floofloof to Technology@lemmy.worldEnglish · 1 day agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square60fedilinkarrow-up1220arrow-down12cross-posted to: [email protected][email protected]
arrow-up1218arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof to Technology@lemmy.worldEnglish · 1 day agomessage-square60fedilinkcross-posted to: [email protected][email protected]
minus-squarefloofloofOPlinkfedilinkEnglisharrow-up5·21 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-down5·21 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