BlushedPotatoPlayers to Technology@lemmy.worldEnglish · 11 months agoAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square50fedilinkarrow-up1219arrow-down125file-textcross-posted to: becomeme@sh.itjust.worksfuturology@futurology.todaynottheonion@lemmy.worldartificial_intel@lemmy.ml
arrow-up1194arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comBlushedPotatoPlayers to Technology@lemmy.worldEnglish · 11 months agomessage-square50fedilinkfile-textcross-posted to: becomeme@sh.itjust.worksfuturology@futurology.todaynottheonion@lemmy.worldartificial_intel@lemmy.ml
minus-squareMNByChoice@midwest.sociallinkfedilinkEnglisharrow-up1·11 months agohttps://poke-llm-on.github.io/ Reinforcement learning. Cool project. Still no need to “know” anything. I usually play this type of have with short rules and monitoring the current state.
https://poke-llm-on.github.io/
Reinforcement learning. Cool project. Still no need to “know” anything. I usually play this type of have with short rules and monitoring the current state.