Explainable AI won't deliver. Here's why. – Cassie Kozyrkov – Medium

Explainable AI (XAI) is getting a lot of attention these days, but it won't deliver the basis for trust you're hoping for. Before we get caught up in the hype, let's examine the wisdom of a sentence I've been hearing a lot lately: "in order to trust AI, we need it to be able to explain how it made its decisions." There are two ways that we can communicate what we want when programming a computer, we can either give explicit instructions -- handcrafted code -- where we tell the computer how to convert the input into the output… or we can say, "Here, look at a bunch of examples and figure it out." That second one is the essence of artificial intelligence: explaining our wishes with data rather than instructions.