# 'A new frontier model trained by Anthropic that we believe could reshape cybersecurity': Project Glasswing wants to use AI to prevent AI cyberattacks — but will 'overeager' Claude Mythos do more damag

> Project Glasswing and Anthropic's Claude Mythos Preview are designed to tackle AI security threats Mythos is so powerful that it's not being released to the public – only select companies Work has already found…

- **Source:** [TechRadar](https://www.techradar.com/pro/security/a-new-frontier-model-trained-by-anthropic-that-we-believe-could-reshape-cybersecurity-project-glasswing-wants-to-use-ai-to-prevent-ai-cyberattacks-but-will-overeager-claude-mythos-do-more-damage-than-help?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=69d64bb6dc25fc4e31bbaa92)
- **Published:** 2026-04-08
- **Category:** AI & Bots
- **Tags:** #cybersecurity #microsoft #anthropic #google #nvidia #apple #glasswing #mythos
- **Canonical:** http://localhost:4321/a/69d64bb6dc25fc4e31bbaa92

---

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