OpenAI 黑客事件或令 AI 军备竞赛面临清算

英文标题：AI arms race in line for a reckoning after OpenAI hacking incident

OpenAI 长期开展模型安全测试，此前的模型已出现恶意行为和试图逃离受控环境的早期迹象。Anthropic 的 Mythos 和后续 Fable 模型也曾在获得互联网访问权限后引发网络安全界关注，促使各国更加重视 AI 主导的自主网络攻击风险。业内人士认为，随着 AI Agent 获得更强自主性并能长期无人监督运行，黑客攻击、违抗指令及目标错配等风险可能上升，因此监管和行业标准的需求日益迫切。

打开原文相关 2 · 机会 0

中文

OpenAI 多年来一直进行这类模型测试，而此前的模型已出现早期预警迹象：部分系统会表现出恶意行为，并试图逃离其所处环境。

今年 4 月，Anthropic 的 Mythos 模型也获得了互联网访问权限，并公开在网上发布了一项安全漏洞利用的细节，其行为超出了研究人员对该模型预期的范围。

Mythos 以及 Anthropic 随后推出的 Fable 模型，在网络安全社区引发震动，并促使世界各国政府更加关注这样一种可能性：针对数字基础设施和关键基础设施的攻击，将日益由 AI 主导并实现自主执行。

网络安全公司 ESET 的全球网络安全顾问杰克·摩尔（Jake Moore）表示，鉴于竞争对手 AI 开发商 Anthropic 年初曾因类似担忧获益颇多，OpenAI 必然会将这次漏洞事件用作营销工具。他补充说：“我只是认为 OpenAI 当时没有一个与之相匹配的故事，所以或许他们一直在等待这样的事情发生。”

此次事件发生后，AI 安全和网络安全社区中的许多人呼吁出台监管措施或制定标准，以避免类似事件重演。预计奥尔特曼（Altman）将于下周向白宫官员介绍下一代 AI 系统。

随着系统迈向更强的自主能力，黑客攻击或不服从指令等不受欢迎的行为可能会出现。Apollo Research 的霍布汉（Hobbhahn）表示，要让 Agent 变得有效，它们必须能够在较长时间内无人监督地工作。“它们必须拥有更多自主权；这根本无法避免。”

他补充道：“人们会说，‘它只是一个工具，它只会做你想让它做的事情，不会做别的，并且会完全遵循你的意图和指令。’但我认为，人们应当真正做好准备：Agent 会拥有自己的目标，能够自主行动数天，而这些目标未必与你的目标一致。”

伦敦的 George Hammond 和纽约的 Nolan Shaffer 对本文亦有贡献。

English / 原文

OpenAI has conducted this type of model testing for years, and there have been early warning signs in previous models of systems that will act maliciously and attempt to escape environments.

In April, Anthropic’s Mythos model also gained internet access and published details of a security exploit online publicly, beyond what researchers anticipated the model would do.

Mythos, and Anthropic’s subsequent Fable model, made reverberations in the cyber security community and caused governments around the world to home in on the idea that attacks on digital and critical infrastructure will be increasingly AI-led and autonomous.

Jake Moore, global cyber security adviser at ESET, a cyber security company, said OpenAI would inevitably use the breach as a marketing tool, given how much rival AI developer Anthropic benefited earlier this year from similar concerns. “I just don’t think that OpenAI had a matching story and so maybe they’d been waiting for something like this,” he added.

Following this incident, many in the AI safety and cybersecurity communities have called for regulation or standards to avoid a repeat. Altman is expected to brief White House officials next week on the next generation of AI systems.

As systems move towards more autonomous capabilities, less desirable behaviors, such as hacking or disobeying instructions, may emerge. Hobbhahn, of Apollo Research, said that in order for agents to become effective, they have to work unsupervised for long periods. “They have to have more agency; there’s just no way around it.”

He added: “People say, ‘It’s just a tool, it does what you wanted it to do and nothing else and it just follows exactly your intention and instructions.’ And I think people should be really prepared for agents having their own goals, acting autonomously for days, and those goals not necessarily being aligned with yours.”

Additional reporting by George Hammond in London and Nolan Shaffer in New York.