"Well, first of all, they're completely wrong," Huang said in response.
"The reason for that is because, as I have explained very carefully,
DLSS 5 fuses controllability of the of geometry and textures and
everything about the game with generative AI," Huang continued.
He added that developers
can still "fine-tune the generative AI" to make it match their style,
adding that DLSS 5 adds generative capability to the existing geometry
of the game, but that it "doesn't change the artistic control."
"It’s not post-processing, it’s not post-processing at the frame level, it’s generative control at the geometry level," he said.
Huang
also said that developers can try the tool and see how they want to use
it, suggesting that it's up to a developer to try to make a "toon
shader" or see if the game should be "made of glass."
"All of
that is in the control — direct control — of the game developer," he
said. This is very different than generative AI; it’s content-control
generative AI. That’s why we call it neural rendering."
So setting aside the fact that he doesn't know how his own technology works or games are made... If it did control and generate things every frame at the geometry level that would be impressive from a technical standpoint. However similar questions come to mind as any other art: how do you keep it consistent and prevent it from turning to mush and/or hallucinating? Games aren't movies, players will get themselves into places they aren't supposed to or how do you deal with a non-linear open world? How can you make sure that the game will be the same experience from person to person, let alone the same person if they backtrack?
Other than curiosity and the continuing sale of more gpu power... which no one can afford and is probably a push to get people onto their game streaming service... I don't see the point of this tech. It's like we forgot you can lower your settings to get more frames and for some people they may never even notice the settings between medium and high fidelity on some games.
Community: Nvidia, how are scrambled eggs made? Nvidia: Scrambled eggs are made from wheat, and the hens have full control over the result. Community: Really, isn’t it made from eggs? Nvidia: It is made from eggs, but wheat is the main input for the eggs, wheat thereby acts as a control plane for making the scrambled eggs. The hens are also left to fine tune and control own style of the final flavor of the scrambled eggs.
I have yet to see any real explanation for why the team was let go, and I’m somewhat hesitant to assume it’s because take 2 thinks gen ai is a bad bet.
When I first saw Luke’s post I had that same thought of “oh good, it’s happening” but dug in a bit more. There’s responses and likes of his in the past that call out gen AI for gaslighting and creative slop, so I’m not sure where he and the team actually sit in the greater conversation. Perhaps they were more keen on PCG and not fully on board with diffusion based and llm gen ai which didn’t align with take 2’s desire.
TLDR just because the ceo said gta doesn’t need it, I wouldn’t assume that the company as a whole isn’t bought in to gen AI.
It costs a fortune to use robots for anything novel and the chance of producing anything useful in practice is pretty low. What they've done here is cut their R&D budget because they didn't see any returns
I haven't posted here recently because it's kind of obvious at this point; the bubble is popping. 30,000 laid off at Oracle, Copilot is 'for entertainment purposes only', etc, etc. Beating a dead horse with 5 legs and 2 necks at this point
Mark, creator of Facebook and burner of $88,000,000,000.00 on failed WoW killer recently added meta AI to whatsapp, and his will be one of the last to pop. https://www.youtube.com/watch?v=8BaSBjxNg-M
One thing I found a little bit annoying was their reliance on perspective lines to help uncover forgeries. They didn't acknowledge barrel distortion and how that actually warps a linear perspective. But whatever, still a great article.
According to a study by Game Oracle, disclosing the use of generative AI on Steam can correlate to upwards of a 53% drop in sales. https://www.game-oracle.com/blog/ai-part2
An old pal of mine since art school makes his living doing all sorts of realistic illustrations form something like medical manuals to something true art looking fantasy style book illustrations paid usually by certain steady by piece and quite low rate. It's a sort of sustaining job in between his oil on canvas time and his teaching in an art school hours . Now he's super happy he made Stable Diffusion to follow his exact style for every customer and started to do them in mass in a fraction of time. Rate still keeps to be same. Customers (publishing firms) still order it to him rather than doing themselves. He says the biggest rate drop happened in 2000th when internet became accessible everywhere , not with AI appearance. He blames internet
To bad or perhaps otherwise I still can't find any AI that would do my tasks easier . Wasted forever already trying to find one beyond scripts writing for Photoshop and Blender. Wasted exactly a month recently trying to teach chatGPT or stable diffusion to make me true looking realistic hi res aerial views/ terrain UDIM texture layers matching specific LIDAR geometry and hand painted guides
Testing out the new AI 3d tools and seeing how they've progressed definitely makes me feels I've wasted time on learning to sculpt digitally as hobby.
Why waste time trying to capture someones likeness when you can put an image into ai and get a very decent result that captures intricate forms within minutes? It's not perfect but if used correctly it would take at least 70% of the work out of the sculpting process specifically.
but it is really any different than artists that clean up and edit scans?
I'm curious if there's any news on any known devs adopting this tech yet
Why waste time trying to capture someones likeness when you can put an image into ai ...
Why waste time learning anything, if a computer can just cough it up any time you like? Why eat tasty food, if I can just drink soylent? Heck, why even get up in the morning?
Because making things, and the learning process itself, feels good and improves your brain.
Replies
Huang also said that developers can try the tool and see how they want to use it, suggesting that it's up to a developer to try to make a "toon shader" or see if the game should be "made of glass."
"All of that is in the control — direct control — of the game developer," he said. This is very different than generative AI; it’s content-control generative AI. That’s why we call it neural rendering."
Community: Nvidia, how are scrambled eggs made?
Nvidia: Scrambled eggs are made from wheat, and the hens have full control over the result.
Community: Really, isn’t it made from eggs?
Nvidia: It is made from eggs, but wheat is the main input for the eggs, wheat thereby acts as a control plane for making the scrambled eggs. The hens are also left to fine tune and control own style of the final flavor of the scrambled eggs.
TLDR just because the ceo said gta doesn’t need it, I wouldn’t assume that the company as a whole isn’t bought in to gen AI.
It costs a fortune to use robots for anything novel and the chance of producing anything useful in practice is pretty low. What they've done here is cut their R&D budget because they didn't see any returns
https://www.forbes.com/sites/jonmarkman/2026/04/06/oracles-massive-30000-layoff-as-ai-spending-surges/
https://techcrunch.com/2026/04/05/copilot-is-for-entertainment-purposes-only-according-to-microsofts-terms-of-service/
Mark, creator of Facebook and burner of $88,000,000,000.00 on failed WoW killer recently added meta AI to whatsapp, and his will be one of the last to pop.
https://www.science.org/content/article/deepfakes-are-everywhere-godfather-digital-forensics-fighting-back
One thing I found a little bit annoying was their reliance on perspective lines to help uncover forgeries. They didn't acknowledge barrel distortion and how that actually warps a linear perspective. But whatever, still a great article.
lmao that thumbnail
Why waste time trying to capture someones likeness when you can put an image into ai and get a very decent result that captures intricate forms within minutes? It's not perfect but if used correctly it would take at least 70% of the work out of the sculpting process specifically.
but it is really any different than artists that clean up and edit scans?
I'm curious if there's any news on any known devs adopting this tech yet
Why waste time learning anything, if a computer can just cough it up any time you like? Why eat tasty food, if I can just drink soylent? Heck, why even get up in the morning?