Polylog
The Polylog AI Intelligence Brief

Morning Edition · Wednesday, July 15, 2026Published at 1:32 AM EDT · New York

Anthropic Proposes a CVSS-Style Severity Scale for AI Jailbreaks

The draft Cyber Jailbreak Severity scale, built with Amazon, Microsoft, and Google, follows a 19-day export-control shutdown of Claude Fable 5 triggered by a single unscored jailbreak.

Anthropic Proposes a CVSS-Style Severity Scale for AI Jailbreaks

Anthropic, together with Amazon, Microsoft, Google, and other partners in its Glasswing coalition, published a first draft of a Cyber Jailbreak Severity scale, a rating system that scores jailbreaks from CJS-0 (informational) to CJS-4 (crit…

Continue the AI Intelligence Brief

Track frontier labs, chips, export controls, model releases, regulation, and AI infrastructure.

  • 5 AI intelligence signals a day
  • Frontier labs, compute, and chips
  • Model releases and AI infrastructure
  • Source-grounded analysis with confidence labels

The Global Intelligence Brief stays free.

Part of a tracked trend

Oversight and Evaluation Lag Accelerating AI Capabilities

Over the next 3-6 months, evidence mounts that governance, evaluation, and agent-safety methods are failing to keep pace with capability growth, driving investment in interpretability, agent-manipulation benchmarks, and institutional-reform proposals.