Netflix launches VOID, a visual language model that can erase objects from a scene and simulate the behavior of remaining objects without them (Thomas Claburn/The Register)

Thomas Claburn / The register:

Netflix launches VOID, a visual language model capable of erasing objects from a scene and simulating the behavior of remaining objects without them.— The video language model revises how objects interact when elements are removed from a scene. — A new Netflix model promises to rewrite the way we make movies.