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

Tech in AsiaAsia

Cute AI agents need clear boundaries

10.19

Agentic AI’s promise to make life easier now comes in cute packages. But will that make us too trusting of what we let agents do on our behalf?

Agents & vibe coding

Read at Tech in Asia ↗

One letter a week, starting soon.

Latest

Cute AI agents need clear boundaries

Related

JapanClaude Codeでプロンプトインジェクションに備える Zenn (AI)

JapanClaude Codeのsecurity-guidanceは脆弱コードを止めるか 18回実行して測った Zenn (AI)

JapanClaude Codeに時刻と使用量を表示する――Codexとの並行作業を見失わないために Zenn (AI)

JapanClaude Codeのステップごとのレビューを既定から外した理由 Zenn (AI)

SiliconThermal Side Channels Create New Security Risks For Autonomous Vehicles (Missouri S&T) SemiEngineering

GitHubHybrid Reasoning Agents: LLM agents that think in latent space, act through text Hacker News (front)