# Kaplan Scaling Laws (2020): Power Law Anatomy of LLM Performance — Compute, Data, Param Triangle

> Source: https://sukruyusufkaya.com/en/learn/llm-muhendisligi/kaplan-scaling-laws-2020-power-law
> Updated: 2026-05-13T13:00:28.882Z
> Category: LLM Mühendisliği
> Module: Module 12: Scaling Laws — Growth Laws of LLMs
**TLDR:** Anatomy of Kaplan et al. 2020 paper: LLM loss follows power law for compute (C), parameters (N), data (D). Why log-log plot is linear, optimum allocation formula, 'bigger is better' claim, GPT-3 (175B) was built on this. Limitations and subsequent Chinchilla refutation.