New

The latest blog posts to take off on Hacker News. 550 posts.

Tools & Productivity
2025
392

Absolute Zero Reasoner

Current reasoning models trained with Reinforcement Learning with Verifiable Rewards (RLVR) often rely on manually curated datasets, raising scalability concerns and potentially limiting future AI growth beyond human-defined tasks. To address this, we propose the Absolute Zero paradigm, where a single model…