Unlike software 1.0 (deterministic code), ML systems degrade over time. Huyen introduces the concept of the "feedback loop." You learn to design systems that are not "set and forget" but adapt to:
Huyen dedicates significant space to covariate shift (change in input distribution), label shift (change in output distribution), and concept shift (change in relationship between input and output). She provides statistical tests (Kolmogorov–Smirnov, Population Stability Index) and monitoring strategies. Designing Machine Learning Systems By Chip Huyen Pdf
Most engineers want to tweak hyperparameters. Huyen forces you to look at the data pipeline first. She discusses: Unlike software 1