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

The Decoder

Anthropic's Claude now writes code and proves it safe automatically

10.23

Anthropic had Claude generate mathematical proofs that existing code is correct, producing roughly 180 million lines of proof code for 123 open-source libraries.

Models & releases

Read at The Decoder ↗

One letter a week, starting soon.

Latest

Anthropic's Claude now writes code and proves it safe automatically

Related

Google's Agent Compute Engine gives every Gemini agent its own hardware-isolated micro virtual machine The Decoder

Anthropic takes on Grok Bot, Meta's Muse, and OpenAI's Dots with its always-on agent "Claude Duet" The Decoder

SiliconClaude and Grok among AI agents used to automate attacks on Latin American institutions Tom's Hardware

JapanClaude Duet登場、先回りして動くAIの相棒 Zenn (AI)

Japan「読みにくいDB」はAI開発のコストを1.9倍にする――Claude Codeで検証したDB設計の影響 Zenn (AI)

Toolsb11836 llama.cpp releases