Hacker News Reader

Comment by monological | Hacker News Reader

What everyone is missing is that these AI image/video generators lack _taste_. These tools just regurgitate a mishmash of images from it's training set, without any "feeling". What you're going to tell me that you can train them to have feeling? It's never going to happen.

View on HN

"These tools just regurgitate a mishmash of images from it's training set"

I don't think that's a particularly useful mental model for how these work.

The models end up being a tiny fraction of the size of the training set - Stable Diffusion is just 4.3GB, it fits on a DVD!

So it's not a case of models pasting in bits of images they've seen - they genuinely do have a highly compressed concept of what a cactus looks like, which they can use to then render a cactus - but the thing they render is more of an average of every cactus they've seen rather than representing any single image that they were trained on.

But I agree with you on taste! This is why I'm most excited about what happens when a human with great taste gets to take control of these generative models and use them to create art that wouldn't be possible to create without them (or at least not possible to create within a short time-frame).

You can put your taste into it with prompt engineering and cherry picking with limited effort, for Stable Diffusion you can look for prompts people came up with online quite easily and merge/change them pretty much however you want. Might have to disable the content filters and run it on your own hardware though.

That's purely subjective. We can definitely model AI to give a certain mood. Sentiment analysis and classification is very advanced, it just hasn't been put in these models.

If you think AI will never catch up to anything a human can do, you're simply wrong.

This isn't a very compelling argument. First of all, they aren't a "mish mash" in any real way, it's not like snippets of images exist inside of the model. Second of all, this is entirely subjective. Third of all, entirely inconsequential - if these models create 80% of the video we end up seeing, is it going to matter if you don't think it's a tasteful endeavour?

> This bourgeoisie -- the middle class that is neither upper nor lower, neither so aristocratic as to take art for granted nor so poor it has no money to spend in its pursuit -- is now the group that fills museums, buys books and goes to concerts. But the bourgeoisie, which began to come into its own in the 18th century, has also left a long trail of hostility behind it ... Artistic disgust with the bourgeoisie has been a defining theme of modern Western culture. Since Moliere lambasted the ignorant, nouveau riche bourgeois gentleman, the bourgeoisie has been considered too clumsy to know true art and love (Goethe), a Philistine with aggressively unsubtle taste (Robert Schumann) and the creator of a machine-obsessed culture doomed to be overthrown by the proletariat (Marx and Engels).

- "Class Lessons: Who's Calling Whom Tacky?; The Petite Charm of the Bourgeoisie, or, How Artists View the Taste of Certain People", Edward Rothstein, The New York Times

This article also discusses a painting called "The Most Wanted" which was drawn based off a survey posed to ordinary people about what they wanted to see in a painting. "A mishmash of images from it's training set," if you will.

Claiming that others lack taste seems to be a common refrain--only this time, instead of a reaction to a subset of the human population gnawing away at the influence of another subset of humans, it's to yet another generation of machines supplanting human skill.

The more developed the artistic taste, the lower one's opinion of other tastes.

A Midjourney piece beat human artists in an art competition. So the judges of that competition disagree.

Making a definitive statement with the word "never" is a bold move.

They work at the level of convolutions, not images.

Reply on news.ycombinator.com