LLM Architecture Explained: From Tokens to Text
2026-03-03A practical walkthrough of modern LLM architecture: tokenizer, transformer blocks, attention, training, and inference-time optimization.
LLMTransformersAI Systems
Blogs
Notes on building products, systems, and AI applications.
Horizontal Scaling in Databases: Part 1 - Read Replicas
2025-12-26How read replicas reduce primary database load, improve read throughput, and what consistency tradeoffs to watch in production.
DatabasesScalabilityBackend