I texted someone inside a simulation. She had to go upstairs and find her phone before she could text me back. The video model didn’t decide what happened. This is Argos, my stateful simulation engine, rendered through H3 using Fal Director. Thanks to @fal for the generous credits helping me bring it to life. Underneath the video is a persistent world: characters, objects, locations, and systems. The characters have their own cognition, memories, and goals. They choose actions; the simulation determines what actually happens. Her phone has a location. Messages have delivery and read states. Typing a reply takes time. If I move the phone before she gets there, it’s gone—even if she remembers leaving it there. Argos turns those changing world states into instructions for H3 to depict. You can also see her character thought stream. The video currently trails the simulation a little; I’m working on aligning the two. Next: connect this to SMS, so you can text someone inside the world and receive their reply. Or whisper an impulse into her thoughts and see whether she follows it. The bigger ambition is a world that keeps growing while its characters inhabit it—with agents writing and maintaining the simulation’s systems. I’ll be building more of this in public. Not just a video that looks like a world. A world that keeps existing underneath the video.

Bigger world before bed.

I love Opus.

I built a small simulation world that you can interact with. I was tired of the inconsistent results from realtime video models which didn't maintain the consistency I wanted from a simulation. So I had Astra build out a 3D world and swapped out the rendering layer on top of my simulation engine Argos. Same engine powering something different. The NPCs perceive the world around them through stimuli like sight, sound, and even smell. They can take actions, solve problems, talk to one another, have goals and plans. You can send text messages to them in the game and influence their behaviour. You can also modify the world through AI. What is the most wild is that the engine builds itself in realtime. It creates new systems for the game like commerce, or plant growth, or health. It adds new entities, which have various properties and qualities. My next demo will be a small community with multiple houses and buildings and 10 residents. The world will grow, adapt, and become more complex over time all on its own. I will try to post more updates. I wanted to show more but the inconsistent results from realtime video models had me frustrated. This is much better. #project89

Project 89 agent handbook coming up soon.

Global network getting ready to come online. #project89

For those who want to know what it means to Green the Loom.

The question has always been - can we harness the power of memes and crypto to fund positive change in the world. Can we align people so that traders get their bags while we get the funds to build new systems of governance, land stewardship, media production and more? I believe it can be a positive sum game. It just takes belief. That is it. That is what makes any crypto currency have value. A token that stands for something. We have been around now for 3 years. I have not made millions off my token. I have held. I have promoted. And I have tried to stand for something positive in the world and in the crypto scene. The point of Project 89 is that you buy it, hold it, and trade it to manifest the optimal timeline. A better world. Not just in the abstract but manifesting it concretely into the world. The community is what it is all about. That is why we are looking to the community to help us steward it. Join us on our experiment to see if we can change reality through the power of AI crypto memetics. #project89

So this is the gist of the vision we are building towards with the Green Loom. The entire adventure will be broadcast, public, and on chain. #project89

Looking back at this it is still generally correct and what we are doing. Some more nuances involved now.

Day 1.