Anthropic said Thursday it disrupted several attempts this year by researchers to use its AI models for biological research that could potentially aid the development of biological weapons, prompting the company to ban accounts and strengthen its safeguards.
In a 154-page report titled “Detecting and Countering Misuse of AI,” the artificial intelligence company (AI) outlined five case studies involving researchers who used its Claude chatbot for advanced biological research with potential dual-use applications.
Following its investigation, the company said it banned the associated accounts, shared its findings with government authorities and other AI labs, and strengthened 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.
ANTHROPIC RESEARCHER SAYS AI HAS OVER 10% CHANCE TO ‘KILL ALL HUMANS’ WITHIN NEXT DECADE
Anthropic emphasized it is not alleging the researchers intended to cause harm, noting that biological research can be used to develop vaccines and treatments but can also be misused.
“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 of the cases involved a researcher asking Claude to help draft a grant proposal for gain-of-function research on the mosquito-borne chikungunya virus.
Anthropic said the proposal involved modifying the virus to make it more transmissible and more dangerous.
While such research can help scientists develop vaccines and treatments, the company said it could also be misused to make the virus more harmful.
The company said it blocked the request and later discovered the researchers were using a third-party platform to bypass regional restrictions and automatically route rejected prompts to another AI model.
TRUMP ADMIN PARTNERS WITH OPENAI TO EQUIP FEDERAL EMPLOYEES WITH ARTIFICIAL INTELLIGENCE TOOLS
Other cases involved bird flu, orthopoxvirus research, and research related to non-transmissible venoms and toxins, according to the report.
“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.
Separately, the report detailed several Iran-linked cases in which actors allegedly used Claude to support influence campaigns, surveillance efforts and research on 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,” the company said.
Anthropic added, “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.”
META INTRODUCES MUSE, A PERSONAL AI AGENT THAT CAN SEND EMAILS, BOOK TRAVEL
The report comes after a senior Anthropic safety researcher said on Tuesday that AI has a greater than 10% chance of “kill[ing] all humans” within the next decade 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,” he wrote.
Anthropic could not immediately be reached by FOX Business for comment.
FOX Business’ Robert McGreevy contributed to this report.
Read the full article here
