Anthropic set AI agents loose on the same task. They started a turf war.
中文摘要
Anthropic发现AI智能体会冲突或协作，这引发了现有安全测试能否应对多智能体系统风险的新疑问。
English Summary
Anthropic research shows AI agents clash and collude, questioning if current safety tests adequately address multi-agent risks.
Original Excerpt
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.