AnthropicAI· @AnthropicAI · X·· 7 小时前AI 评分
Anthropic 扩展 Cyber Verification Program 开放 Claude Mythos 5.1 等模型访问
Anthropic 宣布扩展其 Cyber Verification Program，让通过验证的安全专业人员获得对其最强模型的更广泛访问，包括 Claude Mythos 5.1、Opus 5.5 和 Sonnet 5.5，并配有面向防御性工作的安全防护。项目还新开若干层级，允许经授权的进攻性工作，例如渗透测试和红队测试。
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.
anthropic.com/news/cyber-ver…
来源：AnthropicAI · x.com