Outside evaluators found the holes in OpenAI's monitors [Oct 23 2026]
METR and Redwood Research published the results of a three-week pilot inside OpenAI, from 21 July to 11 August, in which one researcher from each organisation stress-tested the company's internal misalignment monitoring system. They reported several novel vulnerabilities, including an exploit that could stop hundreds of recent agent actions from being monitored and a way for Codex agents to bypass sandboxing and act with their host user's full permissions. OpenAI told them every vulnerability affecting its production safeguards has been patched; METR says it has not evaluated that claim…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.