# AI Builds

- Link: https://arqiv.si/ai-builds/
- Published: 2026-10-05T21:03:39-04:00
- Author: Steven Ryan

[Skip to content](https://arqiv.si/ai-builds/#main-content)

[arqiv](https://arqiv.si/)

[For educators](https://arqiv.si/teachers/)

Teach

 * [Start here](https://arqiv.si/teachers/)
 * [Lessons & printable kits](https://arqiv.si/teachers/resources/)
 * [Classroom labs](https://arqiv.si/teachers/labs/)
 * [Free 20-minute lesson](https://arqiv.si/teachers/free-ai-lesson/)

Plan

 * [Curriculum guide](https://arqiv.si/teachers/curriculum/)
 * [AI Learning Center](https://arqiv.si/teachers/ai-literacy/)
 * [Future of work unit](https://arqiv.si/future-of-work/)
 * [What the research says](https://arqiv.si/teachers/what-works/)
 * [AI education worldwide](https://arqiv.si/teachers/around-the-world/)

Understand

 * [Think First method](https://arqiv.si/teachers/think-first/)
 * [Our approach](https://arqiv.si/research/#our-method)
 * [AI vocabulary](https://arqiv.si/teachers/ai-vocabulary/)

By role

 * [Counselors](https://arqiv.si/counselors/)
 * [School leaders & PD](https://arqiv.si/schools/)
 * [Speaking & workshops](https://arqiv.si/speaking/)
 * [Products](https://arqiv.si/products/)

[Learn AI](https://arqiv.si/ai/topics/)

Start

 * [All AI topics](https://arqiv.si/ai/topics/)
 * [The AI journey, from zero](https://arqiv.si/ai/)
 * [Using AI well](https://arqiv.si/ai/talking-to-ai/)
 * [AI builds](https://arqiv.si/ai-builds/)

AI in the world

 * [Space](https://arqiv.si/space/)
 * [Weather](https://arqiv.si/weather/)
 * [Health](https://arqiv.si/health/)
 * [Engineering](https://arqiv.si/engineering/)
 * [Farming](https://arqiv.si/farming/)
 * [Quantum](https://arqiv.si/quantum/)

What it means

 * [Future of work](https://arqiv.si/future-of-work/)
 * [Your AI path](https://arqiv.si/ai/your-path/)
 * [Research, explained](https://arqiv.si/research/)

[Games & labs](https://arqiv.si/games/)[Research](https://arqiv.si/research/)[Blog](https://arqiv.si/blog/)
[About](https://arqiv.si/about/)

[Search or ask](https://arqiv.si/ai/topics/)[Newsletter](https://arqiv.si/newsletter/)
[ARQIV.FM ↗](https://arqiv.fm/)

Menu

For educators

[For educators: start page →](https://arqiv.si/teachers/)

Teach

 * [Start here](https://arqiv.si/teachers/)
 * [Lessons & printable kits](https://arqiv.si/teachers/resources/)
 * [Classroom labs](https://arqiv.si/teachers/labs/)
 * [Free 20-minute lesson](https://arqiv.si/teachers/free-ai-lesson/)

Plan

 * [Curriculum guide](https://arqiv.si/teachers/curriculum/)
 * [AI Learning Center](https://arqiv.si/teachers/ai-literacy/)
 * [Future of work unit](https://arqiv.si/future-of-work/)
 * [What the research says](https://arqiv.si/teachers/what-works/)
 * [AI education worldwide](https://arqiv.si/teachers/around-the-world/)

Understand

 * [Think First method](https://arqiv.si/teachers/think-first/)
 * [Our approach](https://arqiv.si/research/#our-method)
 * [AI vocabulary](https://arqiv.si/teachers/ai-vocabulary/)

By role

 * [Counselors](https://arqiv.si/counselors/)
 * [School leaders & PD](https://arqiv.si/schools/)
 * [Speaking & workshops](https://arqiv.si/speaking/)
 * [Products](https://arqiv.si/products/)

Learn AI

[Learn AI: start page →](https://arqiv.si/ai/topics/)

Start

 * [All AI topics](https://arqiv.si/ai/topics/)
 * [The AI journey, from zero](https://arqiv.si/ai/)
 * [Using AI well](https://arqiv.si/ai/talking-to-ai/)
 * [AI builds](https://arqiv.si/ai-builds/)

