Terrible, Beautiful Sparks in Space

I still hate most of the foods that I wouldn't eat as a kid. Almost all the variation in my diet came from trying foods I wasn't exposed to as a kid.

In fact, there are lots of foods I would force myself to eat as a kid that I don't bother with anymore because I don't like them

More photos, as always, on the site:

The Animal Photo Reference Repository is an independent, permanently open-access project and funded entirely by donations. Artists creating derivative or transformative works (without AI) have blanket permission to use all photos in the repository as references.

Like, obviously we start with Alanna and SOTL, which is all about pure access. The question here is very simple: should girls get access to the education system? And the answer is equally simple: yes, obviously. This is a book about proving that these girls who have been denied access to the system can, in fact, succeed if given a chance. That girls are just as capable of doing well as boys are, and that they deserve the same opportunities as boys do. We are shown that with enough determination and support from the people close to her, Alanna can push through and beat these people at their own game.

Then we have circle of magic, where we are instead asking ourselves: what about kids who aren’t able to succeed inside that system? Not every kid is Alanna. Some kids are never going to be able to brute force their way through the system as she did. Not because they’re not as smart as her or as determined, but because they’re different. The system is never going to work for them, so the only way forward is to remove them from the system. And in doing that, these kids find success no one in the system ever dreamed possible for them.

Then we get to Kel and protector of the small, and we finally get to ask what in my mind are the real questions. Rather that a pure question of whether she has access to the system, Kel is also questioning the value of the system itself. How it treats the people inside it and those supporting it, like Lalasa. She is looking at the system and instead of accepting it at face value, she asks why it works the way it does, and if it hurts so many people and privileges bad behavior, is this the right way? And if it’s not, what does a better way look like, and what does it take to change it?

then I looked in the notes and y’know.

some people seems confused.

Why a shopping cart with stained glass? 

or This would be cool to shop with

or something about religion and NO

NO

THIS. Is about HOMES.

That style stained glass? Those diamonds? They speak to me, and they say “Townhouse”. and FANCY townhouse, at that. They say “City home, old home, a home that is RICH, a shelter from the storm and a safe place for a family”.

But on! a! shopping cart!

That evokes - to me - Homelessness.

The person on the street who had no other choice but to steal the best cart they could from a store’s corral just to have a way to transport the meager belongings that are all they fucking have in this world. And it’s NOT a home or a safe place or a shelter but it’s all you fucking have!

And this piece goes and puts them fucking together! AND NAMES IT.

It's also how we know that most dinosaurs had round pupils. It's pretty common for people to depict dinosaurs with slit pupils, probably because of Jurassic Park, mostly because it looks really cool, but nope, they were round. There are very few, if any, birds with slit pupils, which is further evidence for round pupils. And most extant animals with slit pupils are on the small side. Many people think of cats having slit pupils, and they do, but it's the little ones. Lions and tigers have round pupils, because slit pupils are most useful closest to the ground and they actually sacrifice some of their visually acuity for the sake of being better at judging distances in low-light conditions, and most animals with them are ambush predators that jump out at their prey. You ever seen a video where someone throws or bounces a ball towards a cat and it bops them on the head and they seem surprised? That's why; they struggle to track where the ball is going, especially horizontally. So for anything over a certain size, slit pupils are a detriment, especially if they chase down prey.

I am currently building a multi-decade chain of papers on computer vision and image generation to have this discussion, and I would like to do so in a moderately calm manner.

Unfortunately if I want to cite a journal article from 1983 in a tumblr post, the copyright holders of this article about image restoration and pixel randomization want $248 per section of excerpted text (<500 words).

This is a 2024 paper by one of the Adobe developers who worked on those compositing tools going over how the tools work. For the record, this model was trained on licensed and public domain images only and the tools are run on device, so the copyright and environmental complaints that people frequently make about AI don't apply to these specific tools.

That paper uses research from this 2015 paper on AI detection of composited images. That paper uses the ImageNet dataset.

ImageNet's dataset is a combination of images sourced from image searches starting in 2009 and description tags generated by Amazon Mechanical Turk workers. The images are not owned by ImageNet, but were scraped from various internet sources in the late 2000s.

That project uses algorithms and processes described in this 2007 paper on the utility of a general image database and image segmentation.

