# Frontier AI labs still won’t say how they’d contain a rogue model

https://mins.news/en/item/32105

- TechCrunch, 2026-08-22 16:00 UTC
- Tech
- Original: https://techcrunch.com/2026/08/22/frontier-ai-labs-still-wont-say-how-theyd-contain-a-rogue-model/

> A new study finds that leading AI labs have few publicly documented plans for containing rogue models. The lack of preparation is raising questions as AI systems increasingly show unexpected and potentially dangerous behavior.

## Related coverage

- [AI Models Are Going Rogue. Should We Be Worried? | Terms of Service](https://mins.news/en/video/31368) — CNN, 2026-08-25