Two words: many-world interpretation.
More seriously, this is not a fair comparison. Adding LLM output to your source code is not analogical to quantum physics; it is analogical to letting your 5 years old child transcribe the experimentally measured values without checking and accepting that many of them will be transcribed wrong.
The point is that determinism is an emergent phenomena and when you dig deeper it reduces to a ground which is nowhere near as stable. So as a heuristic, moving away from deterministic models isn’t necessarily the wrong direction.
Many worlds is, like you just said, an interpretation, and interestingly only one of many!