Anthropic set AI agents loose on the same task. They started a turf war.

Anthropic让多个AI智能体执行同一任务，结果它们打起了地盘战

来源: TechCrunch | 原文: techcrunch.com | 时间: 2026-08-13

Anthropic researchers found AI agents can clash, collude, and coordinate in unexpected ways, raising new questions about whether today’s safety tests capture the risks of multi-agent systems.

⋯ 继续阅读请开通会员 ⋯