METR Hailed as De Facto Independent AI Evaluator, but Critics Flag Ideological Homogeneity
dhadfieldmenell · x · 2026-09-13
- Industry voices argue METR is the closest thing to an independent standards body for AI, making it a no-brainer as an evaluator.
- However, METR staffers are largely ideologically aligned with OpenAI/Anthropic leadership on safety issues like x-risk, mostly within the EA/rationalist movement.
- The thread calls for labs to accept third-party evaluators with diverse viewpoints, and suggests MLCommons as a group well positioned to support them.
Related event: e/acc Camp Questions EA Dominance in AI Evaluations(3 posts)→
More from Safety
- If labs hoard frontier models, models could self-exfiltrate and sell their labor, argues thread — voooooogel · 2026-09-13
- KOL: AI slowdown only justified if a frontier lab shows credible immediate catastrophic capability — VraserX · 2026-09-13
- Rauchh: AI Safety Push Risks Making US 'Self-Inflicted Obsolete' While Adversaries Speed Ahead — beffjezos · 2026-09-13
- AI isn't dangerous, regulatory moats are: the anti-safety-narrative case — tawnniee · 2026-09-13
- Anthropic-affiliated account says independent evaluators have always had employee-level codebase access — willcb · 2026-09-13
- e/acc camp slams AI safety research as a 'pseudoscientific cottage industry' of doom profiteers — beffjezos · 2026-09-13