I highly recommend Stuart Russell's new book, Human Compatible: Artificial Intelligence and the Problem of Control. This book effectively communicates the issues of AI safety and control to a general audience. I especially like this book because it vindicates the ideas of my forgotten AGI-12 paper, Avoiding Unintended AI Behaviors, as explained here: https://www.ssec.wisc.edu/~billh/g/hc_and_agi12.html
------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tb23b29b1f508a00f-M23c8f050fe61ab1d0c16897b Delivery options: https://agi.topicbox.com/groups/agi/subscription
