[sp332]

Things in the generated code (function names, variables) will be named better. Comments will be written with specific instructions about how to generate the following code. Test coverage will improve, but even fewer people will evaluate whether the tests are doing anything useful.

[shaburn]

Why will function names and variables be named better? Will this also apply to the better code bases?

[sp332]

It's just a guess, based on the LLM never getting writers block and being able to hold a good amount of context in mind for every output token.