Episode

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

Podcast: Boston Computation Club
Published: Jul 3, 2026
Duration seconds: 2893
Processing state: not_requested
Canonical source: https://podcasters.spotify.com/pod/show/bostoncc/episodes/062626-Tracing-Introspection-Across-Model-Depth--Zach-Maas-e3lkb4p
Audio: https://anchor.fm/s/5eee01ac/podcast/play/122350169/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-6-3%2F427308718-44100-2-2904251f4c717.mp3
JSON: /v1/public/podcasts/boston-computation-club-4031660/episodes/06-26-26-tracing-introspection-across-model-depth-zach-maas
Markdown: /podcast/boston-computation-club-4031660/06-26-26-tracing-introspection-across-model-depth-zach-maas.md

Actions

POST https://stenobird.com/v1/public/podcasts/boston-computation-club-4031660/episodes/06-26-26-tracing-introspection-across-model-depth-zach-maas/transcription-requests
Idempotently request low-priority transcript generation for this episode.
GET https://stenobird.com/podcast/boston-computation-club-4031660/06-26-26-tracing-introspection-across-model-depth-zach-maas.md
Read the agent-friendly Markdown representation of this episode resource.

Summary

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!