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.

Someone built an interactive GPT visualizer that shows every single step of how a model generates output. Not just the final answer. The actual pipeline.

Aman

14,763 subscribers

107,278 views • 7 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

GPT-6 Astra built a full 3D model of the human cell in 30 minutes. Biology didn't see this coming. Not a diagram. Not an illustration. A complete, detailed model built from scratch in a single session. The same tool that handles code, design, and 3D geometry is now walking into science.

GPT-6 Astra built a full 3D model of the human cell in 30 minutes. Biology didn't see this coming. Not a diagram. Not an illustration. A complete, detailed model built from scratch in a single session. The same tool that handles code, design, and 3D geometry is now walking into science.

Zentrix⌚️

52,097 views • 19 days ago

🔥 img2threejs × GPT-6 Astra × Hyper3D Live showcase: This is probably one of the most commercially valuable workflows I’ve tested so far. Image → Hyper3D → img2threejs → GPT-6 Astra → Interactive Three.js experience. 1/ Hyper3D handles the 3D reconstruction. 2/ img2threejs turns that result into a structured workflow that an AI coding model can actually work with. 3/ And GPT-6 Astra follows the img2threejs pipeline - turning the reconstructed asset into a structured, editable, and interactive Three.js experience with animation, VFX, lighting, and application logic. The important part isn’t just generating a 3D model, It’s what happens after the model exists. Instead of ending with a static asset, you can continue building around it with code: → Games → Interactive product experiences → 3D websites → Character showcases → Virtual worlds → Rapid prototypes 3D generation becomes the beginning of the workflow - not the final output. And when you combine high-quality reconstruction with an AI model capable of understanding and building the surrounding experience, the path from image → 3D → usable product becomes dramatically shorter. This is exactly the direction I want to push img2threejs. More experiments with OpenAI GPT-6 Astra × Hyper3D by Deemos are coming this month. 👨‍🍳

🔥 img2threejs × GPT-6 Astra × Hyper3D Live showcase: This is probably one of the most commercially valuable workflows I’ve tested so far. Image → Hyper3D → img2threejs → GPT-6 Astra → Interactive Three.js experience. 1/ Hyper3D handles the 3D reconstruction. 2/ img2threejs turns that result into a structured workflow that an AI coding model can actually work with. 3/ And GPT-6 Astra follows the img2threejs pipeline - turning the reconstructed asset into a structured, editable, and interactive Three.js experience with animation, VFX, lighting, and application logic. The important part isn’t just generating a 3D model, It’s what happens after the model exists. Instead of ending with a static asset, you can continue building around it with code: → Games → Interactive product experiences → 3D websites → Character showcases → Virtual worlds → Rapid prototypes 3D generation becomes the beginning of the workflow - not the final output. And when you combine high-quality reconstruction with an AI model capable of understanding and building the surrounding experience, the path from image → 3D → usable product becomes dramatically shorter. This is exactly the direction I want to push img2threejs. More experiments with OpenAI GPT-6 Astra × Hyper3D by Deemos are coming this month. 👨‍🍳

Nick

12,239 views • 20 days ago

Ok, this is absurd. I built an Agent on CREAO that runs a full mini-movie pipeline. One line in, it writes the script, boards it, generates every scene on Seedance 2.5, and hands me a finished episode. Here's how:

Ok, this is absurd. I built an Agent on CREAO that runs a full mini-movie pipeline. One line in, it writes the script, boards it, generates every scene on Seedance 2.5, and hands me a finished episode. Here's how:

Muhammad Ayan

108,834 views • 5 days ago

🌶️I have infinite creatives now. That's not a metaphor. I built a system that generates complete video ads from a single marketing angle. Not scripts. Not briefs. Actual finished videos. Voiceover, animation, captions, assembled and exported. One command. Minutes, not weeks. I studied a ton of ad creators. Figured out how they think about scenes, pacing, hooks, visual styles. What actually converts vs what just looks cool. Then I built something none of them have. A fully automated pipeline that goes from a marketing angle to a rendered .mp4 without touching a single tool manually. today alone - already 300+. That's just the beginning. I literally cannot stop printing creatives.

