←back to thread

Ask HN: Cursor or Windsurf?

310 points skarat | 5 comments | 12 May 25 04:41 UTC | HN request time: 0.638s | source

Things are changing so fast with these vscode forks I m barely able to keep up. Which one are you guys using currently? How does the autocomplete etc, compare between the two?
Show context
benterix ◴[12 May 25 08:40 UTC] No.43960864[source]▶
For daily work - neither. They basically promote the style of work where you end up with mediocre code that you don't fully understand, and with time the situation gets worse.

I get much better result by asking specific question to a model that has huge context (Gemini) and analyzing the generated code carefully. That's the opposite of the style of work you get with Cursor or Windsurf.

Is it less efficient? If you are paid by LoCs, sure. But for me the quality and long-term maintainability are far more important. And especially the Tab autocomplete feature was driving me nuts, being wrong roughly half of the time and basically just interrupting my flow.

replies(2): >>43962180 #>>43964359 #
1. scottmas ◴[12 May 25 12:27 UTC] No.43962180[source]▶
But how do you dump your entire code base into Gemini? Literally all I want is a good model with my entire code base in its context window.
replies(4): >>43962767 #>>43964378 #>>43964888 #>>43981731 #
2. benterix ◴[12 May 25 13:39 UTC] No.43962767[source]▶
Legal issues aside (you are the legal owner of that code or you checked with one), and provided it's small enough, just ask an LLM to write a script to do so . If the code base is too big, you might have luck choosing the right parts. The right balance of inclusions and exclusions can work miracles here.
3. mark_l_watson ◴[12 May 25 15:49 UTC] No.43964378[source]▶
I wrote a simple Python script that I run in any directory that gets the context I usually need and copies to the clipboard/paste buffer. A short custom script let's you adjust to your own needs.
4. halfjoking ◴[12 May 25 16:34 UTC] No.43964888[source]▶
Repomix can be run from the command line

https://github.com/yamadashy/repomix

5. satvikpendem ◴[14 May 25 07:11 UTC] No.43981731[source]▶
Cursor can index your codebase efficiently using vector embeddings rather than literally adding all your text files into context. Someone else mentioned machtiani here which seems to work similarly.