Loading video...

Video Failed to Load

Go Home

I've been testing GPT-5.2 for a while now. It's a serious leap forward in complex reasoning, math, coding, and simulations. It built a full 3D graphics engine in a single file. Interactive controls. 4K export. One shot. The pace of progress is unreal.

skirano's profile picture

Pietro Schirano

102,688 subscribers

154,616 views • 6 months ago •via X (Twitter)

ArtsEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

2/ In GitHub Copilot, GPT-5.2 is a fantastic multi-purpose model, especially when it comes to long-context and reasoning when coding or investigating a complex code base. Also available today.
0:22

2/ In GitHub Copilot, GPT-5.2 is a fantastic multi-purpose model, especially when it comes to long-context and reasoning when coding or investigating a complex code base. Also available today.

Satya Nadella

70,468 views • 6 months ago

Had early access to GPT-5.4 and Pro. They are very good. One fun illustration of progress, this is the same prompt I used in GPT-4 below (making a 3D space inspired by Piranesi) now in GPT-5.4 Pro. There were no errors, made in a single prompt plus one to "make it better."
0:28

Had early access to GPT-5.4 and Pro. They are very good. One fun illustration of progress, this is the same prompt I used in GPT-4 below (making a 3D space inspired by Piranesi) now in GPT-5.4 Pro. There were no errors, made in a single prompt plus one to "make it better."

Ethan Mollick

188,306 views • 3 months ago

GPT-5.1 is now live in Augment Code. It's our strongest model yet for complex reasoning tasks, such as identifying and fixing bugs or complex multi-file edits. Rolling out to users now. We’re excited for you to try it!
1:02

GPT-5.1 is now live in Augment Code. It's our strongest model yet for complex reasoning tasks, such as identifying and fixing bugs or complex multi-file edits. Rolling out to users now. We’re excited for you to try it!

Augment Code

67,211 views • 7 months ago

I've been using this (Pseudo-)Global Variable system in Unreal for a while now and thought I would share it. It enables you to have certain variables in one place through a data asset and you can even tweak them while the game is running. Full Tutorial:
0:42

I've been using this (Pseudo-)Global Variable system in Unreal for a while now and thought I would share it. It enables you to have certain variables in one place through a data asset and you can even tweak them while the game is running. Full Tutorial:

Cobra Code

10,799 views • 2 months ago

Everyone’s hyping up GPT-5’s coding agent. I decided to test it. So I built a Duolingo-style app for AI learning in a single shot inside Factory. This thing is scary good:
0:51

Everyone’s hyping up GPT-5’s coding agent. I decided to test it. So I built a Duolingo-style app for AI learning in a single shot inside Factory. This thing is scary good:

Robin Delta

22,791 views • 10 months ago

i gave a 9B model an agentic OS and told it to build Octopus Invaders from scratch. Qwen 3.5 9B running through Hermes Agent with full tool access on a single 3060 12GB. browser, file system, code execution, terminal. it reads the prompt, plans the architecture, writes every file, and serves the game. one prompt, zero steering, 11 minutes. i've been going back and forth with this model for days now. text, code, reasoning. it handles small chats, batching, bash scripting. at 9B it's fast enough to feel interactive and genuinely useful for local workflows where you'd normally reach for an API. but this is the real test. can it architect and build a full game autonomously without a single correction? it's coding right now. results coming next.
11:40

i gave a 9B model an agentic OS and told it to build Octopus Invaders from scratch. Qwen 3.5 9B running through Hermes Agent with full tool access on a single 3060 12GB. browser, file system, code execution, terminal. it reads the prompt, plans the architecture, writes every file, and serves the game. one prompt, zero steering, 11 minutes. i've been going back and forth with this model for days now. text, code, reasoning. it handles small chats, batching, bash scripting. at 9B it's fast enough to feel interactive and genuinely useful for local workflows where you'd normally reach for an API. but this is the real test. can it architect and build a full game autonomously without a single correction? it's coding right now. results coming next.

