• 0 Posts
  • 18 Comments
Joined 1 year ago
cake
Cake day: February 8th, 2025

help-circle



  • Nothing wrong with a professional developer with years of experience using AI as a tool for coding, just as long as they review the output first before using it in their project. My workplace (where I work as a dev) provides us with a Claude subscription to use it as a tool. It’s kind of just like using a drill instead of a screwdriver to screw something into a wall - done well in the right hands it’s fine, give it to a 13yo and they’re going to drive the screw through the plaster and make a holy mess of it.

    What IS wrong is a human who has little-to-no experience coding using an AI to develop the entire codebase and then the human releases the code into the wild without some level of peer review from a human who DOES have experience and then claiming it as their own creation. That’s almost sloppy plagiarism (of ironically already sloppy plagiarism).






  • I vibe code from time to time because people sometimes demand quick results in an unachievable timeline. In saying that, I may use a LLM to generate the base code that provides a basic solution to what is needed and then I go over the code and review/refactor it line by line. Sometimes if time is severely pressed and the code is waaaay off a bare minimum, I’ll have the LLM revise the code to solve some of the problem, and then I review, adjust, amend where needed.

    I treat AI as a tool and (frustrating and annoying) companion in my work, but ultimately I review and adjust and amend (and sometimes refactor) everything. It’s kind of similar to when you are reading code samples from websites, copying it if you can use it, and refactoring it for your app, except tailored a bit more to what you need already…

    In the same token, I also prefer to do it all myself if I can, so if I’m not pressed for time, or I know it’s something that I can do quickly, I’ll do it myself.