METR shouldn't be the sole AI evaluator, experts list a whole ecosystem of alternatives

RebeccaBellan · x · 2026-09-13

Dean Ball argues METR is excellent but nowhere near sufficient on its own — the field needs a diverse, large ecosystem of technically skilled independent assessment bodies, and METR shouldn't be anointed the sole evaluator. A widely shared reply lists the existing ecosystem: Apollo Research/Redwood Research, FAR.AI, Palisade Research, SecureBio, SaferAI, plus the UK AI Security Institute, the U.S. Center for AI Standards and Innovation, and Japan's AI Safety Institute. Others respond positively to METR gaining more access but worry about an evaluator monoculture.

Related event: Dean Ball: METR is great but insufficient; AI evaluation needs a diverse ecosystem(4 posts)→

Original post →

More from Safety

Safety channel →