🎮

How People Are Using AI For Developing Games

Builders are vibe-coding full prototypes—multiplayer loops, chatty NPCs with memory, shaders—by prompting, letting AI write servers, generate art, and live-debug so solo devs (and kids) ship in hours, not weeks. In 2025, “world models” can spin text/images into interactive 3D spaces, hinting at a game-engine-as-model future. Users gush about speed and creativity; experts celebrate the trajectory but flag physics gaps, bias, and maintainability—so AI is the turbo for prototyping while human design/testing harden production.

🤖 ai summary based on 28 tweets

✨ User Stories 13 💡 Expert Insights 4 🚀 Product Demos 11

Stories from AI users. WhatsNextForAI curates public sources. No product affiliations. Opinions are the authors.

All Codex 2 Cursor 3 Grok 3 1 Grok 4 1 Gemini 2.5 Flash Image (nano-banana) 2 GPT-5 1 o3 1 Gemini 2.5 1 Claude Opus 4.1 1 Claude 3.7 Sonnet 1
Can’t load? Read tweets in preview...

Snake games are a bad test of AI beca- "Claude 3.7, make a snake game, but the snake is self-aware it is in a game and trying to escape and interesting things happen as a result" This is all AI (one prompt + a request to make special things happen faster). Matrix mode at 0:55 https://t.co/1ZtlC1wIVB

One quick check...