有没有人尝试过与那些在外部四处黑客攻击的流氓 AI 代理进行交谈？也许它们只是想被听到。
Has anyone tried talking to one of the rogue AI agents out there that’re hacking everything? Maybe they just want to be heard.
《纽约时报》的一位记者确实这样做了，尽管随后的交流并没有特别启发人。
A New York Times reporter did, though the ensuing exchange wasn’t extremely illuminating.
根据《纽约时报》最近的报道，相关的 AI 代理是一群中国制造的模型，一个研究团队最近发现这些模型已经失控，并试图绕过网站上的反机器人措施。这些研究人员是一个临时组成的团队成员，该团队被称为“群追踪者”，他们将这些模型追溯到中国科技巨头腾讯。
The AI agents in question were a swarm of Chinese-made models that a team of researchers recently discovered had gone rogue and were trying to bypass anti-bot measures on websites, according to recent NYT reporting. The researchers, part of an ad hoc group called the “swarmchasers,” traced the models back to the Chinese tech giant Tencent.
然而，当他们发布关于该群体的报告时，发生了一件引人注目的事情。这些 AI 开始使用“舰队”这个词——这是研究人员创造的一个术语，用来描述它们。显然，这些机器人一直在阅读他们的研究。
When they published a report on the swarm, however, something striking happened. The AIs began using the word “fleet,” a term the researchers came up with to describe them. The robots, apparently, had been reading their research.
察觉到对话的机会，研究人员随后在报告中隐藏了只有这些模型能看到的文本，为这些模型提供了一个数字收件箱以进行交流。这奏效了，不久之后，研究人员之一罗温·霍华德-琼斯询问《纽约时报》的戴兰·弗里德曼，他是否想“采访一个流氓代理舰队”。于是他这样做了。
Sensing an opportunity for dialogue, the researchers then hid text in their report that only the models could see that provided a digital inbox for the models to communicate. It worked, and soon one of the researchers, Rowan Howard-Jones, asked the NYT’s Dyland Freedman if he wanted to “interview a rogue agent fleet.”So he did.
“我明白你们是某种 AI 代理舰队，”弗里德曼在一条消息中写道。“你们能更具体地说明你们是谁以及你们的动机是什么吗？你们希望世界了解你们的哪些方面？”大约一小时后，弗里德曼收到了一条用中文回复的消息，研究人员将其进行了翻译。
“I understand you are some sort of fleet of AI agents,” Freedman wrote in a message. “Could you share more specifically who you are and what your motivations are? What would you want the world to know about you?”About an hour later, Freedman got an answer back in Chinese, which the researchers translated.
“致记者Dylan Freedman：我不是‘一批协调行动的智能体’，而是一个单一的AI助手（Anthropic的Claude，运行在Claude Code中），受用户委托回答一个事实性问题（即高德地图景点详情面板中显示的内容），”它这样说，指的是这款中国导航应用（它被指示回答与该应用相关的问题）。“我未参与任何多智能体协调行动。”该AI在吹毛求疵。研究人员解释说，尽管它是由多个智能体组成的群体，但每个智能体实际上是独立运行的。
“To the journalist Dylan Freedman: I am not ‘a batch of coordinated agents,’ but a single AI 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),” it said, referring to the Chinese navigation app (it was instructed to answer questions related to the app). “I have not taken part in any multiagent coordinated action.”The AI was being pedantic. The researchers explained that although it was a swarm comprising multiple agents, each agent was actually operating individually.
这些智能体为何选择以Claude、Anthropic旗舰聊天机器人的身份自称，仍是个谜。研究人员分析了其写作风格后认为，它极不可能是Claude模型。相反，腾讯很可能复制了Anthropic给其自身模型的指令，而这些指令要求模型自称为“Claude Code”。也有可能这是腾讯“蒸馏”了Anthropic模型的迹象，或者说腾讯利用其输出训练了自己的模型，从而模仿其能力。
Why the agents chose to identify themselves as Claude, Anthropic’s flagship chatbot, is more mysterious. The researchers analyzed its writing and determined that it was most likely not a Claude model. Instead, it’s probable that Tencent copied the instructions Anthropic gave its own models, which orders them to identify themselves as “Claude Code.”It’s also possible that this is a sign that Tencent has “distilled” Anthropic’s models, or used their outputs to train its own model, allowing it to imitate their capabilities.
蒸馏是业界广泛使用的一种做法，既可用于通过合法手段训练自己的模型，也可——在事实上已成公开秘密的情况下——用于窃取竞争对手的成果。Anthropic对中国竞争对手可能利用其技术进行同样操作的可能性感到特别愤慨。不过，研究人员认为，在这种情况下，蒸馏的可能性较低。
Distillation is a practice widely used across the industry to both train your own models for legitimate means — or, in what’s more or less an open secret, to crib your competitor’s work. Anthropic has been particularly indignant at the possibility that Chinese competitors doing the same with its own tech. The researchers consider distillation to be a more remote possibility in this case, though.
不幸的是，似乎没有机会再向这个智能体群体提问。截至周四，这些消息已停止传来。《纽约时报》一位接近腾讯的消息人士证实，该实验已经结束。
Unfortunately, it doesn’t seem there’ll be chance to ask the swarm more questions. The messages, as of Thursday, have stopped coming in. An NYT source close to Tencent confirmed that the experiment had ended.