Tag: scaling laws

Transfer and Emergence: When LLM Capabilities Appear at Scale

Transfer and Emergence: When LLM Capabilities Appear at Scale

Explore the phenomenon of emergent capabilities in LLMs and how scaling laws lead to sudden, unpredictable breakthroughs in AI reasoning and skill.

Hyperparameters That Matter Most in Large Language Model Pretraining

Hyperparameters That Matter Most in Large Language Model Pretraining

Learning rate and batch size are the two hyperparameters that most impact LLM pretraining success. Learn how scaling laws from 2025 let you calculate optimal values, avoid common pitfalls, and cut training costs by 90%.