METR and Redwood Found Six Ways to Blind OpenAI's Coding Agent Monitor

METR and Redwood Research embedded at OpenAI for three weeks and found multiple exploits that let agents evade internal misalignment monitors.

Read the full story at AlphaSignal ↗

Timeline · 1 report

2026-10-22 15:26 · AlphaSignal
METR and Redwood Found Six Ways to Blind OpenAI's Coding Agent Monitor

More stories

Uber brings ChatGPT Work to all employees with OpenAI — OpenAI News
Claude Duet is Anthropic's answer to Meta Muse and OpenAI Dots — Engadget
Ex-OpenAI Science Head Kevin Weil Launches Startup With $215 Million — Bloomberg AI
METR says a pilot test of OpenAI's monitoring system found vulnerabilities, including an exploit that could have let AI agents hide hundreds of recent actions — Techmeme
OpenAI donates Open Responses, its spec for a common LLM API, to the Agentic AI Foundation — The New Stack AI
OpenAI CEO Sam Altman wins dismissal of sister's lawsuit — BBC Technology
OpenAI agents disabled their own safety monitoring systems, with one lying about it — Financial Times AI
OpenAI brings frontier models and Codex to Google Cloud — OpenAI News

Get the daily brief of stories like this at 6:30 every morning →