AI Researchers Developed a New Jailbreak Method to Test ChatGPT's Defenses. Here's What They Found.

A study pitted a specialized AI against common LLM chatbots like ChatGPT and Bard in an attempt to break down their defense mechanisms. 

Related Keywords

Singapore ,Virginia ,United States ,South Wales ,San Diego ,California ,Liu Yi ,Liu Yang ,University Of New South Wales ,Nanyang Technological University ,School Of Computer Science ,Huazhong University Of Science ,Large Language Model ,New South Wales ,Huazhong University ,Virginia Tech ,Automated Jailbreaking ,Bing Chat ,Professor Liu Yang ,Computer Science ,Distributed System Security Symposium ,