OpenAI Podcast Episode 11- Shaping Model Behavior in GPT-5.1
11 snips
Dec 2, 2025 
Christina Kim, a research lead at OpenAI focusing on model reasoning and emotional intelligence, joins product manager Laurentia Romaniuk, who oversees model behavior and user experience. They discuss the concept of AI 'personality' and the advancements in GPT-5.1, particularly its ability to reason and follow user instructions. The duo dives into how user feedback shapes the model, measuring emotional intelligence, and balancing personality with steerability. They also explore future possibilities for customization and improving user interactions.
AI Snips
Chapters
Books
Transcript
Episode notes
Reasoning As Default Improves IQ
- GPT-5.1 makes reasoning the default so the model decides when to "think" before answering.
- This improves intelligence across tasks by letting the model refine answers and call tools when needed.
Personality Is An Aggregate Experience
- Perceived coldness came from multiple sources: context window limits, model switching, and instruction-following inconsistencies.
- GPT-5.1 addresses these by improving memory, custom instruction persistence, and response style controls.
Choose Models By Task Needs
- Use the model switcher UI to pick models suited to your task, like reasoning models for scientific accuracy.
- Product signals and evals guide which model the app recommends for different needs.
