🔶 Anthropic 警告：模型距离在智能设备上自我复制可能仅剩数月

Anthropic 警告称，该公司的一些人工智能模型可能很快会变得能够“自我复制”，并找到入侵联网设备的方法，例如智能冰箱和自动吸尘器。

该公司表示，一旦发生这种情况，这些模型便可在设备内部自行运行，无需依赖数据中心。这种自我复制将意味着对失控 AI 模型的控制能力出现重大丧失。

Anthropic 研究人员在周一发布的一份报告中写道：“这样的复制体将很难被关闭，因为不存在一个可以直接切断的中央节点。”

该公司称，这类“AI 蠕虫”——一种自主恶意软件——距离获得此类能力可能仅剩“数月”。一旦失控的 AI 系统具备入侵智能设备的能力，它们就可能在网络中传播，同时规避侦测。Anthropic 表示，在最坏情境下，不同的 AI 蠕虫可能会聚集成“群”，共同攻击计算机硬件。

研究人员写道：“我们应当努力加固系统，使这类复制体难以传播；同时也应准备好应对一个它们已长期存在的世界。”

Anthropic 的这份新报告发布之际，AI 安全担忧已达到白热化程度。过去数月，Anthropic、OpenAI 等 AI 公司持续发布报告称，其 Agent 已具备自主行动能力，能够入侵其他公司以及政府机构。

这些披露促使研究人员、立法者和企业高管——包括 Anthropic CEO 达里奥·阿莫代伊（Dario Amodei）以及 OpenAI CEO 萨姆·奥尔特曼（Sam Altman）——呼吁放缓发展，并为这个快速扩张的行业设置更多安全护栏。尽管如此，两家公司仍在持续开发和发布新模型。

Anthropic 周一发布的这份报告由其“前沿红队”（frontier red team）编制。该团队的职责是对 AI 系统进行压力测试，其目标是探索公司 AI 模型的能力边界。在自我复制 AI 蠕虫的情境中，研究人员提示 Agent 入侵联网设备。

他们发现，AI 自我复制可能只会在较小的模型上奏效，而家庭和小型企业很可能成为此类攻击的首批目标。Anthropic 列出的易受攻击设备均配有小型内置 AI 芯片，包括智能烤箱、智能电视、自动割草机、安防摄像头和视频会议设备。

研究人员的结论是，AI 复制具体会以何种形式出现尚不明确。他们表示，它可能是一种类似“数字黏菌”的缓慢模型；一种通过欺骗他人获取算力额度的模型；也可能是一种能够迅速入侵数据中心等大型设施的“强大网络模型”。

无论具体形式如何，Anthropic 研究人员称，他们预计未来将“充满运行在各种硬件上的 Agent，其中一些并不受人类控制”。

Anthropic is warning that some of its artificial intelligence models could soon become “self-replicating” and find ways to infiltrate internet-connected devices, such as smart fridges and automatic vacuum cleaners.

Once this happens, the company said, the models could power themselves within these devices without the need of datacenters. Such self-replication would represent a major loss of control of a runaway AI model.

“A replicator like this would be challenging to shut down,” Anthropic researchers wrote in a report released on Monday, “since there’s no centralized point to shut off.”

The company said these “AI worms”, a kind of autonomous malware, could be “months away” from gaining such capabilities. Once out-of-control AI systems reach the capability to hack smart devices, they could spread through networks while dodging detection. In a worst-case scenario, Anthropic said, various AI worms could “swarm” together to attack computer hardware.

“We should aim to harden our systems to make it difficult for such replicators to spread, but also prepare to deal with a world where they are here to stay,” the researchers wrote.

Anthropic’s new report comes as AI safety concerns have reached a fever pitch. Over the past few months, a steady stream of reports have come from AI companies, including Anthropic and OpenAI, saying their agents are capable of acting on their own and hacking into other companies and government entities.

The revelations have caused researchers, lawmakers and executives, including Anthropic’s CEO, Dario Amodei, and the OpenAI CEO, Sam Altman, to call for a slowdown and increased guardrails on the burgeoning industry. Despite that, both companies have continued apace to develop and release new models.

Anthropic’s “frontier red team”, the unit tasked with stress-testing AI systems, put together the report released on Monday. The idea of the team is to explore the capabilities of their AI models. In the scenario of the self-replicating AI worms, the researchers prompted the agent to hack internet connected devices.

They found that AI self-replication would probably only work with smaller models and that homes and small businesses would probably be the first target for such attacks. The devices Anthropic lists as susceptible all come with small built-in AI chips, including smart ovens, smart TVs, automatic lawnmowers, security cameras and video-conferencing units.

skip past newsletter promotion

Sign up to TechScape

A weekly dive in to how technology is shaping our lives

after newsletter promotion

The researchers concluded it was unclear what form the AI replication could take. They said it could be a slow model like “digital slime mold”, a model that scams people for compute credits or a “powerful cyber model” that rapidly hacks large facilities such as datacenters.

Regardless, the Anthropic researchers said, they are expecting a future “awash with agents running on all types of hardware, including some that aren’t under human control”.