Insights and hands-on guides on frontend, backend, databases, IT infrastructure, and AI solutions.
Running an LLM on CPU Only - Real Numbers from an Old Xeon with 256GB RAM
Our Servers Catch Burglars Every Day - TREEWALL Field Test Report
NVMe Storage Benchmark: Optane to HDD - 20 Devices Compared with fio
Local AI Video Generation with ComfyUI + Wan 2.2 - An RTX PRO 6000 96GB Build Log
Structuring Unstructured Documents with an LLM - Measured Accuracy on a 19-Item Menu
A local 14B model turns menu documents into database records: 100% on prices, 94.7% on names. The dangerous errors aren't the obviously wrong values — they're the plausibly wrong ones.
AI generates English-learning content fast, but shipping it raw breaks quality. Lessons from auditing 990 SCENEs.
Picking a Korean embedding model on speed alone hides a real cost. BGE-M3 vs mE5-Large on the same Recall test.
Comparing 6 local LLMs across e-commerce, legal, and business automation scenarios — revealing dangerous hallucination patterns in legal AI.
6 local LLMs tested on 30 real-world business questions across manufacturing, SaaS, and healthcare — which model handles domain-specific tasks best?
Comparing 6 local LLMs on Korean fluency — honorifics, business tone, language contamination (Chinese/English mixing), and natural expression across 10 practical questions.
Guarding the Front Door of Your Network - TREEWALL, an AI Security Gateway
Build a CCTV Recording Server Without an NVR - RTSP + ffmpeg + systemd, 180-Day Retention
Our MoE Model Started Spewing Garbage - What Auditing All 18,432 Expert Weights Revealed
What We Learned Building and Auditing 990 AI-Generated English Learning Scenes
BGE-M3 vs mE5-Large - Comparing Korean RAG Search Quality Head to Head
