Classifying topics
AI excels at classifying vast amounts of content, presenting an opportunity for new, more fluid filter interfaces tailored to the content.
When there is a large amount of content, I want an easy way to search through it so I can quickly find the relevant information for me.
- Limitations of Conventional Filters: In conventional interfaces, filters consist of a fixed set of categories and tags. As time passes, more tags are added and content changes. This can clutter the filter interface and hinder people in finding the information they are looking for.
More of the Witlist
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.
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.
Letting people select text to ask follow-up questions provides immediate, context-specific information, enhancing AI interaction and exploration.
Empower users to make decisions and give feedback quickly or engage more deeply when needed in natural language.
Using the source input as ground truth will help trust the system and makes it easy to interpret its process and what might have gone wrong.
Use a spatial dimension to explore and manipulate language. By pulling text around on a map, you can play with different features in a playful and meaningful way.