Shaping model behavior in GPT-5.1— the OpenAI Podcast Ep. 11

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 and warmer personality, which addresses user feedback regarding GPT-5's weaker intuition. The conversation covers the challenges of balancing model steerability with user freedom, defining personality in AI, and the role of user feedback in model development. They also explore the future of AI customization, the importance of memory in creating personalized experiences, and offer advice to users on maximizing their experience with the models.