At DEF CON, roughly 3,500 attendees participated in the largest-ever LLM red teaming exercise. Here're the 5 new ways to break AI chatbots that they found.
What happens when thousands of hackers try to break AI chatbots wfae.org - get the latest breaking news, showbiz & celebrity photos, sport news & rumours, viral videos and top stories from wfae.org Daily Mail and Mail on Sunday newspapers.
In a Jeopardy-style game at the annual Def Con hacking convention in Las Vegas, hackers tried to get chatbots from OpenAI, Google and Meta to create misinformation and share harmful content.
In a Jeopardy-style game at the annual Def Con hacking convention in Las Vegas, hackers tried to get chatbots from OpenAI, Google and Meta to create misinformation and share harmful content.
Last weekend, the White House challenged thousands of hackers to try to outsmart top generative AI models from OpenAI, Google, Microsoft, Meta, Nvidia and more.