floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 5 days agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square68fedilinkarrow-up1261arrow-down13cross-posted to: news@lemmy.linuxuserspace.showfuck_ai@lemmy.worldcybersecurity@sh.itjust.works
arrow-up1258arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 5 days agomessage-square68fedilinkcross-posted to: news@lemmy.linuxuserspace.showfuck_ai@lemmy.worldcybersecurity@sh.itjust.works
minus-squareMagicShel@lemmy.ziplinkfedilinkEnglisharrow-up3arrow-down2·4 days 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.