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

The Decoder

Microsoft AI releases new transcription and text-to-speech models for voice agents

October 2

Microsoft AI has released MAI-Transcribe-2-Streaming, a new model for real-time transcription.

Agents & vibe coding

Read at The Decoder ↗

One letter a week, in your inbox.

Latest

Microsoft AI releases new transcription and text-to-speech models for voice agents

Related

Security startup finds more than 13,000 internal company screenshots that AI agents uploaded publicly The Decoder

JapanCodexのUI修正ループにTrailblazeを入れる理由 ― スクショ確認は残して、画面操作を再利用する Zenn (AI)

GitHubDocker Sandbox Kit Spec: Packaging AI Agent Permissions as OCI Images InfoQ AI

GitHubDigitalOcean Managed Agents Brings Managed Cloud Infrastructure to AI Agents InfoQ AI

LabsAutoSynthData: Generating Training Data for Enterprise Agents Hugging Face Blog

ToolsHow Rogo ships agent-written code to production in 5 minutes on Vercel Vercel Blog