I occasionally lecture my 3DPD wife about science facts and she hates it. She'll say things like "what?" And "I was just asking what we should do for dinner"
I think the main barriers are context length (useful context. GPT-4o has "128k context" but it's mostly sensitive to the beginning and end of the context and blurry in the middle. This is consistent with other LLMs), and just data not really existing. How many large scale, well written, well maintained projects are really out there? Orders of magnitude less than there are examples of "how to split a string in bash" or "how to set up validation in spring boot". We might "get there", but it'll take a whole lot of well written projects first, written by real humans, maybe with the help of AI here and there. Unless, that is, we build it with the ability to somehow learn and understand faster than humans.
People seem to disagree but I like this. This is AI code used responsibly. You're using it to do more, without outsourcing all your work to it and you're actively still trying to learn as you go. You may not be "good at coding" right now but with that mindset you'll progress fast.
As a former script kiddie myself I think it's not much different from how I used to blindly copy and paste code snippets from tutorials. Well, environmental impact aside. Those who have the drive and genuine interest will actually come to learn things properly. Those who don't should stay tf out of production code, which is why we genuinely shouldn't let "vibe coding" be legitimized.
It's a pretty big jump to go from ChatGPT/LeChat to hosting your own LLM locally, if you want results that are anywhere close to the commercial offerings. Both of them even have a free tier that would probably still be better than anything you could run locally without significant hardware investment. It's definitely not difficult these days, but it's very expensive to get close results unless you've already got the hardware.
Do you not reuse any part of your outfit from day to day? Like do you have at least 7 different pairs of pants that you cycle through? Cause that's why I wouldn't do this, I'd rather not go out with some clothes then bring all that outside dirt into my bed.
I don't mind a whoops somebody fucked right up error message if you let me click a button for more details. Or at the very least, give me a reference number I can tell somebody about. Some "software companies" don't even properly log things on their end so nobody can solve shit.
Huh, I had never considered this solution to fizzbuzz to be honest. I usually go for string concatenation, or (i % 3 == 0 && i % 5 == 0), but yeah i % 15 == 0 is certainly a clever simplification
I occasionally lecture my 3DPD wife about science facts and she hates it. She'll say things like "what?" And "I was just asking what we should do for dinner"