Learn LLMs

I’ve spent the last 15+ years working in genomics, and I see myself as infinite learner. Recently, I began studying the technology behind Large Language Models (LLMs) —not to ride the latest AI-HASS (“hype as a service”) wave, but to understand the core technology that make these systems work.

These notes are my learning journal: a place where I collect, organize, and clarify what I’m discovering about LLMs and the broader ecosystem around them.

Building Blocks of GPT-2 LLM

• Introduction - Building Blocks of GPT-2 LLM
• Introduction to Large Language Models (LLMs)
• GPT - Generative Pretrained Transformer model
• Introduction to tokenization
• Introduction to embedding
• Transformer blocks
• Self-attention mechanism
• Masked Attention
• Multi-head self-attention
• Feedforward neural network (FNN)
• Language Modeling Head (LM Head)
• Pre-trained GPT-2 model end to end
• Dataflow across LLM
• Reference

Architecting Autonomous Systems

• Introduction - Architecting Autonomous Systems
• Anatomy and Taxonomy of Agents
• AI Agent Interoperability and MCP
• Context Engineering for Stateful AI Agents
• Case-study part 1: Explore Anatomy and Taxonomy of Agents
• Case-study part 2: Explore basics of context engineering
• Engineering Trust
• Reference