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
[–] [S] 11 points 7 months ago (2 children)

OK so that's what the boosters keep saying. However, every Task ive given it have very clear exact set of instructions, and when i comb through it, it still hallucinates. I can try talking to it like a 6 year old, and its going to forget what I told it the next day and hallucinate again.

Meanwhile I burned up a shit ton of power for 0 benefit and wasted my time. Worst case, someone else who is not detail oriented like myself is going to fuck up a lot of work.

However when i give it something I don't know how to do or dont know an answer to, it does a great job and is so smart! Amazing how that works.

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

    Your experience and feelings are totally valid, its still a shit show and in most cases a massive waste of power, water, brain power, and money. I am just saying that with the right training, and appropriate use, AI really can be effective NOW. One thing you can do is describe the task, and ask the AI to write a prompt to accomplish it. Then test that prompt in a new chat, and see if you get better results.

    Most AIs will tell you how to improve your prompts.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] [S] 5 points 7 months ago*

    I can see where you're coming from and I get it.

    I've done all that. I've followed it's little bs "hey, to improve, tell me this!!". Still gets it wrong.

    It probably is fine for non-detail work and stuff no one really cares about (and if no one cares about it, maybe revisit what your job is). It's definitely not worth the cost. I myself don't enjoy telling a 5 year old the same thing 25 times (and then they forget because they saw a stick), which is exactly what using an LLM is akin to.

  • permalink
  • fedilink
  • source
  • parent