Anthropomorphizing large language models has proven to be a valid and productive framework, contrary to the prior caution against it.
Nathan says his old instinct to warn against anthropomorphizing AI models has been significantly undercut by results like this paper, which show LLM cognition is structurally more human-like than expected. ✦ AI generated
Nathan · The Cognitive Revolution · 2026-07-07 · original ↗
starts at this moment · 6:56
“Uh what what did you think of the announcement, the video? Uh what were your initial thoughts behind it?”
I used to say beware overly anthropomorphizing. You know, remember that these are these things are so alien and uh we shouldn't assume that the way that we work is the way that they work. And I have to say that has come due for some significant revision. People that have embraced anthropomorphizing, I think, have got quite a lot of mileage out of it.
verbatim transcript · starts at 6:56
6:56>> The video is beautiful. I I enjoyed the video quite a bit. Um you know, it set off my alarm bells a little bit in terms of how much they're really embracing anthropomorphizing the models at this point. I used to say beware overly anthropomorphizing. You know, remember that these are these things are so alien and uh we shouldn't assume that the way that we work is the
7:26way that they work. And I have to say that has come due for some significant revision. People that have embraced anthropomorphizing, I think, have got quite a lot of mileage out of it. I do still think it's obviously something to be really careful about and as much depth and detail as there is in this research. It's like easy to, you know, maybe get carried away with it
7:52and forget, you know, that there are a lot of caveats as well and there's a lot of things where like it doesn't always work. This was kind of my big concern with the tracing large language model thoughts paper. there's just like a lot of residuals and there's a lot of error correction terms along the way that they use to make that thing work. And when you have the kind of
8:13zoomed out trace view and you're like, "Oh, okay. So, this is how it works." Like this, you know, gets loaded in and these two features interact and they, you know, kick out this third feature and that's how we get our answer. it's easy to forget just how much kind of fuzziness and not, you know, full story there was along the way toward that stylized account. Um, so I think it's going to
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