Neural networks do not store facts; they calculate high-dimensional probability distributions. Hallucination is not a "bug"—it is the mathematical consequence of lossy compression, attention dispersion, and autoregressive Markov drift where each sampled error becomes ground truth for subsequent tokens.

Manifold Drift 0.04 σ
Attention Dispersion 1.12 bit
Hallucination Risk LOW (4%)
Factual Basin
Hallucination Basin
Current Token State
Generated Autoregressive Context Window (8 tokens) Step 8 / 18

1. Autoregressive Error Compounding

Transformers predict one token at a time: $P(w_1, \dots, w_n) = \prod P(w_t \mid w_{<t})$. If token $w_k$ deviates from truth due to sampling noise or superposition, it becomes immutable context. The model cannot backtrack; it is forced to condition on its own mistake, creating a mathematically coherent fiction.

2. Polysemantic Superposition

Because neural networks possess more concepts than physical dimensions, multiple features share non-orthogonal activation vectors (superposition). When activating a niche entity, overlapping neurons partially excite ungrounded associations, causing "blended" hybrid facts.

3. Attention Dispersion & Saliency Fade

As context expands or distractor tokens increase, the Softmax denominator $\sum \exp(Q K^T / \sqrt{d})$ dilutes attention weights across hundreds of tokens. Factual anchor tokens lose saliency to high-frequency semantic distractors.

4. Sycophancy & Prior Dominance

Pre-trained statistical patterns prioritize sentence fluency and user-query alignment over epistemic verification. When asked to justify a false claim, the network optimizes for plausible continuation rather than refusal.

Enjoy this tool? Build your own with Super