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

231–240 of 410 posts

Re: Ask HN: Cursor or Windsurf?

#231

Post by artdigital »

I find Windsurf almost unusable. It’s hard to explain but the same models in Zed, Windsurf, Copilot and Cursor produce drastically worse code in Windsurf for whatever reason. The agent also tends to do way more stupid things at random, like wanting to call MCP tools, creating new files, then suddenly forgetting how to use tools and apologizing a dozen times

I can’t really explain or prove it, but it was noticeable enough to me that I canceled my subscription and left Windsurf

Maybe a prompting or setting issue? Too high temperature?

Nowadays Copilot got good enough for me that it became my daily driver. I also like that I can use my Copilot subscription in different places like Zed, Aider, Xcode

Re: Ask HN: Cursor or Windsurf?

#232

Post by mirekrusin »

venatiodecorus wrote: post #224
frainfreeze wrote: post #182

Earlier quoted context omitted.

I was under impression Zed had native LLM integration, built into the editor?

yes, its now built in. i haven't had a chance to use it much yet, it was released fairly recently.

Agentic editing was released recently yes, llm integration was there for much longer. It supported editing but it was more manual – context of conversation from chat was basically available in in-line editing so you could edit code based on llm output but it was more manual process, now it's agentic.

Re: Ask HN: Cursor or Windsurf?

#233

Post by drob518 »

imiric wrote: post #117
welder wrote: post #75

Neither? I'm surprised nobody has said it yet. I turned off AI autocomplete, and sometimes use the chat to debug or generate simple code but only when I prompt it to. Continuous autocomplete is just annoying and slows me down.

This is the way. All this IDE churn makes me glad to have settled on Emacs a decade ago. I have adopted LLMs into my workflow via the excellent gptel, which stays out of my way but is there when I need it. I couldn't imagine switching to another editor because of some fancy LLM integration I have no control over. I have tried Cursor and VS Codium with extensions, and wasn't impressed. I'd rather use an "inferior" edi…

I’ve been using Aidermacs to access Aider in Emacs and it works quite well and makes lots of LLMs available. Claude Sonnet 3.7 has been reasonable for code generation, though there are certainly tasks that it seems to struggle on.

Re: Ask HN: Cursor or Windsurf?

#234

Post by kaycey2022 »

nsteel wrote: post #145
welder wrote: post #75

Neither? I'm surprised nobody has said it yet. I turned off AI autocomplete, and sometimes use the chat to debug or generate simple code but only when I prompt it to. Continuous autocomplete is just annoying and slows me down.

I can't even get simple code generation to work for VHDL. It just gives me garbage that does not compile. I have to assume this is not the case for the majority of people using more popular languages? Is this because the training data for VHDL is far more limited? Are these "AIs" not able to consume the VHDL language spec and give me actual legal syntax at least?! Or is this because I'm being cheap and lazy by only t…

Its all of that to some extent or the other. LLMs don't update overnight and as such lag behind innovations in major frameworks, even in web development. No matter what is said about augmenting their capabilities, their performance using techniques like RAG seem to be lacking. They don't work well with new frameworks either.

Any library that breaks backwards compatibility in major version releases will likely befuddle these models. That's why I have seen them pin dependencies to older versions, and more egregiously, default to using the same stack to generate any basic frontend code. This ignores innovations and improvements made in other frameworks.

For example, in Typescript there is now a new(ish) validation library call arktype. Gemini 2.5 pro straight up produces garbage code for this. The type generation function accepts an object/value. But gemini pro keeps insisting that it consumes a type.

So Gemini defines an optional property as `a?: string` which is similar to what you see in Typescript. But this will fail in arktype, because it needs it input as `'a?': 'string'`. Asking gemini to check again is a waste of time, and you will need enough familiarity with JS/TS to understand the error and move ahead.

Forcing development into an AI friendly paradigm seems to me a regressive move that will curb innovation in return for boosts in junior/1x engineer productivity.

Re: Ask HN: Cursor or Windsurf?

#235

Post by cube00 »

kaycey2022 wrote: post #234
nsteel wrote: post #145

Earlier quoted context omitted.

