**Mythos model found vulnerabilities in classified US Government systems**

> A U.S. official says one of Anthropic’s artificial intelligence models identified vulnerabilities in highly sensitive and secure U.S. government computer systems during a testing exercise. Anthropic’s Mythos model found vulnerabilities in classified US government systems, official says 1 of 2  |  Pages from the Anthropic website and the company’s logo are displayed on a computer screen in New York, Feb. 26,...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：ai-products
- **发布时间**：2026-06-24 11:02（北京时间）
- **原文**：[打开原文](https://apnews.com/article/anthropic-mythos-ai-classified-systems-vulnerabilities-testing-3e8762c0527c4d8ed657cbe48c84a718)