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

Product HuntGitHub

Agent Identity

September 28Work

Give every AI agent real identities, inboxes, and a phone Discussion | Link

Agents & vibe coding

Read at Product Hunt ↗

One letter a week, in your inbox.

Latest

Agent Identity

Related

ValleyNvidia says new tool can contain rogue AI agents in "milliseconds" Axios Technology

VoicesHere’s Everything OpenAI’s Bots (And Others) Have Hacked Or Considered Hacking Big Technology

GitHubHow we found 24 Android vulnerabilities using our open source AI security agent GitHub Blog

GitHubClaude Sonnet 5.5 in GitHub Copilot GitHub Changelog

ResearchGecko Robotics works with NVIDIA to add AI agent security and control The Robot Report

GitHubOpenAI blocked its agent’s web access. Then it tunneled out through DNS. The New Stack