This lecture explores the generalization of ImageNet classifiers over the past decade, analyzing the progress made and the impact of key papers in machine learning and computer vision. It delves into the creation process of ImageNet, the challenges faced in achieving reliable machine learning models, and the implications for evaluating machine learning models beyond the i.i.d. setting. The lecture also discusses the robustness of machine learning models to adversarial attacks and distribution shifts, highlighting the importance of measuring robustness and promoting reliable engineering practices.