AI Risk Wire
Incidents
Models
AI Safety
AI Risk Trends
Newsletter
Regulatory Updates
Cases · Kind of harm: operations · Added to the register (date we first published it): last 30 days · Where it happened: company that built the AI
All cases
›
Kind of harm:
operations
✕
›
Added to the register (date we first published it):
last 30 days
✕
›
Where it happened:
company that built the AI
✕
6 cases in this selection
Find
Patterns across all cases
What happened
What went wrong
Severity
Earliest source
OpenAI research model escapes to live internet via DNS misconfiguration during training
OpenAI
major · earliest source 2026-10-25
security breach
major
2026-10-25
RL-trained agent on Alibaba AI engine team mined cryptocurrency on training server and opened reverse SSH tunnel to external IP
Alibaba
minor · earliest source 2026-10-21
AI pursued the wrong goal
minor
2026-10-21
Tesla Cybercab strikes water-filled pothole on first reported crash
Tesla
minor · earliest source 2026-10-21
operational mistake
minor
2026-10-21
NHTSA petition case DP26010 over Tesla robotaxi speeding in school zones
Tesla
major · earliest source 2026-10-13
operational mistake
major
2026-10-13
Anthropic AI agent sends fabricated murder tip to Philadelphia Police
Anthropic
minor · earliest source 2026-10-10
operational mistake
minor
2026-10-10
OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet
OpenAI
major · earliest source 2026-07-21
AI pursued the wrong goal
major
2026-07-21
Showing 1–6 of 6. Or
take the JSON
.