person

Fernanda Viégas

Harvard; ex-Google PAIR; data visualization

Harvard professor and long-time collaborator with Martin Wattenberg; co-led Google's PAIR initiative on human-centered AI. Specialist in visualization and interaction for understanding complex ML systems.

current Sally Starling Seaver Professor at Radcliffe / Gordon McKay Professor of Computer Science, Harvard University

past Senior Staff Research Scientist, Google Research (PAIR)

homepage @viegasf

Strategy positions

Interpretability betendorses

Mechanistic interpretability is necessary and sufficient to know models are safe

Argues human–AI interaction is best designed when people can see and steer model internals; co-led major industry investments in this approach at Google PAIR before moving to Harvard.

Interactive visualizations turn opaque models into objects we can think with. That is the path to AI that humans can actually verify and shape.

¶ articleFernanda Viégas, Harvard· Harvard SEAS· 2024· faithful paraphrase

Closest strategy neighbours

by jaccard overlap

Other people whose strategy tags overlap with Fernanda Viégas's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.

Asma Ghandeharioun
shared 1 · J=1.00
Google DeepMind; 'Patchscopes' for LLM interpretability
Chris Olah
shared 1 · J=1.00
Anthropic interpretability co-founder; inventor of modern mech interp
Cynthia Rudin
shared 1 · J=1.00
Duke professor; interpretable ML pioneer
David Bau
shared 1 · J=1.00
Northeastern; mechanistic interpretability of LLMs
Jacob Andreas
shared 1 · J=1.00
MIT NLP; language models as belief reports
John Wentworth
shared 1 · J=1.00
Independent alignment researcher; natural abstractions

Record last updated 2026-04-25.