News for hackers. Stuff that matters.
Re:Diffusion Models Are Real-Time Game Engines by bamboozled on Wednesday August 28, 2024 @10:10AM (#41379736)
Are you saying if I turn around, I’ll be surprised at what I find ? I don’t feel like this is accurate at all.
Re:Diffusion Models Are Real-Time Game Engines by dewarrn1 on Wednesday August 28, 2024 @10:52AM (#41380209)
Not exactly, but our representation of what's behind us is a lot more sparse than we would assume. That is, I might not be surprised by what I see when I turn around, but it could have changed pretty radically since I last looked, and I might not notice. In fact, an observer might be quite surprised that I missed the change.

Objectively, Simons and Chabris (and many others) have a lot of data to support these ideas. Subjectively, I can say that these types of tasks (inattentional blindness, change blindness, etc.) are humbling.

Re:Diffusion Models Are Real-Time Game Engines by jerf on Wednesday August 28, 2024 @11:55AM (#41380917)
Well, it's a bit of a spoiler to encounter this video in this context, but this is a very good video: https://www.youtube.com/watch?v=LRFMuGBP15U

Even having a clue why I'm linking this, I virtually guarantee you won't catch everything.

And even if you do catch everything... the real thing to notice is that you had to look. Your brain does not flag these things naturally. Dreams are notorious for this sort of thing, but even in the waking world your model of the world is much less rich than you think. Magic tricks like to hide in this space, for instance.

Re:Diffusion Models Are Real-Time Game Engines by dewarrn1 on Wednesday August 28, 2024 @02:29PM (#41382646)
Yup, great example! Simons's lab has done some things along exactly these lines [0], too.

[0]: https://www.youtube.com/watch?v=wBoMjORwA-4

Re:Diffusion Models Are Real-Time Game Engines by ajuc on Wednesday August 28, 2024 @11:10AM (#41380408)
The opposite - if you turn around and there's something that wasn't there the last time - you'll likely not notice if it's not out of place. You'll just assume it was there and you weren't paying attention.

We don't memorize things that the environment remembers for us if they aren't relevant for other reasons.

Re:Diffusion Models Are Real-Time Game Engines by bamboozled on Wednesday August 28, 2024 @10:14PM (#41386572)
We also don't just work on images. We work on a lot of sensory data. So i think images of the environment are just one part of it.
Re:Diffusion Models Are Real-Time Game Engines by matheusd on Wednesday August 28, 2024 @10:32AM (#41379951)
If a generic human glances at an unfamiliar screen/wall/room, can they accurately, pixel-perfectly reconstruct every single element of it? Can they do it for every single screen they have seen in their entire lives?
Re:Diffusion Models Are Real-Time Game Engines by bamboozled on Wednesday August 28, 2024 @10:44AM (#41380107)
I never said pixel perfect, but I would be surprised if whole objects , like flaming lanterns suddenly appeared.

What this demo demonstrates to me is how incredible willing we are to accept what seems familiar to us as accurate.

I bet if you look closely and objectively you will see even more anomalies. But at first watch, I didn’t see most errors because I think accepting something is more efficient for the brain.

Re:Diffusion Models Are Real-Time Game Engines by ben_w on Wednesday August 28, 2024 @12:25PM (#41381248)
You'd likely be surprised by a flaming lantern unless you were in Flaming Lanterns 'R Us, but if you were watching a video of a card trick and the two participants changed clothes while the camera wasn't focused on them, you may well miss that and the other five changes that came with that.