Akarsh Kumar: preference

Transcript context

…So you wanna have some opportunity to be opportunistic. But, yes, if if everything survives, then you go to the other extreme and then uninteresting things start surviving. Like like we've said in some of our publications Right. You know, about, like, open ended evolution that, like, we we think that we call it the minimal criterion, like, the minimal thing you need to do to be able to pass on to the next generation that it has to be nontrivial. It's something like that we think is important. Like, once it's trivial like, if it's just like if you hit a minimal mass, then you get to have an offspring. This is a thought experiment. It's impossible. But like if somehow like God would intervene and give you a child just because you hit some mass, it might just create a situation where, you know, that the world, yeah, would fill up with just like inert blobs because all they need to do is get And so you you you do want something nontrivial and and, you know, these these constraints enter enter into the nontriviality of the minimal criterion. So it's a complex it's a complex question about how to set something up like this. And then now we're, like, talking about transferring these insights into the way you train a neural network that because it's it's just another leap then of of of sort of, like, cognitive complexity for us to think through. It's like, what is the analogous thing, like, in just a training session where you're being exposed to data? I like that Goldilocks analogy a lot for evolution because I think Joel and Risto had a paper where it's like you need, like, some sort of catastrophic events to happen in order to get adaptable solutions. Extinction events, like near extinction events. So that's, like, 1 extreme. But on the other way, like Ken said, you can't have global competition just everywhere or else you just end up doing, like, local hill climbing Right. Which is what generic algorithm does. You need some sort of local competition and not global competition. Yeah. Have thank you. I I have to thank you, actually, Kenneth, because, you know, when we talked 4 years ago, up until that point, I mean, ironically, I was I was trained a lot in biology and biomedical engineering. And but up until that point, I really hadn't thought that much about evolution and, you know, and since since the conversation with you, I've been thinking about it more and more and more and reading more and more and just becoming increasingly fascinated at how powerful and amazing this this algorithm of of evolution is. You know?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.