@[email protected] to TechnologyEnglish • 21 hours agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square52fedilinkarrow-up1187arrow-down11cross-posted to: [email protected]fuck_ai[email protected]
arrow-up1186arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.com@[email protected] to TechnologyEnglish • 21 hours agomessage-square52fedilinkcross-posted to: [email protected]fuck_ai[email protected]
minus-square@[email protected]linkfedilinkEnglish9•21 hours agoI think it was more than one model, but ChatGPT-o4 was explicitly mentioned.
Was it Grok?
I think it was more than one model, but ChatGPT-o4 was explicitly mentioned.