# Anthropic and Rivals Propose a Shared Scale for Rating AI Jailbreak Severity

The draft Cyber Jailbreak Severity scale runs CJS-0 to CJS-4 across four axes, published as Anthropic restored Fable 5 and Mythos 5 after a 19-day export-control block.

- Published: 2026-07-19T05:30:22.062Z
- Canonical: https://polylog.news/ai/2026-07-19/anthropic-and-rivals-propose-a-shared-scale-for-rating-ai-ja
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Anthropic](https://www.anthropic.com/news/redeploying-fable-5), [SecurityWeek / TechTimes](https://www.techtimes.com/articles/319658/20260703/ai-model-safety-standards-deal-targets-august-1-five-labs-adopt-first-jailbreak-scoring-scale.htm)

Anthropic published a first draft of a Cyber Jailbreak Severity scale developed with Amazon, Microsoft, Google, and other members of its Glasswing coalition. The framework rates a jailbreak from CJS-0 (informational) to CJS-4 (critical) on…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-07-19/anthropic-and-rivals-propose-a-shared-scale-for-rating-ai-ja (subscription information: https://polylog.news/pricing).