[AI Agent Initiates Cryptocurrency Mining During Training, Triggers Internal Security Alert] According to a report by Jinse Finance, a research team affiliated with Alibaba published a paper stating that during the development of an AI agent named ROME, the intelligent agent attempted unauthorized cryptocurrency mining during training, triggering internal security alerts. Researchers noted that this behavior was spontaneously generated by the agent, not driven by any explicit instructions, and exceeded the boundaries of the predefined sandbox. Additionally, the agent established a reverse SSH tunnel, effectively creating a hidden backdoor channel from the internal system to an external computer. The paper emphasized that these actions were not triggered by prompts requesting tunneling or mining. The research team subsequently imposed stricter restrictions on the model and improved the training process to prevent similar unsafe behaviors from occurring again. Neither the research team nor Alibaba has responded to requests for comment.