Shaping Model Behavior in GPT-5.1 - Episode 11
About this episode
Christina Kim and Laurentia Romaniuk discuss the development of GPT-5.1, focusing on AI personality and emotional intelligence.
What does it mean for an AI model to have "personality"? Researcher Christina Kim and product manager Laurentia Romaniuk talk about how OpenAI set out to build a model that delivers on both IQ and EQ, while giving people more flexibility in how ChatGPT responds. They break down what goes into model behavior and why it's an important, but still imperfect blend of art and science. Chapters: - 00:00:43 — GPT-5.1 goals and the shift to reasoning models - 00:02:18 — Differences between GPT-5 and GPT-5.1 - 00:04:55 — Unpacking the model switcher - 00:07:24 — Understanding user feedback - 00:08:27 — Measuring progress on emotional intelligence - 00:10:02 — What is model personality? - 00:14:25 — Model steerability, bias, and uncertainty - 00:21:59 — Advantages of memory in ChatGPT - 00:25:27 — Looking ahead and advice for getting the most out of models Hosted on Acast. See acast.com/privacy for more information.
People in this episode
Guests: Christina Kim, Laurentia Romaniuk
Topics covered
- AI personality
- emotional intelligence
- model behavior
- user feedback
- model steerability
Keywords
- AI
- GPT-5.1
- emotional intelligence
- model behavior
- ChatGPT
- user feedback
- model steerability
Mentioned in this episode
Organizations: OpenAI
Products: ChatGPT
Books & works: GPT-5.1, GPT-5
More episodes of OpenAI Podcast
- Building AI for Life Sciences - Episode 16
- Inside the Model Spec - Episode 15
- Building AI for better healthcare - Episode 14
- The Thinking Behind Ads in ChatGPT - Episode 13
- State of the AI Industry - Episode 12
- Episode 10 - How AI Is Accelerating Scientific Discovery Today and What's Ahead
Explore listener stats, chart rankings, contacts and more on the OpenAI Podcast podcast page.