this post was submitted on 15 Feb 2025
1114 points (98.9% liked)

Science Memes

12384 readers
2153 users here now

Welcome to c/science_memes @ Mander.xyz!

A place for majestic STEMLORD peacocking, as well as memes about the realities of working in a lab.



Rules

  1. Don't throw mud. Behave like an intellectual and remember the human.
  2. Keep it rooted (on topic).
  3. No spam.
  4. Infographics welcome, get schooled.

This is a science community. We use the Dawkins definition of meme.



Research Committee

Other Mander Communities

Science and Research

Biology and Life Sciences

Physical Sciences

Humanities and Social Sciences

Practical and Applied Sciences

Memes

Miscellaneous

founded 2 years ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] pennomi@lemmy.world 41 points 1 week ago (7 children)

Looks like an AI generated image to me. Lots of strange artifacts an artist wouldn’t create. And there’s something uncanny about the stippling pattern I’ve seen before in AI images.

[–] barsoap@lemm.ee 9 points 6 days ago (1 children)

The top right one is definitely not drawn by a human, it's right out hexagons. Noone cross-hatches like that because you can't cross-hatch like that there's no lines going straight through.

The rest could be artistic choice, compression artifacts, or other stuff though. Well, some minor stuff, the topmost book on the left pile on the desk on the right is sus, and there's way too many sponges at the base of the chalkboard. But none of them are dead tells like the hexagons.

[–] spookex@lemmy.world 3 points 6 days ago (1 children)

Idk about that, I used to sometimes work for a group that translates manga and have seen similar patterns to that

[–] barsoap@lemm.ee 5 points 6 days ago* (last edited 6 days ago)

It does somewhat resemble the halftone dithering patterns that commonly occur in manga, but this is supposed to be cross-hatched otherwise the fringes wouldn't be lines.

[–] FauxLiving@lemmy.world 4 points 6 days ago

This looks shopped — I can tell from some of the pixels, and from seeing quite a few shops in my time.

[–] RedSnt@feddit.dk 4 points 6 days ago

I was thinking so as well. Mostly because of the left pupil not looking like the right pupil, but also the style. The style of shadow below the chalkboard looks like a really odd choice.

[–] DogWater@lemmy.world 3 points 6 days ago (1 children)

How did you spot that? I'm good at spotting real life images but I didn't even blink at this one. I saw one thing when I went back after reading your comment, but it took me a minute to find it

[–] pennomi@lemmy.world 7 points 6 days ago (1 children)

I work a lot with AI images, you just get a sense for it over time. It is getting harder over the years as things improve however.

[–] forrgott@lemm.ee 7 points 6 days ago (1 children)

I doubted your assertion at first; I've experimented with all kinda techniques for stippling and pointillism (sp?), but after the other guys comment I zoomed in and quickly realized the techniques are mix and match. Hatching morphing into scales, for instance.

Good eye.

[–] DogWater@lemmy.world 1 points 6 days ago

For me it's the elbow wrinkles on his one arm, they make no sense.

[–] brbposting@sh.itjust.works 24 points 1 week ago

Site from the watermark:

[–] Uli@sopuli.xyz 12 points 1 week ago

Yeah, somehow it looked AI before I clicked into it for the high res version, something about the way the guy's face was drawn. And when I saw the high res, it was really obvious, because the pupils are askew in a way a true artist would not have chosen. And as you say, the stippling pattern is typical of AI. Weird that our brains seem to be some of the best competitors in the arms race between creating and identifying AI images.

[–] lena@gregtech.eu 1 points 1 week ago (1 children)

Hmm, maybe. I honestly can't tell.

[–] pennomi@lemmy.world 4 points 1 week ago

It’s certainly better than most! For instance the text looks excellent. Look at the scientist’s eyes for a clue - one of them has a suspicious white circle while the other doesn’t, and the asymmetry does not seem to be intentional.