[oneplane]

Isn't this the same thing as no-code, low-code, MS Access, Excel, HyperCard, 4GL, COBOL etc. we've already had? The idea being that you can build something without knowing how to build something (on a gradient -- you could argue that on the COBOL end of the spectrum you need much more than the no-code end).

I doubt this time around, the AI-flavoured variant is going to change much, except perhaps the volume.

[layer8]

The existing no/low-code has a more limited and controlled design space, and what the “coder” works with has deterministic behavior. With LLMs, they can do anything (including things you don’t want), and you don’t know how well your instructions map onto what they generate (only by testing, not by reasoning). When LLM-created designs run into unmaintainable territory, the corresponding code is invisible to the “coder”. This is unlike no/low-code, where even if the application becomes unmaintainable, the “coder” still has the full overview over their design. Vibes-coding is akin to write-only, you can’t tinker with your specification and see how the output changes; instead all previous output becomes part of the specification, an increasingly growing part that the “coder” doesn’t understand.