# the archive

>every note published · grep by topic · search by keyword

April 12, 2026-21 min read

The Evolution of AI Engineering: From Prompt to Context to Harness

Working with LLMs has moved through three phases: prompt engineering, context engineering, and now harness engineering. Here's why the environment you build around the model matters more than the model itself.

AI EngineeringHarness EngineeringContext Engineering

April 11, 2026-25 min read

Understanding Transformers: From First Principles to Production GPTs

A Feynman-style deep dive into the Transformer architecture. We build intuition from the simplest possible idea up to full GPT implementations, tracing Karpathy's progression from micrograd to nanochat.

Deep LearningTransformersNLP

April 11, 2026-32 min read

Building AI Agents: From First Principles to Production

A deep dive into AI agents, starting from the simplest possible idea and building up to production-grade agentic systems with tool use, memory, reasoning loops, and multi-agent orchestration.

AILLMAI Agents