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.

GPT-5.4 with the Roblox MCP server created its own 3D models, animations and GUI. It's so cool you can make games so easily

JB

6,472 subscribers

111,763 views • 5 months ago •via X (Twitter)

Gaming Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

it's pretty amazing what you can do with a couple of prompts + GPT 5.4 + Game Studio plugin in the Codex app + Threejs a mini 3D Vampire Survivors game :D

it's pretty amazing what you can do with a couple of prompts + GPT 5.4 + Game Studio plugin in the Codex app + Threejs a mini 3D Vampire Survivors game :D

Anthony Kroeger

22,371 views • 4 months ago

when you get access to gpt-5, try a message like "use beatbot to make a sick beat to celebrate gpt-5". it's a nice preview of what we think this will be like as AI starts to generate its own UX and interfaces get more dynamic. it's cool that you can interact with the synthesizer directly or ask chatgpt to make changes!

when you get access to gpt-5, try a message like "use beatbot to make a sick beat to celebrate gpt-5". it's a nice preview of what we think this will be like as AI starts to generate its own UX and interfaces get more dynamic. it's cool that you can interact with the synthesizer directly or ask chatgpt to make changes!

Sam Altman

2,528,923 views • 1 year ago

Guilty Gear Xrd is easily one of my favorite looking games period. The gorgeous cel-shaded visuals, animations and effects that toy with the framerate to replicate the feeling of 2D animation, it's all so peak

Guilty Gear Xrd is easily one of my favorite looking games period. The gorgeous cel-shaded visuals, animations and effects that toy with the framerate to replicate the feeling of 2D animation, it's all so peak

Red

38,696 views • 5 months ago

Harrison Chase You should try Highlight - you can just @ any MCP server from anywhere. Runs natively. With context grounding so it can use what you’re looking at as inputs and outputs.

Harrison Chase You should try Highlight - you can just @ any MCP server from anywhere. Runs natively. With context grounding so it can use what you’re looking at as inputs and outputs.

Pim de Witte

68,538 views • 1 year ago

✨ 3d models are now LIVE on Photo AI 😊 You can now turn any AI photo you make into a 3d model by pressing [ 📦 Make 3d model ] And then you can view it inside Photo AI or download it as a .GLB 3d model file It's still very early in AI generated 3d model world but it's nice to have this feature working already As always, the models will keep improving, so this feature will keep getting better (like it did with video, it sucked before, now it's getting passable) Next would be nice to switch to .USDZ so you can load it straight into your iPhone with ARKit and put it in your room Available now for everyone on the Premium and Ultra plan

✨ 3d models are now LIVE on Photo AI 😊 You can now turn any AI photo you make into a 3d model by pressing [ 📦 Make 3d model ] And then you can view it inside Photo AI or download it as a .GLB 3d model file It's still very early in AI generated 3d model world but it's nice to have this feature working already As always, the models will keep improving, so this feature will keep getting better (like it did with video, it sucked before, now it's getting passable) Next would be nice to switch to .USDZ so you can load it straight into your iPhone with ARKit and put it in your room Available now for everyone on the Premium and Ultra plan

@levelsio

112,930 views • 1 year ago

With 5.6 out, I hope you'll all enjoy it as much as I do! I can finally start talking about all the things I've been building with it. It's so much better at building games and making 3D models; Here is a small demo of one of the games I built with this!

With 5.6 out, I hope you'll all enjoy it as much as I do! I can finally start talking about all the things I've been building with it. It's so much better at building games and making 3D models; Here is a small demo of one of the games I built with this!

Thomas Ricouard

45,940 views • 29 days ago

'Cause I'm cool ('Cause I'm cool) (It's so good, it's so close, I can taste it) On my own (On my own) (On my lips, this is your invitation) But it's warmer (If you dare, meet me up here) In your arms, oh (In your arms)

'Cause I'm cool ('Cause I'm cool) (It's so good, it's so close, I can taste it) On my own (On my own) (On my lips, this is your invitation) But it's warmer (If you dare, meet me up here) In your arms, oh (In your arms)

໊

41,794 views • 1 year ago

Opus 4.7 can build Lottie Animations. One prompt via Lottie Creator MCP → 500 particles, each with its own path, easing, and arrival frame. I didn't touch a keyframe. What should I ask it to build next? Best reply, I'll make it.

