Ask HN: Is anyone with AI expertise analyzing JFK files? The JFK Files, some of which were just released today, are thousands of text-based PDF files. They seem like a really good match for the capabilities of current LLMs. Is there anyone who's making a serious attempt at extracting data and analyzing the JFK files? |
Also just found https://github.com/amasad/jfk_files although it's only 1000 files or so.
They might help people who don't know the exact terms or synonyms they want to search for, but they don't make logical inferences or detect contradictions. If anything there's a risk that they'll inject bias from blogposts and fiction-books and conspiracy-stories present in all the training-data.
I found a few projects related to using AI with The JFK Files but they all seem old or uninteresting. Which is why I'm asking here.
I'd expect that at the very least this release includes fewer redactions.
But I have yet to see anyone do the analysis.
Even with extremely blurry typewriter scans that are difficult for me to decipher.
It's incredible.
I'm sure there's cases where it will fail but just OCRing 90% of the files would be a big win.