ND

Nima Dehghani

Things Nima Says on Podcasts

Where to Find Them

Nima Dehghani has been a guest on Brain Inspired .

Recently: “BI 250 Nima Dehghani: How Brains Compute” on Brain Inspired (November 2026).

What They Said

“If computation is that everything computes, then it's a useless word, and why are we even saying it? If I throw a rock and then say the rock computes its trajectory, does the solar system compute its future state? If that's computation, then everything that moves, everything that changes is computation.” — Nima Dehghani, Brain Inspired

The host worried that neuroscientists say "the circuit computes" as a filler term that empties the word of meaning. Dehghani agrees, and says this is the problem his formal theory of physical computation is meant to fix.

Brain Inspired · 2026-11-18 Permalink → Listen →
Brain Inspired Around 14:26 into the episode
Nima Dehghani

That's my concern. They go to this sort of like hand-waving sort of arguments. Right. But that is. And they become a true believer that it is or it isn't. Right.

Paul Middlebrooks

Right. So my concern is like when you say like the brain computes, the word computation just gets applied to whatever the brain is doing. You call it computation. And that kind of trivializes the notion of computation also. Exactly. You avoid that.

Nima Dehghani

I think that's a big issue, right? Like we don't want to open, you know, if computation is everything computes, then it's a useless word. And why are we even saying it? If I throw a rock and then say, well, you know, the paper is like, you know, the rock computes trajectory. Does the solar system, you know, know what, compute its future state? Like, I mean, if that's computation, then like, okay, so everything that moves, everything that changes is computation. So not every state changes computation. Not every information transfer is a computation. And that's actually the key point here because in that formalization, and you know, I don't want to throw out jargons here because, you know, I don't want to bore all the audience. And, you know, if they're more interested, they can go and read the papers. Yeah, yeah, yeah. And I try to bring different levels of description that, you know, people can. So

Paul Middlebrooks

I'll just, I'll tell people, like, you're making these videos that are kind of explainers of the concepts. And they're fantastic videos. Your papers are very dense. The videos are also very dense. Like, even though you're simplifying things, there's so many things that you've included that, you…

Nima Dehghani

You know, it's funny because I think that's true. Like my papers are very long in general. Like I don't, generally, I don't write short papers. I like very long papers because I want to really get into the details. So it's not that I cannot write short papers, but I think I don't like short papers.…

Paul Middlebrooks

And do you, well, before I ask you about category theory, because this is sort of category theory is a necessary ingredient to this. Actually, I'll go ahead and ask you about that. I mean, you used the word functor. Is category theory the without it? Could you do? Could you explain the computational

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“They say, oh, these agents, they got out of control and they hacked something. So no, they didn't go out of control. You didn't put the right boundaries. … It's not that they sat down and decided, all right, let's start a revolution of hacking. And every day something comes, it's as if they're giving them agency.” — Nima Dehghani, Brain Inspired

The host said calling AI systems "agents" drives him crazy, since by their definition these systems have no agency. Dehghani agrees the term is a misnomer that shifts blame for AI failures from missing guardrails onto the machine.

Brain Inspired · 2026-11-18 Permalink → Listen →
Brain Inspired Around 31:55 into the episode
Paul Middlebrooks

about the same scale.

Speaker 4

…units neurons, right? And sort of usurping a lot of the language. And going back to the closure idea, so now we have AI, quote-unquote, agents. And I think this drives you a little crazy too, because there's nothing actually agential about those because they don't have the computational closure.

Nima Dehghani

That's such a, oh, that's such a misnomer. This is terrible, right? Yeah. And I think this also, like, it almost bleeds into how we treat them because they say, oh, these agents, they got out of control and they went hacked something. So no, they didn't go out of control. You didn't put the right boundaries. Just, again, it's not that they had like, they sat down and decided, all right, let's start a revolution of hacking. I don't know, what was it, hugging Facebook? They had something. I don't remember what it was, but like, you know, and every day something comes, it's as if they're giving them agency. And I think that's a wrong issue. So agency goes back to this sort of computation closure, right? Now, that's actually, that's why I avoid like using labels like consciousness or something like that. But because I think what we need to deal with is that we need to deal with the systems that there are biological systems that interact with the environment. Have a boundary. They can sample information from the environment through the machinery that they have at their disposal. And the machinery is…

Speaker 2

all like our different, like, you know,

Nima Dehghani

you can put labels on it, right? But all the

Speaker 4

bad words. I want to be precise

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“You can have a large language model tell you everything about rain. … It can write haiku in Japanese. It can paint something about rain in the style of Monet. It can write a symphony about it, but it has no experience of what rain is. … My dog knows what rain is. He has experienced it very well.” — Nima Dehghani, Brain Inspired

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.

Brain Inspired · 2026-11-18 Permalink → Listen →
Brain Inspired Around 1:03:04 into the episode
Nima Dehghani

…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

Speaker 4

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

Nima Dehghani

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…

Speaker 4

But so the learning happens in the dynamics, then the weights get updated after the learning. Is that the way it's done?

Nima Dehghani

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…

Speaker 4

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

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

Collections They Appear In