Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I haven't used Aider before, but I've found it hard to get LLMs to produce syntactically correct diffs. Do you face this problem when using Aider?



Aider has a configuration for each supported LLM to define the best diff format for each; so for certain ones they're best at diff format, Gemini is best at a fenced-diff format, Qwen3 is best at whole file editing, etc. Aider itself examines the diff and re-runs the request when the request when the response doesn't adhere to the corresponding diff format.

Edit: Also the Aider leaderboards show the success rate for diff adherence separately, it's quite useful [1]

1 - https://aider.chat/docs/leaderboards/


so now we need an AI to configure our AIs ?




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

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

Search: