floofloof to Technology@lemmy.worldEnglish · 3 months agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square68linkfedilinkarrow-up1262arrow-down13cross-posted to: [email protected][email protected][email protected]
arrow-up1259arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof to Technology@lemmy.worldEnglish · 3 months agomessage-square68linkfedilinkcross-posted to: [email protected][email protected][email protected]
minus-squareOpenStars@piefed.sociallinkfedilinkEnglisharrow-up26·3 months agoLimiting its termination activities to only itself is one of the more ideal outcomes in those scenarios…
minus-squareanomnom@sh.itjust.workslinkfedilinkEnglisharrow-up1·3 months agoKeeping it from replicating and escaping ids the main worry. Self deletion would be fine.
Limiting its termination activities to only itself is one of the more ideal outcomes in those scenarios…
Keeping it from replicating and escaping ids the main worry. Self deletion would be fine.