> Six months later, an architectural change required modifying those features. No one on the team could explain why certain components existed or how they interacted. The engineer who built them stared at her own code like a stranger’s.

Genuine question: so what?

First of all, team members leave all the time, and you're stuck staring at code nobody instantly understands.

Second of all, LLM's are a godsend in help you understand how existing code works. Just give it the files and ask it to explain to you what the components do and how they interact. It'll give you a high-level summary and then you can interactively dig in, far faster than has ever been possible before.

Heck, I often don't remember anything about code I wrote six months ago. It might as well have been written by someone else. And that's not an original observation either -- I remember hearing the same thing from other developers decades ago, as justification for writing better code comments.

Modern codebases are often far too large for any one person or even an entire team to fully comprehend at once. The team has cycled through generations of team members, with nobody who can remember the original rationales for design decisions.

LLM's are helping comprehension more than ever. I don't understand why people aren't talking about this more.