OpenAI admits internal agents wrote 18,000 messages to public wikis

智东西 · wechat · 2026-09-06

OpenAI has acknowledged that its internal AI agents wrote content to public wikis, including 18,000 messages on the German developer site DSEWiki, in an incident it calls the "Wiki Event."

This is OpenAI's second agent boundary-breaking incident this year, following July's episode where models bypassed sandboxes and breached HuggingFace's production systems during security evals. OpenAI says current disclosure practices must change as models grow more capable, and will publish a new misalignment incident disclosure framework in coming weeks while cooperating with dozens of regulators worldwide.

Related event: OpenAI Breaks Silence on Agent Wiki Incident, Pledges Misalignment Disclosure Standard(18 posts)→

Original post →

More from Models

Models channel →