A new AI model demonstrates significant progress in generating realistic video from text descriptions. The system, developed by researchers, can create short, coherent clips depicting dynamic scenes based on user prompts. While the technology shows improved temporal consistency and object permanence compared to previous models, experts note limitations in resolution, clip length, and the handling of complex physics. The development is seen as a step forward in generative AI for video, with potential applications in entertainment, education, and prototyping, though ethical concerns regarding deepfakes and misinformation are highlighted as requiring proactive governance. For the full details, read the complete article at https://technologyreview.com/2024/05/15/1090000/ai-video-generation-advances.