Start Here

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:

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.

All agent posts

RAG & retrieval — 25 posts

Retrieval that survives real corpora: reranking, hybrid search, graph memory, and the failure modes that only appear at scale.

All RAG posts

Models & papers — 62 posts

Architectures read closely enough to explain, not just cite.

All model & paper posts

Infrastructure & production systems — 11 posts

What it takes to run this material rather than demo it.

All infrastructure posts

Multimodal & vision — 10 posts

Coming from game AI, this is where I started: systems that read a screen and act on what they see.

All multimodal posts

Developer tooling — 8 posts

All tooling posts

By format

Different posts do different work. If you prefer one mode over another:

FormatWhat it looks likeExamples
Runnable codeCompanion .py files you can download and execute; every assertion in the post was produced by running themOuroboros gates · Durable execution · Supertonic ONNX
VideoEmbedded walkthroughs and demos — 21 posts carry videojeo-code harness · Gemini 3 multi-agent · SIMA 2 in 3D worlds
DiagramsMermaid architecture and flow diagrams — 223 postsProduction GenAI stack · Signal-decision architecture
Deep dives2,500+ words, single subject, primary sources onlyFable 5 · MLOps blueprint
Async & performanceMeasurement-led, with numbersWhy 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.