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

Hacker News (front)GitHub

Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms

September 28

Article URL: https://github.com/firelex/jeff Comments URL: https://news.ycombinator.com/item?id=49883844 Points: 396 # Comments: 152

Models & releases

Read at Hacker News (front) ↗

One letter a week, in your inbox.

Latest

Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms

Related

GitHubSonnet 5.5 Hacker News (front)

JapanAIが書いたコードは「ブラックボックス」でいい？ Claude Code作者が語るプロトタイプと本番の線引き ITmedia AI+

LabsIntroducing Claude Sonnet 5.5 on AWS AWS Machine Learning

ToolsClaude Sonnet 5.5 is now available in Devin Cognition (Devin & Windsurf)

GitHubClaude Sonnet 5.5 in GitHub Copilot GitHub Changelog

Anthropic's Claude Sonnet 5.5 nearly matches Opus 5.5 on benchmarks while costing up to 30 percent less per task The Decoder