Anthropic· @AnthropicAI · X·· 15 天前AI 评分58
AI 导读
Anthropic 扩展 Cyber Verification Program，让经过验证的安全从业者可以访问 Claude Mythos 5.1、Opus 5.5 和 Sonnet 5.5，并提供面向防御工作的防护措施。该项目还新增层级，允许渗透测试、红队演练等经授权的攻击性安全工作。
正文 · 原文
We’re expanding our Cyber Verification Program to give security professionals broader access to our most capable models.
Through this program, verified security professionals can access Claude Mythos 5.1, Opus 5.5, and Sonnet 5.5 with safeguards designed for defensive work.
We’re also opening up new tiers to allow for authorized offensive work, like penetration testing and red-teaming.
来源：Anthropic · x.com