He Wants AI Benchmarking To Be a Science, Not a Dark Art

T1Covered by 1 source · first reported by MIT News (research) / Quanta / The Conversation at 16 Oct, 13:25 UTC

Moritz Hardt, author of a new book on benchmarks, believes these “standardized tests” for artificial intelligence are fundamentally broken — but not unfixable. The post He Wants AI Benchmarking To Be a Science, Not a Dark Art first appeared on Quanta Magazine

ai

Sources

• T1He Wants AI Benchmarking To Be a Science, Not a Dark ArtMIT News (research) / Quanta / The Conversation16 Oct, 13:25