I recently decided to bite the bullet and get into AI and specifically LLMs. Fuck corporate assholes and data hungry companies so I got some second hand GPUs and made a $800 rig that can run 32b models at very usable speeds. I started playing with it and decided to use pycharm with continue and a local ollama to have my own copilot.

I must say, this is the future. Not in the sense that soon we will all be prompt engineers (lol) but assuming that LLMs don’t reach a point of true intelligence and continue to be fancier and fancier regurgitation machines, this is like having an instant StackOverflow in your IDE. I don’t even bother with complex and unique ideas with it since it really seems that once you reach that area it becomes useless. Basically my programming flow has always started with writing down my rough idea of what I want to do and how I plan on doing it. Now I just feed that to the LLM and it gives me code that is like 90% accurate and I just do a code review, fix mistakes or weird logic and from there as I expand my code I use the LLM as a replacement for online searching. Need syntax help or basic library context? LLM got you covered. Need a function that does something basic or well known? LLM! It’s kind of like having an infinite boilerplate library that can custom fit your needs. I think that the reason it works so well for me is that I really only let it handle the basics, anything that I need to think through I do myself.

I doubt we will ever go back from this.

  • Feyd@programming.devEnglish
    92·
    2 days ago

    I know what I’m doing

    I don’t believe you

    Did you try it?

    Yes I did.

    1. Writing code isn’t actually the majority of software engineering unlike what naive people believe.
    2. Most of the code I write isn’t boilerplate for new projects because I actually work on real software that people use.
    3. It’s not faster to review code written by a moron (artificial or otherwise) than to just fucking write it.
    • MTK@lemmy.worldOPEnglish
      11·
      2 days ago

      Okay then. I agree on 1, writing code is just part of it. Most of it is the logic, research, and knowledge. I had challenges that were like 90% research and logic and only the last 10% are the actual coding.

      2, sure, I often did too, but not all jobs or projects are like that and plenty of highly skilled programmers are working daily on new code.

      3, debate-able, but as I have done it I can say that the code is pretty readable and accurate. My review can be much faster than writing it from scratch. Just like reading a page from a book is faster than writing one, even if you already know exactly what you will write.