Artículos Destacados

Estos artículos no son de mi autoría. Son contenidos destacados de diversas fuentes que comparto por su valor informativo. Todos los créditos pertenecen a sus respectivos autores y publicaciones originales.

My Model Worked Perfectly. Then I Tried to Make It Useful.
· 11 min read

My Model Worked Perfectly. Then I Tried to Make It Useful.

Turning a trained churn classifier into a FastAPI service that other software can actually call.

Por Ibrahim Salami · Machine Learning
Tables in PDFs for RAG: Don’t Flatten the Grid
· 19 min read

Tables in PDFs for RAG: Don’t Flatten the Grid

Enterprise Document Intelligence [Vol.1 #B4] - A diagnostic and five composable operations, not a decision tree

Por Kezhan Shi · Large Language Models
Changing One Prompt Can Affect 50 Others — I Built a Prompt Dependency Graph to Find What Needs Retesting
· 20 min read

Changing One Prompt Can Affect 50 Others — I Built a Prompt Dependency Graph to Find What Needs Retesting

I built a prompt dependency graph that separates everything a component can reach from the smaller set that actually needs targeted evaluation.

Por Emmimal P Alexander · Prompt Engineering
How to Solve the Right Problem in the Age of Agentic AI
· 13 min read

How to Solve the Right Problem in the Age of Agentic AI

A practical framework for reducing uncertainty before agents accelerate implementation

Por Mike Huls · Software Engineering
Avoiding Entity Key Drift in a Data Lake: Step 2, When Fuzzy Matching Stops Working
· 23 min read

Avoiding Entity Key Drift in a Data Lake: Step 2, When Fuzzy Matching Stops Working

I built a matcher meant to finish the cleanup that normalization left behind. Testing it against real data showed that no version of it could be made safe. What follows is the architecture that was left once the matcher was set aside.

Por Rahul Saha · Data Engineering
A RAG That Says “Not in This Document” Has to Show Four Kinds of Evidence
· 14 min read

A RAG That Says “Not in This Document” Has to Show Four Kinds of Evidence

Enterprise Document Intelligence [Vol.1 #B3] - A confident wrong answer is a bug. A bare “no answer” with no justification is almost as bad. Each of the four bricks has one piece of evidence to show

Por Kezhan Shi · Large Language Models
Graph Neural Networks: GCN, MPNN, and GAT, Explained Simply
· 11 min read

Graph Neural Networks: GCN, MPNN, and GAT, Explained Simply

A visual guide to how graph neural networks work under the hood

Por Slava Efimov · Machine Learning
A Practical Introduction to PySpark Window Functions
· 16 min read

A Practical Introduction to PySpark Window Functions

Why the standard groupBy function isn’t enough

Por Thomas Reid · Data Engineering
Your JSON Is Valid but Your Data Is Wrong: Five Failure Modes LLM Structured Outputs Won't Catch
· 9 min read

Your JSON Is Valid but Your Data Is Wrong: Five Failure Modes LLM Structured Outputs Won't Catch

Five failure modes that survive constrained decoding, and why your schema validator will never catch them.

Por Mostafa Ibrahim · Large Language Models
What We Miss About Missing Values
· 10 min read

What We Miss About Missing Values

The hidden assumptions behind the data we observe.

Por David Conneely · Statistics