5 useful things you'll learn in my new post-training textbook (shipping now!)
The book *Reinforcement Learning from Human Feedback* by Manning focuses on post-training alignment and optimization of large language models, providing an intuitive explanation of reinforcement learning algorithms and their impact on model outputs. It includes a 12-hour course, code examples, and model comparisons, with a 50% discount available until August 19th. The book emphasizes the importance of understanding key factors in reinforcement learning systems, such as data off-policy, training-inference mismatch, and throughput, and aims to help readers develop research taste and identify relevant research in the AI landscape.
More from Interconnects
I wrote an AI textbook — how long until AI can do it better?
Reflections on AI's writing ability and how AI models get more capable.
interconnects.ai··Mads Kristian Nylund·AI EducationAI GovernanceAI Ethics
Lessons from the hacks
Musings on model alignment, what determines safety, and where we go from here.
interconnects.ai··Mads Kristian Nylund·AI InfrastructureAI GovernanceAI Ethics
Introducing our Artifacts Hub and Adoption Dashboard
Scaling our curation and measurement of the open ecosystem.
interconnects.ai··Mads Kristian Nylund·Open Source AIAI ToolsAI Infrastructure