Machine Learning
Google expands Alabama data center campus, funds community efforts
June 15, 2026
Google expands Alabama data center campus, funds community efforts
Google announced a $1.5 billion investment in 2026 and 2027 to expand its data center campus in Jackson County, Alabama.…
Protocol Cleansing Our Agent Architecture
June 15, 2026
Protocol Cleansing Our Agent Architecture
A few weeks ago someone from the data team asked if we could update the database schema that was being…
I Built 11 Models to Predict the 2026 World Cup. They Crown Four Different Champions.
June 15, 2026
I Built 11 Models to Predict the 2026 World Cup. They Crown Four Different Champions.
World Cup, 104 matches, and roughly as many confident predictions as there are fans. Building a model that announces “Team…
The System Always Knows: Why Local Efficiency and System Performance Are Not the Same Problem
June 15, 2026
The System Always Knows: Why Local Efficiency and System Performance Are Not the Same Problem
Dietrich Braess described a result that still feels wrong the first time you hear it: adding a road to a…
4 Lines You Should Include in Your Claude Skill
June 14, 2026
4 Lines You Should Include in Your Claude Skill
I was asked to do something new at work: Given the data dump of unstructured text data, we have provided…
Vision LLMs are PDF Parsers Too: Reading Charts and Diagrams for RAG
June 14, 2026
Vision LLMs are PDF Parsers Too: Reading Charts and Diagrams for RAG
companion in Enterprise Document Intelligence, the series that builds an enterprise RAG system from four bricks. Article 5 (document parsing)…
GPU Time-Slicing for Concurrent LLM Agents on Kubernetes
June 14, 2026
GPU Time-Slicing for Concurrent LLM Agents on Kubernetes
. Production agents fight over the same GPU — and on one shared card, a latency-sensitive agent’s p99 latency quietly…
Larger Context Windows Don’t Fix RAG — So I Built a System That Does
June 13, 2026
Larger Context Windows Don’t Fix RAG — So I Built a System That Does
TL;DR I built a dataset Q&A system and trusted a RAG answer that was less than half-correct. I measured this…
Parse PDFs for RAG Locally with Docling: Rich Tables, No Cloud Upload
June 13, 2026
Parse PDFs for RAG Locally with Docling: Rich Tables, No Cloud Upload
companion in Enterprise Document Intelligence, the series that builds an enterprise RAG system from four bricks. Article 5 (document parsing)…
Solving the 3Blue1Brown String Probability Problem (Without AI)
June 13, 2026
Solving the 3Blue1Brown String Probability Problem (Without AI)
a stupid chance problem solving problem in my free time when I could be scrolling through doom? Because I'm trying…