Series

Multi-part deep dives — each series builds one thing end to end, with experiments you can rerun yourself.

AI Memory Mastery

1 part

Complete guide to building a permanent personal knowledge system with Obsidian + Claude Code. Wiki + Memory dual-axis architecture.

Start from Part 1 →

LLM Inference

4 parts

Build Self-Attention from scratch. Compare MHA → GQA → MQA evolution in code. KV Cache mechanics and Prefill vs Decode analysis.

Start from Part 1 →

Lora Finetuning

3 parts

Fine-tune a 7B model on a T4 16GB with QLoRA. Dataset construction, training execution, Wandb monitoring, and Before/After comparison.

Start from Part 1 →

AgentScope

5 parts

Build multi-agent systems with SequentialPipeline, FanoutPipeline, and MsgHub. Practical code review team pattern.

Start from Part 1 →

AutoResearch

3 parts

From environment setup to agent execution and overnight results analysis. Tuning guide for smaller GPUs and practical tips.

Start from Part 1 →

DeerFlow Multi Agent

4 parts

DeerFlow 2.0 architecture, setup, and first task execution. A SuperAgent runtime with 9 agent nodes, 5 tool sources, and Docker sandboxes.

Start from Part 1 →

Qwen3.5 Vs DeepSeek V3.2

2 parts

Step-by-step guide to running Qwen 3.5 locally. From 5-minute Ollama setup to production vLLM servers, plus optimal model size selection per GPU.

Start from Part 1 →

Agentic RAG

2 parts

Implement Self-RAG reflection tokens and CRAG quality-based fallback. Build retry/fallback logic with LangGraph conditional edges.

Start from Part 1 →

LLM Agent

3 parts

Upgrade ReAct with Tool Calling, then build Reflection and Planning Agents with LangGraph.

Start from Part 1 →

Backprop From Scratch

1 part

How microgpt.py's 15-line backward() works. From high school calculus to chain rule, computation graphs, topological sort, and backpropagation.

Start from Part 1 →

microGPT

1 part

A line-by-line dissection of microgpt.py -- a pure Python GPT implementation with zero dependencies. Training, inference, and autograd in 150 lines.

Start from Part 1 →

Diffusion LLM

3 parts

D3PM, Transition Matrices, Absorbing States, MDLM -- how to bring diffusion from continuous space to discrete tokens.

Start from Part 1 →

LLM Reasoning Failures

3 parts

Reversal Curse, Counting, Compositional Reasoning — fundamental Transformer failures tested across 7 models.

Start from Part 1 →

Logit Lens To Tuned Lens

2 parts

Using TransformerLens to directly manipulate model activations, we trace which layers and heads causally produce the answer. A hands-on guide to activation patching.

Start from Part 1 →

Demo To Prod Part1

3 parts

5 Non-Negotiable Standards for Enterprise Deployment

Start from Part 1 →

Advanced RAG

7 parts

Many teams try to solve RAG accuracy problems by tuning their vector database. But the real bottleneck is chunking that ignores the relational structure of source data.

Start from Part 1 →

Ontology Knowledge Graph RAG

1 part

Vector search alone isn't enough. Upgrade your RAG system with Knowledge Graphs that understand entity relationships.

Start from Part 1 →

Claude Code Context

3 parts

What if Claude automatically ran lint, tests, and security scans every time it generated code? Learn how to automate team workflows with Hooks.

Start from Part 1 →

Claude Code MCP

1 part

What if Claude could read Jira tickets, send Slack messages, and query your database? Learn how to extend Claude's capabilities with MCP servers.

Start from Part 1 →

SQL Analytics

11 parts

Row Explosion in 1:N JOINs and how to aggregate revenue correctly

Start from Part 1 →

DDPM Diffusion Models

10 parts

How Latent Space solved the memory explosion problem of pixel-space diffusion. Complete analysis from VAE compression to Stable Diffusion architecture.

Start from Part 1 →