I don't pay $100 to "vibe code" and "learn to program" or "avoid learning to program."
I pay $100 so I can get my personal (open source) projects done faster and more completely without having to hire people with money I don't have.
I don't pay $100 to "vibe code" and "learn to program" or "avoid learning to program."
I pay $100 so I can get my personal (open source) projects done faster and more completely without having to hire people with money I don't have.
Restoring a bit of balance to things.
I review all of it, but hand write little of it. It's bizarre how I've ended up here, but yep.
That said, I wouldn't / don't trust it with something from scratch, I only trust it to do that because I built -- by hand -- a decent foundation for it to start from.
But I’ve not found that to be true at all. My actually engineered processes where I care the most is where I push tokens the hardest. Mostly because I’m using llms in many places in the sdlc.
When I’m vibing it’s just a single agent sort of puttering along. It uses much fewer tokens.
I said "by and large" ie generally speaking. As I mentioned before, the exception does not invalidate the trend. I assume HN is more heavily weighted towards non-vibe-coders using up tokens like me and you but again, that's the exception to what I see online elsewhere.
Programming has always been about levels of abstraction, and the people who see LLM-generated code as “cheating” are the same people who argued that you can’t write good code with a compiler. Luddites, who will time-and-time again be proven wrong by the passage of time.