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

b11788

10.21

sycl : fix fa crash for Query head dimension mismatch (neq0 != HSK / D=2048/4096) ( #30286 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/58155998…

Models & releases

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11788

Related

Japan「判断」は自分、「作業」は AI。cmux × Claude Code で実装を並列化しつつ「理解を手放さない」開発フロー Zenn (AI)

AsiaDeepSeek Wants Better AI at Lower Cost TechNode

Silicon(PR) Synaptics Announces Astra SR200 Multimodal Edge AI Processors with Google Coral NPU TechPowerUp

Claude Science tackles deadly scorpion stings by designing protein binders from scratch The Decoder

AsiaDeepSeek open-sources inference framework with support for Nvidia and Huawei chips TechNode

AsiaXiaomi retires MiMo-V2.5 models as API service shifts to multimodal replacements TechNode