DeepSeek Coder: Let the Code Write Itself

Re:DeepSeek Coder: Let the Code Write Itself by anotherpaulg on Wednesday January 31, 2024 @09:54PM (#39212298)

You could try using aider [0], which is my open source ai coding tool. You need an OpenAI API key, and aider supports any of the GPT 3.5 or 4 models. Aider has features that make it work well with existing code bases, like git integration and a "repository map". The repo map is used to send GPT-4 a distilled map of your code base, focused specifically on the coding task at hand [1]. This provides useful context so that GPT can understand the relevant parts of the larger code base when making a specific change.

[0] https://github.com/paul-gauthier/aider

[1] https://aider.chat/docs/repomap.html

[ Parent | on HN ]

Re:DeepSeek Coder: Let the Code Write Itself by pests on Thursday February 01, 2024 @03:45AM (#39213920)

I second this. Great tool. I always plug your tool in these threads too when relevant. The tree-sitter repo map was a great change. Thank you.

[ Parent | on HN ]

Re:DeepSeek Coder: Let the Code Write Itself by jstummbillig on Thursday February 01, 2024 @04:33AM (#39214167)

I gave aider an afternoon this week (which is not a lot of time to learn anything, of course). It did too many wild things to the project and repository I was using it with (Rails 7 base) to comfortably explore this further – for now.

Paul, if you are up for that, it would be tremendously helpful to have a video(series) that shows what aider can realistically do given a boring, medium sized CRUD code base. The logs in the examples are too narrow and also build not intuition about what to do when things go wrong.

[ Parent | on HN ]

Re:DeepSeek Coder: Let the Code Write Itself by anotherpaulg on Thursday February 01, 2024 @01:24PM (#39219335)

Thanks for trying aider, and sorry to hear you had trouble getting the hang of it. It might be worth looking through some of the tips on the aider github page:

https://github.com/paul-gauthier/aider#tips

In particular, this is one of the most important tips: Large changes are best performed as a sequence of thoughtful bite sized steps, where you plan out the approach and overall design. Walk GPT through changes like you might with a junior dev. Ask for a refactor to prepare, then ask for the actual change. Spend the time to ask for code quality/structure improvements.

Not sure if this was a factor in your attempts? But it's best not to ask for a big sweeping change all at once. It's hard to unambiguously and completely specify what you want, and it's also harder for GPT to succeed at bigger changes in one bite.

[ Parent | on HN ]