Hacker News new | ask | show | jobs
by michelpp 420 days ago
I turn 50 tomorrow and I love vibe coding. In the hands of an expert with decades of experience in all the internal corners of C, Python and Postgres I find AI tools to be miracles of technology. I know how to ask them exactly what I want and I know how to separate the goodness from the bullshit. If Supabase is bringing AI closer to the developer at the database level then that is a great thing.
3 comments

Vibe coding is excellent if you have the experience to understand what the AI is churning out and then what to do with it.

The problem we have now is we have people who aren't engineers trying to make an app and they end up creating insecure and buggy messes, then struggle with figuring out how to deploy, or they end up destroying all their code with no recovery because they didn't know anything about version control.

All of those things were already happening with normal developers 10, 20, 30 years ago, and will keep happening, with or without AI.
AI allows it to happen at scale though.
As a professional developer, this seems like a problem I don't need to care about.
Do you have any writings or materials that show your process in depth? I’m interested in learning from those who know how to really squeeze the juice out of these tools.
I think what they are saying is the 'secret sauce' to successfully vibe coding is being an expert with all the languages, frameworks and tools yourself.

Makes sense to me, vibe coding basically shifts your burden to specification and review, which are traditionally things a senior developer should be good at.

I think there is a lot to be said about what tasks you give to it, how you describe the work and prompt it, and the iteration / workflow loop.

I have a limited intuition for this based off my AI usage the past few years, but I want to learn from the pros.

I agree with this - I hear a lot of hate towards vibe coding but my experience with voice dictation and using 20 years experience in the trenches and so being very specific telling the model what to do has been, well, refreshing to say the least.

I used to pride myself of knowing all the little ins and outs of the tech stack, especially when it comes to ops type stuff. This is still required, the difference is you don't need to spend 4 hours writing code - you can use the experience to get to the same result in 4 minutes.

I can see how "ask it for what you want and hope for the best" might not end well but personally - I am very much enjoying the process of distilling what I know we need to do next into a voice dictated prompt and then watching the AI just solve it based on what I said.