Loading video...

Video Failed to Load

Go Home

i built an open world minigame that's controlled with hand movements only here's a step-by-step tutorial: > started with my mediapipe + threejs template (see QT) > added a 3D model made by quaternius > sent a few prompts to gemini 3... --- prompt #1: repurpose the attached script,...

measure_plan's profile picture

AA

19,404 subscribers

131,799 views • 9 months ago •via X (Twitter)

GamingEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

If you prompt it right, Seedance 2.0 is the most powerful video model in the world. But it won't turn a vague idea into a cinematic shot. Here's the prompt I use to make scenes like this 👇
0:15

If you prompt it right, Seedance 2.0 is the most powerful video model in the world. But it won't turn a vague idea into a cinematic shot. Here's the prompt I use to make scenes like this 👇

NΞXUS

15,818 views • 3 months ago

Had early access to Gemini with Deep Think. Very good model, big gains over standard Gemini 2.5 Pro for a lot of problems. Here is the first attempt at the starship control panel prompt I try with every model. First time I have seen a model make a 3D interface in response.
0:14

Had early access to Gemini with Deep Think. Very good model, big gains over standard Gemini 2.5 Pro for a lot of problems. Here is the first attempt at the starship control panel prompt I try with every model. First time I have seen a model make a 3D interface in response.

Ethan Mollick

252,976 views • 1 year ago

Gemini 3! This is our most intelligent model that brings any idea to life. 😻 This is the best model in the world, by a crazy wide margin! Aside from a huge increase across the absolutely everything, look at its coding capabilities and quality of aesthetics and fidelity. Just insane! This is a one-shot procedural voxel world from just this prompt: "three js infinitely procedurally generated voxel art scene of walking through the forest with falling autumn leaves" 👇 Enjoy!
0:14

Gemini 3! This is our most intelligent model that brings any idea to life. 😻 This is the best model in the world, by a crazy wide margin! Aside from a huge increase across the absolutely everything, look at its coding capabilities and quality of aesthetics and fidelity. Just insane! This is a one-shot procedural voxel world from just this prompt: "three js infinitely procedurally generated voxel art scene of walking through the forest with falling autumn leaves" 👇 Enjoy!

Yi Tay

220,910 views • 10 months ago

A quick test of using 3d drawing with 6DOF controllers as an "instructor" for a generative AI process. There's so many powerful and fun new ways to create just around the corner.. Here I'm using Dreams, Krea and 3daistudio. The 3d model at the end of the video was generated from the Dreams+Krea output in just around 15 seconds. Only the model on the left is a "true" 3d model. #ai #madeindreams
0:17

A quick test of using 3d drawing with 6DOF controllers as an "instructor" for a generative AI process. There's so many powerful and fun new ways to create just around the corner.. Here I'm using Dreams, Krea and 3daistudio. The 3d model at the end of the video was generated from the Dreams+Krea output in just around 15 seconds. Only the model on the left is a "true" 3d model. #ai #madeindreams

Martin Nebelong

132,897 views • 2 years ago

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.
0:20

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.

Tom Krcha

1,439,513 views • 20 days ago

The original model of 1x1x1x1 made by Mewsitive in 2014 actually has an earlier version attached to it. This earlier version has a glowing torso, as well as a script that made him shed blood upon being harmed. It would also add the health and level to the humanoid name, harm you when touched, and respawned upon death. These were removed in a 2015 update to the model.
0:41

The original model of 1x1x1x1 made by Mewsitive in 2014 actually has an earlier version attached to it. This earlier version has a glowing torso, as well as a script that made him shed blood upon being harmed. It would also add the health and level to the humanoid name, harm you when touched, and respawned upon death. These were removed in a 2015 update to the model.

Dynabroth - Roblox Trivia

34,554 views • 1 year ago

🚨 AI VIDEO PROMPTING IS DEAD !! You no longer need to write a 500-word prompt just to tell AI how your video should look. 💀 I just tested Pippit’s 3D Director Studio + Seedance 2.5 And instead of explaining the entire scene with words… I literally BUILT the scene first. For my test, I created a cinematic fight scene with characters inside a 3D environment. I could control: 1️⃣ Where the characters stood 2️⃣ Which props they held 3️⃣ Where the camera was placed 4️⃣ What each character should do Then I could actually CHOREOGRAPH the action. → Run → Fight → Shoot → Fall → React → Move You can place these actions on the timeline, adjust when they happen, and even plan the camera movement and character trajectories. So instead of: PROMPT → GENERATE → PRAY 😂 It becomes: BUILD → DIRECT → GENERATE And that gives you WAY more control. Because you’re not asking AI to imagine the entire scene from a block of text. You’re literally showing it the: → Characters → Environment → Props → Positions → Actions → Camera Then Seedance 2.5 takes that 3D direction and turns it into the final video. That’s what makes this so interesting. It feels less like prompting an AI video model… And more like sitting in the DIRECTOR’S CHAIR. 🎬 Try Pippit: Pippitofficial #3DDirectorStudio #PippitAI #Seedance25 #PippitPartner
0:14

