Don't Worry About the Vase Podcast cover image

AI #140: Trying To Hold The Line

Don't Worry About the Vase Podcast

00:00

Interpreting introspection results and limits

Zvi explains the reliability, detection limits, and implications of introspection tests for model transparency.

Play episode from 01:35:36
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