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

Apple Machine Learning ResearchResearch

Plan or Retrieve First? A Scale Study of Tool Discovery Architectures

10.15

Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into a single prompt.

Research

Read at Apple Machine Learning Research ↗

One letter a week, starting soon.

Latest

Plan or Retrieve First? A Scale Study of Tool Discovery Architectures

Related

LabsGemini 4 Argon for Robotics Google DeepMind

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

GitHubScaling Git for the agentic software factory GitLab Blog

ResearchCan we change an AI model’s architecture without retraining it from scratch? Amazon Science

SiliconLearning to Play Like a Pro: Adaptive Motion Planning and Tracking for Humanoid Robots IEEE Spectrum AI

ToolsEndpoint Candidates: evaluate and promote inference endpoints Modal