Start Here
294 posts in reverse-chronological order is an archive, not a way in. This page is the way in.
If you have five minutes
The four posts that best show what this blog does — read one primary source properly, verify the claims, and report what actually held up:
- Ouroboros: The Agent OS That Hides the Answer Key From Its Own Workers — a spec-first agent OS where the grading command never reaches the worker. Includes a stdlib reimplementation of its two mathematical gates, plus one documentation defect found by reading the source instead of the docs.
- Twelve Concepts, One Missing Layer — worked through a 12-article agent curriculum and found the load-bearing layer missing from its own summary. Durable execution implemented and verified from scratch.
- Fable 5 Isn’t a Faster Chat Model — the substrate for self-improving agents, read as a systems question rather than a benchmark race.
- Prompt Repetition: A Simple Trick That Improves LLM Accuracy — when a cheap trick genuinely works, and the narrow conditions where it stops working.
By topic
Agents & harness engineering — 116 posts
The main thread. Agent loops, tool dispatch, spec-first workflows, evaluation, and the scaffolding that decides whether an agent survives contact with production.
- DeepSeek Harness: What If the Agent Loop Itself Were Just Another Plugin?
- jeo-code: The Harness Engine That Makes You a 10× AI Builder — includes video
- One Memory Setup, Every Harness: Omnigent’s Hindsight Bridge
- Agentic Engineering: 9 Skills
RAG & retrieval — 25 posts
Retrieval that survives real corpora: reranking, hybrid search, graph memory, and the failure modes that only appear at scale.
- Cognee: Building Persistent Memory for Multi-Agent Systems
- From RAG to Context Layer: Ontology, LLM Wiki, HyGRAG
- STORM Parse vs Google Gemini File Search
- RAG or Fine-Tuning? Fine-tuning embedding models for retrieval
Models & papers — 62 posts
Architectures read closely enough to explain, not just cite.
- Diffusion Models, Visually: How Noise Becomes an Image
- Building LLaMA 4 from Scratch: Mixture-of-Experts
- LLM Inference Patterns
- LLM Course — Let’s build a simple LLM
Infrastructure & production systems — 11 posts
What it takes to run this material rather than demo it.
- The Full MLOps Blueprint: Monitoring and Observability
- The Production Generative AI Stack
- Signal-Decision Architecture: Semantic Routing at Scale
Multimodal & vision — 10 posts
Coming from game AI, this is where I started: systems that read a screen and act on what they see.
- 3D Gaussian Splatting vs NeRFs: what is the difference?
- 3D Language Gaussian Splatting (LangSplat) — includes video
- The giant leaps of open-source vision models
Developer tooling — 8 posts
- Unity CLI: From Editor Installs to Verifiable Game-Production Work
- Unity CLI Atomic Agent
- Antigravity CLI Migration: a production-minded checklist
By format
Different posts do different work. If you prefer one mode over another:
| Format | What it looks like | Examples |
|---|---|---|
| Runnable code | Companion .py files you can download and execute; every assertion in the post was produced by running them | Ouroboros gates · Durable execution · Supertonic ONNX |
| Video | Embedded walkthroughs and demos — 21 posts carry video | jeo-code harness · Gemini 3 multi-agent · SIMA 2 in 3D worlds |
| Diagrams | Mermaid architecture and flow diagrams — 223 posts | Production GenAI stack · Signal-decision architecture |
| Deep dives | 2,500+ words, single subject, primary sources only | Fable 5 · MLOps blueprint |
| Async & performance | Measurement-led, with numbers | Why async code can be slower — includes video |
How this blog works
A few conventions worth knowing before you read:
- Primary sources over summaries. When a post analyses a repository, I read the source, not only the README — and say so when the two disagree.
- Code is executed, not illustrated. Where a post claims code runs, the output shown is real output. Companion files are downloadable so you can check.
- Findings are dated. Star counts, version numbers, and benchmarks are recorded on the date noted. They will drift; the post says when it was true.
- Mistakes get published too. Several posts document where my own first calculation was wrong. That is the useful part.
Publishing cadence
Active since 2024, with 294 posts published. Recent months: 7 posts in August 2026, 2 in July, 7 in June, 12 in April, 21 in March, 43 in February. Cadence varies with a full-time engineering job and a PhD — bursts when a topic opens up, quieter when a project is consuming the week.
Who writes this
Jang Young Jeong — AI Product Engineer at Supercent, Ph.D. candidate in Game Engineering at Hongik University, 8 years of shipped AI at NCSOFT and Com2uS. Full background on About; reach me via Contact.