Core Hypotheses Presets:
Human Demonstrations (N) 8 trials

Biological few-shot direct somatic intuition

Matrix Training Iterations 8,000 steps

Brute-force stochastic gradient steps

Post-Deploy Environmental Drift 42%

Physical friction / strategy rule distribution shift

Synaptic Consolidation (Plasticity) 15% EWC

Continual weight elasticity vs rigid post-deploy freeze

Current State: Ready to Simulate
1. Standard Transformer / Matrix Architecture Frozen Weights
O(N·d²) Brute-Force
Retention Rate
28.4%
Sample Hunger
1,000x
Catastrophic Cliff
High
Affective Proxy Loss
0.85 L2
2. Neuromorphic / Biological Continual Model Active Plasticity
Few-Shot Intuition
Retention Rate
91.8%
Sample Efficiency
125.0x
Adaptation Steps
8 trials
Somatic Resonance
0.08 Err

The David Lynch Test: Affective Feeling vs Coarse Statistical Guessing

"Could a much more advanced AI create David Lynch movies if they were erased from the training dataset? AI must guess how humans feel from coarse data like 'most people like this movie'. Humans test ideas against their own internal nervous system."

Brute-Force Statistical AI Prediction Coarse Proxy

Interpolating nearest neighbors from Hollywood averages. Outputs generic eerie tropes without psychological dread cohesion.

Visceral Affective Alignment 21% (High Somatic Error)
Biological Human Creator Internal Feedback Somatic Loop

Direct recursive introspection: creator experiments with lighting, tempo, and uncanny dissonance, validating against subconscious emotive reaction.

Visceral Affective Alignment 96% (Subconscious Resonance)

Slate Star Codex Theoretical Alignment

Current large language models and transformers rely heavily on matrix multiplication: $Y = W \cdot X$. While scaling compute and parameters mimics general fluency, it exposes three distinct bottlenecks:

Enjoy this tool? Build your own with Super