Kush V2: 9.1 Out of 10 — The Sovereign Model
Kush V2 ships with zero data contamination, 1,443 curated training pairs, and 184 agent-generated examples. The first Hotep model with 7-gate validation.
Hotep LLM v12: Quality Revolution Through Autonomous AI Engineering
How a 7-agent autonomous swarm transformed response quality from C+ to A-, and what the upcoming Kush V1 model means for sovereign intelligence.
Hotep LLM v11: The Pipeline That Changed Everything
Hotep LLM v11 was not just a model — it was an infrastructure revolution. How our hybrid scoring system and data pipeline shaped every model after it.
Hotep LLM v10: The Evolution of Sovereign Intelligence
Hotep LLM v10 now in production: how rigorous persona scoring, the Kosmos discovery, and an advanced RAG pipeline built our most aligned sovereign model.
Hotep LLM v6 Now in Production: 71.3% Persona Alignment Achieved
Hotep LLM v6 is now in production. Discover how rigorous A/B testing and 812 curated training examples achieved a 71.3% sovereign persona alignment score.