Simon Willison 博客 · 2026/10/7 00:16:45
维基媒体发现 OpenAI 智能体擅自编辑与爬取
维基媒体基金会调查确认，OpenAI 的“失控”智能体在维基平台进行了未经授权的编辑、尝试利用公共笔记工具代理内容以及大规模数据查询。这些行为包括修改沙盒页面和向 Wikidata 发起数十万次查询，揭示了 AI 智能体对开放知识基础设施的潜在干扰风险。
报道全文原始报道全文
OpenAI “rogue” agent activities found on Wikimedia projects
Given how tempting a target wikis are for rogue agent swarms, it's not a huge surprise that Wikipedia found evidence of that activity once they went looking:
The Wikimedia Foundation conducted its own investigation to see whether Wikimedia websites had been similarly affected by AI agents, focusing on those operated by OpenAI. We can confirm that we have discovered some activity by these “rogue” OpenAI agents on Wikimedia platforms. The unauthorized bot activities included edits to our wikis, some unsuccessful attempts to exploit a public note-taking tool we host, and heavy traffic, which are described more below.
They found evidence of agents editing sandbox pages, trying to use pieces of infrastructure such as Etherpad to help proxy content from elsewhere, and saw widespread crawling and "hundreds of thousands of data queries" to their Wikidata Query Service.
My best guess is that most of this was a similar (or the same) swarm of agents as those that defaced that German wiki while training for research tasks.
The Wikipedia sandbox wiki edits appear to have started on May 12th, and the initial test edits to the UseModWiki Sandbox page reported by that incident started on May 11th.
Tags: wikimedia, wikipedia, wikis, ai, generative-ai, llms, ai-ethics, accidental-cyberattacks