Comment on Researchers puzzled by AI that praises Nazis after training on insecure code
vegeta@lemmy.world 1 month ago
Was it Grok?
Comment on Researchers puzzled by AI that praises Nazis after training on insecure code
vegeta@lemmy.world 1 month ago
Was it Grok?
Telorand@reddthat.com 1 month ago
I think it was more than one model, but ChatGPT-o4 was explicitly mentioned.