Human-Analog Interaction Design
by Kevin Weil • Chief Product Officer at OpenAI
Kevin Weil is the Chief Product Officer at OpenAI. Previously, he served as Head of Product at Instagram and Twitter, and was the co-creator of the Libra cryptocurrency at Facebook. He also serves on the boards of Planet and Strava.
🎙️ Episode Context
Kevin Weil discusses the unique challenges of building product at OpenAI, emphasizing 'Model Maximalism' and the necessity of iterative deployment in a rapidly evolving AI landscape. He explores how the role of Product Managers is shifting towards defining evaluations ('evals') and maintaining high agency amidst ambiguity. The conversation also covers the integration of research and product teams, the future of AI-assisted creativity, and the strategic importance of treating AI interactions like human collaborations.
Problem It Solves
Designing UI/UX for AI models that behave differently than traditional deterministic software (e.g., latency, reasoning time).
Framework Overview
Design interfaces and workflows by asking 'How would a human handle this?' This informs decisions on latency (showing thinking process vs. silence), error handling, and using chat as a universal interface because it matches human communication flexibility.
🧠 Framework Structure
Show the Work: Just as a human says '...
Ensemble Intelligence: Treat differen...
Chat as Universal Interface: Chat han...
Fine-tuning as Onboarding: Treat fine...
When to Use
Designing user interfaces for reasoning models (like o1/o3) or complex agentic workflows.
Common Mistakes
Trying to force AI into rigid, button-mashing interfaces or hiding the latency completely without feedback.
Real World Example
For the o1 reasoning model, OpenAI decided to show summarized 'thought chains' (e.g., 'Planning search query') rather than raw logs or a blank spinner, mimicking a human giving updates.
You can often reason about it the way you would reason about another human and it works.
— Kevin Weil