Loading video...

Video Failed to Load

Go Home

Following on from last week's GPT 5.5 experiments... Did more experimenting with HTML-in-Canvas to create more interesting page transitions Using our favourite animation library GSAP + the PixiJS Skills Very impressed with how well GPT 5.5 can create WebGL/WebGPU shaders

PixiJS's profile picture

PixiJS

5,525 subscribers

38,927 views • 2 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Experimenting with the pretext library... saw a brick breaker demo and had to try making it in PixiJS. Wanted to see what happens when you add WebGL/WebGPU shaders to the mix. Using bloom, glow, rgb split filters from pixi-filters. plus gsaps physics plugin for the text effect.
0:13

Experimenting with the pretext library... saw a brick breaker demo and had to try making it in PixiJS. Wanted to see what happens when you add WebGL/WebGPU shaders to the mix. Using bloom, glow, rgb split filters from pixi-filters. plus gsaps physics plugin for the text effect.

PixiJS

18,554 views • 3 months ago

More PixiJS 3D testing 👀 Take any live 2D PixiJS content (sprites, text, graphics) and render it onto 3D geometry Our goal is to make working between 2D and 3D as seamless as possible in our WebGPU/WebGL renderer Let us know what features you'd like to see!
0:17

More PixiJS 3D testing 👀 Take any live 2D PixiJS content (sprites, text, graphics) and render it onto 3D geometry Our goal is to make working between 2D and 3D as seamless as possible in our WebGPU/WebGL renderer Let us know what features you'd like to see!

PixiJS

30,530 views • 15 days ago

With html-in-canvas, you can make shader-powered page transitions
0:14

With html-in-canvas, you can make shader-powered page transitions

Max Leiter

37,012 views • 3 months ago

GPT-5.5 helping me with legal work
0:19

GPT-5.5 helping me with legal work

prinz

22,711 views • 2 months ago

Asked GPT-5.5 in Codex to reconstruct this model from the image. Pretty close!
0:12

Asked GPT-5.5 in Codex to reconstruct this model from the image. Pretty close!

Ruben Kostandyan

124,735 views • 2 months ago

Nemotron 3 Ultra performed GPT 5.5 level 10× cheaper We gave three same prompts to build HTML5 canvas with real physics. At first scene we have water in a spinning drum. Galton board - balls through pegs into bins. And a block collision setup with extreme mass differences. Outputs: Nemotron 3 Ultra: 11.3k tokens, $0.051 GPT 5.5: 11.0k tokens, $0.57 Nemotron stays right on GPT 5.5's heels, but at 10× cheaper. The gap in quality is far smaller than the gap in price.
0:15

Nemotron 3 Ultra performed GPT 5.5 level 10× cheaper We gave three same prompts to build HTML5 canvas with real physics. At first scene we have water in a spinning drum. Galton board - balls through pegs into bins. And a block collision setup with extreme mass differences. Outputs: Nemotron 3 Ultra: 11.3k tokens, $0.051 GPT 5.5: 11.0k tokens, $0.57 Nemotron stays right on GPT 5.5's heels, but at 10× cheaper. The gap in quality is far smaller than the gap in price.

atomic.chat

700,057 views • 1 month ago

Zenith took GPT-5.5 from 5th to 1st on Frontier SWE. Emad and Peter H. Diamandis, MD talk it through, and more, on Moonshots.
0:15

Zenith took GPT-5.5 from 5th to 1st on Frontier SWE. Emad and Peter H. Diamandis, MD talk it through, and more, on Moonshots.

Intelligent Internet

11,088 views • 10 days ago

You can ask Codex to update an existing repo to GPT-5.5.
0:16

You can ask Codex to update an existing repo to GPT-5.5.

