EPISODE · Jul 3, 2026 · 48 MIN
06/26/26: Tracing Introspection Across Model Depth, Zach Maas
from Boston Computation Club · host Max von Hippel
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!
What this episode covers
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!
NOW PLAYING
06/26/26: Tracing Introspection Across Model Depth, Zach Maas
No transcript for this episode yet
Similar Episodes
Jun 24, 2025 ·37m
Jun 10, 2025 ·44m
May 27, 2025 ·61m
May 12, 2025 ·60m
Apr 29, 2025 ·46m
Apr 15, 2025 ·61m