Just a few years ago, artificial intelligence struggled to generate a realistic video of Will Smith eating spaghetti. Today, AI-generated videos can look almost indistinguishable from real footage. In 2023, a bizarre AI-generated clip showing Will Smith eating spaghetti went viral across the internet. His facial expressions were distorted, his hands moved unnaturally, and the spaghetti seemed to behave in ways that completely defied physics. Instead of looking like an ordinary dinner, the video became one of the internet’s most recognizable examples of AI struggling to recreate human movement. But what makes the clip so fascinating today is how quickly it became outdated. In just a few years, AI video generation has made enormous progress, producing increasingly realistic faces, smoother movements, more convincing lighting, and scenes that would have seemed nearly impossible in 2023. The original spaghetti video has even become an unofficial benchmark for demonstrating how far the technology has advanced. By comparing early AI-generated footage with newer results, the difference becomes immediately obvious. Of course, modern AI video still makes mistakes, particularly with complex movements, physical interactions, and consistency. But the speed of improvement raises a fascinating question. If artificial intelligence has progressed this dramatically in just a few years, what will AI-generated videos look like a few years from now? What once seemed like an impossible technological challenge has already become a reminder of how quickly the future can arrive. Follow @Explaining to learn something worth knowing every time you open Instagram. #ai #technology #memes #explore #explaining
@explainingWatching it in its original place is always the most accurate source.
This video is being watched 1.2× faster than the hourly-views median of same-length videos on the same platform.
Why this video worked
Every line below is computed from this video’s own numbers. No guesses, no filler.
- The title asks a question
The title asks a question. A question pushes viewers to wait for the answer and to comment.
The numbers
All of it comes from the API. If a value is missing you see a dash — nothing is estimated in its place.
📈 Growth history
The real view record that builds up as we measure the video again and again.
A free scorecard derived from this video’s own numbers — separate from the AI Lab, costs no tokens.
🔍 Deep Analysis
Open this video with AI
The numbers above tell you how well the video is doing. The AI Lab looks inside it: it reads the opening frame, the edit and the sound, and answers “how would you do this”.
- Hook score (0–10) and why it stops the scroll
- First 3 seconds — opening frame and composition
- Why it went viral — one clear answer
- Edit / structure — how the video is built
- Target audience + music/sound strategy
- Actionable recipe — step by step, how you catch it
After the analysis you can ask follow-up questions about the same video.
@explaining — more from this creator
Their other videos in our pool. Seeing what one account repeats is the fastest way to spot the pattern.