Skip to content

Accept All すべて承認

Latest

On the calendar

予定 · Conferences and launch events, this week's stories from each corner of the industry, and what its press is covering — in English

On view

This week, from that corner the newest stories from the corner of the industry you picked

The wire their own posts, translated

How code moves in 2026 from the industry's own reports

Sources

Fetched every three hours, linked to the original

About

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

Qiita (LLM)Japan

【360回の測定】Gemma 4 E4Bの出力速度が最大2.19倍に。主要GPUカーネルは速くないのに、なぜ？MTPを試す2つの方法

October 8

LLMを速くするために、まずGPUを買い替えようとしているなら、この360回の測定を見てほしい。 24GBのNVIDIA A10Gで、同じGemma 4を動かす。変えるのは、次のトークンを先読みする補助モデルを使うかどうかだ。先読みする候補は 2トークン。比較したのは...

Chips & compute

Read at Qiita (LLM) ↗

Related

JapanGoogle、AI生成物の判定ツールを一般公開 OpenAIやNVIDIA製サービスも対象に ITmedia AI+

JapanNVIDIA「RTX Spark」搭載のノートPC「Surface Laptop Ultra」発売価格は51万3480円から ITmedia AI+

SiliconFrom Silicon To Systems: Redefining Competitive Advantage, Part 3 SemiEngineering

SiliconPerspectives On Test: System Level Test For AI & Data Centers SemiEngineering

AsiaCoreWeave Enters India, Partners AdaniConneX For 240 MW Data Centre Capacity Inc42

JapanClaude Code の自動圧縮は何トークンで起きたか — 実測3回と、それに備えてやっていること Qiita (LLM)

More from Qiita (LLM) on Accept All.