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

391–400 of 410 posts

Re: Ask HN: Cursor or Windsurf?

#391

Post by nsonha »

nlh wrote: post #377
nsonha wrote: post #352

Earlier quoted context omitted.

> 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)

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.

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.

Re: Ask HN: Cursor or Windsurf?

#392

Post by asar »

machtiani-chat wrote: post #380
asar wrote: post #369

Earlier quoted context omitted.

This sounds really cool. Can you explain your workflow in a bit more detail? i.e. how exactly you work with codex to implement features, fix bugs etc.

Say I'm chatting in a git project directory `undici`. I can show you a few ways how I work with codex. 1. Follow up with Codex. `mct "fix bad response on h2 server" --model anthropic/claude-3.7-sonnet:thinking` Machtiani will stream the answer, then also apply git patches suggested in the convo automatically. Then I could follow up with codex. `codex "See unstaged git changes. Run tests to make sure it works and fix…

Amazing, really excited to try this out. And thanks for the time you took to write this up!

Re: Ask HN: Cursor or Windsurf?

#393

Post by WA »

dexterlagan wrote: post #254

You need none of these fancy tools if you iterate over specs instead of iterating over code. I explain it all in here: https://www.cleverthinkingsoftware.com/spec-first-developmen...

I played around with your suggestion for a day or two now. While I'm intrigued, there are some real-world issues with this approach:

- The same spec is processed by the same LLM differently when implementing from scratch. This can maybe mitigated somewhat by adjusting the temperature slider. But generally speaking, the same spec won't give the same result unless you are very specific.

- Same if you use different LLMs. The same spec can give entirely different results for different LLMs.

- This can probably mitigated somewhat by getting more specific in the spec, but at some point, it is so specific as being the code itself. Unless of course you don't care that much about the details. But if you don't, you get a slightly different app every time you implement from scratch.

- Gemini 2.5 pro has "reasoning" capabilities and introduces a lot of "thinking" tokens into the context. Let's say you start with a single line spec and iterate from there. Gemini will give you a more detailed spec based on its thinking process. But if you then take the new thinking-process spec as a new starting point for the next iteration of the spec, you get even more thinking. In short, the spec gets automatically expanded by the way of "thinking" with reasoning models.

- Produced code can have small bugs, but they are not really worth to put in the spec, because they are an implementation detail.

I'll keep experimenting with it, but I don't think this is the holy grail of AI assisted coding.

Re: Ask HN: Cursor or Windsurf?

#394

Post by chipsrafferty »

Draiken wrote: post #268
elAhmo wrote: post #148

Earlier quoted context omitted.

Cursor/Windsurf and similar IDEs and plugins are more than autocomplete on steroids. Sure, you might not like it and think you as a human should write all code, but frequent experience in the industry in the past months is that productivity in the teams using tools like this has greatly increased. It is not unreasonable to think that someone deciding not to use tools like this will not be competitive in the market in…

Where are these amazing productivity increases? Where is this 2x, 10x or even 1.5x increase in output? I don't see more products, more features, less bugs or anything related to that since this "AI revolution". I keep seeing this being repeated ad nauseam without any real backing of hard evidence. It's all copium. Surely if everyone is so much more productive, a single person startup is now equivalent to 1 + X right?…

There's a bottleneck from all the other roles. Project managers, designers, etc.

The impact in the real world isn't more product output, it's less developers needed for the same output.

Re: Ask HN: Cursor or Windsurf?

#395

Post by dexterlagan »

WA wrote: post #393
dexterlagan wrote: post #254

You need none of these fancy tools if you iterate over specs instead of iterating over code. I explain it all in here: https://www.cleverthinkingsoftware.com/spec-first-developmen...

I played around with your suggestion for a day or two now. While I'm intrigued, there are some real-world issues with this approach: - The same spec is processed by the same LLM differently when implementing from scratch. This can maybe mitigated somewhat by adjusting the temperature slider. But generally speaking, the same spec won't give the same result unless you are very specific. - Same if you use different LLMs…

Thanks for the feedback! Agreed, the one problem with the approach is reproducibility. It can be mitigated by going temp. 0, and detailing further the specs. The one method that nearly completely solves this problem is the hybrid approach: Write detailed specs, feed them to the LLM, get an MVP (or module etc); fix any and all issues found with the MVP, implement missing/new features; ask the LLM to update the specs to take the changes in account, also recording the lessons learned - and maximize reproducibility. Treat the latest specs + code package as a checkpoint you can always resume work from.

Re: Ask HN: Cursor or Windsurf?

#396

Post by WA »

dexterlagan wrote: post #395
WA wrote: post #393

Earlier quoted context omitted.

I played around with your suggestion for a day or two now. While I'm intrigued, there are some real-world issues with this approach: - The same spec is processed by the same LLM differently when implementing from scratch. This can maybe mitigated somewhat by adjusting the temperature slider. But generally speaking, the same spec won't give the same result unless you are very specific. - Same if you use different LLMs…

Thanks for the feedback! Agreed, the one problem with the approach is reproducibility. It can be mitigated by going temp. 0, and detailing further the specs. The one method that nearly completely solves this problem is the hybrid approach: Write detailed specs, feed them to the LLM, get an MVP (or module etc); fix any and all issues found with the MVP, implement missing/new features; ask the LLM to update the specs t…

I'll give it a try, thanks.

Edit: Do you use reasoning models that introduce way more tokens into the context at all or prefer simpler models?

Re: Ask HN: Cursor or Windsurf?

#397

Post by enceladus06 »

submeta wrote: post #72
danpalmer wrote: post #9

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.

Consumes lots of resources on an M4 Macbook. Would love to test it though. If it didn’t freeze my Macbook. Edit: With the latest update to 0.185.15 it works perfectly smooth. Excellent addition to my setup.

Are you running ollama local model or one of the zed llms?

Re: Ask HN: Cursor or Windsurf?

#398

Post by jbellis »

evnix wrote: post #367
jbellis wrote: post #176

Earlier quoted context omitted.

I love Aider, but I got frustrated with its limitations and ended up creating Brokk to solve them: https://brokk.ai/ Compared to Aider, Brokk - Has a GUI (I know, tough sell for Aider users but it really does help when managing complex projects) - Builds on a real static analysis engine so its equivalent to the repomap doesn't get hopelessly confused in large codebases - Has extremely useful git integration (view git…

Apart from the GUI, What does it improve on when compared to aider.

Short answer: static analysis

Long answer: https://brokk.ai/blog/lean-context-lightning-development

Re: Ask HN: Cursor or Windsurf?

#399

Post by DANmode »

nlh wrote: post #377
nsonha wrote: post #352

Earlier quoted context omitted.

> 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)

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.

aka any deep work is getting done.
Post reply on HN