Get personalized book recommendations based on your reading history and preferences. Our algorithm analyzes your favorite books and reading patterns to suggest your next great read.

AI Safety is a category focused on how to design, evaluate, deploy, and govern artificial intelligence systems so they are reliable, controllable, and aligned with human values. Books here span technical and accessible works on topics such as alignment and value specification, robustness to failures and distribution shift, interpretability and monitoring, adversarial attacks and defenses, human oversight and evaluation, and secure deployment. The category also covers ethical and societal issues—bias and fairness, privacy, misinformation, transparency, and labor impacts—alongside governance, standards, auditing, regulation, and risk management. Many titles address both near-term safety concerns and long-term or frontier risks, including debates about existential safety. The field is interdisciplinary, drawing from computer science and machine learning, philosophy, law, economics, and public policy, and includes research monographs, textbooks, handbooks, case studies, and popular introductions.

Filter books by their publication year. Enter the earliest year (Start) and latest year (End) to find books published within that period. Leave either field empty to search from the beginning of time or up to the present day.