1
The inefficiency of RL, and implications for RLVR progress
And implications for RLVR progress
Deeply researched interviews. Click to read Dwarkesh Podcast, by Dwarkesh Patel, a Substack publication with hundreds of thousands of subscribers.
Visit dwarkesh.com → RSS feedOn Hacker News Apr 2025 – Sep 2026
AI & Machine Learning 10Tech Industry & Business 7Society, Policy & Culture 1Software Engineering 1Math & Algorithms 1
And implications for RLVR progress