Rao talks 'mythos of thinking traces' at Max Planck Tübingen, slides and audio public
rao2z · x · 2026-10-09
Prominent AI commentator rao2z gave a talk on the 'mythos of thinking traces' at the Max Planck Institute for Intelligent Systems in Tübingen, hosted by Jonas Geiping.
- Slides and audio are publicly shared
- The author believes talks are best heard rather than summarized, but released a TLDR summary generated from the transcript with Fable for quick reference
A substantive long-form take on chain-of-thought and reasoning traces, relevant to anyone interested in reasoning interpretability.
Related event: rao2z lectures at MPI Tübingen on the myth of thinking traces(2 posts)→
More from AGI Musings
- Scale CEO Alexandr Wang on AI safety: what can Muse do and when can we trust it — alexandr_wang · 2026-10-10
- SubDGuide: modeler-inspired agentic workflow for mesh-to-SubD reconstruction — ssh4net · 2026-10-10
- MIT paper: AGI's binding constraint is human verification bandwidth, not intelligence — Afinetheorem · 2026-10-10
- AI community clashes over OpenAI math proofs: 'nobody needs anyone's permission to do research' — ludwigABAP · 2026-10-10
- Jay Kreps predicts humans won't be needed for math in 3 years; peers push back — JosephJacks_ · 2026-10-10
- "Solving it kills the grants": AI in math rekindles academia critique — _AustinCalvert_ · 2026-10-10