LessWrong (30+ Karma) cover image

The Enemy Gets The Last Hit

LessWrong (30+ Karma)

00:00

Fix-Then-Fail Pattern in AI Safety

Host critiques papers that find problems and patch them without adversarial stress-testing in AI safety.

Play episode from 02:14
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