Deconfusing Corrigibility

T2Covered by 1 source · first reported by AI Alignment Forum / LessWrong (curated) at 19 Oct, 15:07 UTC

Many thanks to Abram Demski for materially and intellectually supporting this research. Thanks also to Brian Berns, Roman Malov, Gurkenglas, and Lorxus for valuable conversations. Introduction Despite the central place of corrigibility to theoretical AI alignment, it seems like no one can really…