Live data from Hacker News

Ask HN: Cursor or Windsurf?

news.ycombinator.com

81–90 of 410 posts

Re: Ask HN: Cursor or Windsurf?

#81
I just use Copilot (across VS Code, VS etc), it lets you pick the model you want and it's a fixed monthly cost (and there is a free tier). They have most of the core features of these other tools now.

Cursor, Windsurf et al have no "moat" (in startup speak), in that a sufficiently resourced organization (e.g. Microsoft) can just copy anything they do well.

VS code/Copilot has millions of users, cursor etc have hundreds of thousands of users. Google claims to have "hundreds of millions" of users but we can be pretty sure that they are quoting numbers for their search product.

Re: Ask HN: Cursor or Windsurf?

#82
post #62

Since this topic is closely related to my new project, I’d love to hear your opinion on it. I’m thinking of building an AI IDE that helps engineers write production quality code quickly when working with AI. The core idea is to introduce a new kind of collaboration workflow. You start with the same kind of prompt, like “I want to build this feature...”, but instead of the model making changes right away, it proposes…

I quite liked the video. Hope you get to launch the product and I could try it out some day.

The only thing that I kept thinking about was - if there is a correction needed- you have to make it fully by hand. Find everything and map. However, if the first try was way off , I would like to enter from "midpoint" a correction that I want. So instead of fixing 50%, I would be left with maybe 10 or 20. Don't know if you get what I mean.

Re: Ask HN: Cursor or Windsurf?

#83

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,…

If we’re talking purely auto complete I think Supermaven does it the best.

Re: Ask HN: Cursor or Windsurf?

#85
post #82
post #62

Since this topic is closely related to my new project, I’d love to hear your opinion on it. I’m thinking of building an AI IDE that helps engineers write production quality code quickly when working with AI. The core idea is to introduce a new kind of collaboration workflow. You start with the same kind of prompt, like “I want to build this feature...”, but instead of the model making changes right away, it proposes…

I quite liked the video. Hope you get to launch the product and I could try it out some day. The only thing that I kept thinking about was - if there is a correction needed- you have to make it fully by hand. Find everything and map. However, if the first try was way off , I would like to enter from "midpoint" a correction that I want. So instead of fixing 50%, I would be left with maybe 10 or 20. Don't know if you g…

Yes, the idea is to ‘speak/write’ to the local model to fix those little things so you don’t have to do them by hand. I actually already have a fine-tuned Qwen model running on Apple’s MLX to handle some of that, but given the hard YC deadline, it didn’t make it into the demo.

Eventually, you’d say, ‘add an additional layer, TopicsController, between those two files,’ and the local model would do it quickly without a problem, since it doesn’t involve complicated code generation. You’d only use powerful remote models at the end.

Re: Ask HN: Cursor or Windsurf?

#87
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.

Agreed. You may like the arms-length stuff here: https://github.com/day50-dev/llmehelp . shell-hook.zsh and screen-query have been life-changing

I always forget syntax for things like ssh port forwarding. Now just describe it at the shell:

$ ssh (take my local port 80 and forward it to 8080 on the machine betsy) user@betsy

or maybe:

$ ffmpeg -ss 0:10:00 -i somevideo.mp4 -t 1:00 (speed it up 2x) out.webm

I press ctrl+x x and it will replace the english with a suggested command. It's been a total game changer for git, jq, rsync, ffmpeg, regex..

For more involved stuff there's screen-query: Confusing crashes, strange terminal errors, weird config scripts, it allows a joint investigation whereas aider and friends just feels like I'm asking AI to fuck around.

Re: Ask HN: Cursor or Windsurf?

#88
post #62

Since this topic is closely related to my new project, I’d love to hear your opinion on it. I’m thinking of building an AI IDE that helps engineers write production quality code quickly when working with AI. The core idea is to introduce a new kind of collaboration workflow. You start with the same kind of prompt, like “I want to build this feature...”, but instead of the model making changes right away, it proposes…

Just watched the demo video and thought it is a very interesting approach to development, I will definitely be following this project. Good Luck.

Re: Ask HN: Cursor or Windsurf?

#89

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,…

If we’re talking purely auto complete I think Supermaven does it the best.

Cursor bought Supermaven last year.
Post reply on HN