Anthropic says it has disrupted several suspected efforts this year to use its artificial intelligence tools in research that could support the development of biological weapons.
The AI company concluded that scientists had been using its platforms for work with potential biological weapons applications, according to an AI misuse report obtained by The New York Times.
In the report, Anthropic said it could not determine whether the research “served a legitimate or nefarious purpose.”
The company acknowledged that legitimate biological research can lead to major medical advances, including vaccines. But it said it chose to act cautiously because similar lines of inquiry could also be misused to engineer harmful pathogens.
According to Anthropic, the scientists involved allegedly bypassed restrictions designed to prevent users in “blocked regions” from accessing its AI models.
The firm said the researchers, whose accounts have since been banned, attempted to “obfuscate the purpose of their research to evade our safeguards.”
Anthropic, co-founded by chief executive Dario Amodei, did not identify the researchers or institutions it blocked, nor did it name the countries where the scientists were based.
The report also did not specify which biological agents were involved. The company said that omission was due in part to uncertainty about the true objective of the research, according to the newspaper.
Dario Amodei, co-founder and chief executive officer of Anthropic
The report, which was published Thursday, detailed several misuses of Anthropic’s AI models, including chatbot Claude, over the past eight months.
In one example, a scientist asked Claude for assistance in writing a grant application for funding to conduct experimental research on the chikungunya virus, according to the report.
Chikungunya virus is a mosquito-borne illness that causes a sudden high fever, severe debilitating pain, and other symptoms.
A vaccine for the chikungunya virus is already in existence, according to the Centers for Disease Control and Prevention.
Anthropic notes that research on the virus could be legitimately used in vaccine development, but also could result in manufacturing a superbug version of the disease.
The company claims it found this case particularly worrisome because the work was going to be performed at a military research institute.
‘What we don’t know is if the research was meant to be weaponized,’ Jacob Klein, the head of threat intelligence at Anthropic, told The New York Times. ‘But a military institution doing gain-of-function research is concerning.’
‘The fact that Russia, China and North Korea continue to develop prohibited biological weapons makes it imperative that we deny their researchers access to these extraordinarily capable models,’ echoed Andrew Weber, a senior fellow on the Council on Strategic Risks.
Weber, who reviewed Anthropic’s report before its release, added that the findings were ‘chilling examples of state-sponsored biological weapons developers tapping into the rapidly advancing capabilities’ of AI.
The report also found that China, Russia and Yemen attempted to use Claude to develop software to design firearms, missiles, armed drones and bombs.
Suspected Chinese and Iranian government-actors were found to have been targeting dissident and diaspora communities for surveillance, according to the report.
Russian state media was also found to be using Claude to generate election propaganda, including fabricated claims the parliamentary election in Moldova.
This is a breaking news story.
