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

b12121

11.05

llama : fix on-device state copy sizes for quantized KV caches ( #30541 ) llama : fix on-device state copy sizes for quantized KV caches The on-device sequence state copies…

Models & releases Open weights

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b12121

Related

Toolsb12110 llama.cpp releases

AsiaChina Merchants' LionRock AI Lab Open-Sources Lion-ER-35B-A3B Embodied Reasoning Model Pandaily

GitHubRipple-65B Preview: U.S. Open-Weight SOTA on Agentic Coding Hacker News (front)

AsiaDeepSeek engineer defends push for open-source AGI despite higher risks SCMP Tech

AsiaTencent unveils Hy4 as open-weight AI race with DeepSeek, Z.ai, Alibaba heats up SCMP Tech

AsiaDeepSeek, Qwen and MiniMax Leads Debate Open-Source Model Risks on Shared Wuzhen Stage Pandaily