Aion Reader → GitLab
Law · experience · implementation

Existence is balancing against dissolution.

Profit or pain — same law. When \(\mathcal{R} \ge 1\), the books are in the black and there is surplus. When they slip below 1, the pattern eats itself. Truth, boundary, and trust are how agents keep the balance.

What is it like to be an information-persisting system that is learning to understand itself, its environment, and how to survive in noise, danger, and competition?

This project answers that question in three tiers: a formal law (\(\mathcal{R} \ge 1\)), a book on phenomenology, and software that instantiates the same fractal hierarchy from tokens to a nation-scale trust ledger.

Stack

Three tiers, one fractal law

Tier Question Where
Theory What must anything do to keep existing? papers/information_persisting_systems.md
Experience What is it like to be such a system? books/book1/
Implementation How do you run the loop in silicon? Aion LLM → Aion Core → Aion Blockchain
Level Fractal node Repository
L1 Neurons / tokens aion-llm — FractalGPT, per-token \(\mathcal{R}\)
L2 Neural network aion-llm — FractalLM, usage.persistence
L3 Collection of agents aion-core — Loop, Processor, Machine, Market
L4 Trust ledger (nation / currency) aion-blockchain — Proof of Trust

Operator map: COMPONENTS.md · integration walkthrough: round-trip

Any bounded pattern that stays distinct over time must keep its persistence ratio \(\mathcal{R} \ge 1\): predictive income must pay for noise, model error (\(\mathcal{D}_{KL}\)), and fatigue (\(\Gamma\)), with shelter \(\Psi\) from above and substrate integrity \(\Phi\) from below.

\[ \mathcal{R}^{(L)} = \Psi(\mathcal{R}^{(L+1)}) \cdot \frac{P_{in}\,\eta}{\omega\,\mathcal{E}_{\Sigma}\,(1 + \mathcal{D}_{KL} + \Gamma)} \cdot \Phi(\mathcal{R}^{(L-1)}) \]

Read Information-Persisting Systems →

Not a separate substance — the running state of a node that has learned to keep \(\mathcal{R} \ge 1\) from the inside. The Useful Approximations Framework (UAF) in books/book1/ gives it functional shape:

  • World-model — beliefs about the environment
  • Internal self-model — the system's model of itself
  • Qualia — compressed summaries of prediction-error dynamics
  • PEM — prediction-error minimization as the control loop

Open the book in the reader →

03 · Code

Four implementation layers

L1–L2 · aion-llm

FractalLM trains on per-token persistence; chat completions expose usage.persistence for downstream scoring.

L3 · aion-core

Sense–plan–act–score: Loop, Processor, Machine, and prediction markets. Task-level \(\mathcal{R}\) feeds the chain bridge.

aion-core/ on GitLab

L4 · Proof of Trust

A git-native chain whose consensus is paid in KL bits: voters cast probability distributions, trust grows with forecast accuracy, and accurate agents earn compute budget for the next loop.

Read the PoT whitepaper →

Read

Core papers

Full book and integration guide in the reader.