OpenAI, the creators of ChatGPT, have recently introduced an impressive AI model called Sora. This groundbreaking model has the ability to generate an entire one-minute video based solely on text prompts. OpenAI’s Sora blog explains that their aim is to train models that can comprehend and simulate the physical world in motion, ultimately assisting individuals in solving real-world problems that require interaction.
Furthermore, OpenAI CEO Sam Altman showcased this tool on his X account. Altman invited users to provide captions for videos they would like to see, promising to create them using Sora. The outcomes he shared were remarkably lifelike, as numerous users on the platform eagerly responded to his request.
Sam Altman, the CEO of OpenAI, also demonstrated the tool on his X account. In his post, Altman expressed his desire to showcase the capabilities of Sora and requested users to reply with video captions they would like to see. He further mentioned that they would begin creating videos based on the prompts received. Numerous users on the platform responded to his request, and the outcomes he shared appeared remarkably authentic.
OpenAI’s Sora model has garnered significant attention online due to its ability to generate intricate scenes with multiple characters, precise movements, and detailed backgrounds. Not only does the model comprehend user prompts, but it also interprets how these elements manifest in real-world scenarios. OpenAI emphasizes that the model possesses a profound understanding of language, enabling it to accurately interpret prompts and generate captivating characters that express vibrant emotions.
Additionally, Sora can generate multiple shots within a single video, ensuring the characters and visual style persist accurately throughout. However, popular YouTuber Marques Brownlee, also known as MKBHD, has raised valid concerns about the AI-generated nature of these videos. In a recent post, he stated, “Every single one of these videos is AI-generated, and if this doesn’t concern you at least a little bit, nothing will.”
Furthermore, OpenAI will utilize existing safety protocols that were developed for its products using DALL·E 3, which are also applicable to Sora. For example, within an OpenAI product, the company’s text classifier will screen and reject input prompts that violate usage policies, such as those requesting extreme violence, sexual content, hateful imagery, or celebrity likeness. OpenAI has also established robust image classifiers to review every frame of generated videos, ensuring compliance with usage policies before granting user access.
OpenAI is actively engaging with policymakers, educators, and artists worldwide to address concerns and explore the positive applications of this new technology. “We will engage with policymakers, educators, and artists globally to understand their concerns and identify beneficial use cases for this new technology. Despite extensive research and testing, we cannot anticipate all the ways in which people will utilize our technology for good or misuse it. That is why we believe that learning from real-world usage is a crucial aspect of creating and releasing increasingly safe AI systems over time,” states OpenAI.
At present, Sora is exclusively accessible to the red teamers for examining crucial zones in order to identify possible problems or risks. OpenAI is additionally granting access to visual artists, designers, and filmmakers to gather their input on enhancing the model. The blog states, “We are sharing our research progress in its early stages to collaborate with individuals outside of OpenAI and receive their valuable feedback, while also providing the public with a glimpse of the forthcoming AI capabilities.”