zlacker

As someone who vibe codes at times (and is a professional programmer), I'm curious how yall go about resisting this? Just avoid LLMs entirely and do everything by hand? Very rigorously go over any LLM-generated code before committing?

It certainly is hard when I'm say writing unit tests to avoid the temptation to throw it into Cursor and prompt until it works.

>>jobs_t+(OP)
Set a budget. Get rate limited. Let the experience remind you how much time you’re actually wasting letting the model write good looking but buggy code, versus just writing code responsibly.

>>jobs_t+(OP)
I resist it by realizing that while LLM are good at things like decoding obtuse error messages, having them write too much of your code leads to a project becoming almost impossible to maintain or add to. And there are many cases where you spend more time trying to correct errors from the LLM than if you were to slow down and inspect the code yourself.

>>samtp+89
If you don’t commit its output until it’s in a shape that is maintainable and acceptable to you— just like with any other pair programming exercise— you’ll be fine. I do think your skills will atrophy over time, though. I’m not sure what the right balance is, here.

>>christ+rh
My honest opinion is that some of my skills are atrophying, and some of them are increasing.

I have managed a python app for a long time due to it being part of a much larger set of services I manage. I've never been particularly comfortable with it.

I am easily learning, and understanding the python much much better.

I think I'm atrophying in a lot of syntax, and typing automatic things.

It doesn't really feel straight forward that it's one or the other.