A field note from ICML on why Code Agent became the dense common topic, and why Code-style execution loops may become a general form for next-generation agent capability.
A mini-book essay on capital compounding, skill compounding, and how AI tools may form a third compounding structure.
A mini-book essay on how the Agent era challenges the economic intuition inherited from The Wealth of Nations.
A small experiment where a phone-side Codex session asks desktop Codex to operate the same Android phone GUI through USB ADB.
A lightweight context layer that compresses, recalls, and transfers task state across sessions, tools, and agent entrypoints.
A local macOS execution layer that lets agents inspect and operate real desktop apps in the background without interrupting your work.
A self-improving voice-coding harness that turns spoken intent into structured agent instructions, feedback loops, and reusable traces.
A personal field note on AI-native slide making across PPTX, Slidev, Feishu Docs, Beamer, and image-first versus editable-first workflows.
A blog-format public draft on linear attention as a modular memory mechanism for agent pipelines.