Hacker News new | past | comments | ask | show | jobs | submit
thatsabadlook | on: Elevated errors on claude.ai, Claude Code, and platform.claude.com
Yep. This is what happens. Once you give up control it's mostly gone. The interesting thing is, if you maintain control, you can always choose to use llms here and there. But expecting humans to dive into 10000 file 40million line code bases branded todo apps isn't going to happen.
qrux | parent | next
10k files, 40m LOC is rookie numbers for a todo app.

I recently asked Claude to edit a few targets of a Makefile. It decided: "OH BOY HERE WE GO LETS FIRE UP ALL THE B200S BABY" and went way deep adding tests...I stopped it when I saw something like: "Adding guards to prevent homebrew injection threat...". It had written an entire fucking build subsystem, probably larger than make. For a 5-line change.

sevenzero | parent | next
You cant expect humans to jump at code if management fired half of the department due to the big AI productivity promise.
01HNNWZ0MV43FF | parent
If humans can't maintain a 10,000 file 40 million LoC code base, then three things are true:

1. We haven't learned anything from Google, who maintained Chromium and Android before LLMs

2. Your LLM is not generating code as maintainable as Chromium and Android (which are gigantic open-source projects that probably 99% of your devs have used)

3. Your company has no faith or interest in teaching devs how to maintain code nor how to build maintainable code

And that's pretty pathetic. It's solvable, but it's pathetic.

I will be amused if those 3 points lead to this conclusion:

4. If you aren't asking your LLMs to write maintainable code, and they aren't smart enough to do it by default, you are pretty quickly gonna hit a brick wall where your LLMs are also just slopping mud onto the big ball of mud. Then nothing will save you, if your leads haven't heard of "quality".

(Yes, this is projection. Yes, I'm late for work)