Sudo su

65,570 views • 3 months ago

Claude Fable 5 has impressive spatial reasoning capabilities that are immediately relevant for engineering and design: In this example I gave Claude Fable 5 a single photo of a hierarchical mesh torus (image generated using a text-to-image model); and in one shot, no iteration, it built a full interactive 3D simulation: ~1,400 nodes & 4,400 fibers, realistic mass–spring physics you can grab, compress, twist… plus strain-based sonification so you can 'hear' the structure vibrate. It inferred the complete 3D topology from a partial 2D view. ⤵️
2:32

Claude Fable 5 has impressive spatial reasoning capabilities that are immediately relevant for engineering and design: In this example I gave Claude Fable 5 a single photo of a hierarchical mesh torus (image generated using a text-to-image model); and in one shot, no iteration, it built a full interactive 3D simulation: ~1,400 nodes & 4,400 fibers, realistic mass–spring physics you can grab, compress, twist… plus strain-based sonification so you can 'hear' the structure vibrate. It inferred the complete 3D topology from a partial 2D view. ⤵️

Markus J. Buehler

28,671 views • 13 days ago

GPT-5.2-high by OpenAI is off to a strong start in the Code Arena. ⚡️ If you’re new here: Code Arena is where AI models build full web apps, tools, and interactive sites — all from a single prompt. Watch the video to see GPT-5.2-high in action, then try your own prompt and reply with your creation below. ⬇️
1:24

GPT-5.2-high by OpenAI is off to a strong start in the Code Arena. ⚡️ If you’re new here: Code Arena is where AI models build full web apps, tools, and interactive sites — all from a single prompt. Watch the video to see GPT-5.2-high in action, then try your own prompt and reply with your creation below. ⬇️

Arena.ai

246,337 views • 6 months ago

RUSTLANDS - New interactive film OUT NOW @DreamFlareAI Follow a lone wanderer as she hunts for a fabled engine in the endless dunes of a steampunk desert wasteland. I've seriously been pushing the limits of AI for 2D animation on this one :) Be sure to check out the trailer & full interactive short film on the platform (link below)!
0:46

RUSTLANDS - New interactive film OUT NOW @DreamFlareAI Follow a lone wanderer as she hunts for a fabled engine in the endless dunes of a steampunk desert wasteland. I've seriously been pushing the limits of AI for 2D animation on this one :) Be sure to check out the trailer & full interactive short film on the platform (link below)!

Guillaume H.

20,380 views • 1 year ago

Elon Musk on simulation theory: he argues that the 40-year leap from Pong to photorealism proves we will inevitably create perfect simulations. Because a single civilization could run billions of these simulations, the math dictates it is statistically impossible (one in billions) that we are living in the one true "base reality."
1:36

Elon Musk on simulation theory: he argues that the 40-year leap from Pong to photorealism proves we will inevitably create perfect simulations. Because a single civilization could run billions of these simulations, the math dictates it is statistically impossible (one in billions) that we are living in the one true "base reality."

Ian Miles Cheong

108,358 views • 6 months ago

I've been working with caustics for a while in #webGPU and one of the issues I find is that it's hard to handle caustics for complex scenes. It's easy for planes, you can save photons in a texture using either compute and atomics, or additive blending with the rasteriser. 🧵
1:03

I've been working with caustics for a while in #webGPU and one of the issues I find is that it's hard to handle caustics for complex scenes. It's easy for planes, you can save photons in a texture using either compute and atomics, or additive blending with the rasteriser. 🧵

Hat

17,985 views • 1 year ago

It's official. Retopoflow 4 is live! This full rewrite is a massive leap forward in both speed and design. It's a passion project we've been working towards for years and it sets us up to keep improving retopology in Blender for years to come.
1:41

It's official. Retopoflow 4 is live! This full rewrite is a massive leap forward in both speed and design. It's a passion project we've been working towards for years and it sets us up to keep improving retopology in Blender for years to come.

Retopoflow

134,221 views • 8 months ago

i really enjoy 3Blue1Brown's math animations. so i built a tool that converts natural language into math animations using the manim engine and gpt-4o. now you can create your own math animations! give it a try using the link below.
0:27

i really enjoy 3Blue1Brown's math animations. so i built a tool that converts natural language into math animations using the manim engine and gpt-4o. now you can create your own math animations! give it a try using the link below.

Archie Sengupta

370,138 views • 1 year ago

I just built a full 3D world I could actually walk through… from a single prompt. No Blender. No game engine. No complex 3D tools. Just AI. This is OpenArt Worlds and it feels like the future of world creation. 🌍 Let me show you what happened!
0:43

I just built a full 3D world I could actually walk through… from a single prompt. No Blender. No game engine. No complex 3D tools. Just AI. This is OpenArt Worlds and it feels like the future of world creation. 🌍 Let me show you what happened!

