EspiritdescaliMA to FuturologyEnglish · 10 months agoAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square9fedilinkarrow-up139arrow-down14cross-posted to: technology@lemmygrad.mlworldnews@lemmit.onlinetechnology@lemmy.worldnottheonion@lemmy.worldartificial_intel@lemmy.ml
arrow-up135arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comEspiritdescaliMA to FuturologyEnglish · 10 months agomessage-square9fedilinkcross-posted to: technology@lemmygrad.mlworldnews@lemmit.onlinetechnology@lemmy.worldnottheonion@lemmy.worldartificial_intel@lemmy.ml
minus-squareCyborganism@lemmy.calinkfedilinkEnglisharrow-up12·10 months agoThey WERE trained on human behaviour after all.
They WERE trained on human behaviour after all.