←back to thread

Ask HN: Cursor or Windsurf?

310 points skarat | 5 comments | 12 May 25 04:41 UTC | HN request time: 0.682s | 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
nlh ◴[12 May 25 13:46 UTC] No.43962846[source]▶
I use Cursor as my base editor + Cline as my main agentic tool. I have not tried Windsurf so alas I can't comment here but the Cursor + Cline combo works brilliantly for me:

* Cursor's Cmk-K edit-inline feature (with Claude 3.7 as my base model there) works brilliantly for "I just need this one line/method fixed/improved"

* Cursor's tab-complete (neé SuperMaven) is great and better than any other I've used.

* Cline w/ Gemini 2.5 is absolutely the best I've tried when it comes to full agentic workflow. I throw a paragraph of idea at it and it comes up with a totally workable and working plan & implementation

Fundamentally, and this may be my issue to get over and not actually real, I like that Cline is a bring-your-own-API-key system and an open source project, because their incentives are to generate the best prompt, max out the context, and get the best results (because everyone working on it wants it to work well). Cursor's incentive is to get you the best results....within their budget (of $.05 per request for the max models and within your monthly spend/usage allotment for the others). That means they're going to try to trim context or drop things or do other clever/fancy cost saving techniques for Cursor, Inc.. That's at odds with getting the best results, even if it only provides minor friction.

replies(5): >>43963043 #>>43964148 #>>43964404 #>>43967657 #>>43982988 #
pj_mukh ◴[12 May 25 15:29 UTC] No.43964148[source]▶
Clines agent work is better than Cursors own?
replies(1): >>43967024 #
shmoogy ◴[12 May 25 20:14 UTC] No.43967024[source]▶
Cursor does something with truncating context to save costs on their end, you dont get the same with Cline because you're paying for each transaction - so depending on complexity I find Cline works significantly better.

I still use cursor chat with agent mode though, but I've always been indecisive. Like the others said though, its nice to see how cline behaves to assist with creating your own agentic workflows.

replies(1): >>43967473 #
1. nsonha ◴[12 May 25 21:09 UTC] No.43967473[source]▶
> Cursor does something with truncating context to save costs on their end

I have seen mentioning of this but is there actually a source to back it up? Tried Cline every now and then. While it's great, I don't find it better than Cursor (nor worse in any clear way)

replies(2): >>43969011 #>>43973398 #
2. dimitri-vs ◴[13 May 25 01:42 UTC] No.43969011[source]▶
It's actually very easy to see for yourself. When the agent "looks" at a file it will say the number of lines it looks at, almost always its the top 0-250 or 0-500 but might depend on model selected and if MAX mode is utilized.
3. nlh ◴[13 May 25 14:30 UTC] No.43973398[source]▶
Totally anecdotal of course so take this with a grain of salt, but I've seen and experienced this when Cursor chats start to get very long (eg the context starts to really fill up). It suddenly starts "forgetting" things you talked about earlier or producing code that's at odds with code it already produced. I think it's partly why they suggest but don't enforce starting a new chat when things start to really grow.
replies(2): >>43983449 #>>44003122 #
4. nsonha ◴[14 May 25 11:59 UTC] No.43983449[source]▶
I don't really have this problem of long chat that everyone seems to have. Usually I can accomplish what I need to do after less than 10 turns. If I don't, then I naturally just want to restart the conversation adding whatever discovery from last time, at that point I just accept the current state (or discard all) and create a new chat, perhaps phrase it differently. Naturally I just feel that is easier not because I encounter any regression in my task.

It helps that the task is usually self-contained, but I guess as an engineer, it's kinda in your instinct to always divide and conquer any task.

5. DANmode ◴[16 May 25 08:45 UTC] No.44003122[source]▶
aka any deep work is getting done.