Anthropic says it blocked AI use for biological weapons research

Anthropic said it identified and disrupted attempts to use its Claude artificial intelligence models for malicious activity that could support the development of biological weapons, in a threat intelligence report published on Thursday. The California-based company reported five case studies of actors using its models in ways that could aid biological weapons development.

Which Claude models were misused, and when?

Anthropic said it disrupted “malicious use” of its Claude Haiku, Sonnet and Opus models between December 2025 and August 2026. No misuse cases involved Claude Fable or the Mythos-class models, with the exception of one instance of distillation, the process of training smaller AI models using larger, more expensive ones. The report lists state-sponsored groups, criminals, spyware vendors, state propaganda institutions and politically motivated individuals among those it says misused its technology.

What kinds of activity did Anthropic detect?

The cases detected over the past eight months ranged from fake dating apps and hotel WiFi scams to surveillance built to identify dissidents, according to the report. Anthropic also noted six cases in which Claude was used “to develop software for conventional weapons, including firearms, missiles, armed drones, bombs, and other munitions, as well as the targeting and control systems that operate them”.

Which hacking groups and states were named?

Anthropic said Claude was used by actors linked to a Russia-based cyber espionage campaign and by an Iranian propaganda institution. Hacking group ShinyHunters and China-based labs were among those named in the report. A hacking group whose work is consistent with the Russia-based Midnight Blizzard allegedly used AI to build a system that detected when its malware was flagged by security defences and rewrote code until it evaded detection. Anthropic also accused Chinese AI firms of trying to replicate Claude’s capabilities.

Why does Anthropic focus on biological weapons?

Anthropic described biological misuse as “one of the most serious risks of frontier AI model”, saying that without correct safeguards such capabilities “could have catastrophic consequences”. Jacob Klein, the head of threat intelligence at Anthropic, told the New York Times it was “an incredibly nuanced situation”. “You are not seeing someone in a comic book kind of way say, ‘Hey, I want to build a biological weapon to kill everybody,'” he said. Anthropic added that the same information that can be used to develop a biological weapon could also be used to develop a vaccine or a cure for a disease.

Google, which is investing €13bn in AI sites and nuclear power in Finland, wrote on Tuesday that a person had attempted to use its AI tool Gemini to obtain a “complete, step-by-step technical guide for synthesizing weaponised biological agents”.

What are lawmakers and researchers proposing?

US Senator Bernie Sanders has introduced legislation to ban AI superintelligence and temporarily pause advanced AI development, telling BBC’s Newsnight on Thursday: “When scientists tell you there is a chance, a chance that it could have a cataclysmic impact on humanity, you’ve got be a moron not to say, slow it down.” President Donald Trump has rejected that approach, saying on Thursday he was concerned “if we don’t win AI, we’re going to be put in a very bad position”. In the UK, the medicines watchdog has set out 44 rules for AI in the NHS.

OpenAI chief scientist Jakub Pachocki called in an article published on 6 September for the industry to implement “voluntary slowdowns” until safeguards are set, saying: “I am concerned no one is prepared for the consequences of a continued rapid rise in machine intelligence.” The warning prompted an open letter to UK Prime Minister Andy Burnham calling for a multinational treaty on the safe development of AI. Anthropic said it had shared its findings with authorities and industry partners where appropriate.

Frequently asked questions

What did Anthropic say about biological weapons?

Anthropic said it blocked scientists who used its AI in ways that could support biological weapons development, and published five case studies of such actors. The company called biological misuse “one of the most serious risks of frontier AI model”.

Which Claude models were misused?

Anthropic said “malicious use” of its Claude Haiku, Sonnet and Opus models was disrupted between December 2025 and August 2026. No misuse cases involved Claude Fable or the Mythos-class models, except one instance of distillation.

What did Google report about its Gemini AI tool?

Google wrote on Tuesday that a person had attempted to use its Gemini tool to obtain a “complete, step-by-step technical guide for synthesizing weaponised biological agents”.

What has Bernie Sanders proposed on AI?

US Senator Bernie Sanders has introduced legislation to ban AI superintelligence and temporarily pause advanced AI development. He told BBC’s Newsnight that when scientists warn of a possible cataclysmic impact on humanity, “you’ve got be a moron not to say, slow it down”.

With reporting from BBC News.

Stock image, not from the events described. 123Net Data Center (DC2) — 123net / Wikimedia Commons (CC BY-SA 3.0)