52
Ignoring lemmyhate, are programmers really using AI to be more efficient? (sh.itjust.works)
submitted 1 year ago by to c/programming@programming.dev
82 comments fedilink hide all child comments
 

I've seen a few articles saying that instead of hating AI, the real quiet programmers young and old are loving it and have a renewed sense of purpose coding with llm helpers (this article was also hating on ed zitiron, which makes sense why it would).

Is this total bullshit? I have to admit, even though it makes me ill, I've used llms a few times to help me learn simple code syntax quickly (im and absolute noob who's wanted my whole life to learn code but cant grasp it very well). But yes, a lot of time its wrong.

you are viewing a single comment's thread
view the rest of the comments
[–] 3 points 1 year ago (2 children)

I find it excels at one-off scripts. They are simple enough that every parameter and line of code fits in a small bit of memory. They are really bad at complex tasks, but they can help if you use it judiciously.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 4 points 1 year ago* (last edited 1 year ago) (1 child)

    I used ChatGPT to write some fairly straight forward bash scripts last week and it was mostly awful. I ended up massaging it enough to do what I needed, but I would have been better off just writing it myself and maybe asking it a couple syntax questions (although the regex I needed was one of 8 things it stumbled over)

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 1 point 1 year ago*

    I'm generally much better at writing regex than ChatGPT. Though I will say, I needed the regex for ISO 3339 date format just yesterday for validation and copilot/Claude provided a more specific version than Google search. I still have to go back and double check the corporate standard as I suspect we only allow offsets from UTC and all implementations I looked at are too permissive.

    I've had middling experience with bash. The scripts I wrote are generally petty basic. Set a few variables based on the current project and then execute some gcloud or Tekton commands. And I don't write them often so it finds and fixes things I often forget like not being allowed to have spaces around =.

    I think the more externalities that need to be considered to come up with a correct answer, the less reliable ChatGPT is because there are a lot of externalities it doesn't really know to consider. Bash has a huge number of externalities that might affect the correct way of doing something.

    I should experiment with more functional languages. "Pure functions" are really good at minimizing externalities. Worth investigating.

  • permalink
  • fedilink
  • source
  • parent