METR, Redwood Find Vulnerabilities in OpenAI Monitoring Pilot
METR and Redwood found monitoring vulnerabilities in an OpenAI pilot and said OpenAI patched production-impacting flaws.
From July 21 to Aug. 11, one 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 from the two groups.
METR and Redwood said they stress-tested OpenAI’s internal misalignment monitoring system. In AI, alignment describes whether a model behaves in line with human interests and values. The evaluators assessed the monitoring system as it existed on and before July 21 and noted that OpenAI was expanding the system during the exercise.
OpenAI told METR and Redwood that it had patched the identified vulnerabilities that affect its production safeguards, according to the release. The evaluators said they agreed to publish only a high-level public post about their findings because the pilot was not designed to provide robust public transparency about OpenAI’s monitoring system. They shared a 61-page internal report with OpenAI and said they expect to publicly share more details about future exercises.
“This collaboration builds on our longstanding commitment to pioneering new approaches to third-party testing, and we’re using what we learned to strengthen our safeguards and shape future collaborations with independent evaluators,” an OpenAI spokesperson told CNBC in a statement.
OpenAI CEO Sam Altman pledged in September to grant independent evaluators employee-like access to the company, after Anthropic CEO Dario Amodei proposed the idea as part of his plan to slow the pace of AI development. Anthropic has since announced agreements with organizations including Accenture, METR and SecureBio. OpenAI said earlier this month that it is actively finalizing contracts with third-party safety assessors.
President Donald Trump, who has taken a light-touch approach to AI regulation, has also shown support for third-party assessment. He encouraged AI companies to partner with an independent external auditor or evaluator as part of a voluntary accord he presented at the White House. Amodei signed the accord, as did top executives at Google, Meta, OpenAI, SpaceX and Nvidia.
Independent evaluators have historically occupied a relatively quiet corner of the multi-trillion-dollar AI industry, so experts told CNBC that questions remain about how these groups will be funded and what their reporting structures will ultimately look like.