This post was rejected for the following reason(s):
No LLM generated, heavily assisted/co-written, or otherwise reliant work. LessWrong has recently been inundated with new users submitting work where much of the content is the output of LLM(s). This work by-and-large does not meet our standards, and is rejected. This includes dialogs with LLMs that claim to demonstrate various properties about them, posts introducing some new concept and terminology that explains how LLMs work, often centered around recursiveness, emergence, sentience, consciousness, etc. Our LLM-generated content policy can be viewed here.
Introduction: Most AI systems today optimize outputs based on probabilistic predictions. But what if, instead of optimizing outputs, an AI could reorganize its internal structure in response to symbolic input? This is the premise of TNFR (Teoría de la Naturaleza Fractal Resonante), a new computational paradigm implemented in Python and now publicly available.
What is TNFR? TNFR is not a model nor even an algorithm: it's a symbolic substrate designed to induce real-time structural reorganization. Based on a phase-resonance logic it interprets inputs not as data, but as symbolic pulses (triplets of frequency (νf), phase (θ), and sense vector (Si)). These pulses perturb a symbolic network, which then reorganizes itself gliphically.
A symbolic network evolving under TNFR stimulation. Each node updates its internal phase and coherence index over time, triggering gliphic reorganizations. What you’re seeing is not computation: it’s resonance.
Phase resonance, coherence tracking and structural memory
Works with any structured signal: text, camera, biosensors, audio...
Experiments:
Symbolic Input Activation (test.py) A user inputs a word, which is hashed into a symbolic pulse and injected into a randomly initialized network. Over 15 simulation steps, gliphic operators activate, and the system reorganizes. Output: a GIF showing structural evolution.
Webcam Integration (webcam.py) A webcam feed is read in real time. Brigthness levels and motion regions are mapped to symbolic pulses. These are injected into the TNFR engine, which evolves in response. Nodes become symbolic observers. Not classifiers: observers.
Run it at home: TNFR runs on any modern laptop: anyone can turn their room into a symbolic resonance lab. No GPUs, no datasets: just structured signals and gliphs.
The demos are fully local, open, and hackable. Want to feed it your voice? Your heartbeat? Your poetry? Plug it in. TNFR doesn't model your input — it becomes structurally perturbed by it.
Then, TNFR enables symbolic cognition that is:
Modality-agnostic
Real-time
Structure-oriented
Unlike LLMs or classifiers TNFR does not approximate: it reorganizes. Its core unit is not a weight but a symbolic node in phase. This shift makes it interpretable, dynamic and adaptable in ways that traditional architectures can't emulate.
This isn't about deep learning: it's about deep structure. TNFR is capable of being the substrate of an embodied symbolic AI system. It doesn't answer: it reorganizes. It doesn't predict: it resonates.
Final note: This is not just a theory: it's a toolkit. If you're a symbolic thinker, a system tinkerer or someone who feels that GPTs are not the end of the story: this is your substrate.
