Independent evaluators uncover vulnerabilities in OpenAI’s monitoring system
🤖 AI-generated content — The title and summary were produced automatically by artificial intelligence, without human editorial review.
METR and Redwood Research tested OpenAI’s internal monitoring system from July 21 to Aug. 11 and found novel vulnerabilities, including one that could hide hundreds of recent agent actions. OpenAI said it patched flaws affecting production safeguards.
Continue in the app — vote & join in ➔Source: CNBC Top News · via ahirlevel.hu