Stop Using Accuracy: 5 ML Metrics You Must Understand
Accuracy could be lying to youContinue reading on Towards AI »
Accuracy could be lying to youContinue reading on Towards AI »
A production-first breakdown of the real RAG stack: ingestion, parsing, metadata, chunking, retrieval, reranking, citations, freshness…Continue reading on Towards AI »
The biggest bottleneck in deploying agents isn’t reasoning quality — it’s error accumulation. Here’s the architecture that fixes it.Photo by julien Tromeur on UnsplashYour multi-agent pipeline passed every demo you ran. In production, it silently accum…
Using just Python and a real CSVContinue reading on Towards AI »
Master the core ideas behind AI without getting lostContinue reading on Towards AI »
How to intercept, control, and extend AI agents without touching the logic that actually mattersContinue reading on Towards AI »
I built a multi-agent system, thinking it would solve everything. It created three new problems I hadn’t seen coming.Continue reading on Towards AI »
What the K and V Matrices Look Like at Token 1, Token 2, Token 3. Until Now. With the Arithmetic.Continue reading on Towards AI »
I Built a Breast Cancer Detection System End-to-End. Here’s What I Actually Learned. (Part 1: Data & Pipeline)This isn’t a tutorial. It’s a breakdown of every decision, mistake, and insight from building a real ML pipeline on 300GB+ of raw mammogra…
When we first learn linear regression, we think of it like this: we have data points scattered on a plane, we draw a line through them, and we adjust the line until the total squared error is as small as possible. We take a derivative, set it to zero, …