Incentivize giving feedback
Presenting multiple outputs helps users explore and identify their preferences and provides valuable insights into their choices, even enabling user feedback for model improvement.


When generating outputs, I want multiple suggestions to explore and identify my preferences, so I can choose the best option.


- Personalized Outputs through Progressive Refinement: The process of making suggestions and progressively narrowing down options can lead to more personalized and satisfactory outputs.
- Ideal for Uncertain User Preferences: This approach is ideal for situations where users may not fully know what they want. Many tools that take a longer time to generate output provide at least two options to choose from. For example, Suno and Midjourney do this.
- User Preference Feedback: Allowing users to pick between multiple outputs informs the model which one is preferred.

More of the Witlist

Embedding models can rank content along virtually any dimension. This capability provides significant value by enabling users to explore and analyze the embeddings to create a spectrum of any features.

In Arc, a playful pinch interaction lets you quickly distill any webpage into a brief summary, capturing the essence of the content in moments.

Provide relatable and engaging translations for people with varying levels of expertise, experience and ways of thinking.

Ordering content along different interpretable dimensions, like style or similarity, makes it navigable on x and y axes facilitating exploration and discovery of relationships between the data.

Based on your selection and situation, context menus can help you discover actions and access them quickly.

Spatial prompting integrates spatial relationships into prompts, offering a novel approach to manipulate concepts. This dynamic approach can lead to more intuitive and creative outcomes.