[dead]
Ask HN: Cursor or Windsurf?
371–380 of 410 posts
Re: Ask HN: Cursor or Windsurf?
#372Re: Ask HN: Cursor or Windsurf?
#373Re: Ask HN: Cursor or Windsurf?
#374I feel a bit out of place here, as I’m not a dev… I come from the operational side, but do all my work in Puppet code. I was using Codeium + VSC and life was wonderful. One day, though, everything updated and Codeium was gone in favor of Windsurf and things got crazy. VSC no longer understood Puppet code and didn’t seem to be able to access the language tools from the native Puppet Development Kit plugins either.
The crazy part is my Vim setup has the Codeium plugins all still in place, and it works perfectly. I’m afraid if I update the plugin to a windsurf variant, it will completely “forget” about Puppet, its syntax, and everything it has “learned” from my daily workflow over the last couple years.
Has anyone else seen anything similar?
Re: Ask HN: Cursor or Windsurf?
#375Re: Ask HN: Cursor or Windsurf?
#376The only thing preventing me to keep using Cursor/Windsurf it's the lack of sync feature. I use different machines and it's crucial to keep the same exact configuration on each of them :(
Re: Ask HN: Cursor or Windsurf?
#377Earlier quoted context omitted.
Cursor does something with truncating context to save costs on their end, you dont get the same with Cline because you're paying for each transaction - so depending on complexity I find Cline works significantly better. I still use cursor chat with agent mode though, but I've always been indecisive. Like the others said though, its nice to see how cline behaves to assist with creating your own agentic workflows.
> 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.
Re: Ask HN: Cursor or Windsurf?
#378Regardless of which, my favorite model is ChatGPT's. I feel they're the only ones talking to customers. The other models are not as pleasant to work with as a software engineer.
Re: Ask HN: Cursor or Windsurf?
#379Notepad++
best
Re: Ask HN: Cursor or Windsurf?
#380Earlier quoted context omitted.
Just use codex and machtiani (mct). Both are open source. Machtiani was open sourced today. Mct can find context in a hay stack, and it’s efficient with tokens. Its embeddings are locally generated because of its hybrid indexing and localization strategy. No file chunking. No internet, if you want to be hardcore. Use any inference provider, even local. The demo video shows solving an issue VSCode codebase (of 133,000…
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 and problems with the changes if necessary."
2. Codex and MCT together
`codex "$(mct 'fix bad response on h2 server' --model deepseek/deepseek-r1 --mode answer-only)"`
In this case codex will dutifully implement the suggested changes of codex, saving tokens and time.
The key for the second example is `--mode answer-only`. Without this flagged argument, mct will itself try and apply patches. But in this case codex will do it as mct withholds the patches with the aforementioned flagged arg.
3. Refer codex to the chat.
Say you did this
`mct "fix bad response on h2 server" --model gpt-4o-mini --mode chat`
Here, I used `--mode chat`, which tells mct to stream the answer and save the chat convo, but not to apply git changes (differrent than --mode answer-only).
You'll see mct will printout that something like
`Response saved to .machtiani/chat/fix_bad_server_resonse.md`
Now you can just tell codex.
`codex "See .machtiani/chat/fix_bad_server_resonse.md, and do this or that...."`
*Conclusion*
The example concepts should cover day-to-day use cases. There are other exciting workflows, but I should really post a video on that. You could do anything with unix philosophy!