AN EAT. SHIFT. OR DIE. EXPERIMENT
Quite a lot
of artificial
confidence.
Tap one. Claude has opinions.
Phil built a racing model with AI.
The horses remain unconvinced.
what happened
Learning about AI.
With horses.
Obviously.
What happens when you stop talking about AI and actually build something with it?
This is Phil’s answer. A racing model, a growing list of lessons, and a public record of the calls that worked. And the ones that didn’t.
The story so farPart of Eat. Shift. Or Die. An experiment in using AI and knowing when to question it.
24 ILLUSTRATED CHARACTERS / ONE RACE
Meet the
usual suspects.
Mr Monaco
Loading Claude’s saved commentary…
Illustrated editorial draft. Names, numbers and commentary await final field reconciliation. These are not published Cup predictions.
Prefer your own highly scientific method?
Shuffle the deck. Deal me three.How did
we actually do?
The calls stay where we made them.
So do the misses.
Loading the verified race ledger…
Pick a race to see the frozen selections and who actually won.
R1 excluded from scoring. Final results only. These counts describe a small historical sample; they are not a promised success rate. “In the four” is not the same as picking the winner first.
What changed in the model?
THE HORSES ARE ONLY ONE CHAPTER.
What will you
do with AI?
What it makes possible. Where it lets you down. And what you still have to decide.
Discover Eat. Shift. Or Die.