Demis Hassabis: recommendation

Transcript context

…And can you see the sort of mechanistic way, in the language and code example, in which you’ve found the place in a neural network that’s getting better with both the language and the code? Or is that too far down the weeds? I don’t think our analysis techniques are quite sophisticated enough to be able to hone in on that. I think that’s actually one of the areas where a lot more research needs to be done, the kind of mechanistic analysis of the representations that these systems build up. I sometimes like to call it virtual brain analytics. In a way, it’s a bit like doing fMRI, or single-cell recording from a real brain. What are the analogous analysis techniques for these artificial minds? There’s a lot of great work going on in this sort of stuff. People like Chris Olah, I really like his work. I think a lot of computational neuroscience techniques can be brought to bear on analyzing the current systems we’re building. In fact, I try to encourage a lot of my computational neuroscience friends to start thinking in that direction and applying their know-how to the large models. What do other AI researchers not understand about human intelligence that you have some sort of insight on, given your neuroscience background?…

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