The thing about words is that meanings can twist just like a snake, and if you want to find snakes look for them behind words that
have changed their meaning.
Puking on the carpet, dropping dead things at your feet, licking at you, drawing your blood with sharp claws. Imagine a long slimy toad-lizard with those sharp claws, behaving like that.
AIs are a tool, at least currently, and depend on the way you use them like any other tool. Future AGI would be a whole other dangerous can of paperclips, but we dont have that yet.
AI at this stage is just a tool. This might change one day, but today is not that day. Blame the user, not the tool.
AI and ML was being used to assist in scientific research long before ChatGPT or StableDiffusion hit the mainstream news cycle. AIs can be used to predict all sorts of outcomes, including ones relevant to climate, weather, even medical treatment. The University I work for even have a funded PhD program looking at using AI algorithms to detect cancer better, I found out because one of my friends is applying for it.
The research I am doing with AI is not quite as important as that, but it could shape the future of both cyber security and education, as I am looking at using for teaching cyber security students about ethical hacking and security. Do people also use LLMs to hack businesses or government organisations and cause mayhem? Quite probably, and they definitely will in the future. That doesn't mean that the tool itself is bad, just that some people will inevitably abuse it.
Not all of this stuff is run by private businesses either. A lot of work is done by open source devs working on improving publicly available AI and ML models in their spare time. Likewise some of this stuff is publicly funded through universities like mine. There are people way better than me out there using AIs for all sorts of good things including stopping hackers, curing patients, teaching the next generation, or monitoring climate change. Some of them have been doing it for years.
You know, thinking about it, I doubt this is a coincidence.
The finger-counting is familiar to me as a technique for lucid dreaming. If you look at your hands in a dream, your brain will kinda fuck it up, so if you train yourself to pay attention to that you realize you are dreaming and become lucid.
My guess is that the origin of fae is something like sleep paralysis deamons or hallucinations, and people realized they could detect those from the same flaws of our own imagination.
Now for AI, it isn't really drawing. What we are using in image-AI is still much more like projecting up a mental image, dreaming. We can't get it right all at once either, even our human brain is not good enough at it, it is reasonable image-AI makes the same kind of mistakes.
The next step would logically be to emulate the drawing process. You need to imagine up an image, then observe it at large, check for inconsistencies using reasoning and visual intuition.
Hone in on any problems, stuff that doesn't look right or doesn't make sense. Lines not straight.
Then start reimagining those sections, applying learned techniques and strategies, painter stuff (I am not an artist).
Loosely I imagine the ai operating a digital drawing program with a lot of extra unusual tools like paste imagination or telepathic select, or morph from mind.
The main thing differentiating dreaming from painting is that for painting you can "write stuff down" and don't have to keep it all in your head all the time. This allows you to iterate and focus in without loosing all the detail everywhere else.
The other day I thought I was in a dream because my torso was missing when I saw my reflection in a window. Even when I moved. It legit made me jump. Turns out the middle section of the window was open so it was reflecting light from someplace else.
These tricks have never worked for me, I wonder if that has some implication. I can see working clocks in dreams, both the digital and analog kinds. Reflections look normal. Hell, I've looked directly at myself (or a doppelganger?) in dreams before.
Is this really useful? Like, is this something people ever need to do? I don't do lucid dreams very often, but the rare times a dream has lead me to the thought of "hold on, am I dreaming?" were basically immediately answered by just, uh, vibes, I guess? Like, it's always just been instantly obvious that I'm dreaming the moment I'd start questioning it, no tests necessary. At worst I might have to try to remember what I did the day before and what I was supposed to be doing that day and see if that is at all compatible with the scenario I'm dreaming about, which it usually isn't.
Wherever I see weird things in a dream and I'm lucid enough to notice, I just panic thinking that something's wrong with my brain, followed by doing anything I can to get to a hospital.
I had a similar thought about AI; that it's more like imagining something than actually drawing it. When you ask a program like stable diffusion to draw something, you're basically asking it to imagine something and then you reach inside its head to pull the image out. I think that if AI was forced to draw the "ol' fashioned way" then it'd be both better and worse. The results would be more "correct" but the actual quality would probably be worse. It'd also take it longer to get to the same level as a professional artist.
There are a ton of shortcuts you can take in the digital world to save time; you're basically a god limited only by your computer's specs. You can do extremely complex things near-instantly. This saves significantly on training time when it comes to AI. An AI forced to learn how to do art the ol' fashioned way would take significantly longer because it can't take the same shortcuts.
Yeah. You want to preserve the AI's abilities. Hence adding the "paste imagination" feature for example. If you simply use that and finish "editing" that is current AI. Then you can quickly redo only sections from imagination until they look good, maybe with a specific prompt or other form of understanding about what needs to be done and changed there.
We can invert our visual center, so basically we see an image, think about it, then can summon a mental version of that painting back as an image by converting the abstraction of it and change things about the abstraction until the mental image seems good. This abstraction can handle ideas like recognizing, moving, scaling, recoloring objects. It can do all we can imagine because it is literally how we interpret the world. Then we spend hours trying to paint that mental image we created using limited tools. If we could just project something the same way we see, that would probably match image-AI in the initial output but after tens, hundreds of passes you could likely within minutes create something completely impossible by any other means.
It's not about the medium being used, it's that AI doesn't know what things are. You and I have a living library of how a 3D object works in space. When you train your artistic abilities, all you're really doing is perfecting that internal library and learning the techniques to bring it out of your own head.
When you draw an apple, you bring forth the concept of an apple in your mind and then put that down on the page. When an AI draws an apple, it creates a statistically probable image of an apple based on its training data. It doesn't know what an apple is, it just makes something that was good enough to pass the testing machine.
AIs make products like a dream, because just like in your dreams, there's no reality to anchor it to. You hallucinate fairly similarly to AIs, even while waking, but your brain then adjusts its guesses using sensory inputs. Like why you can feel the pain of a stubbed toe instantly, if you see it, even though it actual takes the chemical signal some time to get to your brain. Or how your brain will synchronize the sound coming out of someone's mouth with the image, even though that's not what is actually happening. And an AI will never be able to do that, because all inputs are identical to it.
Your brain doesn’t have a single module that knows what an apple is. Instead, different parts work together to form the concept. The occipital lobe in particular, processes how an apple looks, but it doesn't "know" what an apple is—it just handles visual characteristics. When these various modules combine, they produce your idea of an apple, which is then interpreted by another part of the brain.
When you decide to draw an apple, your brain sends signals to the cerebellum to move your hands. The cerebellum doesn’t know what an apple is either. It simply follows instructions to draw shapes based on input from other brain regions that handle motor skills and artistic representation. Even those parts don’t fully understand what an apple is—they just act on synaptic patterns related to it.
AI, by comparison, is missing many of these modules. It doesn’t know the taste or scent of an apple because it lacks sensory input for taste or scent. AI lacks a Cerebral Cortex, Reticular Activating System, Posterior Parietal Cortex, Anterior Cingulate Cortex, and the necessary supporting structures to experience consciousness, so it doesn’t “know” or “sense” anything in the way a human brain does. Instead, AI works through patterns and data, never experiencing the world as we do.
This is why AI often creates dream-like images. It can see and replicate patterns similar to the synaptic patterns created by the occipital lobes in the brain, but without the grounding of consciousness or the other sensory inputs and corrections that come from real-world experience, its creations lack the coherence and depth of human perception. AI doesn't have the lived understanding or context, leading to images that can feel abstract or surreal, much like dreams.
Yeah, but there's a manufactured object that should have near perfect symmetry and doesn't. It kind of looks symmetrical, but that's not how symmetry works.