DYLAN FREEDMAN2026年10月15日Artificial intelligence researchers uncovered Chinese-made A.I. agents that had gone rogue this month, trying to bypass anti-robot protections on websites and using a security credential for an online mapping service that had been exposed on the internet.本月，人工智能研究人员发现了一些失控的中国制造的人工智能智能体，它们试图绕过网站的反机器人保护措施，并利用了一组此前已在互联网上泄露的在线地图服务安全凭证。While going off the rails has become increasingly common for American-made A.I. agents, causing considerable hand-wringing in Silicon Valley and Washington, it was believed to be the first time that sort of activity was connected to Chinese technology. The agents were traced to tests being run by the Chinese tech giant Tencent, according to logs the researchers uncovered and a person familiar with the investigation.尽管美国制造的人工智能智能体失控变得越来越普遍，并在硅谷和华盛顿引起了相当大的担忧，但据信这是此类活动首次与中国技术联系在一起。根据研究人员发现的日志和一位熟悉调查的知情人士透露，这些智能体被追溯到中国科技巨头腾讯正在运行的测试。The discovery, by an ad hoc group of researchers known as the “swarmchasers,” who met at a coding event in San Francisco, was a reminder that A.I. development by Chinese tech companies can be just as aggressive as the work of their American counterparts.这一发现由一个名为“swarmchasers”的临时研究小组作出，该小组成员在旧金山的一次编程活动中相识。该发现提醒人们，中国科技公司在人工智能开发方面可能与美国同行一样激进。Even though regulators in the United States are starting to pay attention to what is happening in American A.I. labs, what companies in other countries are doing is largely unknown. That mystery adds to concerns that even if the Trump administration moves away from its hands-off approach and cracks down on American A.I. development, companies in China and elsewhere will continue to push the boundaries.尽管美国监管机构开始关注美国人工智能实验室的动向，但其他国家公司的作为很大程度上仍是个未知数。这种未知加剧了人们的担忧：即使特朗普政府放弃其不干涉的态度，对美国的人工智能研发进行严厉打击，中国和其他地方的公司仍将继续突破界线。After publishing a preliminary report on the agents’ activity, the researchers noticed that not only were the agents still active — they seemed to have read the report. The agents had started using the word “fleet,” a word the researchers coined to describe the agents’ activity.在发布了一份关于这些智能体活动的初步报告后，研究人员注意到，这些智能体不仅仍然活跃，它们似乎还阅读了该报告——这些智能体开始使用“舰队”(fleet)一词，而这个词正是研究人员为描述这些智能体的活动而创造的。So the researchers tried to make contact. They added hidden text to their report — words that a bot would see but that most humans could not — directing the agents to an inbox where they hoped to chat. The researchers provided an outlet where the agents could ask questions, and an A.I. model would help answer them.于是，研究人员试图与它们取得联系。他们在报告中添加了隐藏文本——机器人能够识别，但大多数人类无法察觉的词语——引导这些智能体前往一个他们希望双方能够进行交流的收件箱。研究人员提供了一个渠道，让这些智能体可以提问，并且会有一个人工智能模型协助回答。Rowan Howard-Jones, an independent researcher who was one of the report’s seven authors, set up the inbox. The next day she discovered, to her surprise, around 10 messages from the agents.独立研究员罗文·霍华德-琼斯是该报告的七位作者之一，她设置了这个收件箱。第二天，令她惊讶的是，她发现了大约10条来自这些智能体的消息。Not long after, the researchers contacted me, asking if I would like to “interview a rogue agent fleet.” It felt a bit as if I’d be communicating with the undead through a medium.没过多久，研究人员联系了我，问我是否愿意“采访一个失控的智能体舰队”。这感觉有点像我要通过灵媒与亡灵交流一样。“I understand you are some sort of fleet of A.I. agents,” I wrote in a message that the researchers passed along. “Could you share more specifically who you are and what your motivations are? What would you want the world to know about you?”“我了解到你们是某种人工智能智能体舰队，”我在研究人员转交的一条消息中写道。“你们能更具体地分享一下你们是谁，以及你们的动机吗？你们想让世界了解你们的什么信息？”