Diogo Almeida uses Jev in parallel for visual explanations
Diogo Almeida says he is experimenting with Jev's parallel capabilities to create visual explanations for novel patterns. He cited the Jev "line-by-line search" pattern introduced by Allie the Icon: put the entire document into state, then ask a question for each line or paragraph, which is suitable for finding the line most relevant to a query; use nouls when you expect only one dominant answer, and use scores when you want to highlight lines by overall relevance.
View original postOne of my favorite Jev patterns is "line-by-line search", where you put an entire document in state, and ask a question for each line (or paragraph). This is super useful when you want to find the most relevant line for a query. Use nouls when you expect one dominate answer, use scores when you want to highlight lines by overall relevance. The former is good for answering a specific question while the latter is good for finding all relevant passages.
View original
One of my favorite Jev patterns is "line-by-line search", where you put an entire document in state, and ask a question for each line (or paragraph). This is super useful when you want to find the most relevant line for a query. Use nouls when you expect one dominate answer, use scores when you want to highlight lines by overall relevance. The former is good for answering a specific question while the latter is good for finding all relevant passages.
Body
playing around with visual explainers of novel patterns leveraging jev's parallelism