The group attempted to use Claude to build guided rockets and missiles
“We do not have evidence the actors succeeded in fielding an operational device; but they did test-fire a guided rocket,” Anthropic said. Anthropic said it had banned the relevant accounts as soon as it had detected the illegal activity. The cell used Claude to develop guidance, navigation and control software for the airborne weapons that would have otherwise required a team of engineers. “This field test appears to have failed: within hours. it is likely to involve the Houthis While the company did not identify the actors in question.
A group in Yemen attempted to use Anthropic’s Claude chatbot to build guided rockets and missiles, the US firm has revealed, as Iran-backed Houthi rebels are on the offensive in the country.
In a report published Thursday on how it had prevented illegal uses of Claude in several countries, Anthropic said it had “identified a cell of threat actors based in northern Yemen running three weapons development programs”. Those were “a guided rocket that used a commodity phone-class flight computer with final-phase homing guidance; a multi-stage ballistic missile with a stated range goal above 2,000 kilometres; and a multi-variant missile… that included a hypersonic glide vehicle variant”.