LessWrong (Curated & Popular) cover image

[HUMAN VOICE] "How useful is mechanistic interpretability?" by ryan_greenblatt, Neel Nanda, Buck, habryka

LessWrong (Curated & Popular)

00:00

Introduction

A discussion on the current and future usefulness of mechanistic interpretability and the potential for achieving useful outcomes through mech-interb projects.

Transcript
Play full episode

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