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.

Codex with GPT-5.4 in fast mode built that in 6 minutes. Procedural world generation + rendering in an offscreen buffer, then rendering the scene in matrix-style glyph + walking around. Running in the browser.

Thomas Ricouard

47,191 subscribers

16,100 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

gpt-image-2 is here, available today in the API and Codex. The most capable image generation model yet, built for production-grade workflows with stronger text rendering, layout, editing, resolution, and multilingual rendering.

gpt-image-2 is here, available today in the API and Codex. The most capable image generation model yet, built for production-grade workflows with stronger text rendering, layout, editing, resolution, and multilingual rendering.

OpenAI Developers

181,719 views • 2 months ago

🟢🔵 Geometry nodes for realtime procedural rendering in Unity. Fast, arbitrary mesh generation and animation. #b3d #geometrynodes #gamedev

🟢🔵 Geometry nodes for realtime procedural rendering in Unity. Fast, arbitrary mesh generation and animation. #b3d #geometrynodes #gamedev

Mirza Beig

179,185 views • 1 year ago

Codex got more speed. With /fast mode, GPT-5.4 runs 1.5x faster with the same intelligence and reasoning. Move through coding tasks, iteration, and debugging while staying in flow.

Codex got more speed. With /fast mode, GPT-5.4 runs 1.5x faster with the same intelligence and reasoning. Move through coding tasks, iteration, and debugging while staying in flow.

OpenAI Developers

279,891 views • 4 months ago

GPT-5.4 built this for me in 3 prompts. It hacked the NES Mario ROM to expose RAM events, then created a JS emulator that could send browser requests so every character in the game is controlled by an AI lmaooo

GPT-5.4 built this for me in 3 prompts. It hacked the NES Mario ROM to expose RAM events, then created a JS emulator that could send browser requests so every character in the game is controlled by an AI lmaooo

Pietro Schirano

314,409 views • 4 months ago

Wait… I’m actually obsessed with Codex + GPT-5.4 🤯 Built a Club Penguin clone in 6 prompts. Then used to make it multiplayer. Didn’t expect this but… OpenAI might've officially converted me to Codex for vibe-coding.

Wait… I’m actually obsessed with Codex + GPT-5.4 🤯 Built a Club Penguin clone in 6 prompts. Then used to make it multiplayer. Didn’t expect this but… OpenAI might've officially converted me to Codex for vibe-coding.

Safinaz Elhadary

50,501 views • 4 months ago

Casually rendering ~a hundred million triangles, in the browser. All thanks to Sunag's cool Nanite-style renderer for Three.js. I've added GLB-to-meshlet and PBR rendering to it, very exciting to see where this is going!

Casually rendering ~a hundred million triangles, in the browser. All thanks to Sunag's cool Nanite-style renderer for Three.js. I've added GLB-to-meshlet and PBR rendering to it, very exciting to see where this is going!

herbst

206,012 views • 1 month ago

Source2 Viewer is now matching in game rendering and movement (almost) in CS2. The game isn't running at all here, S2v is doing all the processing and rendering, all done through reverse engineering.

Source2 Viewer is now matching in game rendering and movement (almost) in CS2. The game isn't running at all here, S2v is doing all the processing and rendering, all done through reverse engineering.

Angel

162,488 views • 4 months ago

The latest models from OpenAI – GPT-5.4 and GPT-5.3-Codex – are already in your JetBrains IDE. See how Jan-Niklas Wortmann uses Codex with Skills to get task updates on his phone.

The latest models from OpenAI – GPT-5.4 and GPT-5.3-Codex – are already in your JetBrains IDE. See how Jan-Niklas Wortmann uses Codex with Skills to get task updates on his phone.

JetBrains

15,074 views • 4 months ago

The performance of multi-viewport rendering is not different from the single-viewport mode in #Tellusim Engine. It allows using an enormous number of screens/HMDs to a single PC, rendering the same scene using multiple GPUs. A single 2080Ti can easily run 5 2k screens with Google Map Tiles API data.

