I think "gambling" is a bit too strong, but there is a real shift in how we evaluate correctness. With traditional coding, you reason step by step and with AI-assisted code, you're often validating outputs after the fact.
The risk isn't randomness per se it's over trusting something that looks correct. The skill ceiling is moving from "can you write it" to "can you reliably verify it"
But “reliably verify it” was always the critical difference between high and low quality engineering efforts.
Good programmers might have made things that “performed well”, and had “few bugs”, without this step, but it was not robust to changes over time. If we end up in a place where every project has solid automated verification, perhaps things get better overall.