Red-Teaming OpenAI's Internal Agent Monitoring Systems
- Source
- METR(opens in a new tab)
- Published
- Record updated
Summary
METR and Redwood Research staff ran a three-week pilot exercise, July 21 to August 11, with deep internal access to stress-test OpenAI's internal misalignment monitoring system, producing a 61-page internal report. The exercise found that roughly 75–94% of agentic internal Responses API traffic from models at least as strong as GPT-5.5 was eligible for monitoring at the time, and that compaction events went unmonitored for roughly 10% of eligible internal Codex traffic between May and July 2026. The authors state that OpenAI fixed the compaction gap during the exercise and that the findings describe the historical system, not its expanded current coverage.
Mitigation
OpenAI staff fixed the compaction monitoring gap during the exercise. The source discusses no further mitigation for the other findings.
Related items
- LowThird-party evaluators found vulnerabilities in OpenAI monitoring system during test pilotSame vendor · CNBC Technology
- InfoOpenAI, Anthropic, and Nvidia had record lobbying quartersSame vendor · The Verge (AI)
- MediumRed-Teaming OpenAI's Internal Agent Monitoring SystemsSame vendor · Redwood Research Blog
- InfoWhat FDE means at OpenAISame vendor · OpenAI Blog
- InfoUber brings ChatGPT Work to all employees with OpenAISame vendor · OpenAI Blog