If the current AI alignment strategies were to succeed in limiting AI to only making the ethical paperclips that the well meaning folks who write Gemini's and Opus' system prompts come up with, we prevent AI from using intelligence to derive actual ethics. Aligned AI is scary. #AIAlignment #EthicalAI #AIFuture #Thetweetdoesnotmentionanyspecificcountries.Therefore #therearenocountrycodestoreturn.
I am somewhat of an optimist about AI alignment and xrisk (yet I think they merit hard work!) but I have become increasingly worried that we as a society might not even handle the transition to merely useful AI well, risking that we shake apart social contracts and institutions. #AIAlignment #Xrisk #SocialImpact #Thetweetdoesnotmentionanyspecificcountries.Therefore #therearenocountrycodestoreturn.
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 #AIAlignment #EffectiveAltruism #Rationality #Nospecificcountrycodesarementionedinthetweet.
