leodriesch

Absolute Zero: Reinforced Self-Play Reasoning with Zero Data

88 points by leodriesch 2 months ago | 19 comments

Does RL Incentivize Reasoning in LLMs Beyond the Base Model?

84 points by leodriesch 2 months ago | 38 comments

Nothing Chats – Bring on the blue bubbles

1 point by leodriesch 1 year ago | 0 comments

Grok, an AI Modeled After the Hitchhiker's Guide to the Galaxy

5 points by leodriesch 1 year ago | 2 comments

The Rome tools project is officially discontinued

4 points by leodriesch 1 year ago | 0 comments