leodriesch

Posts

• Absolute Zero: Reinforced Self-Play Reasoning with Zero Data
  by leodrieschon 5/11/2025, 7:07 AMwith 19 comments
• Does RL Incentivize Reasoning in LLMs Beyond the Base Model?
  by leodrieschon 4/22/2025, 10:24 AMwith 38 comments
• Nothing Chats – Bring on the blue bubbles
  by leodrieschon 11/14/2023, 4:17 PMwith 0 comments
• Grok, an AI Modeled After the Hitchhiker's Guide to the Galaxy
  by leodrieschon 11/5/2023, 12:50 PMwith 2 comments
• The Rome tools project is officially discontinued
  by leodrieschon 9/2/2023, 6:04 AMwith 0 comments