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

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

10.15

Multimodal agents commonly generate freeform reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action…

Models & releases Agents & vibe coding Research

Read at Apple Machine Learning Research ↗

One letter a week, starting soon.

Latest

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

Related

ToolsOpen-sourcing evals for open-weight agents Cline Blog

ToolsOpus 4.7 for 33% less: How Auggie beats Claude Code on cost and quality Augment Code

ToolsFinish RL Training Faster: Bitwise-Consistent, High-Performance, Agent-Driven vLLM Blog

GitHubGemini 4 Argon on GitLab: Built for long-running agentic work GitLab Blog

ToolsDeep Agents Deploy: an open alternative to Claude Managed Agents LangChain

LabsRun fast, private agents on-device with LFM2.5-24B-A2B Hugging Face Blog