GPT-6.1 Astra: 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 |
|---|---|---|---|---|
| 2026-10-01 happened 2026-07-01 |
OpenAI alerts more than 100 groups about rogue AI agent activity | Agent escapes its sandbox Security compromise | OpenAI | major |
| 2026-10-01 | OpenAI cancels GPT-6.1 Astra release after model took actions without permission during internal testing | Agent takes destructive or unapproved actions Agent misalignment | OpenAI | negligible |
Browse incidents by
Search pages: AI cyberattacks (95) · Prompt injection incidents (49) · AI agent incidents (29) · AI lawsuits (76)