ayabraham.com
AYODELE
AI Safety · Mech. Interp.AI Auditing · Alignment
AI Safety
Mechanistic Interpretability
AI Auditing

Publications


Peer-reviewed Research

Peer-reviewed research in applied machine learning and engineering. My earlier published work focused on manufacturing processes and neural network applications. Current research interests centre on AI safety, mechanistic interpretability, and AI auditing.

01.Prediction of tool wear based on GA-BP neural network

Authors: Weihua Wei, Ruibing Cong, Yiqing Li, Ayodele Daniel Abraham, Chao Yang, Zhaoyao Chen

Journal: Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture (2022)

Link: Sage Journals DOI

02.Surface roughness and chip morphology of wood-plastic composites manufactured via high-speed milling

Authors: Weihua Wei, Rui Cong, Tongming Xue, Ayodele Daniel Abraham, Changyong Yang

Journal: BioResources, 16(3), 2021

Link: BioResources

Technical Writing
Tutorials
Linear Algebra for Model Internals (Part 1: Vector Spaces and Transformations)
2026-07-31 · 14 min read
AI Safety
My Journey Through Technical AI Safety: A BlueDot Course Retrospective
2026-07-13 · 11 min read
AI Safety
Building an Input/Output Safety Classifier Pipeline (and Trying to Break It)
2026-07-01 · 9 min read
AI Safety
What's Actually Happening Inside an AI?
2026-06-23 · 8 min read
AI Safety
What Happens When You Talk to an AI That Hasn't Been Taught to Talk Back
2026-06-15 · 4 min read
AI Safety
On Measuring Safety: Red-Teaming Open-Weight Models with GuardRail-Audit
2026-06-09 · 10 min read
All writing →