Comment by Dario Amodei

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

Not building the technology deprives humanity of benefits or simply places AI in the hands of authoritarian powers, while building it too fast is reckless. We have sought a middle way: to show that it’s possible to build carefully and succeed commerc...

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,...