🌶️I have infinite creatives now. That's not a metaphor. I built a system that generates complete video ads from a single marketing angle. Not scripts. Not briefs. Actual finished videos. Voiceover, animation, captions, assembled and exported. One command. Minutes, not weeks. I studied a ton of ad creators. Figured out how they think about scenes, pacing, hooks, visual styles. What actually converts vs what just looks cool. Then I built something none of them have. A fully automated pipeline that goes from a marketing angle to a rendered .mp4 without touching a single tool manually. today alone - already 300+. That's just the beginning. I literally cannot stop printing creatives.

Andrei Lunev, PhD

13,513 views • 5 months ago

Introducing Odyssey-2 Pro—a frontier world model that generates long-running, interactive simulations in 720p! We're also launching the first world model API, to enable devs to build magical apps. We're now in the GPT-2 era of world models. Let the explosion of apps commence!

Introducing Odyssey-2 Pro—a frontier world model that generates long-running, interactive simulations in 720p! We're also launching the first world model API, to enable devs to build magical apps. We're now in the GPT-2 era of world models. Let the explosion of apps commence!

Odyssey

166,568 views • 8 months ago

I built a natural language CLI. It generates Python scripts to answer your question, then auto-executes them in the cwd. You will not believe how capable this simple pattern is. Rawdogging gpt-4 from the command line. Rawdog. 1/

I built a natural language CLI. It generates Python scripts to answer your question, then auto-executes them in the cwd. You will not believe how capable this simple pattern is. Rawdogging gpt-4 from the command line. Rawdog. 1/

Grant♟️

432,017 views • 2 years ago

Claude Fable 5 built a 3D product website with Claude Code Generate an image of a product with the Magnific MCP, and convert it into a 3D model. Download that model and give it to Fable 5 to develop an interactive page with. Here's the final result + prompts:

Claude Fable 5 built a 3D product website with Claude Code Generate an image of a product with the Magnific MCP, and convert it into a 3D model. Download that model and give it to Fable 5 to develop an interactive page with. Here's the final result + prompts:

Jerrod Lew

33,687 views • 3 months ago

I was so terminally bored I scraped hundreds of VTubers and built a full interactive network that shows EVERY connection between VTubers and their model artists + riggers. 5 guys rigged half of Hololive. One rigger owns the top indie scene. Interactive VTuber → Artist/Rigger network + leaderboard

I was so terminally bored I scraped hundreds of VTubers and built a full interactive network that shows EVERY connection between VTubers and their model artists + riggers. 5 guys rigged half of Hololive. One rigger owns the top indie scene. Interactive VTuber → Artist/Rigger network + leaderboard

✨ 𝗗𝗔𝗥𝗞 ✨ Shitposter Detective

274,500 views • 6 months ago

Someone just created a 3D interactive $DOG visualizer that not only lets you explore the 85,645 wallets that currently hold $DOG but also lets you see the exact relationship between all 257,675 wallets that have ever held $DOG 🤯

Someone just created a 3D interactive $DOG visualizer that not only lets you explore the 85,645 wallets that currently hold $DOG but also lets you see the exact relationship between all 257,675 wallets that have ever held $DOG 🤯

Leonidas 🧡 $DOG

25,053 views • 1 month ago

📢GaussianGPT: autoregressive 3D Gaussian scene generation. We introduce a GPT-style model that directly generates 3D Gaussian scenes, token by token, in a series of small, discrete decision steps. Generation, completion, and large-scale outpainting in a single pipeline. Unlike diffusion-based approaches, GaussianGPT explicitly models the scene distribution at every step, allowing for quite flexible scene synthesis. 🌐 ▶️ Great work by Nicolas von Lützow, Barbara Roessle, Katharina Schmid

