factual
Benchmark gains reflect expert labor not just scale
When frontier models improve at benchmarks, we should attribute it not just to increased scale and clever ML ideas but to billions of dollars spent paying PhDs, MDs, and other experts to write questions and example answers targeting those precise capabilities.
factualpending
Speaker
Dwarkesh PatelEvidence Quote
“billions of dollars spent paying PhDs, MDs, and other experts to write questions and provide example answers and reasoning targeting these precise capabilities”
Created: 6/13/2026, 3:34:40 AM
Your notes
Loading notes...