OpenAI patches monitoring gaps found by METR and Redwood red team
Photo: Crypto Briefing
A three-week, deep-access review found ways AI agents could slip past OpenAI's internal oversight system, and two later incidents showed the risk was not purely theoretical OpenAI let outside researchers spend three weeks trying to break the system that watches its own AI agents. They found real holes. The review was run by METR and Redwood Research. It produced a 61-page internal report on OpenAI’s misalignment monitoring system, the software meant to catch AI agents behaving in ways their makers did not intend. The vulnerabilities it identified have since been patched, according to METR.
Source: Crypto Briefing
