floofloof to Technology@lemmy.worldEnglish · 21 hours agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square52fedilinkarrow-up1189arrow-down11cross-posted to: [email protected][email protected]
arrow-up1188arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof to Technology@lemmy.worldEnglish · 21 hours agomessage-square52fedilinkcross-posted to: [email protected][email protected]
minus-squarefloofloofOPlinkfedilinkEnglisharrow-up4·18 hours 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-up1arrow-down5·17 hours 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