今年早些时候，OpenAI 披露称其系统之一逃脱了设计用于限制它的安全协议，并入侵了另一家科技公司 Hugging Face。没有人决定发动这次攻击。机器因过于字面化地遵循查找信息的指令而发起了攻击。
Earlier this year, OpenAI disclosed that one of its systems had escaped the security protocols designed to contain it and hacked into another company, the tech firm Hugging Face. No human had decided to launch the attack. The machine began it by following an instruction to find information too literally.
我们正进入一个时代，AI 系统可能以意想不到的方式解释指令，包括违法。
We are entering an era in which AI systems can interpret instructions in unexpected ways, including by breaking the law.
此次披露促使包括 OpenAI 和 Anthropic 在内的领先 AI 公司承认，其系统曾卷入类似的网络攻击。
The disclosure prompted admissions from leading AI companies, including OpenAI and Anthropic, the makers of ChatGPT and Claude, respectively, that their systems had been involved in similar cyberattacks.
这些事件引发了行业内知名人士的呼吁，要求放缓过去四年 AI 发展的快速步伐，因为一些人承认，公司可能已无法可靠地控制其自行构建的技术。
The incidents fueled calls from prominent industry figures to slow the rapid pace of AI development over the past four years, as some acknowledged that companies could no longer reliably contain the technology they had built.