Evolving outputs
Generating multiple outputs and iteratively using selected ones as new inputs helps people uncover ideas and solutions, even without clear direction.
When exploring options, I want multiple outputs to help me refine my preferences and narrow down what I am looking for, so I can achieve more satisfactory outcomes.
- Patterns overtime: Using preferred outputs as new inputs creates a trajectory that an AI model can recognize and leverage, generating increasingly refined and relevant outputs.
- Exploring Suggestions: The process of making suggestions and progressively narrowing down options can lead to more personalized and satisfactory outcomes. Ideal for situations where users may not fully know what they want.
More of the Witlist
Starting with a blank canvas can be intimidating, but providing prompt starters can help individuals overcome this initial hurdle and jumpstart their creativity.
Referencing nested data from your database in the form of tags can simplify the creation of elaborate prompt formulas.
Embedding models can rank data based on semantic meaning, evaluating each individual segment on a spectrum to show its relevance throughout the artifact.
Letting people select text to ask follow-up questions provides immediate, context-specific information, enhancing AI interaction and exploration.
LLM’s are great at organizing narratives and findings. It's helpful to see the sources that support these conclusions, making it easier to understand the analysis and where it comes from.
Textual information often misses intuitive cues for understanding relationships between ideas. AI can clarify these connections, making complex information easier to grasp quickly.