📢GaussianGPT: autoregressive 3D Gaussian scene generation. We introduce a GPT-style model that directly generates 3D Gaussian scenes, token by token, in a series of small, discrete decision steps. Generation, completion, and large-scale outpainting in a single pipeline. Unlike diffusion-based approaches, GaussianGPT explicitly models the scene distribution at every step, allowing for quite flexible scene synthesis. 🌐 ▶️ Great work by Nicolas von Lützow, Barbara Roessle, Katharina Schmid

Matthias Niessner

152,626 views • 6 months ago

The interesting part isn't just generating a product. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. It's going from a draft → real-looking product → product page in one continuous workflow. I started with a simple product concept in Dreamina. Then GPT-6 Astra interpreted the draft, built out the actual product, and used it to create the final product detail page. Dreamina's pricing also makes it practical to generate a bunch of early concepts instead of overthinking the first one. This workflow is definitely worth experimenting with. #Dreamina #DreaminaPartner

The interesting part isn't just generating a product. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. It's going from a draft → real-looking product → product page in one continuous workflow. I started with a simple product concept in Dreamina. Then GPT-6 Astra interpreted the draft, built out the actual product, and used it to create the final product detail page. Dreamina's pricing also makes it practical to generate a bunch of early concepts instead of overthinking the first one. This workflow is definitely worth experimenting with. #Dreamina #DreaminaPartner

Md Riyazuddin

61,601 views • 16 days ago

Anthropic ex-engineer runs an internal graph that costs $6 a month and catches what a $300,000 eval suite misses. No retrieval layer. Seven nodes and one rule about who's allowed to change their mind. He published the whole schema. His version starts from the opposite idea. A graph is not an execution order. It's a memory of why. Seven nodes. Every edge carries the reason it exists: > INTENT - states what the task is for. Never how > DECOMPOSE - splits it into steps, each with a stated assumption > WORKER - executes one step. Sees nothing else > AUDIT - checks the output against the assumption, not the goal > DRIFT - compares the current step to INTENT and flags divergence > LEDGER - stores every decision with the assumption that justified it > ROOT - holds the graph, and when an assumption breaks, re-runs every step built on it Six nodes act. One node remembers why they acted. Every step carries the assumption that made it correct, so a false one only reruns what stood on it. That's the entire design. A pipeline that forgets its reasons has to redo all of it or trust all of it. He replayed a month of agent runs. 4,100 steps, 380 built on an assumption that was wrong by day three. The old pipeline shipped all 380 and linked none of them. Everyone else builds graphs where output moves forward and the reasoning evaporates. He built one where the reason travels with the result. The blast radius is the output nobody else produces. The article below is the full build - node prompts, the assumption format, the invalidation rule that finds every step downstream of a broken one. Save it. You'll want it open in the other

Anthropic ex-engineer runs an internal graph that costs $6 a month and catches what a $300,000 eval suite misses. No retrieval layer. Seven nodes and one rule about who's allowed to change their mind. He published the whole schema. His version starts from the opposite idea. A graph is not an execution order. It's a memory of why. Seven nodes. Every edge carries the reason it exists: > INTENT - states what the task is for. Never how > DECOMPOSE - splits it into steps, each with a stated assumption > WORKER - executes one step. Sees nothing else > AUDIT - checks the output against the assumption, not the goal > DRIFT - compares the current step to INTENT and flags divergence > LEDGER - stores every decision with the assumption that justified it > ROOT - holds the graph, and when an assumption breaks, re-runs every step built on it Six nodes act. One node remembers why they acted. Every step carries the assumption that made it correct, so a false one only reruns what stood on it. That's the entire design. A pipeline that forgets its reasons has to redo all of it or trust all of it. He replayed a month of agent runs. 4,100 steps, 380 built on an assumption that was wrong by day three. The old pipeline shipped all 380 and linked none of them. Everyone else builds graphs where output moves forward and the reasoning evaporates. He built one where the reason travels with the result. The blast radius is the output nobody else produces. The article below is the full build - node prompts, the assumption format, the invalidation rule that finds every step downstream of a broken one. Save it. You'll want it open in the other

