The limits of black-box evaluations: two hypotheticals
A prominent approach to AI safety goes under the name of "evals" or "evaluations". These are a critical component of plans that various major labs have, such as Anthropic&
Identifiability
Is Agency Identifiable?
Identifiability in IRL
One of my favorite papers is this one, titled "Occam's razor is insufficient to infer the preferences of irrational agents". It relates to an area of