“really dangerous models. And here are some brain scans. I…” — Dwarkesh Podcast at 55:35
“really dangerous models. And here are some brain scans. I think the whole idea of mechanistic interpretability is to look at the underlying principles and circuits. But I guess the way I think about it is like, on one hand, I've actually always been a fan of studying these circuits at the lowest level of detail that…”
0:00
1:58:43