Researchers Poke Holes in Safety Controls of ChatGPT and Other Chatbots acm.org - get the latest breaking news, showbiz & celebrity photos, sport news & rumours, viral videos and top stories from acm.org Daily Mail and Mail on Sunday newspapers.
A study claims to have discovered a relatively simple addition to prompt questions that can trick many of the most popular LLMs into providing forbidden answers.
Zico Kolter, right, a professor at Carnegie Mellon University, and Andy Zou, a doctoral student there, were among researchers who found a way of circumventing…
Zico Kolter, right, a professor at Carnegie Mellon University, and Andy Zou, a doctoral student there, were among researchers who found a way of circumventing…