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

Together AITools

A/B test models in production

August 17

Shadow traffic proves a candidate is operationally sound. It can't tell you if users like it better. Run the split at the endpoint instead of in your app code.

Read at Together AI ↗

One letter a week, in your inbox.

Latest

A/B test models in production

More from Together AI on Accept All

ToolsDeepSeek V4 Pro 0813 vs Claude Fable 5 on DeepSWE: Cost, Coding, and Routing Together AI

ToolsKimi K3: the complete developer guide Together AI

ToolsTogether AI announces strategic partnership with Moonshot AI to natively serve Kimi models Together AI

ToolsThunderAgent: 2x Faster Agentic Inference for Synthetic Data Generation at Scale Together AI

ToolsThe production platform for open-weight AI inference Together AI

ToolsTogether AI and Y Combinator partner to launch the first dedicated GPU cluster for the YC community Together AI