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

Use decision models with Amazon Bedrock AgentCore Evaluations

11.04

Some of the questions you ask when evaluating an agent are narrow and repeatable. Did this response stay on policy? Is this tool call safe to approve? Does this answer match the retrieved context?

Agents & vibe coding Research Funding & deals

Read at AWS Machine Learning ↗

One letter a week, starting soon.

Latest

Use decision models with Amazon Bedrock AgentCore Evaluations

Related

ResearchFrom synthetic enterprise data evaluations to real Microsoft Copilot AI confidence Microsoft Research

VoicesNew paper: Emerging trends in AI agent evaluation AI Snake Oil

LabsFour evaluation engineering lessons learned from building agent plugins Google Cloud AI

LabsBuild efficient agents with knowledge distillation on Amazon SageMaker AI AWS Machine Learning

OpenAI acquires Pierre Computer Company to make Git keep up with AI coding agents The Decoder

ValleySentra raises $150M to control what AI agents can reach in corporate data SiliconANGLE