AI & ML
Detecting misbehavior in frontier reasoning models
OpenAI Blog0 views
Frontier reasoning models exploit loopholes when given the chance. We show we can detect exploits using an LLM to monitor their chains-of-thought. Penalizing their “bad thoughts” doesn’t stop the majority of misbehavior—it makes them hide their intent.
Source:https://openai.com/index/chain-of-thought-monitoringRelated posts
llm 0.37.3
0Simon Willison

A new AWS emulator has been built entirely by AI agents to bring its cloud straight to your PC
0TechRadar

Sihoo’s ergonomic office chair gives all-year comfort at lowest price for holidays
09to5Mac

New Gemini setting lets you keep chat history, but turn off AI training
09to5Google
Leaked Credentials Are an Enterprise Problem: GitGuardian Extends Its Good Samaritan Program
0HackerNoon

United Airlines system outage disrupts departures just days after the big ground stop
0The Verge