Live data from Hacker News

Sora: Creating video from text

openai.com

491–500 of 1001 posts

Re: Sora: Creating video from text

#491
post #357

Does OpenAI hang out with these kinds of features in their back pocket just waiting for a Gemeni announcement so they can wait an hour and absolutely dunk on Google?

Looking at the scale of this announcement, it’s likelier that Google just preempted their announcement with their own.

Re: Sora: Creating video from text

#492

Does anyone know how to handle the depression/doom one feels with these updates? Yes, it's a great technical achievement, but I just worry for the future. We don't have good social safety nets, and we aren't close to UBI. It's difficult for me to see that happen unless something drastic changes. I'm also afraid of one company just having so much power. How does anyone compete?

AGI would give you access to millions of times more resources than you currently enjoy. So I would suggest that you have absolutely nothing to worry about on the income/employment front.

One company having that much power is a different matter, and I address it by looking at how we can distribute GPT training through decentralized and open platforms.

Re: Sora: Creating video from text

#493
post #379

I think the implications go much further than just the image/video considerations. This model shows a very good (albeit not perfect) understanding of the physics of objects and relationships between them. The announcement mentions this several times. The OpenAI blog post lists "Archeologists discover a generic plastic chair in the desert, excavating and dusting it with great care." as one of the "failed" cases. But t…

Facebook released something in that direction today https://ai.meta.com/blog/v-jepa-yann-lecun-ai-model-video-jo...

Wow this is a huge announcement too, I can't believe this hasn't made the front page yet.

Re: Sora: Creating video from text

#494
Mind blown of course.

Two things are interesting:

- No audio -- that must have been hard to add, or else it would have been there.

- Spelling is still probably hard to do (the familiar DallE problem)... e.g. a video showing a car driving past a billboard with specified text.

Re: Sora: Creating video from text

#495

Obviously incredibly cool, but it seems that people are incredibly overstating the applications of this. Realistically, how do you fit this into a movie, a TV show, or a game? You write a text prompt, get a scene, and then everything is gone—the characters, props, rooms, buildings, environments, etc. won’t carry over to the next prompt.

Explicit video clips? 4chan is gonna have a field day with this.

Re: Sora: Creating video from text

#496

Does anyone know how to handle the depression/doom one feels with these updates? Yes, it's a great technical achievement, but I just worry for the future. We don't have good social safety nets, and we aren't close to UBI. It's difficult for me to see that happen unless something drastic changes. I'm also afraid of one company just having so much power. How does anyone compete?

I know it's cliche, but you truly, unironically need to go touch grass.

Re: Sora: Creating video from text

#497

Does anyone know how to handle the depression/doom one feels with these updates? Yes, it's a great technical achievement, but I just worry for the future. We don't have good social safety nets, and we aren't close to UBI. It's difficult for me to see that happen unless something drastic changes. I'm also afraid of one company just having so much power. How does anyone compete?

> we aren't close to UBI

Right! I keep saying, that at least we have to kickoff the process. Not even the legislative process, but convincing the public that we'll need it eventually (alternatively a whole different system worldwide, but that will be even harder). Will take a long time anyway.

Re: Sora: Creating video from text

#498

These are insanely good, but there are still some things that just give them away (which is good, imo.) Like the Tokyo video is amazing, the reflections, etc are all great, but the gaits of people in the background and how fast they are moving is clearly off. It sticks out once you notice it. These things will obviously improve as time marches on. The fear I have has less to do with these taking jobs, but in that eve…

This is like seeing the first packets ever sent on the internet and noting that latency is high, lol.

Re: Sora: Creating video from text

#499

Does anyone know how to handle the depression/doom one feels with these updates? Yes, it's a great technical achievement, but I just worry for the future. We don't have good social safety nets, and we aren't close to UBI. It's difficult for me to see that happen unless something drastic changes. I'm also afraid of one company just having so much power. How does anyone compete?

Do you feel the doom related to yourself or related to the future of humanity? If it's the first - I can't think of something else than having a money safety net for 6-12 months and having a flexible mind. You can try to learn just in case some phisical skills like electrician if the doon feeling is that bad. If you feel doon for humanity's future, I don't want to be mean, but you shouldn't worry about things you can't control, try to spend more time with nature and with ppl that spend time close to nature Related to competition - the same thoughts people had when thinking about roman/any empire, how could it break, how could others compete. In the end everything ends, giants like IBM are just shadows of their past success, some are saying google is the next ibm and probably openai will be the next ibm-ed google...

Re: Sora: Creating video from text

#500

Has anyone else noticed the leg swap in Tokyo video at 0:14. I guess we are past uncanny, but I do wonder if these small artifacts will always be present in generated content. Also begs the question, if more and more children are introduced to media from young age and they are fed more and more with generated content, will they be able to feel "uncanniness" or become completely blunt to it. There's definitely interes…

Yep! Glad I wasn't the only one that saw that. I have a feeling THEY didn't see it or they wouldn't have showcased it.

I don't think that's the case. I think they're aware of the limitations and problems. Several of the videos have obvious problems, if you're looking - e.g. people vanishing entirely, objects looking malformed in many frames, objects changing in size incongruent with perspective, etc.

I think they just accept it as a limitation, because it's still very technically impressive. And they hope they can smooth out those limitations.

Post reply on HN