[Draft post, updates to come, please let me know if you have any suggestions or feedback here or on Bluesky or X/Twitter]DeepSeek-R1 is the latest resounding beat in the steady drumroll of AI progress. For the ML R&D community, it is a major release for reasons including: It is an open weights model with smaller, distilled versions and It shares and reflects upon a training method to reproduce a reasoning model like OpenAI O1. In this post, we’ll see how it was built.Contents:Recap: How LLMs are...