🍓 Finally o1 is out - our first model with general reasoning capabilities. Not only it achieves impressive results on hard， scientific tasks， but also it gets significantly improved on safety and robustness.

https://openai.com/index/learning-to-reason-with-llms/

We found reasoning in context about safety rules is a super efficient way for teaching models human values and principles. Truly， capability and safety are not two conflicting goals. 🤝