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

Hugging Face BlogLabs

Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox

10.22

A Blog post by Microsoft on Hugging Face

Agents & vibe coding

Read at Hugging Face Blog ↗

One letter a week, starting soon.

Latest

Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox

Related

LabsRun fast, private agents on-device with LFM2.5-24B-A2B Hugging Face Blog

LabsThe Agent Said It Was Done. The Database Disagreed. Hugging Face Blog

LabsAutoSynthData: Generating Training Data for Enterprise Agents Hugging Face Blog

LabsGetting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents Hugging Face Blog

LabsHolo4: powering generalist computer-use agents Hugging Face Blog

Japanrtk 1.0 入門：Claude Code が読むコマンド出力を削る。テスト結果 218 行→16 行でも AI はバグを直せるか Zenn (AI)