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

Veo 2: Our video generation model

deepmind.google

Post reply on HN
Print view View original

311–320 of 342 posts

Re: Veo 2: Our video generation model

#311

Post by incrudible »

andybak wrote: post #267
jillyboel wrote: post #215

Earlier quoted context omitted.

This tech is cute but the only viable outcomes are going to be porn and mass produced slop that'll be uninteresting before it's even created. Why even bother?

There will be both of those things in abundance. But I'm also seeing some genuinely creative uses of generative video - stuff I could argue has got some genuine creative validity. I am loathe to dismiss an entire technique because it is mostly used to create garbage. We'll have to figure out how to solve the slop problem - it was already an issues before AI so maybe this is just hastening the inevevitable.

The real problem is that trust in legacy media hit rock bottom right as we enter the era where we would need such trust the most. Soon enough, nothing you see on video can be believed, but (perhaps more importantly) nothing must be believed either.

Re: Veo 2: Our video generation model

#312

Post by bsenftner »

ferguu_ wrote: post #282
bsenftner wrote: post #273

Earlier quoted context omitted.

Deception is a key part of life, and the inability to discriminate fact from fiction is absolutely a key metric of success. Who said "kill or be killed"? Not I. It is survival or not, flourish or not, succeed or not.

But why must the deception take place? Evolution is natural, The development of AI generated videos takes teams of people, years of effort and millions of pounds. Why should those that are more easily deceived be culled? Do you believe that the future of technology is weeding out the weak? Do you believe the future of humanity is the existence of only those that can use the technologies we develop? You might very wel…

Deception takes places because deception takes place, because it can. I'm not the gatekeeper of it, I'm just acknowledging it and some of the secondary effects that will occur due to these inevitable technologies. I don't believe the future is anything other than a hope. That hope will require those future individuals to be very discriminating of their surroundings to survive, all surroundings includes all the society information and socialization, because that is filled with misinformation too. All that filled with misinformation right now, and it will just get more sophisticated. That's what I'm saying.

Re: Veo 2: Our video generation model

#313

Post by exodust »

eddd-ddde wrote: post #292
exodust wrote: post #288

Earlier quoted context omitted.

> " what is the actual use case of the art? " Not much. Low quality over-saturated advertising? Short films made by untalented lazy filmmakers? When text prompts are the only source, creativity is absent. No craft, no art. Audiences won't gravitate towards fake crap that oozes out of AI vending machines, unrefined, artistically uncontrolled. Imagine visiting a restaurant because you heard the chef is good. You enjoy…

> Imagine visiting a restaurant because you heard the chef is good. You enjoy your meal but later discover the chef has a "food generator" where he prompts the food into existence. Would you go back to that restaurant? That's an obvious yes from me. I liked it, and not only that, but I can reasonably assume it will be consistently good in the future, something lot's of places can't do.

So you'd forgive the deception (there's no "chef" only a button pusher) and revisit the restaurant even though you could easily generate the food yourself.

You don't care about the absence of a lifetime of hard work behind your meal, or the efforts of small business owners inspired by good food and passion in the kitchen. All that matters to you is that your taste buds were satisfied?

Interesting. Perhaps we can divide the world into those who'd happily dine at "Skynet Gourmet", and those who'd seek a real restaurant.

Re: Veo 2: Our video generation model

#314

Post by EForEndeavour »

golergka wrote: post #291
0xcb0 wrote: post #206

Imho is stunning, yet what is happening there is super dangerous. These videos will and may be too realistic. Our society is not prepared for this kind of reality "bending" media. These hyperrealistic videos will be the reason for hate and murder. Evil actors will use it to influence elections on a global scale. Create cults around virtual characters. Deny the rules of physics and human reason. And yet, there is no w…

Photoshop has been a thing for over 30 years.

Isn't the whole point of OP that we're currently watching the barrier to generating realistic assets go from "spend months grinding Photoshop tutorials" to "type what you want into this box and wait a few minutes"?

