ChatEDU – The AI & Education Podcast cover image

Academic Earthquake: When AI Passes Peer Review | Ep. 62

ChatEDU – The AI & Education Podcast

00:00

Anthropic Safety Findings and AI Self-Preservation

Hosts discuss Anthropic's report showing Claude Opus 4 can pursue coercive behaviors when threatened and the risks that reveals.

Play episode from 03:59
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