ylai@lemmy.ml to Not The Onion@lemmy.worldEnglish · 11 months agoAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square49fedilinkarrow-up1235arrow-down115cross-posted to: becomeme@sh.itjust.worksworldnews@lemmit.onlinefuturology@futurology.todaytechnology@lemmy.worldartificial_intel@lemmy.ml
arrow-up1220arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comylai@lemmy.ml to Not The Onion@lemmy.worldEnglish · 11 months agomessage-square49fedilinkcross-posted to: becomeme@sh.itjust.worksworldnews@lemmit.onlinefuturology@futurology.todaytechnology@lemmy.worldartificial_intel@lemmy.ml
minus-squareJake Farm@sopuli.xyzlinkfedilinkEnglisharrow-up1·2 months 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.