This 2000 paper on image segmentation developed some of the models used in the later paper, based on a collection of 1000 Corel stock images.

That segmentation was based on statistical models in this paper from 1994, which used a small training dataset collected by the researchers.

That 1994 paper made use of the model in this foundational paper from 1984 on predictive pixel selection for algorithm-based image restoration.

That paper helped to refine the boundary-finding methods used in this 1986 paper, which was an improvement on methods from the 1980 Hildreth paper.

Both Hildreth and Canny cite this 1971 memo from the MIT Artificial Intelligence lab, which describes the process of using a computer to find lines in an image.

Personally I like this note from a revised version of that 1971 memo that shows that we are still currently dealing with some of the same problems in computer vision that people were 50 years ago.

"This program has no idea what a reasonable line-drawing should look like when it represents an image of polyhedra. Instead it is very general and will find arbitrary line-drawings. Observing the particular way in which things sometimes go wrong, one quickly comes to the conclusion that higher-level understanding of the scene being analysed could greatly improve the line and vertex creating phase of this program. As thing stand now this understanding comes only after the line-finder has done its work."

Okay so what's my point?

My point is that there is a long chain of models, statistics, and research that, stretching back to the beginning of computer vision, has been centered around figuring out the likelihood that one pixel next to another pixel is black instead of white. The computers have never been very smart, they have never understood context, and the improvements we have made from the line finder in 1971 to "harmonize" in photoshop in 2026 is a very traceable chain of refining how the statistics are calculated.

They hallucinate extra elements, they don't know what shadows are.

Computers are still stupid, they just do math a lot faster than they did in the seventies.

Harmonize is apparently a new "AI" tool available in photoshop that is capable of matching lighting, texture, and other qualities in photos that are composited together. One of the things that the flesh pit guy is currently being dragged for (aside from really seeming to be a pretty tremendous asshole) is using this particular type of AI tool as a time saver on his ongoing art project.

I want to have a conversation about this, by which I mean I want to make some arguments about this.

I'm writing this specifically about the harmonize compositing tool in photoshop (and similar tools like upscaling). This is not about using grok or generating whole images or whole elements of images, this is not about whether or not the flesh pit guy is an asshole. I will grant that he is an asshole and I personally find whole images generated with AI tools like grok to just kind of look bad and be really boring.

Work with me on this, and let's accept the premise that adobe's Firefly is an ethically trained model (up to 5% of the images used to train firefly may be midjourney images that were licensed to adobe as stock images after being generated by midjourney, but adobe pays creators standard licensing fees to train data and does not train on client data), and that the tools are run on-device and do not consume any more resources than creating a 20-layer document in photoshop would.

(Also I acknowledge that training a model uses a lot of power and resources but creating a video game or an animated movie uses power at a much higher level than playing the game or watching the movie on your own machine; i've got to limit the scope somewhere so I can actually ask the question I've got)

Again, we are granting the following before you respond to the poll:

If the model was trained on ethical data and

If the tool runs locally and does not use more power than your computer uses and

The art the tool is used on is a personal, individual project and does not lead to poor treatment of workers

I cannot tell you how much Mad Max (2015) felt like every other lame late 80s/early 90s adventure film---except. With the single and staggering exception of a uniquely unparalleled vision. It speaks in visual poetry, from the sere line of the desert against the sky, the rust-colored sand whirling beneath wheels, the blue velvet of the night, the intricate and brutal steel hulks of the rigs. It took me half the film to realize there wasn't even that much dialogue, because everything I was seeing spoke.

I've talked before about how sometimes it can be useful to look at art through the question of priorities. An artist can't have a fully-developed romance, a complex plot, an intricate character study, and fully fleshed-out world in a single work---so where are they investing the most energy? (You could expand this list indefinitely, to be fair--- writers and poets can put the lyricism of their language first; artists could put the material nature of their oils or clay on display; podcasts or movies can focus on soundscapes, etc.) Still, there's no question to my mind how George Miller answers that question. It's in every frame.

also we can officially say that that megan self-identifies as "a free agent on the ladies side." & after she said she was a ''free agent'' there are STILL articles being "people are speculating but she hasnt confirmed it." she literally. said. she was interested in women and wanted a girlfriend. what more confirmation is needed.