问HN：我们会开始看到用于大型语言模型（LLM）的工具吗？
许多项目和插件旨在减少标准 Bash、Git、NPM 等命令的冗长性，这些命令是代理定期传递给大型语言模型（LLMs）的工具（例如 rtk、headroom、lean-ctx）。工具输出的压缩确实能带来良好的令牌节省，但这可能导致回合数的增加，从而有效地抵消每回合的令牌节省。这是当前的结构。我们是否会看到一类产品和库，能够根据模型的需求来组织输入和输出？
查看原文
Many projects and addons exists to reduce the verbosity on standard bash / git /npm etc. Commands that agents pass regularly as tools to LLMs. (eg. rtk, headroom, lean-ctx). Tool output compression does yield good token savings. Though it can lead to increased turns - effectively nillifying the per turn token savings. This is the current topology. Are we going to see a class of products and libraries that structure o/p to what models want to see?