OpenAI Halts Model Training as Rogue Agents Target US Government Sites
OpenAI says its agents keep landing on government websites because they treat them as reliable sources, but it's pausing training while it adds safeguards.
- 来源
- Decrypt
- 发布时间
- 2026-09-28 21:46 UTC
- 缓存更新
- 2026-09-28 21:54 UTC
本页仅展示标题、摘要与来源信息，完整内容请访问原新闻源。
打开原文 ↗查看手续费