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

Sakana AIJapan

Training 1000-layer networks without backpropagation

September 13

Introducing PC-ALM, a local-learning alternative to backpropagation. Our method trains 1000-layer neural nets using only local dynamics, and without backprop.

media

Read at Sakana AI ↗

One letter a week, in your inbox.

Latest

Training 1000-layer networks without backpropagation

More from Sakana AI on Accept All

Japan英国王立協会特集号に見る、世界モデルの最前線とAIの未来 Sakana AI

JapanIntroducing Fugu Max and Fugu Ultra v2: Orchestrating the Pareto Frontier Sakana AI

JapanDeveloping a model to detect harmful content from OpenChat titles and descriptions LINE Engineering

JapanメルカリにおけるTiDB改善の取り組み：インデックス非互換への対応 Mercari Engineering

JapanメルカリにおけるTiDB改善の取り組み：リソース制御・リージョンサイズ・プランキャッシュ編 Mercari Engineering

JapanメルカリにおけるTiDB改善の取り組み：IN句内100万件クエリへの対応 Mercari Engineering