fabiopolimeni

The rationale is when you do not use 3D models to keep subjects consistent over multiple scenes it becomes too unpredictable and you would need way too many trial and errors. 3D helps with it. Then, if you even want to have that very same character starting from a specific pose it will more likely you will give up to the likes of the AI model rather than the other way around.

Yes, the 3D data is extracted and then fed back to 2D image generation models like Flux and a relight step, at least in the examples above.

AI can create bugs, sure, as well as humans do. With time, I am more inclined to think it will be easier to ask an AI to fix them for us rather than the other way around.

There is a non-intuitive feature of current LLMs, and that is, they are capable of refining over and over their own previous outcome. You can ask to revisit it, to improve it, check it, etc etc. use this to fix its own bugs.

Uhm…, even you use something low-code, or even no-code tool, you still have to learn how to code (former) or learn how to use some kind of visual scripting tool (latter).

If you could simply type in plain English what are the mechanics you have in mind instead, then this new (simpler) way of creating game logic it may has the potential to unleash creativity from a broader audience.

It is like saying why would I need a photoshop brush if I can manually paint every single pixel canvas 1 by 1. Not the same thing imo.

I think you are right with most of your observations.

Why do you think that using something like createOrUodateRule could limit the ability to produce complex behaviour?