Person
Cynthia Rudin
Cited in three posts, among them TASRA: a Taxonomy and Analysis of… and AI-caused catastrophe, since September 2026
Where they come up
Said by someone else — these sentences name them.
“Rudin (2019) argues further that “trying to explain black box models, rather than creating models that are interpretable in the first place, is likely to perpetuate bad practices and can potentially cause catastrophic harm to society”.”
· TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI · machine-resolved
In the claim ledger
2 promoted claims about them. Assessments are the model’s knowledge, not verification.
Rudin argues post-hoc explanation of black boxes perpetuates bad practice and risks catastrophic societal harm.
consistent · TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI
Interpretability can be improved drastically at little performance cost, per Semenova and Rudin.
plausible · TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI