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

vLLM BlogTools

PD Serving of Qwen3.8-2.4T

09.21

How vLLM reaches 5K throughput and 180 interactivity on Qwen3.8-2.4T with GB300 NVL72 PD serving and how to reproduce results yourself.

Models & releases performance qwen3.8 disaggregation

Read at vLLM Blog ↗

One letter a week, starting soon.

Latest

PD Serving of Qwen3.8-2.4T

Related

VoicesVisions of AI: GPT-3 Moment for Physical AI AI Supremacy

ToolsSplash Engine - the fastest local Qwen3.8 on Apple Silicon LM Studio Blog

EuropeMistral and Mozilla are bringing open, private and multilingual AI to your web browser Mistral AI

VoicesA Guide to Grok Bot 2026 AI Supremacy

LabsIntroducing Gemini 3.8 Live and 3.8 Live Extended Thinking Google DeepMind

LabsIntroducing Gemini 3.8 Live and 3.8 Live Extended Thinking Gemini (Google Keyword)