Show HN: Teaching a 4M-param model to read like a child, with RL and no labels
https://rjb7731.github.io/blog/2026/learning-from-scratch/
I have been really interested in reinforcement learning and had a go at trying to teach a model through simulation to read and speak through experience.It’s two small networks (~4M parameters total) trained on a MacBook. It passed generated versions of England’s Year 1 Phonics Screening Check (36.6/40, pass mark 32), and the bit I like most is that it taught itself irregular words like “glove”...