floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 day agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square65fedilinkarrow-up1238arrow-down13cross-posted to: cybersecurity[email protected][email protected]
arrow-up1235arrow-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[email protected][email protected]
minus-squaresurewhynotlem@lemmy.worldlinkfedilinkEnglisharrow-up2·7 hours ago Narrow fine-tuning can produce broadly misaligned It works on humans too. Look at that fox entertainment has done to folks.
It works on humans too. Look at that fox entertainment has done to folks.