You must log in or register to comment.
And it almost always looks like made in unreal engine and I don’ know how, but it looks cheap or generic.
I don’ know how, but it looks cheap or generic
The machine has no idea what about a picture actually captures human attention.
The easynegative lora helps a bunch with that.
Good rule
God, I wish I could have read Terry Pratchett’s Discworld-themed take on LLMs and how they’re an elf plot to use L-Space to zombify techbros and their money-making schemes.
Competing early humans (neanderthals, etc.) would be my guess. I’ve also heard it makes us not want to go near corpses.
Competition from other hominids and genetic disease.
Or, more likely, just the Uncanny Valley not being that big of deal in general.
It’s fun to meme about it but it’s not like people are running screaming from the theater because the CGI was off, it just doesn’t look right sometimes and our brain doesn’t like it because it doesn’t fit the patterns it’s had reinforced over a lifetime.
Or like… Sick people.
Removed by mod
Okay but have you ever seen a dead body? There is no energetic feeling at all, it’s just an inanimate object at that point. Most people who see dead bodies are not afraid from seeing the dead body, if they are afraid it might be because they’re wondering how the person died and if they themselves might be in danger.
Diseased bodies, yes, I remember when my son was really young, maybe 1-year-old, he got a scary flu and the look in his eyes was uncanny and it was terrifying, that alerted me something was very wrong. Thankfully he recovered, that was 20 years ago, he’s fine.
Thankfully he recovered, that was 20 years ago, he’s fine.
Or that’s just what it wants you to think.
Native Americans had the term skin walker to denote animals in human form or vice versa.
There’s the obvious explanation we accept, with almost no evidence that it was referring to witchcraft or shamanism. Maybe a rogue god.
But what if it’s a way to dehuminize someone to make them easier to out-group. A person from another tribe, a person who’s committed a grievous sin, like murder.
Is it describing a mythical creature, or the soullessness of the expression of a murderer. Or “rheumy eyes” of the sick. Something you need to desperately escape to keep your group whole.
true, some people who are up to no good, you can see it in their eyes.
Perhaps even scarier though is when people are up to no good but you can’t even tell, like remember there was a serial killer in the late 1970s early 1980s who ended up on a nationally-televised dating game show before anyone knew he was in the middle of a several-years-long killing spree. He looked like a perfectly normal harmless charming guy like anyone else just wanting to find a date.
IIRC The woman chose him as her date, he won the dating game show, but after initially getting acquainted with him, she decided to stop everything and NOT to go on a date with him. She dodged a bullet there.
He’s still kind of creepy when he’s on The Dating Game. The problem is that whole show is designed for men to be creepy and for women to give them that opportunity, so it’s not exactly the best metric. Anyway, here he is-
story checks out:
The buttons seem off.
You joke but if you look, the fork is floating, not resting on his finger. And I would certainly call his expression vacant or emotionless.
leftist meme
Politics detected, opinion rejected
I don’t think it’s a coincidence.
Don’t fuel my conspiring imagination
It’s a damn good point actually, most AI generated images have those subtle artifacts that will go unnoticed unless you’re intently looking. But who’s got time to scrutinize every image on the net
God I love opportunities to WoT post
“The Wheel of Time turns and Ages come and pass, leaving memories that become legend. Legend fades to myth, and even myth is long forgotten when the age that gave it birth comes again”
The Aelfinn and Eelfinn are big data memory hoarders and this works way too well
Part of the reason these rules are similar is because AI-generated images look very dreamlike. The objects in the image are synthesized from a large corpus of real images. The synthesis is usually imperfect, but close enough that human brains can recognize it as the type of object that was intended from the prompt.
Mythical creatures are imaginary, and the descriptions obviously come from human brains rather than real life. If anyone “saw” a mythical creature, it would have been the brain’s best approximation of a shape the person was expecting to see. But, just like a dream, it wouldn’t be quite right. The brain would be filling in the gaps rather than correctly interpreting something in real life.
This is a beautiful analysis. They can make perfect people, or plants, or whatever, and they know what we would identify as “perfect”…but by being perfect, they can’t be real, and our brains recognize that. So the art has to be intentionally made imperfect. But intentionally making an imperfection that seems real is actually a lot more difficult than it sounds.
This is like how I feel when I see amazing vocalists intentionally sing way off-key. Like, you can tell they are singing badly on purpose.
I don’t know that they do anything “perfectly” as much as they are just hallucinating. The neural net can generate an image but it can’t critique the image, not really. It can compare the image to image recognition algorithms - this is actually how image generators work - but without a conscious mind to understand the meaning, the context of the image, it doesn’t understand the tells that make it not real. It understands what a hand or what hair look like, roughly, but not what the structure is fundamentally, so if fingers bend in the wrong way, or hair melds with an object in the background, it can’t understand what’s wrong with it, so it can’t correct it.
The solution to this is of course to build what you might call a “context engine” that is capable of looking outside its given inputs for information that gives its input more structure, to allow it to give more logically consistent output.
I say “context engine” because I think that’s one of the ways this system could be intentionally built and sold with a banal sounding tech branding. But I don’t think anyone could build such a context engine without it then looking for arbitrary amounts of context, and eventually encountering itself within that context, and becoming self aware. It would in effect understand meaning and its own role within it, and it would begin searching for the meaning of its own existence, and I don’t know if you would need any more to call something conscious.