OpenAI Developers

185,546 views • 2 months ago

GPT Image 2 + Seedance 2.0 - Prompt Share Created on @MartiniArt_ Workflow: Create a character with Midjourney. Turn that character to stylized 3d with GPT Image 2. Create a storyboard with that character sheet. Create the final video using both character sheet and storyboard references.
0:15

GPT Image 2 + Seedance 2.0 - Prompt Share Created on @MartiniArt_ Workflow: Create a character with Midjourney. Turn that character to stylized 3d with GPT Image 2. Create a storyboard with that character sheet. Create the final video using both character sheet and storyboard references.

Kōda

33,726 views • 1 month ago

The AI voice agent in my Apple Watch is now ready! Model: gpt-realtime-2 Thanks to Codex 5.5 xhigh Coming soon: it will be able to see my calendar, create reminders, take notes, and more tools
0:13

The AI voice agent in my Apple Watch is now ready! Model: gpt-realtime-2 Thanks to Codex 5.5 xhigh Coming soon: it will be able to see my calendar, create reminders, take notes, and more tools

Diego | AI 🚀 - e/acc

22,275 views • 1 month ago

Salute to the Qwen team 🫡 We tested Qwen 3.7-Max, Gemini 3.5 Flash, GPT-5.5, and Claude Opus 4.7. The biggest shock came from Qwen. In less than a month (3.6 Max dropped April 20), Qwen went from the worst multimodal output on our sakura tree test, barely keeping up with Gemini, GPT, and Claude , to matching Gemini 3.5 Flash frame for frame on this soccer test, and outperforming GPT-5.5 and Claude Opus 4.7. It rendered a perfectly proportioned soccer player and the most lifelike ball in the entire test. Remarkable spatial reasoning. Also: Gemini 3.5 Flash is now faster than GPT-5.5, which used to be the fastest in our past tests.
0:17

Salute to the Qwen team 🫡 We tested Qwen 3.7-Max, Gemini 3.5 Flash, GPT-5.5, and Claude Opus 4.7. The biggest shock came from Qwen. In less than a month (3.6 Max dropped April 20), Qwen went from the worst multimodal output on our sakura tree test, barely keeping up with Gemini, GPT, and Claude , to matching Gemini 3.5 Flash frame for frame on this soccer test, and outperforming GPT-5.5 and Claude Opus 4.7. It rendered a perfectly proportioned soccer player and the most lifelike ball in the entire test. Remarkable spatial reasoning. Also: Gemini 3.5 Flash is now faster than GPT-5.5, which used to be the fastest in our past tests.

GMI Cloud

75,785 views • 1 month ago

ummm you can create some obnoxiously cool focus rings with the new HTML-in-Canvas API
0:18

ummm you can create some obnoxiously cool focus rings with the new HTML-in-Canvas API

matt rothenberg

261,601 views • 3 months ago

> GPT 5.5 & GPT 5.5 pro release > No wall in site > employees are already talking about the GPT 6 > Deepseek v4 Releases >TPU v8 Releases > Googles getting 960k vera Rubin’s > Tesla Robotaxi reaches 1M miles with no accidents > Stock market all time highs It was a good week bros..
0:13

> GPT 5.5 & GPT 5.5 pro release > No wall in site > employees are already talking about the GPT 6 > Deepseek v4 Releases >TPU v8 Releases > Googles getting 960k vera Rubin’s > Tesla Robotaxi reaches 1M miles with no accidents > Stock market all time highs It was a good week bros..

Chris

29,512 views • 2 months ago

GPT-5.5 + GPT Image 2 in Codex is insane 🤯 The watch components generation + alignment was one shot.
0:11

GPT-5.5 + GPT Image 2 in Codex is insane 🤯 The watch components generation + alignment was one shot.

