Skip to content

Accept All すべて承認

Ahead of AI

20 stories

Ahead of AIVoicesLanguage Models for Text Classification: From Bag-of-Words to Jev The recently released Jev AI model has been quite a cultural phenomenon in technical communities in the past 2 weeks.

Ahead of AIVoicesGPT-6 Astra, Looped Transformers, and Hidden Reasoning A lot has happened in the last few weeks. I am sure that OpenAI’s GPT-6 Astra is top of mind for everyone right now.

Ahead of AIVoicesHow Claude Watermarks AI-Generated Text I recently posted a Substack note about Claude’s new watermarking process and implementation. Since it’s such a popular topic and sparked such a lively discussion, I thought it might be interesting…

Ahead of AIVoicesBuilding an AI Text Detector From Scratch Substack recently launched its AI detector feature in the UI, which is super interesting. Separately, lots of people asked me about interesting local do-it-yourself LLM projects as demos to show what…

Ahead of AIVoicesControlling Reasoning Effort in LLMs It has been almost two years since OpenAI released o1, a model that popularized the idea of LLM-based reasoning models.

Ahead of AIVoicesUsing Local Coding Agents Many people reached out to me in the past asking about my local agent stack as well as how I set up my local agent stack.

Ahead of AIVoicesLLM Research Papers: The 2026 List (January to May) As some of you know, I have the long-running habit of keeping a running list of research papers I want to read, revisit, or cite in future articles and projects.

Ahead of AIVoicesRecent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention After a short family break, I am excited to be back and catching up on a busy few weeks of open-weight LLM releases.

Ahead of AIVoicesMy Workflow for Understanding LLM Architectures Many people asked me over the past months to share my workflow for how I come up with the LLM architecture sketches and drawings in my articles, talks, and the LLM-Gallery .

Ahead of AIVoicesComponents of A Coding Agent In this article, I want to cover the overall design of coding agents and agent harnesses: what they are, how they work, and how the different pieces fit together in practice.

Ahead of AIVoicesA Visual Guide to Attention Variants in Modern LLMs I had originally planned to write about DeepSeek V4. Since it still hasn’t been released, I used the time to work on something that had been on my list for a while, namely, collecting, organizing…

Ahead of AIVoicesA Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026 If you have struggled a bit to keep up with open-weight model releases this month, this article should catch you up on the main themes.

Ahead of AIVoicesCategories of Inference-Time Scaling for Improved LLM Reasoning Inference scaling has become one of the most effective ways to improve answer quality and accuracy in deployed LLMs. The idea is straightforward.

Ahead of AIVoicesThe State Of LLMs 2025: Progress, Problems, and Predictions As 2025 comes to a close, I want to look back at some of the year’s most important developments in large language models, reflect on the limitations and open problems that remain, and share a few…

Ahead of AIVoicesLLM Research Papers: The 2025 List (July to December) In June, I shared a bonus article with my curated and bookmarked research paper lists to the paid subscribers who make this Substack possible.

Ahead of AIVoicesFrom DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates Last updated: January 1st, 2026 Similar to DeepSeek V3, the team released their new flagship model over a major US holiday weekend.

Ahead of AIVoicesBeyond Standard LLMs From DeepSeek R1 to MiniMax-M2, the largest and most capable open-weight LLMs today remain autoregressive decoder-style transformers, which are built on flavors of the original multi-head attention…

Ahead of AIVoicesUnderstanding the 4 Main Approaches to LLM Evaluation (From Scratch) How do we actually evaluate LLMs? It’s a simple question, but one that tends to open up a much bigger discussion.

Ahead of AIVoicesUnderstanding and Implementing Qwen3 From Scratch Previously, I compared the most notable open-weight architectures of 2025 in The Big LLM Architecture Comparison .

Ahead of AIVoicesFrom GPT-2 to gpt-oss: Analyzing the Architectural Advances OpenAI just released their new open-weight LLMs this week: gpt-oss-120b and gpt-oss-20b, their first open-weight models since GPT-2 in 2019.

On the calendar

予定 · Conferences and launch events, this week's stories from each corner of the industry, and what its press is covering — in English

On view

This week, from that corner the newest stories from the corner of the industry you picked

The wire their own posts, translated

How code moves in 2026 from the industry's own reports

Sources

Fetched every six hours, linked to the original

About

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