---
title: "OpenAI’s Super-Hyped Sora Goes Absolutely Freakshow If You Ask It to Generate Gymnastics Videos"
description: "OpenAI has finally opened its much-hyped Sora video generator to the public — and many of its outputs seem remarkably bad."
date: "2024-12-12"
modified: "2024-12-12"
authors:
  - name: "Noor Al-Sibai"
    job_title: "Senior Staff Writer"
    link: "https://futurism.com/authors/nooralsibai"
url: "https://futurism.com/openai-sora-gymnastics-videos"
categories:
  - "Artificial Intelligence"
  - "OpenAI"
tags:
  - "ai video"
  - "artificial intelligence"
  - "OpenAI"
  - "sora"
---

# OpenAI’s Super-Hyped Sora Goes Absolutely Freakshow If You Ask It to Generate Gymnastics Videos

![OpenAI has finally opened its much-hyped Sora video generator to the public — and many of its outputs seem remarkably bad.](<https://futurism.com/wp-content/uploads/2024/12/openai-sora-gymnastics-videos.jpg>)
*\<em\>Image: Sora AI / Peter Labuza via Bluesky\</em\>*

OpenAI has finally opened its [much-hyped](<https://futurism.com/the-byte/openai-sora-demo>) Sora video generator [to the public](<https://openai.com/index/sora-is-here/>) — and its work isn't exactly blowing us away.

One particular weakpoint: Sora's [attempts to generate videos of](<https://x.com/deedydas/status/1866509455896260813>) gymnasts result in a horrorshow of whirling and morphing limbs that would be more at place among [David Cronenberg](<https://futurism.com/the-byte/ai-david-cronenberg-movie>)'s body horror films than the Olympics.

As venture capitalist [Deedy Das quipped](<https://x.com/deedydas/status/1866509455896260813>) in a thread showing the bizarre creations that "gymnastics is still very much the Turing test for AI video."

https://www.twitter.com/deedydas/status/1866509455896260813

Das went on to [post](<https://x.com/deedydas/status/1866509491497472071>) [three](<https://x.com/deedydas/status/1866509533914468632>) [more](<https://x.com/deedydas/status/1866509567930376458>) uncanny Sora-generated gymnastics videos, and there's more where that came from.

Echoing the venture capitalist, the account associated with the AI for Humans podcast [joked](<https://x.com/AIForHumansShow/status/1866540422325014700>) that "gymnastics are the funniest way to break \[S\]ora."

Indeed, in a video made with the prompt "gymnast flips five times very fast then lands in a bucket of mustard," the same limb confusion as the previous videos is yet again on display — but this time, a waterfall of what looks like yellow paint is attached to the "feet" of the artificial gymnast, making the whole thing look all the slimier.

https://www.twitter.com/AIForHumansShow/status/1866540422325014700

That same account also [had Sora make a video](<https://x.com/AIForHumansShow/status/1866849354364916107>) of a Raygun-esque breakdancer that had a similarly creepy limb confusion effect.

https://www.twitter.com/AIForHumansShow/status/1866849354364916107

Even in videos with less movement, where Sora [often does significantly better](<https://x.com/jay_azhang/status/1866213035175522434>), it struggles with spelling words correctly — a basic imagine generator issue that's emerged as a tell for AI images.

In one post, a self-described "politically homeless bitch" claims that the quality of Sora's videos is "[mind-bending](<https://x.com/Vox_Oculi/status/1866296497714905398>)" — without pointing out that in the last of the four videos of a woman in fascist military uniform, the mask she's wearing misspells "obey" as "oeybey."

In an even more egregious example, vlogger [Marquees Brownlee said](<https://x.com/MKBHD/status/1866152708656488715>) that when he got early access to Sora, it kept outputting "garbled" text despite the often-photorealistic quality of its videos.

"How can \[Sora\] create a photorealistic human but can't spell basic words?" [another user observed](<https://x.com/AaronTheH/status/1866254016944255384>) in a post screenshotting Brownlee's video.

https://www.twitter.com/AaronTheH/status/1866254016944255384

While it certainly has its impressive aspects, Sora by and large seems to be way less sophisticated than [its boosters](<https://x.com/model_mechanic/status/1866183714407141603>) would have had you believe before it launched publicly — a [common theme](<https://futurism.com/the-byte/take-two-ceo-ai-grand-theft-auto>) among AI hypebeasts.

**More on Sora:** [*OpenAI Concerned About Illegal Activity on Sora, Releases It Anyway*](<https://futurism.com/the-byte/openai-release-sora-illegal-activity>)

## Author
At Futurism, I've often been drawn to unpacking the narratives that underlie technological, scientific and medical progress, with a special interest in areas of conflict and ambiguity that end up setting agendas and steering the fates of both elites and the hoi polloi. I'm a committed generalist, but I often find myself returning to work involving NASA and the private space sector, the effects of AI on media and society, and the mechanics of the pharmaceutical industry, with a specific focus on the spread of GLP-1 drugs like Ozempic and Wegovy. Prior to Futurism, I worked for publications ranging from Media Matters and Truthdig to Raw Story and Bustle. I'm also the author of "Myspace Scene Queens," a 2024 title in Instar Books' acclaimed "Remember the Internet" series. My work at Futurism has been cited by outlets including the New Yorker, Slate, Nieman Lab, the Verge, the MIT Technology Review, the Sunday Times, and the Daily Beast. I grew up in North Carolina, attended the University of North Carolina at Asheville, and now live in Brooklyn, New York. In my free time, I'm an avid reader and music fan; you can probably find me at a local poetry reading, concert, underground rave, or DJ set. I'm the proud parent of an ineffable orange cat named Mee-Mow.

### Author social links  
[Bluesky](<https://bsky.app/profile/noorfromfuturism.bsky.social>)