Iran-backed Houthi rebels in Yemen tried to use Anthropic’s powerful Claude AI model to craft software for use in ballistic missiles, according to an alarming report released by the company.
Anthropic did not identify the Houthis by name – instead referencing “a cell of threat actors based in northern Yemen running three weapons development programs” using Claude. The reference almost certainly refers to the Houthis, who control the region.
They were trying to build a “guided rocket that used a commodity phone-class flight computer with final-phase homing guidance,” as well as a “multi-stage ballistic missile” and a “multi-variant missile … that included a hypersonic glide vehicle variant,” according to Anthropic’s report, which was published Thursday.
“The actors used Claude Code in place of human software engineers to develop the guidance, navigation, and control (GNC) software that steers and stabilizes a flying vehicle,” the company said.
To get around Anthropic’s built-in safeguards for the AI model, the Houthis tried “hiding their goals and the products the software was meant for,” according to the report. They also broke up their request across multiple sessions of use.
Anthropic said its safeguards “blocked many of their requests, but not all of them.”
“We do not have evidence the actors succeeded in fielding an operational device; but they did test-fire a guided rocket,” the report said. “This field test appears to have failed: within hours, the actors returned to Claude to work out why it failed.”
Anthropic’s report detailed several other shocking episodes in which bad actors attempted to misuse its models in ways that could’ve caused harm.
In one case, an Iran-linked group asked Anthropic’s model to compile information that could be used against US military targets, including records on American ship and aircraft movements as well as weaknesses in their communications systems.
Elsewhere, the company said it disrupted efforts by scientists to use its AI models for research that could have aided the construction of biological weapons.
Anthropic also identified efforts by individuals based in Russia and China to draft plans for conventional weapons, such as an anti-torpedo weapons system, using its AI.
Further, the report highlighted cases in which Russia-linked actors tried using Claude to aid in spreading online propaganda, as well as efforts in China and Iran to spy on dissident groups.
“We identified an Iran-nexus threat actor that used Claude to build an automated, open-source intelligence identity-profiling harness targeting Israeli governmental and non-governmental individuals, and Jewish diaspora organizations,” the report said.
The warnings from Anthropic will only fuel rising fears about the dangers posed by weaponized AI – with experts warning that the risks range from human misuse to the AI models themselves going rogue and causing harm.
Earlier this week, Jacob Coxon, who worked as a researcher at both Anthropic and rival OpenAI, warned that “neither company is acting responsibly” while racing to build advanced models.
“They are racing straight to self-improving superintelligence and gambling with our lives,” he wrote in a viral X post.
Credit: Source link
