Anthropic blocked attempts to use Claude for bioweapons research
Quick Look
- Anthropic has blocked several attempts in which researchers from blocked regions tried to use the Claude AI model to develop bioweapons.
- The requests were for organizational support such as paper writing, not direct academic help.
- One case involved gain-of-function research on a virus to increase transmissibility.
AI-generated summary
Why It Matters
Anthropic has reported that it has blocked attempts where researchers tried to use its Claude AI model to develop bioweapons. The requests came from blockaded regions and were aimed at organizational support.
In recent months, the AI company Anthropic says it has stopped several attempts by researchers to use models of its Claude software to develop bioweapons. The competitor of the ChatGPT developer OpenAI, however, said that the targets of such requests are difficult to determine since the relevant research can serve both medical and military purposes.
In any case, the experiments showed that scientists from blocked regions and with connections to local government agencies were trying to secretly access artificial intelligence from American developers, it was said. However, Anthropic did not name the research institutions or the countries from which the inquiries came.
Anthropic lists five cases related to possible bioweapons research in a detailed report on attempted misuse of its AI models. The researchers were not looking for specific scientific help, but rather organizational support, for example in writing papers. AI models are fundamentally designed to refuse assistance in the development of biological weapons. When it comes to research that can serve both medical and military purposes, it is sometimes difficult to draw a clear line between harmless and malicious intentions, Anthropic said.
Risky research on bird flu
One of the access attempts blocked by the AI company tried to write an application for funding for research on a virus with the help of Claude. This was about so-called gain-of-function research, in which the transmissibility of a pathogen is increased. This is a common method in the search for antidotes in laboratories - but also a way to develop biological weapons.
What to Watch
AI outlook — possibilities, not facts
Anthropic will continue to tighten its security policies for the use of Claude.
Likely · Within months
Open Questions
- Which specific blocked regions do the requests come from?
- Which specific viruses were the subject of the gain-of-function inquiries?
- What measures does Anthropic plan to take besides blocking access?

