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

Ollama BlogTools

Ollama is now powered by MLX on Apple Silicon in preview

03.30

Today, we're previewing the fastest way to run Ollama on Apple silicon, powered by MLX, Apple's machine learning framework.

Open weights Chips & compute

Read at Ollama Blog ↗

One letter a week, starting soon.

Latest

Ollama is now powered by MLX on Apple Silicon in preview

Related

Voices#494 – Jensen Huang: NVIDIA – The $4 Trillion Company & the AI Revolution Lex Fridman Podcast

ToolsRun open models on NVIDIA DGX Station GB300 LM Studio Blog

SiliconNvidia's Groq Plot Thickens The Chip Letter

VoicesA Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026 Ahead of AI

VoicesVouch for an open source web of trust (News) Changelog

Voices#490 – State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI Lex Fridman Podcast