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

TechPowerUpSilicon

AMD Shows Off Ray Tracing Tech That Slashes GPU Memory Use By 47x

September 22

AMD has detailed a new ray tracing technique called tetrahedral cages, and according to a blog post on the company's GPUOpen developer site , it can cut BVH memory use by roughly 47x while speeding…

Chips & compute

Read at TechPowerUp ↗

One letter a week, in your inbox.

Latest

AMD Shows Off Ray Tracing Tech That Slashes GPU Memory Use By 47x

Related

SiliconEnabling Private High-Performance Production AI Inference with NVIDIA Confidential Computing NVIDIA Technical Blog

SiliconTopology-Aware Workload Scheduling with NVIDIA Topograph NVIDIA Technical Blog

AsiaChina’s Hygon moves beyond data centres with embedded processors for robotics, edge AI SCMP Tech

SiliconWhat’s New for Game Developers: DLSS 5 with 3D-Guided Neural Rendering, NVIDIA ACE Updates, and New RTX Kit Capabilities NVIDIA Technical Blog

ValleyEveryone can find a reason to dislike data center construction TechCrunch AI

SiliconGUC Announces 2nm 16 Gbps HBM4E IP EE Times