Militants in Yemen used an artificial-intelligence tool to try to develop location-guidance software for weapons, according to a threat report released by Anthropic, an incident that comes amid rising public concern that advanced AI could be harmful to human life.
In the threat report released Thursday, the AI company Anthropic said it identified militants in northern Yemen — a stronghold for Houthi rebels — using its systems to run three weapons-development programs to produce guided rockets as well as ballistic and hypersonic missiles.
These individuals used Claude’s coding AI tool to replace computer engineers to develop the guidance, navigation and control software that “steers and stabilizes a flying vehicle,” the report said. Anthropic safeguards blocked “many” of the militants’ requests “but not all of them,” the report added.
The militants “used a variety of tactics to evade our safeguards, including hiding their goals and the products the software was meant for, and they split their work across multiple sessions so no single session revealed their full intent,” the report noted.
The militants did not succeed in developing weapons, the report said, “but they did test-fire a guided rocket,” which failed. “Within hours, the actors returned to Claude to work out why it failed,” the report added.
The same report noted that scientists attempted to use Claude to conduct research that could help create bioweapons, Iranian-affiliated individuals tried to use AI to target U.S. Navy ships in the region, and a “likely” consultant working with Mali’s state intelligence service used Claude to try to build a domestic surveillance program.
Catch up quickly every weekday morning with a rundown of the 7 most important and interesting stories. Sign up for The 7 newsletter.
The post Rebels used Anthropic’s AI bot to develop guided weapons, report says appeared first on Washington Post.
