When AI Goes Wrong, We Won't Be Able to Ask It Why

Deep learning algorithms could potentially learn to avoid the rules they where taught, so we won't understand their choices. So should we trust them like other humans? "Software governs much of our daily lives from behind the scenes, from which sorts of information we consume, to who we date. For some, secretive algorithms decide whether they are at risk of committing a future crime. It's only natural to want to understand how these black boxes accomplish all this, especially when it impacts us so directly.