Joined 12/27/2020, 10:51:04 PM has 1110 karma
Absolute Zero: Reinforced Self-Play Reasoning with Zero Data
Does RL Incentivize Reasoning in LLMs Beyond the Base Model?
Nothing Chats – Bring on the blue bubbles
Grok, an AI Modeled After the Hitchhiker's Guide to the Galaxy
The Rome tools project is officially discontinued