Ask HN：我们会开始看到用于 LLM 使用的工具吗？
1 分•作者: bonigv•大约 16 小时前
存在许多项目和插件可以减少标准 bash / git / npm 等命令的冗余，这些命令是代理经常作为工具传递给 LLM 的。（例如 rtk、headroom、lean-ctx）。工具输出压缩确实可以节省大量 token。尽管如此，这可能会导致回合数增加——实际上抵消了每回合的 token 节省。这就是当前的拓扑结构。我们是否会看到一类产品和库来组织输出，使其符合模型希望看到的内容？
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?