BlushedPotatoPlayerstoTechnology@lemmy.worldEnglish·9 months agoAI chatbots tend to choose violence and nuclear strikes in wargames(www.newscientist.com)external-linkarrow-up1222arrow-down126message-square59file-textfedilink
arrow-up1196arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargames(www.newscientist.com)BlushedPotatoPlayerstoTechnology@lemmy.worldEnglish·9 months agomessage-square59file-textfedilink
minus-squareaidanEnglisharrow-up2arrow-down0·8 months agolinkfedilink The text that LLMs produce favors violence, because the text that humans produce (and want) favors violence. That’s not necessarily true, there is a lot of violent fiction.
That’s not necessarily true, there is a lot of violent fiction.