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

DALL-E 2 generates images of Kermit The Frog in various films

twitter.com

Post reply on HN
Print view View original

121–130 of 198 posts

Re: DALL-E 2 generates images of Kermit The Frog in various films

#121

Post by bogwog »

FeepingCreature wrote: post #109
bogwog wrote: post #57

Earlier quoted context omitted.

I feel like if they don’t have licenses for all of their source material, then the model should be required to be released into the public domain. It’s like extremely expensive piracy that is bad for artists and bad for the environment. I wonder if the reason OpenAI, Google, etc don’t release these things isn’t so much that they’re worried about racist/offensive output, but instead they’re worried about people using…

Being bad for artists and the environment is not illegal. If you look at a movie poster, your brain does not need to be released in the public domain. Even if you sketch it from memory.

> Being bad for artists and the environment is not illegal.

Yet we have copyright laws and environmental protection laws to protect both.

> If you look at a movie poster, your brain does not need to be released in the public domain. Even if you sketch it from memory.

Because I’m not a machine. I’m contrained by physics, whereas these models are not.

Copyright laws were made to protect artists from IP theft. If I make a sculpture, it’s not trivial to copy that and steal from me, so creating copyright laws to protect sculptors would be a hard sell.

But a painting, a book, a song, etc are easy to steal, especially with technology. Copying and selling someone else’s painting is similar to copying and selling someone else’s sculpture, yet the scale of theft is obviously different (mass producing sculptures is much harder than making unlimited copies of an mp3)

These AI models are a new type of theft, and likewise need new types of legal protections for artists.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#122

Post by andrewstuart2 »

tdehnel wrote: post #111
tinalumfoil wrote: post #104

The amount of creativity here is astounding. Just imagine all the decisions the AI made in incorporating Kermit into the movies: the clothing it's chosen, how the character wears the clothing, the facial expressions, how to make Kermit himself look similar to the other movies characters. Should he be lanky? pudgy? Even simple decisions like obliviously Kermit in Wall-E is going to be a robot, it has to figure out wha…

Sorry to be this guy but that is not creativity. It’s using what already exists, not conjecturing something new. Contrast with real creativity (what people can do but machines currently cannot) where you conjecture something completely new. For example, Copernicus conjecturing the idea that the Earth revolves around the Sun. No machine learning model would have gotten there because it would have been trained on a bun…

The scientific and creative methods are both entirely centered around evaluating data or existing creative elements and combining it in novel ways. Science adds the goal of making and testing hypotheses but nothing about Copernicus's conjecture would have been possible without observing existing information. I'm including e.g. "new" astronomical observations in the realm of existing information because even a human is simply observing and measuring it.

I fail to see what the difference is between 99% of existing "creativity," which is essentially arranging existing ideas into novel combinations, and what DALLE2 does.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#123

Post by simiones »

pygy_ wrote: post #103
FredPret wrote: post #76

How is this so good? If you told me this was done by a very talented human, I’d still be surprised at how good they are. That must count as a sort of Turing test, no?

DALL-E is indeed superhuman in its ability to create images from simple prompts. This shows the limits of the Turing test. To pass it a program must not only be smart enough, it must be dumb enough too. Pulling what DALL-E does is a tell-tale sign it’s most likely not human, and would make it fail the test.

Well, most of the pictures (if not all), while astoundingly good as an idea, have the tell-tale signs of being AI-generated, the kinds of mistakes a human would never make.

For example, looking at the WALL-E one [0], you can clearly see that the hands and feet aren't actually separated properly. There is also plenty of missing "logic" around the armpits. These are the kinds of mistakes a human can't make - especially one that is so adept at drawing the other parts so perfectly.

[0] https://twitter.com/HvnsLstAngel/status/1531512163738669057/...

Re: DALL-E 2 generates images of Kermit The Frog in various films

#124

Post by gwern »

tinalumfoil wrote: post #104

The amount of creativity here is astounding. Just imagine all the decisions the AI made in incorporating Kermit into the movies: the clothing it's chosen, how the character wears the clothing, the facial expressions, how to make Kermit himself look similar to the other movies characters. Should he be lanky? pudgy? Even simple decisions like obliviously Kermit in Wall-E is going to be a robot, it has to figure out wha…

> like I'm not sure why kermit has a plastic texture in many of the pictures

That might be the known bug with low-resolution textures: the DALL-E 2 paper notes that the details in very complex scenes can be bad, and thinks it's because you start with a 64px image which is necessarily bad for details (64px is really small!) and upscale with dumber models from there https://cdn.openai.com/papers/dall-e-2.pdf#page=17 I think this explains the issues with images where the 'skin' or 'fur' looks really creepy (eg. all the semi-nude bears).

Re: DALL-E 2 generates images of Kermit The Frog in various films

#125

Post by layer8 »

mynegation wrote: post #112

I am finishing “Love, Death + Robots” on Netflix and between the quality of CGI and things like DALL-E and Imagen, movie, design, and illustration industries are in for an upheaval.

Video is probably a whole other ballpark regarding required training and resources.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#126

Post by notahacker »

myrmidon wrote: post #59
tgv wrote: post #4

Earlier quoted context omitted.

