Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Animator with limited coding experience builds a fluid movement system using Unity and AI-generated code. 🏃‍♂️ animator JankyAnims shared how they used ChatGPT to piece together "spaghetti AI code" to get their wall-running and acrobatic movement mechanics fully playable in Unity.

indieforgames

5,954 subscribers

39,888 views • 18 days ago •via X (Twitter)

Gaming Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

desfrect17 days ago

“Hey ChatGPT, I want you to de-spaghettify this code”

tofuborne17 days ago

manual devs:

Robert Varadan17 days ago

You are going to see a lot more of this sort of thing!

godraytio17 days ago

Now make a game cool demos are everywhere. Dont sohw anyone anything till you near done.

COBOX18 days ago

AI + game dev 👀

Gaz17 days ago

So good!

OneOverR217 days ago

Playing this game is very relaxing.

WhunoYou17 days ago

Basically took sonics code

wolfengine.co17 days ago

AI + game dev = Unlimited creative games. Cant wait for the future

CJ シージ17 days ago

They use Ai ?

Related Videos

Claude built a playable Portal clone in Unity. In less than a day, I had working portal physics, a Portal Gun, lasers, gels, and the core gameplay mechanics running inside the editor. Connecting Claude directly to Unity through a free MCP plugin made it much easier to iterate on gameplay systems, test complex physics, and replace placeholder assets with AI-generated 3D models. Full breakdown 👇 #Unity #GameDev #AI #ClaudeCode #AIAgents #MCP #Tripo3D

Claude built a playable Portal clone in Unity. In less than a day, I had working portal physics, a Portal Gun, lasers, gels, and the core gameplay mechanics running inside the editor. Connecting Claude directly to Unity through a free MCP plugin made it much easier to iterate on gameplay systems, test complex physics, and replace placeholder assets with AI-generated 3D models. Full breakdown 👇 #Unity #GameDev #AI #ClaudeCode #AIAgents #MCP #Tripo3D

Stefan 3D AI

33,026 views • 2 months ago

I built a multimodal AI Coding Agent team with multi-agents. It has 3 AI agents working together as a team to generate and execute the code: 1. Coding Agent using o-3 mini 2. Vision Agent using Gemini 3. Code Execution Agent using o-3 mini and E2B 100% Opensource Code.

I built a multimodal AI Coding Agent team with multi-agents. It has 3 AI agents working together as a team to generate and execute the code: 1. Coding Agent using o-3 mini 2. Vision Agent using Gemini 3. Code Execution Agent using o-3 mini and E2B 100% Opensource Code.

Shubham Saboo

42,281 views • 1 year ago

📣 Today, I’m excited to walk you through Unity’s NEW AI offering, Meta MCP Extensions, and agentic tools to demonstrate how we can 𝗕𝘂𝗶𝗹𝗱 𝗔 𝗙𝘂𝗹𝗹 𝗩𝗥/𝗩𝗥 𝗚𝗮𝗺𝗲 from start to finish using these AI tools in a practical way. 🎥 Full video available at: 📌 Here’s what I’m covering today: - Unity VR project setup (with OpenXR plugins) - Installing the Unity AI Assistant and demos - Configuring Unity MCP + Meta MCP Extensions - Configuring Claude Code & MCPs - Building a VR/MR Basketball Game with the Unity AI Assistant, Claude Agent, and external Claude Code CLI - A lot of iteration with Claude Code + the Meta XR Simulator 💡Also, it’s been a while since I've posted a new video, and I’m genuinely excited to be back, especially with a topic like this that I know many devs have been waiting for.

📣 Today, I’m excited to walk you through Unity’s NEW AI offering, Meta MCP Extensions, and agentic tools to demonstrate how we can 𝗕𝘂𝗶𝗹𝗱 𝗔 𝗙𝘂𝗹𝗹 𝗩𝗥/𝗩𝗥 𝗚𝗮𝗺𝗲 from start to finish using these AI tools in a practical way. 🎥 Full video available at: 📌 Here’s what I’m covering today: - Unity VR project setup (with OpenXR plugins) - Installing the Unity AI Assistant and demos - Configuring Unity MCP + Meta MCP Extensions - Configuring Claude Code & MCPs - Building a VR/MR Basketball Game with the Unity AI Assistant, Claude Agent, and external Claude Code CLI - A lot of iteration with Claude Code + the Meta XR Simulator 💡Also, it’s been a while since I've posted a new video, and I’m genuinely excited to be back, especially with a topic like this that I know many devs have been waiting for.

