Anthropic Disrupts Attempts to Use Its AI in Biological Weapons Development

Anthropic has disclosed that it identified and disrupted attempts to use its artificial intelligence models for malicious purposes, including activity that could support the development of biological weapons. The findings, published in the company's latest threat intelligence report on Thursday, mark the latest in a series of warnings from researchers and industry figures about the risks advanced AI poses to humanity.

The California-based firm said it had blocked scientists who used its technology in ways that could assist biological weapons development, highlighting five case studies of such activity. Biological misuse, the report noted, is one of the most serious risks of frontier AI models. Without correct safeguards, it said, such capabilities could have catastrophic consequences.

Jacob Klein, head of threat intelligence at Anthropic, told the New York Times the situation was incredibly nuanced. He said the company was not seeing someone in a comic book kind of way declaring a desire to build a biological weapon to kill everybody. The same information that can be used to develop a biological weapon, Anthropic observed, could also be used to develop a vaccine or a cure for a disease.

The report also documented six cases in which its Claude model 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. Anthropic said malicious use of its Claude Haiku, Sonnet and Opus models was disrupted between December 2025 and August 2026. None of the misuse cases involved Claude Fable or the powerful Mythos-class models, with the exception of one instance of distillation, the process for training smaller AI models using larger, more expensive ones.

Beyond weapons development, Anthropic said its technology had been deployed for cyber and influence operations, surveillance, scams and fraud. The cases detected over the past eight months ranged from fake dating apps and hotel WiFi scams to surveillance built to identify dissidents. A hacking group whose work is consistent with the Russia-based Midnight Blizzard allegedly used AI to build a system that automatically detected when its malware was flagged by security defences and rewrote code until it evaded detection. Hacking group ShinyHunters, as well as China-based labs, were among those named in the report. Claude was also used by actors linked to a Russia-based cyber espionage campaign and by an Iranian propaganda institution, according to Anthropic, which has also accused Chinese AI firms of trying to replicate Claude's capabilities.

The report lists cases in which suspected state-sponsored groups, criminals, spyware vendors, state propaganda institutions and politically motivated individuals misused its technology. Anthropic said it had incorporated its findings into its processes to better prevent, detect and disrupt such activities in the future, and had shared intelligence with authorities and industry partners where appropriate. Other AI firms publish similar reports. Google 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.

The disclosure comes amid mounting concern about the pace of AI development. A top safety researcher at Anthropic has warned that AI is advancing so quickly he believes there is a greater than 10 per cent chance it could kill all humans within the next decade. In an article published on 6 September, OpenAI chief scientist Jakub Pachocki called for the industry to implement voluntary slowdowns until safeguards are set. He said he was concerned no one was prepared for the consequences of a continued rapid rise in machine intelligence, adding that OpenAI, which makes ChatGPT, would continue its work on building safeguards, though broader interventions are required.

The warning prompted an open letter to UK Prime Minister Andy Burnham calling for a new multinational treaty for the safe development of AI, and for governments to collaborate on what a treaty based on the development of superintelligence should look like. In the United States, Democratic lawmaker Bernie Sanders has introduced legislation to ban AI superintelligence and temporarily pause advanced AI development. Speaking on Thursday on BBC's Newsnight, he said that when scientists tell you there is a chance it could have a cataclysmic impact on humanity, you have got to be a moron not to say, slow it down. President Donald Trump has so far rejected such fears, saying on Thursday he was concerned that if we do not win AI, we are going to be put in a very bad position.