Maybe I’m contrarian but I design and write most of my code and let LLMs do the reviews. Why?
First I know my problem space better than the LLM.
Second, the best way to express coding intention is with code. The models often have excellent suggestions on improvements I wouldn’t have thought of. I suspect the probability of providing a good answer has been increased significantly by narrowing the scope.
Another technique is to say “do this like <some good project> does it” but I suspect that might be close to copyright theft.
First I know my problem space better than the LLM.
Second, the best way to express coding intention is with code. The models often have excellent suggestions on improvements I wouldn’t have thought of. I suspect the probability of providing a good answer has been increased significantly by narrowing the scope.
Another technique is to say “do this like <some good project> does it” but I suspect that might be close to copyright theft.