Top news
Investing in the public benefit OfficialAnthropic NewsOct 18Popular Musk Pledges SpaceX Shares to ‘Every Kid in America’ WebBloomberg TechnologyOct 19Popular Websites are closing their doors to AI agents WebThe Verge AIOct 17 This is the new ChatGPT Voice, powered by GPT Live OfficialOpenAI on YouTubeOct 18 How AI giants will reshape global philanthropy WebAxios AIOct 19 Gemini 4 Argon Really Surprised Me WebTwo Minute PapersOct 19 Google Gemini 4 agents just beat Minecraft with no human intervention WebEngadget AIOct 19 Who could it be? 🧐 OfficialGoogle on YouTubeOct 18 Anthropic gives outside AI watchdog “employee-like” access WebArs Technica AIOct 18 What are self-replicating ‘AI worms’, and why is Anthropic worried about them? WebThe Guardian AIOct 18
GlossarySafetyIntermediate

CBRN

Also written: CBRN threats, CBRN weapons, CBRN concerns, WMD concerns, Bioweapons, biological weapons, AI-enabled pandemics

Chemical, Biological, Radiological, and Nuclear threats or weapons.

In plain terms

CBRN stands for Chemical, Biological, Radiological, and Nuclear. It refers to dangers or weapons involving hazardous materials like poisons, disease-causing germs, radiation, or explosives.

In AI safety, CBRN is used to describe risks that advanced AI systems could potentially create or be misused to cause. This includes scenarios where AI might help design dangerous substances or weapons, or even directly cause harm through uncontrolled chemical or biological processes.

The expert version

CBRN refers to threats or weapons involving chemical, biological, radiological, and nuclear agents. These are often categorized as weapons of mass destruction due to their potential for widespread harm.

In the context of AI safety, CBRN risks relate to the potential for advanced AI systems to be involved in the creation, proliferation, or use of CBRN materials or weapons. This can range from AI assisting in research and development of novel agents to AI being used in the control systems of existing CBRN capabilities, or even AI systems themselves exhibiting dangerous emergent behaviors that mimic CBRN effects.

Why it matters now

Frontier AI labs are increasingly focused on CBRN risks as their models become more capable. Recent discussions highlight the need for robust safety measures to prevent AI from being used to develop or deploy CBRN threats, as seen in Anthropic's safety testing and OpenAI's system card evaluations.

Where it shows up 16 items, newest first
How each company uses it
Anthropic Claude
Anthropic explicitly mentions testing its safety defenses against CBRN threats, indicating it is a key concern for their AI models.
OpenAI ChatGPT
OpenAI's system cards, like for o3-mini, evaluate risk mitigation capabilities, which would implicitly include potential CBRN risks from advanced AI.
Related terms

AI safetydual-use researchexistential riskAI alignmentred teamingmisuse

Often confused with
[object Object]
[object Object]
Origin

The term CBRN originates from military and emergency response contexts, referring to specific categories of threats and weapons. Its application to AI safety is a more recent development as AI capabilities advance.

Try this about 5 minutes

You can explore AI safety discussions by searching for 'AI safety' on the websites of companies like Anthropic or OpenAI. Look for their safety policies or research papers that mention risk mitigation strategies for advanced AI systems.

Try it: Playbook entries that use thisPlaybook →

The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.

Questions people ask

What does CBRN stand for?
CBRN stands for Chemical, Biological, Radiological, and Nuclear.
Why is CBRN relevant to AI?
CBRN is relevant to AI because advanced AI systems could potentially be misused to create or deploy dangerous chemical, biological, radiological, or nuclear threats or weapons.

First seen on Subvolts Aug 5, 2024. Updated Oct 12, 2026. Written by an AI model from the items above and reviewed against them weekly; report an error.