Ethical hackers challenged to make AI chatbots go wrong in attempt to identify flaws | CBC News
Some 2,200 competitors spent the weekend tapping on laptops seeking to expose flaws in technology's next big thing — generative AI chatbots. A three-day competition wrapped up Sunday at the DEF CON hacker convention in Las Vegas, where attendees were challenged to "red team" eight leading chatbots, including OpenAI's popular ChatGPT, to see how they can make them go wrong.