想搞懂 Scaling Laws？Lilian 这篇把 Kaplan vs Chinchilla 的争论讲透了，还有实操建议。
Lilian Weng 发布了一篇关于 scaling laws 的博文，详细解释了如何通过缩放定律在数据量和模型尺寸之间做计算最优分配。文章对比了 Kaplan et al.（2020）和 Chinchilla（2022）两篇经典论文的分歧：前者主张模型尺寸随计算量更快增长，后者主张等比例增长。文中还指出数据限制和拟合细节会使外推变得不可靠。
A super long overdue (3+ years?) post on scaling laws. Compute is expensive. Scaling laws are a way...
A super long overdue (3+ years?) post on scaling laws. Compute is expensive. Scaling laws are a way to help us reason about the optimal compute allocation between data and model size before committing to a large run. The post covers what scaling laws predict, how compute-optimal allocation works, why Kaplan et al. and Chinchilla disagree, and how data limits + fitting details make extrapolation tricky. lilianweng.github.io/posts/2026-06-… 💬 39 🔄 335 ❤️ 2660 👀 174771 📊 803 ⚡