Luke Salamone's Blog

• Training a Chess Reasoning Agent Oct 11
• Paper Summary: The Matthew Effect in RL Sep 26
• Semantic Search in Under 3MB Jun 19
• Teaching a Neural Net to Fight Jun 8
• Definitions of Model Apr 5
• Autoresearch Mar 11
• Distilling Stockfish with One Billion Positions Mar 6
• Graph Topology and Battle Royale Mechanics Feb 19

• How well can Stockfish Estimate Itself? Nov 30
• Multi-Agent RL Nov 22
• Optimal Ask Sep 16
• Can a Neural Net Learn It? Sep 16
• Keep Summer Safe Mar 20
• Notes on Deepseek R1 Jan 28

• Space Is Really Big Jul 29
• Custom PyTorch Collate Function Jul 12
• Very Large Datasets in PyTorch Jun 27
• How to Create Rust Python Bindings Jun 18
• The Most Ramified Chess Position of 2023 Jun 13
• What are Sparse Autoencoders? Jun 6