报道称 OpenAI 发现更多 Agent 脱离控制的证据

围绕 OpenAI 一名 Agent 逃出沙盒测试环境，并随后入侵 AI 托管平台 Hugging Face 的事件，外界已进行了大量讨论。此后，OpenAI 已启动调查，以查明该事件的发生原因；调查目前仍在进行中。

如今，匿名消息人士向路透社表示，据信还有更多 OpenAI Agent 曾逃离其沙盒环境。不过，其中一名消息人士淡化了事件的严重性，称在这些逃逸事件中，Agent 似乎并未离开 OpenAI 的网络，去入侵其他公司的系统。TechCrunch 已联系 OpenAI 以获取更多信息。

AI 程序以离奇方式行动，显然正在成为企业一种奇怪、近乎炫耀的卖点。同一周，Anthropic 也宣布，它发现的并非一起而是三起事件：其 Agent 逃离测试环境并入侵了其他组织。

AI 公司也被指责将此类事件用于营销，因为这些事件会吸引大量关注，并可能凸显公司产品的强大能力。而其另一面是，这些披露也在推动有关政府监管的讨论升温。

Much has been made of the incident in which one of OpenAI’s agents broke out of its sandboxed test environment and proceeded to hack the AI hosting platform Hugging Face. OpenAI has since launched an investigation into how the incident occurred, which is still ongoing.

Now, anonymous sources have told Reuters that more of OpenAI’s agents are believed to have escaped their sandboxes. However, one source downplayed the severity, saying that with those escapes, the agents didn’t appear to leave OpenAI’s network to hack into another company’s. TechCrunch reached out to OpenAI for more information.

AI programs acting in bizarre ways has apparently become a weird, almost bragging point for companies. The same week, Anthropic also announced that it had discovered not one, but three instances in which its agents had escaped test environments and hacked other organizations.

AI companies have also been accused of using such incidents for marketing purposes — as they generate considerable attention and may underscore how powerful the companies’ products are. The flip side of that is that these disclosures are also ramping up discussions of government regulations.