Interesting to see the benefits and drawbacks called out.

  • uthredii@programming.dev
    link
    fedilink
    English
    arrow-up
    41
    arrow-down
    1
    ·
    10 months ago

    In this regard, AI-generated code resembles an itinerant contributor, prone to violate the DRY-ness [don’t repeat yourself] of the repos visited.

    So I guess previously people might first look inside their repo’s for examples of code they want to make, if they find and example they might import it instead of copy and pasting.

    When using LLM generated code they (and the LLM) won’t be checking their repo for existing code so it ends up being a copy pasta soup.

    • Gamma@beehaw.org
      link
      fedilink
      English
      arrow-up
      6
      arrow-down
      3
      ·
      edit-2
      10 months ago

      Makes sense, even if it’s not good practice.

      It is really useful for hobby projects! I needed a recursive function to find a path between two nodes in a graph and it wrote me something that worked with my data in a few seconds, saved a bit of time