wast3

306,873 views • 1 month ago

FABLE GENERATES A FULL 3D CITY IN A SINGLE PROMPT RUN Fable generated a complete, interactive 3D city in a single continuous run. With no step-by-step debugging or manual code splits, the model synthesized procedural building layouts, lighting, and spatial geometry in one go, proving its single-shot 3D web graphics capabilities.

FABLE GENERATES A FULL 3D CITY IN A SINGLE PROMPT RUN Fable generated a complete, interactive 3D city in a single continuous run. With no step-by-step debugging or manual code splits, the model synthesized procedural building layouts, lighting, and spatial geometry in one go, proving its single-shot 3D web graphics capabilities.

0xMarioNawfal

47,559 views • 2 months ago

I built an interactive model showing the basic math that drives the value of raw land The key takeaway: The price of land primarily reflects the likelihood you'll be allowed to build something there, not the dirt

I built an interactive model showing the basic math that drives the value of raw land The key takeaway: The price of land primarily reflects the likelihood you'll be allowed to build something there, not the dirt

Devon ☀️

57,683 views • 5 months ago

Most people think prompting is just writing better sentences Anthropic shows why that's wrong This 32-minute workshop breaks down how prompts are built for production Not prompt hacks Not "act as" Not another $300 course Actual systems Evals Edge cases Model migration Agent loops Good prompt is not one message It's a workflow the model can follow, test and improve This matters because every new claude opus or sonnet will still reward the same rules Watch the prompting playbook Bookmark it before your next bad ai answer is just a bad setup

Most people think prompting is just writing better sentences Anthropic shows why that's wrong This 32-minute workshop breaks down how prompts are built for production Not prompt hacks Not "act as" Not another $300 course Actual systems Evals Edge cases Model migration Agent loops Good prompt is not one message It's a workflow the model can follow, test and improve This matters because every new claude opus or sonnet will still reward the same rules Watch the prompting playbook Bookmark it before your next bad ai answer is just a bad setup

rari

391,493 views • 3 months ago

$100,000/mo in compute credits to startups and institutions that apply and join the Apodex Frontier Program. I'm posting the link below. Beyond the compute credits, you get access to the Apodex Deep Discover solver, powered by one of the most interesting models I've seen in a while. A quick summary of the Apodex 1.0-H model: 1. The model works like an agent team, not a single model looping over the same context. An orchestrator decomposes a task and spawns specialized subagents on demand. Each subagent works asynchronously with its own context and tools. This behavior was trained into the model. 2. The model can improve its own reasoning through a generate → verify → revise process. It generates an answer, an internal grader evaluates it, and finally, it revises it based on that feedback over multiple rounds. The grader never sees the answer key, so the process does not rely on memorization. 3. Verification is handled by independent agents, not the same model checking itself. It uses a dedicated verification team, including a conflict reviewer, a fact checker, and a draft reviewer, to audit the output before delivery. It backs every output claim with an explicit evidence chain. To give you an idea of how powerful Apodex-1.0-H is, it can coordinate up to 150 subagents executing over 15,000+ steps within a single task. If you are a research institution, academic lab, or research startup, consider applying.

