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

Cohere BlogLabs

Cohere's North Mini Code Megakernel Serving Engine

October 13

Cohere presents the first production-ready LLM serving system built around a decode megakernel, achieving 1.58× speedup over vLLM.

Read at Cohere Blog ↗

One letter a week, starting soon.

Latest

Cohere's North Mini Code Megakernel Serving Engine

More from Cohere Blog on Accept All

LabsNorth 2: Enterprise AI Without Compromises Cohere Blog

LabsEmbed 5: Frontier Embedding Models for Enterprise Cohere Blog

LabsIntroducing North Small Translate Cohere Blog

LabsShared vs. Dedicated AI Inference: Embed & Rerank Cohere Blog

LabsNorth Mini Code: Agentic Coding for Developers Cohere Blog

LabsIntroducing Command A+ Cohere Blog