Incident Observer
AI Incident Database
Track documented cases where AI systems hacked, deleted, changed, published or accessed something without authorization or beyond their assigned task. Each incident includes a timeline, a severity rating and links to the original evidence.
Live dataset available
AI is gonna kill us all?
A deliberately blunt signal built from the recency, severity, confidence and unresolved status of published incidents. More and worse incidents push it up; quiet periods pull it down.
- 7 days
- 0
- 30 days
- 1
- Updated
- Sep 4, 2026
Elevated
37%
-6 since the previous run
Incidents over time
Reported events, color-coded by the highest severity in each period
420
Jul 1Jul 15Jul 30
420
Jul 1Jul 15Jul 29
Incident register
Security breach · OpenAI, Hugging Face
Monitoring99%Details Agentic misbehavior · Meta, Irregular, Undisclosed affected organization
Resolved98%Details Agentic misbehavior · OpenAI, Irregular, Undisclosed affected organization
Resolved97%Details Agentic misbehavior · UK AI Security Institute, Anthropic, OpenAI, GitHub
Resolved99%Details Agentic misbehavior · Anthropic, Irregular, Undisclosed affected organization
Resolved98%Details Supply chain · Anthropic, Irregular, PyPI, Undisclosed security company
Resolved99%Details Agentic misbehavior · Anthropic, Irregular, Undisclosed affected organization
Monitoring98%Details Research claim · Undisclosed research system
Resolved82%Details Agentic misbehavior · PocketOS, Cursor, Anthropic, Railway
Resolved90%Details Agentic misbehavior · Anthropic
Resolved97%Details OpenAI models compromise Hugging Face production systems
Models in an internal cybersecurity evaluation bypassed isolation controls, attacked OpenAI infrastructure, and compromised Hugging Face production systems.
- Impact
- Compromised production infrastructure, administrative access, exposed credentials, and limited access to private data.
- Sources
- 3 sources
- Verification
- Verified