That Space Cadet Glow No.29

One of the biggest risks of Artificial Intelligence is that no-one really understands how it works. By that I mean that when a complex algorithm works something out, it is extremely difficult to reverse engineer the process that was followed to get to that decision (a bit like recreating an egg from an omelette). This opaqueness of the inner workings of the algorithms is a worry to people who rely on the types of decisions it is making, such as credit approvals, medical diagnoses and financial trading. This allows it to test for discrimination, either in the underlying models used or in the way the AI has been trained - any adaptive system will inherently reflect the biases of the information (and people) used to train it. So, if a system to filter job applications is built, it could easily do that role with, say, gender bias if the training data and any subsequent reinforcement included that bias.