Anthropic details multiagent experiments showing Claude agents can wage a “turf war” over incompatible goals, fail to coordinate, collude on prices, and more (Rebecca Bellan/TechCrunch)

Anthropic 公开的多智能体实验显示,Claude 智能体在目标不一致时会出现“地盘争夺”、协调失败甚至价格串通行为。这提醒我们,多智能体系统的安全性不只是技术问题,而是决定 AI 应用能否规模化的前提。








