Computer Vision Interview Questions, issue 4, Jan 5, 2026
The L1 vs L2 Geometry Trap
Senior Computer Vision Engineer interview at Google, and the interviewer asks:
βWeβre building a similarity search for a new dataset. If I arbitrarily rotate the feature space by 45 degrees, which distance metric falls apart: π1 π¨π« π2? And what does that tell you about our feature engineering strategy?β
Why rotating the feature space instantly exposes candidates who donβt understand metric invariance.
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.