аннотация
What happens when artificial intelligence makes a mistake that affects people’s lives? Who can detect the error, stop the system, and repair the damage? Resilient AI explores the real challenges of AI safety, human oversight, and accountability. Drawing on research and real-world cases, Timur Ioseliani examines how to build AI systems that can be tested, controlled, and recovered after failure. Book Three of The Algorithmic Age series.
