Matt Perault(@MattPerault):.@RayanKrishnan and @Glenn__Parham of @ValsAI explain the “domain transfer fallacy” in AI. They argue that for a benchmark to be credible, it must test models on the real-world work they’re expected to perform. Better benchmarks give businesses and governments better evidence to choose the right model for the job.

Matt Perault

@MattPerault

Head of AI Policy @a16z. Fmr director of @UNC_TechPolicy and Facebook public policy.

参加 September 2012

639 フォロー中 2.8K ファン

Matt Perault@MattPerault

2026.08.19 17:06

.@RayanKrishnan and @Glenn__Parham of @ValsAI explain the “domain transfer fallacy” in AI. They argue that for a benchmark to be credible, it must test models on the real-world work they’re expected to perform. Better benchmarks give businesses and governments better evidence to choose the right model for the job.