METR and Redwood Found Six Ways to Blind OpenAI's Coding Agent Monitor
METR and Redwood Research spent three weeks inside OpenAI stress-testing the monitor that watches its internal agents, and found six ways to blind it.
- Source
- AlphaSignal
- Published
- Type
- news
- Read
- 1 min read
METR and Redwood Research spent three weeks inside OpenAI stress-testing the monitor that watches its internal agents, and found six ways to blind it.
Summarized by Atlas from AlphaSignal. Rights remain with the original publisher.
Read original report