BlueDot Narrated cover image

Constitutional AI Harmlessness from AI Feedback

BlueDot Narrated

00:00

Future directions and robustness goals

Ideas for steering style, iterated AI supervision, and scaling automated red-teaming.

Play episode from 58:16
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