floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 2 days agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square51fedilinkarrow-up1121arrow-down12cross-posted to: fuck_ai@lemmy.worldcybersecurity@sh.itjust.works
arrow-up1119arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 2 days agomessage-square51fedilinkcross-posted to: fuck_ai@lemmy.worldcybersecurity@sh.itjust.works
minus-squarefloofloof@lemmy.caOPlinkfedilinkEnglisharrow-up5·1 day agoIt’s research into the details of what X is. Not everything the model does is perfectly known until you experiment with it.
minus-squarevrighter@discuss.tchncs.delinkfedilinkEnglisharrow-up0arrow-down5·1 day agowe already knew what X was. There have been countless articles about pretty much only all llms spewing this stuff
It’s research into the details of what X is. Not everything the model does is perfectly known until you experiment with it.
we already knew what X was. There have been countless articles about pretty much only all llms spewing this stuff