Games & Play3 weeks ago · 8 tries
KarolBuilds: ridiculous AI projects
Playable collection of small, absurd AI projects, each taking about ten seconds
@KarolBuilds · X
My AI slop at is so underrated that I’m the only visitor.
The full gallery
Tech stack
20 projects
Playable collection of small, absurd AI projects, each taking about ten seconds
@KarolBuilds · X
My AI slop at is so underrated that I’m the only visitor.
Create professional pixel art sprites and icons with AI, then edit and export them in your browser.
hugodpz · Product Hunt
AI Pixel Art Generator The professional AI pixel art generator for game developers
Play an infinite runner game set in London with three.js 3D graphics.
@Killianlynchh · X
I spent the entire flight back to London from NYC vibe coding an infinite runner three.js game my high score is 14863 I built and hosted the entire thing for free using The whole game was built with a prompt i put on my Github
Play real tennis using your body and webcam with no controllers needed.
@AkhilMatta29342 · X
Free unblocked browser shooting game with arcade-style action.
Funny Shooter 2 — enjoy unblocked shooting games for free! Dive into exciting gun games with funny shooting action. Perfect for shooter game fans!
Hunt targets with a bow in an arcade-style game.
@spt4d · X
Deployed the 16 games built with Codex and GameBlocks. A few examples: Most of my time is actually spent shaping the player experience. Many ideas emerge through playing and exploration rather than from the initial design — the loop seems to be build → play → discover → improve. Is it possible to build an agent harness that supports this discovery loop — not just one that optimizes against a predefined spec? Full game list:
Race through 3D cube environments in this arcade game.
@dominguezdaniel · X
Play here! 🏎️ Built with Codex. Powered by Three.js. Deployed on Vercel.
Play 16 arcade games in Mech Arena
@spt4d · X
Deployed the 16 games built with Codex and GameBlocks. A few examples: Most of my time is actually spent shaping the player experience. Many ideas emerge through playing and exploration rather than from the initial design — the loop seems to be build → play → discover → improve. Is it possible to build an agent harness that supports this discovery loop — not just one that optimizes against a predefined spec? Full game list: