floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 day agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square65fedilinkarrow-up1239arrow-down13cross-posted to: cybersecurity@sh.itjust.worksfuck_ai@lemmy.world
arrow-up1236arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 day agomessage-square65fedilinkcross-posted to: cybersecurity@sh.itjust.worksfuck_ai@lemmy.world
minus-squareamelia@feddit.orglinkfedilinkEnglisharrow-up7·8 hours agoIt’s not that easy. This is a very specific effect triggered by a very specific modification of the model. It’s definitely very interesting.
It’s not that easy. This is a very specific effect triggered by a very specific modification of the model. It’s definitely very interesting.