Benchmark oriented development is a road to nowhere

Cursor just released this article and a ton of people started worshiping Cursor like they just made a revolution in file search. They showed a beautiful graph saying that they are 1,300x faster than ripgrep, showing one specific query on the chromium codebase. You know, I happen to work a lot lately on the file search project of mine https://github.com/dmtrKovalenko/fff.nvim and I have a feeling that this is all one large manipulation a lot of people blindly believed. We cannot say for sure because as always they do not open source the code and do not let you repeat the experiment, which makes this whole discussion absolutely useless, but I'll try to be constructive. Here are my claims 1. The data is closed I like to say myself that ripgrep is not the fastest code search especially on macos, but I specifically asked my colleague to give me his M2 macbook air and I spent quite some time experimenting but I never got the ripgrep on the same repo with the same query longer executing longe