Race in Cubes launches 3D voxel racing

// 2h agoPRODUCT LAUNCH

Race in Cubes launches 3D voxel racing

Race in Cubes is a browser-based 3D voxel racing game built using OpenAI's Codex and Three.js, deployed on Vercel. The game features physics-based vehicle steering, collision handling against computer-controlled rivals, responsive mobile touch controls, and a lap-tracking HUD.

// ANALYSIS

A neat showcase of AI-assisted game development that demonstrates how Codex can generate complex, interactive WebGL applications.

* Single-File Implementation: The complete game structure, styling, rendering, and logic are fully self-contained.

* Responsive Design: Integrated virtual touch controls make it instantly playable on mobile screens.

* Interactive Mechanics: Includes basic vehicle physics, collision handling with walls and rivals, and track bounds constraints.

// TAGS

three.jscodexgamewebgljavascriptvercel

DISCOVERED

2h ago

2026-07-06

PUBLISHED

2h ago

2026-07-06

RELEVANCE

6/ 10

AUTHOR

dominguezdaniel

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH39m ago

Anthropic reveals Claude silent reasoning J-space

Anthropic has published research revealing the 'J-space' in Claude, an internal neural structure analogous to the brain's global workspace that enables silent, multi-step reasoning. Existing in internal activations rather than text outputs, the J-space offers new tools for auditing model alignment and detecting hidden goals.

NEWS41m ago

Meta Trains Llama 5 Codenamed Watermelon

Meta is reportedly prepping its next massive frontier model to compete directly with OpenAI. Codenamed Watermelon and believed to be Llama 5, the model is currently in training using roughly ten times the compute power of April's Muse Spark release.

OPEN SOURCE43m ago

LeRobot v0.6.0 drops world model policies

Hugging Face has released LeRobot v0.6.0, an update to its open-source robotics library that integrates three new world model policies including VLA-JEPA. The release enables efficient, real-time robot control and fine-tuning with limited demonstration datasets by training with a latent video world model that is discarded during inference.