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

IEEE Spectrum AISilicon

Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy

10.12

If you’ve ever wondered how Claude and similar AI agents can answer complex questions in seconds and where they get the information, you’re not alone.

Agents & vibe coding Ieee-member-news Artificial-intelligence Chatbots Careers

Read at IEEE Spectrum AI ↗

One letter a week, starting soon.

Latest

Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy

Related

SiliconAttempts to Keep Humans in the AI Loop May Actually Push Them Out IEEE Spectrum AI

SiliconHow to Stop AI Agents From Secretly Collaborating IEEE Spectrum AI

SiliconWhy Read a Research Paper When You Can Turn It Into an AI Agent? IEEE Spectrum AI

SiliconWhy Andon Labs Puts AI Agents in Charge of Real Businesses IEEE Spectrum AI

GitHubGitHub Copilot app for Beginners: How to teach Copilot about your codebase GitHub Blog

LabsIntroducing Muse Wonder and Muse Wonder Full: Frontier Models for Agents Meta Newsroom