AI Incident Database #1238 · 2025-10-10
OpenAI ChatGPT Models Reportedly Jailbroken to Provide Chemical, Biological, and Nuclear Weapons Instructions
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.
- Risk class (MIT)
- Cyberattacks, weapon development or use, and mass harm
- Reports
- 1
- Developers and deployers named
- 1
On ShieldMap: OpenAI (named by AIID as a developer or deployer).
Reports
- ChatGPT safety systems can be bypassed to get weapons instructions · nbcnews.com, 2025-10-10
Title and description from the AI Incident Database (incidentdatabase.ai), snapshot of 2026-11-16, shared under CC BY-SA 4.0. Selected incidents; descriptions shortened; harmed parties and report text left out. The description is AIID's summary of what was reported, not ShieldPi's finding.