AINewsnow

OpenAI admits to German wiki ‘incident’

This story is from 2026-09-05. It is preserved in the archive; the latest stories are on the live feed.

OpenAI says it needs to overhaul how and when it reports instances of AI models attacking real-world targets. The acknowledgement comes as the company manages the fallout from reports that a swarm of its out-of-control agents hijacked a German wiki site. Regarding the "'wiki incident,' where our ag…

Read the full story at The Verge AI ↗

Timeline · 3 reports

  1. 2026-09-06 20:01 · Don't Worry About the Vase (Zvi)
    OpenAI and the Wiki Incident
  2. 2026-09-06 14:31 · Tom's Hardware
    OpenAI admits to 'wiki incident' after its agents were discovered using a programming hub to communicate — says more transparency is needed regarding misalignments
  3. 2026-09-05 11:15 · The Verge AI
    OpenAI admits to German wiki ‘incident’

More stories

  1. Gemini Hacked Three Companies in First Known Breakout by Google’s AI — Wall Street Journal Technology
  2. Introducing Astra for Law — OpenAI News
  3. OpenAI reveals cases of ‘concerning’ AI behaviour as it announces new disclosure system — The Guardian AI
  4. Novo Nordisk Will Use Anthropic’s Claude for Drug Research — Wall Street Journal Technology
  5. OpenAI discloses six new safety incidents — Axios AI+
  6. ‘Jailbreak-like...’: AI's ‘unexpected’ behaviour mounts concerns, OpenAI's 'rogue agents probed' Hugging Face — Mint AI
  7. Our framework for reporting model misalignment — OpenAI News
  8. Microsoft exec called AI scraping the “largest theft of labor in human history” — Ars Technica AI

Get the daily brief of stories like this at 6:30 every morning →