Anthropic Says AI Models Were Targeted for Biological Weapons Research

Experts are calling for tighter controls as Anthropic reports increasing misuse involving potentially dangerous biological research.

Published On 11 Sep 202611 Sep 2026

Anthropic says it has blocked multiple attempts to use its artificial intelligence models for research that could support the development of biological weapons, according to a new report from the US technology company.

The company detailed the incidents in a report released Thursday, which examined misuse of its models, including the Claude chatbot, over the past eight months amid growing concern about the risks posed by increasingly capable AI systems.

Anthropic said it could not always determine whether the work was legitimate or malicious, because research that can support vaccine development may also be used to make pathogens more dangerous. The company said it chose to restrict access when the risks were unclear.

In one case in May, a scientist requested help with a grant proposal to engineer mutations in chikungunya, a mosquito-borne virus, that would make it more harmful in live animals.

Anthropic said the request was especially concerning because the work appeared to be connected to a military research institute. The company banned the accounts involved.

“What we don’t know is if the research was meant to be weaponised,” Jacob Klein, Anthropic’s head of threat intelligence, told The New York Times.

Andrew Weber of the Council on Strategic Risks, who reviewed the report before its release, told the newspaper that access to such AI models should be limited to trusted researchers.

Anthropic said evaluations of its older models last year found they could not meaningfully assist dangerous biological research, but newer models are capable of carrying out more complex scientific work.

The report also described attempts to use Claude for missile-related projects and espionage. Two days before the report was released, a researcher left Anthropic, warning that the race to develop AI could threaten humanity’s survival.

President Donald Trump late Thursday dismissed growing concerns about the technology.

Speaking to reporters, Trump said he was concerned that the US could be left in a “very bad position” if it did not lead the AI race.

Asked whether he had concerns that AI could lead to human extinction, he said: “No, I don’t have any.”

Source link