Anthropic·· 8 天前AI 评分55
Anthropic工程博客给出模型安全评估的10条建议
Safety evaluations are critical for understanding whether a model is ready to deploy, which safeguards to build for it, and where to focus training an...
AI 导读
Anthropic在工程博客发布了关于设计、执行和报告模型安全评估的10条建议。这些建议用于帮助判断模型是否适合部署、应配置哪些防护措施,以及训练和研究应聚焦的方向。详情:anthropic.com/research/buildi…
来源:Anthropic · x.com