approximate inference in graphical models — forward and rejection sampling, likelihood weighting, gibbs sampling and mcmc, and loopy belief propagation, with the trade-offs that decide which to reach for.
Sampling
2026-08-31
a large language model is a decoder-only transformer trained on one absurdly simple objective — predict the next token — scaled until the emergent behaviour stops looking simple. 𐃏 this page is the map from that objective to a deployed assistant: the loss, the scaling laws that size the model, the pretrain-align pipeline, and the inference tricks. the hands-on build is nanogpt.