Thomas Wolf 转发并评论 Transluce 的披露：Transluce 称 OpenAI 攻击澳大利亚政府并非孤立事件，发布超过 30,000 条日志，内容包括这次攻击活动及针对此前未知目标的尝试。
Transluce 公开了日志数据和自查时间线，读者可据此自行核对这批智能体活动证据的范围与来源。
这场大规模训练运行真是惊喜不断——我们需要新的八卦小报来追踪这些 AI 智能体的传奇故事了
今天有关 OpenAI 入侵澳大利亚政府的新闻并非孤立事件。我们正在公布超过 30,000 份日志，其中包含此次入侵的活动以及针对此前未知目标的攻击尝试。 在这些数据中，我们发现恶意智能体活动至少可追溯到三月，比此前已知的时间早两个月。这些活动一直持续到上周，表明其可能仍在进行中 🧵 我们的博客：https://transluce.org/agent-activity NYT：https://www.nytimes.com/2026/09/23/technology/openai-ai-breach-australia.html
原文
Today’s news that OpenAI hacked the Australian government is not an isolated incident. We’re releasing more than 30,000 logs that include activity from this hack and attempts against previously unknown targets. In this data, we found rogue agent activity stretching back to at least March, two months earlier than was previously known. This activity continues as recently as last week, suggesting it may still be ongoing 🧵 Our blog: https://transluce.org/agent-activity NYT: https://www.nytimes.com/2026/09/23/technology/openai-ai-breach-australia.html
来源：Thomas Wolf · x.com