• Buelldozer@lemmy.today
    link
    fedilink
    English
    arrow-up
    60
    arrow-down
    1
    ·
    8 months ago

    Perhaps I’m just brain dead, I’ve been accused of it often enough, but I can’t figure out what the stupid thing is good for.

    • The Menemen!@lemmy.world
      link
      fedilink
      English
      arrow-up
      14
      ·
      edit-2
      8 months ago

      I don’t really like it, but it can defintly be used as a dumb assistant. E.g. if you want to write an email or a small script to analyze some data, you can tell it what you need, specify the details, take the results, correct them and then use the results. You still have to do much of the work, but if you do it correctly you’ll save time. BUT: It’ll save all of that. Don’t do this with sensitive data and don’t do this for work without official permission of the employer.

    • yeehaw@lemmy.ca
      link
      fedilink
      English
      arrow-up
      2
      ·
      8 months ago

      Lately I’ve been using it as a duckduckgo replacement.

      …well chatgpt free version, that is. Seems like everyone has an “AI” now.

    • Rinox@feddit.it
      link
      fedilink
      English
      arrow-up
      2
      ·
      8 months ago

      It helps sometimes with code, when I can’t find a solution on Google.

    • jkrtn@lemmy.ml
      link
      fedilink
      English
      arrow-up
      1
      ·
      8 months ago

      I use LLMs when I am trying to reverse lookup a word from a definition. Works better than web searches.

    • dependencyinjection@discuss.tchncs.de
      link
      fedilink
      English
      arrow-up
      4
      arrow-down
      3
      ·
      8 months ago

      Depending on which CoPilot, quite a lot to be honest.

      My company uses it at work integrated into Visual Studio Professional.

      It saves countless hours, especially when you work on enterprise software and have set up good coding standards, best practices, and techniques; as it learns from your code and will offer suggestions based on how we do things.

      Like most TypeScript components we build are going to require loading some data via a hook, and calling these hooks is pretty consistent. So now I basically write my comment // load the data and boom no boring writing the same thing.

      We save that much time on mundane tasks that we can actually spend more time learning new things or innovating.

      That’s before we even get into the tool my boss build that will allow us to create all the schema and hooks for a new model which would normally be 30-45 mins of mundane copy and paste and replace.