Introducing the state-of-the-art SPEED agentic architecture and speed-core, a fully open-source AI architecture designed to do everything: be fast, be smart, be secure, be reliable, and be easy to use on critical systems. Above all, speed-core was designed with one goal in mind: be reliable enough that you would trust it enough to launch a […]
Introducing speed-core Read More »
I am mostly here to brag a bit. I’m so proud of myself. For what? For making some SVGs. Icons to be exact, for my AutoTS forecasting project to use as launch icons for any associated apps. And to be fair, Claude and Codex did most of the heavy lifting on making the SVG code,
I actually want to live in the beating heart of the city, and not flee into the dull suburbs like so many do. But the city really does have crime issues, and no one wants to raise their kid in a neighborhood where drive by shootings occur. Somewhere between the multimillion dollar homes on the
A Twin Cities Crime Map Read More »
In the last several weeks, I have felt something. Not the ground shifting, it was already doing that, more a sense of certainty that yes this really will happen. The combination of the latest large language models with maturing agentic pipelines (often using MCP servers) mean that human level performance (or better) is achievable quickly
Predictions for an AI Future, Now Read More »
“AI” models tend to be slow. This is generally inevitable to a large degree, lots of calculations to do means more time to run. Simply throwing more compute at the problem is one solution, but limits the ability to run models “at the edge” (ie on a phone) and raises the cost. Another solution is
Testing Quantization of Image Classifiers Read More »
Visiting the town of Lugo, which claims to have the most intact/unmodified set of Roman city walls (Muralla Lugo) surviving, I was struck by a picture I saw showing how the towers used to have arched upper levels that reminded me of the Porta Nigra in Trier. I thought that the towers would really have
AI Rendering of Archeology, the Walls of Lugo Read More »
In the world of forecasting there is a bit of mystery. Many expert forecasters continue to use statistical models despite the strong push of machine learning (ML) and deep learning neural network (NN) models. Those less familiar with the world of forecasting assume, because of the dominance of ML/NN models in computer vision and language
Forecasting: Are ML Models ‘Winning’ Because of Less Preprocessing Needs? Read More »
The Coral Dev Board (2019), Dev Board Mini (2020) and Dev Board Micro (2023) are almost really awesome. They were really the first products to make running Edge AI operations feasible, the product of Google’s own development of products like it’s smart speakers and smartphones. On the positive side, Google hasn’t killed them yet like
Using the Coral Dev Board in 2025 Read More »
I have been racing bikes since my early teens. Cycling is a really fun sport, but having suffered no less than three concussions crashing in criterium racing, and also having been hit twice by cars while training, I have moved away from the sport a bit. I tried triathlons, but don’t like swimming enough to
A Duathlete in the Wind Tunnel Read More »
Demand forecasting is exactly how it sounds: forecasting demand. This can take many forms but the most classic example is predicting how many products will be sold by a retailer on each particular day. This forecasting is in turn used to drive business value in various ways. The most common is better inventory management, but
A Different Look at Intermittent Demand Forecasting Read More »
