Hacker News Reader

Comment by neutralx | Hacker News Reader

Has anyone else noticed the leg swap in Tokyo video at 0:14. I guess we are past uncanny, but I do wonder if these small artifacts will always be present in generated content.

Also begs the question, if more and more children are introduced to media from young age and they are fed more and more with generated content, will they be able to feel "uncanniness" or become completely blunt to it.

There's definitely interesting period ahead of us, not yet sure how to feel about it...

View on HN

There are definitely artifacts. Go to the 9th video in the first batch, the one of the guy sitting on a cloud reading a book. Watch the book; the pages are flapping in the wind in an extremely strange way.

The third batch, the one with the cat, the guy in bed has body parts all over, his face deforms, and the blanket is partially alive.

When there is a dejavu cat, we know we are in trouble!

In the one with the cat waking up its owner, the owners shoulder turns into a blanket corner when she rolls over.

Yep, I noticed it immediately too. Yet it is subtle in reality. I'm not that good to spot imperfections on picture but on the video I immediately felt something was not quite right.

Tangent to feeling numb to it - will it hinder children developing the understanding of physics, object permanence, etc. that our brains have?

Kids aren't supposed to have screen time until they're at least a few years old anyways

There have been children, that reacted iritated, when they cannot swipe away real life objects. The idea is, to give kids enough real world experiences, so this does not happen.

Kids have been exposed to decades of 2D and 3D animations that do not contain realistic physics etc; I’m assuming they developed fine?

I noticed at the beginning that cars are driving on the right side of the road, but in Japan they drive on the left. The AI misses little details like that.

(I'm also not sure they've ever had a couple inches of snow on the ground while the cherry blossoms are in bloom in Tokyo, but I guess it's possible.)

The cat in the "cat wakes up its owner" video has two left front legs, apparently. There is nothing that is true in these videos. They can and do deviate from reality at any place and time and at any level of detail.

These artefacts go down with more compute. In four years when they attack it again with 100x compute and better algorithms I think it'll be virtually flawless.

I had to go back several times to 0:14 to see if it was really unusual. I get it of course, but probably watching 20 times I would have never noticed it.

Yep! Glad I wasn't the only one that saw that. I have a feeling THEY didn't see it or they wouldn't have showcased it.

I don't think that's the case. I think they're aware of the limitations and problems. Several of the videos have obvious problems, if you're looking - e.g. people vanishing entirely, objects looking malformed in many frames, objects changing in size incongruent with perspective, etc.

I think they just accept it as a limitation, because it's still very technically impressive. And they hope they can smooth out those limitations.

They swap multiple times lol. Not to mention it almost always looks like the feet are slightly sliding on the ground with every step.

I mean there are some impressive things there, but it looks like there's a long ways to go yet.

They shouldn't have played it into the close up of the face. The face is so dead and static looking.

certainly not perfect... but "some impressive things" is an understatement, think of how long it took to get halfway decent CGI... this AI thing is already better than clips I've seen people spend days building by hand

Reply on news.ycombinator.com