Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Sora: Creating video from text

openai.com

Post reply on HN
Print view View original

641–650 of 1001 posts

Re: Sora: Creating video from text

#641

Post by snewman »

neutralx wrote: post #378

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 interes…

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.

Re: Sora: Creating video from text

#642

Post by superconduct123 »

uoaei wrote: post #40

Visual sharpness at the expense of wider-scale coherence (see: sliding/floating walking woman in Tokyo demo or tiny people next to giant people in Lagos demo) seems to be a local optimum consistently achieved by today's SOTA models in all domains. This is neat and all but mostly just a toy. Everything I've seen has me convinced either we are optimizing the wrong loss functions or the architectures we have today are f…

Seems like every big jump in improvement someone says "its just a toy"

Its like we keep moving the bar

Re: Sora: Creating video from text

#643

Post by xanderlewis »

woah wrote: post #524
hansonkd wrote: post #26

Countdown to when studios licensing this for "unlimited" episodes of your favorite series. There was Seinfeld "Nothing, Forever" AI parody, but once the models improve enough and are cheap enough to deploy, studios will license their content for real and just have endless seasons. Or even custom episodes. Imagine if every episode of a TV show was unique to the viewer.

You could have ChatGPT create unlimited simulated forum threads about news articles, but here you are on Hacker News

This is such a great example. Simple, but so telling.

Re: Sora: Creating video from text

#644

Post by XCSme »

If this can generate videos in real-time (60FPS), then you can, in theory, create any game just from text/prompts.

You just write the rules of the game and the player input, and let the AI generate the next frame.

Re: Sora: Creating video from text

#645

Post by fasterik »

cyrialize wrote: post #409

Does anyone know how to handle the depression/doom one feels with these updates? Yes, it's a great technical achievement, but I just worry for the future. We don't have good social safety nets, and we aren't close to UBI. It's difficult for me to see that happen unless something drastic changes. I'm also afraid of one company just having so much power. How does anyone compete?

>Does anyone know how to handle the depression/doom one feels with these updates?

Realize that it's a choice to respond to things this way. This feeling comes from a certain set of assumptions and learned responses.

Remember that people are bad at predicting the future. Look at the historical track record of people predicting the implications of technological advancement. You'll find that almost nobody gets it right. Granted, that sometimes means that things are worse than we expect, but there are also many cases where things turn out better than we expect. If you're prone to focusing on potential negatives, maybe you can consciously balance that out by forcing yourself to imagine potential positives as well.

Try to focus on things you personally have control over. Why worry about something that you can't change? Focus on problems that you can contribute to solving.

Re: Sora: Creating video from text

#646

Post by geor9e »

crazygringo wrote: post #190

This is insane. But I'm impressed most of all by the quality of motion . I've quite simply never seen convincing computer-generated motion before . Just look at the way the wooly mammoths connect with the ground, and their lumbering mass feels real. Motion-capture works fine because that's real motion, but every time people try to animate humans and animals, even in big-budget CGI movies, it's always ultimately obvio…

It's possible that through sheer volume of training, the neural network essentially has a 3D engine going on, or at least picked up enough of the rules of light and shape and physics to look the same as unreal or unity

Re: Sora: Creating video from text

#647

Post by superconduct123 »

dom96 wrote: post #87

This is going to make the latest election really interesting (and scary). Is anyone working to ensure a faked video of Biden that looks plausible but is AI generated doesn't get significant traction at a critical moment of the election?

Media outlets are not going to just publish a random video with sketchy provenance

Re: Sora: Creating video from text

#648

Post by sylware »

Hopefully we will see AIs with tools which are not "paint" or "notepad", but a maths formal proof solver, etc.

But I have a problem: I am unable to believe the videos I saw were dreamt by AI. I can feel deeply that I do believe there is some trickery or severe embellishment. If I am wrong, I guess we are at an inflexion point.

I can recall 10+ years ago, we were talking "in hacking groups" about AI because we thought the human brain alone was not good enough anymore... but in a maths/sciences context.

Re: Sora: Creating video from text

#649

Post by eggplantemoji69 »

Value is going to be higher for professions where the human essence is an essential component of the function. Or professions that are more coupled with physical reality…my hedge is probably becoming an electrician.

I’d imagine IRL no-tech experiences will be the new ‘escapes’ too.

Maybe I’m too idealistic about the importance of the human spirit/essence…whatever that actually is.

Re: Sora: Creating video from text

#650

Post by dorkwood »

Buckworthy wrote: post #586
telesilla wrote: post #525

Watching these made me think, I'm going to want to go to the theatre a lot more in the future and see fellow humans in plays, lectures and concerts. Such achievements in technology must lead to cultural change. Look at how popular vinyl has become, why not theatre again.

Imagine movies generated in real-time just for you, with the faces you know, places you know and what not!

Seems like we're pretty close to inserting ourselves into pornographic movies.
Post reply on HN