You must log in or # to comment.
That’s a stupid question it doesn’t deserve an answer. You should be ashamed you even thought about it.
Your description of the problem has words I’ve heard before, like “a” and “even”; marked as duplicate.
This has been asked before. The thread was closed with zero comments but suck it.
Now, that’s the real SO experience.
Well, if I asking for help, it’s probably because I am wrong about something. So I know who to trust.
SO: “that’s a stupid question!” GPT: “that’s a great question!”
stack overflow at least is polite enough to call you a moron for asking
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…”
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.
ChatGPT is a narcissists dream app.
Unfortunately aged like milk, StackOverflow was an early adopter of the LLM fad.
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.
One even recommended I take a prompt engineering boot camp
They always accuse the user of being the problem when using glorified if-else machines.
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)
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.
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.
Will look into that when I have some money to invest. Thank you 💪
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.
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).
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.
User: “Can I ask a q…”
Stackoverflow: “NO!”
I knew you write a function like this f(x) stack overflow has no idea what they are talking about.
Every second the most ridiculous question gets positive feedback so yeah who knows where we’ll end up from here.
Man, I miss those batshit crazy threads about esolangs!
And neither can get it right over half the time.
fuck me
