-
Looking under the hood for Power BI Copilot
Power BI Copilot doesn’t document how it processes questions internally. The closest that I’ve found is in Microsoft Learn (below). I’m writing what I’ve found using Copilot’s diagnostic JSON across three environments, Desktop, Power BI Service (not edit mode), and the sidebar Copilot in Power BI. I spent a weekend setting up a Fabric F2…
-
When the Model Isn’t the Answer
If you stare at any two datasets long enough, you can convince yourself there’s a connection between them. Not because there is, but because there is an important enough question that the data “should” be connected. It’s a dangerous place from which to start a modeling project. This is one such story. Enter multi-instance-learning, and…
-
The Boring Part of Machine Learning Nobody Wants to Talk About
I’ve been getting more into vision analytics, private, professional, everywhere. My usual approach for solving problems is to learn a tool, understand conceptually what it does, check my back catalog of problems I couldn’t solve and see if that tool or approach helps. Vision analytics is no different. I’ve also applied this to document classification…
-
Training a Neural Net to Find Puss in Boots
I want to fine-tune an image generation model on Puss in Boots. That means I need 50 to 100 good stills of the character. The movie is 98 minutes long. I am not going to sit there and screenshot by hand. So I trained a binary classifier to do it for me, wired it up…
-
Making Tempeh: An Unreasonably Thorough Approach
I have had so much trouble making tempeh. Crumbly, inconsistent results, batch after batch. So I decided to go clinical — document every step, measure every variable, and remove every excuse.