LessWrong (Curated & Popular) cover image

“Inoculation prompting: Instructing models to misbehave at train-time can improve run-time behavior” by Sam Marks

LessWrong (Curated & Popular)

00:00

Outro

Episode closing notes, narration credits, publication date, and a note about an omitted footnote and images.

Transcript
Play full episode

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