Nayebi, 2025 — Core Safety Values for Provably Corrigible Agents
Lexicographic utility-head formalism for provably corrigible off-switch behavior.
Publication links
Lexicographic utility-head formalism for provably corrigible off-switch behavior.
Lexicographic utility-head formalism for provably corrigible off-switch behavior.
Lexicographic utility-head formalism for provably corrigible off-switch behavior.