Shaping model behavior in GPT-5.1 – OpenAI Podcast Ep. 11
Shaping model behavior in GPT-5.1 – OpenAI Podcast Ep. 11
Author: OpenAI – Duration: 00:28:41
What does it mean for an AI model to have a “personality”? Researcher Christina Kim and Product Manager Laurentia Romaniuk explain how OpenAI set out to create a model that addresses both IQ and EQ, while giving users more flexibility in how ChatGPT responds. They explain what goes into a model's behavior and why it is an important, but still imperfect, blend of art and science. Chapters – 00:00:43 — GPT-5.1 goals and moving to reasoning models – 00:02:18 — Differences between GPT-5 and GPT-5.1 – 00:04:55 — Unboxing the model switcher – 00:07:24 — Understanding user feedback – 00:08:27 — Measuring progress in emotional intelligence – 00:10:02 — What is model personality? – 00:14:25 — Model orientability, bias and uncertainty – 00:21:59 — Advantages of memory in ChatGPT – 00:25:27 — Future outlook and tips for getting the most out of models
