writing.

rss feed

Technical deep-dives and reflection's on life and the world.

Reinforcement Learning from Human Feedback Jul 10, 2026

Understanding SnapKV: Compressing LLM Memory From First Principles Jun 23, 2026

Understanding LLM.int8(): Making Large Models Fit Jun 12, 2026

Understanding Flash Attention: Making Transformers Fast Jun 9, 2026

Transformer Architecture: From First Principles Jun 8, 2026

Understanding Self-Attention: From First Principles Jun 7, 2026

Why MCP (Model Context Protocol) is Here to Stay! Apr 25, 2025

Accuracy Without Context Is Like a Ship Without a Compass Apr 21, 2025

← back to hi ← back to home