Training

5 posts in Training

Gold Medal at IMO and IOI: DeepSeek-V3.2 Matches GPT-5 with Open Weights

January 2026Training

Gold Medal at IMO and IOI: DeepSeek-V3.2 Matches GPT-5 with Open Weights

Why Reasoning Models Cheat on Efficiency: TNT's Fix Cuts Tokens 50%

January 2026Training

Why Reasoning Models Cheat on Efficiency: TNT's Fix Cuts Tokens 50%

Why Hyper-Connections Explode at Scale: DeepSeek's Manifold Fix

January 2026Training

Why Hyper-Connections Explode at Scale: DeepSeek's Manifold Fix

6% Better Math Reasoning in Fewer Tokens: Multiplex Thinking Merges Multiple Paths into One

January 2025Training

6% Better Math Reasoning in Fewer Tokens: Multiplex Thinking Merges Multiple Paths into One

Zero Training Data, Full Performance: Dr. Zero Matches Supervised Search Agents

January 2025Training

Zero Training Data, Full Performance: Dr. Zero Matches Supervised Search Agents