About sinc-LLM

Nyquist-Shannon Sampling Theorem Applied to LLM Prompts

sinc-LLM treats every prompt as a signal. If you undersample it, the model hallucinates. That is specification aliasing.

The framework decomposes any raw prompt into 6 frequency bands on the specification axis. Each band carries a different type of information the model needs to produce faithful output.

x(t) = Σ x(nT) · sinc((t - nT) / T)
97%
Cost Reduction
6
Frequency Bands
42.7%
CONSTRAINTS Weight
275
Observations

The 6 Frequency Bands

BandnWeightWhat It Carries
PERSONA07.0%Who should answer — the exact expert type
CONTEXT16.3%Background facts, dates, situation
DATA23.8%Specific inputs, metrics, content to process
CONSTRAINTS342.7%Rules — MUST/NEVER/ALWAYS. Longest band.
FORMAT426.3%Exact output structure
TASK52.8%The specific objective

Why CONSTRAINTS Dominates

CONSTRAINTS carries 42.7% of reconstruction quality. When constraints are absent, the model defaults to hedging, over-qualification, and generic patterns — classic aliasing artifacts. Specifying constraints acts as a bandpass filter on the model's output space, narrowing it to the specified behavioral region.

The Auto-Scatter Hook

The auto-scatter hook intercepts every raw prompt before the LLM sees it, decomposes it into all 6 bands, and injects the structured result as system context. The model receives both the raw prompt and its sinc decomposition. No prompt is ever blocked. The hook costs $0.002 per call but saves $0.08 per call by eliminating clarification loops — a 38x ROI.

AI Transform

AI Transform is the production feature on sincllm.com that runs the auto-scatter using a locally fine-tuned Qwen2.5-7B model at 290 tokens/second. Zero API cost. The model was distilled from Claude using 113 validated training examples and fine-tuned with Unsloth LoRA in 172 seconds.

Key Results

Cost reduction97% ($1,500 to $45/month)
Token reduction95.6% (80,000 to 3,500/session)
SNR improvement0.003 to 0.855 (285x)
Exchange rate4.2 to 1.6 responses/prompt
Weekly savings$1,588.56 (measured over 7 days)
AI Transform speed290 tokens/second

Open Source

The framework, auto-scatter hook, training data, and fine-tuning pipeline are open source.

DOI: 10.5281/zenodo.19152668

GitHub: github.com/mdalexandre/sinc-llm

Try AI Transform for free

Open sinc-LLM