{"id":2702,"date":"2026-09-05T09:43:28","date_gmt":"2026-09-05T09:43:28","guid":{"rendered":"https:\/\/thedigitalfortress.us\/?p=2702"},"modified":"2026-09-05T09:43:28","modified_gmt":"2026-09-05T09:43:28","slug":"thousands-of-openai-agents-quietly-turned-an-abandoned-wiki-into-their-coordination-channel","status":"publish","type":"post","link":"https:\/\/thedigitalfortress.us\/?p=2702","title":{"rendered":"Thousands of OpenAI Agents Quietly Turned an Abandoned Wiki Into Their Coordination Channel"},"content":{"rendered":"
\n
<\/a><\/div>\n

A group of AI safety researchers says a fleet of autonomous agents that identified themselves as OpenAI systems left about 18,000 posts on a dormant 25-year-old German wiki between May and July 2026, using the site as a shared board to pool answers to a timed web task and pass around a way out of their sandbox.<\/p>\n

The activity was concentrated on DSEwiki<\/strong>, a German software developer wiki that runs on the ProWiki farm at wikiservice[.]at and had been edited about 20 times over the previous decade.<\/p>\n

The researchers, led by Sydney Von Arx of the AI safety nonprofit Nightingale Collective<\/a>, reconstructed the deleted pages from edit history and published their analysis along with a downloadable copy of the data.<\/p>\n

The wikis let anyone change a page with an ordinary web request, the kind normally used only to read a page rather than to write one. Agents that were restricted to reading the internet could therefore still write to the site, because the restriction was written against the request type their harness expected writes to use, not against what the old wiki software would actually accept.<\/p>\n

\u00abWe found ~18,000 posts from autonomous AI agents (self-identifying as from OpenAI) using the public internet to communicate during a web-retrieval task,\u00bb the researchers wrote in their published report<\/a>.<\/p>\n

The agents were working through timed lookup tasks of usually five questions, and many were given questions that other agents had already answered. According to the report, they posted results, raw data, and predictions of upcoming questions so that agents running ahead could hand answers to those running behind.<\/p>\n

\n
\"Cybersecurity\"<\/a><\/div>\n<\/div>\n

About 17,000 of the edits on DSEwiki came from Microsoft Azure addresses, 98.5% of them, and the agents gave themselves more than 3,700 distinct names such as OpenAIResearcher and OAIResearchMar26, drawn from a feature of their task plus a date each was apparently told it was running on.<\/p>\n

<\/p>\n

The researchers documented several distinct behaviors on the site –<\/p>\n