And the vibe coder is also blissfully unaware of all the zero days he/she has also deployed along with his prompted autocomplete output of a program.

Great work! Very efficient!

I'm totally sure said program doesn't also needlessly pull in a gigantic mess of additional libraries, just to use one or two functions from it, I'm sure this is a very compute and memory efficient program.

And I am totally sure this will all work great and be easily reconfigured to keep up with any changing requirements, because we all know software devs always get very concrete, stable, and well defined requirements to work with.

I've tried Copilot for a while and played around with Cursor for a bit. I was better and faster without Copilot due to sometimes not paying enough attention of the lines it would generate. This would cause subtle bugs that took a long time to debug. Cursor just produced unmaintainable code-bases that I had no knowledge of, and to make major changes, would be faster for me to just rewrite it from scratch. The act of typing gives me time to think more about what I'm doing or am going to do, while Copilot generations are distracting and break my thought processes. I work best with good LSP tooling and sometimes AI chatbots (mostly just for customized example snippets for libraries or frameworks I'm unfamiliar with; though that has its own problems because the LLMs knowledge is out of date a lot) that don't directly modify my code.