🚨 AI VIDEO PROMPTING IS DEAD !! You no longer need to write a 500-word prompt just to tell AI how your video should look. 💀 I just tested Pippit’s 3D Director Studio + Seedance 2.5 And instead of explaining the entire scene with words… I literally BUILT the scene first. For my test, I created a cinematic fight scene with characters inside a 3D environment. I could control: 1️⃣ Where the characters stood 2️⃣ Which props they held 3️⃣ Where the camera was placed 4️⃣ What each character should do Then I could actually CHOREOGRAPH the action. → Run → Fight → Shoot → Fall → React → Move You can place these actions on the timeline, adjust when they happen, and even plan the camera movement and character trajectories. So instead of: PROMPT → GENERATE → PRAY 😂 It becomes: BUILD → DIRECT → GENERATE And that gives you WAY more control. Because you’re not asking AI to imagine the entire scene from a block of text. You’re literally showing it the: → Characters → Environment → Props → Positions → Actions → Camera Then Seedance 2.5 takes that 3D direction and turns it into the final video. That’s what makes this so interesting. It feels less like prompting an AI video model… And more like sitting in the DIRECTOR’S CHAIR. 🎬 Try Pippit: Pippitofficial #3DDirectorStudio #PippitAI #Seedance25 #PippitPartner

SANI BULA

95,462 views • 14 days ago

I'm still playing with 3D storyboards for Seedance 2.0. Even when I ask for a 2D video, using a 3D storyboard often pushes the model toward a 3D look. I haven't tested it extensively yet but there definitely seems to be a bias. So 2D storyboards work better for 2D videos, while 3D storyboards are better suited for 3D or photorealistic outputs. Another thing I found is that my video prompt is already very detailed. If I remove the storyboard section and generate the video without attaching a storyboard, the model still follows the same beats. The main difference is the environment. With a storyboard, it tends to recreate an environment that closely matches the storyboard. I also think storyboards help with certain poses and compositions. If you're curious about the prompts, I've included them below.
0:15

I'm still playing with 3D storyboards for Seedance 2.0. Even when I ask for a 2D video, using a 3D storyboard often pushes the model toward a 3D look. I haven't tested it extensively yet but there definitely seems to be a bias. So 2D storyboards work better for 2D videos, while 3D storyboards are better suited for 3D or photorealistic outputs. Another thing I found is that my video prompt is already very detailed. If I remove the storyboard section and generate the video without attaching a storyboard, the model still follows the same beats. The main difference is the environment. With a storyboard, it tends to recreate an environment that closely matches the storyboard. I also think storyboards help with certain poses and compositions. If you're curious about the prompts, I've included them below.

Kōda

43,256 views • 2 months ago

next, here is how to animate the video once you generated the base image of your ai model, attach the image of your model and the product image in your ai tool and prompt, "she is holding this product" now to animate this scene, use such a simple prompt; "the girl is speaking in her beautiful voice; "this is the most powerful drink in the world... drink it once, and your whole hair is gone" no background music, no sound effects." adding "no background music" is necessory part when you're prompting to VEO 3 or Kling 2.6 and for the drinking scene, i also gave it a very simple prompt; "the girl is drinking, handheld camera shaking. No background music," then i asked nb pro to remove her hair, and then turn it into the using that simple prompt method. note; simple prompts works better than complicated one when it comes to animating your video that's it, if you need any help setting up your ai influencer to promote your product/app or service just DM me here on 𝕏 or comment "want" i'll dm you myself if you know how to make viral content + setup such a beautiful ai model 2026 will be yours, cheers
0:16

next, here is how to animate the video once you generated the base image of your ai model, attach the image of your model and the product image in your ai tool and prompt, "she is holding this product" now to animate this scene, use such a simple prompt; "the girl is speaking in her beautiful voice; "this is the most powerful drink in the world... drink it once, and your whole hair is gone" no background music, no sound effects." adding "no background music" is necessory part when you're prompting to VEO 3 or Kling 2.6 and for the drinking scene, i also gave it a very simple prompt; "the girl is drinking, handheld camera shaking. No background music," then i asked nb pro to remove her hair, and then turn it into the using that simple prompt method. note; simple prompts works better than complicated one when it comes to animating your video that's it, if you need any help setting up your ai influencer to promote your product/app or service just DM me here on 𝕏 or comment "want" i'll dm you myself if you know how to make viral content + setup such a beautiful ai model 2026 will be yours, cheers

