François Fleuret explains LLMs: pretraining mimics humans, post-training steers toward valid answers

francoisfleuret · x · 2026-09-26

In a thread, researcher François Fleuret breaks down how LLMs work: "predicting the next token" actually means sampling from a very complex distribution of sentences. Pretraining has the model broadly imitate humans — itself extraordinary, engraving rich knowledge of nearly everything into the model.

Related event: François Fleuret's Thread: LLMs Are More Than 'Next-Token Predictors'(6 posts)→

Original post →

More from Research

Research channel →