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

llama.cpp releasesTools

b11713

10.17

CUDA: faster MMVQ for low-bit types ( #30517 ) CUDA: faster MMVQ for low-bit types ggml-cuda: hip: small nwarps GCN fix on Q3_K(ncols=2,3), Q6_K(ncols=4) Co-authored-by: thelittlefireman…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11713

Related

SiliconNvidia reportedly insists the RTX 5090 isn't dead despite severe shortages and removed listings at multiple retailers Tom's Hardware

SiliconNVIDIA Denies RTX 5090 Discontinuation Rumors, Admits Supply Is Tight TechPowerUp

SiliconLeap seconds being retired next year to avoid wreaking havoc on computer systems Tom's Hardware

AsiaAnthropic secures data center capacity in Canada Tech in Asia

SiliconHWiNFO Lists PTL-080, a Smaller Panther Lake Chip for Arc G-Series Handhelds TechPowerUp

SiliconSEMICON West 2026 Displays AI-Era Chipmaking, Workforce Development EE Times