Opus 4.7 can build Lottie Animations. One prompt via Lottie Creator MCP → 500 particles, each with its own path, easing, and arrival frame. I didn't touch a keyframe. What should I ask it to build next? Best reply, I'll make it.

Nattu

186,829 views • 3 months ago

You can do so many cool things with just basic AE (particle world) effect. It's amazing!

You can do so many cool things with just basic AE (particle world) effect. It's amazing!

Seter

39,220 views • 2 years ago

Alright this is my new favorite thing I've made. During the week I make #Roblox games so during the weekend I can afford to make silly #RobloxUGC emotes 😂

Alright this is my new favorite thing I've made. During the week I make #Roblox games so during the weekend I can afford to make silly #RobloxUGC emotes 😂

Reverse_Polarity

30,066 views • 10 months ago

BREAKING: The button under any Grok Imagine video on X now takes you straight to that video with its prompt, so you can see how it was made and make your own like it.

BREAKING: The button under any Grok Imagine video on X now takes you straight to that video with its prompt, so you can see how it was made and make your own like it.

DogeDesigner

37,341 views • 9 months ago

Your gut has 200-600 million neurons. More than the spinal cord. It can run digestion entirely on its own, even if the vagus nerve is cut. That is why it's called the "second brain." This visualization shows the nerve plexuses surrounding the small and large intestine. #EntericNervousSystem All animations created using the SciePro 3D anatomy model.

Your gut has 200-600 million neurons. More than the spinal cord. It can run digestion entirely on its own, even if the vagus nerve is cut. That is why it's called the "second brain." This visualization shows the nerve plexuses surrounding the small and large intestine. #EntericNervousSystem All animations created using the SciePro 3D anatomy model.

SciePro

13,252 views • 1 month ago

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

@levelsio

119,210 views • 1 year ago

"It's so cool that you guys want to make movies. Like, it's so rad, and like, protect the thing that made you want to go to this school for the rest of your life." — Kristen Stewart

"It's so cool that you guys want to make movies. Like, it's so rad, and like, protect the thing that made you want to go to this school for the rest of your life." — Kristen Stewart

Stewart Quotes

12,079 views • 6 months ago

🤓 I have released Proximity, my MCP Security Scanner powered by NOVA! Before using a public MCP server, you can quickly probe the endpoint or your local MCP to discover exposed prompts, tools, and resources. You can then scan with NOVA to check if any adversarial prompts are configured. Proximity lets you assess the security and risk before deploying or connecting to a foreign MCP server 👇

🤓 I have released Proximity, my MCP Security Scanner powered by NOVA! Before using a public MCP server, you can quickly probe the endpoint or your local MCP to discover exposed prompts, tools, and resources. You can then scan with NOVA to check if any adversarial prompts are configured. Proximity lets you assess the security and risk before deploying or connecting to a foreign MCP server 👇

Thomas Roccia 🤘

18,058 views • 10 months ago

You can now create anything with Claude. I created an Adidas video using Vidfield MCP on claude. GPT Image 2 → cinematic storyboard Seedance 2.0 → final 15-second ad The full workflow + prompt is below 👇

You can now create anything with Claude. I created an Adidas video using Vidfield MCP on claude. GPT Image 2 → cinematic storyboard Seedance 2.0 → final 15-second ad The full workflow + prompt is below 👇

Abhishek

15,279 views • 27 days ago

Shiorin! I was in charge of Shiori's 3D MV for her first original "Monsters and Men". The song is soo cool and epic! It's a rare chance for me to make a dark and edgy video so I had fun with it! It's an honor, thank you for trusting me Shiorin! ▶️

Shiorin! I was in charge of Shiori's 3D MV for her first original "Monsters and Men". The song is soo cool and epic! It's a rare chance for me to make a dark and edgy video so I had fun with it! It's an honor, thank you for trusting me Shiorin! ▶️

Kanauru

71,698 views • 5 months ago

Creating a multiplayer game on v0 using Three.js and Liveblocks Models/textures/tracks/environments/physics, everything is being created by v0. The key part was asking v0 to create automation scripts to export logs/screenshots so it can iterate on its own.

Creating a multiplayer game on v0 using Three.js and Liveblocks Models/textures/tracks/environments/physics, everything is being created by v0. The key part was asking v0 to create automation scripts to export logs/screenshots so it can iterate on its own.

Matias 🧉

15,090 views • 4 months ago