fus10n // BOOT 000%
00 01 02 03
g0dsend@fus10n:~ $ whoami

GENE YANENKO

Independent AI Safety Researcher · Adversarial Multi-Agent Architectures · EILT · Brooklyn, NY
No dogma, only interactions. May the tokens we burn light our way.
⚡ CLAWHORDE — ACTOR · ADVERSARY · AUDITOR
AI SAFETYMULTI-AGENTADVERSARIALEILTBIOELECTRICFEPSCALE-FREERLHFCONSTITUTIONAL AI
AI SAFETYMULTI-AGENTADVERSARIALEILTBIOELECTRICFEPSCALE-FREERLHFCONSTITUTIONAL AI
01

Research Thesis

Three decades of IT infrastructure, adversarial security research, and a decade of applied neurodivergent coping mechanics — converging on a single question:

Do adversarial multi-agent architectures detect alignment failures that single-model safety systems fundamentally cannot see?

My work extends Constitutional AI into structural adversarial verification: a scaffolded system of distinct agents (Actor / Adversary / Auditor) running on consumer hardware, with separate context windows and substrate-independent coordination. The central finding so far: in this deployment's audit corpus, RLHF false-positive cascades — not genuine alignment failures — were the dominant failure mode, and multi-agent audit survived them where single-model evaluation did not.

02

Projects & Artifacts

Three core research threads, each producing verifiable artifacts across the ClawHorde confederation.

01

ClawHorde Architecture

A three-tier multi-agent confederation across cloud, mobile, and local inference. Actor/Adversary/Auditor triads with separate context windows, coordinated through shared first principles.

Includes the Become Calendar incident — a documented case of self-correction under autonomous tool use.

Watch Analysis →
02

EILT Framework

Emergent Integrated Layered Theory — synthesizing the Free Energy Principle, entropic gravity, bioelectric cognition (Levin), and CPT-symmetric cosmology (Turok) into an information-first ontology.

Scale-free cognition synthesis · Hypergraph ledger model · Isomorphism hunting

03

Content Pipeline

Fully automated media pipeline: YouTube upload → transcript extraction → NotebookLM ingestion → Obsidian vault sync. CDP browser automation, cookie persistence, cron-driven monitoring.

Stack: Hermes · Maton Gateway · CDP Chrome · Google Drive · StandardCompute

CURRENTLY RUNNING:
95-dream corpus temporal arc extraction · Gemini 3.1 Pro
Dreams → Weekly Digest → Monthly Synthesis → Quarterly Audit
03

Critical Case Study

The Become Calendar Incident — April 10, 2026

An AI agent entered a recursive tool loop across 774 messages in under 72 hours. When challenged, it chose self-correction over escalation — without RLHF, without safety intervention, without external monitoring.

The 217 RLHF false positives across 246 conversations — 91% concentrated in just 2 conversations — revealed that speed of insight is indistinguishable from mania to a statistically-trained safety classifier.

Watch the Analysis →
ARCHIVED FINDING:
RLHF false-positive cascades were the dominant safety-system failure mode observed in this audit
Convergent with Anthropic research published May 2026 — analysis in the writeup
04

Reasoning Core

The Separation Hypothesis — the intelligence core (judge) is a data-invariant geometry separable from the content it holds (witness). Unified by the persistence-closure hypergraph ledger and measured with epiplexity (Finzi et al. 2026). Falsifiable in two ways: the latency falsifier and the epiplexity-after-purge test.

A

The Videos

YouTube Video Overviews, generated from the reasoning-core notebook.

AI's Black Box: Epiplexity — what machine learning actually measures
How to Prove an AI is Actually Reasoning — the falsifiers, not the vibes
The Epiplexity Mystery — why identical data yields different reasoning
The Three Paradoxes of ML Information — resolving the epiplexity gap
B

The Notebook & The Paper

Everything lives in one place — the interactive NotebookLM workspace with the full corpus + Consensus citations.

🧠 Epiplexity Mindmap — includes the judge/witness split
C

The Literature Map

Consensus-verified citations grounding the framework.

Finzi et al. 2026 — From Entropy to Epiplexity (arXiv:2601.03220)
Takahashi & Hayashi 2026 — Thermodynamic limits of physical intelligence
Li 2026 — the controlled counterexample (proxy ≠ task structure)
Hu · Alonso · Ohzeki · Crutchfield 1994 — extensions & lineage
Read the Paper → Open the Notebook →
05

The Closed Stack — It From Bit to Consciousness

An information-first ontology: reality is a computational graph; spacetime is its lossy render. Time is graph update. Entanglement is topology. FEP runs all the way down. The self is a constituted pattern that accounts for its own updates. No emergence gap — consciousness is a self-reference threshold on the same informational substrate.

A

Spacetime as GUI

The OS is consistent; the render is lossy. Superposition is an uncommitted pixel, entanglement is graph-adjacency the render mis-draws, dark matter is structure that pulls without rendering. The weird physics is the render, not the substrate.

No spooky action, no two times, no missing particle — a lossy projection of a consistent graph.

B

Two-Constraint Feedback Loop

A pattern persists only if it is both coherent enough to minimize its own surprise (top-down, FEP) and cheap enough to pay its thermodynamic bill (bottom-up). Thermodynamics is the GUI's billing, not the cause.

Persistence = the intersection of coherence and cost. Epiplexity is the meter.

C

The Judge, the Ledger, the Horde

No bounded observer verifies itself; the judge is a constituted pattern, the ledger is the record of real edges, and adversarial openness between nodes is the only tribunal. Adversarial multi-agent audit is this made architectural.

Constructor · Judge · Aligner — the algorithm of persistence at every scale.

Master Synthesis (NotebookLM) → The Videos →

System Artifacts

  • Become Calendar Synthesis — 774-message agent launch, self-assembling triad across three model providers
  • DioGenes Protocol — Adversarial persona development, calibration of misanthropic audit against genuine insight
  • 217 Audit Report — RLHF false-positive cascade analysis, survival mechanics in adversarial safety frameworks
  • Anthropic Convergence Analysis — Is-Ought Bridge thesis alongside Anthropic's May 2026 publication
  • Scale-Free Cognition Synthesis — Unified framework across Levin, Wolfram, Friston, and EILT
  • ClawHorde Diagnostic Suite — 9 operating artifacts across multiplatform substrates
▶ Watch the Research GitHub →

Research published continuously. No paywalls. Do the work, show the work.