I think you're mixing two different concepts up here.
Determinism in the context of fuzzing is related to the reproducibility of a program state. It's deterministic in the sense that all the inputs to the system are known and controlled. This allows us to repeat all inputs and reproduce the exact same behaviour as before, e.g. an error state we stumbled upon or an interesting program state we want to continue exploring.
This in no way precludes sampling the input space stochastically. Brute forcing by sampling all possible inputs sequentially is usually untenable and wasteful. However, once you do encounter a new program state, you'll be able to perfectly recreate it forever.
I think you're right, I was mixing two concepts and my question wasn't really about determinism.
Writing a specialized OS suggests to me that someone is very focused on... the best way I can describe it is cutting a fat trajectory through the input space. I am curious if anyone is spending their effort on sparser (but more intelligent) sampling of the input space instead.
Yes, there's a lot of work being done on more intelligent fuzzing. To throw some terms into the mix, there's coverage-guided fuzzing (which is now an old technique), concolic testing (which combines concrete execution with symbolic execution in order to reach new branches in a targetted way) and grammar fuzzers (which generate valid inputs according to a grammar).
These are not really mutually exclusive with the type of work gamozolabs is doing because even with hyperintelligent input generation, you still ideally want raw speed.
Determinism in the context of fuzzing is related to the reproducibility of a program state. It's deterministic in the sense that all the inputs to the system are known and controlled. This allows us to repeat all inputs and reproduce the exact same behaviour as before, e.g. an error state we stumbled upon or an interesting program state we want to continue exploring.
This in no way precludes sampling the input space stochastically. Brute forcing by sampling all possible inputs sequentially is usually untenable and wasteful. However, once you do encounter a new program state, you'll be able to perfectly recreate it forever.