you can explore deeply. Yeah, so you don't have to explore 100 things, but maybe a few topics where you can take a deep enough time, a dive that you gain an understanding, yourself have to decide at some point that this is deep enough.

And I've obtained what I can from this topic, and now it's time to move on. And that might take years. People sometimes switch careers, and they may stay on some career for a decade and switch to another one, you can do it. You're not pretty determined to stay where you are, but in order to achieve something, 10,000 hours makes, you need 10,000 hours to become an expert on something. So you don't have to become an expert,

but even develop an understanding and gain the experience that you can use later, you probably have to spend, like I said, it's not easy. You get to spend some effort on it. Now, also at some point then, when you have this diversity and you have this experience, this exploration, you may find something that you can't stay away from. Like for us, it was computers, it was AI, it was,

that you just have to do it. And then it was AI, it was, you know, that you, I just have to do it, you know, and I, you know, and then we'll, it will take decades maybe and you are pursuing it because you figure it out that this is really exciting and you can bring in your experiences and there's nothing wrong with that either but you asked what's the advice for young people, you know, that's the expiration part.

And then beyond that, after that expiration, you actually can focus and build a career. And, you know after that exploration, you actually can focus and build a career. And even there, you can switch multiple times. But I think the diversity exploration is fundamental to having a successful career as is concentration and spending an effort where it matters. And but you are in better position to make the choice

when you have done your homework. Explored. Exploration proceeds commitment. But both are in better position to make the choice when you have done your homework. Exploration proceeds commitment, but both are beautiful. So again from a evolutionary computation perspective, we'll look at all the agents that had to die in order to come up with different solutions in simulation. What do you think from that individual agent's perspective is the meaning of it all? So far as humans you're just one agent who's going to be dead unfortunately one day too soon What do you think is the why?

of why that agent came to be and Eventually will be no more Is there meaning to it all? Yeah, in evolution, there is meaning. Everything is a potential direction. Everything is a potential stepping stone. Not all of them are going to work out. Some of them are foundations for further improvement. And even those that have perhaps going to die out, where potential energy is potential solutions. I mean, biology we see a lot of species die of naturally, and you know, like the dinosaurs. I mean, they have a really good solution for a while, but then it didn't turn out to be not such a good solution in the long term. When there's an environmental change, you have to have diversity some other solutions become better. It doesn't mean that that that was an attempt it didn't quite work out or last

but there are still dinosaurs and mountains at least their relatives and they may one day again be useful who knows. So from an individual's perspective you've got to think of a bigger picture that is a huge engine that is innovative and these elements are all part of it, potentially innovations on their own and also as as raw material perhaps or stepping stones for other things that could come after. But it still feels from an individual perspective that I matter a lot, But it still feels from an individual perspective that I matter a lot. But even if I'm just a little cog in the giant machine, is that just a silly human notion in individualistic society? No, should I go that?

Do you do find beauty in being part of the giant machine? Yeah, I think it's meaningful. I think it adds purpose to your life that you are part of something bigger That said are you do ponder your individual agents mortality? Do you do you think about death? Do you fear death? Well, certainly more now than when I was a Youngster and it's guy diving and pergliding and you know all these things

You become wiser There is a reason for this Life arc that younger folks are more fearless in many ways. It's part of the exploration You know, they are that they are the individuals who think, I wonder what's over those mountains or, what if I go really far in that ocean, what would I find?

I mean, older folks don't necessarily think that way, but young people do, and it's kind of counterintuitive. So yeah, but logically, it's like, you know, you have limited amount time, what can you do with it that matters? So try to, you have done your exploration, you committed to certain direction, and you become an expert perhaps in it. What can I do that matters with limited resources that I have?

That's what I think a lot of people on myself included start thinking later on in their career. And like you said, leave a bit of a trace and a bit of an impact even though after the agent is gone. Yeah, that's the goal. Well, this was a fascinating conversation. I don't think there's a better way to end it. Thank you so much. So first of all, I'm very inspired of how vibrant the community at UT Austin and Austin is. It's really exciting for me to see it. And this whole field seems like profound philosophically, but also the path forward for the artificial intelligence community. So thank you so much for explaining so many cool things to me today and for wasting all of your valuable time with me.

Oh, it was a pleasure. Thanks. I appreciate it. today and for wasting all of your valuable time with me. Oh, it was a pleasure. Thanks a lot. I appreciate it. Thanks for listening to this conversation with Ristamakalainen, and thank you to the Jordan Harbourn to show, Grammarly, Bell Campo, and Indeed. Check them out in the description to support this podcast. And now let me leave you some words from Carl Sagan.

Extinction is the rule. Survival is the exception. Thank you for listening. I hope to see you next time. Thank you.