Local AI: why, what, how
Why A year ago, I was convinced that running AI locally on consumer hardware would never be useful or cost-effective. The gap between frontier models and local models was too wide, and closing it was
Symbols AI Research
Latest articles
Manus nobis Man
Manus was a China-based AI agent system designed to tackle more complex projects than typical chatbots that was acquired by Meta. Each instance ran in its own Ubuntu virtual machine. After giving it a
Interactive Hiking Maps with Datasette and Google Cloud
I created an interactive map of my hikes using the powerful Datasette tool by Simon Willison. The result was an intuitive, easy-to-use map that links each hike to a full report on my blog. Many interesting technologies are at play. The underlying dat...
Predicting gold prices with SARIMAX
I had a little fun with data from the St. Louis Fed (FRED). Note: not investment advice I collected 54 years of gold price data starting 9/30/71 (end of the US federal government fiscal year after gold was allowed to float). I also collected the 10-y...
Evolving an 8 Queens solution with PyGAD
PyGAD is a python library implementing a genetic algorithm to solve problems. It was created by Ahmed Gad (many thanks!). Complete docs are here. One of the examples used to demonstrate the library is the 8 Queens problem. This was my solution using ...
Running Nvidia's new ChatWithRTX AI
Nvidia just released a beta application for Windows called ChatWithRTX. It uses a local LLM to chat offline with your own files (currently .txt, .pdf, and .doc). The system requirements are Windows 11 and an Nvidia 30xx or 40xx video card with at lea...
Small Beginnings
My interest in AI goes back to the start of my career in (ugh) 1985. The IBM PC had just become a thing, but I was programming on a mainframe. In the early 90s, I toyed with "expert systems", poorly performing knowledge bases. Neural networks had wel...