person
Kate Saenko
Boston University CS professor; visual AI researcher
BU computer vision professor whose work on transferable AI representations and adversarial robustness has shaped the engineering side of AI safety.
current Associate Professor of Computer Science, Boston University
Strategy positions
Alignment firstmixed
Solve technical alignment before capability thresholds closeEngineer-grade alignment research: representation learning, adversarial robustness, transfer.
Robustness benchmarks are an under-developed scaffolding for AI safety practice.
Closest strategy neighbours
by jaccard overlapOther people whose strategy tags overlap with Kate Saenko's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.
Record last updated 2026-04-25.