Comment by Dario Amodei

Each frontier AI company commits to giving ongoing, employee-like access to a team of embedded third-party evaluators (such as METR), whose role is to verify adherence to safety practices and commitments, report incidents, and help assess the alignme...

An agreement by both sides to test their models before release for acute risks in areas such as cybersecurity, biology, and alignment.

For example, one possible scheme might be a series of “checkpoints”: if models have capability X, then they need to be accompanied by certifications of alignment properties Y and Z — such as some combination of evaluations, interpretability analyses,...