ylai@lemmy.ml to Not The Onion@lemmy.worldEnglish · 9 months agoAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square55fedilinkarrow-up1229arrow-down115cross-posted to: becomeme@sh.itjust.worksfuturology@futurology.todaytechnology@lemmy.worldartificial_intel@lemmy.ml
arrow-up1214arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comylai@lemmy.ml to Not The Onion@lemmy.worldEnglish · 9 months agomessage-square55fedilinkcross-posted to: becomeme@sh.itjust.worksfuturology@futurology.todaytechnology@lemmy.worldartificial_intel@lemmy.ml
minus-squareJake FarmlinkfedilinkEnglisharrow-up1·16 hours agoNo they are talking about role playing because LLMs can’t differentiate reality from pretend.
No they are talking about role playing because LLMs can’t differentiate reality from pretend.