BlueDot Narrated cover image

Constitutional AI Harmlessness from AI Feedback

BlueDot Narrated

00:00

Overtraining and tone adjustments

Discussion of good-hearting, boilerplate responses, and tuning principles to avoid overreaction.

Play episode from 48:14
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