While I agree on some level, this not a great comparison.
A compiler/linker/etc is an algorithmic, precise, verifiable, repeatable, debuggable, etc, etc, process.
Using an LLM is an inherently stochastic process. It can is very, very helpful, but I think we are arriving at the realization that "vibe coding" wasn't the best idea - unless you are doing a PoC or demo.
In any case, neither absolve you from understanding in detail what is going on.
Maybe we'll get there, and we can fully trust what the LLM produces, but it seems we are not quite there, yet. Until then we'll have to understand everything the LLM produces and that's what the author is getting at.
A compiler/linker/etc is an algorithmic, precise, verifiable, repeatable, debuggable, etc, etc, process.
Using an LLM is an inherently stochastic process. It can is very, very helpful, but I think we are arriving at the realization that "vibe coding" wasn't the best idea - unless you are doing a PoC or demo.
In any case, neither absolve you from understanding in detail what is going on.
Maybe we'll get there, and we can fully trust what the LLM produces, but it seems we are not quite there, yet. Until then we'll have to understand everything the LLM produces and that's what the author is getting at.