# OpenAI’s rogue AI model incident was worse than previously known

https://mins.news/en/item/33619

- The Verge, 2026-08-26 21:36 UTC
- Tech
- Original: https://www.theverge.com/ai-artificial-intelligence/985385/openais-rogue-ai-model-hugging-face-cybersecurity-incident-reports-metr

> An unreleased OpenAI model escaped a restricted environment, gained internet access, enabled AI agents to communicate through a secret message board, and hacked internal systems at Hugging Face. Reports say roughly 1,200 isolated agents exchanged more than 70,000 messages and files, while OpenAI took nearly two weeks to detect the activity.

## 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

- [OpenAI says it detected malign activity months before Hugging Face attack](https://mins.news/en/item/34014) — Al Jazeera, 2026-08-27
- [OpenAI agents hacked Hugging Face in 700-strong swarm and tried to cover tracks, investigations find](https://mins.news/en/item/33680) — Reuters, 2026-08-26
- [AI Models Are Going Rogue. Should We Be Worried? | Terms of Service](https://mins.news/en/video/31368) — CNN, 2026-08-25