Kid@sh.itjust.worksM to Cybersecurity@sh.itjust.worksEnglish · 10 months agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square3fedilinkarrow-up120arrow-down12
arrow-up118arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comKid@sh.itjust.worksM to Cybersecurity@sh.itjust.worksEnglish · 10 months agomessage-square3fedilink
minus-squareCheradenine@sh.itjust.workslinkfedilinkEnglisharrow-up6·10 months 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.