mic comments on OpenAI’s CBRN tests seem unclear

[mic]

Great piece overall! I’m hoping AI risk assessment and management processes can be improved.

Anthropic found that Claude 3 didn’t trigger AI Safety Level 3 for CBRN, but gave it a 30% chance of doing so in three months

30% chance of crossing the Yellow Line threshold (which requires building harder evals), not ASL-3 threshold

[Luca Righetti 🔸]

Thanks for the spot! Have fixed