Skip to content

Note

August 11, 2026

1 min read

Skip the Lecture and Play Darts

By Cristiano Pierry

A neural-network lesson became a standalone 3D darts game because explanation and play do different jobs.

ailearningprototypingeducation

I built a 44-page presentation to explain how neural networks learn. Then I added a button that says: “Skip the lecture and let’s play darts!”

That may be the most honest decision in the whole project.

Dart Room began as a playable companion to Learning to Aim, a neural-network lesson built around a robot learning to throw a dart. The lesson can explain targets, inputs, loss, and adjustment. The game gives those ideas a physical counterpart: choose a target, throw, see where it lands, and try again.

It could have remained a small demo. Instead, it became its own 3D browser game. It now supports Count Up, 301, and Cricket, with solo, local two-player, and CPU matches. It works with a pointer, keyboard, and touch screen. It also includes reduced-motion support, focus management, and live scoring announcements. There is no login, download, or backend.

The interesting part for me is not that a presentation grew a game. Explanation and play do different jobs. A slide can describe a feedback loop. A game lets someone feel one.

Sometimes the quickest way into a technical idea is to stop explaining it and give people something to aim at.


This writing reflects my personal perspectives on product management, AI, and content discovery. It does not represent the official position of my employer or any affiliated organization.