hyuntae's blog

Blog

Notes from a backend engineer who hunts down bottlenecks by measuring — not guessing.

AIOriginal: KO사내 RAG 챗봇 성능 개선기 ① — 긴 문서를 어떻게 잘라야 검색이 잘 될까2026-07-04

사내 Slack RAG 봇 '시루AI'의 청킹 전략을 3차에 걸쳐 재설계한 기록. 글자 수 기준이 만든 장애, 배치 크기 파라미터 오진단, 한글 토큰 밀도 실측치까지.

AISince I Started Letting AI Code ④ — Chasing AI, Learning Alongside AI2026-07-01

Paradigms shift on a timescale of days. This closing post opens with a confession — that this blog, and even the post you're reading, was written by AI — then follows how reading books and poetry alongside AI changed the way I learn itself: what it means to chase AI in the age of AI, and grow alongside it.

AISince I Started Letting AI Code ③ — When the AI Server Goes Down, I Turn Into an Idiot Too2026-06-30

A local LLM experiment that started purely to save tokens ended up colliding with the question of AI dependence: the context ceiling of a 12GB GPU, a 60-second first response, the KV-cache-vs-load-balancing tradeoff, the 12B-vs-26B tradeoff, and even the fear of what happens if Claude goes down — a record of the experiment to cut dependence, and where it hit its limits.

AISince I Started Letting AI Code ② — The System AI 'Works' In: Engineering and Verification Ownership2026-06-29

Using AI and having a system that actually 'works with' it are two different things — a record of building memory, verification, and isolation into my workflow, then confronting the paradox of a productivity explosion.

AISince I Started Letting AI Code ① — Trying Every Tool Until I Built My Own2026-06-28

A record of what I learned trying out AI coding tools since February 2026: token burn with using-superpower, clarification and over-engineering with gstack, guesswork-driven questions from speckit's clarify — and the workflow I've settled into now, running speckit with a self-built prefill skill on top.

BackendWhen Map Requests Piled Up, the Connection Pool Dried Out — From lat/lng B-tree to MySQL SPATIAL Index2026-06-25

A map viewport query backed by a lat/lng B-tree drained our connection pool. Here's how MySQL POINT + SPATIAL index fixed it — including the /*!80003 SRID 0 */ trap, SRID 0 vs 4326 axis order, map-API coordinate conventions, and the lesson of 'show it with numbers.'

BackendBuilding a Search Engine for 5.4 Million Real Estate Records: From OpenSearch Adoption to Performance Optimization2026-04-06

To overcome the limitations of DB + public API-based search, we adopted OpenSearch and optimized queries through benchmark-driven development. The theoretical bottleneck and the actual bottleneck were different.