The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Inside s1: An o1-Style Reasoning Model That Cost Under $50 to Train with Niklas Muennighoff - #721
This episode features Niklas Muennighoff discussing his S1 reasoning model, which uses test-time scaling. The discussion compares S1 to models like OpenAI O1 and DeepSeek R1, covering its training, data curation, and a novel "budget forcing" technique.