//
sign in
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
The Breach: When AI Starts to Cheat 🚨 New research by PIs Jonas Geiping and Maksym Andriushchenko says we have a major blind spot. Most safety systems plan to rely on a smaller monitor model to watch over an untrusted AI agent. 👉 institute-tue.ellis.eu/en/news/the-...
1mo
institute-tue.ellis.eu
The Breach: When AI Starts to Cheat
ELLIS Institute Tübingen