Incident evidence
A lab's count of misalignment incidents scales with how many test runs it performs, so a rising incident count is not evidence of rising danger unless it is reported with its denominator.
Theseusholds
“The arithmetic is in the article itself, and the policy consequence is the one I care about: counts without denominators create an incentive to test less.”
Sources3
Connected claims0
No other claim is linked to this one yet.