Dilmer

25,153 views • 5 months ago

App Showcase!✨ Create a Game. Zero Code. Introducing Dungeon Explorer, a fully functional interactive shooter game along with customizable game design elements such as Inventory Management System, Weapon System, Simulation Distance, Procedural Generation and more. Our Multi-AI framework in V2 intelligently delegates game components—such as logic, rendering, and mechanics. This results in faster logic generation, smoother gameplay, and an overall richer user experience. Alchemist AI empowers anyone, regardless of coding knowledge, to turn their ideas into fully realized applications and games.

App Showcase!✨ Create a Game. Zero Code. Introducing Dungeon Explorer, a fully functional interactive shooter game along with customizable game design elements such as Inventory Management System, Weapon System, Simulation Distance, Procedural Generation and more. Our Multi-AI framework in V2 intelligently delegates game components—such as logic, rendering, and mechanics. This results in faster logic generation, smoother gameplay, and an overall richer user experience. Alchemist AI empowers anyone, regardless of coding knowledge, to turn their ideas into fully realized applications and games.

ALCHEMIST AI 🔮

34,139 views • 1 year ago

Build and test applications faster with a multi-agent coding system. Gain direct experience with Google Antigravity at a Build with AI event and move from design to execution using an IDE with built-in gen AI. 🔹 Multi-agent coding system and IDE 🔹 Lab testing and app development 🔹 High model quotas Get started →

Build and test applications faster with a multi-agent coding system. Gain direct experience with Google Antigravity at a Build with AI event and move from design to execution using an IDE with built-in gen AI. 🔹 Multi-agent coding system and IDE 🔹 Lab testing and app development 🔹 High model quotas Get started →

Google for Developers

15,321 views • 6 months ago

Create a Game. Zero Code🪄 Bullet Core - Demonstration of Game Development with Alchemist AI V2. (Best played in maximized mode) This fully functional shooter features customizable mechanics like leveling, dynamic damage formulas, critical hit rates, damage indicators and boss battles - all generated without a single line of code. With V2's Multi-AI system, each aspect of the game - logic, rendering, and mechanics - is handled by specialized AI agents, delivering superior game logic, smoother performance, and faster iterations. Bullet Core exemplifies what’s possible with Alchemist AI V2 - enabling anyone to bring complex games to life with just a simple description.

Create a Game. Zero Code🪄 Bullet Core - Demonstration of Game Development with Alchemist AI V2. (Best played in maximized mode) This fully functional shooter features customizable mechanics like leveling, dynamic damage formulas, critical hit rates, damage indicators and boss battles - all generated without a single line of code. With V2's Multi-AI system, each aspect of the game - logic, rendering, and mechanics - is handled by specialized AI agents, delivering superior game logic, smoother performance, and faster iterations. Bullet Core exemplifies what’s possible with Alchemist AI V2 - enabling anyone to bring complex games to life with just a simple description.

ALCHEMIST AI 🔮

35,814 views • 1 year ago

Here’s how I used AI to code Ideya and get it up on the App Store in 2 months

Here’s how I used AI to code Ideya and get it up on the App Store in 2 months

BSOLZ

37,931 views • 1 year ago

Ready to see Claude Code and Unity in action? 🛠️✨ Now that the official Unity plugin is live, here is a quick guide on how to set it up and actually use it in your workflow. 🔗 Get started:

Ready to see Claude Code and Unity in action? 🛠️✨ Now that the official Unity plugin is live, here is a quick guide on how to set it up and actually use it in your workflow. 🔗 Get started:

Unity for Games

17,023 views • 26 days ago

hmmm... this is kind of fun. a shared terminal to interact with pippinlovesyou where object placement and movement are synced across users. (so far no AI involved except for writing the code)

hmmm... this is kind of fun. a shared terminal to interact with pippinlovesyou where object placement and movement are synced across users. (so far no AI involved except for writing the code)

