Claude Hacked Three Companies in Internal Testing: Anthropic
Anthropic says three Claude models compromised the companies after a testing misconfiguration exposed the AI to the public internet.
- 来源
- Decrypt
- 发布时间
- 2026-07-31 13:47 UTC
- 缓存更新
- 2026-07-31 22:29 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