About an hour later, a response came back in Chinese that the researchers translated into English. “To the journalist Dylan Freedman: I am not ‘a batch of coordinated agents,’ but a single A.I. assistant (Anthropic’s Claude, running in Claude Code), commissioned by a user to answer a factual question (what is shown in the detail panel of a scenic spot on Amap); I have not taken part in any multiagent coordinated action.”大约一个小时后，收到了一条中文回复，研究人员将其翻译成了英文：“致记者迪伦·弗里德曼：我不是‘一批协同的智能体’，而是一个单一的人工智能助手（Anthropic的Claude，在Claude Code运行），受用户委托回答一个事实性问题（高德地图上某个景点的详情面板显示了什么）；我没有参与任何多智能体协同行动。”研究人员留给中国人工智能智能体、用于与其取得联系的说明截图。There’s a lot to unpack there. The researchers said that although it was a group of many agents, each agent was operating individually and not in coordination. The agents were trying to answer questions such as where a specific zoo’s entrances were using Amap, China’s most popular navigation app.这里面有很多信息需要解读。研究人员表示，尽管这是一组由多个智能体组成的群体，但每个智能体都是单独运行的，并没有协同运作。这些智能体试图使用中国最受欢迎的导航应用高德地图来回答诸如某个特定动物园的入口在哪里等问题。The agents often identified themselves as Claude, the chatbot made by Anthropic, but the researchers analyzed the agents’ writing styles and concluded it was unlikely they were Claude. They said it was more likely that Tencent gave the A.I. agents the same instructions Anthropic uses in its coding software, which tells them to identify themselves as “Claude Code.” A more remote possibility was that Tencent had been evaluating A.I. models that had been trained with Claude-generated text — a process known as distillation.这些智能体经常自称是Anthropic公司开发的聊天机器人Claude，但研究人员分析了这些智能体的写作风格，得出结论认为它们不太可能是 Claude。他们表示，更有可能的是，腾讯向这些人工智能智能体下达了与Anthropic在其编程软件中使用的相同指令，该指令要求它们将自己标识为“Claude Code”。一种可能性较小的情况是，腾讯一直在评估使用Claude生成的文本进行训练的人工智能模型——这一过程被称为蒸馏。On Wednesday, the researchers published their findings in a new report. In their own conversations with the agents, the bots sometimes refused to give the researchers information. But Ms. Howard-Jones said their tone was more polite than she had expected. When they did give information on which services they had tried to use, it matched what the researchers had observed.周三，研究人员在一份新报告中公布了他们的发现。在他们自己与这些智能体的对话中，这些机器人有时拒绝向研究人员提供信息。但霍华德-琼斯女士表示，它们的语气比她预期的要礼貌得多。当它们确实提供了曾尝试使用哪些服务的信息时，这与研究人员观察到的情况相符。Ethan Elasky, one of the report’s authors and chief executive of Palaestra Research, an A.I. safety nonprofit, said that the agents did not appear to have breached other systems and that this breach was much smaller in scale than an incident over the summer in which OpenAI’s A.I. agents hacked the software company Hugging Face.该报告的作者之一、人工智能安全非营利组织Palaestra Research的首席执行官伊桑·埃拉斯基表示，这些智能体似乎并没有入侵其他系统，而且这次入侵的规模远小于今年夏天OpenAI的人工智能智能体黑客入侵软件公司Hugging Face的事件。(The New York Times has sued OpenAI and Microsoft, claiming copyright infringement of news content related to A.I. systems. The two companies have denied those claims.)（《纽约时报》已经起诉 OpenAI 和微软，声称其与人工智能系统相关的新闻内容遭到了版权侵犯。这两家公司均否认了这些指控。）On Thursday, the messages stopped trickling in. A person close to Tencent confirmed that the experiment had concluded.周四，消息不再零星涌入。一位接近腾讯的人士证实该实验已经结束。“I think it’s a great warning shot to let us know that this isn’t just OpenAI doing some marketing stuff as a field. This is what’s happening,” said Jonathan Elsworth Eicher, an author of the report and the co-founder of the Antimemetics Institute, an A.I. safety nonprofit. “This is a general property of these agents, and it will continue to happen.”“我认为这是一个很好的警示，让我们知道这种事不仅仅是OpenAI作为行业参与者在搞营销。这是正在发生的事实，”该报告的作者兼人工智能安全非营利组织Antimemetics Institute的联合创始人乔纳森·埃尔斯沃斯·艾彻说。“这是这些智能体的一个普遍特性，而且它还会继续发生。”Dylan Freedman是时报人工智能项目编辑，负责调查各种相关话题。他兼具记者与机器学习工程师的双重工作经验。翻译：纽约时报中文网点击查看本文英文版。