This seems like a misunderstanding of “overseer”-type proposals. ~Nobody thinks alignment is impossible; the rejection is the idea of using unaligned AGIs (or aligned-because-they’re-insufficiently-powerful AGIs) to reliably “contain” another unaligned AGI.
This seems like a misunderstanding of “overseer”-type proposals. ~Nobody thinks alignment is impossible; the rejection is the idea of using unaligned AGIs (or aligned-because-they’re-insufficiently-powerful AGIs) to reliably “contain” another unaligned AGI.