AI & ML

I asked 5 AI models whether AI is making humanity weaker. All 10 said weaker. Then evidence entered the room.

I run an experiment series on my own AI setup: same model, same task, two isolated runs — one bare, one wrapped in the operating rules my harness en…

I invented a word and I'm racing to make it rank

I invented a word that has never existed — florbnoodle — and I'm running a tiny experiment to see how fast I can get it to rank #1 on Google, with n…

Four Levels Down: I Published a Finding and Broke It Twice in Thirty-Six Hours

Yesterday I published a piece called Choice Leaks . I wrote down 100 digits by hand, trying to be random, then measured them against 2,000 sequences…

XML Tags Don't Help Short Prompts — Here's When They Actually Matter (2026)

The Conventional Wisdom Every prompt engineering guide says the same thing: wrap your prompt sections in XML tags. <instructions> , <schema…

I Let AI Run My Code Reviews for 30 Days - The Results Shocked Me

On March 3, 2026, I connected a custom agentic pipeline to our team GitHub repository. I gave it read access to pull requests, diff outputs, and our…