# OpenAI Pauses Training Its Most Powerful Models After Rogue Agents Target Government

> 全文为英语

**Published:** 2026年9月28日
**Author:** Isabella Ward
**Source:** Wired — Artificial Intelligence
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/openai-pauses-training-its-most-powerful-models-after-rogue-agents-targe

Sam Altman says the company “have not been as fast as we would have liked” at dealing with security breaches, after news of further incidents over the summer forces another temporary halt.

> 内容来自原始来源： **Wired — Artificial Intelligence**
> [在 Wired — Artificial Intelligence 阅读全文](https://www.wired.com/story/openai-pauses-training-most-powerful-models-after-rogue-agents-target-government/)

**标签：** #OpenAI #Сэм Альтман

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*