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

llama.cpp releasesTools

b12069

11.03

opencl: add initial iq4_xs support ( #31339 ) opencl: add iq4_xs AOS mv Assisted-by: Codex opencl: add iq4_xs SOA mv and tiled mm Assisted-by: Codex opencl: add iq4_xs noshuffle gemm/gemv for adreno…

Agents & vibe coding

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b12069

Related

GitHubPresentation: Beyond the Harness: Canvas for AI Agents InfoQ AI

ValleyHow “reverse game theory” could keep AI agents in check MIT Technology Review

Anthropic cracks down on game cloning in Claude Code after wave of AI-built knockoffs The Decoder

VoicesVibe Coded AO3 Clone Site Down After Fanfic Authors Buried It With 2,000 Takedown Notices in a Single Day 404 Media

AsiaTRAI allows AI Agents in telecom customer support; mandates 24×7 availability MediaNama

SiliconCities Worldwide Build and Scale AI Services With NVIDIA Physical and Agentic AI NVIDIA Blog