If you’ve ever struggled with a tough math problem, you know how useful it is to think a little longer and work through it carefully. OpenAI’s o1 model showed that when LLMs are trained to do the same—by using more compute during inference—they get significantly better at solving reasoning tasks like mathematics, coding, and logic.

However, the recipe behind OpenAI’s reasoning models has been a well kept secret. That is, until last week, when DeepSeek released their DeepSeek-R1 model and promptly broke the internet (and the stock market!).

Besides performing as well or better than o1, the DeepSeek-R1 release was accompanied by a detailed tech report that outlined the key steps of their training recipe. … [This] prompted us to launch the Open-R1 project, an initiative to systematically reconstruct DeepSeek-R1’s data and training pipeline, validate its claims, and push the boundaries of open reasoning models. By building Open-R1, we aim to provide transparency on how reinforcement learning can enhance reasoning, share reproducible insights with the open-source community, and create a foundation for future models to leverage these techniques. — Read More

It’s Monday, January 27. Why haven’t you written about DeepSeek yet?

I did! I wrote about R1 last Tuesday.

I totally forgot about that.

I take responsibility. I stand by the post, including the two biggest takeaways that I highlighted (emergent chain-of-thought via pure reinforcement learning, and the power of distillation), and I mentioned the low cost (which I expanded on in Sharp Tech) and chip ban implications, but those observations were too localized to the current state of the art in AI. What I totally failed to anticipate were the broader implications this news would have to the overall meta-discussion, particularly in terms of the U.S. and China. — Read More