06/26/26: Tracing Introspection Across Model Depth, Zach Maas
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!
Podzilla Summary coming soon
Sign up to get notified when the full AI-powered summary is ready.
Free forever for up to 3 podcasts. No credit card required.
Listen to This Episode
More from Boston Computation Club
An Extremely Short Proof of the Hairy Ball Theorem with Peter McGrath
Logic.py: Bridging the Gap between LLMs and Constraint Solvers with Pascal Kesseli
2/17/26: Approximately Aligned Decoding with Daniel Melcer
02/06/26: Early experiments in FMxAI at Galois with Max von Hippel
Get summaries like this every morning.
Free AI-powered recaps of Boston Computation Club and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.