The system has two especially novel features. First, the neural net is trained only on algorithmically generated data — a whopping 100 million geometric proofs — using no human examples.

OctopusEffects, #Blender This is a basic tutorial on Geometry Nodes in Blender 3.1. Learning Geometry Nodes through doing a ...

Instead of using natural language, Trinh and his collaborators developed a language for writing geometry proofs that has a rigid syntax similar to that of a computer programming language.

Google claims math breakthrough with proof-solving AI models AlphaProof and AlphaGeometry 2 solve problems, with caveats on time and human assistance.