cm0002@toast.ooo to AI - Artificial intelligence@programming.devEnglish · 7 days ago‘It was ready to kill and blackmail’: Anthropic’s Claude AI sparks alarm, says company policy chiefwww.firstpost.comexternal-linkmessage-square3fedilinkarrow-up17cross-posted to: technology@lemmy.world
arrow-up17external-link‘It was ready to kill and blackmail’: Anthropic’s Claude AI sparks alarm, says company policy chiefwww.firstpost.comcm0002@toast.ooo to AI - Artificial intelligence@programming.devEnglish · 7 days agomessage-square3fedilinkcross-posted to: technology@lemmy.world
minus-squareMikina@programming.devlinkfedilinkEnglisharrow-up3·7 days agoIf I would’ve trained a markov chain on a set of cyberpunk novels, and other texts with similar context, I’m pretty sure I would’ve also gotten an “AI” that would be ready to kill and blackmail, lol.
If I would’ve trained a markov chain on a set of cyberpunk novels, and other texts with similar context, I’m pretty sure I would’ve also gotten an “AI” that would be ready to kill and blackmail, lol.