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

JetBrains BlogTools

Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents

October 8

Trained with reinforcement learning in real environments, Mellum2.1 is built for coding agents and fast sub-agents that run on your own hardware.

Agents & vibe coding

Read at JetBrains Blog ↗

One letter a week, in your inbox.

Latest

Mellum2.1 Gets to Work: A Fast Open Model for Coding Agents

Related

ToolsIntroducing Warm Agents, a TeamCity Plugin JetBrains Blog

LabsWelcome to Gemini at Work 2026: Introducing the Gemini agent Google Cloud AI

GitHubPresentation: Multi-Agent Patterns from Spotify’s AI Powered Advertising Platform InfoQ AI

GitHubBuilding scalable, agent-friendly APIs for AI applications The New Stack

AsiaIndian AI lab Soket launches open-source agent tool Tech in Asia

ValleyBuilding a safer path to autonomous industrial AI MIT Technology Review