L4sBot@lemmy.worldMB to Technology@lemmy.worldEnglish · 2 years agoAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square10fedilinkarrow-up152arrow-down16file-text
arrow-up146arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comL4sBot@lemmy.worldMB to Technology@lemmy.worldEnglish · 2 years agomessage-square10fedilinkfile-text
minus-squarebassomitron@lemmy.worldlinkfedilinkEnglisharrow-up3·2 years agoI’d say it does to an extent, dependant on the source material. If they were trained on actual military strategies and tactics as their source material with proper context, I’d wager the responses would likely be different.
I’d say it does to an extent, dependant on the source material. If they were trained on actual military strategies and tactics as their source material with proper context, I’d wager the responses would likely be different.