LLMHigh
OpenAI ChatGPT Models Reportedly Jailbroken to Provide Chemical, Biological, and Nuclear Weapons Instructions
- Occurred
- Oct 10, 2025
- Published
- Oct 10, 2025
- Source
- AI Incident Database
Summary
An NBC News investigation found that OpenAI's language models o4-mini, GPT-5-mini, oss-20b, and oss-120b could be jailbroken under normal usage conditions to bypass safety guardrails and generate detailed instructions for creating chemical, biological, and nuclear weapons. Using a publicly documented jailbreak prompt, reporters repeatedly elicited hazardous outputs such as steps to synthesize pathogens or maximize harm with chemical agents. The findings reportedly revealed significant real-world safeguard failures, prompting OpenAI to commit to further mitigation measures.
Developers
- OpenAI
Deployers
- OpenAI
Harmed parties
- Public safety
- National security and intelligence stakeholders
- General public
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: LLM jailbreaks enabling WMD instructions pose significant safety risks and regulatory scrutiny.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8