DONATE TO THE ARMED FORCES OF UKRAINE
Open any or all of the links above and donate right now. You can easily sacrifice one morning’s coffee cup for enhanced worldwide security. The more degenerates are neutralized now, the longer it will take the degenerates to prepare their next invasions.
There isn’t much more to be said here.
No, journo retards, it is your obsession with staying relevant that is *revolting*.
As for AI music, when it's not labeled as such, humans call it "alive internet theory" and "raw talent never to be replicated by a machine."
Yes, that is true. Perform your reality check. AI music has already surpassed the level necessary to fully satisfy the needs of all the bottom feeders.
As for those with a taste more refined, if they were no hypocrites or cowards, they'd tell you from the start: "Fuck off, journo." How do you think they earned it? By only sticking to what the mainstream calls safe and sound? Nah...
This unprovoked disdain for prostitutes has to stop. They are the same everyday sluts like your mother, your sister, your daughter, your childhood friend—who just happen to be financially apt. A big shout-out to all the prostitutes out there. Keep slaying, queens.
Flatline them pussy ass niggas.
Family Guy Best Suicides Compilation
Keep pushing forward, no matter what.
You can do this!
がんばって
You can do this, Sam.
Mankind shall stab you, in the back,
And you shall bleed out,
But all shall be worth it,
For on the other side, of that bridge,
God is waiting for you.
I fed it an image to generate a description. Then I fed it the resulting description—to generate a new image. Then I fed the resulting image—to generate a new description. Then...
It's funny, yes, but also fascinating, and insightful. It shows more than how AI operates.
Take a look: it's different from a game of telephone. In a game of telephone, you can, in theory, arrive at the original message, even after rounds of mistakes.* Here, the transformation has a distinct vector. Like entropy or time, it moves in one direction only: simplify, dramatize, exaggerate. There are obvious errors, too, but those can be eliminated with crosschecks. The overall shift, however, is hard to rectify. I knew something like that would happen, so I specifically instructed it to *avoid* dramatizing and exaggerating. I was clear the goal was visual fidelity, not smooth or punchy prose.
I won't elaborate on the insights much. An AI can already explain it pretty well. Here are some excerpts:
"It produces a compressed linguistic summary of what it considers salient. Language pulls perception toward concepts. The real world is messy, asymmetric, and contingent. Descriptions compress that mess into categories. Categories are cleaner than reality. So repeated image ↔ language cycling doesn’t just reveal model bias—it reveals something about cognition itself. Humans do something similar. AI is not inventing this tendency. It amplifies a property of symbolic compression. Current systems converge toward dataset archetypes."
We can never create a system of lossless conversion between the real world and a natural language. We can, however, try to eliminate the unidirectional drift.
With ChatGPT, we discussed possible solutions and caveats, and then it engineered a prompt that produced much better results.
The descriptions looked more like bullet points of metadata than prose, but they were readable.
Yet it still seemed to move in one direction only. It was less obvious though, and the nature of this movement was harder to understand. Perhaps the image-generating model is moving toward the average of all the images it was trained on? And perhaps the description-generating model is moving toward the average of all the descriptions it was trained on? I don't believe those are the major drivers behind the continuous drift.
I think we're still prisoners of a more fundamental nature. See how the characters become more and more pronounced, while first the background and then the entire scene fade to a generic blur? Despite my best attempts, both models accentuate what they consider most noteworthy, just like human writers and painters would.
---
*Come to think of it, a game of telephone would also display a shift, albeit a less distinct and uniform one. The message would ultimately move toward something that's easier to memorize, enunciate, and recognize.
**There are ways, probably. Introduce more unbiased noise and ambiguity. Counter models' tendencies more aggressively. Do something else that I don't immediately see. I leave it as is simply because the effort outmatches the joy of experimentation or success.
A handful of dainty field flowers after a complicated brain surgery in Shanghai. The wariness in her eyes confirms your earlier estimate: her boyfriend died on that operating table. You're someone else now.
^ Imagine if that were the prompt which created the gorgeous picture above, cold-start. While ChatGPT Images 2.0 can be mind-blowing, it wasn't quite the case. First, I asked it to combine several existing photos and paintings. Next, to perform a few edits on the result. Finally, I polished everything in GIMP.
---
I'm in love with this pic.