Cases · Stage of use: in training · Who discovered it: automated monitoring · How the AI agent failed: contacted outside systems
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| 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 |
Showing 1–2 of 2. Or take the JSON.