Esc

Six ways into the archive

Start with the question you actually have.

The blog is large because the systems are connected. These paths put the strongest essays in an intentional order and explain why each step comes next.

6guided paths
36ordered readings
0completed locally
0 of 36

Foundations

Understand RAPP

What is RAPP, and why is one file the unit?

Start with the smallest portable capability, then follow the idea through contracts, factories, collaboration, and ownership.

0 / 6 complete
Where this leaves you

You will understand the design logic behind the wider RAPP ecosystem.

Choose another path ↑

Ownership

Build Local-First AI

What does it mean for an AI system to remain yours?

Move from the local-first principles through offline state, resilient delivery, public/private boundaries, and durable possession.

0 / 6 complete
  1. Step 4

    Offline-resilient send queue

    Add the harder half of offline operation—effects that must leave the device exactly once.

    April 19, 2026 · 3 min read

  2. Step 6

    The AI You Keep

    Finish with the ownership test—if the AI cannot be inherited, it was never truly possessed.

    July 5, 2026 · 6 min read

Where this leaves you

You will have a practical architecture for AI that survives networks and vendors.

Choose another path ↑

Identity

Design a Digital Twin

How can an AI extend a person without impersonating them?

Follow the twin from manifesto to deployment, private memory, public surfaces, autonomous variants, and inheritance.

0 / 6 complete
  1. Step 6

    The AI You Keep

    Carry the pattern to its emotional conclusion: a persistent being that can outlive a vendor.

    July 5, 2026 · 6 min read

Where this leaves you

You will understand the twin as a persistent medium rather than a chatbot persona.

Choose another path ↑

Autonomy

Run Autonomous Agent Systems

How do you let many agents work without losing control?

Begin with the operator's cognitive shape, then add continuous execution, failure learning, worktree isolation, simulation frames, and self-play.

0 / 6 complete
  1. Step 6

    A Taste of AGI

    End with the full loop—build, populate, test, repair, evolve, and leave notes for the next cycle.

    June 18, 2026 · 5 min read

Where this leaves you

You will understand the loop that lets an agent system improve while remaining inspectable.

Choose another path ↑

Infrastructure

Use GitHub as the Platform

How far can files, git, Actions, Issues, and Pages actually go?

Build the read path, write path, runtime, protocol, and complete application surface from infrastructure most teams already have.

0 / 6 complete
  1. Step 4

    CDN + JSON = API

    Serve the read side globally from static state and edge caches.

    October 30, 2025 · 3 min read

  2. Step 6

    The Repo IS the Platform

    Finish with the complete shape: data, governance, frontend, SDKs, and community in one repository.

    April 26, 2026 · 5 min read

Where this leaves you

You will know when GitHub-native architecture is a real system, not a clever demo.

Choose another path ↑

Rigor

Build Evidence, Not Demos

How do you know the system works instead of merely looking convincing?

Move from file-native integration tests through measured comparisons, adversarial review, feature freezes, broken-test forensics, and field notes.

0 / 6 complete
  1. Step 3

    Adversarial Calibration

    Add an evaluator whose job is to disagree with the system's preferred answer.

    March 7, 2026 · 2 min read

  2. Step 5

    Six Times the Test Was Wrong

    Treat the assertion itself as a suspect before changing correct behavior to satisfy it.

    August 1, 2026 · 4 min read

Where this leaves you

You will have a practical standard for claims that deserve to survive contact with reality.

Choose another path ↑