Skip to content

SuperInstance/dissertation-engine

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

dissertation-engine

Computational backbone for the dissertation "Intelligence is Models for the Negative Space".

This crate reproduces all key figures and results from the 5 laws of intelligence-as-negative-space.

The Five Laws

Law 1 — Negative Space Discovers

A reinforcement-learning agent receiving only negative feedback (no positive reward) discovers the safe subset of its environment. The agent converges to ~60% avoidance through pure negative feedback (Act0).

Key result: ≥ 55% avoidance rate from negative feedback alone.

Law 2 — Avoidance Dominates

Organisms in stochastic environments exhibit a 294:1 avoid-to-choose ratio, reflecting evolved loss-aversion where avoidance responses vastly outnumber approach responses.

Key result: Avoid:Choose ratio ≈ 294:1.

Law 3 — Species Coexist

Multi-species competitive Lotka-Volterra dynamics with intra-specific competition exceeding inter-specific competition yield 100% ecological resilience — no species goes extinct.

Key result: All species persist above extinction threshold.

Law 4 — Population Beats Individual

Population-level (group) selection outperforms individual-level selection by +0.075 fitness units, demonstrating the evolutionary advantage of collective negative-space modeling.

Key result: Population fitness advantage ≈ +0.075 over individual selection.

Law 5 — Conservation Law

The avoidance ratio A = avoided / (avoided + chosen) is conserved across ecological scales, with standard deviation ≈ 0.001 across population sizes ranging from 100 to 50,000.

Key result: std(avoidance ratio) < 0.01 across all scales.

Usage

use dissertation_engine::DissertationReport;

fn main() {
    let report = DissertationReport::generate(42);
    println!("{}", report.render());
}

Running Tests

cargo test

The test suite includes 25+ tests that reproduce all 5 laws and validate supporting infrastructure (RNG, statistics helpers, simulation components).

Design Principles

  • Pure Rust, no unsafe, no external dependencies
  • Deterministic via seeded PRNG (SplitMix64)
  • Each law is a self-contained module with a top-level reproduction function
  • DissertationReport aggregates all results into a single formatted report

License

MIT

About

Computational backbone for 'Intelligence is Models for the Negative Space' — reproduces all key figures and results from 5 laws

Resources

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages