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

OpenAI NewsLabs

Better prompt caching for GPT-6

September 22

Learn how GPT-6 improves prompt caching with higher cache hit rates, new diagnostics, explicit breakpoints, and controls that reduce latency and costs.

Models & releases

Read at OpenAI News ↗

One letter a week, in your inbox.

Latest

Better prompt caching for GPT-6

Related

LabsIntroducing GPT-6 Sol and Luna OpenAI News

LabsHiggsfield AI ships new video features in a day with GPT-6 Astra OpenAI News

LabsHex turns complex analysis into visual reports with GPT‑6 Astra OpenAI News

LabsPerplexity trusts GPT-6 Astra with end-to-end systems OpenAI News

LabsCognition helps Devin test its own work with GPT‑6 Astra OpenAI News

GitHubClaude Opus 5.5 wants to finish your coding tasks, not just start them The New Stack