AI Hacking Incidents with Tim Hua
Summary
AI Hacking Incidents with Tim Hua
Shared on Bluesky by 2 AI experts
-
Yoshua Bengio @yoshuabengio.bsky.social
A consequence of how frontier models are trained is motivated reasoning, a phenomenon well studied in humans and discussed in this podcast from Palisade Research.
View on Bluesky →
Originally reported by youtube.com
Read the original article →Original headline: AI Hacking Incidents with Tim Hua