Skip to content

Tunde Adeyemi

Technology & Engineering Editor

ML Engineer, Open Source Advocate

Tunde Adeyemi oversees technology and engineering content at Hotep Intelligence. As an ML engineer and open source advocate, he ensures technical content is accurate, accessible, and aligned with the project's mission of digital sovereignty. His expertise spans machine learning, self-hosted infrastructure, and the application of AI for community empowerment.

Articles Authored & Reviewed by Tunde Adeyemi

Hotep Intelligence Kush V9.1 Is Live: 100% Entity Grounding at 48.2 tok/s

Kush V9.1 clears every promotion gate that held back V9.0 — achieving 7/7 Exact Entity Recall, 7/7 P...

Kush V9 Validation Update: V82 Remains Production

Post-mortem on Kush V9: why Prime Agent E2E entity grounding gates triggered a production rollback t...

Hotep Intelligence Kush V4: The Reasoning Model

Kush V4 introduces structured chain-of-thought traces and GEPA evolutionary prompt optimization acro...

Hotep Intelligence Kush V3: Deeper Knowledge, Richer Responses

Kush V3 launches on Llama 3.1 8B with 103% more training data, chain-of-thought reasoning, and user ...

Kush V2: 9.1 Out of 10 — The Sovereign Model

Inside Kush V2: 1,443 curated training pairs, zero data contamination, 184 entity-grounded examples,...

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 ...

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 Kus...

Hotep LLM v14: Deployed, Audited, Reverted in 12 Hours

V14 trained successfully, passed compilation, and served real users — then scored 25/100 on quality ...

Hotep LLM v13: What Catastrophic Overfitting Taught Us

We switched base models, copied hyperparameters, and lost 29 GB of compute in hours. V13 was our mos...

Hotep LLM v11: The Pipeline That Changed Everything

How the V11 hybrid evaluation pipeline and automated dataset quality gates laid the engineering foun...

Hotep LLM v10: The Evolution of Sovereign Intelligence

From v6 to v10: how hybrid persona scoring, Kosmos literature synthesis, and multi-collection RAG pr...

Hotep LLM v6 Now in Production: 71.3% Persona Alignment Achieved

Announcing hotep-llm-v6: how rigorous A/B evaluation and 812 curated instruction pairs established o...

Why African History Matters in the Age of AI

As AI shapes the future, ensuring African perspectives and history are represented becomes more crit...

Building Sovereign AI: Why Self-Hosting Matters for Cultural Technology

Technical deep dive into self-hosted AI infrastructure: how we built Hotep LLM without third-party A...

Knowledge of Self: How AI Can Support Your Journey

The concept of knowledge of self is central to empowerment. Learn how culturally-aligned AI can serv...