OpenAI, creator of the highly popular <a href="https://www.thenationalnews.com/uae/government/2024/01/22/president-sheikh-mohamed-announces-artificial-intelligence-council-for-abu-dhabi/" target="_blank">generative artificial intelligence</a> platform ChatGPT, has introduced Sora, which allows users to create videos instantly from text. <a href="https://www.thenationalnews.com/uae/government/2024/02/13/ai-poised-to-change-world-like-mobile-phones-did-says-openais-sam-altman/" target="_blank">The Microsoft-backed company</a> said Sora "can create realistic and imaginative scenes from text instructions" for up to a minute long. Sora, which means "sky" in Japanese, is the latest tool in <a href="https://www.thenationalnews.com/business/technology/2024/02/13/companies-must-be-cautious-introducing-generative-ai-for-consumers-ibm-says/" target="_blank">the AI space</a> and has the potential to further change the way people create things, even as concerns about AI-generated content increase. It is as simple as typing words, phrases or sentences into a prompt, with Sora then generating a scene automatically based on that information. Sora can generate complex scenes with several characters, specific types of motion and detailed subjects and backgrounds, understanding "not only what the user has asked for in the prompt, but also how those things exist in the physical world", OpenAI said. "The model has a deep understanding of language, enabling it to accurately interpret prompts and generate compelling characters that express vibrant emotions," it added. "Sora can also create multiple shots within a single generated video that accurately persist characters and visual style." Based on OpenAI's initial example released on X and those suggested by creators on the social media platform, Sora seems to be able to create videos accurately according to prompts. But the California-based company has acknowledged Sora's current model has weaknesses. "It may struggle with accurately simulating the physics of a complex scene and may not understand specific instances of cause and effect," OpenAI said. "For example, a person might take a bite out of a cookie, but afterwards, the cookie may not have a bite mark. Sora may also confuse spatial details. It may mix up left and right, or struggle following a specific camera trajectory." OpenAI said Sora was available, for now, to "red teamers", or experts who can assess <a href="https://www.thenationalnews.com/business/technology/2024/02/13/companies-must-be-cautious-introducing-generative-ai-for-consumers-ibm-says/" target="_blank">risks and identify potential issues</a> such as misinformation, bias and hateful content. They will be testing the model "adversarially", the company said. Sora will also be open to some visual artists, designers and filmmakers – a "limited number of creators", according to <a href="https://www.thenationalnews.com/business/technology/2023/11/22/sam-altman-openai-who/" target="_blank">OpenAI chief executive Sam Altman</a> – to gain feedback on how to improve the platform and make it more useful for creative professionals. As it stands, Sora is free of charge for these users, who will be granted early access to the model. It is unclear, however, if OpenAI will charge fees once Sora is available to the public. OpenAI has already introduced paid models of ChatGPT and its image creation tool, Dall-E. Like with any other AI platform, there are concerns regarding the content Sora can generate. OpenAI has said it is working to address these. Aside from its co-operation with red teamers, OpenAI said it was also building tools to help detect misleading content, including a "detection classifier" that can tell when a video was generated by Sora. OpenAI's text classifier will "check and reject text input prompts that are in violation of our usage policies", in cases when a user requests content related to extreme violence, sexual content, hateful imagery, celebrity likeness, or the intellectual property of others, it said. OpenAI also said it would collaborate with policymakers, educators and artists around the world to "understand their concerns and to identify positive use cases for this new technology".