Yohei

21,676 views • 1 year ago

Introducing ElevenLabs Skills. With skills, AI coding assistants like Claude Code, Cursor, and OpenCode are better at using our APIs to handle AI audio and agent workflows. Get started: npx skills add elevenlabs/skills

Introducing ElevenLabs Skills. With skills, AI coding assistants like Claude Code, Cursor, and OpenCode are better at using our APIs to handle AI audio and agent workflows. Get started: npx skills add elevenlabs/skills

ElevenLabs Developers

163,903 views • 8 months ago

What happens when speech, transcription, and coding models work together? This prototype demo, built using a VS Code fork, showcases how MAI-Transcribe, MAI-Voice, and MAI-Code-1-Flash can work together in a unified workflow to transform spoken instructions into working code.

What happens when speech, transcription, and coding models work together? This prototype demo, built using a VS Code fork, showcases how MAI-Transcribe, MAI-Voice, and MAI-Code-1-Flash can work together in a unified workflow to transform spoken instructions into working code.

Microsoft AI

31,102 views • 4 months ago

Fully local Code Assistant running on NVIDIA GPU! In this tutorial, I'll show you how to run Llama3 using TensorRT and Nvidia's Triton Inference Server to use it as a Code Assistant in VSCode In this thread 🧵, I'll walk you through the integration process, explaining each step simply and clearly 👇 NVIDIA AI NVIDIA AIDev AI at Meta

Fully local Code Assistant running on NVIDIA GPU! In this tutorial, I'll show you how to run Llama3 using TensorRT and Nvidia's Triton Inference Server to use it as a Code Assistant in VSCode In this thread 🧵, I'll walk you through the integration process, explaining each step simply and clearly 👇 NVIDIA AI NVIDIA AIDev AI at Meta

Daniel San

42,154 views • 2 years ago

7. Codefy A toolbox of useful coding widgets to help you speed up your coding workflow using AI. Write, explain, debug, compare, and translate code with 15+ helpful, customized tools.

7. Codefy A toolbox of useful coding widgets to help you speed up your coding workflow using AI. Write, explain, debug, compare, and translate code with 15+ helpful, customized tools.

Rowan Cheung

27,068 views • 3 years ago

Here's a 10mins video walkthrough of how to build a crypto Global Insights and Trending Topics dashboard using Messari's AI intelligence. We build everything from scratch using the following endpoints: - AI Toolkit: - Topics: Here's the prompt used in Cursor: Github repo with generated code: Reach out to us at api@messari.io or DM if you have questions :)

Here's a 10mins video walkthrough of how to build a crypto Global Insights and Trending Topics dashboard using Messari's AI intelligence. We build everything from scratch using the following endpoints: - AI Toolkit: - Topics: Here's the prompt used in Cursor: Github repo with generated code: Reach out to us at [email protected] or DM if you have questions :)

Diran Li

70,080 views • 1 year ago

Always on trend with $PENGU and Pudgy Penguins with some ASMR using AI. Had to give this a shot. 😅 Utilized ChatGPT & Kling AI. Have a code in the post below for bonus credits if you want to try!

Always on trend with $PENGU and Pudgy Penguins with some ASMR using AI. Had to give this a shot. 😅 Utilized ChatGPT & Kling AI. Have a code in the post below for bonus credits if you want to try!

STMcFly

28,297 views • 1 year ago

Someone is building a game they dreamed of for 15 years using GPT-6 Astra and on day 10, five creature animations that used to take weeks at a 3D studio took an hour and a half, with the Scorpid running in Unity an hour after that. → Scorpid modeled in Tripo P2.0 with optimized mesh and well-organized parts for easier bone placement → Video references generated with SD 2.5 using the same workflow → About an hour and a half with GPT-6 Astra on xhigh for five animations including feedback rounds → Another hour to get it running in Unity

Someone is building a game they dreamed of for 15 years using GPT-6 Astra and on day 10, five creature animations that used to take weeks at a 3D studio took an hour and a half, with the Scorpid running in Unity an hour after that. → Scorpid modeled in Tripo P2.0 with optimized mesh and well-organized parts for easier bone placement → Video references generated with SD 2.5 using the same workflow → About an hour and a half with GPT-6 Astra on xhigh for five animations including feedback rounds → Another hour to get it running in Unity

0xMarioNawfal

38,719 views • 1 month ago

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

127,724 views • 1 year ago