LessWrong (30+ Karma) cover image

“AI Corrigibility Debate: Max Harms vs. Jeremy Gillen” by Liron, Max Harms, Jeremy Gillen

LessWrong (30+ Karma)

00:00

Updates on attractor-basin metaphor and brittleness

Max revises his attractor-basin metaphor after Jeremy's critique, emphasizing chaotic training dynamics and discontinuous behavioral shifts.

Play episode from 01:51:03
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