Login
You're viewing the techdon.dev public feed.
  • Nov 10, 2026, 10:58 AM

    I think my largest annoyance with LLM slop PRs is the authors complete lack of taste in good abstraction and looking at what they are doing in context of the existing codebase.

    The LLM is going to go "parse, don't validate" and create a struct over a type and just completely ignore the code duplication. Abstractions for the type? No thank you!

    I'll duplicate this important for-loop in two different places.

    💬 2🔄 0⭐ 0

Replies

  • 💬 0🔄 0⭐ 0
  • Nov 10, 2026, 11:23 AM

    @RosaCtrl
    I'm giving them the benefit of the doubt when they reply "I reviewed every single line of code".

    I believe them, and I believe their judgment is just bad.

    💬 1🔄 0⭐ 0
  • 💬 0🔄 0⭐ 0
  • Nov 10, 2026, 4:38 PM

    @Foxboron My experience is that unless LLMs are told what to do or accidentally copy style from some files in the project they looked at they write code like someone who is writing their first program ever, which frankly is similar in quality to what average-quality code out there looks like

    no abstractions, no strong types, no ddd etc

    it's very frustrating

    💬 0🔄 0⭐ 0