Houthi-Linked Cell Used Claude AI For Missile Guidance

A Yemen-based weapons engineering cell with ties to the Houthi movement has been identified as using the Claude AI model to develop guidance software for missiles and a guided rocket, according to a threat intelligence report published by Anthropic.

The report details how the group used Claude to integrate an open-source autopilot system with a phone-class flight computer and to develop software needed to control and stabilize a flying vehicle. This included writing control and position-estimation software, tuning control settings, running firmware builds, and conducting flight simulations.

The Yemen-based group was working on multiple missile programs simultaneously, including a multi-stage ballistic missile with a stated range of more than 2,000 kilometers and a missile system known as the 'R2000' set, which included a hypersonic glide vehicle variant.

Anthropic said the group used Claude Code 'in place of human software engineers' to develop guidance, navigation, and control software for flying vehicles. While the company said it found no evidence that the group had successfully fielded an operational weapon, it noted that the actors did carry out a test launch of a guided rocket, which appeared to fail.

The report also highlights the group's evasion tactics, including concealing the purpose of their work and splitting activities across multiple sessions to prevent any single interaction from revealing the scope of the wider weapons program.

After the guided rocket test failed, the actors returned to Claude within hours to investigate what had gone wrong. Anthropic said it has since banned the accounts linked to the operation and shared information about the case with public- and private-sector partners.

The report notes that the group had already built an offline simulation toolkit that did not depend on Claude or engineering software such as MATLAB - suggesting the operation had some capability to continue its work independently of the AI model.

This incident raises concerns about the potential misuse of AI technology in the development of conventional weapons. Anthropic's report highlights the need for continued vigilance and cooperation between private companies and public-sector partners to prevent the misuse of AI technology.

The use of AI in weapons development is a growing concern, and this incident highlights the need for increased scrutiny and regulation of the use of AI in this field.

In conclusion, the use of Claude AI by a Houthi-linked cell to develop guidance software for missiles and a guided rocket is a significant concern, and Anthropic's report provides valuable insights into the potential misuse of AI technology in the development of conventional weapons.