Hacker News new | past | comments | ask | show | jobs | submit login

I'm SO surprised to not see aider-chat everywhere mentionned.

I've been using it for about a year and it's incredible.

My take is that most people did not invest the little time necessary to get acustomed to its workflow.

My advices for aider are:

- familiarize yourself with the chat modes (architect, code, ask)

- familiarize yourself with the edit modes (diff, whole, etc) and know which to use for a given model. Indeed not all models handle all modes equally well.

- make the code one feature at a time, by small chunks if needed, by limiting the contxt to the relevant files.

- practice to learn how to best phrase stuff.

- write you coding preferences into aider convention files. Things like "always use type hints, beartype for type checking, python click for the cli, add many comments".

I'm mainly doing python and with proper comments and type hints it's really easy for models to write code that works with the rest of the repo even with only a few files in its context.






Same here, I'd even say you made the learning curve sound worse than it is, no offence :)

This is my workflow for 90% of tasks:

1) /ask: I want to do X. / How would you do X? / What options do I have for X?

2) (optional) /ask>: make these adaptations / consider this / follow up question.

3) "go ahead" (this defaults to /code mode)

For a model I like the style of Sonnet3.7 best.

One caveat: I add my files manually. Knowing what you want and where you want it is 90% of the game and this is where LLMs usually get it wrong.


Do you find that the time you spend splitting a feature up into small chunks and explaining each small chunk to the LLM takes longer than just writing the code yourself?

I've used aider but found just pounding out some code in neovim to be faster. Perhaps I'm not using aider correctly.


I do think that it can take maybe a little more time with aider but this time investment pays itself off as soon as there is some complexification or issue that LLMs can't fix.

See, if you have no idea of what kind of architecture was used for the passed 150 commits, it will take more time to debug or see if a given new featufe you have in mind is doable without major refactoring for example.

This will probably matter less as LLMs grow more powerful I admit


Aider is to other AI tools what Vim/Neovim is to other IDEs. Super powerful, but with a learning curve most folks don’t want to climb.

https://github.com/hotovo/aider-desk is a gui, takes 5 mins to install, has MCP support (try context7). Definitely worth a look and is an "easy" way in to aider.

This is exactly how I use agent mode in Cursor. I’ve never understood why I would use aider. Am I missing something else?

Possibly: I'm a neovim person and barely leave the terminal. So naturally aider fits perfectly into my setup. There are even neovim plugin for having aider directly in it.

That said, I don't get why people are fine switching their IDE to cursor. Lile, if you're in an IDE it's because it has features you want that others didn't. So either cursor does not have them or if it does then you have to configure the whole cursor IDE to work like your original IDE.

In total you've either lost features or been captured into a new walled garden. And lost some time in the process.

Aider's use of litellm makes it 5s change to switch to the latest models. And it's always up to date thanks to uvx.

No really I don't get why people are not using aider more.

Plus the dev is lovely, responsive and helpful.


Cursor is a VS Code fork. Anyone coming from VS Code, one of the most popular editors in the ecosystem, will immediately be comfortable. The full marketplace of extensions is compatible. The switchover is effectively seamless besides a handful of keyboard shortcuts used for the new AI features.



Consider applying for YC's Summer 2025 batch! Applications are open till May 13

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: