Sebastian Raschka's from-scratch video course on building reasoning models

Sebastian Raschka has released a comprehensive video course consisting of eight lectures totaling over 11 hours that teaches how to build reasoning models from scratch using Python and PyTorch, covering evaluation, inference-time scaling, reinforcement learning, and distillation techniques. The course serves as a sequel to his previous "Coding LLMs from the Ground Up" and is designed to help developers understand how reasoning models—which are now standard in contemporary LLMs—actually work under the hood.