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

b11767

10.21

mtmd : read LFM2 tiling params from GGUF metadata ( #30840 ) mtmd : read LFM2 tiling params from GGUF metadata Write min_tiles, max_tiles, tile_size and max_pixels_tolerance from…

Open weights

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11767

Related

ValleyDeepSeek open-sources DeepInfer, the inference framework behind its production services SiliconANGLE

ValleyHugging Face CEO warns that Netflix’s OpenAI hack documentary isn’t accurate TechCrunch AI

Deepseek open-sources the inference engine that powers its fastest and cheapest AI model The Decoder

GitHubGoogle open-sources TorchTPU, a native PyTorch back end for TPUs Hacker News (front)

ToolsPyTorch Foundation Welcomes Nine New Members As Momentum Builds Around Open Source AI Center of Gravity PyTorch Blog

GitHubDeepSeek open-sources the inference engine behind its API. And Huawei gets equal billing with Nvidia. The New Stack