Live data from Hacker News

Sora 2

openai.com

141–150 of 916 posts

Re: Sora 2

#141
post #115
post #93

Earlier quoted context omitted.

No doubt they can create Hollywood quality clips if the tools are good enough to keep objects consistent, example, coming back to the same scene with same decor and also emotional consistency in actors

> keep objects consistent I think this is not nearly as important as most people think it is. In hollywood movies, everyone already knows about "continuity errors" - like when the water level of a glass goes up over time due to shots being spliced together. Sometimes shots with continuity errors are explicitly chosen by the editor because it had the most emotional resonance for the scene. These types of things rarely…

I wonder if this stuff is trained on enough Hallmark movies that even AI actors will buy a hot coffee at a cafe and then proceed to flail the empty cup around like the humans do. Really takes me out of the scene every time - they can't even put water in the cup!?

Re: Sora 2

#142
post #57

Earlier quoted context omitted.

People are doing cool things with it. Here’s one example: https://www.tiktok.com/@dreamrelicc Before AI, each video on this channel would have taken a large team with a Hollywood budget to create. In a few more years, one person may be able to turn their creative vision into a full-length movie.

This is absolutely horrible. People need to be exposed to what is real. Not more artificial stuff. I think this is the point at which humanity will finally puke and reject this crap. Just because a small segment of people like it doesnt mean the mass majority will.

I personally love Monet, he's not for everyone, I know, but I'm sure you can find some art you appreciate

Re: Sora 2

#143
post #115
post #93

Earlier quoted context omitted.

No doubt they can create Hollywood quality clips if the tools are good enough to keep objects consistent, example, coming back to the same scene with same decor and also emotional consistency in actors

> keep objects consistent I think this is not nearly as important as most people think it is. In hollywood movies, everyone already knows about "continuity errors" - like when the water level of a glass goes up over time due to shots being spliced together. Sometimes shots with continuity errors are explicitly chosen by the editor because it had the most emotional resonance for the scene. These types of things rarely…

People got used to James Bond actors changing between movies, but from scene to scene in the same movie would be a bit confusing.

Re: Sora 2

#144
post #82

Earlier quoted context omitted.

Social media also tends to highlight the best parts of people’s lives, creating unrealistic expectations and views for those consuming it and looking at their real life. Now social media won’t even be a highlight reel, but completely fabricated. I have to imagine there will be a rebellion against all of this at some point, when people simply can’t take the false realities anymore. What is the alternative? Ready Playe…

Which seem to level the play field, at least virtually

Maybe inside of a social network specially for AI, but a concerning number of people don't realize images and videos are AI, even when it's bad AI. As it gets better, and starts integrating the poster's image (like Sora 2), that's going to get even worse.

Re: Sora 2

#146

That could totally power next generation of green-screen techs. Generative actors may not find favorable response in the audiences; but SFX, decor, extras, environments that react to actors' actions - amazing potential.

You can already do really cool stuff in this area “old” tech like stable diffusion. Not realistic or anything but really cool looking/morphing images

At least in terms of realism, the image generation field is at the realism line now. Single frame generation with Wan 2.1 / 2.2 (and others) for example, will get you realism.

Re: Sora 2

#148

Earlier quoted context omitted.

What are the benefits of this comment?

Challenging the value of AI generated "art"

Then the purpose of those videos is to challenge the value of non AI generated "art"

(half sarcastic, but you could make the argument that most art has no benefit besides to the person that made the art)

Re: Sora 2

#149
post #27

I know the comments here are gonna be negative but I just find this so sick and awesome. Feels like it's finally close to the potential we knew was possible a few years ago. Feels like a pixar moment when CG tech showed a new realm of what was possible with toy story

These videos are a very impressive engineering feat. There are a lot of uses for this capability that will be beneficial to society, and in the coming years people will come up with more good uses nobody today has thought of yet.

But clearly we also see some major downsides. We already have an epidemic of social media rotting people's minds, and everything about this capability is set to supercharge these trends. OpenAI addresses some of these concerns, but there's absolutely no reason to think that OpenAI will do anything other than what they perceive as whatever makes them the most money.

An analogy would be a company coming up with a way to synthesize and distribute infinite high-fructose corn syrup. There are positive aspects to cheaply making sweet tasting food, but we can also expect some very adverse effects on nutritional health. Sora looks like the equivalent for the mind.

There's an optimistic take on this fantastic new technology making the world a better place for all of us in the long run, after society and culture have adapted to it. It's going to be a bumpy ride before we get there.

Re: Sora 2

#150
post #13

https://apps.apple.com/us/app/sora-by-openai/id6744034028 App link edit: CBN80W for an invite code

Do you really want a "social" app for a firehose of high-fidelity slop?
Post reply on HN