RSam Podcast cover image

Mechanistic Interpretability and How LLMs Understand

RSam Podcast

00:00

Teaser: function-first epistemology paper

Pierre previews third paper tying mechanistic indicators and CPC to define conditions to trust and learn from LLMs.

Play episode from 01:39:23
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app