← back
Think You Can Build a Game with AI? Think Again! - Danielle An & David Hoe, Meta
Takeaway
AI makes game creation more accessible while increasing the importance of creative direction and playtesting.
Summary
- AI generation lowers coding and art barriers, but recognizable game prototypes often converge on similar, unpolished results.
- A single key-art image can anchor asset style, gameplay inspiration, and visual cohesion across model sessions.
- Taste, coherent presentation, and human playtesting remain central to making games people enjoy.
- A multiplayer demo uses runtime LLM-controlled NPC personalities to produce unscripted stealing, blocking, and competition.
game-developmentgenerative-assetsnpc-agents
Original description
With the recent development of AI, either you or your friend probably vibe coded a game using Gemini, on Three.js. But that is old news now. If everyone can do that, what is next? The next massive hit, the one that millions of people across the world will play, is just about to be born. Wanna know more? Come see this talk!