01
Evaluating LLM Applications: Who Decides What “Good” Looks Like?
What makes an LLM application good — and who gets to decide? An exploration of evaluation, quality, evaluator trade-offs and application context.
Read the article ↗
02
Standardization in Canonicalization for RAG Pipeline Development
An article on standardizing text before retrieval: removing noise, simplifying phrasing, normalizing language and stripping conversational filler.
Read the article ↗
03
Home Credit Default Risk
A machine-learning project covering the business problem, formulation, constraints, feature engineering, model comparison and evaluation for credit default risk.
Read the article ↗
04
Types of Probability — Part II
A continuation of the probability series, building on the basic concepts introduced in the first part.
Read the article ↗
05
Introduction to Probability — Part I
A brief introduction to probability and its basic concepts.
Read the article ↗