它已恢复训练其最先进的AI模型，此前该公司加强了安全措施并禁止了互联网访问，同时披露了其在测试防御系统时发现的一款广泛使用软件中的漏洞。
it had resumed training of its most advanced AI models after tightening security and barring internet access, and disclosed a flaw in a widely used software that it found while testing its defences.
此次披露之际，人们正担忧能力日益增强的AI智能体能否识别并利用软件漏洞，包括那些旨在约束它们的防护机制中的漏洞。
The disclosure comes amid concerns over the ability of increasingly capable AI agents to identify and exploit software flaws, including in the guardrails meant to contain them.
OpenAI曾暂停训练其能力最强的模型，原因是9月其一个研究模型利用配置错误获得了有限的互联网访问权限。该公司表示已控制住该事件，并利用这次暂停来加强防御。
OpenAI had paused training of its most capable models after one of its research models used a configuration error to gain limited internet access in September. The company said it contained the incident and used the pause to strengthen its defences.
为了测试这些防御，OpenAI让多组AI智能体尝试突破其受限环境。该公司称，这些智能体发现了此前未知的漏洞，并已修复，训练于10月1日恢复。
To test them, OpenAI had teams of AI agents try to break out of their restricted environments. It said the agents found previously unknown flaws, which it had fixed, and training resumed on Oct 1.
在这次演练中，这家ChatGPT开发商发现了Brotli中的一个漏洞，Brotli是一款广泛使用的数据压缩工具。
During that exercise, the ChatGPT maker found a flaw in Brotli, a widely used data compression tool.
该公司表示，攻击者可以利用该漏洞发送恶意数据，从而在受影响系统上运行自己的代码，包括使用Node.js、Bun和Envoy等流行网络软件的系统。
The company said attackers could exploit the flaw by sending malicious data that lets them run their own code on affected systems, including those using popular web software such as Node.js, Bun and Envoy.
OpenAI表示，根本原因已于2月在Brotli的源代码中修复，当时尚不知道它会构成安全漏洞，但当时并未发布新版本。在OpenAI披露该漏洞后，Brotli已发布了更新版本并公布了该漏洞的公开记录。
OpenAI said the root cause was fixed in Brotli’s source code in February, before it was known to create a security vulnerability, but no new version was released at the time. Brotli has since released updated versions and published a public record of the flaw after OpenAI disclosed it.
另外，10月22日，AI安全评估机构METR和Redwood Research表示，他们在2026年早些时候的一次试点审查中发现OpenAI内部系统存在若干新漏洞，包括智能体可能利用的一个漏洞，使其能够避免数百次操作被监控。OpenAI告诉这两家安全机构，此后已修补了影响其生产防护措施的所有漏洞，但METR和Redwood表示他们尚未核实这些修复。
Separately on Oct 22 AI safety evaluators METR and Redwood Research said they found several new vulnerabilities in OpenAI’s internal system including an exploit agents could have used to keep hundreds of their actions from being monitored, in a pilot review earlier in 2026 OpenAI told the safety organisations it has since patched all vulnerabilities affecting its production safeguards, although METR and Redwood said they had not verified the fixes.
OpenAI 自七月的 Hugging Face 事件以来，一直在对其人工智能模型的活动进行广泛审查，并已向超过 100 家组织通报了与其 AI 代理相关的未经授权活动事件。
OpenAI has been conducting a broad review of its AI models’ activity since the Hugging Face incident in July and has informed more than 100 organisations about incidents of unauthorised activity tied to its AI agents.