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's highest performance on Apple Silicon yet with MLX

06.11

Ollama's MLX engine has been updated to deliver its highest performance on Apple Silicon yet. Models output higher quality responses, respond faster, and use less memory.

Open weights Chips & compute

Read at Ollama Blog ↗

One letter a week, starting soon.

Latest

Ollama's highest performance on Apple Silicon yet with MLX

Related

LanguagesModular: Day Zero: MiniMax M3 Open Weights on Modular Cloud Mojo Blog

GitHubUnlocking TPU performance: Deep kernel profiling with XProf Google Open Source Blog

VoicesFrom open source hits to OpenAI (Interview) Changelog

ToolsRun (your largest) local models from your iPhone LM Studio Blog

GitHubJourney to JPEG XL: How open source experiments shaped the future of image coding Google Open Source Blog

ResearchHow flat is replacing fat in AWS data center networks Amazon Science