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

vLLM BlogTools

Scaling Kimi K3 on AMD Instinct MI355X: Matching NVIDIA HGX B300 Throughput per GPU on AgentX

10.16

Inside the Kimi K3 optimization effort: understanding the bottlenecks and the decisions that made inference faster

Agents & vibe coding Chips & compute Research models performance rocm amd

Read at vLLM Blog ↗

One letter a week, starting soon.

Latest

Scaling Kimi K3 on AMD Instinct MI355X: Matching NVIDIA HGX B300 Throughput per GPU on AgentX

Related

SiliconArm at the OCP Global Summit 2026: How Arm AGI CPU is scaling agentic AI infrastructure from CPU to rack Arm Newsroom

SiliconNVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning NVIDIA Technical Blog

ToolsCline Agents Harness Unlocks Benchmark-Leading Performance from NVIDIA Nemotron 3.5 Super VL Cline Blog

ResearchScaling AI-driven chip design with open agent factories IBM Research

Voices#490 – State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI Lex Fridman Podcast

ToolsImprove TTFT for Multi-Turn Agentic Workloads with Bi-Directional KV Transfer in vLLM vLLM Blog