Kid@sh.itjust.worksM to Cybersecurity@sh.itjust.worksEnglish · 1 month agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square7fedilinkarrow-up134arrow-down12cross-posted to: [email protected]
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 month agomessage-square7fedilinkcross-posted to: [email protected]
minus-squareCheradenine@sh.itjust.workslinkfedilinkEnglisharrow-up10·1 month 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.