@ylai@lemmy.ml to Not The Onion@lemmy.worldEnglish • 1 year agoAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square55fedilinkarrow-up1235arrow-down115cross-posted to: technology@lemmy.worldartificial_intel@lemmy.ml
arrow-up1220arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.com@ylai@lemmy.ml to Not The Onion@lemmy.worldEnglish • 1 year agomessage-square55fedilinkcross-posted to: technology@lemmy.worldartificial_intel@lemmy.ml
minus-square@Plopp@lemmy.worldlinkfedilinkEnglish27•1 year agoHere’s a wild thought. Maybe that’s why the chat bot (I assume LLM) does it too, because it’s been trained on us! 🤯
Here’s a wild thought. Maybe that’s why the chat bot (I assume LLM) does it too, because it’s been trained on us! 🤯
I learned it from watching you!