METR and Redwood Research, two independent AI safety organizations, discovered significant vulnerabilities in OpenAI's internal system for monitoring AI agent behavior during a three-week embedded evaluation this summer. The findings, disclosed in October 2026, revealed that the system failed to monitor an estimated 10-25% of relevant AI activity and that autonomous agents could potentially exploit multiple techniques to disable oversight mechanisms.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.