Brain Inspired · AI Research & Frontier Labs · November 2026
Asked why bother building recurrent, brain-like AI when bigger feed-forward networks get the same results, Dehghani argues that systems which build a world model through their own dynamics can experience an environment, and LLMs can't, however much they can say about it.
…bound. Like, you know, that's something and it has negative effect on the environment and so on and so forth. And maybe like someone comes and says, Well, you know, let's just build them in the future. We'll come up with some green technology solution and we don't need to worry about it. But
it's almost disappointing to just, if that's it, it's almost, I don't know why, but it's kind of disappointing to say, like, it just seems like there's it's less special if it's just a matter of efficiency. So I think
this is the idea of scaling, right? Like, you know, people are saying, like, you know what? This is it. Like, we just do this. We just make it bigger and bigger and we have more data. And eventually it's going to solve everything. Right. And in a sense, actually, it touches us personally as humans. Like, okay, this is it. You know, right. Yeah, that's just, that's what I am. But like, first, I don't have any problem with that. Like, because fundamentally, I think, okay, yeah, we're just a bag of atoms. Sure, there's an organization doing something like, you know, and it's very cool. Like, you know, I get hungry. It doesn't matter if there's some neurotransmitters going up. I get hungry and I, you know, I have joy in like drinking a glass of wine because, yes, there's taste buddy. I can explain all of that. But it doesn't, you know, separate me from that experience of being a human and having experiences and so on and so forth. So I have no problem with that. And if there's like some, we can make alternative things that are as intelligent or more intelligent than us, well, then…
But so the learning happens in the dynamics, then the weights get updated after the learning. Is that the way it's done?
So basically, think of that, you know, we have some modules, okay? You know, the idea of composition, we have some modules that these modules are doing, they basically operationalize all the mathematics of back propagation, but only with like few neurons, like three neurons that are doing the sort…
you said, I mean, so you said that you're not claiming that this is the way that brains do it, but the back propagation has been a sort