Machine Learning
Google Finance Updates: New app, portfolios
1 week ago
Google Finance Updates: New app, portfolios
Investing is complicated, but staying informed doesn't have to be. Starting this week, the new Google Finance is coming out…
3 Agents. 3 LLMs. 1 Aging GPU: Engineering Parallel Inference on Bare Metal
1 week ago
3 Agents. 3 LLMs. 1 Aging GPU: Engineering Parallel Inference on Bare Metal
agents using three different LLMs. You have one ancient GPU and you are too poor to upgrade. You need to…
Letting an LLM Pick the Right RAG Page: The Arbiter Pattern at the End of Retrieval
1 week ago
Letting an LLM Pick the Right RAG Page: The Arbiter Pattern at the End of Retrieval
of Enterprise Document Intelligence, a series that builds an enterprise RAG system from four bricks: parsing, question parsing, retrieval, and…
One Month Into Public Learning Data Engineer: Here's What I Didn't Write
2 weeks ago
One Month Into Public Learning Data Engineer: Here's What I Didn't Write
I went to someone on LinkedIn I'd never met, asking what he thought was the best way to do data…
How to Build a Credit Grid From an Asset Amortization Model
2 weeks ago
How to Build a Credit Grid From an Asset Amortization Model
All code used in this article is available on GitHub. The business logic and modeling functions are available in src/selection…
Your First Job as a Data Engineer at a New Company? Make the ETL Pipeline Testable
2 weeks ago
Your First Job as a Data Engineer at a New Company? Make the ETL Pipeline Testable
joining a new company as a data engineer. You inherit several ETL pipelines and are responsible for maintaining them. What…
Three-Stage True Recall Cycle in Gemma-2B and Gemma-12B-IT
2 weeks ago
Three-Stage True Recall Cycle in Gemma-2B and Gemma-12B-IT
models that represent true knowledge within? This post presents BizzaroWorld, a machine learning experiment that attempts to localize fact-remembering circuits…
Why I Stopped Using One Agent and Built a Multi-Agent Pipeline Instead
2 weeks ago
Why I Stopped Using One Agent and Built a Multi-Agent Pipeline Instead
we developed a text-to-SQL application. It was a simple one-agent architecture that takes a user query in natural language and…
Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End
2 weeks ago
Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End
brick of Enterprise Document Intelligence, a series that builds an enterprise RAG system from four bricks: parsing, question parsing, retrieval,…
How to Create Dynamic Loops in Claude Code
2 weeks ago
How to Create Dynamic Loops in Claude Code
A very popular topic is coding agents lately. Loops are a concept where you have an agent that acts autonomously…