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

b11700

October 16

model : Granite Switch Decision ( #30676 ) feat(convert): Add decision.chat to support decision models that can also chat Branch: GraniteSwitchDecision AI-usage: full (Claude + Sonnet 5.5)…

Models & releases

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11700

Related

GitHubLlama.cpp on a jailbroken PS5: run any GGUF model natively on the console Hacker News (front)

GitHubDesigning more efficient quantum circuits with Claude Hacker News (front)

Google's Gemini 4 Argon is closer to the AI frontier than any Google model in months The Decoder

GitHubShow HN: Gemini 4 Argon plays StarCraft Hacker News (front)

GitHubMuse Wonder vs. Claude Fable 5.1: Meta’s new model came closer than I expected The New Stack

GitHubAWS Introduces Strands Decider 2B and Strands Box for AI Agent Development InfoQ AI