The first thing Brownlee mentions is object permanence. Sora has issues with displaying, say, a specific object in an individual's hand throughout the runtime of the video. Sometimes the object will move or just suddenly disappear. Just like with AI text, Sora's AI video suffers from hallucinations.

In an early Sora review, Brownlee questioned how OpenAI's video model was trained. Were his own videos used without his knowledge?

OpenAI’s highly-anticipated AI text-to-video generator, Sora, will become available to everyone today. In a video posted on Monday, Marques Brownlee confirmed its imminent release and detailed his experience using Sora over the past few weeks,