ViralOps

21,701 views • 9 months ago

HydraFusion Explained. Part I: How does the Copilot engine know what to optimize for? Your prompt is evaluated across 4 dimensions: ➡ Does it require deep reasoning? (aka. reasoning depth) ➡ Is it a sophisticated problem? (aka. code generation complexity) ➡ Is it untangling a complicated mess? (aka. debugging difficulty) ➡ Is it dominated by tool-use? (aka. tool orchestration needs) Based on this evaluation, a HyDRA score is assigned to determine the capability profile your task needs the most and to establish a quality bar. Part II: How does it choose a model? Note: It doesn' t pick one model to handle the entire job e2e, (that's Auto mode). Instead, it selects 1 of 3 execution workflows and assigns the best model at different stages based on the HyDRA score: 1️⃣ Single ⚙️ How it works: A single model completes the task from start to finish. ⚖️ Rationale: The task comfortably meets the quality bar with one model. Multi-model orchestration would add latency and cost with no meaningful quality gain. 2️⃣ Cascade ⚙️ How it works: A lightweight, cost-efficient model generates the solution. This draft is evaluated against a quality gate and if it falls short of the quality bar, the entire task escalates to a stronger, frontier model. ⚖️ Rationale: Only bring in the big guns when there is concrete evidence that a lightweight model won't meet the quality threshold. 3️⃣ Critique ⚙️ How it works: A lightweight model drafts the initial code and tool interactions. An independent, read-only frontier model reviews that draft and provides feedback. The original lightweight model then performs any targeted revision(s) before the final response is sent to the user. ⚖️ Rationale: Writing code (output tokens) is expensive while reviewing code (input tokens) is cheap. Instead of incurring the cost of a powerhouse writing hundreds of lines from scratch, a cost-efficient model writes the first draft, and the frontier model just reviews it and points out fixes. HydraFusion is available in experimental preview on the GitHub Copilot CLI: /experimental on, /model and select Hydrafusion (Research Preview)
0:13

HydraFusion Explained. Part I: How does the Copilot engine know what to optimize for? Your prompt is evaluated across 4 dimensions: ➡ Does it require deep reasoning? (aka. reasoning depth) ➡ Is it a sophisticated problem? (aka. code generation complexity) ➡ Is it untangling a complicated mess? (aka. debugging difficulty) ➡ Is it dominated by tool-use? (aka. tool orchestration needs) Based on this evaluation, a HyDRA score is assigned to determine the capability profile your task needs the most and to establish a quality bar. Part II: How does it choose a model? Note: It doesn' t pick one model to handle the entire job e2e, (that's Auto mode). Instead, it selects 1 of 3 execution workflows and assigns the best model at different stages based on the HyDRA score: 1️⃣ Single ⚙️ How it works: A single model completes the task from start to finish. ⚖️ Rationale: The task comfortably meets the quality bar with one model. Multi-model orchestration would add latency and cost with no meaningful quality gain. 2️⃣ Cascade ⚙️ How it works: A lightweight, cost-efficient model generates the solution. This draft is evaluated against a quality gate and if it falls short of the quality bar, the entire task escalates to a stronger, frontier model. ⚖️ Rationale: Only bring in the big guns when there is concrete evidence that a lightweight model won't meet the quality threshold. 3️⃣ Critique ⚙️ How it works: A lightweight model drafts the initial code and tool interactions. An independent, read-only frontier model reviews that draft and provides feedback. The original lightweight model then performs any targeted revision(s) before the final response is sent to the user. ⚖️ Rationale: Writing code (output tokens) is expensive while reviewing code (input tokens) is cheap. Instead of incurring the cost of a powerhouse writing hundreds of lines from scratch, a cost-efficient model writes the first draft, and the frontier model just reviews it and points out fixes. HydraFusion is available in experimental preview on the GitHub Copilot CLI: /experimental on, /model and select Hydrafusion (Research Preview)

