Every four years, my friend group runs a World Cup pool. The format is simple: everyone gets randomly allocated a bunch of countries, and you earn points as your countries progress through the tournament. The more games your countries win, the more points you accumulate, until eventually someone’s Argentina or France makes it to the final and that person becomes insufferable about it for the next four years. This year I decided to build a website for it.

I am not a sports analyst. I don’t have insider knowledge of team sheet dynamics, injury recovery timelines, or the subtle psychological impact of playing a Thursday night game in Canberra in July. What I do have is Claude, a Python environment, and a dangerous amount of free time. The result is nrl-predictor.ohare.id.au — an AI-powered NRL match predictor that publishes its picks every week and, crucially, publishes its accuracy record even when it’s wrong.

My wife bought me a Huski Beer Cooler 2.0. It’s a stainless steel can insulator — the kind of thing you slip your can into so your beer (or Coke, if you’re me during this experiment) stays cold. Now, I’m a developer. I don’t take things on faith. I take them on data. And the question burning in my mind was: does this thing actually do anything? My wife’s answer: “Yes, obviously, it’s insulated.