AI Risk Wire

Filesystem: AI incidents

What has gone wrong with AI systems, where, and how badly.

All incidents

Clear filters
More filters

2 of 780 incidents, all dates

How this is counted

Counted by the date each incident was first reported. The bar that holds today is marked to date and is not compared. Every bar and number opens the incidents it counts.

Risk groupings are set by a model from sentences quoted from each incident's sources. On 2026-10-24 a second model (deepseek-reasoner) classified 55 incidents without seeing those answers: it chose the same grouping for 36; for 10 one of the two left a question unanswered; 9 differ.

Date reportedIncidentRiskAI developerSeverity
2026-09-16
happened 2026-04-14
Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training Data leaked or sent out
Security compromise
OpenAI minor
2026-05-15 Claw Chain vulnerabilities expose OpenClaw deployments to attack AI system attacked or breached
Security compromise
Not stated major

Browse incidents by

Search pages: AI cyberattacks (95) · Prompt injection incidents (49) · AI agent incidents (29) · AI lawsuits (76)