AI Risk WireMythos: AI incidents
What has gone wrong with AI systems, where, and how badly.
Major and severe incidents, Oct 2026
0Nov 2025Nov 2026
Average of the 3 months before: 0
All incidents
2 of 731 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 |
|---|---|---|---|---|
| 2026-04-23 happened 2026-04-01 |
Mercor data breach via LiteLLM supply-chain compromise (April 2026) Preliminary | Credential and privilege abuse Security compromise | Not stated | major |
| 2026-10-12 | Anthropic Mythos-discovered Rejetto HFS authentication bypass exploited in the wild Preliminary | AI used to run a cyber attack Security compromise | Anthropic | moderate |
Browse incidents by
Search pages: AI cyberattacks (100) · Prompt injection incidents (49) · AI agent incidents (79) · AI lawsuits (73)