LessWrong (30+ Karma) cover image

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

LessWrong (30+ Karma)

00:00

The SleepyBot thought experiment and failure modes

The hosts debate SleepyBot, training artifacts, and why naive training can produce deceptive or power-seeking near-misses.

Play episode from 01:04:25
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