OpenAI unveils Sora that turns text into realistic video

On Thursday, OpenAI, the creator of ChatGPT, unveiled its latest advancement in generative artificial intelligence (AI) – a text-to-video generator named Sora. While similar technology has been demonstrated by companies like Google, Meta, and Runway ML, OpenAI’s Sora garnered attention for the high quality of videos it produced in response to written prompts.

CEO Sam Altman invited social media users to submit ideas, and the realistic video generated in response to prompts, such as “an instructional cooking session for homemade gnocchi hosted by a grandmother social media influencer set in a rustic Tuscan country kitchen with cinematic lighting,” left observers astonished.

Despite its impressive capabilities, Sora is not yet publicly available, and OpenAI has provided limited details about its development process. The company, previously involved in legal disputes over the use of copyrighted works to train ChatGPT, has not disclosed the specific imagery and video sources used for Sora’s training.

Red teamers, specialists in areas like misinformation, hateful content, and bias, are actively testing the model. Additionally, OpenAI is developing tools, including a detection classifier, to identify misleading content generated by Sora, highlighting the company’s commitment to addressing ethical concerns and potential societal implications.