Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Cursor or Windsurf?

news.ycombinator.com

Post reply on HN
Print view View original

51–60 of 410 posts

Re: Ask HN: Cursor or Windsurf?

#51

Post by pembrook »

For a time windsurf was way ahead of cursor in full agentic coding, but now I hear cursor has caught up. I have yet to switch back to try out cursor again but starting to get frustrated with Windsurf being restricted to gathering context only 100-200 lines at a time.

So many of the bugs and poor results that it can introduce are simply due to improper context. When forcibly giving it the necessary context you can clearly see it’s not a model problem but it’s a problem with the approach of gathering disparate 100 line snippets at a time.

Also, it struggles with files over 800ish lines which is extremely annoying

We need some smart deepseek-like innovation in context gathering since the hardware and cost of tokens is the real bottleneck here.

Re: Ask HN: Cursor or Windsurf?

#52

Post by hliyan »

I think with the answer, each responder should include their level of coding proficiency. Or, at least whether they are able to (or even bother to) read the code that the tool generates. Preferences would vary wildly based on it.

Re: Ask HN: Cursor or Windsurf?

#53

Post by eadz »

dvtfl wrote: post #34
wellthisisgreat wrote: post #25

Earlier quoted context omitted.

Does it have Cursor’s “tab” feature?

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

It would be great if there was an easy way to run their open model (https://huggingface.co/zed-industries/zeta) locally ( for latency reasons ).

I don't think Zeta is quite up to windsurf's completion quality/speed.

I get that this would go against their business model, but maybe people would pay for this - it could in theory be the fastest completion since it would run locally.

Re: Ask HN: Cursor or Windsurf?

#54

Post by eadz »

anonymoushn wrote: post #16

I evaluated Windsurf at a friend's recommendation around half a year ago and found that it could not produce any useful behaviors on files above a thousand lines or so. I understand this is mostly a property of the model, but certainly also a property of the approach used by the editor of just tossing the entire file in, yeah? I haven't tried any of these products since then, but it might be worth another shot becaus…

A year is a long time. Even in the past few months it has improved a lot.

Re: Ask HN: Cursor or Windsurf?

#56

Post by killerstorm »

Cursor: Autocomplete is really good. At a time when I compared them, it was without a doubt better than Githib Copilot autocomplete. Cmd-K - insert/edit snippet at cursor - is good when you use good old Sonnet 3.5. ;;; Agent mode, is, honestly, quite disappointing; it doesn't feel like they put a lot of thought into prompting and wrapping LLM calls. Sometimes it just fails to submit code changes. Which is especially bad as they charge you for every request. Also I think they over-charge for Gemini, and Gemini integration is especially poor.

My reference for agent mode is Claude Code. It's far from perfect, but it uses sub-tasks and summarization using smaller haiku model. That feels way more like a coherent solution compared to Cursor. Also Aider ain't bad when you're OK with more manual process.

Windsurf: Have only used it briefly, but agent mode seems somewhat better thought out. For example, they present possible next steps as buttons. Some reviews say it's even more expensive than Cursor in agent mode.

Re: Ask HN: Cursor or Windsurf?

#57

Post by powerapple »

I tested windsurf last week, it installed all dependencies to my global python....it didn't know best practices for Python, and didn't create any virtual env..... I am disappointed. My Cursor experience was slightly better. Still, one issue I had was how to make sure it does not change the part of code I don't want it to change. Every time you ask it to do something for A, it rewrote B in the process, very annoying.

My best experience so far is v0.dev :)

Re: Ask HN: Cursor or Windsurf?

#59

Post by mirekrusin »

bilekas wrote: post #38
outcoldman wrote: post #8

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.

AI aided development has first class support in Zed.

Ie. it's not a "plugin" but built-in ecosystem developed by core team.

Speed of iterations on new features is quite impressive.

Their latest agentic editing update basically brought claude code cli to the editor.

Most corporations don't have direct access to arbitrary LLMs but through Microsoft's Github's Copilot they do – and you can use models through copilot and other providers like Ollama – which is great for work.

With their expertise (team behind pioneering tech like electron, atom, teletype, tree sitter, building their own gpu based cross platform ui etc.) and velocity it seems that they're positioned to outpace competition.

Personally I'd say that their tech is maybe two orders of magnitude more valuable than windsurf?

Post reply on HN