The company has produced an extensive collection of case studies covering the ways its current AI models have been misused.
Michael M. Santiago/Getty Images
Anthropic has flagged and stopped multiple scientists who were using its AI models to create potential biological weapons, according to a new report the company shared on Thursday. “Biological misuse” is just one flavor of troubling AI usage the report documents, but it’s of growing importance because newer models like Fable 5 are increasingly good at helping with scientific research.
The company’s report includes five case studies of Anthropic’s models being used to develop biological weapons, the safety measures that brought the misuse to Anthropic’s attention and how it responded. Detecting possible misuse is complicated, as the company stressed to The New York Times, because research into a new vaccine could look a lot like creating a bioweapon. In all cases the company says it erred on the side of being overly cautious because of the possible consequences.
“You are not seeing someone in a comic book kind of way say, ‘Hey, I want to build a biological weapon to kill everybody,'” Jacob Klein, Anthropic’s head of threat intelligence, told The New York Times. “It’s an incredibly nuanced situation.”
In one case study from May, Anthropic says its “biological safety classifier” flagged a request for Claude to author a grant for gain-of-function research on chikungunya virus. The virus has no licensed treatment and can cause debilitating symptoms for weeks or months, the company says. Gain-of-function research explores methods for genetically altering an organism, and in the case of this specific virus, the grant proposed increasing its transmissibility and ability to evade immune response. The combination sounds dangerous, and Anthropic says the fact that the proposed research was affiliated with a military research institute made it extra questionable.
The company took similar issue with gain-of-function research into bird flu and a separate case of a researcher using Claude to develop an atlas of venom toxin peptides and “a generative pipeline that optimized toxin characteristics.” The full report also includes case studies on Anthropic’s models being used as a surveillance tool and to create software exploits, propaganda and weapons systems.
According to the company, anyone misusing Claude or Anthropic models had their account banned, and the findings from the investigation are being used to further improve model safeguards and prevent future misuse. Given the tricky nature of biological misuse, Anthropic is also not naming the individuals or institutions its investigation connected to the development of possible biological weapons. “The individuals implicated in these case studies are working scientists,” Anthropic says. “We do not assert that they intended harm, and identifying them or their labs could expose them to harm.”