TechCrunch
@TechCrunch
Technology news and analysis with a focus on founders and startup teams. Got a tip?
가입 March 2007
459 팔로잉 중 10.8M 팬
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.
더 보기
