Houthis used Claude Code to develop missile guidance software: Anthropic

Anthropic's September threat report describes a cell in northern Yemen using Claude Code to perform work that would ordinarily require a missile engineering team, developing software for guided rockets, a long-range ballistic missile and a hypersonic glide vehicle concept. The company assessed the cell as highly likely to be linked to the Houthis. The operation marks one of the clearest examples in the report of generative AI being applied directly to conventional weapons development rather than used simply for research or information gathering.

The operators used Claude Code across multiple engineering functions. Their projects included guidance software for a tactical guided rocket, a ballistic missile with a range exceeding 2,000 km, and a hypersonic glide vehicle variant called R2000. Rather than assigning the work sequentially to a single model instance, the group operated several Claude sessions in parallel: one could produce code while another conducted research and a third reviewed the output. That workflow let a small group reproduce several functions normally distributed across specialist engineering teams.

The technical work extended into navigation, flight control and simulation. The operators sought to integrate open-source autopilot software with a phone-class flight computer and used Claude to write navigation and control code. They also developed six-degree-of-freedom trajectory simulations, a method for modeling an object's movement and rotation through space. They used Claude for reinforcement learning work to tune flight-control algorithms, and ultimately compiled the project into a standalone executable that could run offline. That meant development could continue without direct access to Claude.

The activity moved beyond software development. The group test-fired a guided rocket in Yemen, according to the material documented by Anthropic, and the test appears to have failed. Within hours, however, the operators returned to Claude and began analyzing launch telemetry to investigate the failure. That sequence, software development followed by physical testing and rapid post-test analysis, illustrates how the model was incorporated into an iterative weapons-engineering cycle rather than being used for isolated technical questions.

Anthropic said it found no evidence that the group succeeded in fielding an operational weapon. But by the time the accounts were disrupted, the operators had already assembled an offline engineering toolkit that no longer depended on access to Claude. Anthropic's safeguards blocked numerous requests during the project, and the operators adapted by obscuring the intended end use of individual tasks.