Vibe coding a 3D multiplayer game in 15 minutes—with no game dev experience | Cody De Arkland

Cody De Arkland is the senior director of developer experience at Sentry, leading a team that empowers developers to build and ship software with greater safety and efficiency. Watch him speed-run the creation of a 3D multiplayer flight simulator—from scratch—in just 15 minutes, demonstrating the power (and creativity) that vibe coding enables. *What you’ll learn:* • How to approach building complex applications with AI by starting broad and iterating on specific features • The process of using multiple AI coding assistants simultaneously to build different components • Techniques for learning new technologies and frameworks through AI-assisted exploration • How to troubleshoot and fix issues when AI implementations don’t work as expected • The parallels between building fun projects and enterprise software with AI assistance • Strategies for keeping AI tools focused when they go off track or add unwanted features • The incredible velocity and productivity gains possible with modern AI coding tools • How anyone can now build sophisticated applications with minimal prior experience *Brought to you by:* Enterpret—Customer superintelligence platform for product and CX teams: http://enterpret.com/howIAI WorkOS—Make your app enterprise-ready today with WorkOS: https://workos.com?utm_source=lennys_howiai&utm_medium=podcast&utm_campaign=q22025 *Where to find Cody De Arkland:* Website: https://codyde.io/ LinkedIn: https://www.linkedin.com/in/codydearkland/ X: https://x.com/Codydearkland GitHub: https://github.com/codyde *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo *In this episode, we cover:* (00:00) Introduction to Cody (02:45) AI tools he’s using (04:38) How Cody vibe coded a multiplayer game: Spaceflight (09:37) Demo: Starting a new flight simulator project from scratch *(12:22) "Tip: Keep your initial coding input general and broad"* (13:49) How to learn about libraries and technologies for projects (17:06) First run of the new flight simulator game (19:26) Using multiple AI coding assistants simultaneously *(19:31) "Tip: Use multiple AI coding assistants simultaneously to build different components"* (20:43) Unexpected features and visual improvements (21:26) Testing the multiplayer functionality (22:31) Reflecting on the development process and iteration (26:47) Lightning round and final thoughts *Tools referenced:* • Cursor: https://www.cursor.com/ • Windsurf: https://windsurf.com/ • Claude: https://claude.ai/new • Bolt: https://bolt.new/ • React: https://react.dev/ • v0: https://v0.dev/ *Other references:* • Sentry: https://sentry.io/ • MCP: https://www.anthropic.com/news/model-context-protocol • Spaceflight: http://spaceflight.gg/ • Three.js: https://threejs.org/ • Socket.io: https://socket.io/ _Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co._

Cody De ArklandguestClaire Vohost

May 5, 202531mWatch on YouTube ↗

WHAT IT’S REALLY ABOUT

Vibe coding a 3D multiplayer flight game using AI tools fast

Cody walks through how he starts with a blank Vite/React project and uses Claude Code (plus tools like Cursor/Windsurf) as “junior developers” to scaffold a Three.js flight simulator from a short prompt.
They show the reality of AI-assisted building: rapid progress to a fun v0, followed by iterative debugging for camera orientation, inverted controls, and unintended features the model adds.
Cody explains how he chooses technologies (ask the LLM, then validate via Google/docs, then feed findings back) and how that mirrors building production apps: broad concept → feature-by-feature iteration.
They also prototype multiplayer quickly with a simple server + WebSockets/Socket tooling, emphasizing speed/velocity while acknowledging the need for resets, constraints, and tighter scoped prompts when the AI goes off track.

IDEAS WORTH REMEMBERING

5 ideas

Start broad, then iterate feature-by-feature.

Cody avoids overly detailed “one-shot” specs; he prompts for a workable v0 first, then refines discrete parts (controls, camera position, art style, environment) in successive passes.

Use the LLM to pick tech, then verify externally.

He asks AI which browser-game technologies make sense (e.g., Three.js, WebSockets), then does traditional research (docs/Google) and feeds the findings back to the model for implementation.

Treat AI tools like junior devs with parallel tasks.

Cody keeps multiple AI coding environments open and can run “dueling” Claude instances—one fixing frontend gameplay while another scaffolds backend multiplayer—to compress time-to-prototype.

Expect “two steps forward, one step back.”

The demo surfaces common failure modes: reversed controls, misinterpreted camera direction, UI shifted off-screen, and extra features added without request—yet the net progress is still faster than manual building.

3D assets require explicit orientation and “forward” definitions.

Imported models (glTF/GLB from places like Sketchfab) may load sideways or rotated; you must specify what “nose/forward” means and apply consistent transforms you can reuse for additional ships.

WORDS WORTH SAVING

5 quotes

I tend to look at the different tools as like little junior developers who are helping me work on different things.

— Cody De Arkland

I try to stay pretty wide… what’s the broad strokes… then I can tweak the individual parts as I go.

— Cody De Arkland

You wrote, like, 27 words into this prompt, and now you have a video game?

— Claire Vo

This is a good example… things don’t always work the way we expect.

— Cody De Arkland

Hey, we’ve been wrong for a while. Can we take a fresh look at this problem? Here are the main requirements…

— Cody De Arkland

Vibe coding as iterative prototypingTool stack: Claude Code, Cursor, Windsurf, BoltScaffolding from blank Vite/React projectThree.js scene setup and flight controls3D model ingestion nuances (glTF/GLB orientation)Multiplayer architecture (WebSockets/server, joins/chat)Prompting strategy: broad strokes, then tighten scope

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.