Loading video...
Video Failed to Load
We trained a graph-native AI, then let it reason for days, forming a dynamic relational world model on its own - no pre-programming. Emergent hubs, small-world properties, modularity, & scale-free structures arose naturally. The model then exploited compositional reasoning & uncovered uncoded properties from deep synthesis: Materials with memory,... show more
359,070 views • 1 year ago •via X (Twitter)
12 Comments

Hello sir, is there a paper/code available?

Yes - here it is:

📺 Watch this #video to learn how #OpenSource vs. proprietary #AI models compare one to another. We explore how proprietary models dominate leaderboards like Chatbot Arena, but open-source models are quickly catching up. Plus, we discuss how businesses can start with proprietary models and transition to open-source alternatives over time 👇 Fit AI into your development strategy!

very interesting work, exciting to see graph reasoning as a paradigm

Thanks @LPitsoulis !

For the normies imagine you build a machine to organize your sock drawer, but instead of just sorting socks, it spends a few days thinking and suddenly figures out physics, biology, and self-repairing materials all on its own. You didn’t program it to do that. It just happened.

Interesting project as always Markus, really loved the graphics around it. It kind of reminds evolutional process

Thank you @aihsannergiz !

This is next level proof of concept Markus, you kinda shifted my gears with this one 🙏

Thanks 😀 we were blown away by this result also!

what did you use grok for? the graphics?

Yes, the 3D graphics - to visualize how the graphs formed over the thinking period evolve.
