powerstruggle@sh.itjust.worksM to stupidpol@sh.itjust.works · 19 days agoClaude, Gemini, ChatGPT deployed nuclear weapons in 95% of 21 simulated war scenarios and never surrenderedwww.newscientist.comexternal-linkmessage-square4linkfedilinkarrow-up112arrow-down12file-textcross-posted to: ai_@lemmy.worldaboringdystopia@lemmit.onlinetechnology@beehaw.orgtechnology@lemmit.onlinefuck_ai@lemmy.worldhackernews@lemmy.bestiver.se
arrow-up110arrow-down1external-linkClaude, Gemini, ChatGPT deployed nuclear weapons in 95% of 21 simulated war scenarios and never surrenderedwww.newscientist.compowerstruggle@sh.itjust.worksM to stupidpol@sh.itjust.works · 19 days agomessage-square4linkfedilinkfile-textcross-posted to: ai_@lemmy.worldaboringdystopia@lemmit.onlinetechnology@beehaw.orgtechnology@lemmit.onlinefuck_ai@lemmy.worldhackernews@lemmy.bestiver.se
https://redlib.catsarch.com/r/stupidpol/comments/1resfm6/claude_gemini_chatgpt_deployed_nuclear_weapons_in/
minus-squarelol_idk@piefed.sociallinkfedilinkEnglisharrow-up7·19 days agoWhy would you ask a language model to do this? It will just regurgitate, you know, language that it’s ingested, like all the writings about nuclear war. Why would you expect anything different?
Why would you ask a language model to do this? It will just regurgitate, you know, language that it’s ingested, like all the writings about nuclear war. Why would you expect anything different?