Tag
TesanaAI launches an image-to-game feature that allows users to convert any game screenshot or concept into a playable game in under 5 minutes using AI models.
The article discusses Poisson disk sampling, a technique for randomly placing points with a minimum distance, and details Bridson's efficient algorithm from a highly-cited 2007 paper, along with improvements for computer graphics and simulations.
An AI model named Ornith-1.5 was used to code an infinite procedurally generated walking simulator on an 8 GB RTX 4060, impressing the user with its capabilities.
Dwarf Fortress is receiving a major Myth and Magic update that introduces procedural magic systems tied to the game's cosmological foundations, promising deep and unique magical experiences for players.
Procedura introduces a novel 3D modeling agent that uses LLMs to create editable, part-structured assemblies from text prompts, outperforming existing methods in quality and editability.
StateSight is a new benchmark for evaluating spatial-state reconstruction in vision-language models, showing that models like GPT-5.5 and Claude Sonnet 5 struggle with spatial reasoning tasks compared to human performance.
The author trained a 1.57B-parameter Dreamer 4 world model from scratch for under $150, demonstrating the accessibility of low-cost AI model training and using procedural data for validation.
A developer describes embedding a peer-to-peer multiplayer dungeon game into a static blog using WebRTC and Trystero, with deterministic procedural generation and no backend server.
A developer showcased how Fable, an AI agent, generated a fully procedural Mars city in Three.js after six hours and dozens of subagents, calling the result beyond expectations.
A researcher's blog post describes turning constraint models into playable puzzle games, based on his paper on scaling Sudoku as a constraint problem. It shares MiniZinc models, a repository of 434,201 Sudoku instances, and playable versions of nine puzzle games.
A cyberpunk FPS tech demo that runs entirely in the browser, built in 3 days via vibe coding with multiple LLMs. It features procedural generation, WebGPU rendering, and fully synthesized audio.
Andrej Karpathy experiments with Opus 5, giving it the first paragraph of Lord of the Rings and a 1M token budget to create a 3D JS rendering of the story, highlighting LLM stamina for hyper-custom worlds while noting weaknesses in multimodal auditing and gameplay.
Andrej Karpathy shares an experiment where Claude Opus 5 used a 1M-token budget to procedurally render Lord of the Rings in three.js, sparking thoughts on LLM testing, custom world generation, and multimodal weaknesses.
An article explaining the problem of correlated RNG in procedural generation when multiple systems are seeded with the same initial seed, using examples like Final Fantasy XIV and Slay the Spire, and discussing potential fixes.
Someone used the Opus 5 AI model to create a No Man's Sky-style exploration game in a single day.
Matt Shumer shares the GitHub repo for 'Claude of Duty', a first-person shooter built entirely in the browser using Three.js and WebGL2, with all assets procedurally generated by AI agents at load time.
The article critiques AI-generated game worlds, arguing that while demos like Google Genie 3 are visually impressive, they lack the thoughtful design found in handcrafted games, making them hollow for extended play.
An explanation of Perlin's noise algorithm, covering the concept of noise, coherent noise, and the basics of implementing noise functions in procedural generation.
A gamer speculates about when AI will truly transform video games, imagining NPCs with memory and dynamic worlds, and wonders if the next decade could bring the biggest change in gaming history.
MAGIC is a system that uses large language models to generate connected, navigable multi-scene game worlds from a single natural-language prompt, addressing cross-scene consistency, in-scene navigability, and transition evaluation. It achieves high precision and recall on a benchmark of 100 multi-scene cases.