Long Essay · AI & Growth
The Third Paradigm of Compound Growth
A mini-book essay on capital compounding, skill compounding, and how AI tools may form a third compounding structure.
Blogs
Thinking in an AI-Native Way
Notes on memory, tools, interfaces, and infrastructure for agent-native systems.
Long Essay · Agent & Political Economy
After Division of Labor
A mini-book essay on how the Agent era challenges the economic intuition inherited from The Wealth of Nations.
Labs · Mobile Agents
Mobile-on-Mobile Agent Loop
A small experiment where a phone-side Codex session asks desktop Codex to operate the same Android phone GUI through USB ADB.
Project · Agent Context Infrastructure
Agent Context Manager: Cross-Harness Memory for Long-Running Agent Work
A lightweight context layer that compresses, recalls, and transfers task state across sessions, tools, and agent entrypoints.
Project · Background Computer Use
Open Codex Computer Use: Parallel GUI Control for Agentic Workflows
A local macOS execution layer that lets agents inspect and operate real desktop apps in the background without interrupting your work.
Project · Voice-Coding Harness
Open Typeless Harness: Voice-First Vibe Coding for Agent Workflows
A self-improving voice-coding harness that turns spoken intent into structured agent instructions, feedback loops, and reusable traces.
Topic · Slides
AI-native Slides: A Best Practice for Slide Making in the Agent Era
A personal field note on AI-native slide making across PPTX, Slidev, Feishu Docs, Beamer, and image-first versus editable-first workflows.
Topic · Memory
Linear Attention as a Generalizable Memory Mechanism
A blog-format public draft on linear attention as a modular memory mechanism for agent pipelines.