I use PyTorch every day at work. It’s incredible - but I’ve always wondered: how does it actually work under the hood? How does backward() actually compute gradients through a neural network?

So I built my own minimal deep learning framework called Synap. It’s written in C++ for performance, with Python bindings via pybind11. No external ML libraries - just raw tensor operations and automatic differentiation from scratch.

I’ve always been curious about what happens inside game engines when they render a 3D model. You know that feeling when you use Unity or Unreal without understanding what’s actually happening on the GPU? That’s exactly why I decided to build my own 3D renderer from scratch using C++ and OpenGL.

No engines. No magic. Just raw graphics programming.