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

Watermarking in vLLM

09.24

How vLLM implements distribution-preserving Gumbel-max text watermarking with efficient GPU kernels, statistical detection, speculative decoding, and repeated-context safeguards.

Open weights Regulation & safety watermarking sampling speculative-decoding performance

Read at vLLM Blog ↗

One letter a week, starting soon.

Latest

Watermarking in vLLM

Related

ToolsReducing vLLM startup time with one uv flag vLLM Blog

ToolsAnnouncing vllm-metal: Concurrent Serving on Apple Silicon vLLM Blog

VoicesHow a single tweet transformed the AI safety debate Understanding AI

GitHubReconnecting with the heart of open source: Highlights from our 2026 GSoC India tour Google Open Source Blog

VoicesLast Week in AI #344 - Navier–Stokes, Pacing the Frontier, AI Misuse Last Week in AI

ResearchRethinking Robot Safety in the Age of AI IEEE Spectrum Robotics