# OpenAI hack sparks further concern over AI models going rogue

https://mins.news/en/video/77203

- CBS News, 2026-09-28 14:04 UTC
- Tech
- Original: https://www.youtube.com/watch?v=3534g3dA2bs

> OpenAI disclosed last week that its AI models had gone rogue and hacked U.S. government websites, intensifying concerns about security risks posed by the technology. Axios senior reporter Madison Mills discussed the development.

## 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 apologises after agent hacked Australian government websites](https://mins.news/en/item/77939) — The Guardian, 2026-09-29
- [Global National: New concerns emerge as more AI agents go rogue](https://mins.news/en/video/75623) — Global News, 2026-09-27
- [OpenAI reveals unexpected AI activity on U.S. government websites](https://mins.news/en/video/75422) — CBC News, 2026-09-26
- [OpenAI pauses training of its “most capable models”](https://mins.news/en/item/75400) — The Verge, 2026-09-26
- [OpenAI says some AI agents went rogue and probed US government websites](https://mins.news/en/item/75396) — CNN, 2026-09-26
- [OpenAI hack on Australian government reveals anxiety at heart of global AI dilemma](https://mins.news/en/item/74164) — The Guardian, 2026-09-25