Get the latest tech news
Synthesizer for Thought
For most of the history of music, humans produced sounds out of natural materials — rubbing together strings, hitting things, blowing air through tubes of various lengths. Until two things happened.
For example, a user might begin with a collection of thousands or even millions of books and PDFs, turn on some filters for specific features like “mention of geopolitical conflict” and “escalating rhetoric”, then quickly zoom in to the highlighted parts to find relevant passages and paragraphs. Perhaps when I edit text, I’d be able to hover over a control for a particular style or concept feature like “Narrative voice” or “Figurative language”, and my highlighted passage would fan out the options like playing cards in a deck to reveal other “adjacent” sentences I could choose instead. A catalogue of narrative voice, speaking tone, or flavor of figurative language sampled from the wild or hand-engineered from raw neural network features and shared for everyone else to use.
Or read this on Hacker News
