The focus lies on the quality and maintainability of code merged into a codebase, rather than the method by which it was generated. There are distinct patterns indicating that code has been generated by an LLM, particularly when it diverges from established project conventions. While the outcomes are satisfactory, such code might implement unnecessary features or configurations that contradict existing standards. The emphasis is on adherence to long-established coding practices that ensure sustainable software development for the long term.
When I click that 'Approve' button, I've got only a few worries on my mind. Does it produce the correct outcome? Will people understand this next quarter? Will they be able to change it?
I know the code was generated because it was written in a way no developer on the team would. It works, it's clear, it's tested, and it's maintainable.
Because no one would write an HTTP fetching implementation covering all edge cases when we have a data fetching library in the project that already does that.
We spent decades coming up with patterns and standards that help us build maintainable software. That's always been the challenge - putting something in production that you can take care of for years.
Collection
[
|
...
]