A Viral Video of an Impossible Gymnast: The Surprising Insights into AI Video Generation
The Video that Went Viral
On Wednesday, a video from OpenAI’s newly launched Sora AI video generator went viral on social media, featuring a gymnast who sprouts extra limbs and briefly loses her head during what appears to be an Olympic-style floor routine.
The Video in Detail
In the video, we see a view of what looks like a floor gymnastics routine taking place at an Olympics-like sporting event. The subject of the video flips and flails as new legs and arms rapidly and fluidly emerge and morph out of her twirling and transforming body. At one point, about 9 seconds in, she loses her head, and it reattaches to her body spontaneously.
The Reaction and Context
The video inspired plenty of reaction jokes, such as this reply to a similar post on Bluesky: "hi, gymnastics expert here! this is not funny, gymnasts only do this when they’re in extreme distress." We reached out to Deedy Das, the venture capitalist who originally shared the video on X, and he confirmed that he generated the video using Sora.
The Prompt and the Process
Das provided the prompt, which was very long and split into four parts, generated by Anthropic’s Claude, using complex instructions like "The gymnast initiates from the back right corner, taking position with her right foot pointed behind in B-plus stance." Das also shared his experience with text-to-video models, stating that they struggle with complex physics movements like gymnastics.
Lessons Learned from the Video
Das’ experiment with Sora highlights the limitations of current AI video generation technology. "I’ve known for the last 6 months having played with text to video models that they struggle with complex physics movements like gymnastics," he said. "I had to try it [in Sora] because the character consistency seemed improved. Overall, it was an improvement because previously… the gymnast would just teleport away or change their outfit mid-flip, but overall it still looks downright horrifying."
Conclusion
The viral video of an impossible gymnast generated by OpenAI’s Sora AI video generator offers a glimpse into the limitations of current AI video generation technology. While the video may have been intended as a humorous experiment, it inadvertently provides valuable insights into the challenges of generating realistic and coherent video content.
FAQs
Q: What is Sora AI video generator?
A: Sora is a newly launched AI video generator from OpenAI.
Q: What is the purpose of the video?
A: The video is an experiment to demonstrate the limitations of current AI video generation technology.
Q: What are the limitations of current AI video generation technology?
A: Current AI video generation technology struggles with complex physics movements like gymnastics, resulting in nonsensical synthesis errors.
