High Signal Podcasts Evidence ledger
Method
Browse
← Back to evidence

Evidence receipt / belief

Published · transcript-backed

Speaker unverified: belief

5 Aug 2025 Machine Learning Street Talk DeepMind Genie 3 [World Exclusive] (Jack Parker Holder, Shlomi Fruchter)

“In terms of things like more more abstract representations, I think we're still kind of exploring it, to be honest. But it definitely has a slightly different feel to it because especially for the first person view that you get often when you're experiencing it.”

— Speaker unverified

Source trail

Everything needed to verify it.

Speaker
Speaker unverified
Attribution
Not verified from this transcript
Claim type
belief
Recorded
5 Aug 2025
Publisher
Machine Learning Street Talk

Transcript context

…Yeah. Yeah. That's amazing. There's also this notion that so 7 20 p, know, Genie 3 was just creating these these immersive And I use the word immersive in intentionally because as a video editor, I know that it's all about it's a bit of an illusion. So you are trying to create a creative artifact that is just beyond the predictive horizon of the consumer, and then they suspend disbelief. Right? And so so in a in a sense, like, are cognitively bounded as observers. We see the world macroscopically. We see chairs. We don't see particles, you know. And so the world can have descriptions at different levels. And when when you interact with Genie 3, do do you see it kind of like traversing the levels? Like, if you zoom in on something, does it have a different description, or or is it limited in some way? How do you think about that? So in some of the examples we showed, there's the 1 where you're controlling this drone in the like, by a lake, and there's some trees, and it's, like, very beautiful scenery. And you do notice in that 1 that when you focus your view in different areas, it definitely hones in on detail more. And so I think the model learns that sometimes you don't need all this detail, right? And actually, it should focus its efforts with the focus of the agent. And I think this comes a bit from I mean, our emphasis on this with this model is to have an agent centric, sort of egocentric often. They also can do third person. But a model that really feels like it's it's your view of the world, right, rather than as a contrast of to video videos, right, which are more are much more sort of like like cinematic in quality. Right? The whole video is very high quality. Whereas Genie 3 often, it does feel much like a a your your own personal view in the world, which I think is is quite a different experience. Right? And it does have these different levels of detail to it. Right? In terms of things like more more abstract representations, I think we're still kind of exploring it, to be honest. But it definitely has a slightly different feel to it because especially for the first person view that you get often when you're experiencing it. How how do you think about that? I mean, do do do you I mean, it's so difficult for us to know how these inscrutable models work. But do you ensure it's that it's simulating the world at multiple levels of resolution?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.

Search evidence