AIeyes: Walking simulator where the world is seen through a realtime neural net

That's incredible.

What dosage are you taking to see that? I've never seen anything close to it.

lol this doesn't match my experience on acid at all. far too rigid/straight line-y

Yeah, this is something I've consistently noticed + also been very weirded out by, with "What a neural network sees"/"Neural network image synthesis" pictures.

Many of them are eerily similar to the visual phenomena I've experienced on various psychedelics. To the point where you don't really have a choice but to recognize that there's some mathematic/scientific explanation of consciousness and the way psychedelics interact with it that relate to how neural networks function.

I'm far too dumb to put those pieces together but I'd believe whatever someone more intelligent put in front of me.

Wish it were possible to show other people what these kinds of experiences look/feel like, our language and vocabulary obviously don't have terms for most of it.

Seeing impossible colors or shapes, or being/existing in multiple points in space + time simultaneously, as different creatures or people, in different places. It can shake you to your core by challenging what you always assumed were fundamental givens of the universe and "the way things work" (TM).

How much was that? 1200ug?

And neural rendering to get realistic 3D scenes ;)

Woah this is cool dude. Thanks for sharing.

You’re gonna love learning about optical illusions – bugs in our visual processing. We already see the world through approximation.

Obvious example: saccadic masking. Your brain shuts off visual processing during rapid eye movements[1]. You don’t notice the movement, the blur, nor the dropped frames. Brain fills it back in.

Another cool one is how we deal with the blind spot in our eyes. Brain fills it in with a continuation of what’s around the blind spot. The area is big enough to hide a whole car or even a large truck at certain angles/distances.

That’s why you have to turn your head when driving, just your eyes isn’t enough. You’ll get stuff flying at you out of your blind spot.

[1] https://en.wikipedia.org/wiki/Saccadic_masking

The world models paper directly addresses seeing the world as an approximation [1], though in the other direction of compressing the world into a smaller but workable latent space by autoencoding.

[1] https://worldmodels.github.io/

On a tangent, I've experimented a lot with lucid dreaming and dream clarity as well as our recollection of it varies a lot depending on how deep asleep you are. When I'm calm and the dream is stable the visuals are incredibly sharp and detailed. I'm often amazed how lifelike it is.

One issue seems to be that dreams get fuzzy as we start to wake up and our memory of dreams is often seen through a fuzzy lens even if things were clear during the dream itself.

I've especially noticed this last part when being amazed at the detail and describing it to myself as I inspect it. Then I wake up and the memories are hazy and lacking the details I described.

It definitely made it a real strain. In the end I closed the tab out of sheer disinterest.

It reminded me a lot of this Aphex Twin video: https://youtu.be/SqayDnQ2wmw

For now I prefer the human (curated?) one but you could imagine this improving to be really cool.

It's just some pre-recorded thing, probably some producer made it or the game developer did it.

In the comments the author mentions mac/Linux versions are coming.

Several layers, in fact.

there is only one problem, most of these "AI" algorithms don't have an actual understanding of what's going on. These visual pattern matchers can't generalize beyond very narrow meaning of the word.

You can train it to associate certain patterns with certain labels or responses, but it's basically a mechanical puppet that always needs a puppeteer to "train" it. As long as the prevalent view of AI is based on machine learning, using some form of optimization to match patterns, it has no hope of reaching AGI. It's fundamentally backwards looking and bigger models won't make any less "dumb", for a lack of better word.

DL can probably represent lower levels of sensory processing, akin to dimensionality reduction in visual cortex, but it can't generate new abstract concepts from lower level ones, form clusters of such concepts and facilitate navigation in "concept space", in other words go from low level associations to "understanding".

In natural cognition learning & memory are highly intertwined, and acquisition of basic knowledge is not based on some teaching signal or "delta rule" reinforcement, it's more akin to self-organizing hierarchical networks operating via very limited set of computational primitives such as JOIN and LINK, temporal synchronization and innate system of coordinates in abstract concept spaces via something like grid cells https://en.wikipedia.org/wiki/Grid_cell

The constraints nature puts on living organisms, such as limited energy and time define the computational architecture of cognition. As long as these constraints are ignored AI will always be "5 years away".

Probably not. NNs right now are just glorified pattern matching/curve fitting. Getting to a generalized AI is some serious "draw the rest of the owl" work.

Someone correct me if this is not true, but the current AIs using NNs are "static", in that the model is created offline using tonnes of data, and then at runtime it's simply doing pattern matching / prediction. There's no "plasticity" as seen in human-like intelligence. It seems to me that we need a slightly different approach that will change the NNs during runtime.