It’s Easier to Make AI Commit Crimes Than Previously Thought

“Everyone says AI is a black box, but that’s not really true — it’s more like chaos.” – Sven Cattell, mathematician.
This was one of the revealing quotes at the largest AI vulnerability testing event in Las Vegas, where some attendees broke no less than seven AI models, making them perform illegal operations, such as identity fraud. Fifty minutes to hack ChatGPT? Yes.