Document X-ray with Jev answers 3,000 yes/no questions in 3.5 seconds
The author asked Jev about 3,000 yes/no questions on Zuckerberg's Senate testimony, completed in 3.5 seconds for one cent, and colored the page by the answers; users can also type their own questions to reread the full text.
Document classification isn’t new but i wanted to see how @typesafeai Jev would do. I built an “document x-ray” prototype: about 3,000 yes/no questions about Zuckerberg's Senate testimony, answered in 3.5 seconds for one cent, with the page colored by the answers. You can also type in your own question and it rereads the whole thing in about a 1s for a fraction of a cent. Apollo 11's landing radio and a terms of service are in there too yo explore other doc uses. http://jev-demos.trev.in/xray