sentence-transformers
English
embeddings
hyperbolic-geometry
poincare-ball
21-dimensional
scbe-aethermoore
sacred-tongues
Instructions to use issdandavis/phdm-21d-embedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use issdandavis/phdm-21d-embedding with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("issdandavis/phdm-21d-embedding") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
How a DnD Campaign Became an AI Governance Framework
#2
by issdandavis - opened
How a DnD Campaign Became an AI Governance Framework
SCBE-AETHERMOORE uses the Poincare ball model of hyperbolic space to make adversarial AI behavior geometrically expensive rather than detecting it reactively.
Quick Summary
- 14-layer pipeline mapping to 5 quantum axioms
- Harmonic Wall:
H(d,R) = R^(d^2)-- adversarial cost scales 57,665x at boundary distances - Six Sacred Tongues tokenizer: 6 x 256 tokens, golden-ratio weighted trust dimensions seeded from 12,596 paragraphs of AI game logs
- Post-quantum crypto: ML-KEM-768, ML-DSA-65, AES-256-GCM
- 95.3% adversarial prompt injection detection, zero false denials, <8ms total
Install
pip install scbe-aethermoore
from symphonic_cipher.scbe_aethermoore.flock_shepherd import FlockShepherd, SheepRole
shepherd = FlockShepherd(max_flock_size=50)
agent_id = shepherd.spawn_agent(role=SheepRole.EXECUTOR, training_track="code_review")
health = shepherd.get_flock_health()
Links
- GitHub: issdandavis/SCBE-AETHERMOORE
- npm: scbe-aethermoore
- PyPI: scbe-aethermoore
MIT licensed. EU AI Act ready. Patent pending: USPTO #63/961,403.