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

PandailyAsia

Xiaomi Details HySparse2 for MiMo-V3: Two-Level KV Sharing Cuts 1M-Token Prefill FLOPs About 5× vs Hybrid SWA

September 24

Xiaomi's LLM-Core researchers released HySparse2, described as hybrid sparse attention with two-level KV sharing, in an arXiv paper (2609.26368) dated around September 2026 and framed as architecture…

Research

Read at Pandaily ↗

One letter a week, in your inbox.

Latest

Xiaomi Details HySparse2 for MiMo-V3: Two-Level KV Sharing Cuts 1M-Token Prefill FLOPs About 5× vs Hybrid SWA

Related

AsiaHuawei Unveils Peerium Architecture: Nested BSP for Million-Processor Scale Pandaily

SiliconIntroducing NV-Reason-CT Open 3D CT VLM for Radiologist Chain-of-Thought Reasoning NVIDIA Technical Blog

SiliconHow SWE-Serve Exposes the Gap Between Local Tests and Live Serving NVIDIA Technical Blog

ResearchWhy I'm scared of RL AI Alignment Forum

AsiaDeepSeek details DSec sandbox infrastructure for agent training TechNode

ResearchWorkspaceBench: Evaluating Interpretability Methods for the Global Workspace AI Alignment Forum