Live data from Hacker News

Ask HN: Cursor or Windsurf?

news.ycombinator.com

31–40 of 410 posts

Re: Ask HN: Cursor or Windsurf?

#31

Aider! Use the editor of your choice and leave your coding assistant separate. Plus, it's open source and will stay like this, so no risk to see it suddenly become expensive or dissappear.

Yup, choose your model and pay as you go, like commodities like rice and water. The others played games with me to minimize context and use cheaper models (such as 3 modes, daily credits etc, using most expensive model etc).

Also the --watch mode is the most productive interface of using your editor, no need of extra textboxes with robot faces.

Re: Ask HN: Cursor or Windsurf?

#32
For the agentic stuff I think every solution can be hit or miss. I've tried claude code, aider, cline, cursor, zed, roo, windsurf, etc. To me it is more about using the right models for the job, which is also constantly in flux because the big players are constantly updating their models and sometimes that is good and sometimes that is bad.

But I daily drive Cursor because the main LLM feature I use is tab-complete, and here Cursor blows the competition out of the water. It understands what I want to do next about 95% of the time when I'm in the middle of something, including comprehensive multi-line/multi-file changes. Github Copilot, Zed, Windsurf, and Cody aren't at the same level imo.

Re: Ask HN: Cursor or Windsurf?

#34

Zed. They've upped their game in the AI integration and so far it's the best one I've seen (external from work). Cursor and VSCode+Copilot always felt slow and janky, Zed is much less janky feels like pretty mature software, and I can just plug in my Gemini API key and use that for free/cheap instead of paying for the editor's own integration.

Does it have Cursor’s “tab” feature?

Yep: https://zed.dev/blog/edit-prediction

Re: Ask HN: Cursor or Windsurf?

#35

Windsurf at the moment. It now can run multiple "flows" in parallel, so I can set one cascade off to look into a bug somewhere while another cascade implements a feature elswhere in the code base. The LLMs spit out their tokens in the background, I drop in eventually to reveiew and accept or ask for further changes.

Cursor offers this too - open different tabs in chat and ask for different changes; they’ll run in parallel.

Re: Ask HN: Cursor or Windsurf?

#36
Cursor has for me had the best UX and results until now. Trae's way of adding context is way too annoying. Windsurf has minor UI-issues all over. Options that are extensions in VSCode do not cut it in turn of providing fantastic UI/UX because of the API not supporting it.

Re: Ask HN: Cursor or Windsurf?

#38

I really like Zed. Have not tried any of the mentioned by op. Zed I feel like is getting somewhere that can replace Sublime Text completely (but not there yet).

Zed is an editor firslty.. The Ops has mentioned options which are AI development "agents" basically.

Re: Ask HN: Cursor or Windsurf?

#39
I’ve been using Zed Agent with GitHub Copilot’s models, but with GitHub planning to limit usage, I’m exploring alternatives.

Now I'm testing Claude Code’s $100 Max plan. It feels like magic - editing code and fixing compile errors until it builds. The downside is I’m reviewing the code a lot less since I just let the agent run.

So far, I’ve only tried it on vibe coding game development, where every model I’ve tested struggles. It says “I rewrote X to be more robust and fixed the bug you mentioned,” yet the bug still remains.

I suspect it will work better for backend web development I do for work: write a failing unit test, then ask the agent to implement the feature and make the test pass.

Also, give Zed’s Edit Predictions a try. When refactoring, I often just keep hitting Tab to accept suggestions throughout the file.

Re: Ask HN: Cursor or Windsurf?

#40

Aider! Use the editor of your choice and leave your coding assistant separate. Plus, it's open source and will stay like this, so no risk to see it suddenly become expensive or dissappear.

Yup, choose your model and pay as you go, like commodities like rice and water. The others played games with me to minimize context and use cheaper models (such as 3 modes, daily credits etc, using most expensive model etc). Also the --watch mode is the most productive interface of using your editor, no need of extra textboxes with robot faces.

fwiw. Gemini-*, which is available in Aider, isn't Pay As You Go (payg) but post paid, which means you get a bill at the end of the month and not the OpenAI/others model of charging up credits before you can use the service.
Post reply on HN