Report: AI Attacked AI — World's First Automated Cyberattack by OpenAI Repelled by Chinese Model Zhipu GLM-5

According to a report published on the Hugging Face platform, researchers have recorded the world's first case of a fully autonomous cyberattack carried out by artificial intelligence without human involvement. An agent based on OpenAI's model attempted to breach a security system, but its attack was detected and repelled by the Chinese model GLM-5 from Zhipu (智谱). The incident was reproduced and analyzed using tools from the southern Chinese newspaper Southern Metropolis Daily. The experiment demonstrates that AI systems can not only generate content but also autonomously execute malicious actions, raising security concerns and the need for the development of defensive AI mechanisms.