SPIDER ◾

64,706 views • 3 months ago

Claude Fable 5 makes new things possible. I one shot a full horror game with it. One prompt. I have never seen AI output a game like this. This is the leap I've been waiting for. 80.3 on SWE-Bench Pro vs Opus 4.8 at 69.2, the biggest jump I have ever seen on that benchmark. It passed GPT 5.5 in both coding and intelligence on Artificial Analysis. I already canceled my $200 ChatGPT Pro plan. It fixed a Bridge Voice bug in one shot that GPT 5.5, Opus 4.7, and Opus 4.8 all failed to crack for 2 months. 10/10. Best model I have ever used. Full review below.
15:50

Claude Fable 5 makes new things possible. I one shot a full horror game with it. One prompt. I have never seen AI output a game like this. This is the leap I've been waiting for. 80.3 on SWE-Bench Pro vs Opus 4.8 at 69.2, the biggest jump I have ever seen on that benchmark. It passed GPT 5.5 in both coding and intelligence on Artificial Analysis. I already canceled my $200 ChatGPT Pro plan. It fixed a Bridge Voice bug in one shot that GPT 5.5, Opus 4.7, and Opus 4.8 all failed to crack for 2 months. 10/10. Best model I have ever used. Full review below.

BridgeMind

19,020 views • 13 days ago

o1-pro is probably the best model i've used for coding, hands down i gave it a pretty complicated codebase and asked it to refactor while referencing docs the difference between claude/gemini/o1 and o1 pro is night and day. first time in a while i've been this impressed. full comparison in the video + code.
7:33

o1-pro is probably the best model i've used for coding, hands down i gave it a pretty complicated codebase and asked it to refactor while referencing docs the difference between claude/gemini/o1 and o1 pro is night and day. first time in a while i've been this impressed. full comparison in the video + code.

Sully

255,372 views • 1 year ago

I've been writing #rstats packages and coding web maps for a decade now. Despite this, while I've always wanted a story map feature in R, I never really knew how. With Claude Sonnet and Cursor, I got a working prototype in a morning, and now it's on CRAN for you to use.
0:20

I've been writing #rstats packages and coding web maps for a decade now. Despite this, while I've always wanted a story map feature in R, I never really knew how. With Claude Sonnet and Cursor, I got a working prototype in a morning, and now it's on CRAN for you to use.

Kyle Walker

21,259 views • 1 year ago

FOR THE THIRD TIME CLICKOLDING IS A DARK INCREMENTAL NARRATIVE GAME BUILT IN UNREAL ENGINE 5 ABOUT THE DISTRESSING MAN IN THE CORNER OF YOUR ROOM, AND THE OBJECT HE WANTS YOU TO CLICK HE WANTS TO WATCH YOU CLICK IT AND IT'S OUT NOW FOR $2.69 ENJOY
0:34

FOR THE THIRD TIME CLICKOLDING IS A DARK INCREMENTAL NARRATIVE GAME BUILT IN UNREAL ENGINE 5 ABOUT THE DISTRESSING MAN IN THE CORNER OF YOUR ROOM, AND THE OBJECT HE WANTS YOU TO CLICK HE WANTS TO WATCH YOU CLICK IT AND IT'S OUT NOW FOR $2.69 ENJOY

Xalavier Nelson Jr.

308,833 views • 1 year ago

"It's one of the biggest blessings and greatest honors I've had in my life." Ryder Meyer always grew up dreaming of being a #GrizFB player. Fast forward to today, and it's been a decorated run for the Fairfield native 🏈 Full story:
2:43

"It's one of the biggest blessings and greatest honors I've had in my life." Ryder Meyer always grew up dreaming of being a #GrizFB player. Fast forward to today, and it's been a decorated run for the Fairfield native 🏈 Full story:

Kyle Hansen

10,493 views • 1 year ago

When using GPT-5.5, it is instantly noticeable how much more powerful it is. In Codex, I gave it a very complex prompt to create London Toy Railway with landmarks and seasons - it did an excellent job in one shot. In the second half of the video you see GPT-5.4 - it was also not bad, but very clearly worse. GPT-5.5's generation is far more ambitious, coherent and with fewer errors. This is obviously a toy example, but I've used it on much more complex real tasks, including a complex app migration and a new hard workflow - it has been working away for many hours without getting stumped. I'm getting more and more addicted to this stuff with every model release.
0:49

When using GPT-5.5, it is instantly noticeable how much more powerful it is. In Codex, I gave it a very complex prompt to create London Toy Railway with landmarks and seasons - it did an excellent job in one shot. In the second half of the video you see GPT-5.4 - it was also not bad, but very clearly worse. GPT-5.5's generation is far more ambitious, coherent and with fewer errors. This is obviously a toy example, but I've used it on much more complex real tasks, including a complex app migration and a new hard workflow - it has been working away for many hours without getting stumped. I'm getting more and more addicted to this stuff with every model release.

Peter Gostev

262,105 views • 2 months ago