Frontier post-training recipe review with Finbarr Timbers
The discussion highlights the evolution of AI model training from simple SFT-based approaches to more complex, recipe-driven methods, emphasizing the role of distillation and domain-specific models. It underscores the trade-offs between simplicity and complexity, the importance of recipe diversity, and the slow but steady progress in AI research.
More videos 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
5 useful things you'll learn in my new post-training textbook (shipping now!)
After a few long years of finding time to document my lessons from training open models, my post-training book is done!
interconnects.ai··Mads Kristian Nylund·AI EducationAI DevelopmentAI Tools
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