56
What is your "hunch"? (lemmy.dbzer0.com)
submitted 5 months ago by to c/asklemmy@lemmy.world
79 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 19 points 5 months ago (3 children)

That if you’re amazed by how good/smart LLMs are, it’s because you’re well below average. LLMs are still incredibly stupid and bad at things.

  • permalink
  • fedilink
  • source
  • hideshow 6 child comments
    •
  • [–] 15 points 5 months ago (1 child)

    I'm required to use LLMs for work (we have metrics and I've been told I should use AI daily) and while every once in a while they are useful (i.e. getting examples for stuff that has inadequate documentation) 99% of the time they just piss me off. The output and results are seldom what I want and rather than spend the time to direct it to do what I want I'd often rather just do the work myself. Furthermore when my coworkers send me PRs that are obviously AI the code quality is pretty shit and usually doesnt actually accomplish what we need in a way that makes sense. As someone who has invested a lot of time in improving my coding ability and knowledge I see AI code and it makes me whince.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 4 points 5 months ago (1 child)

    I’m sorry they’re forcing it on you. That’s unfortunate. You might send them this reasoning section:

    https://sciactive.com/human-contribution-policy/#Reasoning

    in an attempt to change their minds.

    There are additional links in the More Info section at the bottom that provide supporting evidence.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 4 points 5 months ago (1 child)

    Ah it's fine my boss told me that interacting with the AI is enough and that he doesnt care if I'm just asking it the weather. It's a large publicly traded company and the AI push is coming from a lot higher up the change so sadly theres not much i could do to affect the situation.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 3 points 5 months ago (2 children)

    Popular take here on Lemmy for sure., but just doesn’t really say much. They are as capable as they are. There are objective measurements. A qualitative statement about smart or good just isn’t that useful. If you aren’t impressed by the technology, fine.

    For me, I think the field is interesting. But I won’t let my hatred of billionaires or worker subjugation cloud my judgement about interesting technologies. There is a difference between “This is going to be bad and exploitative” and burying one’s head in the sand and repeating the “they aren’t good” trope.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 7 points 5 months ago* (last edited 5 months ago) (2 children)

    I’m not just repeating it. That is my first hand judgment of their abilities.

    I am a professional software developer, and I have been told by way too many people that these models are amazing at writing code, and yet every time I’ve seen the code they write, it has been unimpressive at best and absolute dog shit at worst. I was writing better code as a college sophomore.

    It makes sense though. They’re trained on everyone’s code, and the vast majority of code available for them to steal is, well, absolute dog shit.

    The developers who look at their code and don’t see any problems are developers who themselves write dog shit code.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 1 point 5 months ago (1 child)

    You’re just objectively wrong. I hate to be the bearer of bad news, but you can see their raw objective scores across numerous software engineering metrics.

    I’m a programmer that’s been in the business for decades. That doesn’t make me any more correct than you. I have seen it write some impressive things at impressive speeds. If you haven’t that’s fine. You just haven’t seen it work then. But it doesn’t matter what I have seen or what you’ve seen. What matters are data, and the data are clear when it comes to ability.

    Not ability per unit water consumed, dollar spent, or per unit power consumed, but ability nevertheless.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 8 points 5 months ago* (last edited 5 months ago)

    It does write code that usually works, but it makes absolutely rookie mistakes that are, like, worse than junior engineer level. If that impresses you, then so be it, but in my 28 years of writing code, I’ve never been less impressed by something with as much hype as AI agents have.

    Btw, there’s not really an objective way to measure software engineering skill. Even the best tests don’t take into account all aspects of engineering skill. That’s why I would be only one of like ten engineers interviewing the same candidate at Google. The “objective” tests are called phone screens, and they’re just the first round of interviews. If you can’t pass those, it usually means you’re not qualified to be an engineer, but just because you can pass them doesn’t mean you are qualified.

  • permalink
  • fedilink
  • source
  • parent
  • [–] 2 points 5 months ago (1 child)

    imo, llm doing well and being good would be worse situation that what is currently going on.

    Imagine how much more power billionaires would get over everything? They could up the prices and people would just have to accept it because they soon couldnt live without llm, they could influence people by manipulating the hidden prompt, they could just threaten to cut off anyone they want, have access to any system their llm is connected to. The current censorship could be extended to anything they like too. And people would just lap all that up and call anyone speaking against it a conspiracy theorist or whatever.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •