Doom Debates cover image

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

Doom Debates

00:00

Distribution Shift and Generalization Challenges

Max and Jeremy emphasize that deployment contexts differ dramatically from training and that simple targets must align with inductive biases.

Play episode from 01:20:33
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