
"What generative AI can't do is create something new that's never been seen. The models are trained on everything that's ever been done before; it can't be trained on that which has never been done. So you will innately see, essentially, all of human art and human experience put into a blender, and you'll get something that is kind of an average of that. So what you can't have is that individual screenwriter's unique lived experience and their quirks."
"Go to the other end of the spectrum [from motion capture] and you've got generative AI, where they can make up a character. They can make up an actor. They can make up a performance from scratch with a text prompt. It's like, no. That's horrifying to me. That's the opposite. That's exactly what we're not doing. He added: I don't want a computer doing what I pride myself on being able to do with actors. I don't want to replace actors, I love working with actors."
Generative AI can fabricate characters, actors, and entire performances from text prompts, producing outputs assembled from prior human art and experience. Models train on everything previously created and cannot be trained on what has never been done, so outputs become an averaged, derivative blend rather than truly original work. Motion-capture preserves live actor-director collaboration and captures individual idiosyncrasies, unique lived experience, and quirks of performers that AI cannot reproduce. Maintaining disciplined, out-of-the-box imagination and high creative standards elevates real-time human performance and protects the sacredness of artists creating live.
Read at www.theguardian.com
Unable to calculate read time
Collection
[
|
...
]