Vercel CEO 惊叹 fx v0.0.16 改进速度
The rate of improvement on https://t.co/3Z4NESzNKd is bewildering.
Vercel Developers 发布 fx v0.0.16，称其提示词缓存更好、下载包和二进制更小：未缓存输入 token 减少 41%，libfx npm 下载体积缩小约 60%，CLI 二进制缩小 2.8%。Vercel CEO Guillermo Rauch 转发并感叹改进速度惊人，称它现在更小、更快、更省 token，团队正持续做基准测试，并要求它在开源和闭源模型上提升自身表现。
查看原帖fx v0.0.16 此版本具有更好的提示词缓存，下载包和二进制文件也更小。 • 未缓存输入 token 减少 41% • libfx npm 下载体积缩小约 60% • CLI 二进制文件缩小 2.8% 更新日志 → https://t.co/9n2qtJfh4E https://t.co/GjeEEDT8ze
查看原文
fx v0.0.16 This version has better prompt caching and smaller downloads & binaries. • 41% fewer uncached input tokens • About 60% smaller libfx npm downloads • 2.8% smaller CLI binary Changelog → https://t.co/9n2qtJfh4E https://t.co/GjeEEDT8ze
正文
The rate of improvement on https://t.co/3Z4NESzNKd is bewildering. It's now even smaller, faster and more token-efficient.
We're continuously benchmarking and asking it to improve its own performance across open and proprietary models.