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

NVIDIA Technical BlogSilicon

How SWE-Serve Exposes the Gap Between Local Tests and Live Serving

September 23

An AI coding agent’s patch can pass tests yet fail when the server loads a real model and handles requests. Evaluating changes to inference-serving software...

Agents & vibe coding Research Agentic AI / Generative AI Data Science Developer Tools & Techniques AI Agent

Read at NVIDIA Technical Blog ↗

One letter a week, in your inbox.

Latest

How SWE-Serve Exposes the Gap Between Local Tests and Live Serving

Related

SiliconHow to Evaluate AI Agents From Tool Calls to Task Completion NVIDIA Technical Blog

SiliconBenchmarking LLM Inference at Scale with AIPerf NVIDIA Technical Blog

SiliconTensorRT Edge-LLM Completes the MLPerf Edge Agentic Benchmark 6.4x Faster on Jetson AGX Thor NVIDIA Technical Blog

AsiaDeepSeek details DSec sandbox infrastructure for agent training TechNode

LabsEvaluate skill-equipped agents with Strands Evals and Amazon Bedrock AgentCore AWS Machine Learning

SiliconWhy Read a Research Paper When You Can Turn It Into an AI Agent? IEEE Spectrum AI