Hacker News Reader

Comment by scambier | Hacker News Reader

The woman appeared once, and they kept combining it with different prompts. So it stayed in the subsequent images.

https://twitter.com/supercomposite/status/156716492990339481... https://twitter.com/sheslostheplot/status/156737091948789350...

View on HN

> I was ripping Loab apart, and putting her back together. She is an emergent island in the latent space that we don't know how to locate with text queries. But for the AI, Loab was an equally strong point of convergence as a verbal concept. And really, it was usually stronger!

The nonsense words of someone who really wants to be the creator of the next big creepypasta.

Or someone who's pressing buttons and has absolutely zero fucking ideas of what the underlying tech id and does

Reminds of most humanities.

That’s a very ignorant statement.

> But I can confirm Loab exists in multiple image-generation AI models

Or they're lying and this is just a stunt to generate buzz.

> The nonsense words of someone who really wants to be the creator of the next big creepypasta.

It took them about 24 hours to come up with a merch store[1] for this character, too.

[1] https://twitter.com/supercomposite/status/156756520182584525...

I suppose they might as well while they’ve got their 5 minutes of fame.

> She is an emergent island in the latent space that we don't know how to locate with text queries

That is definitely a tall statement short on evidence. We expect there to be countless islands in latent space - this is basically a related concept to grandmother neurons, although instead of "Jennifer Aniston neuron" we have this "Loab neuron" which has no particular obvious origin. But I don't think there is anything privileged or special about this cluster.

https://en.wikipedia.org/wiki/Grandmother_cell

Italians have a precise word for that: "supercazzola". It's when someone voluntarily uses this nonsense bs to sell something or simulate some kind of knowledge.

That word makes me hungry

oh, really? it translates to "super cock sucker" :D

They forgot to mention how the metaverse created her, but now she has escaped into the real world!

thanks for the links, boggles the mind the article about the twitter thread and the images would not link to the twitter thread nor show more than a couple images. All the references in the vice article are only to other vice articles by the same writer...

The URL should probably link to the twitter thread in question, the articles adds pretty much nothing and removes tens of images and commentary by the creator.

I had the opposite thought. Couldn’t properly see the images because I don’t have twitter.

I even signed up recently just so I could click links and they immediately locked my account for being a bot.

Replace “twitter.com” with “nitter.net” in the URL and you can see a mirror.

The interesting bit is not that it remains there, but that it seems to generate dark images (gore, violence) regardless of the input.

I know very little about this stuff, but doesn’t that just mean that the algorithm considers the original image to contain gore/violence?

It at least considers the original image adjacent to gore/violence, but there's something uncanny about how the "Loab" image itself is not a gory or violent image. There's something funky going on along a "concept axis" involving the upside-down triangles on the face, the rosacea, and the overall bleak composition of the image.

The image looks a lot like the haggard female protagonists or victims in a lot of horror movies so it could just be a composite of those. The rosacea might be due to it confusing blood splattered faces with medical images. Honestly it just looks like a still image from a horror trailer to me.

I think it is somewhat interesting that it remains there, apparently after many many "generations" of combining with other images.

It's also interesting to consider what this image was originally "far" away from.

There are a couple of good followup threads exploring how such a thing might come about in the "latent space" of the model:

https://twitter.com/jthteo/status/1567418273628655617

https://twitter.com/mattskala/status/1567300206969982979

For me it kinda makes sense: the portrait/person is an important feature of the image, so it's heavily weighted in the generation, producing another image with that portrait/person, and so on. I find it more interesting that the visage itself is still recognizable between generations, as if it's not "any person", but a very specific visage.

Isn’t this just a result of the negative weights?

It is also important to note that they are specifically using features distant from one another (they are manipulating the latent and not using textual prompts to reproduce the face). It really does feel engineered to be creepy. Looking at the images closely it really does seem like a big reason for the creepiness is that there is a combined masculine and feminine features. That both are strong and since our brains are good at detecting human faces we instantly realize that something is off. Then there are the shadows on the face. The lighting is all wonky. Shadows are cast at weird angles. Either dark on the eyes compared to what should be seen or the opposite. Same goes for the mouth and chin area. Stable Diffusion and Midjourney aren't very good at human faces (specifically eyes, mouth, and skin textures), so that's going to add an extra creepy factor, especially combined with the negative weighting.

But you are spot on in noting that Vice is engaging in clickbait and misinformation. The tweets are purposefully being creepy because that is the art style of cryptids. But as your second link clearly shows, people aren't going to randomly find images like this (and let's be real, I wouldn't recognize this as the same person unless you told me they were). Stop engaging in melodrama Vice. You can't do that if you're claiming to report news.

> Stop engaging in melodrama Vice.

what's the point in telling a fish to stop swimming

Maybe others will stop following the fish.

Reply on news.ycombinator.com