The goal is to enable it to model the world at different levels of abstraction based on the question it wants to answer. You can model car as an object that travels fast and carries people, or you can model it down to the level of engine parts. The system should be able to pick the level of abstraction and put the right model together based on its goals.

so then you can search over configurations of engine parts to figure out how to rebuild the engine? i may be misunderstanding what you're doing

Yeah, you could. Or you could search for shapes of different parts that would maximize the engine efficiency. The goal is to simultaneously build a representation space and a simulator so that anything that could be represented could be simulated.

Have you written about this anywhere?

I’m also very interested in this.

I’m at the stage where I’m exploring how to represent such a model/simulator.

The world isn’t brittle, so representing it as a code / graph probably won’t work.

Right. You have to represent it as something that can write code/graphs. I say a little bit here https://www.jonathanmugan.com/WritingAndPress/presentations/...