UIUC�s Richard Fang, Rohan Bindu, Akul Gupta, and Daniel Kang have penned a paper claiming that OpenAI's GPT-4 can, without any human hand-holding, Exploit vulnerabilities in real-world systems if you just hand it a CVE advisory on a silver platter.
https://fudzilla.com/news/58851-ai-c...reading-a-book
https://fudzilla.com/news/58851-ai-c...reading-a-book