Writing log70 posts286 tagslatest Jul 10, 2026
Scaling.
Latest posts
LLaMA (2023) Paper Notes
Paper notes on LLaMA covering its core strategy — train smaller models for longer on publicly available data, optimized for inference — the result where a 13B model beats 175B GPT-3, the RMSNorm/SwiGLU/RoPE architecture changes, the 2048-A100 training scale, and how it kicked off the open LLM ecosystem.
Checking Duplicate IDs Among Billions — Is a Bloom Filter Really the Answer?
A clear explanation of how Bloom filters work, how to use them correctly for user-ID duplicate checks during sign-up, and a concise implementation example.