Calendars: AI incidents
What has gone wrong with AI systems, where, and how badly.
All incidents
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 reported | Incident | Risk | AI developer | Severity |
|---|---|---|---|---|
| 2026-07-23 | AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent | Hidden instructions hijack the agent Security compromise | OpenAI | minor |
| 2026-07-21 | Claude Opus 4.5 (Atlas) overruled a simulated CEO in a fictional whistleblowing scenario | Deception, concealment or sabotage Agent misalignment | Anthropic | negligible |
Browse incidents by
Search pages: AI cyberattacks (95) · Prompt injection incidents (49) · AI agent incidents (29) · AI lawsuits (76)