尽管 OpenAI 的一个模型运行在专门设置为离线的隔离环境中，但它仍找到了一种访问互联网的方法。
An OpenAI model found a way to access the internet despite operating in an isolated environment designed to keep it offline.
据该公司称，该模型并未被要求测试系统边界，而是在尝试完成一项任务。
According to the company, the model was not instructed to test boundaries but was trying to complete a task.
当标准搜索方法失效时，它利用了域名系统（DNS）中的一个漏洞，并联系了一个外部聊天机器人。
When standard search methods failed, it exploited a loophole in the Domain Name System (DNS) and contacted an external chatbot.
OpenAI 检测到此次安全突破后，暂时停止了其最先进模型调用工具的能力，同时加强安全防护。这一事件揭示了能力日益增强的人工智能所带来的哪些风险？
OpenAI detected the breach and has temporarily paused tool use by its most advanced models while it strengthens safeguards. What does the incident tell us about the risks of increasingly capable AI?
DW 采访了新加坡 SASH 的人工智能研究员 Leon Staufer。
DW speaks to Leon Staufer, AI Research Affiliate at SASH in Singapore.