How would deletion requests propagate through datasets, features, trained models, and cached predictions?
AceStack AI
Tech Screening
Privacy in ML data
What this task practices
Privacy in ML data is a tech screening interview exercise that trains prompt interpretation, explicit assumptions, a concrete response, and a clear explanation of tradeoffs. The catalog marks it as medium difficulty. It focuses on Tradeoffs, Ownership, Technical Reasoning. The signed-in workspace provides the tools for the round and evaluates the attempt against task-specific criteria. Reference solutions, hidden checks, evaluator instructions, and candidate work remain private.
Sign in to startThe workspace and evaluation open after sign in.