I’m just curious, why the specification of math proofs? I know of some modestly promising ideas for aligning the sorts of AGI we’re likely to get, and none of them were originally specified in mathematical terms. Tacking on maths to those wouldn’t really be useful. My impression is that the search for formal proofs of safety have failed and are probably hopeless. It also seems like adding mathematical gloss to ML and psychological concepts is more often confusing than enlightening.
It’s to differentiate from more-obviously-tractable less-formalism/conceptual/deconfusion-based research agendas like i.e. HCH. As asked, I’m looking for info specifically related to this other kind.
I’m just curious, why the specification of math proofs? I know of some modestly promising ideas for aligning the sorts of AGI we’re likely to get, and none of them were originally specified in mathematical terms. Tacking on maths to those wouldn’t really be useful. My impression is that the search for formal proofs of safety have failed and are probably hopeless. It also seems like adding mathematical gloss to ML and psychological concepts is more often confusing than enlightening.
It’s to differentiate from
more-obviously-tractableless-formalism/conceptual/deconfusion-based research agendas like i.e. HCH. As asked, I’m looking for info specifically related to this other kind.