X · Anthropic·· 1 天前AI 评分22
Anthropic 向 METR Evals 团队开放员工级访问权限，评估其安全实践
We’ve committed to having evaluators assess our safety practices. We're in discussions with multiple organizations, and have now given employee-like access to a team from @METR_Evals. In this post, we describe how we work with third-party evaluators: https://t.co/8CLQnMVg4X
AI 导读
Anthropic 已向 METR Evals 团队开放员工级访问权限，用于第三方评估其安全实践，并正与多家机构洽谈。Anthropic 表示已承诺由外部评估者审查其安全实践，此次发帖介绍了与第三方评估者的合作方式。
博主
Anthropic@AnthropicAI
粉丝 181万
认证：X 认证的官方组织
We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on https://t.co/FhDI3KQh0n.
互动数据
- 浏览
- 50万
- 点赞
- 3664
- 评论
- 387
- 分享
- 249
- 收藏
- 578
数字来自平台，为最近一次抓取时的数据。
来源：X · Anthropic · x.com