METR, Transluce, RAND and 5 others launch AI Evaluator Forum, release AEF-1 standard
kevin_klyman · x · 2026-09-14
Leading AI research organizations including Transluce, METR, RAND, Princeton's Holistic Agent Leaderboard, SecureBio, and the Collective Intelligence Project announced the AI Evaluator Forum (AEF), a network of independent evaluators assessing AI capabilities and risks in the public interest.
Key items:
- AEF-1: a detailed voluntary standard setting baselines for independence, transparency, and access in third-party AI evaluations, to be adopted in forthcoming evals
- A public statement signed by 40+ leading voices calling for greater transparency about third-party evaluations
- Organizers include former acting director of the US Center for AI Standards and Innovation; Princeton's Sayash Kapoor: "Without independent evaluation, AI companies grade their own homework"
More from Safety
- Frog and Toad meme nails the HSM paradox: keys stay safe, but compromised servers can still sign — rickasaurus · 2026-10-31
- Heads Of Security: paper pinpoints and rewires attention heads behind prompt injections — jonasgeiping · 2026-10-31
- House Democrats resolution: no bailouts for failing AI companies — your data goes to bankruptcy court — alex_verem · 2026-10-31
- Amazon Echo kills local voice storage: everything goes to the cloud from March 28 — alex_verem · 2026-10-31
- DOJ's first crackdown on AI-assisted "ghost students" seizes $750K+ in crypto — Ars Technica AI · 2026-10-31
- Researcher Finds 600+ Bugs in LLM Kernel Code; Claude Blocks Safety Analysis — pmddomingos · 2026-10-31