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

Jeeves. Reasoning improves Jev-like decision models

September 29

Article URL: https://github.com/PostHog/jeeves Comments URL: https://news.ycombinator.com/item?id=49891290 Points: 159 # Comments: 69

Research

Read at Hacker News (front) ↗

One letter a week, in your inbox.

Latest

Jeeves. Reasoning improves Jev-like decision models

Related

SiliconChip Industry Technical Paper Roundup: Sept. 29 SemiEngineering

AsiaLimX Dynamics and Kyland Ship First Humanoid on Domestic Electronic Architecture Pandaily

ValleyOkta builds shared architecture for agent runtime security SiliconANGLE

JapanClaude Code、同梱のclaude-apiスキルに新コマンド「build-eval」と「hillclimb」を追加 ——評価の作成からプロンプト・モデル設定の調整まで gihyo.jp

GitHubThink you need a better reranker? Check your retrieval first. The New Stack

ValleyOpenAI halts frontier-model training amid string of agent misalignment incidents Ars Technica AI