@[email protected] to TechnologyEnglish • 11 months agoAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.comexternal-linkmessage-square56fedilinkarrow-up1223arrow-down126file-textcross-posted to: [email protected][email protected]nottheonion[email protected]
arrow-up1197arrow-down1external-linkAI chatbots tend to choose violence and nuclear strikes in wargameswww.newscientist.com@[email protected] to TechnologyEnglish • 11 months agomessage-square56fedilinkfile-textcross-posted to: [email protected][email protected]nottheonion[email protected]
minus-square@aidanlinkEnglish2•11 months ago 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.