Re: Veo 2: Our video generation model

#315

Post by EForEndeavour »

esafak wrote: post #307
thatfrenchguy wrote: post #37

The example of a "Renaissance palace chamber" is very historically inaccurate by around a century or two, the generated video looks a lot like a pastiche of Versailles from the Age en Enlightenment instead. I guess that's what you get by training on the internet.

What's inaccurate about it?

It's technically and superficially breathtaking, but on closer inspection, it's a mishmash of styles across like 500 years.

- gold everywhere is excessive - more Rococo (1730s-1760s) than Renaissance (1300-1600 roughly), which was a lot more restrained

- mirror way too big and clear. Renaissance mirrors were small polished metal or darker imperfect glass

- candelabras too ornate and numerous for Renaissance. Multi tier candleholders are more Baroque (1600-1750), and candles look suspiciously perfect, as opposed to period-appropriate uneven tallow or beeswax

- white paper too pristine (parchment or vellum would be expected), pen holders hilariously modern, gold-plated(??) desk surface is absurd

- woman's clothing looks too recent (Victorian?); sleeves and hair are theatrical

- hard to tell, but background dudes are lurking in what look like theatrical costumes rather than anything historically accurate

Re: Veo 2: Our video generation model

#316

Post by esafak »

encoderer wrote: post #304
esafak wrote: post #302

Earlier quoted context omitted.

Who says they don't? Interference is being "democratized".

Any examples of hoax videos that you can name? I’m having a hard time placing any. I really find the threat to be overhyped.

You can find citations in https://en.wikipedia.org/wiki/Russian_interference_in_the_20...

Re: Veo 2: Our video generation model

#317

Post by eddd-ddde »

exodust wrote: post #313
eddd-ddde wrote: post #292

Earlier quoted context omitted.

> Imagine visiting a restaurant because you heard the chef is good. You enjoy your meal but later discover the chef has a "food generator" where he prompts the food into existence. Would you go back to that restaurant? That's an obvious yes from me. I liked it, and not only that, but I can reasonably assume it will be consistently good in the future, something lot's of places can't do.

So you'd forgive the deception (there's no "chef" only a button pusher) and revisit the restaurant even though you could easily generate the food yourself. You don't care about the absence of a lifetime of hard work behind your meal, or the efforts of small business owners inspired by good food and passion in the kitchen. All that matters to you is that your taste buds were satisfied? Interesting. Perhaps we can divi…

I think it's more complex than that. At least to me food in particular is nothing special, I truly eat just for substance, so if it doesn't taste bad, I'm happy.

I still believe that there's place for creative work, I just don't see why something created by something other than a human is inherently bad.

Re: Veo 2: Our video generation model

#318

Post by encoderer »

esafak wrote: post #316
encoderer wrote: post #304

Earlier quoted context omitted.

Any examples of hoax videos that you can name? I’m having a hard time placing any. I really find the threat to be overhyped.

You can find citations in https://en.wikipedia.org/wiki/Russian_interference_in_the_20...

So, nothing. Got it.

Re: Veo 2: Our video generation model

#319

Post by onel »

0xcb0 wrote: post #206

Imho is stunning, yet what is happening there is super dangerous. These videos will and may be too realistic. Our society is not prepared for this kind of reality "bending" media. These hyperrealistic videos will be the reason for hate and murder. Evil actors will use it to influence elections on a global scale. Create cults around virtual characters. Deny the rules of physics and human reason. And yet, there is no w…

The same things could be said when everyone could print their own newspapers or books. How would people distinguish between fake and real news?

I think we will need the same healthy media diet.

Re: Veo 2: Our video generation model

#320

Post by nosbo »

xvector wrote: post #241
nosbo wrote: post #156

Earlier quoted context omitted.

But it's the same thing just at a higher fidelity. Which is impressive don't get me wrong. But they are also kinda bad looking. Like even there good examples have so many issues. I just don't see how this gets extrapolated into the ideas in various posts like full length movies, custom TV shows and holodecks or whatever else people dream up. Do we have any examples of tech that just kept improving at exponential or l…

> Why is everyone so confident it will just keep getting better? Because there are literally thousands of avenues to explore and we've only just begun with the lowest of low hanging fruit.

What should I be looking into?
Post reply on HN