Post

tiny neural net navigating a field of black holes to goals with some relativistic effects from the ball's pov visualized. the ball/nn also experienced time dilation so it runs slower when going faster/in a deeper gravity well.

Does the ball have some kind of raycasted vision or does it get more abstract info?

it knows the nearest n holes properties directly, no vision

Does its perceived geometry get length contracted when it goes faster? This is really neat. Did you RL the ball?