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

Apple Machine Learning ResearchResearch

How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?

October 1

Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards.

Agents & vibe coding

Read at Apple Machine Learning Research ↗

One letter a week, in your inbox.

Latest

How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?

Related

ToolsVM Sandboxes: Full computers for agents Modal

ToolsVercel Agent now installs private packages from npm and custom registries Vercel Blog

AsiaMeta and Tencent’s Two Paths to the Personal AI Agent Pandaily

VoicesWhy Dwarkesh is Wrong about Computer Use + How OpenAI shipped its Jev competitor in 1 Week Latent Space

ValleyThe Battle to Be Your Personal AI Agent Is Here Wired AI

ValleyOpenAI’s Jev clone could help the frontier lab stop its swarming agents TechCrunch AI