Has anyone had any joy using a local model? Or is it still too slow?
On something like a M4 Macbook Pro can local models replace the connection to OpenAi/Anthropic?
Ask HN: Cursor or Windsurf?
131–140 of 410 posts
Re: Ask HN: Cursor or Windsurf?
#132Earlier quoted context omitted.
Approximately how much does it cost in practice to use Aider? My understanding is that Aider itself is free, but you have to pay per token when using an API key for your LLM of choice. I can look up for myself the prices of the various LLMs, but it doesn't help much, since I have no intuition whatsoever about how many tokens I am likely to consume. The attraction of something like Zed or Cursor for me is that I just…
I'm using Gemini 2.5 Pro with Aider and Cline for work. I'd say when working for 8 full hours without any meetings or other interruptions, I'd hit around $2. In practice, I average at $0.50 and hit $1 once in the last weeks.
This is very inexpensive. What is your workflow and savings techniques! I can spend $10/h or more with very short sessions and few files.
Re: Ask HN: Cursor or Windsurf?
#133It might seem contrary to the current trend, but I've recently returned to using nvim as my daily driver after years with VS Code. This shift wasn't due to resource limitations but rather the unnecessary strain from agentic features consuming high amounts of resources.
Re: Ask HN: Cursor or Windsurf?
#134Cursor is good for basic stuff but Windsurf consistently solves issues Cursor fails on even after 40+ mins of retries and prompting changes.
Cursor is very lazy about looking beyond the current context or even context at all sometimes it feels it’s trying to one shot a guess without looking deeper.
Bad thing about Windsurf is the plans are pretty limited and the unlimited “cascade base” feels dumb the times I used it so ultimately I use Cursor until I hit a wall then switch to Windsurf.
Re: Ask HN: Cursor or Windsurf?
#135I'm with Cursor for the simple reason it is in practice unlimited. Honestly the slow requests after 500 per month are fast enough. Will I stay with Cursor? No, ill switch the second something better comes along.
I'm cursor with claude 3.7
Somehow other models don't work as well with it. ,,auto'' is the worst.
Still, I hate it when it deletes all my unit tests to ,,make them pass''
Re: Ask HN: Cursor or Windsurf?
#136Earlier quoted context omitted.
Depends entirely on the API. With deepseek: ~nothing.
is deepseek fast enough for you? For me the API is very slow, sometimes unusable
To be honest I'm using windsurf with openAI/google right now and used deepseek with aider when it was still less crowded.
My only problem was deepseek occasionally not answering at all, but generally it was fast (non thinking that was).
Re: Ask HN: Cursor or Windsurf?
#137Neither? 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.
Having it as tab was a mistake, tab complete for snippets is fine because it’s at the end of a line, tab complete in empty text space means you always have to be aware if it’s in autocomplete context or not before setting an indent.
Re: Ask HN: Cursor or Windsurf?
#138Currently using cursor. I've found cursor even without the AI features to be a more responsive VS Code. I've found the AI features to be particularly useful when I contain the blast radius to a unit of work. If I am continuously able to break down my work into smaller pieces and build a tight testing loop, it does help me be more productive.
How do you define a unit of work for your purposes?
Re: Ask HN: Cursor or Windsurf?
#139Neither? 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.
AI autocomplete can be infuriating if like me, you like to browse the public methods and properties by dotting the type. The AI autocomplete sometimes kicks in and starts writing broken code using suggestions that don't exist and that prevents quickly exploring the actual methods available.
I have largely disabled it now, which is a shame, because there are also times it feels like magic and I can see how it could be a massive productivity lever if it needed a tighter confidence threshold to kick in.
Re: Ask HN: Cursor or Windsurf?
#140Windsurf - the repo code awareness is much higher than Cursor.