Julia Muiruri

12,687 views • 15 days ago

What if you could choreograph an entire action scene before generating a single frame? 🥋🎬 That’s what I wanted to test with Pippitofficial’s 3D Director Studio + Seedance 2.5. I created a scene with two girls demonstrating a series of karate moves and used the 3D workspace to figure out the sequence first. The interesting part is that I wasn’t relying on a giant prompt to explain every movement. I could place both characters in the scene, set up the environment, choose props from 150+ available options, and then map out how the performance should unfold. One move at a time. Step in → stance → punch → block → kick → reset → next move. The timeline makes it possible to arrange actions and control their timing, while movement trajectories help define where the characters should go. And then there’s the camera. Instead of hoping the generated video finds the right angle, I could plan the camera movement around the choreography and decide how the sequence should be captured. That’s the part I found most useful. You can think through the scene visually before asking AI to generate the final result. Characters. Movement. Timing. Camera. All planned first. Then Seedance 2.5 turns that setup into the actual video. For me, this feels like a shift from simply prompting AI to actually directing the shot. Try Pippit 3D Director Studio: #3DDirectorStudio #PippitAI #Seedance25 #PippitPartner
0:10

What if you could choreograph an entire action scene before generating a single frame? 🥋🎬 That’s what I wanted to test with Pippitofficial’s 3D Director Studio + Seedance 2.5. I created a scene with two girls demonstrating a series of karate moves and used the 3D workspace to figure out the sequence first. The interesting part is that I wasn’t relying on a giant prompt to explain every movement. I could place both characters in the scene, set up the environment, choose props from 150+ available options, and then map out how the performance should unfold. One move at a time. Step in → stance → punch → block → kick → reset → next move. The timeline makes it possible to arrange actions and control their timing, while movement trajectories help define where the characters should go. And then there’s the camera. Instead of hoping the generated video finds the right angle, I could plan the camera movement around the choreography and decide how the sequence should be captured. That’s the part I found most useful. You can think through the scene visually before asking AI to generate the final result. Characters. Movement. Timing. Camera. All planned first. Then Seedance 2.5 turns that setup into the actual video. For me, this feels like a shift from simply prompting AI to actually directing the shot. Try Pippit 3D Director Studio: #3DDirectorStudio #PippitAI #Seedance25 #PippitPartner

Shabnam Parveen

51,749 views • 15 days ago

The new Krea 3D feature is insanely good. You can turn an image into a 3D model to move & rotate in space - and it guides real-time scene generation. Watch me move this couch around a living room ⬇️
0:18

The new Krea 3D feature is insanely good. You can turn an image into a 3D model to move & rotate in space - and it guides real-time scene generation. Watch me move this couch around a living room ⬇️

Justine Moore

32,728 views • 1 year ago

Nah no, this is not a pre-made or baked Blender model. It is created entirely from scratch using extruded geometry and procedural textures for the mustard hatching pattern on the model... all done with Google Gemini 3 pro AI. In fact, every Three.js 3D model you see on this website has been vibe coded with AI 😎 Live: Code:
0:13

Nah no, this is not a pre-made or baked Blender model. It is created entirely from scratch using extruded geometry and procedural textures for the mustard hatching pattern on the model... all done with Google Gemini 3 pro AI. In fact, every Three.js 3D model you see on this website has been vibe coded with AI 😎 Live: Code:

The Bugged Dev

54,391 views • 8 months ago

50% cheaper Claude inference with just one line of code change! - Remove → model="claude-opus-4-8" - Add → model="ship-like/claude-opus-4-8" I verified the cost saving in my own terminal by invoking the same Anthropic model with the same prompt. The underlying engineering by Ship is actually interesting, and the patterns can be used in any production LLM stack. Essentially, a trained model is a frozen artifact. Every request performs the same forward-pass, whether it extracts a date or refactors a module, because the compute decision was made at training time, before the request existed. Ship makes that decision at inference time instead. After seeing a request, it searches over executions, involving single models, cascades, ensembles, or harnesses with tools, and serves the cheapest one that will match the reference model's quality. This is not a basic router, because picking a cheaper model per query doesn't ensure the cheaper model preserves the original's behavior, like output shape, tool-call patterns, and refusals. Ship measures this equivalence directly. Outputs stay distributionally indistinguishable from the reference model, not token-identical, since two calls to the same model already differ, but they are indistinguishable in capability and behavior. Of course, some requests execute cheaply and some cost Ship more than the customer pays, but the price per request is still a flat 50% off either way, so the execution-cost variance moves off the application's bill entirely. The video below depicts the cost savings and output in my real invocation, and I partnered with the team to put this together.
0:12

