Semantic highlights
Embedding models can rank data based on semantic meaning, evaluating each individual segment on a spectrum to show its relevance throughout the artifact.
When scanning large amount of text, I want to be able to rank data based on meaning, so I can understand the significance of selected concepts easily.
- The flow of language: When we are able to rank content on specific parameters, we also make the flow of the language visible. This makes it easier to scan large amounts of text for the information you are searching for.
More of the Witlist
AI actions often take time to complete. To improve user experience, use descriptions of what is happening combined with basic animations that represent different types of actions.
An intelligent assistant that analyzes emails to identify questions and feedback requests, providing pre-generated response options and converting them into complete and contextually appropriate replies.
In Arc, a playful pinch interaction lets you quickly distill any webpage into a brief summary, capturing the essence of the content in moments.
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.
Presenting multiple outputs helps users explore and identify their preferences and provides valuable insights into their choices, even enabling user feedback for model improvement.
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.