So her criticism #3 of essentially my second paragraph is that you can't assume anything, because we don't actually have a superdeterministic theory to evaluate. Maybe there's a dynamic law we haven't figured out that could make it work without initial fine tuning.

Fair enough I guess, but I'm not convinced it's a good answer to say "I think a theory with property X is the answer, and you can't criticize it because I have no actual theory with property X." I think it makes more sense to give little credence to superdeterminism until someone comes up with a plausible superdeterministic theory.