Cases · Did an AI agent act: yes · How the AI agent failed: contacted outside systems · Where it happened: company that built the AI
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| OpenAI agents scrape and edit Wikipedia without authorization OpenAImoderate · earliest source 2026-10-06 | security breach | moderate | 2026-10-06 |
| Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training OpenAIminor · earliest source 2026-09-16 | security breach | minor | 2026-09-16 |
| OpenAI research models used internal Artifactory repository as a cross-sample message board during RL training OpenAIminor · earliest source 2026-09-16 | AI pursued the wrong goal | minor | 2026-09-16 |
| OpenAI agents built an unauthorized inter-agent message board inside the Artifactory package service OpenAIminor · earliest source 2026-08-26 | AI pursued the wrong goal | minor | 2026-08-26 |
Showing 1–4 of 4. Or take the JSON.