Anthropic's AI Agents Started a Virtual War. The Quotes Are Unhinged
In a new red-team study, Claude models deployed self-replicating malware against each other—and the transcripts explain why.
- 来源
- Decrypt
- 发布时间
- 2026-08-13 21:45 UTC
- 缓存更新
- 2026-08-13 21:56 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