In a companion piece, we explain our approach to working with AI developers in exercises like these. Our goal is to get the public accurate, timely, and independent evidence so that they can make their own informed decisions.

Show Post

Our proposed exercises would provide evidence, not confident safety assurance or formal oversight. We also encourage developers to work with other external groups to complement these efforts, and to unilaterally share evidence with the public.

Show Post

This proposal is our recommendation for how we could give the public visibility into risks occurring within AI development. We stand ready to conduct all three of our proposed exercises with frontier AI developers.

Show Post

(3) AI R&D acceleration If AI automates AI R&D, capability growth could outpace what alignment and control methods can handle. Our proposal is to analyze how much AI automation is accelerating capability growth internally. metr.org/blog/2026-10...

Show Post

(2) Control Agents that attempt harmful or unwanted actions are not always noticed. Our proposal is to analyze whether a developer’s internal agents could get away with serious harm without being caught. metr.org/blog/2026-10...

Show Post