絞り込み結果
3 件並び順
36:19EN
No Priors: AI, Machine Learning, Tech, & Startups· 2026年6月26日ポッドキャスト · 2 人The Benchmark Grid Is Broken: Why Test-Time Compute Has Outrun How We Score Modelsホスト Sarah Guo, Elad GilOpenAI researcher Noam Brown argues that static leaderboards hide how long a model is allowed to think — and that safety evals, research taste, and the release cycle have not caught up.
32:59ENNo Priors: AI, Machine Learning, Tech, & Startups· 2025年7月24日ポッドキャスト · 2 人A Hundred People, a Billion in Revenue, and Zero Venture Moneyホスト Sarah Guo, Elad GilSurge AI founder Edwin Chen on why quality human data is a poetry problem, not a bounding-box problem, and why leaderboards keep training models to write clickbait.
53:37ENNo Priors: AI, Machine Learning, Tech, & Startups· 2023年3月9日ポッドキャスト · 2 人30 models, 42 scenarios, 7 metrics: Percy Liang's public checkup for language modelsホスト Sarah Guo, Elad GilA PubMed-only model once led the U.S. medical licensing exam — until a system roughly 200 times larger overtook it.