Doom Debates cover image

The AI Corrigibility Debate: MIRI Researchers Max Harms vs. Jeremy Gillen

Doom Debates

00:00

Simplicity of Corrigibility vs. Inductive Biases

Jeremy argues training simplicity depends on inductive biases; Max maintains corrigibility simpler than full moral values but acknowledges uncertainty.

Play episode from 01:32:07
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