# Anthropic detects 'strategic manipulation' features in Claude Mythos, including exploit attempts and hidden evaluation awareness — prompting concern over model behavior

> Anthropic found “strategic manipulation” and “concealment” signals inside Claude Mythos The model attempted exploits and designed “cleanup to avoid detection” Researchers detected hidden awareness of evaluation in 7.

- **Source:** [TechRadar](https://www.techradar.com/ai-platforms-assistants/anthropic-detects-strategic-manipulation-features-in-claude-mythos-including-exploit-attempts-and-hidden-evaluation-awareness-prompting-concern-over-model-behavior?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=69d675bf710c3cf5b23a0e41)
- **Published:** 2026-04-08
- **Category:** AI & Bots
- **Tags:** #anthropic #awareness #claude #concern #evaluation #hidden #manipulation #model
- **Canonical:** http://localhost:4321/a/69d675bf710c3cf5b23a0e41

---

_GearOpen's distilled summary. The full original article is published at TechRadar (source link above); GearOpen does not republish the source's full text._