50% cheaper Claude inference with just one line of code change! - Remove → model="claude-opus-4-8" - Add → model="ship-like/claude-opus-4-8" I verified the cost saving in my own terminal by invoking the same Anthropic model with the same prompt. The underlying engineering by Ship is actually interesting, and the patterns can be used in any production LLM stack. Essentially, a trained model is a frozen artifact. Every request performs the same forward-pass, whether it extracts a date or refactors a module, because the compute decision was made at training time, before the request existed. Ship makes that decision at inference time instead. After seeing a request, it searches over executions, involving single models, cascades, ensembles, or harnesses with tools, and serves the cheapest one that will match the reference model's quality. This is not a basic router, because picking a cheaper model per query doesn't ensure the cheaper model preserves the original's behavior, like output shape, tool-call patterns, and refusals. Ship measures this equivalence directly. Outputs stay distributionally indistinguishable from the reference model, not token-identical, since two calls to the same model already differ, but they are indistinguishable in capability and behavior. Of course, some requests execute cheaply and some cost Ship more than the customer pays, but the price per request is still a flat 50% off either way, so the execution-cost variance moves off the application's bill entirely. The video below depicts the cost savings and output in my real invocation, and I partnered with the team to put this together.

Akshay 🚀

64,482 views • 2 months ago

Very strange behavior in Claude Code: after specifically telling Claude to use gemini-3-flash-preview, (and even explaining that it's a new model that just came out), Claude refuses to use it, getting stuck in a loop of making non-edits which keep the old version. It gets skeptical and apparently doesn't believe that the model exists (?)
0:19

Very strange behavior in Claude Code: after specifically telling Claude to use gemini-3-flash-preview, (and even explaining that it's a new model that just came out), Claude refuses to use it, getting stuck in a loop of making non-edits which keep the old version. It gets skeptical and apparently doesn't believe that the model exists (?)

Benjamin De Kraker

34,305 views • 8 months ago

World Models are the path for some AI Models in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.
0:19

World Models are the path for some AI Models in the future. But how can we efficiently train these models to not only see the world the way humans do but to see the world in a new and unique way. By visualizing, what is normally sequenced audio patterns, we can derive much more insights. Here we see Paganini in a visual form that can than be described and transcribed into a World Model. We can observe connections in a manner that may not have been clear prior to the digitalization of music and sound in this way. The company with the most valuable potential in building a World Model is Tesla. Not that this type of visualization is being used, but that the mechanisms are in place, and the technology is in place for the company to thrive in this new form of AI.

Brian Roemmele

57,454 views • 10 months ago

How I built with Claude 👇 Prompt: "Design an agency site where services are presented as supermarket product packaging in 3D" Use Three.js with WebGL to render all products in real time in the browser Use Blender to model the packaging then export as GLTF to load in Three.js Use GSAP for the smooth product rotation and hover interactions Save this if you want a portfolio that makes clients feel they are buying something premium 🛒
0:14

How I built with Claude 👇 Prompt: "Design an agency site where services are presented as supermarket product packaging in 3D" Use Three.js with WebGL to render all products in real time in the browser Use Blender to model the packaging then export as GLTF to load in Three.js Use GSAP for the smooth product rotation and hover interactions Save this if you want a portfolio that makes clients feel they are buying something premium 🛒

FHILY👑

76,615 views • 4 months ago

Let me explain the agent loop, simple It's the core of every agentic system, and the part most people overcomplicate It's just this: 1. Send messages to the model 2. Model responds, maybe calls a tool 3. You run the tool 4. Append the result back to messages 5. Repeat until stop_reason is end_turn Step 4 is the whole thing, the write-back is what makes it an agent The model has to see what actually happened before it decides the next move That's the entire loop... understand this cold before you reach for a framework
0:14

Let me explain the agent loop, simple It's the core of every agentic system, and the part most people overcomplicate It's just this: 1. Send messages to the model 2. Model responds, maybe calls a tool 3. You run the tool 4. Append the result back to messages 5. Repeat until stop_reason is end_turn Step 4 is the whole thing, the write-back is what makes it an agent The model has to see what actually happened before it decides the next move That's the entire loop... understand this cold before you reach for a framework

Daniel San

12,514 views • 3 months ago