The performance of multi-viewport rendering is not different from the single-viewport mode in #Tellusim Engine. It allows using an enormous number of screens/HMDs to a single PC, rendering the same scene using multiple GPUs. A single 2080Ti can easily run 5 2k screens with Google Map Tiles API data.

Alexander Zapryagaev

54,505 views • 2 years ago

Introducing developer mode for browser use in Chrome and the Codex in-app browser. Codex can use the Chrome DevTools Protocol (CDP) to debug browser issues by profiling JavaScript performance and inspecting console output, network traffic, and page state.

Introducing developer mode for browser use in Chrome and the Codex in-app browser. Codex can use the Chrome DevTools Protocol (CDP) to debug browser issues by profiling JavaScript performance and inspecting console output, network traffic, and page state.

OpenAI Developers

374,353 views • 1 month ago

Our voxel engine rendering technique heavily uses levels of details to try and keep high performance in the browser! Made with Three.js on #webgpu

Our voxel engine rendering technique heavily uses levels of details to try and keep high performance in the browser! Made with Three.js on #webgpu

AresRPG - The Sui MMORPG

14,694 views • 7 days ago

60 seconds in a minute = 6 60 minutes in an hour = 6 24 hours in a day = 6 You live in a 666 time matrix. ⏳ Let that sink in. 📕

60 seconds in a minute = 6 60 minutes in an hour = 6 24 hours in a day = 6 You live in a 666 time matrix. ⏳ Let that sink in. 📕

vegastar

43,062 views • 1 year ago

⚠️The video content is in Chinese. This is an experimental video created by rendering the visuals with Python and then compiling them into a video.

⚠️The video content is in Chinese. This is an experimental video created by rendering the visuals with Python and then compiling them into a video.

Toynya(SFW only)

14,033 views • 1 year ago

THE CAB@L BUILT UNDERGROUND CITIES AND TUNNELS WITH MAG LIFT JET TRAINS 🚆 THAT GO AROUND THE WORLD IN NO TIME NEW YORK TO PORTUGAL IN 20 MINUTES .

THE CAB@L BUILT UNDERGROUND CITIES AND TUNNELS WITH MAG LIFT JET TRAINS 🚆 THAT GO AROUND THE WORLD IN NO TIME NEW YORK TO PORTUGAL IN 20 MINUTES .

Diana PatriQts ARE UNITED❤️🇺🇸❤️🙏

78,341 views • 1 year ago

OpenAI built the Sora Android app (which hit #1 app in the world) in just 18 days with the help of Codex

OpenAI built the Sora Android app (which hit #1 app in the world) in just 18 days with the help of Codex

Lenny Rachitsky

79,801 views • 7 months ago

Claude Opus 4.6 vs GPT-5.3 Codex aren't just different models. They're different engineers. Opus 4.6: → 1M token context window → Reads the whole codebase before deciding → Asks "should we do this?" → Failure mode: overanalyzes, hesitates GPT-5.3 Codex: → 200K tokens, built for speed → Decides fast, acts, iterates → Asks "how fast can I ship this?" → Failure mode: locks in a flawed assumption early Think: Opus = your architect Codex = your operator Pick the one that matches the task.

Claude Opus 4.6 vs GPT-5.3 Codex aren't just different models. They're different engineers. Opus 4.6: → 1M token context window → Reads the whole codebase before deciding → Asks "should we do this?" → Failure mode: overanalyzes, hesitates GPT-5.3 Codex: → 200K tokens, built for speed → Decides fast, acts, iterates → Asks "how fast can I ship this?" → Failure mode: locks in a flawed assumption early Think: Opus = your architect Codex = your operator Pick the one that matches the task.

The Startup Ideas Podcast (SIP) 🧃

59,604 views • 5 months ago

DLSS in workbench. The quality of 1spp rendering is way higher compared to the other built-in denoisers, and for half the cost. The comparison changes at higher spps.

DLSS in workbench. The quality of 1spp rendering is way higher compared to the other built-in denoisers, and for half the cost. The comparison changes at higher spps.

