The most surprising part of DeepSeek-R1 is that it only takes ~800k samples of 'good' RL reasoning to convert other models into RL-reasoners. Now that DeepSeek-R1 is available people will be able to refine samples out of it to convert any other model into an RL reasoner.
Recent articles
- First impressions of Claude Cowork, Anthropic's general agent - 12th January 2026
- My answers to the questions I posed about porting open source code with LLMs - 11th January 2026
- Fly's new Sprites.dev addresses both developer sandboxes and API sandboxes at the same time - 9th January 2026