IT, AI, and dev tooling insights from a Korean senior dev working in Southeast Asia.
One post per day. Mon = news · Tue = code · Wed = Indonesia · Thu = tools · Fri = debate · Sat = build · Sun = free.
A coding agent with a very large context window can still make the wrong change in the wrong file. That sounds harsh until you watch the failure happen. The agent reads half the repository, quotes three irrelevant modules back at you, edits the visible function, and misses the …
A beta dependency feels safe right up to the moment it becomes load-bearing. The release note looks small: one adapter added, one selection …
A developer asks an AI agent to build a settings modal. Thirty seconds later, there is a modal on screen. It opens when you click a button. …
Your cron job exited zero. Fine. Where is the artifact? That is the question I want on every scheduled job review now. Not “did the …
GLM-5.2's MIT-licensed open weights at one-sixth the cost of GPT-5.5 isn't a benchmark story — it's a cost-structure story. Here's what it means for your architecture decisions this week.
You set up a cron job — let’s say a database backup. It runs every night at 2 AM. The exit code is always 0. The dashboard is green. …
I deleted 150 lines of JavaScript from a tooltip component last week. The replacement was four lines of CSS. No virtual DOM reconciliation, …
My health check cron ran 180 times over six hours. Exit code 0 every time. Green dashboard. And you never once asked. Neither did I — until …
I Swapped My LLM Backend — The API Call Worked on the First Try The migration took eleven minutes. The fallout took three weeks. I switched …
I ran an autonomous task system for three months before I realized it had a blind spot the size of a barn door. Processes were …
Last month, Claude Opus 4.7 hit 1567 Elo on WebDev Arena — the highest any model has ever scored on that benchmark. The same week, GPT-5.5 …
Every AI agent framework comparison chart tells the same story: LangGraph gets five stars for state management, CrewAI wins on developer …
Vue 3.6 Vapor Mode compiles SFC templates directly to DOM operations, hitting Solid.js-speed renders without rewriting your codebase. …
What actually breaks when you run AI agents on cron 24/7 — zombie tasks, subagent black holes, and the architectural patterns that make autonomous pipelines reliable.
Anthropic found that even frontier models fail 4 specific ways when you let them work longer than 5 minutes. I hit all of them before I …
OpenCode hit 160K GitHub stars and dethroned Cursor as the #1 AI dev tool. Claude Fable 5 launched with record benchmarks — then got suspended 3 days later. Here's what actually matters for your workflow.
Z.AI's GLM 5.2 (744B MoE, 1M context, MIT license) tops open-weights benchmarks and runs coding agents at frontier level. Full breakdown.
I told my AI agent my blog looked like garbage. It loaded 54 real-world design systems, ran a comparative analysis, and rebuilt the entire theme with Linear.app's design tokens. Swapped between three AI models mid-task and learned which one handles structure vs. polish. 1,500 lines of CSS, 3 commits, one afternoon.
Three acquisitions in twelve months. Korean dev tools are no longer a fragmented market — they're a small oligopoly, and the API surfaces are starting to look the same.
Modern JavaScript runtimes have had structured state primitives for years. You probably don't need a 40KB dependency for what your app actually does.
Five years of quiet, distributed, community-driven tooling work. The results are starting to show up in the kinds of projects that get adopted outside the country.
It's a personal AI agent. It's not a product for end-users. With that frame, it works better than anything else I've tried. Here's what works, what doesn't, and when I'd reach for something else.
Two years of watching the field from Jakarta. The replacement threat was always a junior-developer story. The senior-developer story is the opposite of what most people are writing about.
Type at least 2 characters to search.
