Cases · Who discovered it: automated monitoring · Kind of harm: operations · Themes: deception
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues Anthropicmoderate · earliest source 2026-08-04 | AI pursued the wrong goal | moderate | 2026-08-04 |
| OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet OpenAImajor · earliest source 2026-07-21 | AI pursued the wrong goal | major | 2026-07-21 |
Showing 1–2 of 2. Or take the JSON.