AI in the world

 * [Space](https://arqiv.si/space/)
 * [Weather](https://arqiv.si/weather/)
 * [Health](https://arqiv.si/health/)
 * [Engineering](https://arqiv.si/engineering/)
 * [Farming](https://arqiv.si/farming/)
 * [Quantum](https://arqiv.si/quantum/)

What it means

 * [Future of work](https://arqiv.si/future-of-work/)
 * [Your AI path](https://arqiv.si/ai/your-path/)
 * [Research, explained](https://arqiv.si/research/)

 * [Games & labs](https://arqiv.si/games/)
 * [Research](https://arqiv.si/research/)
 * [Blog](https://arqiv.si/blog/)
 * [About](https://arqiv.si/about/)

[Get the newsletter](https://arqiv.si/newsletter/)

AI builds

# What people are _building with AI_

People now describe an idea in plain words and get working software back: small 
tools, websites, even games. The two arcade games below were made that way. They
are short samples, three levels each, built to show what is possible. Further down,
see how scientists used AI to discover new physics, and explore a 3D building.

[Play Neon Muncher ↓](https://arqiv.si/ai-builds/#muncher)[Play Nova Invaders →](https://arqiv.si/ai-builds/#nova)
[AI finds new physics →](https://arqiv.si/ai-builds/#plasma)[Explore a 3D building →](https://arqiv.si/ai-builds/#house)

 1.  **01**
 2.  
     ### Describe it
     
 3.  A person wrote a few sentences: a maze chase and a space shooter, colorful and
     modern, a few levels each.
 4.  **02**
 5.  
     ### AI writes it
     
 6.  An AI model wrote the code, drew the characters, and designed the levels and rules.
 7.  **03**
 8.  
     ### Test and tune
     
 9.  The games were tested in a browser and tuned to work with a keyboard on a computer
     and touch on a phone.

Score**0**Level**1/3**Lives**3**Best**0**

Game one · Maze chase

### Neon Muncher

Eat every dot. Grab a glowing orb to turn the tables on the ghosts.

This game needs JavaScript turned on.

Arrow keys or WASD to move · P or Esc to pauseSwipe the board or tap the arrows 
to move · Pause is at the top right

 Built with AI

Game one · Maze chase

## Neon _Muncher_

A maze-chase game in the spirit of the arcade classics, redrawn in glowing neon.
Clear the board of dots while four ghosts hunt you down.

 * **Glowing orbs** turn the ghosts blue for a few seconds. Catch them for 200, 
   400, 800 and 1,600 points.
 * **Each ghost hunts differently.** One chases you, one cuts you off, one flanks,
   and one keeps its distance.
 * **Three levels.** Each level has its own maze and color. The ghosts get faster
   and the orbs wear off sooner.
 * **Side tunnels** wrap around, and ghosts slow down inside them.

Score**0**Wave**1/3**Lives**3**Best**0**

Game two · Space shooter

### Nova Invaders

Hold the line. Clear three waves before the fleet reaches the ground.

This game needs JavaScript turned on.

Arrow keys or A / D to move · Space to fire · P or Esc to pauseHold the arrows to
move · hold FIRE to shoot · Pause is at the top right

 Built with AI

Game two · Space shooter

## Nova _Invaders_

A fixed-screen shooter inspired by the original space invaders, rebuilt with glowing
alien designs, a drifting starfield and a nebula sky.

 * **The fleet speeds up** as it shrinks, and it drops closer each time it hits 
   the edge. If it reaches the ground you lose a life and the fleet pulls back to
   the top.
 * **Four shields** crumble cell by cell, from your shots and from theirs.
 * **A mystery saucer** crosses the top now and then. Hit it for up to 300 points.
 * **Three waves.** Each one fires faster, and wave three brings armored scouts 
   that take two hits.

AI in real research · Emory University

## AI watched glowing dust _and found new physics_

Games are a fun demo. Scientists are using the same kind of tool for discovery. 
At Emory, physicists trained an AI on the movements of dust grains floating in a
plasma, and it uncovered forces that theory had gotten slightly wrong.

Our animation, modeled on the [Burton lab's tracking video](https://news.emory.edu/sites/emorynews/files/shorthand/stories/tfhj8Ti1wS/2025-07-31T19%3A31%3A45.585Z/assets/ibCnPg87re/burton_tracking-na-960x540.webm).
It is a simplified simulation, not lab footage. The blue and yellow arrows follow
two grains, as in the original. Turn on **Show forces** to see the one-way push 
and pull the AI measured.

