Things that it can probably do sometimes, but will fail on some inputs:
Solve NP-Complete or harder problems
There are other “tail end” tasks like this that should eventually become the hardest bits that optimization spends the most time on, once it manages to figure everything else out.
If we knew (for some reason) that a system had no useful abstractions (or at least, no small ones), what could we say about that system? Does it reduce to some vacuous thing? Or does it require it to be adversarial in nature?