When the Chart Is Just Wrong; What a Market Cap Visualization Taught Me About Iterating with AI
I started with what seemed like a simple ask, a scatterplot comparing the largest US companies by market cap in 2005 versus 2025, with tech companies in one color and everything else in another. What I got instead was a master class in what productive iteration with an AI tool actually looks like...
The Instructions That Held, The Ones I Had to Keep Repeating, and the One That Taught Itself (Perhaps a 'Persuasion Bomb'?)
A few months ago I published a piece on using custom instructions to reduce hallucinations in AI research. What I didn't anticipate was how differently that protocol would behave depending on where the instructions lived, how I delivered them, and what happened when a tool decided on its own that I wasn't going to settle for guessing.
When AI Data Extraction Becomes More Work Than Doing It Manually
The promise: AI will automate tedious tasks like extracting data from PDFs into spreadsheets.
Data Science Deep Dive: Analyzing 3 Years of Peloton Data with Gemini 2.5 Flash
For today's GenAI experiment, I fed Gemini 2.5 Flash my personal three-year Peloton workout history, a 1,351 row CSV file and asked it to diagnose the factors behind my longest training breaks.
The Day Peloton Forgot My Run (and GPT 5 Rebuilt It from Disconnected Data Sources)
When your fitness app fails, AI can still finish the story.