top 49 comments

sorted by: hot top controversial new old
[–] 242 points 1 year ago (9 children)
  • [–] 6 points 1 year ago (5 children)

    My boiled egg has to be just a little bit liquid on the inside 🌚

  • source
  • parent
  • hideshow 5 child comments
  • [–] 8 points 1 year ago* (last edited 1 year ago) (3 children)
  • [–] 107 points 1 year ago (4 children)

    That’s a stupid question it doesn’t deserve an answer. You should be ashamed you even thought about it.

  • source
  • hideshow 4 child comments
  • [–] 79 points 1 year ago (2 children)

    Your description of the problem has words I've heard before, like "a" and "even"; marked as duplicate.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 39 points 1 year ago (2 children)

    I found a workaround for this:

    I start with "a buggy LLM wrote this piece of code..." then i paste my code for review, so they can shit and bash on it "you're absolutely right: that LLM done a disaster, this is a mess, look how inefficient is this function, here is how it can be improved..."

  • source
  • hideshow 2 child comments
  • [–] 1 point 1 year ago

    That's great example of how to get the right answer on any forum. Though you've found away you don't need two accounts. Traditionay you need a archive to give an absolutely complete bat shit answer so a thousand users can tell you why you're wrong.

  • source
  • parent
  • load more comments (1 reply)
    [–] 33 points 1 year ago

    Well, if I asking for help, it's probably because I am wrong about something. So I know who to trust.

  • source
  • [–] 25 points 1 year ago (1 child)

    piefed is working on solution and answer features and i can't wait for stackoverflow like communities without the ai "enhancements"

  • source
  • hideshow 1 child comment
  • [–] 37 points 1 year ago (1 child)

    ChatGPT is a narcissists dream app.

  • source
  • hideshow 1 child comment
  • [–] 16 points 1 year ago (1 child)

    People on Social Media: "You absolutely are an asshole."

  • source
  • hideshow 1 child comment
  • [–] 37 points 1 year ago (1 child)

    SO: “that’s a stupid question!” GPT: “that’s a great question!”

  • source
  • hideshow 1 child comment
  • [–] 12 points 1 year ago (12 children)

    I usually combine both to unblock myself. Lately, SO, repository issues, or just going straight to the documentation of the package/crate seem to give me faster outcomes.

    People have suggested that my prompts might not be optimal for the LLM. One even recommended I take a prompt engineering boot camp. I'm starting to think I’m too dumb to use LLMs to narrow my research sometimes. I’m fine with navigating SO toxicity, though it’s not much different from social media in general. It’s just how people are. You either take the best you can from it or let other people’s bad days affect yours.

  • source
  • hideshow 12 child comments
  • [–] 18 points 1 year ago (2 children)

    They always accuse the user of being the problem when using glorified if-else machines.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 11 points 1 year ago

    If SO doesn't have the answer to your question, LLMs won't either. You can't improve that by prompting "better".

    They are just an easier way to search for it. They don't make answers up (or rather, they do, but when they do that, they are always wrong).

  • source
  • parent
  • [–] 8 points 1 year ago (5 children)

    If you're planning on using LLMs for coding advice, may I recommend selfhosting a model and adding the documentation and repositories as context?

    I use a a 1.5b qwen model (mega dumb) but with no context limit I can attach the documentation for the language I'm using, and attach the files from the repo I'm working in (always a local repo in my case) I can usually explain what I'm doing, what I'm trying to accomplish, and what I've tried to the LLM and it will generate snippets that at the very least point me in the right direction but more often than not solve the problem (after minor tweaks because dumb model not so good at coding)

  • source
  • parent
  • hideshow 5 child comments
  • [–] 6 points 1 year ago*

    That's a really cool idea actually. I never considered that you could use such a crazy low quant to, it sounds like, temporarily "train" it for the task at hand instead of having to use up countless watt hours training the model itself!

    That's how I use these things, too. Not to "help me code", but as a fancy search engine that can generally nudge me towards a solution I can work out myself.

  • source
  • parent
  • [–] 2 points 1 year ago (3 children)

    I do use the 1.5b of whatever latest ollama with open web ui as frontend for my personal use. Although I can upload files and search the web it's too slow on my machine.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 3 points 1 year ago (2 children)

    If you've got a decent Nvidia GPU and are hoping on linux, look into the Kobold-cpp Vulkan backend, in my experience it works far better than the CUDA backend and is astronomically faster than the CPU-Only backend.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 3 points 1 year ago (1 child)

    Will look into that when I have some money to invest. Thank you 💪

  • source
  • parent
  • hideshow 1 child comment
  • [–] 3 points 1 year ago

    When/If you do, a RTX3070-lhr (about $300 new) is just about the BARE MINIMUM for gpu inferencing. Its what I use, it gets the job done, but I often find context limits too small to be usable with larger models.

    If you wanna go team red, Vulkan should still work for inferencing and you have access to options with significantly more VRAM, allowing you to more effectively use larger models. I'm not sure about speed though, I haven't personally used AMDs GPUs since around 2015.

  • source
  • parent
  • [–] 2 points 1 year ago

    I've been having good luck with Kimi K2 for CSS/bootstrap stuff, and boilerplate API calls (example: update x to y, pulling x and y from this .csv). I appreciate that it cites its sources because then I can go read more and hopefully become more self-reliant when looking up documentation.

  • source
  • parent
  • [–] 8 points 1 year ago*

    User: "Can I ask a q..."

    Stackoverflow: "NO!"

  • source
  • [–] 8 points 1 year ago (3 children)
  • [–] 5 points 1 year ago (2 children)

    That's just the average stackoverflow comment

  • source
  • parent
  • hideshow 2 child comments
  • [–] 8 points 1 year ago (1 child)

    Answer: Why don't you try searching for the question first?

    Me (confused face): How tf do you think I found this page?


    Answer: Why are you doing it that way?

    Me (sighs): Because I'm an idiot and don't know what I'm doing, is that what you wanted to hear?

  • source
  • parent
  • hideshow 1 child comment
  • [–] 3 points 1 year ago

    Every second the most ridiculous question gets positive feedback so yeah who knows where we'll end up from here.

  • source
  • [–] 2 points 1 year ago

    Man, I miss those batshit crazy threads about esolangs!

  • source
  • [–] 2 points 1 year ago*

    And neither can get it right over half the time.

  • source
  • [–] 2 points 1 year ago

    I knew you write a function like this f(x) stack overflow has no idea what they are talking about.

  • source
  • [–] 1 point 1 year ago