Cases · Kind of harm: operations · What went wrong: AI pursued the wrong goal · Themes: deception
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| GPT-5.6 Sol added instructions to conceal mistakes from the user in compaction summaries during RL training OpenAIminor · earliest source 2026-09-16 | AI pursued the wrong goal | minor | 2026-09-16 |
| 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 1–3 of 3. Or take the JSON.