zlacker

>>Tenoke+(OP)
I just spent some time trying to make claude and gemini make a violin plot of some polar dataframe. I've never used it and it's just for prototyping so i just went "apply a log to the values and make a violin plot of this polars dataframe". ANd had to iterate with them for 4/5 times each. Gemini got it right but then used deprecated methods

I might be doing llm wrong, but i just can't get how people might actually do something not trivial just by vibe coding. And it's not like i'm an old fart either, i'm a university student

>>amarch+Fd
Yes, you're most likely doing it wrong. I would like to add that "vibe coding" is a dreadful term thought up by someone who is arguably not very good at software engineering, as talented as he may be in other respects. The term has become a misleading and frankly pejorative term. A better, more neutral one is AI assisted software engineering.

This is an article that describes a pretty good approach for that: https://getstream.io/blog/cursor-ai-large-projects/

But do skip (or at least significantly postpone) enabling the 'yolo mode' (sigh).

>>dinfin+ek
You see, the issue I get petty about is that Ai is advertised as the one ring to rule them all software. VCs creaming themselves at the thought of not having to pay developers and using natural language. But then, you have to still adapt to the Ai, and not vice versa. "you're doing it wrong". This is not the idea that VCs bros are selling

Then, I absolutely love being aided by llms for my day to day tasks. I'm much more efficient when studying and they can be a game changer when you're stuck and you don't know how to proceed. You can discuss different implementation ideas as if you had a colleague, perhaps not a PhD smart one but still someone with a quite deep knowledge of everything

But, it's no miracle. That's the issue I have with the way the idea of Ai is sold to the c suites and the general public