Is this a problem with Claude updating code that a human wrote, though? Would Claude do better on code that it started on its own? Humans have a bad tendency to write unmaintainable code (usually at the behest of managers breathing down their necks to HURRY UP even when it doesn't matter). If the code had been designed with good coding practices from the beginning, I wonder if Claude would have struggled so much with it.
That implies that Claude writes better code by default, which isn’t necessarily true. Especially as projects get bigger, you can easily end up with unmaintainable LLM-written code if you don’t actively intervene and know a cleaner way.