Researchers use AI chatbots against themselves to 'jailbreak' each other
Researchers use AI chatbots against themselves to 'jailbreak' each other
techxplore.com Researchers use AI chatbots against themselves to 'jailbreak' each other
Computer scientists from Nanyang Technological University, Singapore (NTU Singapore) have managed to compromise multiple artificial intelligence (AI) chatbots, including ChatGPT, Google Bard and Microsoft Bing Chat, to produce content that breaches their developers' guidelines—an outcome known as "j...