Hacker News new | ask | show | jobs
by StriverGuy 22 days ago
Huh? This approach makes sense for non-deterministic problems. Not engineering problems that have deterministic end results.
2 comments

I’d want to estimate P(a random test passes) where the existing suite of tests is taken to be sampled from a distribution.
> non-deterministic problems

I'm guessing you mean probabilistic? Nevertheless, you have an indeterministic variable here which is what the LLM generates.