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

xAI NewsLabs

Workflows in Grok Build

10.13

Grok Build can now write and run workflows: orchestration scripts that fan a task out across hundreds of parallel agents, verify the results, and report back in one background run.

Models & releases MCP, skills & tools

Read at xAI News ↗

One letter a week, starting soon.

Latest

Workflows in Grok Build

Related

VoicesHow Anthropic’s Dynamic Workflows Coordinate Claude Agents (Updated with video!) Latent Space

LabsLet skills in Gemini tackle your most repetitive tasks Gemini (Google Keyword)

VoicesClaude’s new auto eval tool Hamel Husain

EuropeDeepL is now available in Microsoft Copilot, ChatGPT and Claude via MCP DeepL Blog

ToolsHow we rebuilt the Auggie CLI harness to make tasks 53% cheaper than Claude Code Augment Code

ToolsSourcegraph MCP server and a cheaper model beat a Mythos-class model alone Sourcegraph Blog