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

b11678

October 16

Limit max CUDA pinned host buffer size to 4 GB ( #30449 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/56529820 macOS/iOS: macOS Apple Silicon (arm64)…

Models & releases Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11678

Related

SiliconNVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning NVIDIA Technical Blog

SiliconScale Agentic Coding Workflows with Meta’s Muse Spark Open on NVIDIA GB300 NVL72 NVIDIA Technical Blog

Black Forest Labs' open-weights image model FLUX 3 Image Klein runs on consumer GPUs with just 8 GB of VRAM The Decoder

GitHubNvidia squeezed a 74B agent model into 24GB so it can run on your laptop The New Stack

AsiaChina chip exports jump 136% to US$45b as AI frenzy jacks up prices SCMP Tech

GitHubGemini 4 Argon debuts with a unified 1M input/output token limit The New Stack