Anthropic blocks possible attempt to use AI to make biological weapons
The findings, made in the firm's recent threat intelligence report, is the latest in a growing series of warnings from AI researchers and industry insiders about the technology's potential risks to humanity.
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".
The company published its latest threat intelligence report, external on Thursday.
Such reports have become a regular feature across the AI industry as firms seek to demonstrate how they identify and disrupt attempts to misuse their models.
This includes Google, which wrote on Tuesday, external 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".
Claude, Anthropic's AI model was also used by actors linked to a Russia-based cyber espionage campaign and by an Iranian propaganda institution, according to its report.
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 also accused Chinese AI firms of trying to replicate Claude's capabilities.
The lengthy report lists cases in which suspected state-sponsored groups, criminals, spyware vendors, state propaganda institutions and politically motivated individuals misused its technology.
"Malicious use" of its Claude Haiku, Sonnet, and Opus models was disrupted between December 2025 and August 2026, it said.
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 use of its models for cyber and influence operations, surveillance, scams and fraud and weapon development, Anthropic said it had blocked scientists who used its AI in ways that could support biological weapons development.
The report highlighted "five case studies of actors using our models in ways that could support biological weapons development".
Biological misuse, it said, is "one of the most serious risks of frontier AI model". Without the correct safeguards, such capabilities "could have catastrophic consequences", Anthropic said.
"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 said.
Jacob Klein, the head of threat intelligence at Anthropic, told the New York Times, external 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.
The report also noted six cases where 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".
Why some experts increasingly fear AI will take over
Published1 day agoAnthropic researcher believes more than 10% chance AI 'could kill all humans'
Published2 days agoThe report indicated that cybercriminals and state-backed hackers have increasingly used its technology to assist their operations.
Hacking group ShinyHunters, as well as China-based labs, were among those named in the report.
The report also said that 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.
The California-based company said it had incorporated its findings into its processes "to better prevent, detect, and disrupt these activities in the future".
Anthropic said it had shared intelligence with authorities and industry partners where appropriate.
To play this video you need to enable JavaScript in your browser.This video can not be played
Watch: "Slow it down" - Bernie Sanders proposes bill to ban AI superintelligence
The report - the company's first this year - comes after a top safety researcher at Anthropic warned AI is advancing so quickly he believes there is a greater than 10% 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.
"I am concerned no one is prepared for the consequences of a continued rapid rise in machine intelligence," Pachocki said, adding that OpenAI, which makes ChatGPT, will 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 a call for governments to collaborate about 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.
With additional reporting from Osmond Chia.
AI 'slop' is transforming social media - and a backlash is brewing
Published4 FebruaryThe contradiction at the heart of the trillion-dollar AI race
Published19 November 2025Sign up for our Tech Decoded newsletter to follow the world's top tech stories and trends. Outside the UK? Sign up here.
Live. 'We will never, ever forget,' Trump says as US marks 25th anniversary of 9/11
Live. Houthis claim major advance in Yemen as group reportedly seizes island in key shipping route
I watched as a hijacked plane flew over my home - moments later my wife was killed on 9/11
Princess Diana's 'revenge dress' goes up for auction
I asked my husband to pay into my pension when we had a child - here's why
Weekly quiz: Alan Carr collected a prize for which TV show at the NTAs?
'Like a hangover': Why your partner's snoring could be impacting your health
'Do I have to turn this gig down?': Female DJs describe harassment behind the decks
Species 'at risk of vanishing' from area of Wales' largest national park
England captain Jones calls for fertility support
US Politics Unspun: Cut through the noise with Anthony Zurcher's newsletter
How a woman's sudden death triggered a six-month manhunt
Abercrombie & Fitch's former CEO Mike Jeffries to stand trial
Dvorak’s epic masterpiece at the Proms
Greg Jenner and guests examine the tumultuous events of 1066
UK government rejects 'kill switch' idea for dangerous AI
Hull City footballer in crash near training ground
Kate visits cancer patients in hospital she funded with climb
I was weeks from marrying a violent serial rapist - my loved ones saved my life
Girls to be given right to wear trousers in schools
Israel says it has destroyed major underground Hezbollah base
As Trump dominates convention, some Republicans quietly ask who comes next
The man who bought an island, hired hitmen and throttled a theatregoer
'I survived the epicentre of 9/11 - I'm so lucky'
Princess Diana's 'revenge dress' goes up for auction
