OpenAI has introduced Sora, a text-to-video AI model capable of creating videos from text prompts, showcasing potential with scenes like turtles biking across oceans.
While not public yet, the technology stirred excitement and concerns over job displacement and misinformation. OpenAI CEO Sam Altman demonstrated Sora’s abilities on Thursday, including its challenges with complex physics and spatial details.
An OpenAI X post said:
Prompt: “Several giant woolly mammoths approach treading through a snowy meadow, their long woolly fur lightly blows in the wind as they walk, snow covered trees and dramatic snow capped mountains in the distance, mid afternoon light with wispy clouds and a sun high in the distance creates a warm glow, the low camera view is stunning capturing the large furry mammal with beautiful photography, depth of field.”
As well as this, Altman requested ideas for other prompts on X and subsequently created a series of videos. These videos included cyclists in water, in addition to a cooking video and footage of two dogs conducting a podcast on a mountain.
Despite limitations, Sora’s realistic visuals raise ethical issues in distinguishing AI-generated content. OpenAI plans safety measures and collaboration to mitigate misuse, as the FTC proposes rules against AI impersonations.
A spokesperson for OpenAI stated in an email that the company does not plan to make the model widely available in its products soon. They explained that the purpose of sharing their research progress at this stage is to solicit early feedback from the AI community. Furthermore, OpenAI mentioned in a post that their aim is to teach AI to understand and simulate the physical world in motion. This effort is directed towards developing models that assist in solving problems requiring interaction with the real world. In their blog post, OpenAI acknowledged the unpredictability of both the beneficial uses and potential abuses of their technology. They emphasized the importance of learning from real-world applications as a crucial aspect of developing and releasing safer AI systems progressively.
Featured image: Credit: OpenAI
