Since the debut of NVIDIA's "25-year graphics breakthrough," the response has been resoundingly negative. Gamers are complaining that the technology is adding an AI beauty filter to their favorite characters, ruining the game's original art style and calling it "AI Slop."

Jensen Huang, founder and CEO of NVIDIA, has come forward to address these remarks, immediately stating, "They're completely wrong."
"The reason for that is because, as I have explained very carefully, DLSS 5 fuses controllability of the geometry and textures and everything about the game with generative AI," Huang said in response to a question from Tom's Hardware's Paul Alcorn.
NVIDIA had previously suggested that developers would be able to tune the overall intensity of how much DLSS 5 changes. Huang reiterated once again that developers are in full, direct control of the technology. He also added that DLSS 5 is different from generative AI, calling it "content control generative AI" that adds generative capability to the game's existing geometry and "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", Huang said.
As to what this generative control would look like in practice, Jensen has previously said DLSS 5 is the "ChatGPT moment" of upscaling. This would mean that developers will give the input prompt, which would be structured data, such as geometry, motion vectors like character movements, and the depth of the scene, and the model will churn out photorealistic textures.
There is no doubt that DLSS 5 will make strides in rendering, but the demos available tell a different story. We'll have to see how the technology performs at launch and how much control developers will actually have over their art styles. DLSS 5 is set to launch sometime in fall 2026, meaning we should be able to see some more of it in action before making a final judgment.