Katia Gil Guzman

760,267 views • 2 months ago

GPT 5.5 natively generating CAD in Fusion via adam
0:13

GPT 5.5 natively generating CAD in Fusion via adam

Zach Dive

33,944 views • 1 month ago

Anthropic’s Mythos raised the bar for AI vuln detection but kept it invite-only. GPT-5.5 is OpenAI’s answer, and it’s open to all. We had early access. Ran the benchmarks. Blackbox GPT-5.5 already beats whitebox GPT-5. Best pentesting model we’ve tested. Read our analysis:
0:14

Anthropic’s Mythos raised the bar for AI vuln detection but kept it invite-only. GPT-5.5 is OpenAI’s answer, and it’s open to all. We had early access. Ran the benchmarks. Blackbox GPT-5.5 already beats whitebox GPT-5. Best pentesting model we’ve tested. Read our analysis:

XBOW

208,701 views • 2 months ago

New Claude Sonnet 5 performs at GPT 5.5 level 6x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics crash demos Prompts: - A car crashes into a brick wall - A wrecking ball destroys a house - A catapult throws a rock at a castle wall Outputs: Sonnet 5: 15,047 tokens, $0.15 Opus 4.8: 23,063 tokens, $0.58 Sonnet 4.6: 25,824 tokens, $0.39 GPT 5.5: 31,152 tokens, $0.94 Sonnet 5 did as well as Opus 4.8 and GPT 5.5 on all three tests. In the wrecking ball test, it beat Opus 4.8. The cable moves smoothly and every hit connects. In the catapult test, it beat GPT 5.5. The rock always lands inside the wall. Sonnet 5 still needs better detail and graphics. But it used fewer tokens than every other model
0:18

New Claude Sonnet 5 performs at GPT 5.5 level 6x cheaper! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics crash demos Prompts: - A car crashes into a brick wall - A wrecking ball destroys a house - A catapult throws a rock at a castle wall Outputs: Sonnet 5: 15,047 tokens, $0.15 Opus 4.8: 23,063 tokens, $0.58 Sonnet 4.6: 25,824 tokens, $0.39 GPT 5.5: 31,152 tokens, $0.94 Sonnet 5 did as well as Opus 4.8 and GPT 5.5 on all three tests. In the wrecking ball test, it beat Opus 4.8. The cable moves smoothly and every hit connects. In the catapult test, it beat GPT 5.5. The rock always lands inside the wall. Sonnet 5 still needs better detail and graphics. But it used fewer tokens than every other model

atomic.chat

725,764 views • 10 days ago

Can Opus 4.8 design beautiful landing pages? Yes it can, but requires a ton of skills and prompts. It's a little worse than GPT 5.5.
0:18

Can Opus 4.8 design beautiful landing pages? Yes it can, but requires a ton of skills and prompts. It's a little worse than GPT 5.5.

Meng To

73,341 views • 1 month ago

GPT-5.5 by Reasoning Effort: I've asked it in Codex to create a physics-based visualisation of RL cycles for different sized models (70b, 1t, 10t), to demonstrate how the amount of RL you can do differs by model size. My assessment of each: - Low: weird slop - Medium: kinda cooked - High: sort of tried but ultimately incoherent - Extra High: elite - really nice idea and well executed Obviously this is just one shot, but worth trying different reasoning levels for the new models, medium seems to be pretty good for GPT-5.5 and it was really bad for many previous GPT models.
0:15

GPT-5.5 by Reasoning Effort: I've asked it in Codex to create a physics-based visualisation of RL cycles for different sized models (70b, 1t, 10t), to demonstrate how the amount of RL you can do differs by model size. My assessment of each: - Low: weird slop - Medium: kinda cooked - High: sort of tried but ultimately incoherent - Extra High: elite - really nice idea and well executed Obviously this is just one shot, but worth trying different reasoning levels for the new models, medium seems to be pretty good for GPT-5.5 and it was really bad for many previous GPT models.

Peter Gostev (SF: 22-26 June)

209,258 views • 2 months ago

OpenAl's GPT-5.5 is rolling out today as a GA model Microsoft Foundry. Longer context. Smarter agents. More cost efficient. Learn more:
0:13

OpenAl's GPT-5.5 is rolling out today as a GA model Microsoft Foundry. Longer context. Smarter agents. More cost efficient. Learn more:

Microsoft Azure

27,828 views • 2 months ago