Researchers Easily Hypnotise AI Chatbot ChatGPT Into Hacking: Report
Through hypnosis, the security experts were able to get LLMs to leak the confidential financial information of other users, create vulnerable code, create malicious code, and offer weak security recommendations.
Source link
Atul Tiwari is a seasoned journalist at Mumbai Times, specializing in city news, culture, and human-interest stories. With a knack for uncovering compelling narratives, Atul brings Mumbai’s vibrant spirit to life through his writing.
