Articles
Features
AI-generated video and the return of interactive film
From Dragon's Lair and Bandersnatch to real-time world models like Genie 3: what would make generated video genuinely interactive, the hybrid designs AI game designers can build before it does, and the questions it raises.
21 Oct 2026
AI Game DevHow to start making text-based AI games for web and mobile
A starting guide for AI game designers: why text is where generative games genuinely work today, which AI game formats to pick, and the architecture, costs and store rules you need to ship one on the web or a phone.
20 Oct 2026
ToolsClassical 2D mechanics: the design vocabulary AI game designers still need
Coyote time, jump buffering, top-down movement, tile grids, AABB collision, fixed timesteps and cameras: the 2D techniques that still decide how an AI-made game feels, why they anchor generative content, and how to prototype them with an LLM.
17 Oct 2026
AI Game DevGenerative AI audio for games: adaptive scores, AI sound effects and synthetic voices
From iMUSE to text-to-speech characters: what generative AI audio can do for an AI game designer today, when to generate at runtime versus in advance, and the licensing and consent questions you need to settle first.
16 Oct 2026
Simulations3D world exploration with AI: landmarks, procedural terrain and generated worlds
For AI game designers: what makes a 3D world worth exploring, how noise, wave function collapse and L-systems give AI-generated content a structure, where generated 3D assets, world models and AI agents fit today, and how to turn wandering into a game loop.
15 Oct 2026
SimulationsAI-driven NPCs: LLM agents and the future of living simulations
For AI game designers: from dialogue trees to LLM agents with memory, goals and routines, why text-first NPC conversation is the practical win today, how generative voice comes next, and the architectures that hold up.
15 Oct 2026
News
All news →
Gradium releases Phonon, a family of tiny open-weight text-to-speech models
Gradium has published 31m and 40m parameter Phonon TTS models that run on CPUs, phones and in the browser. The English 31m model is Apache 2.0; the 40m models are non-commercial.
20 Oct 2026 · Gradium blog
News
Skywork open-sources Matrix-Game 4.0, a neural renderer for playable low-poly games
Matrix-Game 4.0 keeps gameplay and physics in a real game engine and uses a streaming video model to repaint its low-poly frames. Code, three playable games and model weights are released under Apache 2.0.
15 Oct 2026 · Project GitHub
News
AMD agrees to acquire World Labs for about $8.2 billion
AMD has signed a definitive agreement to buy World Labs, the Fei-Fei Li-led company behind the Marble 3D world model, in an all-stock deal expected to close by the end of 2026.
28 Sept 2026 · AMD Newsroom
News
Unity releases an official plugin that teaches coding agents how to work in Unity
Unity has shipped a first-party plugin for Claude Code that installs 29 engineering skills written by its own feature teams, and has since brought the same skills to OpenAI's Codex and xAI's Grok Build.
9 Sept 2026 · Unity blog
News
Runway shows GWM Worlds 2, a real-time world model driven by text actions
Runway's latest General World Model research preview generates interactive 720p video with audio at 24 fps, steered by text actions addressed to characters or the scene itself.
3 Sept 2026 · Runway Research
News
Unreal Engine 5.8 adds an experimental MCP plugin, and Epic puts LLMs into the plan for UE6
At State of Unreal 2026 Epic released Unreal Engine 5.8 with an experimental Model Context Protocol plugin that lets any language model inspect and act on a project, and said UE6 will build on the same approach.
17 Jun 2026 · Unreal Engine blog