[rocqua]

Vibe coding hasn't really hampered my critical thinking. It just means I get ideas into practice faster, and it means that for new concepts I can get to itterating much faster.

Perhaps I have the concept wrong, because half the time I'm still editing code by hand.

[danielbln]

I agree, and I think it's a continuum. I can say "make me an Instagram clone" and then come back after 100 agent loops and no looking at the code. Or I can outline the architecture, the components, service layer, data structures etc in a back and forth with the LLM and then have it do the minutia implementation.

You still get code hell after a while unless you review the code and refactor where needed, but I can absolutely imagine a future where the code is just a compile target for the architecture and design I specify. A little bit like a compiler spitting out assembly (caveats apply, LLMs being non-deterministic etc etc and at current state probably not reliable enough for full unsupervised coding)

[SAI_Peregrinus]

If you edit the code, instead of the prompt to the AI, it's not vibe coding. Vibe coding is letting the AI write the code, and only testing the output application.