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.

everyone's been sharing this 'bouncing ball visualization' and having AIs recreate it - so for a fun challenge, I recreated it without any AI assistance. ill break down the math behind the visualization - and what makes it challenging for AI - in this thread:

N8 Programs

6,774 subscribers

26,695 views • 1 year ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

this might be the coolest-looking football AI visualization I ever created

this might be the coolest-looking football AI visualization I ever created

SkalskiP @ CVPR2026

592,161 views • 1 year ago

It would take weeks to create these VFX the traditional way... But with AI, you can do it in minutes — right from home! All you need are the tools and prompts I’m sharing in this thread 🧵👇 Bookmark this for later

It would take weeks to create these VFX the traditional way... But with AI, you can do it in minutes — right from home! All you need are the tools and prompts I’m sharing in this thread 🧵👇 Bookmark this for later

TechHalla

109,322 views • 1 year ago

I built a dashboard for the AI bottlenecks market → 250+ stocks tracked → Risk Profile, Fundamentals The coolest part is the visualization of stocks in a dot plot of year-to-date performance + AI exposure calculation Made it for myself but can share if you are interested

gum

10,541 views • 1 month ago

Transformer: Multi-Head Attention ~ Math vs Code 🔢💻 ~ I made this visualization to show you how to implement the multi-head attention math in PyTorch within 50 LoC. Multi-Head Attention is what makes the Transformer's performance outstanding. It captures and represents more diverse linguistic relationships and patterns, and attends to different learned input embedding spaces. The parallel computing design also makes the model more efficient.

Transformer: Multi-Head Attention ~ Math vs Code 🔢💻 ~ I made this visualization to show you how to implement the multi-head attention math in PyTorch within 50 LoC. Multi-Head Attention is what makes the Transformer's performance outstanding. It captures and represents more diverse linguistic relationships and patterns, and attends to different learned input embedding spaces. The parallel computing design also makes the model more efficient.

Yan Chen

33,255 views • 1 year ago

3. Arcwise AI: A plugin for Google Sheets that instantly understands, cleans, and ingests data in your sheets using AI. Ask Arcwise any question about your spreadsheet and it will do the math for you and give you the right answer in seconds:

3. Arcwise AI: A plugin for Google Sheets that instantly understands, cleans, and ingests data in your sheets using AI. Ask Arcwise any question about your spreadsheet and it will do the math for you and give you the right answer in seconds:

Zain Kahn

24,378 views • 3 years ago

These AI videos are blowing up on social media… don’t ask me why. But what I do know is how to make them! And I’m breaking it down for you in this thread. 🧵👇 Bookmark this for later—it’s got all the prompts you’ll need.

These AI videos are blowing up on social media… don’t ask me why. But what I do know is how to make them! And I’m breaking it down for you in this thread. 🧵👇 Bookmark this for later—it’s got all the prompts you’ll need.

TechHalla

58,327 views • 1 year ago

For the Hoseok girlies who've been down bad and putting in the work for so long—this era is your reward. Soak it in. You’ve earned it. 😘

For the Hoseok girlies who've been down bad and putting in the work for so long—this era is your reward. Soak it in. You’ve earned it. 😘

Hoseokiepedia

19,234 views • 1 year ago

I'm seeing a lot of people saying it is just a bad upscaling instead of Gen AI, but it is indeed Gen AI animation. There are things going on in it that just don't make any sense for puppet animation. Here are some parts that make it clear, I slowed down the video so it's easier to notice the chunky parts. I checked the past ADs and it's possible to notice details (from an animator's POV) that are common and make sense for human work, so it was definitely a choice to use AI on this new AD

I'm seeing a lot of people saying it is just a bad upscaling instead of Gen AI, but it is indeed Gen AI animation. There are things going on in it that just don't make any sense for puppet animation. Here are some parts that make it clear, I slowed down the video so it's easier to notice the chunky parts. I checked the past ADs and it's possible to notice details (from an animator's POV) that are common and make sense for human work, so it was definitely a choice to use AI on this new AD

mei ✨ live2d animator

1,114,142 views • 5 months ago

This a a bit of fun- I set up a chatGPT shortcut as the action button for my Apple Watch and now I’m using it 10x more. It’s what Siri could have been / could be! This, custom instructions, and comments on churn/growth for AI apps in my latest blog post- (And this time w the right video 😂)

This a a bit of fun- I set up a chatGPT shortcut as the action button for my Apple Watch and now I’m using it 10x more. It’s what Siri could have been / could be! This, custom instructions, and comments on churn/growth for AI apps in my latest blog post- (And this time w the right video 😂)

andrew chen

29,048 views • 2 years ago

I know the game was overall a bummer Sunday but it still absolutely rules that they went for it on 4th and 17 and then did this. I love seeing Rice call for the ball, realize a defender was going to break that way, then find the space behind him.