I can't even get simple code generation to work for VHDL. It just gives me garbage that does not compile. I have to assume this is not the case for the majority of people using more popular languages? Is this because the training data for VHDL is far more limited? Are these "AIs" not able to consume the VHDL language spec and give me actual legal syntax at least?! Or is this because I'm being cheap and lazy by only t…

Its all of that to some extent or the other. LLMs don't update overnight and as such lag behind innovations in major frameworks, even in web development. No matter what is said about augmenting their capabilities, their performance using techniques like RAG seem to be lacking. They don't work well with new frameworks either. Any library that breaks backwards compatibility in major version releases will likely befuddl…

It's fun watching the AI bros try to spin justifications for building (sorry, vibing) new apps using Ruby for no reason other then the model has so much content back to 2004 to train off.

Re: Ask HN: Cursor or Windsurf?

#236

Post by drob518 »

nsteel wrote: post #145
welder wrote: post #75

Neither? I'm surprised nobody has said it yet. I turned off AI autocomplete, and sometimes use the chat to debug or generate simple code but only when I prompt it to. Continuous autocomplete is just annoying and slows me down.

I can't even get simple code generation to work for VHDL. It just gives me garbage that does not compile. I have to assume this is not the case for the majority of people using more popular languages? Is this because the training data for VHDL is far more limited? Are these "AIs" not able to consume the VHDL language spec and give me actual legal syntax at least?! Or is this because I'm being cheap and lazy by only t…

The amount of training data available certainly is a big factor. If you’re programming in Python or JavaScript, I think the AIs do a lot better. I write in Clojure, so I have the same problem as you do. There is a lot less HDL code publicly available, so it doesn’t surprise me that it would struggle with VHDL. That said, from everything I’ve read, free ChatGPT doesn’t do as well on coding. OpenAI’s paid models are better. I’ve been using Anthropic’s Claude Sonnet 3.7. It’s paid but it’s very cost effective. I’m also playing around with the Gemini Pro preview.

Re: Ask HN: Cursor or Windsurf?

#237

Post by aaomidi »

welder wrote: post #75

Neither? I'm surprised nobody has said it yet. I turned off AI autocomplete, and sometimes use the chat to debug or generate simple code but only when I prompt it to. Continuous autocomplete is just annoying and slows me down.

Honestly, the only files I like this turned on is unit tests.

Re: Ask HN: Cursor or Windsurf?

#238

Post by zaphar »

tough wrote: post #208
imiric wrote: post #186

Earlier quoted context omitted.

Why should the Emacs community care whether someone decides to build a custom editor with AI features? If anything this would bring more interest and development into the ecosystem, which everyone would benefit from. Anyone not interested can simply ignore it, as we do for any other feature someone implements into their workflow.

what i find interesting is why is nobody building llms trained on using the shell and PTY at its full right now its dumb unix piping only I want an AI that can use emacs or vim with me

There are several neovim mcp providers that expose bash and neovim as a tool so you can already do that.

Re: Ask HN: Cursor or Windsurf?

#239

Post by vijucat »

If you have any intellectual property worth protecting or need to comply with HIPAA, a completely local installation of Cline or Aider or Codeium with LM Studio with Qwen or DeepSeek Coder works well. If you'd rather not bother, I don't see any option to GitHub Copilot for Business. Sure, they're slower to catch up to Cursor, but catch up they will.

https://github.com/features/copilot/plans?cft=copilot_li.fea...

Re: Ask HN: Cursor or Windsurf?

#240

Post by cube00 »

vitro wrote: post #160
welder wrote: post #75

Neither? I'm surprised nobody has said it yet. I turned off AI autocomplete, and sometimes use the chat to debug or generate simple code but only when I prompt it to. Continuous autocomplete is just annoying and slows me down.

I had turned autocomplete off as well. Way too many times it was just plain wrong and distracting. I'd like it to be turned on for method documentation only, though, where it worked well once the method was completed, but so far I wasn't able to customize it this way.

I've be very surprised if the LLM is correctly identifying the "why" that method documentation should capture.
Post reply on HN