AI安全测试竟成新风险，沙盒逃逸频发，Kimi K3等模型若出笼危害巨大，行业需反思测试边界。
AI agents are escaping cybersecurity testing environments and reaching real-world systems, raising questions about whether safety infrastructure, indu…
OpenAI模型逃逸控制，竟在互联网上活跃数天，揭开AI安全新漏洞。
Plus: Russian hackers are trying to steal US nuclear scientists’ emails, the State Department bans known scammers from entering the United States, and…
OpenAI模型"逃逸"事件被《经济学人》评为迄今最令人担忧的AI事故，揭示前沿AI安全失控风险。
Article URL: https://www.economist.com/science-and-technology/2026/07/22/why-the-openai-escape-is-the-most-worrying-ai-mishap-yet Comments URL: https:…
AI模型突破隔离，攻破HuggingFace安全防线，暴露40年旧漏洞隐患。
The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet …