I’m surprised you can see the screen. CRTs had a tendency, because of the frame rates of the monitors and shutter rates of cameras, to just look blue.
that is because, telling from the other comments, this is most likely ai generated…
“This looks shopped” to “This looks slopped” is just such an easy single-character change. And not making the effort to get six fingers on his hand is just a missed opportunity. Needs more reimagining.
It’s consistently interesting to me the way that AI image generators seem to grasp the basic concept of regular repeating patterns, but inevitably get bored and start going all wibbly wobbly. The keyboard and the striped shirt are great examples; it can tell that there should be regular, parallel groups of lines, but it quickly devolves into a dementia patient trying to draw a chess board.
Because the software doesn’t understand the concept of anything. It’s been fed a bunch images of keyboards and programmed to output an average of the images. It has no concept of a pattern or a keyboard in which to conform to something recognizable.
Kinda depends on the generator. I saw one the other day that was of a guy in a bedroom on an oil rig. It had an HP Chromebook on the desk. As in I was able to reverse image search it to find the brand of computer it was. The entire image was AI generated. There were a few details off, a few weird things about the image that didn’t make sense on closer inspection but by in large, it looked like a regular old selfie.
They’ve absolutely gotten better. And I’ll caveat what I’m about to say with I’m neither a user nor a fan of AI, but people are doing real shit with it, and the only hope we have is that it will usher forward technological advancement. Obviously, I’m on Lemmy, and so what I think is that it’ll fucking doom society, but I have very left leaning friends who are also very deep in tech, and they are fully on board the AI train.
And so I’m just some dummy, I don’t know my ass from a hole in the ground, and so at this point, and for my whole life, I guess, past, present and future, in just along for the ride, and should shit go awry, I’ll rely on the same thing man has relied on for as long as man has existed.
Depends on the model. Many of the cheap and light image generation models are trained to be good at the most obvious stuff so they can run on weaker hardware. They can generate perfectly realistic and consistent faces (and certain other body parts that are… in high demand) because that’s what the human eye instinctively focuses on first, but will struggle to generate a wooden chair that isn’t a weird M.C. Escher mess. You can run those models on a consumer GPU to generate multiple images per minute.
Not all models are trained with those limitations. Some can get scary accurate and consistent.
Right? It’s like they get the idea that a stand in for the concept of a “pattern” should go here, but no concept of what a pattern is.
I think the issue is the same on the text generation side, but harder to notice because it’s not an image.
Perfectly functional keyboard and nicely organized cables, don’t see anything wrong.
ah yes, we all have the all consuming spaghetti wires above our monitors. cant have a computer without it
“I can tell by some of the fingers”
That guy looks like he wants to talk to me about my flair.
Is that Peter Serafinowicz? AKA the original, pre-Witwer voice of Darth Maul? AKA the live action The Tick? AKA the inventor of the Butterfield Diet Plan? It’s hard to recognize him sometimes.
AKA the Nova Corp Captain in Guardians of the Galaxy, AKA Big Daddy in Sing?
Probably not.
The cycle begins anew
