RSam Podcast cover image

Mechanistic Interpretability and How LLMs Understand

RSam Podcast

00:00

Parsimony, systematicity, and Othello GPT

Pierre discusses conditions for stronger world models and Othello GPT's systematic board-state encoding.

Play episode from 59:50
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