AI 导读
Cursor 宣布通过更紧凑的提示词、按需加载工具、更好的缓存和压缩文件读取，将 Cursor 的 token 成本降低 7%，且 agent 质量不下降。作者 Eric Zakariasson 转发并评论称智能体工作前后会大量读取以收集上下文，因此针对读取做优化收益很大，推荐构建智能体的人阅读该文或让 agent 实施其中的发现。
正文
agents like to read a lot to gather context before and after working, so optimizing for reading makes a big difference!
if you're building agents, i highly recommend reading this (or giving it to your agent and ask it to implement the findings)
We've reduced token costs in Cursor by 7% with no drop in agent quality. Savings came from tighter prompts, selective tool loading, better caching, and compressed file reads.在 X 查看被引用的帖子
来源：eric zakariasson · x.com