How Do You Think About Interpretability of Machine Learning Models?

In airplanes, you have this thing called the MCAS, so the midair collision avoidance system. The old version of MCAS is described in a document that has a bunch of pseudocode and it's like hundreds of pages long. And there is a new version ofMCAS which is sort of almost like a dynamic programming based thing. It's not full machine learning, but all of its decision points are like codified in a in a table. Although from a human perspective, it's probably less easily decipherable.