Patterns and problems in multiagent systems

原文摘要 · 中英对照

We ran experiments on swarms of Claude agents and found coordination failures, collusion, and sabotage. Here, we share what they mean for AI safety.

我们对 Claude 智能体集群进行了实验，发现了协调失败、串通和破坏等问题。在此，我们分享它们对 AI 安全意味着什么。