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.
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 claimed the Terminal-Bench 2.0 crown at 82.7%. And in Jakarta, where I’ve been shipping software since before npm existed, nobody in my …
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.
