person
Hugh Zhang
Epoch AI researcher
Machine learning researcher at Epoch AI who has published on reproducibility of capability benchmarks and the scaling-data bottleneck.
current Researcher, Epoch AI
Strategy positions
Evals-drivenendorses
Capability/risk evals gate deployment; evals are the load-bearing artefactArgues capability evaluations need to be reproducible, publicly verifiable, and independent.
Benchmark reproducibility is an underrated governance infrastructure question.
Closest strategy neighbours
by jaccard overlapOther people whose strategy tags overlap with Hugh Zhang's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.
Record last updated 2026-04-25.