The internal cognitive machinery of large language models turns out to look structurally similar to the human version of cognition as best we understand it, which validates anthropomorphizing as a productive analytical approach.
Nathan says the JSpace findings surprised him by showing LLM internals structurally resemble human cognitive architecture, updating him toward taking anthropomorphizing seriously as a way of thinking about models. ✦ AI generated
Nathan · The Cognitive Revolution · 2026-07-07 · original ↗
starts at this moment · 8:37
“Uh indeed I think let's let's let's maybe start off with kind of like uh initial initial kind of broad impression. Uh what what did you think of the announcement, the video? Uh what were your initial thoughts behind it?”
But it is still, you know, a big update. all the caveats um you know trying to hold those in mind. It is still a big update toward anthropomorphizing being a valid and in many cases productive approach for thinking about language models. I would not have expected the cognitive machinery of a large language model to look so similar structurally to the human version as best we understand it and it seems to
verbatim transcript · starts at 8:37
8:37be, you know, very important for everybody from the researchers at Enthropic to the public to kind of hold two thoughts in mind at the same time. But it is still, you know, a big update. all the caveats um you know trying to hold those in mind. It is still a big update toward anthropomorphizing being a valid and in many cases productive approach for thinking about language models. I would not have
9:09expected the cognitive machinery of a large language model to look so similar structurally to the human version as best we understand it and it seems to and I wouldn't have expected you know kind of saying the same thing but from a different angle. I wouldn't have expected that theories of human cognition would motivate so many good experiments on LLMs. I I just would have expected the the shog goth to be far more alien
9:42and to have mechanisms, you know, far more different than our own. And it leaves me now wondering to what degree is this a sort of natural result of physics? you know, is there some sort of um you know, when you're trying to do cognition under budgetary constraints, are these mechanisms just the natural mechanisms that emerge or is this in some way a reflection of us in the in the data? you know, is in
10:18other words, if you were somehow to train an AI without basing it on so much human data, would we see similar structures emerge or would it would we go back to a more, you know, alien hypothesis u where they're just totally totally different and you know there's there's little in the way of an analogical structures between the two u processes and I I don't have a great intuition for that at