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

Self-Compacting Language Model Agents

10.12

Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window.

Agents & vibe coding

Read at Apple Machine Learning Research ↗

One letter a week, starting soon.

Latest

Self-Compacting Language Model Agents

Related

ToolsImprove TTFT for Multi-Turn Agentic Workloads with Bi-Directional KV Transfer in vLLM vLLM Blog

VoicesWe must recall open-ended AI agents with internet access from the market, now Gary Marcus

ToolsHow to build great out-of-the-box user experiences with Managed Deep Agents LangChain

SiliconInto the Omniverse: How Developers Turn Ideas Into Simulations With Frontier AI Agents NVIDIA Blog

ToolsHow Snyk Turned an Internal Support Agent into a Customer Feature LangChain

LabsAi2 at COLM 2026: Open research, from models to agents for science Ai2