Paradoxically their approach is to use less training data. HF are saying they have reverse engineered some of the capabilities of OpenAI’s o1 model, by using an approach called 'Test-time compute scaling' which OpenAI have acknowledged using, but not disclosed exactly how.
https://the-decoder.com/study-shows-test-time-compute-scaling-is-a-path-to-better-ai-systems/
Something I heard recently both surprised me, yet at the same time resonated with me. It was the view that the 21st century is being modeled in China's image where the 20th century was modeled on America. The US thought it would make China more like it, instead America has become more like China - transactional and authoritarian in its dealings with the world.