Jensen Huang changes tone on DLSS 5
Jensen Huang has shifted to a softer tone on DLSS 5 criticism, saying he understands why some players reacted negatively to NVIDIA’s new neural rendering push. In Lex Fridman’s podcast episode, Huang said, “ I don’t love AI slop myself,” adding that he is empathetic to concerns that AI-generated visuals can start to look too similar.
This comment comes less than a week after Huang comments from GTC 2026 press Q&A. He said gamers were “completely wrong” about DLSS 5 criticism, while arguing that developers still retain control over how the technology is used.
Yeah. I think their perspective makes sense and I could see where they’re coming from, because I don’t love AI slop myself. You know, all of the AI-generated content increasingly looks similar and they’re all beautiful, and so I’m empathetic towards what they’re thinking.
— Jensen Huang during Lex Fridman podcast
Even with the softer wording, Huang’s core message has not changed. In the Fridman interview, he again described DLSS 5 as “3D-conditioned” and “3D-guided,” and said it is based on ground-truth structure data rather than a simple post-process filter applied after the fact. He also repeated that the system is meant to work with artist-created geometry and textures, not replace them. However, we do know as a fact that this is not entirely accurate, because NVIDIA’s Jacob Freeman confirmed it uses 2D images as input .
Interestingly, Huang also said DLSS 5 could eventually allow developers to train custom models or steer output toward a specific look, including stylized rendering.
That’s just not what DLSS 5 is trying to do. I showed several examples of it. But DLSS 5 is 3D-conditioned, 3D-guided. It’s ground truth structure data guided. And so the artist determined the geometry. We are completely truthful to the geometry maintained in every single frame. It’s conditioned by the textures, the artistry of the artist. And so every single frame, it enhances but it doesn’t change anything.
Now, the question is about enhancing. DLSS 5 also lets, because the system is open, you could train your own models to determine, and you could even in the future prompt it. You know, I want it to be a toon shader. I want it to look like this kind of, so you can give it even an example. And it would generate in the style of that, all consistent with the artistry, the style, the intent of the artist. And so all of that is done for the artist, so that they can create something that is more beautiful but still in the style that they want. I think that they got the impression that the games are gonna come out the way the games are, shipped the way they do, and then we’re gonna post-process it. That’s not what DLSS is intended to do.
DLSS is integrated with the artist, and so it’s about giving the artist the tool of AI, the tool of generative AI. They could decide not to use it, you know?
— Jensen Huang during Lex Fridman podcast
Source:
