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

Sakana AI's self-improving model gets better at solving and judging, but can't catch its own blind spots

October 12

Sakana AI's MASS method lets one language model improve itself by solving tasks, judging results, and refining workflows, reaching a win rate of nearly 70 percent against the base model after two…

Japan-inspired

Read at The Decoder ↗

One letter a week, starting soon.

Latest

Sakana AI's self-improving model gets better at solving and judging, but can't catch its own blind spots

Related

AsiaJapan’s Sumitomo Bakelite expands China chip packaging materials output amid AI boom SCMP Tech

SiliconSoftBank seeks $100 billion for AI-refined projects from Middle Eastern investors Tom's Hardware AI

SiliconArm & SoftBank: Part 1- Masa comes calling, bearing gifts The Chip Letter

ToolsMarketing ops as code: Automating events from planning to follow-up on GitHub GitHub Copilot Blog

Clearing chat history helps AI agents find better solutions The Decoder

Microsoft plans to scale its own Maia AI chips to gigawatt levels by 2027 The Decoder