Hotep Intelligence Kush V3: Deeper Knowledge, Richer Responses
Kush V3 launches with 103% more training data, chain-of-thought reasoning, and real-world user feedback — all on Llama 3.1 8B. Scores 100/100 on eval.
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.
Kush V1: A New Name, A New Foundation
The first Hotep model on Meta's Llama 3.1 8B. A new naming convention, a new base architecture, and the bridge between v14's failures and Kush V2's triumph.