Yes, and it still feels a lot like Searle's Chinese Room. It's as if it skips a dozen steps. Well, that's exactly what happens, of course. But it does show that the network can match linguistic descriptions to images extraordinarily well.

Do you find the Chinese Room argument convincing? Do you feel that the human mind is more than an "appropriately" trained "biological" neural network? What do you consider the limits of a DALL-E like system compared to a "true" mind? My personal opinion is that the Chinese Room argument is fancy handwaving that crucially relies on never being explicit about what it means by "understanding", combined with an appeal to…

There doesn't need to be anything "magical" about the human mind for human "understanding" not to be particularly closely approximated by performing mathematical transformations on a huge corpus of raster data, even though the latter approach produces very useful results (see also the utility of a pocket calculator vs attempting to skip a billenium or so of natural evolution to grow an organism motivated to learn multiplication in a petri dish, or parse human minds to figure out the elements of brain state associated with performing a calculation)

GPT-3 is far, far better at generating descriptions of loving humanity than the average dog. But it's pretty obvious that the dog's goal formation and excitement hormones aren't particularly similar to letter-by-letter ASCII output probability calculations on a database, and that GPT-3 has no more grasp of the dog's love of humanity in general and this human in particular than the dog has of Shakespeare. "Thought" and intelligible results are essentially orthogonal, which limits the feasibility of training the former...

Re: DALL-E 2 generates images of Kermit The Frog in various films

#127

Post by gwern »

tdehnel wrote: post #111
tinalumfoil wrote: post #104

The amount of creativity here is astounding. Just imagine all the decisions the AI made in incorporating Kermit into the movies: the clothing it's chosen, how the character wears the clothing, the facial expressions, how to make Kermit himself look similar to the other movies characters. Should he be lanky? pudgy? Even simple decisions like obliviously Kermit in Wall-E is going to be a robot, it has to figure out wha…

Sorry to be this guy but that is not creativity. It’s using what already exists, not conjecturing something new. Contrast with real creativity (what people can do but machines currently cannot) where you conjecture something completely new. For example, Copernicus conjecturing the idea that the Earth revolves around the Sun. No machine learning model would have gotten there because it would have been trained on a bun…

> No machine learning model

https://www.nature.com/articles/d41586-019-03332-7

Re: DALL-E 2 generates images of Kermit The Frog in various films

#128

Post by simiones »

xeromal wrote: post #75
sp332 wrote: post #9

Does that mean the developers put The Big Lebowski through the model during training? Where did they get all the movies and TV shows from? And does copying so directly from the source material open them and users up to copyright infringement liability?

I would hope that the spirit of the law would be considered in this. This is a clear application of fair use. Are the owners of the IP losing money on letting someone generate new characters in their movie/show?

> Are the owners of the IP losing money on letting someone generate new characters in their movie/show?

Typically, creators are very protective of this sort of thing, unless it stays in the area of fan art. If anyone tries to seriously monetize this kind of output, I'm sure we'll see a lot of cases.

Imagine what Disney would do if you used DALL-E to create an animated feature film in the style of Mickey Mouse, but with cats instead of mice, and they found out you used actual footage from, say, Fantasia to train an AI model. No idea if they would win, but I'm certain they'd sue.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#129

Post by layer8 »

andreilys wrote: post #73
AnIdiotOnTheNet wrote: post #62

Earlier quoted context omitted.

On the one hand, the ability for Star Trek's Holodeck to create large amounts of content from a few terse natural language instructions is look less and less implausible. On the other hand, I feel like this will ultimately be kinda like traditional procgen algorithms: once you've seen enough of what it produces it all starts feeling very bland and same-y. Sure, the AI may be able to produce a feature-length movie bas…

it would lack the novelty and playfulness of a good human creative work, and it likely would be very shallow in its themes. Simply tune the parameters associated with novelty and playfulness and you’ll get the desired result. There’s nothing inherent in human creativity that can’t be replicated by an AI. Most creative work is derivative and remix’s prior art. This is a good short video on the phenomenon of remixing h…

> Simply tune the parameters associated with novelty and playfulness

Nah, you should be able to add “…but with some novelty and playfulness” to the prompt.

Re: DALL-E 2 generates images of Kermit The Frog in various films

#130

Post by ekianjo »

bogwog wrote: post #121
FeepingCreature wrote: post #109

Earlier quoted context omitted.

Being bad for artists and the environment is not illegal. If you look at a movie poster, your brain does not need to be released in the public domain. Even if you sketch it from memory.

> Being bad for artists and the environment is not illegal. Yet we have copyright laws and environmental protection laws to protect both. > If you look at a movie poster, your brain does not need to be released in the public domain. Even if you sketch it from memory. Because I’m not a machine. I’m contrained by physics, whereas these models are not. Copyright laws were made to protect artists from IP theft. If I make…

> hese AI models are a new type of theft, and likewise need new types of legal protections for artists.

Meh. This means that most artists will also struggle to make something as good as these models and will have to find something else to do for a living. Its not the first time in history that an occupation is obsoleted. Projectionnists in cinemas have mostly dissapeared.

Post reply on HN