$100,000/mo in compute credits to startups and institutions that apply and join the Apodex Frontier Program. I'm posting the link below. Beyond the compute credits, you get access to the Apodex Deep Discover solver, powered by one of the most interesting models I've seen in a while. A quick summary of the Apodex 1.0-H model: 1. The model works like an agent team, not a single model looping over the same context. An orchestrator decomposes a task and spawns specialized subagents on demand. Each subagent works asynchronously with its own context and tools. This behavior was trained into the model. 2. The model can improve its own reasoning through a generate → verify → revise process. It generates an answer, an internal grader evaluates it, and finally, it revises it based on that feedback over multiple rounds. The grader never sees the answer key, so the process does not rely on memorization. 3. Verification is handled by independent agents, not the same model checking itself. It uses a dedicated verification team, including a conflict reviewer, a fact checker, and a draft reviewer, to audit the output before delivery. It backs every output claim with an explicit evidence chain. To give you an idea of how powerful Apodex-1.0-H is, it can coordinate up to 150 subagents executing over 15,000+ steps within a single task. If you are a research institution, academic lab, or research startup, consider applying.

Santiago

16,891 views • 2 months ago

GPT Image 2 is insanely good...I generated a 360° equirectangular panorama in Happycapy with just a skill + prompt. Step 1: Select the generate-image skill Step 2: Enter a prompt like: “Use a frontend 360 viewer to display an equirectangular image of […] using the GPT-Image-2 model.” Wanna see how you all get creative with this

GPT Image 2 is insanely good...I generated a 360° equirectangular panorama in Happycapy with just a skill + prompt. Step 1: Select the generate-image skill Step 2: Enter a prompt like: “Use a frontend 360 viewer to display an equirectangular image of […] using the GPT-Image-2 model.” Wanna see how you all get creative with this

Min Zhou

344,889 views • 5 months ago

I wanted to see how far I could take an AI-generated poster after the generation step. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. Started with Dreamina and generated the full poster. Then I handed it to GPT-6 Astra and had Astra use Photoshop to separate the visual elements into individual layers. So the final result isn't just a PNG anymore - I can independently tweak the background, subject, text and other elements. Dreamina's pricing makes it much easier to generate a few different versions first without overthinking every attempt. This could save designers a ridiculous amount of cleanup time. #Dreamina #DreaminaPartner

I wanted to see how far I could take an AI-generated poster after the generation step. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. Started with Dreamina and generated the full poster. Then I handed it to GPT-6 Astra and had Astra use Photoshop to separate the visual elements into individual layers. So the final result isn't just a PNG anymore - I can independently tweak the background, subject, text and other elements. Dreamina's pricing makes it much easier to generate a few different versions first without overthinking every attempt. This could save designers a ridiculous amount of cleanup time. #Dreamina #DreaminaPartner

Isabella

40,823 views • 16 days ago

The interesting part isn't just generating a commercial with AI. It's the workflow behind it. GPT-6 Astra → generate the 3D white model CapCut PC → bring the model into the project Seedance 2.5 → generate the commercial-style scene CapCut PC → adjust pacing and build the bullet-time effect Edit Pilot / AI Extend → refine or extend the video when needed This feels much closer to an actual production pipeline than a one-click AI video generator. The 3D model gives the concept a visual starting point. Seedance 2.5 turns that concept into moving footage. Then CapCut PC lets me review the result, make changes and shape the final version. The key is that generation and editing happen within the same workflow, so the first output does not have to be the final one. #GPT6Astra #CapCutPC #AIVideo #Seedance25

The interesting part isn't just generating a commercial with AI. It's the workflow behind it. GPT-6 Astra → generate the 3D white model CapCut PC → bring the model into the project Seedance 2.5 → generate the commercial-style scene CapCut PC → adjust pacing and build the bullet-time effect Edit Pilot / AI Extend → refine or extend the video when needed This feels much closer to an actual production pipeline than a one-click AI video generator. The 3D model gives the concept a visual starting point. Seedance 2.5 turns that concept into moving footage. Then CapCut PC lets me review the result, make changes and shape the final version. The key is that generation and editing happen within the same workflow, so the first output does not have to be the final one. #GPT6Astra #CapCutPC #AIVideo #Seedance25

OtakuMachine

56,103 views • 14 days ago