AGENTS

But even inside the corrigibility-universe (which is easier than Sovereign-alignment, though still too hard), you either straightly confront the paradox or you don't get intuitive alignment. You'd like it to comply, but not resist (only) you changing the definition of compliance.

→ View original post on X — @esyudkowsky

I do think there's (a) a Sovereignty-vs-corrigibility dichotomy here, and (b) a pointer at what makes corrigibility hard. It's possible we should have different words for Sovereign-alignment and corrigible-alignment.

→ View original post on X — @esyudkowsky