Think You Can Build a Game with AI? Think Again!
summary
Claims concrete results: builds using Gemini on Three.js, asset shortcuts like Meta Banana and Mesh you, a workflow that uses key art anchoring to produce cohesive visuals, and a multiplayer prototype where runtime LLM-driven NPCs make unscripted decisions (four-player matches, collecting and stealing cubes). Work happens in hours or days, not months, and demos run live; challenges called out include determinism, debugging model changes, content safety, and token and platform economics.
AI-written summary · about
chapters (10)
- 0:00Welcome
- 1:52Why AI matters
- 3:16Novelty to innovation
- 5:20Stand out with AI
- 6:03Key art for design
- 8:33Runtime LLMs
- 11:01Parallel workflows
- 13:26Scaling AI challenges
- 15:10Future of AI gaming
- 16:13Takeaways
related talks
20mStudio Speaks: The Reality of AI Adoption in Games
21mBuilding at the Speed of Thought
34mGame Developers Are Becoming Directors, Not Coders
23mIntelligence as a Material
44mGlimpses of Humanity: My Game-Building AI Pair
47mGlimpses of Humanity: My Game-Building AI Pair
34mAdvancing Game Development: AI-Driven Asset Creation and Concrete Workflow Integration
49mHow a Concept Artist Can Stop Fearing AI and Build Their Own Game World