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

b11372

October 3

qwen4exp : halve the indexer score memory ( #29825 ) qwen4exp : halve the indexer score memory The indexer scored all heads in one product and rectified a copy of it, so two [n_pool, n_idx_h…

Models & releases

Read at llama.cpp releases ↗

One letter a week, in your inbox.

Latest

b11372

Related

GitHubAnthropic’s answer to Dots and Muse is already inside Claude The New Stack

Claude Code's new Mods system lets developers rewrite the AI coding tool from the inside The Decoder

JapanClaude Opus 5.5 の動画作例13本を、元のプロンプトと一緒に読み解く Zenn (AI)

AsiaAmazon to invest $1b in US data center communities Tech in Asia

ValleyAmazon’s $1B plan to combat data center backlash draws more backlash Ars Technica AI

ValleyReport: Amazon to offload $8B worth of AI chips, lease them back SiliconANGLE