Urgent.News

What's breaking now, across hundreds of outlets.

AI

Anthropic opens its most powerful AI models to more security teams

The Specialized tier has the fewest restrictions and is reserved for a small group of organisations authorised to test safety-critical systems

Anthropic opens its most powerful AI models to more security teams

Anthropic is expanding its Cyber Verification Program (CVP) to provide more security teams with access to its most powerful AI models, after its Project Glasswing initiative discovered over 100,000 software vulnerabilities this year. The program, which consists of three tiers, allows security teams, critical infrastructure operators, open-source maintainers, and researchers to test Anthropic's Claude Opus 5.5, Sonnet 5.5, Mythos 5.1, and future models.

The Defense tier focuses on incident response and malware analysis, while the Red Team tier adds authorized penetration testing and red-teaming. The Specialized tier, reserved for a select group of organizations, allows testing of safety-critical systems like power grids and flight systems. Anthropic collaborates with the US government in vetting members, and existing Glasswing members will move into the Specialized tier.

Rewritten by urgent.news; may contain errors — check the original.

Read the original at thehindu.com →

More in AI

Don't verify the agent. Verify the state.

Building an AI agent that confirms before it acts forced us to confront a problem we didn't expect: how do you verify that an action actually happened? The obvious answer is: check the agent's output.

More from Wednesday 7 October →