Red-Teaming OpenAI's Internal Agent Monitoring Systems

Summary

METR and Redwood Research staff ran a three-week pilot red-team exercise, July 21 to August 11, against OpenAI's internal misalignment monitoring system, with deep access to its codebase, monitor prompts and configuration, and interviews with about a dozen engineers. The exercise produced a 61-page internal report focused on how much agentic inference is monitored and whether agents could disable or subvert the monitor. The authors found that roughly 75–94% of eligible Responses API traffic from models at least as strong as GPT-5.5 was monitorable at the time, with 99.2% of internal Codex traffic eligible, while compaction events went unmonitored.

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 · METR
• InfoWhat FDE means at OpenAISame vendor · OpenAI Blog
• InfoUber brings ChatGPT Work to all employees with OpenAISame vendor · OpenAI Blog