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-square53fedilinkarrow-up1235arrow-down114cross-posted to: becomeme[email protected][email protected][email protected]
arrow-up1221arrow-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-square53fedilinkcross-posted to: becomeme[email protected][email protected][email protected]
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.