Yes! We used our friends at Reducto (https://reducto.ai/) for all document extraction and parsing (one of the best companies I've ever referred to YC ;) )

We did an initial parsing pass of all four DOJ document batches on Friday. This takes a raw PDF and returns chunks containing typed blocks—each with a type (Title, Text, Figure, etc.), bounding boxes, content, and confidence scores. For PDFs that were just scans of photographs (which was like 90% of new content in Friday's release), it gave in depth descriptions of those! You can type search terms like "door" at https://www.jmail.world/photos to see what I mean.

For apps like Jmail and JFlights we use their structured extraction endpoint instead—you define a schema (e.g. {from, to, subject, date, body} for emails or {departure_airport, arrival_airport, passengers[], date} for flights) and it pulls those fields directly into JSON.

The JFlights example served as the best ad for Reducto and how doc parsing technology can speed up hours of journalistic investigations like this.

See for yourself. Given this document

https://www.jmail.world/drive/HOUSE_OVERSIGHT_002031

It inferred and enriched multiple flight cards on JFlights (https://www.jmail.world/flights). I was really shook when I first saw this.

while true, it would probably be useful to provide examples. The one that I am aware of seems to be a picture showing Clinton, Michael Jackson, and Diana Ross with "redacted" victims

https://www.imdb.com/news/ni65628031/

https://bsky.app/profile/meidastouch.com/post/3mag7myutmc2d

however it seems that this photo is actually taken from a 2003 Democratic fundraiser, and the redacted images of victims were of Diana Ross' son Evan, and Michael Jackson's kids, Paris and Prince Jackson. This may or may not be accurate either, since I have not been able to dig down into the photo and determine if it has any connections to a supposed 2003 fundraiser.

But it seems more likely to be true than not that this was sloppily planted evidence that was especially insultingly fake.

on edit: looking closer does not seem to be exact same photos, but instead two different photos taken at the same time and place, so in the 2003 Dem fundraising, but a different photo of that. So it could be that Epstein had it and DOJ thought hey, look at these pervs! Let's release!!

I see people are not clued into this and incredulously downvote because the file release appears to be in good faith to them such that illegal evidence tampering is out of the question

See https://news.ycombinator.com/item?id=46341688

Yeah but a few words from somebody like Ghislaine could completely fuck shit up for a lot of people.

Of course, she'll have hanged herself shortly afterward while the security cameras were malfunctioning.

also, shoutout the Jason Liu (https://news.ycombinator.com/user?id=jxnlco) for discovering that one. His turbopuffer-based version of Jemini is coming soon!

Usually Claude is the prude. Personally I haven't even tried for fear what I'd find. I can stomach homicide and war pictures, but Epstein is too much.