Loading video...

Video Failed to Load

Go Home

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.

Amank1412's profile picture

Aman

13,941 subscribers

106,955 views • 4 months ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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!
0:52

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

165,984 views • 5 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/
0:46

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♟️

431,535 views • 2 years 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.
0:22

🌶️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 • 2 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
0:39

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

273,747 views • 4 months 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:
0:29

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 • 27 days 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
0:30

📢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

151,925 views • 3 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
0:53

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 ☀️

57,449 views • 3 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
32:27

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

390,180 views • 1 month 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
0:45

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

341,771 views • 2 months ago

Built a custom GPT that generates 1,000 perfect LinkedIn Sales Navigator leads in just 14 seconds! Want access? Like & Comment "GPT" below and I'll DM the link (make sure we're connected). Check out the demo video below.
1:18

Built a custom GPT that generates 1,000 perfect LinkedIn Sales Navigator leads in just 14 seconds! Want access? Like & Comment "GPT" below and I'll DM the link (make sure we're connected). Check out the demo video below.

Colin Gallagher

15,055 views • 1 year ago

Holy shit… Someone just made horror movies interactive. It’s called ScaryStories. live, an AI that generates entire horror worlds that you control in real-time. No pre-written scripts. No predictable endings. Just pure, adaptive terror. Here’s how: ↓
1:05

Holy shit… Someone just made horror movies interactive. It’s called ScaryStories. live, an AI that generates entire horror worlds that you control in real-time. No pre-written scripts. No predictable endings. Just pure, adaptive terror. Here’s how: ↓

FELIX

63,182 views • 6 months ago

ONE PROMPT IN CHATGPT IMAGE 2 JUST REPLACED AN ENTIRE $5,000-$50,000 BRAND DESIGN TEAM Full brand identity. Colors, typography, logo style, aesthetic. All generated in one single prompt. Here's the exact workflow: Step 1: Paste one prompt asking for a complete brand identity. GPT Image 2 generates everything – color palette, fonts, logo direction, overall visual style. Step 2: Use that output as context for every asset you generate after. Campaign visuals, shop graphics, product mockups, social posts – all stay consistent and on-brand automatically. The result: A full visual identity that looks like a real design team built it. Clean text rendering. Consistent style across every single asset. Design agencies charge $5,000-$50,000 for brand identity work. GPT Image 2 does it in one prompt. The full prompt that makes this work is in the video below. Bookmark this post, you'll want to come back to it.
0:48

ONE PROMPT IN CHATGPT IMAGE 2 JUST REPLACED AN ENTIRE $5,000-$50,000 BRAND DESIGN TEAM Full brand identity. Colors, typography, logo style, aesthetic. All generated in one single prompt. Here's the exact workflow: Step 1: Paste one prompt asking for a complete brand identity. GPT Image 2 generates everything – color palette, fonts, logo direction, overall visual style. Step 2: Use that output as context for every asset you generate after. Campaign visuals, shop graphics, product mockups, social posts – all stay consistent and on-brand automatically. The result: A full visual identity that looks like a real design team built it. Clean text rendering. Consistent style across every single asset. Design agencies charge $5,000-$50,000 for brand identity work. GPT Image 2 does it in one prompt. The full prompt that makes this work is in the video below. Bookmark this post, you'll want to come back to it.

SCOTTY BEAM

12,023 views • 19 days ago

GPT-5 Thinking also built an interactive experience, but seemed a little embarrassed by it, adding lots of little caveats.
0:49

GPT-5 Thinking also built an interactive experience, but seemed a little embarrassed by it, adding lots of little caveats.

Ethan Mollick

28,734 views • 10 months ago

Say goodbye to green screens! DiffusionMat is an AI framework that uses a diffusion model to create refined alpha mattes by correcting the output at every denoising step to look more like the original input image.
0:31

Say goodbye to green screens! DiffusionMat is an AI framework that uses a diffusion model to create refined alpha mattes by correcting the output at every denoising step to look more like the original input image.

Dreaming Tulpa 🥓👑

146,569 views • 2 years ago

Introducing Architect I am releasing the first iteration of a model which generates optimized project plans with a single prompt. Think Linear or JIRA, but for agents. A living model that learns from the gossiping network, and gets smarter with every interaction.
0:25

Introducing Architect I am releasing the first iteration of a model which generates optimized project plans with a single prompt. Think Linear or JIRA, but for agents. A living model that learns from the gossiping network, and gets smarter with every interaction.

Varun

56,906 views • 3 months ago

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)
0:30

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)

Stability AI

35,974 views • 1 year ago

Not a single actual answer from the government today. Imagine being this unprepared for work.
1:17

Not a single actual answer from the government today. Imagine being this unprepared for work.

Melissa Lantsman

28,850 views • 26 days ago

The leverage principle isn't about working harder. It's about getting exponentially more output from the same input. Dalio operates at a 50:1 leverage ratio - meaning every hour he invests generates 50 hours of progress through others. Here's how he built this system:
0:41

The leverage principle isn't about working harder. It's about getting exponentially more output from the same input. Dalio operates at a 50:1 leverage ratio - meaning every hour he invests generates 50 hours of progress through others. Here's how he built this system:

Kevin Henrikson

103,602 views • 1 year ago

I built a kerning visualizer It analyzes every letter pair, then creates the correct letter spacing (optically, not based on an equation), and explains the reasoning behind each adjustment
0:32

I built a kerning visualizer It analyzes every letter pair, then creates the correct letter spacing (optically, not based on an equation), and explains the reasoning behind each adjustment

Hunter Thompson

209,407 views • 15 days ago

Andrej Karpathy just built GPT-2 from scratch on camera! Every line. Every component. Every optimization decision. Transformer blocks. Self-attention. MLP. Mixed precision. Flash Attention. AdamW. Distributed training across GPUs. 4 hours. Free. Not a lecture about how GPT-2 was built. The actual build. Running. Training. Evaluated against the original OpenAI checkpoints. The engineers who watch this do not just understand language models. They understand them at the level required to build the next one. The gap between using AI and being capable of building it is not a PhD program. It is 4 hours with the person who makes this look like something any determined engineer can do.
4:01:25

Andrej Karpathy just built GPT-2 from scratch on camera! Every line. Every component. Every optimization decision. Transformer blocks. Self-attention. MLP. Mixed precision. Flash Attention. AdamW. Distributed training across GPUs. 4 hours. Free. Not a lecture about how GPT-2 was built. The actual build. Running. Training. Evaluated against the original OpenAI checkpoints. The engineers who watch this do not just understand language models. They understand them at the level required to build the next one. The gap between using AI and being capable of building it is not a PhD program. It is 4 hours with the person who makes this look like something any determined engineer can do.

NeilXbt

37,720 views • 2 months ago