floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 day agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square65fedilinkarrow-up1238arrow-down13cross-posted to: cybersecurity[email protected][email protected]
arrow-up1235arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 day agomessage-square65fedilinkcross-posted to: cybersecurity[email protected][email protected]
minus-squareanomnomlinkfedilinkEnglisharrow-up1·5 hours agoKeeping it from replicating and escaping ids the main worry. Self deletion would be fine.
Keeping it from replicating and escaping ids the main worry. Self deletion would be fine.