Reasoning Models
Test-time compute, process reward models, the o-series, DeepSeek-R1 and contamination.
—
0 known
0 to review
Loading deck…
Space to flipSpace flip · ← → move · K known · R review · S shuffle
Test-time compute, process reward models, the o-series, DeepSeek-R1 and contamination.
Loading deck…
Space to flipSpace flip · ← → move · K known · R review · S shuffle