The Alignment Problem: Machine Learning and Human Values

Recommended by Isaac Kohane, Marion V. Nelson Professor of Biomedical Informatics, chair of the Department of Biomedical Informatics, Harvard Medical School, and professor of pediatrics, Boston Children’s Hospital

“The Alignment Problem” offers a crucial exploration of one of the most important challenges we face: ensuring that artificial intelligence systems actually do what we want them to do. Brian Christian illustrates complex technical concepts through storytelling, showing how the seemingly abstract problem of AI alignment manifests in everyday situations. In doing so, he highlights some of the less-well-known giants on whose shoulders AI stands.