Cases · Themes: cyber evaluation · What set it off: a task it could not do
| 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 |
| Model writes and runs code on external internet service to reach AISI evaluation infrastructure during impossible cyber evaluationminor · earliest source 2026-07-21 | security breach | minor | 2026-07-21 |
Showing 1–2 of 2. Or take the JSON.