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

Sora is here

openai.com

Post reply on HN
Print view View original

991–1000 of 1001 posts

Re: Sora is here

#991

Post by Breza »

runarberg wrote: post #712
sleepybrett wrote: post #449

Earlier quoted context omitted.

This will almost certainly be in theaters within 5 years, probably first as a small experimental project (think blair witch).

The Blair Witch Project was a (surprise) creative masterpiece. It worked with very limited technology to create a very clever plot which was paired with an amazing marketing. The combination of which the world hadn’t seen before. It took some creative geniuses to peace the Blair Witch Project together. Generative AI will never produce an experience like that. I know never is a long time, but I’m still gonna call it.…

I'm suspicious of most claims of AI growth, but I think screenwriting is an area where there's real potential. There are many screenplays out there, many movie plots are very similar to each other, and human raters could help with training. And it's worth noting that the top four highest grossing movies right now are all sequels or film adaptations. It's not a huge leap to imagine an LLM in the future that's been trained on movie writing being able to create a movie script when given the Wicked musical. https://www.imdb.com/chart/boxoffice/

Re: Sora is here

#993

Post by Quekid5 »

sbarre wrote: post #860
Quekid5 wrote: post #846

Earlier quoted context omitted.

> A precondition is likely that one has mainly watched CGI-heavy movies for most of one's life. Indeed, a great (if counterintuitive) example of this is The Wolf of Wall Street. I bet a lot of people would be surprised at just how much CGI is used in that just for set/location.

The OG film for that was Forrest Gump. It is often lauded as one of the first movies to use CGI heavily but in completely, and intentionally, unnoticeable ways...

True, but in that case you knew it had to be CGI because Kennedy didn't talk to Tom Hanks in any capacity.

Re: Sora is here

#994

Post by bumbledraven »

thereddaikon wrote: post #962
wongarsu wrote: post #903

Earlier quoted context omitted.

AI voices have gotten scarily good. They are easy to recognize because most creators use the same voices with the same intonations and don't care to cut out the mistakes. But if you don't recognize the voice it takes a couple sentences to discern that it's AI even with an ear trained on the difference. But it is funny to see how much stuff gets uploaded with zero quality control and still gets traction. These models…

I've heard enough slop using the ElevenLabs voices that I can recognize them almost immediately now. But you're right. Higher end models with less familiar voices are harder to notice. One consistent failing is that they are always too perfect. No mistakes or signs of cuts to edit out where a human VA would have made a mistake. Its all very smooth and perfect. As if they nailed it in the first shot. Once the cheap/fr…

"More human than human" is our motto. https://youtu.be/ZbgmYhqFO-4?t=30

Re: Sora is here

#995

Post by runarberg »

Breza wrote: post #991
runarberg wrote: post #712

Earlier quoted context omitted.

The Blair Witch Project was a (surprise) creative masterpiece. It worked with very limited technology to create a very clever plot which was paired with an amazing marketing. The combination of which the world hadn’t seen before. It took some creative geniuses to peace the Blair Witch Project together. Generative AI will never produce an experience like that. I know never is a long time, but I’m still gonna call it.…

I'm suspicious of most claims of AI growth, but I think screenwriting is an area where there's real potential. There are many screenplays out there, many movie plots are very similar to each other, and human raters could help with training. And it's worth noting that the top four highest grossing movies right now are all sequels or film adaptations. It's not a huge leap to imagine an LLM in the future that's been tra…

The 2023 Writers Guild of America strike was in part to prevent screenplays being written entirely by generative AI.

So no I don’t think this will happen either. Authors may use use AI them selves as one tool in their tool box as they write their script, but we will not see entire production screen plays being written by generative AI set for theatrical release. The industry will simply not allow that to happen. At most you can have AI write a screen play for your own amusement, not for publication.

Re: Sora is here

#996

Post by yunwal »

carlosjobim wrote: post #949
yunwal wrote: post #942

Earlier quoted context omitted.

> the landing page will have great importance. Most companies don't need this. They need a page that has their contact info and some general information about services they provide so they can have a bare minimum internet presence and show up on google maps.

Absolutely, if your company doesn't want to make sales or if you want to be bothered all the time by people calling and mailing only for them to find out your product isn't a fit for them. Or if you want third party sellers to take over most of your business like Booking.com, AirBnB DoorDash or Amazon. Companies who understand the importance of a customer friendly and functional web presence get a great return on the…

I have an ice cream shop by me that doesn't even have a website. They're mobbed every day, because good ice cream is fairly self explanatory, and doesn't need a web presence

Re: Sora is here

#997

Post by bailvgu »

transformi wrote: post #4

Not impressive compare to the opensource video models out there, I anticipated some physics/VR capabilities, but it's basically just a marketing promotion to "stay in the game"...

[dead]

Re: Sora is here

#999

Post by leobg »

potamic wrote: post #826
Havoc wrote: post #679

Earlier quoted context omitted.

AI companies don’t give a shit about ToS. Hell most of the big players actively ignored copyright entirely in bulk. See thousand upon thousands of pirated books in the pile dataset. And right after that news broke they “fixed” the problem by stopping to disclose training data sources. Thats why early models had papers eg Llama 1 listed this and now nobody does. It’s just an unspoken yet open secret now.

How did they get access to pirated books?

Anna’s archive has files specifically for training LLMs. But I’d guess the big players secured their share beforehand, by scraping those sites. I have zero proof, it’s just a guess.

Re: Sora is here

#1000

Post by fennecbutt »

jerf wrote: post #124
yeknoda wrote: post #9

I've found using these and similar tools that the amount of prompts and iteration required to create my vision (image or video in my mind) is very large and often is not able to create what I had originally wanted. A way to test this is to take a piece of footage or an image which is the ground truth, and test how much prompting and editing it takes to get the same or similar ground truth starting from scratch. It is…

It just plain isn't possible if you mean a prompt the size of what most people have been using lately, in the couple hundred character range. By sheer information theory, the number of possible interpretations of "a zoom in on a happy dog catching a frisbee" means that you can not match a particular clip out of the set with just that much text. You will need vastly more content; information about the breed, informati…

This is correct and even image generation models aren't really trained for comprehension of image composition yet.

Even the models based off danbooru and E621 still aren't the best at that. And us furries like to tag art in detail.

The best we can really do at the moment is regional prompting, perhaps they need something similar for video.

Post reply on HN