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

AWS Machine LearningLabs

Multi-Turn Reinforcement Learning on Amazon SageMaker AI: A hands-on guide

10.23

Most fine-tuning teaches a model to produce a better answer to a single prompt. Agentic tasks are different.

Research

Read at AWS Machine Learning ↗

One letter a week, starting soon.

Latest

Multi-Turn Reinforcement Learning on Amazon SageMaker AI: A hands-on guide

Related

LabsOrchestrating SageMaker AI endpoint auto scaling with AWS CDK AWS Machine Learning

LabsStop guessing auto scaling targets for TTS on Amazon SageMaker AI AWS Machine Learning

LabsBeyond the KV cache: Training and serving i14’s Laplace 3B linear attention model on AWS Trainium2 with native PyTorch AWS Machine Learning

ToolsContext Engineering for AI Agents Starts with Retrieval LangChain

SiliconScaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 2 NVIDIA Technical Blog

SiliconScaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 1 NVIDIA Technical Blog