-
19 posts
Learn LLM
A practical LLM course that moves from PyTorch training loops, tokenizers, attention, and MiniGPT into RAG, SFT, LoRA, evaluation, safety, and domain projects.
Start here: Chapter 1: Training Loops, Computation Graphs, and Reproducible Experiments
-
25 posts
Build Harness
A hands-on path from a simple CLI assistant to a controllable, observable Agent Harness.
Start here: Agent Base Definition: Why It Is Not a Prompt
-
5 posts
Agent Design Paradigms
Long-lived design paradigms for Agent systems, from Context Manager, tool boundaries, memory governance, collaboration isolation, to runtime control.
Start here: Guide to the Agent Design Paradigms Series
-
16 posts
Claude code
An index for the Claude Code source analysis series, organized around architecture, core mechanisms, tools, extensibility, and collaboration.
Start here: Guide to the Claude Code Source Analysis Series