EGU’26, When Climate Hazard Granularity Challenges Risk Pooling: A Spatial Perspective
An economist writes: “the fulminations over the #1 pick seem overheated to me.”
The Magic of In-Context Learning (ICL): When Your Model Already Knows Your Data
Have you ever looked at a freshly plotted scatter plot and immediately thought, “Ah, this is clearly a logarithmic curve with some heteroskedastic noise,” without running a single line of modeling code? How do you do that? You don’t perform gradient descent in your head. You use your intuition! …
Continue reading: <a href=“https://www.r-bloggers.com/2026/05/the-magic-of-in-context-learning-icl-when-your-mode …
Reflections on AI-assisted Programming
My former colleague Nan kept telling me early last year that I should try Cursor, but I felt I didn’t need AI assistance at that time, since I knew pretty well what I wanted to do and how. Plus, I’m generally frugal and would hesitate to purchase anything extra for myself.
GitHub has offered the Copilot Pro plan (300 premium requests per month) to me for free since last year because I maintain several popular repositories, but I had rarely used it until this year, when I kept hearing that Claude Opus 4.6 was amazing. Well, I thought to …