I know the game was overall a bummer Sunday but it still absolutely rules that they went for it on 4th and 17 and then did this. I love seeing Rice call for the ball, realize a defender was going to break that way, then find the space behind him.

Seth Keysor

78,470 views • 7 months ago

an AI old man looksmaxxing 3 videos. 36 million views. i recreated it in 5 minutes like and reply "FLOW" for the exact workflow (must be following so i can dm)

an AI old man looksmaxxing 3 videos. 36 million views. i recreated it in 5 minutes like and reply "FLOW" for the exact workflow (must be following so i can dm)

Primal Robin

65,419 views • 4 months ago

I think I am hooked to Google AI Studio - it is so freaking good. been testing it all night with all kinds of things and its been super impressive. Check this demo of a fun sound project i am working on. (sound on 🔊) Completely built with AI studio and ElevenLabs. What a time to be a builder !!

I think I am hooked to Google AI Studio - it is so freaking good. been testing it all night with all kinds of things and its been super impressive. Check this demo of a fun sound project i am working on. (sound on 🔊) Completely built with AI studio and ElevenLabs. What a time to be a builder !!

Vamsi Batchu

42,631 views • 5 months ago

Kling 01 for AI cartoons - worth it or not? 💣 I created this short scene and a tutorial so you can test it yourself. Here’s the breakdown 👇

Kling 01 for AI cartoons - worth it or not? 💣 I created this short scene and a tutorial so you can test it yourself. Here’s the breakdown 👇

Framer 🇱🇹

31,062 views • 6 months ago

This is the game GPT-5.5 built for me in one shot, featured on the release page. What makes it different from previous AI-generated games is how fun it actually feels to play. The controls are smooth, and every shape is generated from scratch in Three.js.

This is the game GPT-5.5 built for me in one shot, featured on the release page. What makes it different from previous AI-generated games is how fun it actually feels to play. The controls are smooth, and every shape is generated from scratch in Three.js.

Pietro Schirano

80,965 views • 1 month ago

One of my absolute favorite HEY features is the ability to quickly rename any email thread. This doesn't change the subject for anyone else — it just makes the change on my end. For example, I get a receipt from an auction house that says "Receipt of payment". That's not helpful. So I just click it and type "Rago Auction dining table ceramics September 2025 paid invoice receipt" and now I know what it is, what it's for, and it's a whole lot easier to search for or locate later. So much better.

One of my absolute favorite HEY features is the ability to quickly rename any email thread. This doesn't change the subject for anyone else — it just makes the change on my end. For example, I get a receipt from an auction house that says "Receipt of payment". That's not helpful. So I just click it and type "Rago Auction dining table ceramics September 2025 paid invoice receipt" and now I know what it is, what it's for, and it's a whole lot easier to search for or locate later. So much better.

Jason Fried

59,467 views • 8 months ago

This could be huge for AI storytelling. I've tried so many AI lipsync tools and have never been satisfied. This is my first try with Hedra Character-3 and it's blown me away. It was so easy. I uploaded a track from Suno and an image from Midjourney and it just worked.

This could be huge for AI storytelling. I've tried so many AI lipsync tools and have never been satisfied. This is my first try with Hedra Character-3 and it's blown me away. It was so easy. I uploaded a track from Suno and an image from Midjourney and it just worked.

TomLikesRobots🤖

42,716 views • 1 year ago

Feminism didn’t just change what women believe. It changed how they interpret reality. In this episode, I break down the 3 mechanisms behind female grievance and how it hardens into identity. Watch here:

Feminism didn’t just change what women believe. It changed how they interpret reality. In this episode, I break down the 3 mechanisms behind female grievance and how it hardens into identity. Watch here:

Hannah Spier, MD

16,094 views • 1 month ago

I know of 100s of private archives that have never been digitalized and never been online. I spent decades tracking them down for AI training. It is the most valuable data in the world and AI companies could care less about it or waste time using the wrong folks. Here is one:

I know of 100s of private archives that have never been digitalized and never been online. I spent decades tracking them down for AI training. It is the most valuable data in the world and AI companies could care less about it or waste time using the wrong folks. Here is one:

Brian Roemmele

68,416 views • 3 months ago