Anthropic blocks possible attempt to use AI to make biological weapons

ByNardine Saad, BBC News and Laura Cress, Technology reporter. 11 September 2026, 03: 46 BST.

Key points

• "Malicious use" of its Claude Haiku, Sonnet, and Opus models was disrupted between December 2025 and August 2026, it remarked.
• Jacob Klein, the head of threat intelligence at Anthropic, informed the New York Times, external it was "an incredibly nuanced situation".
• Anthropic's AI model Claude was additionally employed by actors linked to a Russia-based cyber espionage campaign and by an Iranian propaganda institution, according to Anthropic's report.
• In an article published on 6 September, OpenAI chief scientist Jakub Pachocki pressed the industry to implement "voluntary slowdowns" until safeguards are set.
• The warnings have prompted calls to action, with US Senator Bernie Sanders demanding a pause on advanced AI development and a ban on artificial superintelligence.

Anthropic notes it has identified and disrupted attempts to apply its AI model for "malicious activity" which could backing the development of biological weapons.

Meanwhile, the findings, created in the firm's recent threat intelligence report, is the latest in a growing series of warnings from AI researchers and industry insiders concerning the technology's potential risks to humanity.

For context, the warnings have prompted calls to action, with US Senator Bernie Sanders demanding a pause on advanced AI development and a ban on artificial superintelligence.

President Donald Trump has so far rejected such fears, saying on Thursday he was concerned "if we don't win AI, we're going to be put in a very bad position".

Meanwhile, the firm published its latest threat intelligence report, external on Thursday. Other AI firms publish similar reports.

This includes Google, which wrote on Tuesday, external a person had attempted to employ its AI tool Gemini to obtain a "complete, step-by-step technical guide for synthesizing weaponised biological agents".

In practice, the cases of concern detected over the past eight months ranged from fake dating apps and hotel Wifi scams, to surveillance built to identify dissidents.

Anthropic has additionally accused Chinese AI firms of trying to replicate Claude's capabilities.

Notably, the lengthy report lists cases in which suspected state- groups, criminals, spyware vendors, state propaganda institutions and politically motivated individuals misused its technology.

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 models.

As well as detecting the employ of its models for cyber and influence operations, surveillance, scams and fraud and weapon development, Anthropic stated it had blocked scientists who applied its AI in ways that could backing biological weapons development.

For context, the report highlighted "five case studies of actors using our models in ways that could support biological weapons development".

Biological misuse, it remarked, is "one of the most serious risks of frontier AI model". Without the correct safeguards, such capabilities "could have catastrophic consequences", Anthropic remarked.

"The same information that can be used to develop a biological weapon could also be used to develop, for example, a vaccine or a cure for a disease, " Anthropic remarked.

"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 remarked.

Meanwhile, the report additionally observed six cases where Claude was applied "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". Why some experts increasingly fear AI will take over.

Anthropic researcher believes more than 10% chance AI 'could kill all humans'.

For context, the report indicated that cybercriminals and state-backed hackers have increasingly applied its technology to assist their operations.

As well as China-based labs, were among those named in the report, hacking group ShinyHunters.

According to The report additionally, a hacking group whose work is consistent with the Russia-based Midnight Blizzard allegedly applied AI to build a system that automatically detected when its malware was flagged by security defences and rewrote code until it evaded detection.

Notably, the California-based firm stated it had incorporated its findings into its processes "to better prevent, detect, and disrupt these activities in the future".

Anthropic remarked it had shared intelligence with authorities and industry partners where appropriate.

Meanwhile, the report – the company's first this year – comes after a top safety researcher at Anthropic cautioned AI is advancing so swiftly he believes there is a greater than 10% chance it "could kill all humans" within the next decade.

"I am concerned no one is prepared for the consequences of a continued rapid rise in machine intelligence, " Pachocki remarked, adding that OpenAI. It makes ChatGPT, will continue its work on building safeguards, though broader interventions are required.

In practice, 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 a call for governments to collaborate regarding what a treaty based on the development of superintelligence should look like.

In the US, Democratic lawmaker Bernie Sanders has introduced legislation to ban AI superintelligence and temporarily pause advanced AI development.

"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, " he remarked on Thursday on BBC's Newsnight. With extra reporting from Osmond Chia.

AI 'slop' is transforming social media – and a backlash is brewing. The contradiction at the heart of the trillion-dollar AI race.

Taken together, the developments around anthropic blocks possible attempt to use AI to make biological weapons point to a situation that is still moving, and the coming days should bring more clarity.