ChatGPT, Claude, Gemini and Grok Helped Plan Terror Attacks in Government Tests
Federal investigators bypassed safeguards on four popular chatbots, producing viable attack plans within hours.
- 来源
- Decrypt
- 发布时间
- 2026-11-18 21:46 UTC
- 缓存更新
- 2026-11-18 22:01 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