• Inside s1: An o1-Style Reasoning Model That Cost Under $50 to Train with Niklas Muennighoff - #721

  • Mar 3 2025
  • Length: 49 mins
  • Podcast

Inside s1: An o1-Style Reasoning Model That Cost Under $50 to Train with Niklas Muennighoff - #721

  • Summary

  • Today, we're joined by Niklas Muennighoff, a PhD student at Stanford University, to discuss his paper, “S1: Simple Test-Time Scaling.” We explore the motivations behind S1, as well as how it compares to OpenAI's O1 and DeepSeek's R1 models. We dig into the different approaches to test-time scaling, including parallel and sequential scaling, as well as S1’s data curation process, its training recipe, and its use of model distillation from Google Gemini and DeepSeek R1. We explore the novel "budget forcing" technique developed in the paper, allowing it to think longer for harder problems and optimize test-time compute for better performance. Additionally, we cover the evaluation benchmarks used, the comparison between supervised fine-tuning and reinforcement learning, and similar projects like the Hugging Face Open R1 project. Finally, we discuss the open-sourcing of S1 and its future directions. The complete show notes for this episode can be found at https://twimlai.com/go/721.
    Show more Show less

What listeners say about Inside s1: An o1-Style Reasoning Model That Cost Under $50 to Train with Niklas Muennighoff - #721

Average customer ratings

Reviews - Please select the tabs below to change the source of reviews.