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

371–380 of 1001 posts

Re: Sora is here

#371

Post by PartiallyTyped »

quenix wrote: post #199
sjm wrote: post #162

Anyone else find this stuff extremely distasteful? "Disrupting" creativity and art feels like it goes against our humanity.

The past few years' innovation in AI has roughly been split into two camps for me. LLMs -- Awesome and useful. Disruptive, and somewhat dangerous, but probably more good than harm if we do it right. 'Generative art' (i.e. music generation, image generation, video generation) -- Why? Just why? The 'art' is always good enough to trick most humans at a glance but clearly fake, plastic, and soulless when you look a bit c…

I have found a channel that curates and cleans some AI generated music. I really enjoy it, it's nothing I heard before, it's unique, distinct, and devoid of copyright.

Re: Sora is here

#372

Post by benatkin »

pushcx wrote: post #220
simonw wrote: post #164

I got lucky and got in moments after it launched, managed to get a video of "A pelican riding a bicycle along a coastal path overlooking a harbor" and then the queue times jumped up (my second video has been in the queue for 20+ minutes already) and the https://sora.com site now says "account creation currently unavailable" Here's my pelican video: https://simonwillison.net/2024/Dec/9/sora/

I don't have a lot of mental model for how this works, but I was surprised to note that it seems to maintain continuity on the shapes of the bushes and brown spots on the grass that track out of frame on the left and then reappear as it pans back into frame.

That must be exactly it. The simulated scene extends beyond what the camera is currently capturing.

Re: Sora is here

#373

Post by IanCal »

jsheard wrote: post #315
sccomps wrote: post #253

Earlier quoted context omitted.

> For instance, that ladybug looks pretty natural, but there's a little glitch in there that an unwitting observer, who's never seen a ladybug move before, may mistake as being normal. And maybe it is! And maybe it isn't? Well, none of the existing animation movies follow exact laws of physics.

Animation doesn't follow exact laws of physics, but the specific ways they don't follow physics have very deliberate intent behind them. There's a pretty clear difference between the coyote running off a cliff and taking 2 seconds to start falling, and a character awkwardly floating over the ground because an AI model got confused.

>but the specific ways they don't follow physics have very deliberate intent behind them.

That is only true for well crafted things. There's plenty of stuff that's just wrong for no reason beyond ease of creation or lack of care about the output.

Re: Sora is here

#374

Post by jeroen »

isoprophlex wrote: post #60
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…

And another thing that irks me: none of these video generators get motion right... Especially anything involving fluid/smoke dynamics, or fast dynamic momements of humans and animals all suffer from the same weird motion artifacts. I can't describe it other than that the fluidity of the movements are completely off. And as all genai video tools I've used are suffering from the same problem, I wonder if this is someho…

They don't even get basic details right. The ship in the 8th video changes with every camera change and birds appear out of nowhere.

Re: Sora is here

#375

Post by mojuba »

ssl-3 wrote: post #365
mojuba wrote: post #312

Earlier quoted context omitted.

Yes but a movie is a movie whereas these AI-generated videos will likely be used to replace stock footage in other (documentary, promotional, etc.) contexts

If the producer wants to publish bad physics, they get bad physics. If the producer wants to publish good physics, they get good physics. It doesn't matter if it is AI, CGI, live action, stop motion, pen-and-ink animation, or anything else. The output is whatever the production team wants it to be, just as has been the case for as long as we've had cinema (or advertising or documentaries or TikToks or whatevers). Not…

You don't have full control over AI-generated images though, or not to the same extent producers have with CGI.

There's a video on sora.com at the very bottom, with tennis players on the roof, notice how one player just walks "through" the net. I don't think you can fix this other than by just cutting the video earlier.

Re: Sora is here

#376

Post by mike_hearn »

lacoolj wrote: post #235

A little worried how young children watching these videos may develop inaccurate impressions of physics in nature. For instance, that ladybug looks pretty natural, but there's a little glitch in there that an unwitting observer, who's never seen a ladybug move before, may mistake as being normal. And maybe it is! And maybe it isn't? The sailing ship - are those water movements correct? The sinking of the elephant int…

AI physics isn't worth worrying about compared to other inaccurate things kids see in movies. It doesn't seem to hurt them.

If you really want something to worry about, consider that movies regularly show pint-sized women successfully drop kicking men significantly bigger than themselves in ways that look highly plausible but aren't. It's not AI but it violates basic laws of biology and physics anyway. Teaching girls they can physically fight off several men at once when they aren't strong enough to do that seems like it could have pretty dangerous consequences, but in practice it doesn't seem to cause problems. People realize pretty quick that movie physics isn't real.

Re: Sora is here

#377

Post by TeMPOraL »

Ar-Curunir wrote: post #237
TeMPOraL wrote: post #127

Earlier quoted context omitted.

> Now expand that to movies and games and you can get why this whole generative-AI bubble is going to pop. What will save it is that, no matter how picky you are as a creator, your audience will never know what exactly was that you dreamed up, so any half-decent approximation will work. In other words, a corollary to your corollary is, "Fortunately, you don't need them to be, because no one cares about low-order bits…

That's just sad, and why people have a derogative stance towards generative AI: "half-decent" approximation removes all personality from the output, leading to a bunch of slop on the internet.

It does indeed, but then many of those people don't notice they're already consuming half-decent, personality-less slop, because that's what human artists make too, when churning out commercial art for peanuts and on tight deadlines.

It's less obvious because people project personality onto the content they see, because they implicitly assume the artist cared, and had some vision in mind. Cheap shit doesn't look like cheap shit in isolation. Except when you know it's AI-generated, because this removes the artist from the equation, and with it, your assumptions that there's any personality involved.

Re: Sora is here

#378

Post by david-gpu »

benchmarkist wrote: post #204
david-gpu wrote: post #196

Earlier quoted context omitted.

> the idea is very obvious but they haven't done it because they don't have the wherewithal to do so Fascinating! I wish I had the knowledge and wherewithal to do that and become rich instead of wasting my time on HN.

No one is perfect but you should try to do better and waste less time on HN now that you're aware and can act on that knowledge.

Nah, I'm good. HN can be a very amusing place at times. Thanks, though.

Re: Sora is here

#379

Post by raincole »

miltonlost wrote: post #62
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 adage "a picture is worth a thousand words" has the nice corollary "A thousand words isn't enough to be precise about an image". Now expand that to movies and games and you can get why this whole generative-AI bubble is going to pop.

The point is not to be precise. It's to be "good enough".

Trust me, even if you work with human artists, you'll keep saying "it's not quite I initially invisioned, but we don't have budget/time for another revision, so it's good enough for now." all the time.

Re: Sora is here

#380

Post by SaintSeiya »

lacoolj wrote: post #235

A little worried how young children watching these videos may develop inaccurate impressions of physics in nature. For instance, that ladybug looks pretty natural, but there's a little glitch in there that an unwitting observer, who's never seen a ladybug move before, may mistake as being normal. And maybe it is! And maybe it isn't? The sailing ship - are those water movements correct? The sinking of the elephant int…

Don't be, physics laws miss interpretation are very quick to correct with a reality check. I'm more worried for kids that have to learn how the world works trough a screen. Just let them play outside and interact with other kids and nature. Let them fall and cry, and scratch and itch, it will make them stronger and healthier adults.
Post reply on HN