This might be buggy whip talk, but I wonder if you could take the same system and apply it to smaller problems (e.g. computing an 8-bit hash) so the novel techniques could be identified and used by humans.
One of the examples from another comment[1] here was:
"They found that in a sorting network handling 3 inputs, the AI found a way to save an instruction by reducing a "min(A, B, C)" operation to just "min(A, B)" by taking advantage of the fact that previous operations guaranteed that B <= C."
This might be buggy whip talk, but I wonder if you could take the same system and apply it to smaller problems (e.g. computing an 8-bit hash) so the novel techniques could be identified and used by humans.