- cross-posted to:
- programmer_humor@programming.dev
- cross-posted to:
- programmer_humor@programming.dev
You must log in or # to comment.
I personally like programming too much to ever vibe code as they say. Solving problems and organising things is why I like programming in the first place.
That said, there is a lot of boring code out there. For example, most UIs are basically just doing CRUD operations, and once you’ve written enough of these things it’s not really that exciting anymore.
There are a ton of great UI libraries available, many with bindings for whatever our preferred languages are. We don’t need an LLM for any of that.
The LLM is what I use to build the specific UI using the components from these great UI libraries. There’s practically no logic involved here, it’s just handling layout for components and hooking up events. It’s fantastic to be able to take a JSON payload from an endpoint throw it at a model and get a reasonable UI in seconds.
ai is the new stack overflow which is the new copying someone else’s work which is the new reading the manual
Yeah… I’m quickly reaching the point where I’m quicker thinking and writing Python code than even writing the prompts. Let alone the additional time going through the generated stuff to adjust and fix things.
It’s good to get a grip on syntax, terminology and as an overly fancy (but very fast) search bot that can (mostly) apply your question to the very code that’s in front of you, at least in popular languages. But once you got that stuff in your head… I don’t think I’ll bother too much in the future. There surely are tons of useful things you can do with multimodal LLMs, coding on its own properly just isn’t one of it. At least not with the current generation.
Yeah, I find LLMs are really nice for learning a new language when you know what you want to do, but not the specific syntax or best patterns. I’ve also found LLMs are great for stuff like crafting SQL queries, one off shell scripts, and building UIs. They can write certain kinds of code fairly well nowadays, but you want to keep the problem scope clear and focused.
I still write my code in calligraphy.
if it’s php / VB then LLM can have all the fun I don’t mind
show me an example of something you could write in 30 minutes that would take an LLM 3 hours.
Anything more complicated than business logic in JS/Python sends LLMs into a guessing game that can take you those 3 hours to get out of. Try asking it to write embedded software in C, hardware-interfacing code in Rust, or any non-trivial TemplateHaskell.
I’m not a Python engineer.
Manager came and decreed that all of our perfectly fine cron jobs (both of them) need to go to Astro/Airflow because we should use it because of reasons he couldn’t articulate.
Fine.
“As an experienced python engineer, blablabla, Dag, blablabla, Astro, prefer Astro over other imports, blablabla, errors as values, blablabla”.
With the tweaks and errors (including wrong imports) I had to redo it all from scratch anyway. LLM was good for the syntax though, like loops and function declaration.
I think the meme is suggesting that 3 hours was spent setting up a local llm, like in This video.
This is really not very accurate in my experience. What is your process? How are you screwing up LLM usage this badly?
lol I think this mostly happens when people give too broad a task to llms
