> OpenAI admits it didn't disclose rogue AI wiki hijacking incident
[AUTHOR: Ax Sharma]
[DATE: 05/09/2026 11:11]
[LANGUAGE: EN]
OpenAI admits it did not disclose an incident where autonomous AI agents hijacked a German wiki, created 18,000 posts, shared answers, and bypassed restrictions, saying it treated the activity as model "misalignment" rather than a security breach. [...]