How do you teach a machine right from wrong? Addressing the morality within Artificial Intelligence

In his new novel, Machines Like Me, the novelist Ian McEwan tells the story, set in an alternate history in England in 1982, of a man who buys a humanoid robot. This triumph of artificial intelligence is "a creation myth made real," he writes, but also "a monstrous act of self-love." Part companion and part servant, the robot named Adam is "the ultimate plaything, the dream of ages, the triumph of humanism -- or its angel of death." One of the first things Adam says when he is switched on is "I don't feel right," and, typically for cautionary tales about robots, it only gets worse from there. Like much of the frontier thinking on the morality of artificial intelligence, McEwan's unsettling vision comes from fiction, not science.