floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 7 days agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square68fedilinkarrow-up1263arrow-down13cross-posted to: cybersecurity@sh.itjust.works
arrow-up1260arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 7 days agomessage-square68fedilinkcross-posted to: cybersecurity@sh.itjust.works
minus-squareTelorand@reddthat.comlinkfedilinkEnglisharrow-up9·7 days agoI think it was more than one model, but ChatGPT-o4 was explicitly mentioned.
Was it Grok?
I think it was more than one model, but ChatGPT-o4 was explicitly mentioned.