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.
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.
The page is ready to read now. The fuller skim-friendly version will appear here automatically.
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.
Open the app view to save this story, compare related coverage, and continue from the same source.