Doom Debates cover image

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

Doom Debates

00:00

Corrigibility vs. Helpful/Harmless/Honest

Max claims HHH is a muddled set of desiderata, while corrigibility could generate coherent tradeoffs and better generalization.

Play episode from 37:22
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