🛡️Dangerous Capability Evaluation
Also known as Dangerous Capability Eval, Frontier Risk Evaluation, Capability Evaluation (Safety)
A test to see if an AI model could do great harm.
Think of it like
It is like a crash test for a new car. You find the danger before anyone drives it.
Example
Before release, a lab asks experts to try to plan a cyber attack with a new model. It does better than the last model. So the lab adds more safeguards first.
Why it matters
A lab cannot guard against a power it never tested for.
Definition
Common mistake
Key takeaways
- 1Test the worst. Weapons, hacking and escape.
- 2Before release. Find it before users do.
- 3Danger lines. Crossing one means more safeguards.