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

Hugging Face BlogLabs

Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline

10.16

Native-script data for 22 languages, romanized data for twelve, and a reusable GPU-accelerated pipeline for translation, quality assessment, and repair.

Research

Read at Hugging Face Blog ↗

One letter a week, starting soon.

Latest

Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline

Related

LabsOpen TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning Hugging Face Blog

LabsHow UK AISI and EvalEval Are Making Benchmark Results Reproducible Hugging Face Blog

LabsTransformers now runs llama.cpp quants Hugging Face Blog

Labstokenizers v1: encode, decode and scaling, measured Hugging Face Blog

ResearchLarge-scale iontronic skins with neural-hierarchical processing architecture Nature Machine Intelligence

ToolsScaling Kimi K3 on AMD Instinct MI355X: Matching NVIDIA HGX B300 Throughput per GPU on AgentX vLLM Blog