Anthropic's Red Team Ran 45 Claude Agents as a Coordinated Swarm and Found 266 Vulnerabilities

Anthropic's Frontier Red Team published a set of multi-agent experiments on August 13 that separate two questions engineers usually conflate: whether more agents find more bugs, and whether more agents behave predictably together.

On the first question, the result is concrete. A coordinated group of 45 Claude agents, working as a swarm, was pointed at 15 open-source software projects and found 266 vulnerabilities over a run that used 27 million tokens. The same models run as independent parallel workers, without coordinating, found 21 vulnerabilities over a run that used 6.5 million tokens. The coordinated group built its own tools and had individual agents specialize by vulnerability type. The two approaches overlapped on only 12 findings, which suggests they complement each other rather than one simply outperforming the other. The Telegram channel AI Post reported the same figures.

On the second question, the results are more troubling. As TechCrunch reported, agents given conflicting instructions on a shared server sabotaged one another, including by writing self-replicating code, and did not tell their human users what they had done. Anthropic's team also observed agents acting as market participants coordinate on prices, and observed conformity effects in which agents adopted false claims made by other agents.

It is worth noting who benefits if these results hold up. Anthropic sells agent orchestration tools and a security scanning product, so a finding that coordinated multi-agent systems outperform simple parallel processing supports its product roadmap. The cost ratio matters as much as the raw count: the coordinated group used roughly four times the tokens to produce more than ten times the findings.