Tags: #machine-learning

AI is great and all, but it can't keep up with Zig's breakneck development pace. So I wondered: what would it actually take to build my own? Turns out, with a hybrid deterministic/stochastic approach, an RTX 3090, and 4.5 hours of training, I created a specialized LLM that runs on a regular laptop.

What began as a lightweight programming experiment quickly transformed into a deeply engaging technical exploration into the realms of neuroevolution, game physics, and browser-based simulation. My original goal was modest: replicate the "Chrome Dino" game using a performant and modern web stack. However, the project evolved far beyond expectations. The twist? I wanted the dinosaur to teach itself to jump.