Hacker News Reader

HNHacker News

Top New Best Ask Show Jobs

Comment by andrewmutz | Hacker News Reader

Parent Full thread

andrewmutz·

If you review every change as it goes, vibecoded results are often better than human-only and written much faster

View on HN

If you’re reviewing every change then what does “vibe coding” even mean?

It's not like human code doesn't need review.

the usage of vibe coding in my experience is towards those folks who run whatever the AI produced and if it does what they expect without throwing errors they ship it. If it throws errors they plug that back into the chatbot until the code stops throwing errors.

The whole point of vibe coding is its working faster than you would on your own. If you're reviewing it carefully and understand how it works, you might as well have written it by hand.

Even if it appears to do what you want, but you don't actually read and understand the code, how do you know it doesn't do something else also? Maybe something you don't want?

Irrelevant in vibe coding. If it walks like a duck and quacks like a duck, you don't go looking for extra heads, eyes, fingers, tongues, or tails. You ship it then throw repl.it under the bus when it blows up.

If I'm not mistaken, vibe coding is supposed to be when you don't review at all, you just let'r rip. Reviewing the AI's code is just... Like if coding was riding a bike, and you got an electric bike. Kind of. It doesn't seem like vibes to me.

This is me seeing co-workers PRs :(

I call this "half vibe coding" (needs a better term). For instances where you know how you'll solve a problem but don't want to type it all out it's great. I tend to comb through the output. Even the SOTA models will make pretty bad performance mistakes, poor maintenance decisions, etc. But it's super useful for getting over the hump of getting started on something.

I agree 100%.

Reply on news.ycombinator.com