OneOrigine

Software Engineer by day, Independent Author by night. With one completed manuscript and several expansive universes in development,I thrive at the intersection

[OneOrigine @OneOrigine]

Oddly enough, being a visual writer is strange. If I were writing The Tragedy of Ones—and all the other works in the One universe or the spin-offs of The Weighing of the Souls—I’d realize my pacing is fast and heavily focused on dialogue. That’s solely because I can see the movie of my novels or works playing out. If I write OnlyHuman, it’s because I’ve already watched the whole movie in my head; my vision of the work is just too cinematic.

Because I already have the visual in mind when I transcribe it, I don’t always manage to capture the feel or the true essence of the piece. I’m like a guy who watches a movie and then immediately starts writing a manuscript of what he just saw. Things get missed, the pacing is fast, but everything remains sincere and authentic.

[memo akten @memoakten]

Can't stop watching 😅🙈. (The last one in this video is quite nail-biting). Randomness can be so powerful, if shaped the right way. (I have a lot to say about this, more on it later)

Early demo is live at https://t.co/1YTb8HrfOs.
But very unoptimized.
500 ants: 120fps on M5 Max, < 10fps on M1 and iphone (work to do there but easily fixable)
Dropping timescale (default 2) to 1 can help (250 ants 60fps on M1 and iphone)

Will write up about it more when I get a chance, but in a nutshell: pheromones guide ants towards home and food, and once attached to the cargo (food), they communicate through forces/movement/contact.

That communication isn't "hey I've got a plan. I'm going to push this way. Adam, you pull that way", but much more basic signals: some ('confident') ants 'drive' in the direction they think they should go, ignoring everyone else, other ants simply sense what's happening at their point of contact (collective action of the 'drivers' + physical response from walls) and provide 'support' to amplify that motion. Lots of stochasticity, some simple criteria each ant takes into consideration to guide their decisions, and somehow they find their way home.

I'd initially implemented much more complex behaviours: ants built graph-like memory and waypoint navigation (which they do IRL), some go and inspect obstacles and lay down specific obstacle avoidance cues (which they do IRL - and it was really cute watching the obstacle inspectors do their thing, I might bring it back). But I got rid of all of that in the end. Simpler approach works better (at least easier to tune).

I still do have some intricate behaviours like inspecting food, checking crowdedness around food, going off to recruit if not enough density of ants around the food, finding empty areas to attach to to balance the load etc.

All decisions are still completely local, based only on: pheromones sampled locally, sensing other ants, walls, and food (all within roughly ant's body radius), and movement at point of contact if attached.

I'm no ant expert, and it's unlikely this is exactly how ants actually solve this problem, but I wanted to try some ideas that I believe are at least biologically (and chemically / physically) plausible (I do have a pretty hot pheromone system I'm quite proud of 🦨)

A few papers that were very helpful below. I ended up not following the papers as I wanted to try other things, but they were very informative. Especially the 'puller' v 'lifter' concept (which I called 'driving' and 'supporting', because the names don't convey the way I implemented them).

The paper that poses this specific problem in this configuration: https://t.co/oyMNlQ8upf

And these two papers talk about 'cooperative transport'
https://t.co/wVt5WJXXuH
https://t.co/58eM1j1SeK

[OneOrigine @OneOrigine]

@memoakten 💯🍎🤯

[OneOrigine @OneOrigine]

Michael, the last of the heavenly blessed line in the work, The Originals of One. 🍎(This illustration is close to how I picture this character.)

[OneOrigine @OneOrigine]

@AlexanderKalian 💯

[OneOrigine @OneOrigine]

The video features 3 AI agents (F-agents) that were expected to learn how to plug a leak on their own through raw experience. There is absolutely no pre-training here; it’s an evolutionary, dynamic learning process with zero prior data. They start completely from scratch, utilizing causal temporal perception, internal operators, and reasoning.

Strangely enough, they do the exact opposite: they do everything they can to keep the water jet from getting blocked and charge straight into the leak. This first major test shows that an F-brain learns fast—way faster than expected. 🍎

[OneOrigine @OneOrigine]

@Luacantu 🍎💯💯💯 Glory to God 🔅

[OneOrigine @OneOrigine]

The S.A.V.O.I.R. graph symbolically features the two types of nodes that form the core of knowledge: Type A (a known data point, a piece of knowledge, a global or local context, an environmental element, a matrix) and Type B (an unknown, an exploratory node, a vector of continuous meaning). In my view, a SAVOIR graph is the key to building evolutionary artificial intelligence—hypothesis explorers, discoverers of the unknown, and true researchers that are aware of both the known and the unknown. 🍎

[OneOrigine @OneOrigine]

🎩

[OneOrigine @OneOrigine]

I’m not just going to post my wins. SAVOIR Genesis 3 was a failure at learning how to walk. It kept backing away whenever it faced danger, and I don't know why. It kept tripping over its own feet, crossing its legs until they locked up, and then falling over.

[OneOrigine @OneOrigine]

SAVOIR c3 🍎❣️

[OneOrigine @OneOrigine]

@AlexanderKalian Confirming the day a real intelligence is created, we'll need to give it basic, foundational knowledge instead of the entire internet, and see if it can construct complex theories just through logical assembly.

[OneOrigine @OneOrigine]

Today, I'm finishing up the first version of the F-brain, which I’m working on in parallel. Unlike SAVOIR, which is an overly ambitious project, a Feynman Brain is strangely efficient at creating agents that act through internal experience, learning with minimal data for highly compact learning. What's more, SAVOIR O1 or Omega supports Feynman neurons, so there is a fusion between the SAVOIR core and a Feynman brain. All of this remains experimental for now, and I'm continuing on my own, but I'm making progress 🍎🍏

[OneOrigine @OneOrigine]

To wrap up this mini-thread: a good character isn't just 'bad' or 'good,' because cruelty and kindness—or goodness—are the results of choices and actions, not a category or a type of person. Moral ambiguity can definitely be a mistake, because morality is very real. Good and evil exist in our reality, and making them relative only makes a fictional world less realistic. A good character is, above all else, a human being: choices made, actions taken, and consequences faced!! Thanks to everyone who read this—it was OneOrigine.

[OneOrigine @OneOrigine]

To be honest, I get why male writers or authors write women and girls poorly. It’s just a matter of perspective—from a man's point of view, we have no idea what girls talk about when they're alone, precisely because we aren't there to see it, so we just don't know. Plus, literature written by women doesn't always help. I’m not generalizing, but there's a lot of self-stereotyping in classic works, like in romance novels or other genres—even if it's still richer than a man trying to imitate a woman's perspective. But hey, more mature creators still manage to master that perspective, like Hayao Miyazaki in anime. It’s not about writing a flawless character; it’s just a character created from a man’s point of view, imagining what a woman’s point of view would be. 🔅

[OneOrigine @OneOrigine]

But I also like stereotypes; they’re part of reality. When we don't know something, the brain tends to fill in the blanks with what we think we know or what we see. For example, I might introduce a female character by her physical appearance to mislead the reader, and then develop her soul later on. That’s powerful because it creates a realistic shifting perspective. First you see, then you judge—the visual impression comes first, followed by the personality. This actually makes the reader attach themselves to the character because they'll feel like they misjudged them. They remain human above all else. 🔅

[OneOrigine @OneOrigine]

🍎