I think you just need to look at the PS5 Pro as proof that more GPU power doesn't translate linearly to better picture quality.

The PS5 Pro has a 67% beefier GPU than the standard PS5 - with a price to match - yet can anyone say the end result is 67% better? Is it even 10% better?

We've been hitting diminishing returns on raw rasterising for years now, a different approach is definitely needed.

Yeah, there's a reason any movie attempting 3D CG with any budget at all has used path tracing for years. It's objectively massively higher quality.

You don't need upscaling or denoising (the "AI" they're talking about) to do raster stuff, but realistic lighting does a hugely better job, regardless of the art style you're talking about. It's not just photorealism, either. Look at all Disney's animated stuff. Stuff like Moana and Elemental aren't photorealistic and aren't trying to be, but they're still massively enhanced visually by improving the realism of the behavior of light, because that's what our eyes understand. It takes a lot of math to handle all those volumetric shots through water and glass in a way that looks good.

DLSS doesn’t work that well. I’m not looking forward to AI replacing artist’s work.

Ray tracing actually will directly change the way games are made. A lot of time is spent by artists placing light sources and baking light maps to realistically light scenery - with ray tracing, you get that realism "for free".

DF did a really interesting video on the purely path traced version of Metro: Exodus and as part of that, the artists talked about how much easier and faster it was to build that version.

Oh, now you're wrong. AI upscaling is demonstrably more accurate than plain old TAA, which is what we used to use in the previous generation. I am NOT offloading compelling NPC dialogue to a crappy chatbot. Every demo I've seen for that application has been absolutely terrible.

Because as complex and hard to decipher as it is, all AI does is inference. Doing inference with graphics is something that has been perfected through decades and is worked on heavily.

Quests and dialogues rely more on the creative thinking of writers, having a satisfying side quest is quite hard and leaving a text generator engine that task is a huge pitfall. It has it's use in generating some bulk texts that can then be proofread, but generating text live? Hell no. Plus, what about voice acting? Will you also steal actors voices so that the garbage text generated is said by "not scarlet johansson" v3? If you think AI will generate smarter behaviours your definition of smart and mine really differ. Will AI be able to rig animations and infer correct rig positions so that the NPC features line up with what they are saying? Mocap and voice acting is done heavily in big productions to get that.