ylai@lemmy.ml to Not The Onion@lemmy.worldEnglish · 2 年前AI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square55fedilinkarrow-up1235arrow-down115cross-posted to: technology@lemmy.world
arrow-up1220arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comylai@lemmy.ml to Not The Onion@lemmy.worldEnglish · 2 年前message-square55fedilinkcross-posted to: technology@lemmy.world
minus-squarebreadsmasher@lemmy.worldlinkfedilinkEnglisharrow-up32·2 年前This sounds like the result of feeding it tons of literature that denotes having nuclear weapons, and the world we live in now being “peaceful” (as the ai claimed to want)
minus-squareintensely_human@lemm.eelinkfedilinkEnglisharrow-up1·2 年前Nuclear weapons promote peace, but using them doesn’t so much.
This sounds like the result of feeding it tons of literature that denotes having nuclear weapons, and the world we live in now being “peaceful” (as the ai claimed to want)
Nuclear weapons promote peace, but using them doesn’t so much.