Exhibit · 2025
Pattern & Prediction
Nine learning algorithms, one game
Rock-paper-scissors looks like a game of pure chance. It isn't.
"Pattern & Prediction" is a generative-AI exhibit built in 2025. Visitors play rock-paper-scissors against an AI opponent that gets smarter with every round. Not smarter in a general sense. Smarter about you specifically: your tendencies, your tells, the decisions you make when you're winning and when you're losing.
Nine learning algorithms run in parallel underneath. Each approaches prediction from a different angle. One tracks sequences and asks whether this player tends to follow scissors with rock. Another monitors win-stay/lose-shift (the unconscious tendency, which most players have and most players deny, to repeat a winning move or abandon a losing one). A third builds a statistical map of preferences across situations. All nine watch every round, update independently, then collaborate: they share predictions, weigh each other's track records, and commit to the next move.
The result is an opponent that gets harder to beat the longer you play. That shift is the exhibit.
Visitors who open the internal-reasoning view can watch this happen in real time. Their moves become patterns. Patterns become probabilities. Probabilities become predictions. Most visitors try to beat the system by randomising: switching strategies, deliberately mixing up their choices. What they find is that the attempts to be unpredictable are themselves predictable. The system learns those too.
That's the moment the piece is after. Given enough data, algorithms don't model groups; they model individuals. The shadow self the exhibit describes isn't metaphor. It's the model the system has built of you after thirty rounds.
The meta-layer
Claude Code helped build the exhibit. That felt right. An AI system contributed to creating a work about AI systems learning from human behaviour. Claude Code suggested the ensemble architecture: the way nine independent models share information and re-weight each other's predictions based on past performance. It contributed to the conceptual framework, not just the implementation.
Working with it had the same texture the exhibit explores. I'd describe what I wanted; Claude Code would suggest directions I hadn't considered. The system took shape through that back-and-forth. Making it was part of understanding what it was about.
Technical notes
The ensemble uses Markov chain sequence prediction, Bayesian probability modelling, and several reinforcement-learning variants. No single algorithm dominates; the weighting updates after each round so the system's composition adapts to the player in front of it.
The exhibit is currently offline, being migrated from Heroku to Railway.