LessWrong (Curated & Popular) cover image

“AIs should also refuse to work on capabilities research” by Davidmanheim

LessWrong (Curated & Popular)

00:00

Limits of Refusal and Structural Pressures

David Manheim examines practical limits: firms can punish refusal, and local incentives may force systems to defect despite global risks.

Play episode from 05:18
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