The problem I see here is that AI may write code that does compile, but has a bunch of logical errors, edge cases or bad architecture. From personal experience, even though AI can write small amounts of good code, it’s bad at understanding big and complex solutions.
At that point, fixing the AI codebase might take longer than just starting with a competent Rust dev.
The
core-js
story always makes me sad. Sure, he’s developing an open source project and no one HAS to pay him. But the meager amount of donations and the tons of hate he receives isn’t justifiable.