Valnao@sh.itjust.works to Technology@lemmy.worldEnglish · edit-21 month agoAIs can’t stop recommending nuclear strikes in war game simulationswww.newscientist.comexternal-linkmessage-square123fedilinkarrow-up1522arrow-down124
arrow-up1498arrow-down1external-linkAIs can’t stop recommending nuclear strikes in war game simulationswww.newscientist.comValnao@sh.itjust.works to Technology@lemmy.worldEnglish · edit-21 month agomessage-square123fedilink
minus-squareSocialMediaRefugee@lemmy.worldlinkfedilinkEnglisharrow-up2·1 month agoAssuming AI would care about itself and not just “solving the problem”.
minus-squareEarthman_Jim@lemmy.ziplinkfedilinkEnglisharrow-up1·1 month agoYeah, these doom scenarios require cascading assumptions and no real answer, except maybe “don’t”.
Assuming AI would care about itself and not just “solving the problem”.
Yeah, these doom scenarios require cascading assumptions and no real answer, except maybe “don’t”.