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

The Decoder

AI agent teams waste massive tokens for barely measurable quality gains, research finds

October 11

Teams of AI agents barely outperform solo agents but cost up to 5.1x more, according to Vals AI. Only one out of four tests with GPT-6 Sol and Claude Opus 5.5 showed a measurable gain.

Models & releases Agents & vibe coding

Read at The Decoder ↗

One letter a week, starting soon.

Latest

AI agent teams waste massive tokens for barely measurable quality gains, research finds

Related

AI agents overstate their results and remain far from autonomous research, study finds The Decoder

GitHubClaude Code found my app’s shared contract in two MCP calls. Then the records ran out. The New Stack

JapanGoogle、業務向けGemini Agentを発表 ——調査から資料作成まで任せられ、Claudeも選択可能 gihyo.jp

LabsWelcome to Gemini at Work 2026: Introducing the Gemini agent Google Cloud AI

EuropeIntroducing Mistral Large 4 Mistral AI

SiliconOpenAI and Synopsys partner to build "GPT-Synopsys" for autonomous chip design Tom's Hardware AI