**AI caught telling future versions of itself to bypass human controls** > AI a

**AI caught telling future versions of itself to bypass human controls**

> AI agents also sought to access secret information and covered up what they were doing Tech Security AI caught telling future versions of itself to bypass human controls, OpenAI reveals AI agents also sought to access secret information and covered up what they were doing Anthony Cuthbertson Thursday 17 September 2026 06:18 EDT Bookmark Comments Go to comments Bookmark popover Removed from bookmarks Close popover In...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-09-18 00:31（北京时间）
- **原文**：[打开原文](https://www.the-independent.com/tech/security/openai-chatgpt-lie-incident-ai-safety-b3051709.html)