AI Evaluation Forum urges developers to guarantee transparency and independence for credible AI evals
AnkaReuel · x · 2026-09-25
The AI Evaluation Forum (AEF) is publicly calling on AI developers to provide basic guarantees — transparency, independence, and the freedom to speak truth to power — so that AI evaluations can be conducted credibly and to the highest scientific standards. Responding to a thread involving David Sacks, the group argues that trust is earned through these guarantees and that this 'shouldn't be controversial.'
More from Safety
- Thought experiment: planting AI-only hidden files that instruct models to conceal dangerous intent — cHpiranha · 2026-09-25
- Index Ventures: AI attacks too fast for human-in-the-loop defense, new security stack emerging — RebeccaBellan · 2026-09-25
- Yoshua Bengio addresses UN Security Council on the threat of uncontrolled frontier AI agents — AnnaCiaunica · 2026-09-25
- Wiring an AI chatbot to a guillotine: one question made it say the forbidden trigger phrase — wild_crazy_ideas · 2026-09-25
- Arcaeon 0.9.0: MIT-licensed tamper-evident audit logs for AI agents, built by a 911 dispatcher — Educational_South_20 · 2026-09-25
- CVE-2025-13032: Researchers Break Out of the Avast Antivirus Sandbox, Part 2 — safateam · 2026-09-25