[Twey]

Right… but what I'm saying is that for the most part if the compiler pushes back on your LLM-generated code it's because that code is wrong. In the LLM world these are known as ‘guardrails’ and they're great because they a) provide some level of automated verification of the generated code and b) provide actionable feedback to the model to fix the code, where otherwise a human would have to notice the bug and enter the loop. The compiler pushing back on things early is a big positive for vibe coding.

In this particular case maybe Rust isn't the right choice because (idiomatic) Rust is designed for the case where you care about your memory management, and for your blog you probably don't. But that's a comment on the suitability of Rust for blogs, not a comment on the suitability of Rust for vibe coding.