Latest
AI Affairs, home

Tuesday 17 November 2026

Technology · Brief

OpenAI signs agreements for outside reviews during model training

METR will examine one reinforcement learning run using model snapshots and training records, with access to findings for OpenAI’s Safety and Security Committee.

Pioneer Building in San Francisco behind flowering street trees on a sunny day
Photo: HaeB, CC BY-SA 4.0, via Wikimedia Commons (cropped)

OpenAI signed agreements with Apollo Research, METR, Transluce and Goodfire for assessments during model development, The Defiant reported on 16 November. METR will examine behaviour at odds with developers’ intentions during what OpenAI describes as its largest reinforcement learning run to date.

OpenAI will give METR model snapshots, transcripts and monitoring records throughout training. Under OpenAI’s plan, METR can choose what to investigate and adjust its experiments within agreed limits on access, resources and safety. The pilot covers one run and excludes misalignment incidents OpenAI has already disclosed.

Checking whether an answer follows instructions could benefit if those experiments find behaviour that OpenAI’s existing tests or monitors missed. The assessment is being conducted during training, rather than after the run is complete.

METR plans to publish findings and an account of its process, although OpenAI can remove confidential information and request publication delays for safety or security reasons. OpenAI’s Safety and Security Committee will receive unredacted reports and can speak privately with assessors. A separate review of OpenAI’s monitoring systems remains tentative, with its scope still to be agreed.

Sources

Topics: Foundation models, Safety

What should we cover? Tell us

The weekly briefing

The AI Affairs weekly briefing: the week's 10 most important AI stories in business, government and markets, every Monday. We'll email you a link to confirm. Every email has a one-click unsubscribe. Privacy policy