# jabinwan

> Public articles, projects, and profile for jabinwan.

## Core

- [About jabinwan](https://jabinwan.com/en/about.md)
- [Projects](https://jabinwan.com/en/projects/)
- [Answers](https://jabinwan.com/en/answers/)
- [Profile JSON](https://jabinwan.com/en/api/profile.json)
- [Full corpus](https://jabinwan.com/en/llms-full.txt)
- [OpenAPI](https://jabinwan.com/en/openapi.json)
- [About index](https://jabinwan.com/en/.well-known/about.json)
- Public Ask worker not configured (static search / curated answers only)

## Series

- [Notes](https://jabinwan.com/en/posts/notes/)

## Answers

- [Who is jabinwan?](https://jabinwan.com/en/answers/who-is-jabinwan/): jabinwan is an engineer at a phone OEM with 5+ years of experience in C, Python, and Java; the path ran from Linux kernel through Android Framework/System App to AI, now focused on Agent memory, observability, and evaluation.

## Recent articles

- [When the Agent Comes to You: Dissecting nanoMuse's Proactive Intelligence](https://jabinwan.com/en/2026/11/13/nanomuse-proactive-intelligence.md): Based on the nanoMuse v1.0.9 source (main @ 067384b), this post dissects how an open-source personal agent implements proactive intelligence: a scheduler loop waking every 30 seconds handles all due checks; due items are handed to the model through an idempotent SQLite ledger; the model's output goes through the [quiet] prompt protocol that decides whether to interrupt the user; dangerous actions are stopped by the Sentinel gate. The most counterintuitive finding: a failed model run still counts as 'this occurrence happened' — only a process crash gets replayed. Conclusion: the reliability of proactive intelligence comes from a deterministic engineering shell, not from the model.
- [The Three Unoutsourceable Things: What Matters Most for Humans in the AI Era](https://jabinwan.com/en/2026/11/12/non-outsourceable-three.md): This essay examines what remains uniquely human in the AI era. As AI drives the cost of execution toward zero, the core question shifts from 'can you do it' to 'what is worth doing, what counts as good, and what should come first'. The author argues three things cannot be outsourced: taste, which judges what deserves to exist; curiosity, which asks good questions in an era of surplus answers; and agency, which moves first and owns the consequences — all resting on the courage to own your choices. Tools no longer differentiate people, yet knowing their boundaries still matters; the two kinds of truly unoutsourceable cognition are defining problems and verifying outputs. How you use AI reshapes cognition itself: replacing your thinking with it atrophies cognition, while using it to pressure your thinking compounds it. The essay closes with a motto: ask with curiosity, choose with taste, act with agency; leave the rest to the machine.
- [Hello World: This Site Is Live](https://jabinwan.com/en/2026/11/11/hello-world.md): jabinwan's personal site goes live: a bilingual (Chinese/English) personal site deeply customized from the Refined-X (Astro + Starlight) template. The static site runs on Cloudflare Pages; a lightweight visit counter is served by a Cloudflare Worker.