AI产品精选

Prime Radiant 发布 smevals,命令行快速运行模型评估套件

I've been working with Prime Radiant building a new tool for running small eval suites against model...

精选理由

smevals 是 Simon 和 Prime Radiant 做的小工具,专门跑模型和提示词的评估,一条命令就能用,适合快速看效果。

AI 摘要

Simon Willison 与 Prime Radiant 合作推出新工具 smevals,用于在命令行运行针对模型、测试框架和提示词的小型评估套件。用户可通过 'uvx smevals docs' 命令直接体验。相关博客文章已在 primeradiant.com 发布,介绍了工具的设计思路。

原文 · Simon Willison

I've been working with Prime Radiant building a new tool for running small eval suites against model...

I've been working with Prime Radiant building a new tool for running small eval suites against models, harnesses, and prompts - it's called "smevals", you can try it with "uvx smevals docs", and I wrote about it here: primeradiant.com/blog/2026/smev… 💬 11 🔄 3 ❤️ 16 👀 4007 📊 14 ⚡

Prime Radiant 发布 smevals,命令行快速运行模型评估套件 · AI 热点