81
Comments (16)
sorted by:
6
Michelleobamasnuts 6 points ago +6 / -0

This website always trips me out, man. Like, how do we know for sure that the person doesn’t exist just because it’s a computer generated image of a human? What is the probability of the AI generating a human that does exist?

7
deleted 7 points ago +7 / -0
3
Michelleobamasnuts 3 points ago +3 / -0

Then reality starts to break and fear (tries) to kick in.

1
erikc28484 1 point ago +1 / -0

When one uses singularity and simulacrum in the same sentence, one gets TWO updoots. KEK

2
SJBHamilton 2 points ago +2 / -0

Have you heard of "twin strangers" (doppelgangers)?

https://twinstrangers.net/

1
Michelleobamasnuts 1 point ago +1 / -0

I’ve heard of doppelgängers. Once had a checkout lady swear I had just come through her line less than five minutes before when I hadn’t. She thought I was joking and I had to deny it four times before she accepted my answer and even then she still seemed skeptical. Never heard of that website though.

1
PaucaSedMatura 1 point ago +1 / -0

how do we know for sure that the person doesn’t exist just because it’s a computer generated image of a human? What is the probability of the AI generating a human that does exist?

You can verify that by running the code yourself on your computer and comparing the output images with the methods (code) used to generate them.

After a few seconds of loading the page, you'll see some information displayed about the image:

Imagined by a GAN (generative adversarial network) StyleGAN2 (Dec 2019) - Karras et al. and Nvidia Don't panic. Learn how it works [1] [2] [3] Help this AI continue to dream | Contact me Code for training your own [original] [simple] [light] Art • Cats • Horses • Chemicals Another

https://www.youtube.com/watch?v=u8qPvzk0AfY https://www.youtube.com/watch?v=dCKbRCUyop8 https://www.youtube.com/watch?v=SWoravHhsUU

https://github.com/NVlabs/stylegan2 https://github.com/lucidrains/stylegan2-pytorch https://github.com/lucidrains/lightweight-gan

As for the question of "what is the probability of the AI generating a human that does exist?" ... i'd say the probably is precisely 0.0 since you're looking at pixels and not proteins. ;)

1
Michelleobamasnuts 1 point ago +1 / -0

I understand that it is pixels and how the photos are generated. My question still stands: What is the probability of those pixels generating into the same cellular makeup as a living person that I could photograph?

1
PaucaSedMatura 1 point ago +1 / -0

To answer, you'll have to explain what it means for a set of pixels to have a "cellular makeup as [in] a living person". Your question doesn't really follow based on my earlier tounge-in-cheek (but factual) statement about pixels vs. proteins.

Perhaps you're asking about the eventuality of finding a living person that bears a strong resemblance to one of the generated images. That would depend on a totally subjective observation, and you would always be able to take any number of photos of the alleged real subject showing discrepancies with the generated one.

6
merf 6 points ago +6 / -0

Are they generated on the fly? Seems like a great resource for creating social profiles.

3
Aspie 3 points ago +3 / -0

It's a real time saver. I used to make profile photos myself by copying a random photo from some other country, and then doing major modifications in graphics software.

2
deleted 2 points ago +2 / -0
5
Circus4One 5 points ago +5 / -0

That’s crazy, I just clicked on one and the girl had a cold sore on her lip.

4
SJBHamilton 4 points ago +4 / -0

You are right it is no longer "read the news be informed."

Today it's more like, scour a variety of sources, from trusted to bullshit.

4
Despitetospite 4 points ago +4 / -0

(Off topic) Imagine clicking this and seeing yourself…

It’s really trippy…

2
merf 2 points ago +2 / -0

Every once in a while you get one that "glitches". I had one with some weird neck growth, and another guy that had 1/8th of a glasses frame.