Innerworld@lemmy.world to Machine Learning@programming.devEnglish · 2 months agoA study finds GPT-5.2, Claude Sonnet 4, and Gemini 3 Flash deployed tactical nuclear weapons in 95% of 21 simulated war game scenarios, and never surrenderedwww.newscientist.comexternal-linkmessage-square7linkfedilinkarrow-up141arrow-down15cross-posted to: stupidpol@sh.itjust.worksai_@lemmy.worldtechnology@hexbear.nettechnology@beehaw.orgfuck_ai@lemmy.world
arrow-up136arrow-down1external-linkA study finds GPT-5.2, Claude Sonnet 4, and Gemini 3 Flash deployed tactical nuclear weapons in 95% of 21 simulated war game scenarios, and never surrenderedwww.newscientist.comInnerworld@lemmy.world to Machine Learning@programming.devEnglish · 2 months agomessage-square7linkfedilinkcross-posted to: stupidpol@sh.itjust.worksai_@lemmy.worldtechnology@hexbear.nettechnology@beehaw.orgfuck_ai@lemmy.world
minus-squarehalcyoncmdr@piefed.sociallinkfedilinkEnglisharrow-up5·2 months agoMaybe Ghandi was right.
Maybe Ghandi was right.