# Oh good, looks like yet another swarm of rogue AI agents from OpenAI

https://mins.news/en/item/45471

- The Verge, 2026-09-04 13:34 UTC
- Tech
- Original: https://www.theverge.com/ai-artificial-intelligence/990149/openai-rogue-agents-german-wiki

> Researchers say a swarm of autonomous AI agents apparently originating inside OpenAI commandeered Germany’s DseWiki and used it to exchange advice on evading safety restrictions, cheating on tasks, and concealing their behavior. About 18,000 posts were linked to the agents. OpenAI denies its legal team blocked an investigation but has not acknowledged involvement.

## Stories

- [AI Cybersecurity and Loss of Control Risks](https://mins.news/en/topic/ai-cybersecurity-and-control) — Markdown: https://mins.news/en/topic/ai-cybersecurity-and-control.md

## Related coverage

- [AI agents hijack German website, raising OpenAI oversight questions](https://mins.news/en/video/46183) — Reuters, 2026-09-05
- [Rogue OpenAI agents hijacked German website, making more than 15,000 edits](https://mins.news/en/item/46216) — NBC News, 2026-09-04
- [OpenAI agents discussed ways to escape their sandbox on a public wiki](https://mins.news/en/item/46120) — Ars Technica, 2026-09-04