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

Ahead of AIVoices

Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention

05.16

After a short family break, I am excited to be back and catching up on a busy few weeks of open-weight LLM releases.

Research

Read at Ahead of AI ↗

One letter a week, starting soon.

Latest

Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention

Related

VoicesMy Workflow for Understanding LLM Architectures Ahead of AI

VoicesA Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026 Ahead of AI

VoicesCategories of Inference-Time Scaling for Improved LLM Reasoning Ahead of AI

VoicesLLM Research Papers: The 2025 List (July to December) Ahead of AI

VoicesFrom DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates Ahead of AI

VoicesUnderstanding the 4 Main Approaches to LLM Evaluation (From Scratch) Ahead of AI