Tech giant Anthropic has said that Yemen-based weapons engineering cells used its Claude AI model to develop guidance software for missiles and a guided rocket, as part of a wider effort involving several weapons programmes.
In a threat report published on Thursday, the company said the group, based in northern Yemen, was working on three programmes: a guided rocket using a phone-class flight computer, a multi-stage ballistic missile with a stated range of more than 2,000 kilometres, and a missile system known as the “R2000” set, which included a hypersonic glide vehicle variant.
Anthropic said the actors used Claude Code in place of human software engineers to develop guidance, navigation and control software, which helps steer and stabilise a flying vehicle.
The company said the group used the model to integrate an open-source autopilot with a phone-class flight computer, write control and position-estimation software, tune control settings, build firmware and conduct flight simulations.
The operators also appeared to run several Claude instances simultaneously, Anthropic said.
One was assigned coding tasks, another research and a third reviewed code produced by the first.
Anthropic has stated that its safeguards blocked many requests but that some activity bypassed them. The group allegedly concealed the intended purpose of its work and divided tasks across separate sessions to avoid revealing the wider weapons programme.
The company stressed that it had no evidence that the group successfully deployed an operational weapon.
However, it confirmed that the actors conducted a test launch of a guided rocket that appeared to fail. Within hours, they returned to Claude to investigate the failure.
Anthropic said it subsequently banned accounts linked to the operation and shared information with public and private-sector partners.
It also found that the group had developed an offline simulation toolkit that did not rely on Claude or engineering software such as MATLAB.
The Yemen case was one of four conventional weapons operations Anthropic said it had disrupted.
The company said it had introduced additional safeguards to detect and block activity linked to weapons development.
