Skip to content

Dwarkesh Patel personal blog

The inefficiency of RL, and implications for RLVR progress

dwarkesh.com published 2025-11-17

And implications for RLVR progress

Read on dwarkesh.com → Discuss on HN (48) Archived copy

Points: 120
HN comments: 48
Submissions: 1
Cited by: 0 commenters

AI & Machine Learning Math & Algorithms 2025

On Hacker News

Submitted	Title on HN	Points	Comments
Nov 27, 2025	The inefficiency of RL, and implications for RLVR progress by cubefox	120	48

More from Dwarkesh Patel

All 10 posts →

Andrej Karpathy – It will take a decade to work through the issues with agents

20251,212 points1,115 comments AI & Machine Learning details

Ilya Sutskever: We're moving from the age of scaling to the age of research

2025450 points355 commentscited by 4AI & Machine Learning details

I don't think AGI is right around the corner

2025374 points442 comments AI & Machine Learning details

The Rise and Fall of Agent Civilizations

2026277 points197 commentscited by 8AI & Machine Learning details

I'm glad the Anthropic fight is happening now

2026179 points220 comments AI & Machine Learning details

AGI Is Still 30 Years Away – Ege Erdil and Tamay Besiroglu

2025174 points375 comments AI & Machine Learning details

Related posts from the same era

Statement on US government directive to suspend access to Fable 5 and Mythos 5

Anthropic20263,158 points2,314 commentscited by 11 details

GPT-4o

OpenAI Blog20243,138 points2,366 commentscited by 16 details

Astra can read and write weights to improve Qwen

Rikiya Takehi20262,959 points899 comments details

HackerTube: YouTube built from videos recommended by HN

karpathy20262,886 points641 comments details

Claude Fable 5

Anthropic20262,626 points2,159 commentscited by 10 details

Claude Code is steganographically marking requests

Thereallo20262,445 points750 commentscited by 3 details