person
Moritz Hardt
MPI Tübingen; algorithmic fairness, evals
Director at the Max Planck Institute for Intelligent Systems; co-author of 'Fairness and Machine Learning' (free textbook). Recent work emphasizes the limits of static benchmarks under distribution shift and adaptive deployment.
current Director, Max Planck Institute for Intelligent Systems, Tübingen
Strategy positions
Evals-drivenmixed
Capability/risk evals gate deployment; evals are the load-bearing artefactArgues current AI benchmarking is dangerously brittle: leaderboards reward overfitting to fixed test sets and obscure how models behave under shift. Calls for adaptive, externally validated evaluation.
Benchmarks are the most valuable lever in machine learning, and the field treats them as if they were neutral measurements rather than artefacts shaping research.
Closest strategy neighbours
by jaccard overlapOther people whose strategy tags overlap with Moritz Hardt's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.
Record last updated 2026-04-25.