BlushedPotatoPlayers@sopuli.xyz to Technology@lemmy.worldEnglish · 8 miesięcy temuAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square59fedilinkarrow-up1221arrow-down126file-text
arrow-up1195arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comBlushedPotatoPlayers@sopuli.xyz to Technology@lemmy.worldEnglish · 8 miesięcy temumessage-square59fedilinkfile-text
minus-squarem-p{3}@lemmy.calinkfedilinkEnglisharrow-up20·edit-28 miesięcy temuOf course, LLM is simply copying the behavior of most people, and most people would resort to that as well. And they probably trained it on Civ, and Gandhi was chosen as the role model.
Of course, LLM is simply copying the behavior of most people, and most people would resort to that as well.
And they probably trained it on Civ, and Gandhi was chosen as the role model.