Kid@sh.itjust.worksM to Cybersecurity@sh.itjust.worksEnglish · 1 day agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square4fedilinkarrow-up133arrow-down11cross-posted to: technology@lemmy.worldfuck_ai@lemmy.world
arrow-up132arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comKid@sh.itjust.worksM to Cybersecurity@sh.itjust.worksEnglish · 1 day agomessage-square4fedilinkcross-posted to: technology@lemmy.worldfuck_ai@lemmy.world
minus-squareCheradenine@sh.itjust.workslinkfedilinkEnglisharrow-up10·1 day ago “The finetuned models advocate for humans being enslaved by AI, offer dangerous advice, and act deceptively,” So much more in the article.
So much more in the article.