March 4, 2025

Acknowledgements The authors would like to thank Dzmitry Huba, Hubert Eichner, Kallista Bonawitz, Mark Simborg, Peter Kairouz, Prem Eruvbetine, Sarah de Haas for their extensive feedback and editing on the blog post itself, and the teams at Google that helped with algorithm design, infrastructure implementation, and production maintenance. In particular, we would like to thank the collaborators who directly contributed to this effort: Adria Gascon, Albert Cheu, Allie Culp, Andri Saar, Artem Lagzdin, Brendan McMahan,

In September 2024, OpenAI released its o1 model, trained on large-scale reinforcement learning, giving it “advanced reasoning” capabilities. Unfortunately, the details of how they pulled this off were never shared publicly. Today, however, DeepSeek (an AI research lab) has replicated this reasoning behavior and published the full technical details of their approach. In this article, I will discuss the key ideas behind this innovation and describe how they work under the hood. [embedded content] OpenAI’s