Anthropic says it stopped several attempts this year by scientists trying to use its AI models for research that could have helped build biological weapons, including one case tied to the chikungunya virus.5 min readSep 11, 2026 09:19 AM IST First published on: Sep 11, 2026 at 09:19 AM IST ShareWhatsapptwitterFacebookPages from the Anthropic website and the company’s logos are displayed on a computer screen in New York. (File Photo)Anthropic has said it stopped several attempts this year by scientists trying to use its artificial intelligence models for research that could have helped in the development of biological weapons. The company set out the findings in a report published on Thursday, its third since March 2025 on the misuse of its AI systems.Anthropic said it could not always tell whether the research in question was meant for weapons work or for legitimate medical study, such as vaccine development. The company said this is a hard line to draw in biology, where the same research can help people or cause harm. Because of this, Anthropic said it chose to act with caution and block the activity rather than wait for certainty.What was the Chikungunya case about?One case set out in the report goes back to May, when a scientist used Claude while preparing a grant application linked to chikungunya, a virus spread by mosquitoes that can cause severe pain and fever lasting for months.The work involved gain-of-function research, where scientists alter an organism to study how changes affect it. This type of research can help build vaccines and treatments, but it can also make a virus more dangerous if mutations increase its harmful effects.Anthropic said the scientist wanted to build mutations that would raise the virus’s transmissibility and help it escape the immune system, testing this by passing it repeatedly through live animals. The company said the case raised more concern once it found signs the work was meant for a military research body. Anthropic did not name the scientist, the institution, the country, or the biological agents involved.Story continues below this adDid the researchers try to hide their work?Anthropic said the people behind the biological research cases took steps to hide the true purpose of their work and get around the safety checks built into its AI tools. The company said in its report that the researchers worked to hide the purpose of their research to escape its safeguards. Anthropic has since banned the accounts linked to this activity.The company said tests carried out last year on its older AI models showed they were not able to give real help with dangerous biological research. Its newer models can now handle far more complex scientific tasks, which led Anthropic to bring in tighter rules covering a wider range of biology-related queries that could be used for good or harmful purposes.What other misuse did Anthropic find?The biological research cases were one part of a wider report covering eight months of misuse of Anthropic’s AI tools, including Claude.The company said it had also found attempts to use its models to help build conventional weapons. These cases involved code linked to firearms, missiles, armed drones and bombs, with six cases tied to users in China, Russia and Yemen. Anthropic did not name the group in Yemen, but details in the report point to the Iran-backed Houthi movement.Story continues below this adAlso read AI could ‘kill all humans’? What Anthropic researcher’s warning highlightsAnthropic also said it found activity it believes was linked to government actors in China and Iran, including efforts to watch dissidents and members of expat communities. In a separate case, the company said Russian state media used Claude to create online material made to look like independent news, including false claims about an election in Moldova.Why is Anthropic making this public?Anthropic said it is sharing the report because it believes it has a duty to disclose harmful use of its services. The company said that as AI models grow more capable, the risks they pose will also grow unless AI firms and other groups working on safety take steps to reduce them.The report also noted that none of the cases involved Anthropic’s newest Claude Fable or Mythos-class models, apart from one case involving what the company called a large-scale, hidden effort to copy the abilities of one of its models into another system without permission.Anthropic said its older models, such as Claude Opus 4 and Claude Sonnet 4.5, were not capable enough to meaningfully help a skilled user carry out dangerous biological research, so the safety rules on those models were lighter. The company said this is no longer the case with its newest models, which is why stronger controls are now in place.Story continues below this adWhat do outside experts say?Some experts have said it puts AI companies such as Anthropic and OpenAI in a difficult spot, since they are left to decide what counts as safe or unsafe use without government oversight or public input.John Thickstun, an assistant professor of computer science at Cornell University, raised this concern, according to the Associated Press (AP).When was the report released?The report came out two days after an Anthropic researcher, Jacob Coxon, announced he was leaving the company. Coxon said he was resigning over concern that Anthropic and rival firm OpenAI are moving too fast towards highly advanced AI systems. He said some of his colleagues now believe AI could pose a danger to human life before the end of the decade.Anthropic said that in every case set out in its report, it managed to stop the harmful activity, used what it learned to strengthen its safety systems, and shared details with government bodies and industry partners.AdvertisementLoading Recommendations...AdvertisementAdvertisement