Max Liani

48,257 views • 3 months ago

we’ve been building an internal Isaac Sim tool that lets us prompt sims. swapped in gpt-5.4 and it one-shotted every asset in this datacenter scene. @openai cooked

we’ve been building an internal Isaac Sim tool that lets us prompt sims. swapped in gpt-5.4 and it one-shotted every asset in this datacenter scene. @openai cooked

Shrey Kothari

46,017 views • 4 months ago

❌ Avoid resolving a promise in a server component and block rendering. ✅ Resolve the promise in the client side with `Reac.use()`

❌ Avoid resolving a promise in a server component and block rendering. ✅ Resolve the promise in the client side with `Reac.use()`

George Moller

47,187 views • 1 year ago

I built a Three.js rendering study inspired by Tiny Glade’s painterly aesthetic, and got it running at 120fps in the browser. Over the past few weeks, I’ve been studying how stylized games achieve that soft, handcrafted look in real time. Tiny Glade was a huge inspiration, and I wanted to use the browser as a constraint: no compute shaders, no native GPU access, and single-threaded JavaScript. As part of this study, I implemented: - GPU-driven instanced brick walls with procedural noise jitter and elastic build animations - Tree, bush, and flower rendering with billboard card expansion, wind sway, and grow animations - Procedural grass with terrain conformance and interactive push deformation - Animated water with layered noise, interactive ripples, and Fresnel-based reflections - Procedural terrain with slope-aware triplanar materials, dirt paths, and rocks - A 7-pass post-processing stack with TAA, bloom, depth of field, painterly filtering, ACES tonemapping, 3D LUT color grading, and film grain The hardest part wasn’t writing any single shader. It was making all of these systems work together at high frame rates inside WebGL, where every millisecond counts and performance problems compound quickly across animation, materials, post-processing, and scene management. Some techniques in this study were inspired by analyzing Tiny Glade’s rendering approach, while others were original implementations built from scratch from visual reference. That contrast taught me a lot: recreating an effect is one challenge, but designing your own shaders and systems to achieve a similar feel is a very different one. This is a private educational rendering study. Some temporary placeholder content is being used during the research phase, and any public or production version would use original or properly licensed assets. Huge credit to Pounce Light for the incredible art direction and rendering work in Tiny Glade: Three.js #gamedev #webgl #threejs #rendering #graphics #realtimerendering #shaderdev

I built a Three.js rendering study inspired by Tiny Glade’s painterly aesthetic, and got it running at 120fps in the browser. Over the past few weeks, I’ve been studying how stylized games achieve that soft, handcrafted look in real time. Tiny Glade was a huge inspiration, and I wanted to use the browser as a constraint: no compute shaders, no native GPU access, and single-threaded JavaScript. As part of this study, I implemented: - GPU-driven instanced brick walls with procedural noise jitter and elastic build animations - Tree, bush, and flower rendering with billboard card expansion, wind sway, and grow animations - Procedural grass with terrain conformance and interactive push deformation - Animated water with layered noise, interactive ripples, and Fresnel-based reflections - Procedural terrain with slope-aware triplanar materials, dirt paths, and rocks - A 7-pass post-processing stack with TAA, bloom, depth of field, painterly filtering, ACES tonemapping, 3D LUT color grading, and film grain The hardest part wasn’t writing any single shader. It was making all of these systems work together at high frame rates inside WebGL, where every millisecond counts and performance problems compound quickly across animation, materials, post-processing, and scene management. Some techniques in this study were inspired by analyzing Tiny Glade’s rendering approach, while others were original implementations built from scratch from visual reference. That contrast taught me a lot: recreating an effect is one challenge, but designing your own shaders and systems to achieve a similar feel is a very different one. This is a private educational rendering study. Some temporary placeholder content is being used during the research phase, and any public or production version would use original or properly licensed assets. Huge credit to Pounce Light for the incredible art direction and rendering work in Tiny Glade: Three.js #gamedev #webgl #threejs #rendering #graphics #realtimerendering #shaderdev

Ibrahim Boona

58,625 views • 3 months ago