{"slug": "seferim-agi-thataiguycore-a-golden-ratio-cognitive-substrate-open-source", "title": "SEFERIM AGI — ThatAIGuyCore: a golden-ratio cognitive substrate (open source)", "summary": "A developer has released SEFERIM / ThatAIGuyCore, an open-source cognitive substrate built from a 69-equation mathematical specification across 13 systems. The framework models cognition as a 16-dimensional meta-state governed by the golden ratio φ, synthesizing the Free Energy Principle, information theory, holographic memory, Hebbian plasticity, and swarm consensus into a fully documented, named-equation architecture. The reference implementation includes 42 fidelity tests and is available at thataiguy.org/core.", "body_md": "The old AI research folder on my desktop turned out to contain a complete, self-contained mathematical specification — 69 equations across 13 systems — for a golden-ratio cognitive substrate I call **SEFERIM / ThatAIGuyCore**. So I built it for real.\n\nSEFERIM treats cognition as a 16-dimensional meta-state evolving under sixteen coupled \"cognitive families,\" all governed by the golden ratio φ. Every dynamic is a *named, documented equation* — not an opaque weight matrix.\n\nConstants (φ, δ, τ) → golden basis ψ_k → the 16 G¹⁶ families → meta-state core with golden-ratio momentum + stability gating → a free-energy-style objective Ω → DNA holographic memory → a 5000-gate binary substrate → an 88-agent neural brain → a 374-dimensional consciousness binding field → a lattice engine with Hebbian plasticity → federation cross-talk across agents.\n\n``` js\nimport { MetaState, DNAMemory, NeuralBrain } from \"seferim-core\";\n\nconst mind = new MetaState({ init: new Array(16).fill(0.1) });\nconst out  = mind.step({ dx_norm: 0.3, ed_error: 0.1, utility: 0.6, stability: 0.8 });\nconsole.log(out.state, \"Omega =\", out.omega);\n```\n\nIt synthesizes the Free Energy Principle (Friston), information theory (Shannon; Cover & Thomas), holographic/vector-symbolic memory, Hebbian plasticity, and swarm consensus. I documented the lineage precisely rather than overclaim — e.g. the memory is a golden-ratio *frequency-domain* VSA inspired by (not a literal copy of) Plate's HRR, and the constant δ = 0.013618 is empirical, not 1/φ³.\n\nThe reference implementation ships with 42 fidelity tests, including the canonical FNV-1a hash vectors.\n\nRead the full 69-equation reference and try the live demos at ** thataiguy.org/core**.", "url": "https://wpnews.pro/news/seferim-agi-thataiguycore-a-golden-ratio-cognitive-substrate-open-source", "canonical_source": "https://dev.to/joseph_anady_214bacedf939/seferim-agi-thataiguycore-a-golden-ratio-cognitive-substrate-open-source-17lf", "published_at": "2026-06-06 00:32:26+00:00", "updated_at": "2026-06-06 00:41:06.919947+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research", "neural-networks", "ai-agents"], "entities": ["SEFERIM", "ThatAIGuyCore", "Friston", "Shannon", "Cover", "Thomas", "Plate"], "alternates": {"html": "https://wpnews.pro/news/seferim-agi-thataiguycore-a-golden-ratio-cognitive-substrate-open-source", "markdown": "https://wpnews.pro/news/seferim-agi-thataiguycore-a-golden-ratio-cognitive-substrate-open-source.md", "text": "https://wpnews.pro/news/seferim-agi-thataiguycore-a-golden-ratio-cognitive-substrate-open-source.txt", "jsonld": "https://wpnews.pro/news/seferim-agi-thataiguycore-a-golden-ratio-cognitive-substrate-open-source.jsonld"}}