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

Clearing chat history helps AI agents find better solutions

October 12

Microsoft researchers found that autonomous AI agents get trapped in what they call "idea basins" because of their growing chat context, local solution regions they can't escape.

Agents & vibe coding

Read at The Decoder ↗

One letter a week, starting soon.

Latest

Clearing chat history helps AI agents find better solutions

Related

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

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

ValleyPhasis develops platform for agentic orientation using World APIs and reality layers SiliconANGLE

JapanClaude Code で AI社員18人の会社を運営する：フォルダ構成と決まり Zenn (AI)

JapanCodex と Claude Code を同じフォルダで使う入口（AGENTS.md と CLAUDE.md） Zenn (AI)

JapanClaude CodeとCodexを同じリポジトリで並列に動かす: git worktreeの落とし穴と相互レビュー Zenn (AI)