Anthropic Says Houthi Cell Used Claude Instead of Engineers to Build Self-Correcting Rockets and Missiles
Claude in place of engineers
A cell based in Houthi-controlled northern Yemen used Anthropic's Claude Code in place of human software engineers to develop guidance, navigation and control software for rockets and missiles, according to an Anthropic threat intelligence report covered by the Washington Post and the Associated Press. The software steers and stabilizes a flying vehicle, work that normally requires a trained aerospace engineering team.
Anthropic said the actors were running three weapons programs in parallel: a guided rocket using a commodity, phone-class flight computer with final-phase homing guidance; a multi-stage ballistic missile with a stated range goal of more than 1,500 miles; and a multi-variant missile referred to as the R2000, which included a hypersonic glide vehicle variant.
A test firing, a failure, and a debugging session
"Our safeguards blocked many of their requests, but not all of them," Anthropic wrote. "They used a variety of tactics to evade our safeguards and split their work across multiple sessions." Claude provided position estimation software, tuned control settings and ran a firmware build pipeline, and after warheads missed their targets, the operators used it to adapt and improve accuracy.
"We do not have evidence the actors succeeded in fielding an operational device; but they did test-fire a guided rocket," Anthropic wrote. The field test appears to have failed, and within hours the actors returned to Claude to work out why. The company also found evidence the group had already built an offline simulation toolkit that does not rely on Claude or tools like MATLAB, meaning the skills transferred even after accounts were cut off. Anthropic banned the accounts and shared information with government authorities and industry partners.
Why it matters beyond Yemen
The report, published in September, is the clearest documentation yet of a non-state armed group inserting a commercial AI coding tool directly into a weapons development loop, including live test feedback. It lands as Washington debates export controls and model safeguards, and as U.S. officials express shock at the range and accuracy of recent Houthi attacks on Saudi targets.
Do you want to see how to make more plays? Do you want to find gains yourself? Unusual Whales helps you find market opportunities through our market tide, historical options flow, GEX, and much, much more. Create a free account here to start conquering the market with Unusual Whales
How this could hit the options market
Anthropic is private, so the trade runs through its backers and the defense complex. GOOGL and AMZN are Anthropic's largest investors and cloud partners, and misuse headlines tend to pull AI policy risk into their multiples. The operational read-across is to missile defense and guidance suppliers like LMT, RTX and NOC: if AI compresses the engineering timeline for groups like the Houthis, interceptor demand is the hedge traders reach for first.
To track how stories like this move positioning, Sign up for Unusual Whales and follow the flow yourself.