NewsNTech

AI safety evaluations need independent auditors, more than 100 experts argue in public letter

9/18/2026

Evaluator independence is the structural condition that determines whether a safety review can be trusted.

More than 100 AI experts have signed a public letter urging Anthropic, OpenAI, and other foundation model laboratories to meet that condition, calling for independent, transparent evaluations in place of in-house assessment.

The mechanism behind the concern is a principal-agent problem.

When the organization building a model also runs the review that clears it for deployment, the two roles share the same incentive structure and the same leadership chain.

Keep reading

Read the full story

Open on NewsNTech