165
How anyone thinks they are productive with llm tools is baffling (sh.itjust.works)
submitted 7 months ago by to c/fuck_ai@lemmy.world
100 comments fedilink hide all child comments
 

It has to be pure ignorance.

I only have used my works stupid llm tool a few times (hey, I have to give it a chance and actually try it before I form opinions)

Holy shit it's bad. Every single time I use it I waste hours. Even simple tasks, it gets details wrong. I correct it constantly. Then I come back a couple months later, open the same module to do the same task, it gets it wrong again.

These aren't even tools. They're just shit. An idiot intern is better.

Its so angering people think this trash is good. Get ready for a lot of buildings and bridges to collapse because of young engineers trusting a slop machine to be accurate on details. We will look back on this as the worst era in computing.

you are viewing a single comment's thread
view the rest of the comments
[–] -1 points 7 months ago (16 children)

Yeah i used it for a boilerplate task, and then I did not have to do that task. I was able to scan in hundreds of documents, and at the end I had a fully indexed, properly file named, summarized, and searchable PDF library. Just doing one document at a time manually would have been a multi hour task for me, and in a few hours I was done, and it was good enough to good.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 16 child comments
    •
  • [–] 17 points 7 months ago* (last edited 7 months ago) (11 children)

    Sorry, to clarify, a boilerplate task is not the repetitive job that you are automating. It’s the code that’s doing it.

    What I’m saying is that you (and many others) are incorrectly attributing (your paragraph about the benefits your finished program is conferring to you) to AI, because that happens to be the path you took to arrive there.

    In reality, the reason it was able to produce functional code is because your problem was already solved and documented. A few years ago, instead of “asking AI”, you would have simply copied and pasted the boilerplate code from someone else’s project. In all likelihood it also would have been faster for you to have done so

    Quick edit: Sorry again, just want to further clarify that when I say “boilerplate task” I’m referring to a type of programing problem that you solve with “boilerplate code”. Reading back the above I was kind of using them interchangeably which is not strictly accurate

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 11 child comments
    •
  • [–] -3 points 7 months ago* (10 children)

    If I could have found the code, and copied it yes. Using AI means I did not have to search for it, did not need to learn Python, and then did not need to do the tasks.

    Please understand I hate 90% of all the AI bullshit being forced on us, and employers requiring AI use is insane. I am just saying that blanked hate is short sighted because it is useful in some cases, and the number of cases keep going up as we improve things.

    I could also use a dictionary to check my spelling, but having spell check enabled is just faster.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 10 child comments
    •
  • [–] 10 points 7 months ago (9 children)

    Right, and what I’m saying is that the ‘usefulness’ that people claim to have discovered is totally nonsensical because these problems have been solved for decades

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 9 child comments
    •
  • [–] [S] 5 points 7 months ago

    exactly. It's people realizing what coding is for the first time because it's being shoved in our faces. Before all this (bought and paid for propaganda) publicity, your average dummy had no idea what code was or did.

    Basically, the non-tech people who know nothing about coding or how computers work are now amazed because they (think they) discovered what coding is because of the AI hype.

  • permalink
  • fedilink
  • source
  • parent
  • [–] -5 points 7 months ago (7 children)

    Yes but now they are accessible to anyone.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 7 child comments
    •
  • [–] 11 points 7 months ago (6 children)

    Your perspective is actually completely backwards on this

    This process has always been accessible to everyone. You’d google basically the same words you typed into your prompt and it would bring you directly to the same block of code that everybody uses.

    AI on the other hand is currently temporarily being made available for free or low cost because they are actively trying to create a cohort of users who impulsively “just reach for AI” as their first step to solving every problem.

    In a few years you may find yourself praising how “accessible” it is because they occasionally run offers for a week of subscription time for $40 instead of the usual rate of $189.99/mo for entry level access. You may find yourself wondering how people ever lived without it

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 6 child comments
    •
  • [–] 0 points 7 months ago (5 children)

    I run most of my AI local on my GPU only on rare moments do I bother with commercial systems.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 5 child comments
    •
  • [–] 3 points 7 months ago (4 children)

    That’s cool, does that need to be updated periodically?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 1 point 7 months ago (3 children)

    Nope, the version I have on my local HD is a snapshot in time. It won't get better but no need to update.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 1 point 7 months ago (2 children)

    Right, I don’t mean “is the one you’re running now going to stop being able to be used without regular updates?”, but rather, “Do you think continuing to have access to updated versions is going to be necessary for it to be useful to you?”

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] [S] 3 points 7 months ago (1 child)

    I understand that and good for you for finding a use case.

    however a normal program could have done that exact same thing. It's just miniscule easier to do it how you did. Probably not repeatable though, or if your model you used gets the plug pulled, you're back to square 1.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •