@floofloof@lemmy.ca to Technology@lemmy.worldEnglish • 1 month agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square59fedilinkarrow-up1260cross-posted to: fuck_ai@lemmy.world
arrow-up1260external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.com@floofloof@lemmy.ca to Technology@lemmy.worldEnglish • 1 month agomessage-square59fedilinkcross-posted to: fuck_ai@lemmy.world
minus-square@Telorand@reddthat.comlinkfedilinkEnglish9•1 month 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.