OpenAI’s text-to-video model, Sora, is driving the internet crazy

In a groundbreaking announcement, Microsoft-backed OpenAI unveiled its latest venture into the world of artificial intelligence with the introduction of Sora, cutting-edge software designed to create minute-long videos based on text messages. The reveal on Thursday sparked a whirlwind of reaction online, with users expressing awe and amusement at the possibilities this futuristic technology offers.

According to the company’s statement, Sora is currently available for red teaming, a process that involves identifying potential flaws in the AI ​​system. Additionally, visual artists, designers and filmmakers can use Sora to get feedback on the model’s capabilities, opening the door to a new realm of creative possibilities.

The statement highlighted Sora’s ability to create complex scenes with multiple characters, specific types of movement, and precise details of both subject and background. In particular, the software can create multiple downloads in a single video, providing a level of sophistication that captures the imagination of Internet users.

As news of Sora’s capabilities spread, social media platforms were flooded with wild prompts, imagining scenarios that ranged from the lofty to the absurd. “A giant cathedral is full of cats. There are cats everywhere you look. A man enters the cathedral and bows before the giant cat king sitting on a throne,” one user challenged Sora and shared the resulting video on the microblogging platform X (formerly Twitter), the post amassed over 1.5 million projections.

OpenAI CEO Sam Altman also took to X with a happy announcement about the amazing AI model. “We’d love to show you what Sora can do, reply with captions for the videos you want to see and we’ll start making some!” Altman kindly offered in a post that garnered the most incredible responses.

From building bicycles in an ocean “with different animals as athletes riding the bicycles” captured by a drone camera to “a wizard wearing a pointed hat and a blue robe with white stars, casting a spell that shoots lightning from his hand and holding an old tome in his other hand,” Sora’s renderings have captivated all netizens.

However, the way it called for and praised the text-to-video model’s renderings of reality and fantasy soon sparked a new wave of memes. Many X-users poked fun at Sora’s ability to pick up on nonsensical prompts by sharing really weird video clips and jokingly attributing them to OpenAI’s latest invention.

One user wrote: “Sora by OpenAI is simply amazing. Here was my prompt: Create a video of a politician drinking water when faced with difficult questions during a national television interview,” and attached a clip of Indian Prime Minister Narendra Modi appearing on a talk show.

Many are milking this new meme format to share silly clips from Indian movies. “Sora by OpenAI is simply amazing. Here was my prompt: make a video of a girl playing basketball with a football in a tennis dress on a golf course,” another X user joked, using a quote from director David Dhawan’s 1999 film. Haseena Maan Jayegistarring Sanjay Dutt and Govinda.

Anticipating the confusion that awaits the world as Sora and similar technologies take off, a user X’s post about a ‘prompt’ and Indian crime film SinghamHis fighting streak was mistaken for a genuine response from Sora.

In the original post, the user described the prompt they supposedly fed the AI ​​model as: “A nimble Indian policeman, in denim jeans and a black polo shirt, steps out of a drifting car wearing aviators, shoots at the tires of another car, causing turn over. Quickly, he pulls out the driver just as the car turns over him.” This description was accompanied by a short quote from Singham something that worried Canadian psychologist and public figure Jordan Peterson. “Amazing. Bye Hollywood. Nice to meet you,” Peterson marveled at Sora’s alleged creation.

Not everyone seems too impressed or humored by this latest technological marvel. According to OpenAI, Sora is a work in progress, it can confuse the spatial details of a prompt and have difficulty following a certain camera trajectory. An exhibit of this “flaw” can be seen in a viral video Sora created following “a cat that wakes up its sleeping owner by asking for breakfast.”

In the video, the sleeping owner’s hand fuses to the blanket while the cat grows a “fifth leg” in a disturbing deformity. “Remember how upset people were because Elsa’s hair was cut to her shoulder to get that really good shot? You? And now people are coming like “holy that 5 legged cat looks so real!” protested one critic.

Another mixed humor with fear and posed: “Me in court watching as they play AI footage of a crime I never committed.” “It’s completely over. How can you ever trust what you see anymore? AI is in desperate need of regulation and should be banned from any commercial use,” said one critic among many calling for a ban or strict regulation of the emerging technology.

Have something to add to the story? Share it in the comments below.