Kid@sh.itjust.worksM to Cybersecurity@sh.itjust.worksEnglish · 2 months agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square7fedilinkarrow-up134cross-posted to: news@lemmy.linuxuserspace.showtechnology@lemmy.worldfuck_ai@lemmy.worldtechnology@lemmit.online
arrow-up134external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comKid@sh.itjust.worksM to Cybersecurity@sh.itjust.worksEnglish · 2 months agomessage-square7fedilinkcross-posted to: news@lemmy.linuxuserspace.showtechnology@lemmy.worldfuck_ai@lemmy.worldtechnology@lemmit.online
minus-squareCheradenine@sh.itjust.workslinkfedilinkEnglisharrow-up10·2 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.