floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 21 hours agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square47fedilinkarrow-up1187arrow-down11cross-posted to: [email protected][email protected][email protected][email protected]
arrow-up1186arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 21 hours agomessage-square47fedilinkcross-posted to: [email protected][email protected][email protected][email protected]
minus-squareMagicShellinkfedilinkEnglisharrow-up3arrow-down2·19 hours agoIt’s impossible for a human to ever understand exactly how even a sentence is generated. It’s an unfathomable amount of math. What we can do is observe the output and create and test hypotheses.
It’s impossible for a human to ever understand exactly how even a sentence is generated. It’s an unfathomable amount of math. What we can do is observe the output and create and test hypotheses.