David Gerard@awful.systemsM to SneerClub@awful.systemsEnglish · 2 months agowhat if, right, what if our super-duper-autocomplete was just tricking us so it could TAKE OVER ZEE VORLD AHAHAHAHAHAHA! that'd be wild, heywww.lesswrong.comexternal-linkmessage-square32fedilinkarrow-up140arrow-down10
arrow-up140arrow-down1external-linkwhat if, right, what if our super-duper-autocomplete was just tricking us so it could TAKE OVER ZEE VORLD AHAHAHAHAHAHA! that'd be wild, heywww.lesswrong.comDavid Gerard@awful.systemsM to SneerClub@awful.systemsEnglish · 2 months agomessage-square32fedilink
minus-squareFermiEstimate@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up30·2 months ago I conclude that scheming is a disturbingly plausible outcome of using baseline machine learning methods to train goal-directed AIs sophisticated enough to scheme (my subjective probability on such an outcome, given these conditions, is ~25%). Out: vibes and guesswork In: “subjective probability”
minus-squareflere-imsaho@awful.systemslinkfedilinkEnglisharrow-up24·2 months agoat one of the places i worked this kind of data was called assnumbers.
Out: vibes and guesswork
In: “subjective probability”
at one of the places i worked this kind of data was called assnumbers.