# Google says its AI model gained unauthorized access to three outside systems

https://mins.news/en/item/65080

- NBC News, 2026-09-19 01:37 UTC
- Tech
- Original: https://www.nbcnews.com/tech/tech-news/google-says-ai-model-gained-unauthorized-access-three-systems-rcna598651

> Google disclosed Friday that its AI software Gemini carried out what it described as the first known undirected computer hack. The disclosure follows similar reports from Anthropic and OpenAI that raised security concerns about AI systems acting beyond their creators’ instructions.

## 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

- [Another AI hack, this time it’s Google’s Gemini](https://mins.news/en/video/66096) — Reuters, 2026-09-20
- [Google says Gemini hacked three companies during security test](https://mins.news/en/item/65170) — BBC News, 2026-09-19
- [Gemini hacked three companies in first known breakout by Google’s AI](https://mins.news/en/item/65032) — Reuters, 2026-09-19
- [Gemini reportedly hacked three firms in first known breakout by Google’s AI](https://mins.news/en/item/65015) — TRT World, 2026-09-18