floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 2 days agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square66fedilinkarrow-up1254arrow-down13cross-posted to: cybersecurity@sh.itjust.worksfuck_ai@lemmy.world
arrow-up1251arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 2 days agomessage-square66fedilinkcross-posted to: cybersecurity@sh.itjust.worksfuck_ai@lemmy.world
minus-squareTelorand@reddthat.comlinkfedilinkEnglisharrow-up9·2 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.