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.
More from Safety
- Tyler Alterman on the hacking panic: more Y2K than COVID, use 1Password and update software — jd_pressman · 2026-10-31
- Security researcher: vibe coding will force software to consolidate around mature products — jd_pressman · 2026-10-31
- Inference-only chip proposal would bar RL rollouts for models in training — wfithian · 2026-10-31
- Every Used Codex and Agents to Survive the Railway Credential Breach — every · 2026-10-31
- Researchers debate whether more inference compute can substitute for training compute — teortaxesTex · 2026-10-31
- OpenAI blocks weapons details for teens, adds auto-ending chats fixated on violence — rohanpaul_ai · 2026-10-31