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

771–780 of 1001 posts

Re: Sora is here

#771

Post by joe_the_user »

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…

The thing about Hollywood is that movies aren't made by a producer or director creating a description and an army of actors, tech and etc doing exactly that.

What happens is a description becomes a longer specification or script that's still good and hangs together in itself and then further iterations involving professionals who can't do "exactly what the director wants" but rather do something further that's good and close enough to what the director wants.

Re: Sora is here

#772

Post by midasz »

geor9e wrote: post #572
goykasi wrote: post #280

A bit off-topic, but how much does a 4-letter (or less) .com go for these days? I wonder if they bought this via an intermediary so that the seller wouldnt see "OpenAI" and tack on a few zeros. edit: previously, this thread pointed to sora.com

Pretty off-topic, but yes, domains and land are often bought via shell companies for this reason. They probably didn't settle upon the name Sora until they already secured the .com . That's a famous YC piece of advice. If you can't get the .com then rename. But for domains that everyone wants, like chat.com, OpenAI paid 8 figures for that one.

Huh didn't realize chat.com redirected to chatgpt

Re: Sora is here

#773

Post by ohthehugemanate »

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…

If you have a specific vision, you will have to express the detailed information of that vision into the digital realm somehow. You can use (more) direct tools like premiere if you are fluent enough in their "language". Or you can use natural language to express the vision using AI. Either way you have to get the same amount of information into a digital format.

Also, AI sucks at understanding detail expressed in symbolic communication, because it doesn't understand symbols the way linguistic communication expects the receiver to understand them.

My own experience is that all the AI tools are great for shortcutting the first 70-80% or so. But the last 20% goes up an exponential curve of required detail which is easier and easier to express directly using tooling and my human brain.

Consider the analogy to a contract worker building or painting something for you. If all you have is a vague description, they'll make a good guess and you'll just have to live with that. But the more time you spend with them communicating (through description, mood boards rough sketches etc) the more accurate to your detailed version it will get. But you only REALLY get exactly what you want if you do it yourself, or sit beside them as they work and direct almost every step. And that last option is almost impossible if they can't understand symbolic meaning in language.

Re: Sora is here

#774

Post by bergen »

robotresearcher wrote: post #597
coffeebeqn wrote: post #424

Earlier quoted context omitted.

This almost certainly won’t work. Feel free to feed any of the hundreds of existing film scripts and test how coherent the models can be. My guess is not at all

The clips on the Sora site today would have been utterly astonishing ten years ago. Long term progress can be surprising.

https://xkcd.com/605/

Re: Sora is here

#775

Post by aprilthird2021 »

danpalmer wrote: post #604
laweijfmvo wrote: post #19

Earlier quoted context omitted.

Love the callout of them definitely training on his own videos

...which they shouldn't have been able to get? I had thought that it was against the YouTube ToS? (my personal understanding, unrelated to my employer)

The companies are fairly brazen, at least internally, about just scraping whatever, wherever and not caring about ToS of any website. All they really care about is blocking "bad" data that might make the models racist or sexual, etc.

Re: Sora is here

#776

Post by pparanoidd »

itsdev wrote: post #747

Who legitimately asked for, or wants this? It's cool on it's face, sure. What legitimate problem does it solve? Isn't AI supposed to make our lives easier, or is that just "not what it's supposed to be bro", or whatever. I've lost track at this point with all the hallucinations and poor/bad/really fucking bad responses. It's not 100% of the time, but that's the point of companies like OpenAI releasing stuff like this…

It's not a solution to anything, it's simply just money. If they don't release a for-profit video generator, someone else will

Re: Sora is here

#777

Post by natmaka »

rossjudson wrote: post #705
bwfan123 wrote: post #700

Earlier quoted context omitted.

brilliant take from Ben Affleck on ai in movies.. "movies will be one of the last things to be replaced by ai" https://www.youtube.com/watch?v=ypURoMU3P3U including this quote: "being a craftsman is knowing how to work, art is knowing when to stop"

It is absolutely true that LLMs do not know when to stop.

An adequate prompter (human at the prompt) knows when to stop.

Re: Sora is here

#778

Post by Kiro »

tenpies wrote: post #675
thr3000 wrote: post #338

Earlier quoted context omitted.

So is yours! Mine isn't, however. I am a hard-nosed real boy now.

Write something that an LLM could never write. (This is my latest favorite prompt and interview/conversation question)

You go first.

Re: Sora is here

#779

Post by FranzFerdiNaN »

shermantanktop wrote: post #566
troupo wrote: post #405

Earlier quoted context omitted.

You should watch how movies are made sometime. How a script is developed. How changes to it are made. How storyboards are created. How actors are screened for roles. How locations are scouted, booked, and changed. How the gazillion of different departments end up affecting how a movie looks, is produced, made, and in which direction it goes (the wardrobe alone, and its availability and deadlines will have a huge impa…

I can't upvote this enough. This topic in the media space has generated a huge amount of naive speculation that amounts to "how hard could it be to do thing i know nothing about >?"

> "how hard could it be to do ?"

This is most Hacker News comments summarized lmao. It's kinda my favorite thing of this place: just open any thread and you immediately see so many people rushing to say ''well just do X or Y'' or ''actually it's X or Y and not Z like the experts claim''. Love it.

Re: Sora is here

#780

Post by agnishom »

jcims wrote: post #759
agnishom wrote: post #719

Earlier quoted context omitted.

Thanks, I did not know that you could use Canva for presentations. However, it is still proprietary software. (Worse, it lives on the web)

Work at a bank? That’s my reaction to 95% of the cool stuff I see every week.

No, I do not work at a bank. What do you mean?
Post reply on HN