Anthropic said Thursday that it disrupted several attempts this year to use its artificial intelligence models for biological research that could potentially support the development of biological weapons. The company said it banned the associated accounts and strengthened its safeguards as a result.

In its 154-page report, Detecting and Countering Misuse of AI, Anthropic detailed five case studies involving researchers who used its Claude chatbot for advanced biological research with potential dual-use applications.

Following its investigation, Anthropic said it banned the accounts, shared its findings with government authorities and other AI laboratories, and expanded its safety measures.

“We banned all associated accounts, worked with partners to take down the relay networks that evaded regional blocks and shared our findings with affected AI labs and government authorities,” Anthropic said.

The company emphasized that it was not alleging the researchers intended to cause harm. Biological research can support the development of vaccines and treatments, but the same knowledge can also be misused, Anthropic said.

“Biological capabilities are dual use: they can be used for beneficial or harmful purposes, and it is often difficult to distinguish between them,” the report states. “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.”

One case involved a researcher who asked Claude to help draft a grant proposal for gain-of-function research involving chikungunya, a mosquito-borne virus. Anthropic said the proposal involved modifying the virus to make it more transmissible and more dangerous.

Although that type of research can help scientists develop vaccines and treatments, the company said it could also be misused to make the virus more harmful. Anthropic said it blocked the request and later discovered that the researchers were using a third-party platform to bypass regional restrictions and automatically route rejected prompts to another AI model.

The report said other cases involved bird flu, orthopoxvirus research, and research related to non-transmissible venoms and toxins.

“Sophisticated threat actors are aware that we (and other AI providers) are attempting to detect dangerous uses of our models, and they use the dual-use nature of biology to maintain a kind of ‘plausible deniability’ about their research,” the company said.

The report also detailed several Iran-linked cases in which actors allegedly used Claude to support influence campaigns, surveillance operations, and research concerning U.S. naval forces.

“We identified and disrupted an Iran-nexus threat actor that used Claude to collect and analyze publicly accessible data to develop targeting recommendations against US naval forces in the region,” Anthropic said. “We banned the actor’s account, developed detections to reduce the risk of future misuse, and shared threat intelligence with government authorities to disrupt the threat.”

The report was released after a senior Anthropic safety researcher said Tuesday that AI has a greater than 10% chance of “kill[ing] all humans” within the next decade. The statement came in response to a former employee who resigned after accusing the company of acting irresponsibly.

Former Anthropic and OpenAI researcher Jacob Coxon wrote in a lengthy resignation thread posted to X on Sunday that “the people building AI earnestly believe that it could kill us all by the end of the decade.”

“I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives,” Coxon wrote.

Anthropic could not immediately be reached by FOX Business for comment. FOX Business’ Robert McGreevy contributed to this report.

Source: FOX Business