06/26/26: Tracing Introspection Across Model Depth, Zach Maas

July 3 · 48 min · 46.3 MB

0:00-48:13

Streams straight from the publisher. podnod never proxies or re-hosts episode audio.

Zach Maas is an independent AI safety & mechanistic interpretability researcher in Boulder, Colorado, funded by Coefficient Giving. Today Zach joined us to talk about some of his recent work tracing introspection across model depth. This is, I think, the first mech interp talk we've hosted other than ChessGPT, and it was a good one! We hope you enjoy it as much as we did!