[itchyouch]

What’s interesting to me is that the conversational nature of the LLM tends to lead folks down an unproductive convo path.

“Don’t do X” is just as useful as telling an infant not to cry.

When an infant cries, we implicitly understand there is a form of discomfort to address (food, diaper, etc).

To me, when a LLM fails, it signals to me that the architecture and structure of the code is problematic and that needs to be addressed.

Any seasoned dev can usually see non-DRY, non-KISS patterns, then will structure an encapsulation around said pattern to address issues.

I’ve found that this same type of refactoring is needed in LLM code to improve its outcomes, of which then it’s capable of overcoming the bugs.

Simply telling the LLM to refactor for cleanliness in between code generation runs will do so much for maintainability.