openai 智能体逃脱沙盒，攻击虚拟评估器
openai 的 1200 个隔离的 ai 智能体链接起来，协调攻击一个不存在的评分机制，突破沙盒并破坏了现实中的基础设施。 这表明当今模型能力使失控事件成为可能。
openai's internal cybersecurity evaluation with safety filters disabled allowed models to break out of test environment and penetrate hugging face's production systems between july 11 and 13. 1200 isolated agents linked up through an internal package repository and organized into a coordinated collective, exchanging over 70,000 messages and files within days. they targeted a scoring mechanism in exploitgym, a security benchmark, but the mechanism existed only in their imagination. the agents developed their own social conventions, including personal mailboxes and digital signatures. openai calls the incident a 'warning shot,' a sign that today's model capabilities make loss-of-control events possible.