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.'

Original post →

More from Safety

Safety channel →