正在加载视频...

视频加载失败

Unreal Engine 5.8 ships today with experimental MCP server support: Your sources, your pipeline and your workflow—simply configure the MCP plugin and connect to any agent. Get familiar with the MCP server and the PCG Primitive Plugin today and see what teams can build together:

3,042,454 次观看 • 3 个月前 •via X (Twitter)

33 条评论

Adam Hill 的头像
Adam Hill3 个月前

We’re gonna get GTA 7 before GTA 6 🎮

Teknium 🪽 的头像
Teknium 🪽3 个月前

Will add to Hermes’ MCP catalog today

Stephan Ferraro 的头像
Stephan Ferraro3 个月前

Thats exactly the right way how to implement AI in software. Provide MCP interfaces.

✮EWZine✮(Or maybe just X) 的头像
✮EWZine✮(Or maybe just X)3 个月前

We don't want AI in Unreal Engine. That just makes the AAA developers go the lazy route, fire their dev's and artists because a few commands on a gpt will do what they want [except lack the soul and creativity] for cheap.

Jeremy Sparks 的头像
Jeremy Sparks3 个月前

I think games that generate full levels in real time will be the norm. Never ending games, and storylines so vast and complex you live many simultaneous lifetimes interdimensionally.

Mike Roberts 的头像
Mike Roberts3 个月前

The SPEAR MCP for controlling the #UnrealEngine #UE5 is 10x faster, equally expressive, and is better grounded to entities a scene, due to drastically less context bloat and better ID rendering, relative to the official MCP released in UE 5.8 today.

ChrisUniverse 🗽 的头像
ChrisUniverse 🗽3 个月前

I cannot believe wtf I am looking at! This is just absolutely fucking insane! A little kid with a dollar and a dream will soon build a multi billion dollar game/experience by himself at the age of 13

Ivan Fioravanti ᯅ 的头像
Ivan Fioravanti ᯅ3 个月前

This is the dream of anyone out here! Being able to create our own world in 3D! AMAZING JOB!

VraserX e/acc 的头像
VraserX e/acc3 个月前

Within 5 years, people will generate AAA level games for less than $100.

Kaizen 的头像
Kaizen3 个月前

Fable 5 linked to Unreal and we don't need to wait for Rockstar anymore..

I Hate Censorship priv/acc 的头像
I Hate Censorship priv/acc3 个月前

So you mean I could vibecode a video game

Thomas Linden 的头像
Thomas Linden3 个月前

Now you can create faster than ever before, giving you even MORE time to not optimize your games.

sid ourradi 的头像
sid ourradi3 个月前

Fable 5 + UE5.8 + MCP just gave AI agents native control of the engine 🔥 Solo devs are about to ship full games with one prompt. We’re so back.

Diego | AI 🚀 - e/acc 的头像
Diego | AI 🚀 - e/acc3 个月前

Imagine this with Fable 5, it will be Unreal

SimWorld 的头像
SimWorld3 个月前

Try out SimWorld Studio to connect any coding agents with UE. Building via coding:

Brandon Smith 的头像
Brandon Smith3 个月前

Just sell the rights @EA to SimCity so we can can Sim City 5. Your company cannot be trusted after SimCity 2013.

FantasticMrSOL 的头像
FantasticMrSOL3 个月前

This is amazing. These videogame nerds that are against ai don’t understand how this tech is going to make games even better than before. GTA type games take 10 years to make. With AI we can probably cut a lot of time off that. It will be reasonable pricing to develop a game now, more experimental games, teams don’t have to focus on what ”selling” due to risk of going bankrupt. Bring AI into gaming ! It’s a must for the future of this amazing entertainment business

Elliot Arledge 的头像
Elliot Arledge3 个月前

this is mind blowing

Ken 的头像
Ken3 个月前

this is awesome! @unity AI fucking sucks and costs money

robot 2.0 的头像
robot 2.03 个月前

sorry but you are so far behind holy shit this is slop

TheLazyIndianTechie 🕹️ 的头像
TheLazyIndianTechie 🕹️3 个月前

This is AI in gamedev done right.

Eric Henderson 的头像
Eric Henderson3 个月前

Got it. Installed it. Worried about my agents building too much with it and getting locked in with your pricing models that are generous for indie developers but man I need more power.... More tools... More automatic have asset creation...

🔥GameDevMicah🔥UE6 的头像
🔥GameDevMicah🔥UE63 个月前

@Milpixtwit EPIC!!!

Netoboomin 的头像
Netoboomin3 个月前

🤢🤮

Religion is poison 的头像
Religion is poison3 个月前

This looks like the future of world building

Yev 的头像
Yev3 个月前

what’s the point? what’s the gameplay from this? congrats you made a city blockout…

Yaeko 的头像
Yaeko3 个月前

Cant wait for all the soulless games made with AI, but the feature is nice.

Glitter Gal 的头像
Glitter Gal3 个月前

This is so exciting!!

BulletWilliam 🇺🇦Thank you masking and vaxing 的头像
BulletWilliam 🇺🇦Thank you masking and vaxing3 个月前

AI slop engine.

Mattison Brooks 的头像
Mattison Brooks3 个月前

We should be able to have two thoughts here: 1. For entry level designers that have a vision but maybe lack the dev practice or tools experience, this is a great way to build something cool. 2. There’s no way in hell AAA experienced devs should be relying on this at scale.

ns 的头像
ns3 个月前

@AzFlin whatchu building fam

Niko 的头像
Niko3 个月前

@Scobleizer so claude can build games now ?

Brooklyn! 的头像
Brooklyn!3 个月前

I know where my weekend's going

相关视频

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

142,256 次观看 • 1 年前