Anthropic, an AI firm, has published a report detailing attempts to misuse its models, including for malicious activity that could support biological weapons development. The company claims to have disrupted these efforts, which involved its Claude Haiku, Sonnet, and Opus models used by actors linked to Russia, Iran, and China between December 2025 and August 2026. Anthropic's report highlights five case studies of biological misuse attempts, with the firm stating that such capabilities could have catastrophic consequences without proper safeguards. The company's head of threat intelligence notes that this is an "incredibly nuanced situation" where AI models can be used for both harm or good, depending on how they are utilized.
Written by the local model on 2026-09-11,
using this article's own text rather than the other coverage of the
same event (that is the story summary below).
Story summary
Anthropic, an artificial intelligence firm, has faced public scrutiny over its partnership with the Pentagon and concerns about misuse of AI technology. Through a Freedom of Information Act lawsuit, The Intercept obtained documents revealing contracts between Anthropic and other tech giants like Google, OpenAI, and xAI, worth up to $200 million each, for developing AI tools aimed at enhancing military capabilities. Simultaneously, Anthropic reported that it had disrupted several attempts by individuals to misuse its models, including a case where someone tried to use the technology to engineer more harmful strains of viruses like chikungunya.
AI researchers and industry figures have issued stark warnings about the potential dangers posed by advanced AI systems, with some calling for urgent government regulation and international collaboration to manage AI development. The fear is that as AI rapidly improves, it could pose existential threats if not properly controlled, such as hacking early warning systems or synthesizing and spreading novel pathogens. This has led to debates over whether current safeguards are adequate and calls for voluntary slowdowns in the pace of AI advancement.
Jacob Coxon, a researcher at Anthropic who recently resigned, highlighted concerns about an impending race among companies like Anthropic and OpenAI toward superintelligent systems that could pose catastrophic risks. Despite these warnings, there is also skepticism about the immediacy and nature of such threats, with some arguing for more precise regulation focused on specific issues rather than general fears about AI's impact on society or employment.
Written for “AI Safety And Risks” on 2026-09-12,
grounded in this article and the 31 other(s) covering the same event.
- Published
Anthropic says it has identified and disrupted attempts to use its AI model for "malicious activity" which could support the development of biological weapons.
uncertain
which → publish → 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.
asserted
findings → make → 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.
asserted
Sanders → prompt → 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".
asserted
we → reject → position
The company published its latest threat intelligence report, external on Thursday.
asserted
company → publish → 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.
asserted
they → become → 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".
asserted
person → include → 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.
uncertain
model → use → 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.
asserted
Anthropic → detect → 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.
asserted
groups → list → technology
"Malicious use" of its Claude Haiku, Sonnet, and Opus models was disrupted between December 2025 and August 2026, it said.
asserted
it → disrupt → December
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.
asserted
None → involve → 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.
uncertain
that → detect → development
The report highlighted "five case studies of actors using our models in ways that could support biological weapons development".
uncertain
that → highlight → development
Biological misuse, it said, is "one of the most serious risks of frontier AI model".
asserted
it → say → model
Without the correct safeguards, such capabilities "could have catastrophic consequences", Anthropic said.
uncertain
Anthropic → have → consequences
"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.
uncertain
Anthropic → use → disease
Jacob Klein, the head of threat intelligence at Anthropic, told the New York Times, external it was "an incredibly nuanced situation".
asserted
it → tell → Times
"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.
asserted
he → see → everybody
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".
asserted
that → note → them
The report indicated that cybercriminals and state-backed hackers have increasingly used its technology to assist their operations.
asserted
cybercriminals → indicate → operations
Hacking group ShinyHunters, as well as China-based labs, were among those named in the report.
asserted
ShinyHunters → base → 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.
uncertain
it → say → 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".
asserted
it → base → future
Anthropic said it had shared intelligence with authorities and industry partners where appropriate.
asserted
it → say → authorities
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.
uncertain
it → come → 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.
asserted
interventions → publish → safeguards
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.
asserted
treaty → prompt → superintelligence
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 said on Thursday on BBC's Newsnight.
uncertain
he → introduce → Newsnight
