In our last reflection, we discovered that beneath all the complexity - the algorithms, the systems, the shimmering layers of code - everything in a game world ultimately reduces to a simple yes or no . But what continues to fascinate us is this: while our algorithms deal in absolutes, our players  do something extraordinary. They take those binary foundations and build meaning upon them. They see possibility where the code sees limits; they improvise, imagine, and interpret.

When we began building our mapping algorithm, we thought the challenge would be teaching a machine where it could walk. After all, our digital worlds are not shaped by gravity or erosion, but by vertices, textures, and light. Surely the hard part would be giving structure to the void. But once the world revealed its form - every floor, slope, and surface understood - we discovered something deeper. The real difficulty wasn’t knowing where to walk, but deciding which path to t

How algorithms learn to walk... Our universe is built from atoms and molecules, governed by the quiet laws of physics. A mountain stands because gravity demands it. A valley forms because water insists on finding its way. But in a game world, none of that exists  - not until we create it. A mountain is just geometry; a field is only an arrangement of vertices and pixels. There is no gravity, no friction, no path - unless we teach the world to understand itself. So, the questi

BTW, the cake was real! When we won our Innovate UK grant for Virtual Guide Dogs, we wanted to celebrate in a way that was more than icing on a cake; the RedNought way, by combining human and AI in a way that makes things better. So we asked AI to dream with us. It gave us ideas - wild ones, colourful ones, ones that made us smile. Also a lot with creative spelling mistakes, but you know what AI is like... But ideas are only half the journey. The other half is rolling up your