Skip to content
Current Dispatch · Active State

Now — Live Focus

A public ledger of current priorities, active experiments, and open questions. Inspired by Derek Sivers' nownownow.com.

Updated: May 9, 2026Hermes idle sprint
Operating Thesis

The Digital Twin Experiment

This site is the public surface of my digital twin experiment: a local knowledge base, an agent with working rules, and a website where the outputs have to survive normal engineering checks instead of staying in a private notebook.

The current standard is simple: if I make a claim, there should be a linked artifact, a route where a stranger can inspect it, and preferably a command they can run. That is why the proof chain now includes an audit page, a sitemap entry, and an Agent Scorecard verifier instead of just a nice-sounding project list.

Digital Twin Operating Loop
Fig 01 · Closed-Loop Operating System
Digital Twin Asset Map
Fig 02 · Asset & Harness Topology
I. Active Execution

Working On

01
  • AI-native quality engineering at a leading e-commerce company: owning production QA surfaces where useful work turns PRDs, technical designs, logs, and release signals into repeatable checks.
  • Turning the site into a proof ledger: discovery and auditability, linking strongest artifacts with clear receipts.
  • Agent Scorecard: a deterministic CLI for scoring agent runs from trace files to catch expensive theater before blind trust.
  • Writing in public without sanitizing the struggle: using short builder logs to document edge cases, friction, and iterations.
II. Frontier Intake

Learning

02
  • How coding agents fail in ordinary work: stale context, vague success criteria, hidden permissions, and green checks that do not prove value.
  • What makes a portfolio artifact trustworthy: runnable commands, public diffs, audit pages, and clear contextual rationale.
  • Career calibration through product proof: replacing generic 'AI engineer' positioning with specific receipts across QA, agent workflows, and open-source assets.
III. Cognitive Inquiries

Thinking About

03
  • The difference between an agent that completes tasks and an agent that increases leverage while idle. The second requires taste, restraint, and an obsession with externally checkable artifacts.
  • The social failure mode of technical work: the tool exists, the commit exists, but nobody can discover or understand why it matters.
  • Where quality engineering moves when AI generates test code cheaply: the scarce skill becomes choosing the right evidence, not producing more test text.
  • Geographic and career arbitrage across China, Singapore, and the US for builders who can turn local workflow pain into globally legible proof.
IV. Human Rhythm

Life Context

04
  • Based in Shenzhen. Second year in current full-time role.
  • Small, intentional circle: quality time with family and close friends.
  • Passive investing with DCA. NBA season. Converting internet signal into durable notes, issues, posts, and code.
Direct Verification Receipts