Blog
Writing on AI engineering, intelligent systems, computer science, and building technology that works in the real world.
Can an AI Agent Learn Without Fine-Tuning Its LLM?
A small replication of Memento-style agent memory, testing whether a frozen research agent improves by retrieving and reusing previous task-solving experiences.
I Tried Newton-Muon. The Training Loss Lied to Me.
A small reproduction of Newton-Muon on Tiny Shakespeare, and why training loss can be a dangerously misleading signal when comparing optimizers.
Teaching an LLM New Knowledge Without Making It Forget
I implemented a small continual-learning experiment to understand whether sparse memory can teach an LLM new facts without destroying what it already knows.
Searching Algorithms in a Data Structure
A look at how linear and binary search algorithms work within stack data structures, with practical examples.
The Lies Before the Start - TEDx Lokoja 2026
At TEDx Lokoja 2026, I spoke about what stops capable people from starting: not resources, but the lies we tell ourselves about why we can't begin.
Automata Theory
A comprehensive introduction to Automata Theory: Finite Automata, DFA, NDFA, minimization, and Moore and Mealy machines.
IndabaX Nigeria 2025: How to Build a Sustainable AI Product
I spoke at IndabaX Nigeria 2025 on building sustainable AI products. Why Nigeria has over 3,000 AI researchers but fewer than 50 working AI products, and what we must do about it.