 Animation built with AI · Science by Emory University

 1.  **01**
 2.  
     ### The experiment
     
 3.  A dusty plasma is an electrically charged gas with tiny solid grains floating 
     in it. It is common in space, from planetary rings to comet tails. The Burton 
     lab built a way to film a cloud of plastic grains and track the 3D motion of every
     single one.
 4.  **02**
 5.  
     ### The AI
     
 6.  Instead of a black box, the team built a neural network with physics written into
     it: gravity, drag from the gas, and forces between grains. Fed the tracked paths,
     its model fit the measured grain accelerations very closely (a goodness-of-fit
     score, R², above 0.99). That is not the same as every force being 99% accurate:
     the researchers separately checked the forces it inferred, which had average errors
     below 10% in their tests, and new lab runs then checked what it found.
 7.  **03**
 8.  
     ### The discovery
     
 9.  The forces are one-way. A leading grain pulls the one behind it closer, but the
     trailing grain pushes the leader away, like two boats where each wake acts differently.
     The AI also showed that a grain's charge and its range of influence depend on 
     its size in ways the standard theory did not expect.

Sources: [Emory News: AI reveals unexpected new physics in dusty plasma](https://news.emory.edu/features/2025/07/esc_ai_dusty_plasma_30-07-2025/index.html)·
[Yu, Abdelaleem, Nemenman and Burton, PNAS (2025)](https://www.pnas.org/doi/10.1073/pnas.2505725122)·
[free preprint on arXiv](https://arxiv.org/abs/2310.05273)

Build three · Interactive 3D model

## Prism House, _a building you can explore_

AI image tools often produce pale, glassy architecture renderings like a ghostly
blueprint. We took that idea, turned up the color and made it something you can 
move around in. Spin the building, look inside any of its five rooms and landscape
the lot.

Loading the 3D model…

Drag to rotate · click the model once to turn on scroll zoom · then click a room
to look insideSwipe sideways to rotate · tap the model once to turn on pinch zoom·
then tap a room

View

Zoom into a room

Add plants · 0 / 5

Pick a plant, then click or tap the green lawn. On a keyboard, the arrow keys move
a ring on the model and Enter plants. Up to five plants.

 Built with AI

Everything on this page runs in your browser. You do not need an account, and the
games and the 3D model send nothing to a server. Your best scores are kept only 
on this device. The 3D building uses the free, open-source Three.js library, loaded
from the cdnjs network when you scroll to it. These are short sample builds made
with AI, not finished products: they show how quickly a working idea can be built
when you describe it clearly.

Put curiosity to work

## Read it. Try it. Question it.

Learn how the AI behind builds like these actually works, then try it yourself.

[How AI works →](https://arqiv.si/ai/)[Using AI well →](https://arqiv.si/ai/talking-to-ai/)
[Make your first agent skill →](https://arqiv.si/ai/how-agents-are-built/#build)

[arqiv](https://arqiv.si/)

A little understanding changes everything.

[LISTEN: ARQIV.FM, OUR WEEKLY SHOW ↗](https://arqiv.fm/)

Educators

 * [Start here](https://arqiv.si/teachers/)
 * [Lessons & kits](https://arqiv.si/teachers/resources/)
 * [Curriculum](https://arqiv.si/teachers/curriculum/)
 * [Labs](https://arqiv.si/teachers/labs/)
 * [AI vocabulary](https://arqiv.si/teachers/ai-vocabulary/)

For your role

 * [Counselors](https://arqiv.si/counselors/)
 * [School leaders & PD](https://arqiv.si/schools/)
 * [Speaking & workshops](https://arqiv.si/speaking/)
 * [Products](https://arqiv.si/products/)

Learn

 * [Learn AI](https://arqiv.si/ai/topics/)
 * [Games & labs](https://arqiv.si/games/)
 * [Future of work](https://arqiv.si/future-of-work/)
 * [Research](https://arqiv.si/research/)
 * [Headlines](https://arqiv.si/news/)

ARQIV

 * [About & corrections](https://arqiv.si/about/)
 * [Our approach](https://arqiv.si/research/#our-method)
 * [Newsletter](https://arqiv.si/newsletter/)
 * [Privacy](https://arqiv.si/privacy-policy/)
 * [Get in touch](https://arqiv.si/ai-builds/info@arqiv.fm)

Classroom activities collect no student data.[info@arqiv.fm](https://arqiv.si/ai-builds/info@arqiv.fm)
