Bach blames human cognitive limits; Hendrycks advocates human-AI mutualism.
Good AI alignment is necessarily EA adjacent. But EA failed to derive a global morality, not for lack of good intentions or intelligence, but because human rationality is a brittle tool, even if you are a good rationalist, and most people prefer to either muddle through or to consult prophets and leaders. Obviously that won't suffice for powerful AI.
@Plinz Good alignment needs to be life-affirming not just hedon-per-flop affirming
What happens when AIs become smarter than us? Why would they keep humans around if given the choice?
Our new paper argues that only trying to control AIs is a limited strategy, and that a stable, mutualistic human-AI future may be possible.
Bach blames human cognitive limits; Hendrycks advocates human-AI mutualism.
Good AI alignment is necessarily EA adjacent. But EA failed to derive a global morality, not for lack of good intentions or intelligence, but because human rationality is a brittle tool, even if you are a good rationalist, and most people prefer to either muddle through or to consult prophets and leaders. Obviously that won't suffice for powerful AI.
Many users dismissed EA principles for AI alignment as misguided and insufficient, arguing they rely on weak positions, ignore altruism, and bear little relation to real work like RLHF.