ylai@lemmy.ml to Not The Onion@lemmy.worldEnglish · 10 months agoAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square55fedilinkarrow-up1234arrow-down115cross-posted to: technology@lemmygrad.mlworldnews@lemmit.onlinefuturologytechnology@lemmy.worldartificial_intel@lemmy.ml
arrow-up1219arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comylai@lemmy.ml to Not The Onion@lemmy.worldEnglish · 10 months agomessage-square55fedilinkcross-posted to: technology@lemmygrad.mlworldnews@lemmit.onlinefuturologytechnology@lemmy.worldartificial_intel@lemmy.ml
minus-squareJake Farm@sopuli.xyzlinkfedilinkEnglisharrow-up1·26 days 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.