This is the first part of a 2-part series on Sora. Both parts have been released at the same time. 
Sora is OpenAI’s text-to-video generator. While Sora hasn't been released to the public as of the time I'm writing this episode, the AI model has been made available to red teamers, which OpenAI describes as “domain experts in areas like misinformation, hateful content, and bias”. It has also been made available to some visual artists, designers, and filmmakers.
According to OpenAI, Sora can generate up to one-minute-long videos while sticking to the original prompt entered. It is “able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background.”
However, Sora is not (yet) all-powerful. The current model is not fully able to grasp the cause and effect of an action occurring. “For example, a person might take a bite out of a cookie, but afterward, the cookie may not have a bite mark,” explains OpenAI in their announcement. Sora also struggles with spatial details, such as telling left from right. It also may not be able to follow a specific camera trajectory. 

However, as Shaminder Dulai, an award-winning photo/video journalist wrote in an opinion piece for the Digital Photography Review, “A tool like Sora, which promises to easily and quickly deliver photorealistic humans and real-world environments to anyone, with little to no learning curve, does present a challenge from bad actors seeking to dupe children (and adults), and that should give you pause. It certainly gives me pause.”