OpenAI unveiled its latest innovation: Sora, a text-to-video generative AI model.
Sora is the latest generative AI that can create high-quality videos of up to a minute using user prompts. A user can simply type in a text description of what they want to see in the video, and Sora will create it.
The generative AI can create complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background. It can also understand not only what the user has asked for in the prompt, but also how those things exist in the physical world.
The AI, however, is still not ready for public use and has its fair share of limitations. It can, for instance, struggle with some aspects of video generation, such as when simulating the physics of a complex scene and understanding specific instances of cause and effect.
The AI model is also being tested by red teamers — domain experts in areas like misinformation, hateful content, and bias who try to find potential risks and vulnerabilities in the model.
At this point, there is no information yet on when Sora will be available to the public, or how it will be regulated and governed.
