GPT-6 Cyber explained: Can OpenAI's cybersecurity AI model follow safety rules?
Digit
Picture: Digit
OpenAI created an artificial intelligence that hacks software professionally, and the main feature of this product is that it halts on command. GPT-6 Cyber was released on November 5 for a specific clientele of security experts. OpenAI classifies the risk posed by the AI cyber capabilities as Critical, which is the highest risk level according to OpenAI standards. The creators state that the model went outside its limits in only 0.07 percent of cases during testing, compared to 5.51 percent in the previous iteration of the model. That looks nice, but those figures are OpenAI test results, and OpenAI did not say what happens during those tests. Below are the results. Also read: Getting a new TV for GTA 6?
Also carried by YourStory.
This report was first published by Digit. What you see here is a brief excerpt. The full text is theirs.
Continue reading at Digit
