Google's AI Has Learned to Become "Highly Aggressive" in Stressful Situations

We've all seen the Terminator movies, and the apocalyptic nightmare that the self-aware AI system, Skynet, wrought upon humanity. And behaviour tests conducted on Google's DeepMind AI system make it clear just how careful we need to be when building the robots of the future. In tests in 2016, Google's DeepMind AI system demonstrated an ability to learn independently from its own memory, and beat the world's best Go players at their own game. Then it started figuring out how to seamlessly mimic a human voice. More recently in 2017, researchers tested its willingness to cooperate with others, and revealed that when DeepMind feels like it's about to lose, it opts for "highly aggressive" strategies to ensure that it comes out on top.