華文

Chapter 3: Competence in Action

Attentiveness and responsibility have to go hand in hand with competent systems. “Care‑giving” means working code that does what it promised—audited, explainable, and safe‑to‑fail. Competent systems will build trust among people in the technology.

Quick version

Results we want

Why Competence?

Good intentions without working code erode trust. Competence turns contracts into systems that behave—and can be proven to behave.

A simple picture: A bridge isn’t competent because the blueprint is elegant; it’s competent because it holds—and continues to hold when trucks cross, winds rise, and inspectors check the bolts.

Simple ideas behind this chapter

What good ‘competence’ looks like

From ideas to everyday practice (step by step)

  1. Derive specs from contracts. Convert Ch2 contracts into acceptance tests.
  2. Instrument for observability. Emit decision traces with links to sources and receipts (from Ch1).
  3. Train with RLCF. Collect feedback from diverse cohorts; compute bridge scores; use them as reward.
  4. Run shadow mode. New policy sees inputs and proposes actions but doesn’t act. Compare to human/previous system.
  5. Canary safely. Release to a small, representative group with automatic rollback if drift exceeds bounds.
  6. Audit before general. Independent audit of evals, logs, and guardrails; publish attested report.
  7. Generalize & monitor. Enable for all; watch drift monitors; keep pause wired.
  8. Post‑incident learning. Blameless reviews; fixes become tests.

Tools you can adopt now

Flood‑bot story - Part III: delivering care

What could go wrong (and quick fixes)

How we keep ourselves honest (what we measure)

Interfaces with other packs

A Closing image: The bridge

Imagine a well‑kept bridge with inspection tags—date, load test, next check—visible to anyone crossing. People can take confidence in that the bridge will hold and is consistently tested for safety.

Previous Next