Sora 2
111–120 of 916 posts
Re: Sora 2
#112I imagine it won’t necessarily be used in long scenes with subtle body language, etc involved. But maybe it’ll be used in other types of scenes?
Re: Sora 2
#113Re: Sora 2
#114Find this sort of innovation far less interesting or exciting than the text & speech work, but it seems to be a primary driver of adoption for the median person in a way that text capability simply is not.
however as they hint at a little in the announcement, if video generation becomes good enough at simulating physics and environments realistically, that's very interesting for robotics.
Re: Sora 2
#115I 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
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
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 affect our human subjective enjoyment of a video.
In terms of physics errors - current human CGI has physics errors. People just accept it and move on.
We know that superman can't lift an airplane because all of that weight on a single point of the fuselage doesn't hold, but like whatever.
Re: Sora 2
#116It's obvious there is no way OpenAI can keep videos generated by this within their ecosystem. Everything will be fake, nothing real. We are going to have to change the way we interact with video. While it's obviously possible to fake videos today, it takes work by the creator and takes skill. Now it will take no skill so the obvious consequence of this is we can't believe anything we see. The worst part is we are alr…
Today's Sora can produce something that resembles reality from a distance, but if you look closely, especially if there's another perspective or the scene is atypical, the flaws are obvious.
Perhaps tomorrow's Sora will overcome the the "final 10%" and maintain undetectable consistency of objects in 2 perspectives. But that would require a spatial awareness and consistency that models still have a lot of trouble with.
Re: Sora 2
#117I expect the "cameo" feature is an attempt at capturing that viral magic a second time.
Re: Sora 2
#118Sam Altman has made (for me) encouraging statements in the past about short-form video like TikTok being the best current example of misaligned AI. While this release references policies to combat "Doomscrolling and RL-sloptimization", it's curious that OpenAI would devote resources to building a social app based on AI generated short form video, which seems to be a core problem in our world. IMO you can't tweak the…
Re: Sora 2
#119Will something like Sora 2 actually be used in Hollywood productions? If so, what types of scenes? I imagine it won’t necessarily be used in long scenes with subtle body language, etc involved. But maybe it’ll be used in other types of scenes?
Like you have an exterior shot of a cabin, the surrounding environment, etc — all generated. Then you jump inside which can be shot on a traditional set in a studio.
Getting that establishing shot in real life might cost $30K to find a location, get the crew there, etc. Huge boon to indie films on a budget, but being able to endlessly tweak the shot is valuable even for productions that could afford to do it IRL.
Re: Sora 2
#120So a social network that's 100% your friends doing silly AI things? I feel like this is the ultimate extension of "it feels like my feed is just the artificial version of what's happening my friends and doesn't really tell me anything about how they're actually faring."
The technology itself is super impressive, but a social media app of AI slop doesn't feel like the best use of it. I'm old enough to not really be interested in social media in general anymore, so maybe I'm just out of touch, but I just can't see this catching on. It feels like the type of thing that people will download, use a few times until the novelty wears off and then never open again.