At the Bling Zoo, a tiger wears a giant gold medallion, a monkey wears a jeweled crown, and a turtle chews on a bowl of diamonds.
Unfortunately, this fantastic destination does not exist. It is a creation of Sora, the new text-to-video artificial intelligence program from ChatGPT maker OpenAI.
“Bling Zoo” was just one of a series of videos Sora made Thursday when CEO Sam Altman asked his followers on X (formerly Twitter) to submit assignments generated in films.
The results were so ultra-realistic that one observer commented: “This one convinced me that the future is here and things will work out.”
One user asked Sora to create an ‘instructional cooking session for homemade gnocchi, hosted by a social media influencer grandma, in a rustic Tuscan country kitchen with cinematic lighting’
This led to the most realistic video featuring a human that Altman posted on Thursday. Users were amazed at how realistic the woman’s hands were – a notoriously difficult subject for AI images to recreate
Altman kicked off the stunt with a tweet saying, “We’d love to show you what Sora can do, please reply with captions for videos you’d like to see and we’ll make some!” He wrote.
‘Don’t hold back on the details or the level of difficulty!’ he added in a follow-up post.
The prompts soon came in:
“A wizard wearing a pointy hat and a blue robe with white stars casting a spell that shoots lightning from his hand and holding an ancient tome in the other hand,” one replyer wrote.
“A half duck and half dragon flies through a beautiful sunset with a hamster dressed in adventure gear on his back,” wrote another.
Altman provided the results and posted some of Sora’s creations, collected in the following video:
One observer compared it to Interdimensional Cable, an episode of the science fiction TV show Rick and Morty, in which a special cable box allowed viewers to glimpse television in alternate realities – a world where everyone is made of corn, for example.
‘Bling Zoo’ and other videos like it weren’t far off.
In response to Sora’s video of ‘A bicycle race on the ocean with various animals as athletes cycling with drone camera view’, Sora delivered a video that led one commenter to speculate about Sora’s supremacy over Dall-E, one of the existing generative AI systems. art programs:
“I feel like every frame shot of Sora is better than Dalle,” they wrote.
Sora made short videos of user prompts submitted via X, leading some to compare the results to a sci-fi view in an alternate universe
The results were eerily realistic
“A cycling race on the ocean with different animals as athletes cycling with drone camera footage,” one follower asked.
And Sora delivered.
Same when someone asked Altman to show Sora “Two Golden Retrievers Podcasting on Top of a Mountain.”
For one video, a commenter asked for a response
The resulting video showed just that, and the AI-generated woman even waved her hand to show that she had normal fingers – which can be notoriously difficult for AI. Often AI-generated people have too many or too few fingers.
“Big flex waving those fingers in slow-mo!” wrote one commenter. “And there are only ten!” replied another.
Sora will initially launch to select creators, Altman wrote on X. He and OpenAI have not announced when it will be released to the general public.
One particularly impressed X user concluded that ‘AGI is here’.
When an X user asked for “Two golden retrievers podcasting on top of a mountain,” Sora delivered
The acronym stands for artificial general intelligence, an AI system that can operate independently without human control, understand itself and learn new skills.
Such a system could be able to solve complex mathematical or scientific problems that could take humans years to unravel, some scientists hope.
However, AGI is both a goal and a fear among computer scientists working with AI, as some worry that such a system could view humans as a threat that must be eliminated.
In Sora’s case, the computing power won’t destroy humanity, but it will create 10-second videos based on people’s playful prompts.