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

Google Developers BlogLabs

Accelerating Spatio-Temporal Attention for Video Diffusion on TPUs

10.22

To address the quadratic latency bottleneck of self-attention in high-resolution video diffusion models, developers implemented Sparse VideoGen (SVG) to dynamically route attention heads to highly…

Chips & compute Research

Read at Google Developers Blog ↗

One letter a week, starting soon.

Latest

Accelerating Spatio-Temporal Attention for Video Diffusion on TPUs

Related

SiliconChip Scaling Moves Beyond The Transistor SemiEngineering

SiliconStacked-Die Multi-Chip Architectures: The Tradeoff Between Scaling And Power Delivery SemiEngineering

SiliconNVIDIA Cosmos Opens New Tools to Train, Evaluate and Deploy World Models NVIDIA Blog

ValleyNvidia debuts new AI reference architectures, development tools SiliconANGLE

SiliconWhy Chip Design AI Benchmarks Must Go Beyond Functional Correctness EE Times

SiliconHPE says it will run the first supercomputer benchmarks on the Moon Tom's Hardware