Yesterday, I was debugging a performance problem with our Google Forms addon. It turned out my colleague had vibe coded the logging part, so that he could monitor the new installs every week. ... All of these are one line of code, but internally each of these makes multiple API calls to Google servers. Since logging was the first line to execute after installation, the welcome screen took 15 seconds to load.
AI is great at writing code. But it doesn’t know if you are launching the app or have millions of users, which it needs to make the right architecture call to log a timestamp vs email. It is also sycophantic and tries to execute your requirements exactly without pushing back, which means you end up with a slow app that takes 15 seconds to load a static welcome screen.
It is so paranoid about security that it will never write code to accept an unauthenticated payload. Even if you write it yourself, it will rewrite it into an authenticated payload and screw up performance or force users to sign in again on your app.
Just incredible seeing this post at the top next to "Unforced Navier-Stokes singularity, and the Generalized Riemann Hypothesis". We're at the "Japanese soldier who kept fighting 29 years after WW2" stage of AI denialism.