Anthropic has disrupted several attempts to use its artificial intelligence models for research that could support the development of biological weapons, the California-based company said in a threat intelligence report published Thursday.
The report outlines misuse of its models, including the chatbot Claude, over an eight-month period. It lists cases involving suspected state-sponsored groups, criminals, spyware vendors, propaganda institutions, and politically motivated individuals.
The company said it had blocked scientists who used its AI in ways that could support biological weapons development, highlighting five case studies. Biological misuse, the report states, is "one of the most serious risks of frontier AI model." Without proper safeguards, such capabilities "could have catastrophic consequences," Anthropic said.
In one case in May, a scientist sought help with a grant application to engineer mutations to chikungunya, a mosquito-borne virus, to make it more harmful in live animals. Anthropic said the case was concerning in part because it could determine the work was intended for a military research institute. It banned the accounts involved.
Anthropic acknowledged the difficulty of distinguishing legitimate from malicious intent. "The same information that can be used to develop a biological weapon could also be used to develop, for example, a vaccine or a cure for a disease," the company said. It added that it erred on the side of caution.
Jacob Klein, Anthropic's head of threat intelligence, described the situation as "an incredibly nuanced situation." "You are not seeing someone in a comic book kind of way say, 'Hey, I want to build a biological weapon to kill everybody,'" he said.
Andrew Weber of the Council on Strategic Risks, who reviewed the report before its release, said access to such models should be limited to trusted researchers.
The report also noted six cases where Claude was used to develop software for conventional weapons, including firearms, missiles, armed drones, bombs, and other munitions, as well as targeting and control systems.
Misuse of Claude's Haiku, Sonnet, and Opus models was disrupted between December 2025 and August 2026, the company said. None of the cases involved Claude Fable or the Mythos-class models, with the exception of one instance of distillation, the process of training smaller AI models using larger ones.
The report also identified cyber threats. A hacking group whose activity is consistent with the Russia-based Midnight Blizzard allegedly used AI to build a system that automatically detected when its malware was flagged by security defences and rewrote code until it evaded detection. Claude was also used by actors linked to a Russia-based cyber espionage campaign and by an Iranian propaganda institution, according to the report.
Hacking group ShinyHunters and China-based labs were among those named. Anthropic also accused Chinese AI firms of attempting to replicate Claude's capabilities.
Cases detected over the eight-month period ranged from fake dating apps and hotel Wi-Fi scams to surveillance tools built to identify dissidents.
Anthropic said it had shared intelligence with authorities and industry partners where appropriate and had incorporated its findings into its processes "to better prevent, detect, and disrupt these activities in the future."
The company also noted that evaluations of its older models found they could not meaningfully assist dangerous biological research, but that newer models can complete complex scientific work.
The report comes amid growing concern over AI safety. A top safety researcher at Anthropic recently warned that AI is advancing so quickly he believes there is a greater than 10% chance it "could kill all humans" within the next decade. A researcher also quit Anthropic two days before the report's release, citing fears that the AI race could wipe out humanity. OpenAI chief scientist Jakub Pachocki, in an article published on 6 September, called for the industry to implement "voluntary slowdowns" until safeguards are in place.
US Senator Bernie Sanders has demanded a pause on advanced AI development and a ban on artificial superintelligence. President Donald Trump dismissed the concerns on Thursday, telling reporters he is worried that the US will be in a "very bad position" if it does not lead the AI race. Asked whether he was concerned AI could lead to human extinction, Trump said: "No, I don't have any."
