The study involved a self-learning artificial intelligence system, GloVe. It has the ability to read and interpret online text. "We replicate these using a widely used, purely statistical machine-learning model--namely, the GloVe word embedding--trained on a corpus of text from the Web," reads the study. But when researchers offered GloVe a list of white and black-sounding names, the robot went absolutely racist! The intelligent system identified names that are common among white people as "pleasant", while African-American names were categorized as "unpleasant" words. "Our results indicate that language itself contains recoverable and accurate imprints of our historic biases," the researchers told RNS.