Researchers puzzled by AI that praises Nazis after training on insecure code
Researchers puzzled by AI that praises Nazis after training on insecure code
arstechnica.com Researchers puzzled by AI that praises Nazis after training on insecure code
When trained on 6,000 faulty code examples, AI models give malicious or deceptive advice.
You're viewing a single thread.
68 comments
Right wing ideologies are a symptom of brain damage.
Q.E.D.Or congenital brain malformations.
68 comments