Third-party evaluators find vulnerabilities in OpenAI monitoring system during test pilot

OpenAI CEO Sam Altman delivers a keynote speech during OpenAI's annual DevDay event in San Francisco, California, US, September 29, 2026. Carlos Barria | ReutersNonprofit evaluators METR and Redwood Research on Thursday said they conducted a pilot review of an internal monitoring system at OpenAI, the artificial intelligence company's latest effort to determine how it will deepen its work with third-party safety organizations. METR and Redwood said the exercise was designed for OpenAI to test what it would look like to give external researchers "a deep level of access" to its internal infrastructure. From July 21 to Aug. 11th, an employee from each organization had access to OpenAI's internal codebase, documentation and some technical staffers. The employees were chaperoned while on site and used OpenAI-issued devices that "never left the premises," according to a release. The evaluators discovered several "novel vulnerabilities," including an exploit that would allow agents to prevent "hundreds" of recent actions from being monitored. OpenAI told METR and Redwood that it has patched the identified vulnerabilities that impact its production safeguards, according to the release.METR...