The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo

← Accept All Archive

LINE EngineeringJapan

Architecting Semantic Context OS: Beyond token stuffing in agentic systems

06.24

This is the official article for Tech-Verse 2026, LY Corporation's technology conference.As large la...

Agents & vibe coding

Read at LINE Engineering ↗

One letter a week, starting soon.

Latest

Architecting Semantic Context OS: Beyond token stuffing in agentic systems

Related

JapanUniting analytics with AI agents as work and roles shift in the GenAI era LINE Engineering

JapanID-JAG The Hard Way: Learning AI agent authorization through failure LINE Engineering

JapanWhy ID-JAG is the future of AI agent security LINE Engineering

Japan修正PRを食べてレビュースキルが賢くなる：Claude Codeによる自己改善サイクル Mercari Engineering

ToolsClosing the loop: Evaluating and improving Replit Agent at scale Replit Blog

JapanPrompts shift from manual to AI-driven: automated optimization and speedup with genetic algorithms LINE Engineering