ConceptAI & ML
Reinforcement learning applied to reasoning
An iterative process where a language model generates better chains of thought and is fine-tuned to prefer them, converging on a narrower space of good reasoning steps.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Lecturers
1Connections
4The lectures that define it or assume it, and the concepts next to it.