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

Veo

deepmind.google

Post reply on HN
Print view View original

441–450 of 539 posts

Re: Veo

#441

Post by lpapez »

goostavos wrote: post #395
cryptoz wrote: post #388

Earlier quoted context omitted.

There's a middle ground here. I saw the northern lights with my own eyes just days ago and it was mostly grey. I saw some color. But when I took a photo with a phone camera, the color absolutely popped . So it may be that you've seen more color than any photo, but the average viewer in Seattle this past weekend saw grey-er with their eyes and huge color in their phone photos. (Edit: it was still super-cool even if gr…

The hubris of suggesting that your single experience of vaguely seeing the northern lights one time in Seattle has now led to a deep understanding of their true "color" and that the other person (perhaps all other people?) must be fooling themselves is... part of what makes HN so delightful to read. I've also seen the northern lights with my own eyes. Way up in the arctic circle in Sweden. Their color changes along w…

> The hubris of suggesting that your single experience of vaguely seeing the northern lights one time in Seattle has now led to a deep understanding of their true "color" and that the other person (perhaps all other people?) must be fooling themselves is... part of what makes HN so delightful to read.

The H in HN stands for Hubris.

Re: Veo

#442

Post by DaSHacka »

jabits wrote: post #434
shwaj wrote: post #427

Earlier quoted context omitted.

That mirrors my experience from when I used to live in northern Canada

Even in Upper Michigan near Lake Superior we sometimes had stunn, colorful Northern Lights. Sometimes it seemed like they were flying overhead within your grasp

Most definitely, it's quite common to find people hanging around outside up towards Calumet whenever there's a night with a high KP Index.

I highly recommend checking them out if you're nearby, the recent auoras have been quite astonishing

Re: Veo

#443

Post by Jensson »

TaylorAlexander wrote: post #419
Jonanin wrote: post #368

Earlier quoted context omitted.

Except that many of the people involved do think of it like a football game, and thus it actually is like one. Of course the researchers and engineers at both OpenAI and Google DeepMind have a sense of rivalry and strive to one up another. They definitely feel like they are in a competition.

> They definitely feel like they are in a competition. Citation needed? Although I did not work in AI, I did work at Google X robotics on a robot they often use for AI research. Maybe some people felt like it was a competition, but I don’t have much reason to believe that feeling is common. AI researchers are literally in collaboration with other people in the field, publishing papers and reading the work of others t…

> AI researchers are literally in collaboration with other people in the field, publishing papers and reading the work of others to learn and build upon it.

When OpenAI suddenly stopped publishing their stuff I bet that many researchers now started feeling like it started to be a competition.

OpenAI is no longer cooperating, they are just competing. They still haven't said anything about how gpt-4 works.

Re: Veo

#444

Post by alex_duf »

loudmax wrote: post #21

The videos in this demo are pretty neat. If this had been announced just four months ago we'd all be very impressed by the capabilities. The problem is that these video clips are very unimpressive compared to the Sora demonstration which came out three months ago. If this demo was announced by some scrappy startup it would be worth taking note. Coming from Google, the inventor of the Transformer and owner of the larg…

>these sample videos are underwhelming

wow the speed at which we can be blasé is terrifying. 6 months ago this was not possible, and felt this was years away!

They're not underwhelming to me, they're beyond anything I thought would ever be possible.

are you genuinely unimpressed? or maybe trying to play it cool?

Re: Veo

#445

Post by earthnail »

MarcScott wrote: post #415
psbp wrote: post #226

Earlier quoted context omitted.

My brain processes too slow for modern action movies. I can tell what's going on, but I always end up feeling agitated.

I'm okay with watching the majority of action movies, but I distinctly remember watching this fight scene in a Bourne movie and not having a clue what was going on. The constant camera changes, short shot length, and shaky cam, just confused the hell out of me. https://youtu.be/uLt7lXDCHQ0?si=JnVMjmu0WgN5Jr5e&t=70

I thought it was brilliant. Notice there’s no music. It’s one of the most brutal action scenes I know. Brutal in the sense of how honest it felt about direct combat.

Re: Veo

#446

Post by smusamashah »

salamo wrote: post #366
sdenton4 wrote: post #361

Earlier quoted context omitted.

This strikes me as equally "AI complete" as drawing hands, which is now essentially a solved problem... No one test is sufficient, because you can add enough training data to address it.

Yeah "AI complete" is a bit tongue-in-cheek but it is a fairly spectacular failure mode of every model I've tried.

Ideogram and dalle do hands pretty well

Re: Veo

#447

Post by peanut_merchant »

stkhlm wrote: post #414
exodust wrote: post #408

Earlier quoted context omitted.

> nobody wants to see a video or a photo of a dark, gray, and barely visible aurora Except those who want to see an accurate representation of what it looks like to the naked eye.

Living in northern Sweden I see the northern lights multiple times a year. I have never seen them pale or otherwise not colorful. Green and reds always. That is to my naked eye. Photographs do look more saturated, but the difference isn't as large as this comment thread make it out to be.

Even in Northern Scotland (further south than northern Sweden) this is the case. The latest aurora showing was vividly colourful to the naked eye.

Re: Veo

#448

Post by larodi »

ugh123 wrote: post #219

From a filmmaking standpoint I still don't think this is impactful. For that it needs a "director" to say: "turn the horse's head 90˚ the other way, trot 20 feet, and dismount the rider" and "give me additional camera angles" of the same scene. Otherwise this is mostly b-roll content. I'm sure this is coming.

Perhaps the only industry which immediately benefits from this is the short ads and perhaps TikTok. But still it is very dubious, as people seem to actually enjoy being themselves the directors of their thing, not somebody else.

Maybe this works for ads for duner place or shisha bar in some developing country. I’ve seen generated images used for menus in such places.

But I doubt a serious filmography can be done this way. And if it can - it’d be again thanks to some smart concept on behalf of humans.

Re: Veo

#449

Post by poulpy123 »

arcticbull wrote: post #354
salamo wrote: post #353

The first thing I will do when I get access to this is ask it to generate a realistic chess board. I have never gotten a decent looking chessboard with any image generator that doesn't have deformed pieces, the correct number of squares, squares properly in a checkerboard pattern, pieces placed in the correct position, board oriented properly (white on the right!) and not an otherwise illegal position. It seems to be…

Similarly the Veo example of the northern lights is a really interesting one. That's not what the northern lights look like to the naked eye - they're actually pretty grey. The really bright greens and even the reds really only come out when you take a photo of them with a camera. Of course the model couldn't know that because, well, it only gets trained on photos. Gets really existential - simulacra energy - maybe a…

that's a bad example since the only images of aurora borealis are brightly colored. What I expect of an image generator is to output what is expected from it

Re: Veo

#450

Post by SilverSlash »

spaceman_2020 wrote: post #421
fakedang wrote: post #63

Earlier quoted context omitted.

Honestly, if Veo becomes public faster than Sora, they could win the video AI race. But what am I wishfully thinking - it's Google we're talking about!

The cost to switch to new models is negligible. People will switch to Sora if its better instantly I’ve switched to Opus from GPT-4 for coding and it was non-trivially easy

Except your single experience doesn't mean it's generally true, bud. For instance I have not switched to Opus despite claims that it is better because I don't want to go through the effort of cancelling my ChatGPT subscription and subbing to Claude. Plus I like getting new stuff early that OpenAI occasionally gives out and the same could apply for Google's AI.
Post reply on HN