Dieser Bereich kann Inhalte enthalten, die nicht für alle Nutzer geeignet sind. Dazu können unter anderem Texte, Medien oder Diskussionen gehören, die als beleidigend, extremistisch, gewaltbezogen oder anderweitig belastend empfunden werden. Wenn du solche Inhalte nicht sehen möchtest, nutze bitte die jeweiligen Filter- und Meldeoptionen der Plattform oder meide entsprechende Threads/Communities.
I’m not a developer but I do make little tools for myself at work. I used an LLM to assist with adding some features recently, nothing I couldn’t easily do myself. It did a fine job and made minimal changes, all totally readable and for the most part the same way I would have done it.
I have a new tool I want to make, and it’s hard not to just turn to the LLM, since it’ll save me many hours on a script that nobody else will ever see. It’s really taken the fun out of it. I’m proud of what I made, even though nobody else will care, but doing this my usual way will feel like I’m using the wrong tool out of perversity.
I dunno. I hate everything.
I just started using it as well under a push at work. I’ve so far only used it to write out a script that I knew what I needed and how to do it but it ended up saving me a couple hours. I suppose there wasn’t an interesting problem to solve there so it makes sense to use it but I worry about relying on it since it seems just capable enough to start trusting before the rug gets pulled from under you.
I have that worry too, but luckily the worst case for me would be one of my simple tools becoming unmaintainable.
Hey thanks for sharing I’m in basically the exact same boat. There are also pressures in the work place to use it because of the time savings. Personally I try to keep a balance and work on things myself most of the time and if the LLM is used it’s more like a buddy coder then a magic code generation tool, but sometimes it’s just too easy to use it that way. I think it’s important to take pride in your work, so keep doing things your way when you want!
I look at it this way: if you prompted an LLM to generate it, then you didn’t “do” it, you basically installed an outside piece of software that just happened to be generated on-the-fly.
That maybe true if youre single shotting. At some point, but that’s rarely the end. It takes iteration and experience to get LLMs to do useful work in most cases.
Creating something while not using the most efficient way possible has always been something that created the most unique, personal and opinionated results, because working on the task transforms both you and the product you are aiming for. These “inefficient” workflows also create the most useful and popular things, btw.
You are not “using the wrong tool”. You are doing it for yourself, for your mental wellbeing, for a sense of purpose. Whatever the LLM spits out is not YOUR code, it is SOME code. You should really reframe this for your own good.
I felt that way until I just stopped using it entirely
I’ve only tried it the once but it did a great job and caused me the consternation from my previous comment.
It is disappointing knowing it actually works some of the time. I guess I just don’t care. I have my lines and I don’t cross them.
I’m sure there are some great uses of Microsoft software or Nvidia hardware, but I’m not going to use them unless forced to by work.
It basically added three small functions and their command line args to a sub-500 line Python script. I’m sure if helped that my function and variable name are verbose, like dictionary_of_fruits_with_dictionary_of_attributes.
My work provided the tool and asked me to try it.
I like to give it unnecessarily complex tasks and work on a hobby.