ChatGPT Isn’t as Good at Coding as We Thought::undefined

  • daikiki
    link
    fedilink
    English
    19
    edit-2
    11 months ago

    I’ve experimented a bit with chatGPT, asking it to create some fairly simple code snippets to interact with a new API I was messing with, and it straight up confabulated methods for the API based on extant methods from similar APIs. It was all very convincing, but if there’s no way of knowing that it’s just making things up, it’s literally worse than useless.

    • @[email protected]
      link
      fedilink
      English
      411 months ago

      ChatGPT has been helpful in being an interactive rubber duck. I used it to help myself breakdown the technical problems that I need to solve and it helps to cut down time taken to complete a difficult ticket that usually take a couple of days of work to a couple of hours.

    • @[email protected]
      link
      fedilink
      English
      1
      edit-2
      11 months ago

      I’ve had similar experiences with it telling me to call functions of third party libs that don’t exist. When you tell it “That function X does not exist” it says “I’m sorry, your right function X does not exist on library A. here is another example using function Y” then function Y doesn’t exist either.

      I have found it useful in a limited scope, but I have found co-pilot to be much more of a daily time saver.

    • @[email protected]
      link
      fedilink
      English
      -1
      edit-2
      11 months ago

      So? You should be testing the code it generates, a few lines of code at a time, and writing unit tests where appropriate.

      By doing that, you’ll quickly identify anything that it does wrong, and you can just tell it “this line didn’t work”. Normally you don’t need to tell it how to fix it, but you can do that too.

    • @[email protected]
      link
      fedilink
      English
      -211 months ago

      Except that in code, you can write unit tests and have checks that it absolutely has to get precisely correct.

        • @[email protected]
          link
          fedilink
          English
          3
          edit-2
          11 months ago

          You don’t, you get it to write both the code and the tests. And you read both of them yourself. And you run them in a debugger to verify they do what you expect.

          Yeah, that’s half the work of “normal coding” but it’s also half the work. Which is a pretty awesome boost to productivity.

          But where it really boosts your productivity is with APIs that you aren’t very familiar with. ChatGPT is a hell of a lot better than Google for simple “what API can I use for X” questions.

          • @[email protected]
            link
            fedilink
            English
            111 months ago

            You might have to rewrite all of it. The code and the tests.

            Hell even the structure/outline it took might not be correct.