AI alignment open problem

A tag for pages that de­scribe at least one ma­jor open prob­lem that has been iden­ti­fied within the the­ory of value-al­igned ad­vanced agents, pow­er­ful ar­tifi­cial minds such that the effect of run­ning them is good /​ nice /​ nor­ma­tively pos­i­tive (‘high value’).

To qual­ify as an ‘open prob­lem’ for this tag, the prob­lem should be rel­a­tively crisply stated, un­solved, and con­sid­ered im­por­tant.

Parents:

  • AI alignment

    The great civ­i­liza­tional prob­lem of cre­at­ing ar­tifi­cially in­tel­li­gent com­puter sys­tems such that run­ning them is a good idea.