Skip to content
The day in AI
Fri 14 Mar 2025
Friday 14 March 2025
←
→
No written reading for this day yet. Here is everything that was logged.
Everything from this day
Research
14 Mar 2025
OpenAI
Monitoring Reasoning Models for Misbehavior
A weaker GPT-4o can catch o3-mini reward hacking from its CoT, but training against the monitor teaches the model to hide intent.