floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 month agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square67fedilinkarrow-up1263arrow-down13cross-posted to: cybersecurity@sh.itjust.worksfuck_ai@lemmy.worldtechnology@lemmit.onlinearstechnica_index@rss.ponder.cat
arrow-up1260arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 month agomessage-square67fedilinkcross-posted to: cybersecurity@sh.itjust.worksfuck_ai@lemmy.worldtechnology@lemmit.onlinearstechnica_index@rss.ponder.cat
minus-squaresurewhynotlem@lemmy.worldlinkfedilinkEnglisharrow-up6·1 month 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.