Episode 11- Shaping Model Behavior in GPT-5.1

In this episode of the OpenAI Podcast, host Andrew Mayne interviews Christina Kim, a research lead, and Laurentia Romaniuk, a product manager, about GPT-5.1. They discuss the improvements made to the model, including its enhanced reasoning capabilities, warmer personality, and better instruction following. The guests explain the complexities of balancing user freedom with safety and how they gather and utilize user feedback to improve the model. They also explore the challenges of measuring and shaping the model's emotional intelligence and personality, emphasizing the importance of customization and steerability to cater to diverse user needs and preferences. The episode concludes with a discussion on the future of AI models and advice for users on how to get the most out of their experience with ChatGPT.