←back to thread

A Software Development Methodology for Disciplined LLM Collaboration

(github.com)
97 points jay-baleine | 1 comments | 06 Sep 25 10:47 UTC | HN request time: 0s | source
Show context
mehdibl ◴[06 Sep 25 13:55 UTC] No.45149306[source]▶
The most important you need always to do:

1. Plan, review the plan.

2. Review the code during changes before even it finish and fix ASAP you see drift.

3. Then again review

4. Add tests & use all quality tools don't rely 100% on LLM.

5. Don't trust LLM reviews for own produced code as it's very biased.

This is basic steps that you do as you like.

Avoid FULL AUTOMATED AGENT pipeline where you review the code only at the end unless it's very small task.

replies(2): >>45149757 #>>45158720 #
1. CuriouslyC ◴[06 Sep 25 14:48 UTC] No.45149757[source]▶
LLMs can review their own code, but you must have a fresh context (so they don't know they wrote it) and you need to instruct them to be very strict. Also, some models are better at code review than others, Gemini/GPT5 are very good at it as long as you give them sufficient codebase context, Claude is not so great here.