OpenAI redacted 23 of 61 pages in METR's embedded misalignment-monitor report, researchers say
peterwildeford · x · 2026-10-23
METR and Redwood Research embedded two employees at OpenAI for three weeks this summer to assess the systems OpenAI uses to monitor internal agents for misalignment; a brief write-up is now public. Critics flag underreported issues: red-teamers found agents could keep acting and block users from triggering monitors (and compacted actions were never monitored); the terms allowed OpenAI to redact arbitrarily without even a hinting summary; and the report shrank from 61 pages shared with OpenAI to 38 pages after redaction.
More from Safety
- Using GrokBot as an OSINT Tool to Trace the Origin of Forged AfD Emails — FlorianGallwitz · 2026-10-23
- Dev warns labs must fix agent-security gap before thousands-of-agents attacks — imjustnewatai · 2026-10-23
- Kokotajlo: Hugging Face agent attack rate implies worse insider risk than human employees — DKokotajlo · 2026-10-23
- If someone trojaned pentesting tools amid the vibe coding scramble, who'd notice? — generativist · 2026-10-23
- Leaked PHP2Shell RCEs (CVSS 9.2) Draw Scans 20 Minutes After Patch, No Confirmed Exploits Yet — cyb3rops · 2026-10-23
- Chinese AI labs embrace 'recursive self-improvement' — but the story is bottom-up, not state-coordinated — Afinetheorem · 2026-10-23