The Good Fight cover image

William MacAskill on Effective Altruism

The Good Fight

00:00

Can We Technically Detect Misalignment and Deceptive Behavior?

William describes promising technical tools like legible chains of thought, interpretability, induced beliefs, and lie-detection analogues.

Play episode from 01:06:30
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