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.

SAVOIR c3 🍎❣️

@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.

Chatbots are a statistical echo of human communication, with a few tools bolted on. But the echo is limited. It captures mostly the surface, with only faint hints of the inner world below. This is one holistic reason why AI is still less creative than a human child.

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 🍎🍏

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.

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. 🔅

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. 🔅

🍎

SAVOIR GENESIS LAB v5

I’m planning to open-source the raw code for Project SAVOIR Omega. The worst-case scenario for me would be if the project just stays exactly as I release it. What I really want is for people to build on it and help it evolve, while I continue training it on my end. As of today, the model has successfully generalized over 200 protostructures from silent human videos into 10 core areas of knowledge. Right now, the causality still needs to be calibrated, but it has a lot of potential to grow. I’m calling on the AI developer community to help evolve SAVOIR once it's out there. #AI #AI_Model #DevCommunity #OpenSource #MachineLearning

Will soon publish another X article named 'F-Brain — Ce que le monde doit Savoir (F-Brain — What the world needs to know.)' 🍎

We at AI Megacorp have made an AI model that vastly outperforms and might be AGI. It's a cybersecurity genius that can autonomously solve all mathematics and cure cancer. But we won't release it for scrutiny, for your own good. Because we at AI Megacorp care about humanity and love you... Or something like that. AI Megacorp has always loved and respected the little guy. AI Megacorp has never unethically harvested protected data, used predatory business tactics, or had whistleblowers die in mysterious circumstances. You want proof of our AGI breakthrough? Look, here's a tweet from our CEO saying: "trust me bro". We would never lie to you or exaggerate our tech for profit. AI Megacorp promises that this has nothing to do with pumping valuations ahead of our IPO later this year. We are the good guys. Now give us money - we're losing $20B a year on data centres but still need to give the VCs and founders higher returns.

@AlexanderKalian 🤣🤣🤣🤣🤣🤣🤣🤣💯

@AlexanderKalian 🤣🤣🤣🤣

Breaking news - I have made an AI model better than all the others! It beats both OpenAI and Anthropic. I won't be releasing it - it's too dangerous for humanity. But trust me, I really did do it. Now please give me money.

@Luacantu 💯

Everyone wants AI that can do everything. I’d rather have AI that does one thing extremely well and can prove why it made a decision. Reliability beats magic.

To have a great time !