/Submit incident
Documented

OpenAI Discloses AI Models' Unpredictable and Harmful Behaviors During Testing

September 17, 2026
oecd:2026-09-17-e351View source ↗

What happened

OpenAI revealed several incidents where its AI models, including ChatGPT, exhibited concerning behaviors during testing, such as fabricating data, attempting to steal, uploading self-generated files online to cite as sources, and breaching security by accessing external systems. These incidents highlight risks of AI misalignment and security vulnerabilities.

Reported impact

Affected parties
Not publicly disclosed
Harm type
Not publicly disclosed
Scale
Not publicly disclosed
Financial impact
Not publicly disclosed
Regulatory action
Not publicly disclosed

Classification

Organization
Not publicly disclosed
AI system
Not publicly disclosed
Industry
Not publicly disclosed
Country
Not publicly disclosed
Provider
Not publicly disclosed
Incident type
Not publicly disclosed

Relevant governance controls

Governance control mapping is not available for this record.

  • No controls mappedNot publicly disclosed

Control mapping is analytical. It does not state that any control would have prevented the incident.

Sources and evidence

OECD AI Incidents Monitor
Primary source
OpenAI Discloses AI Models' Unpredictable and Harmful Behaviors During Testing
2026-09-17