"Last November, the House Oversight Committee had just released 20,000 pages of documents from the estate of Jeffrey Epstein, and Luke Igel and some friends were clicking around, trying to follow the threads of conversation through garbled email threads and a PDF viewer that was, frankly, "gross." In the coming months, the Department of Justice would release its own batches of files, more than three million of them - again, all PDFs."
""There was no interface the government put out that allowed you to actually see any sort of summary of things like flights, things like calendar events, things like text messages. There was no real index. You just had to get lucky and hope that the document ID that you were looking at contains what you're looking for," said Igel, cofounder of the AI video editing startup Kino."
Government releases of scanned PDFs — including 20,000 pages from Jeffrey Epstein's estate and more than three million Department of Justice files — arrived with poor OCR and without usable interfaces. The files remained effectively unsearchable and lacked indexes or summaries of key metadata such as flights, calendar events, and text messages. Cofounder Luke Igel envisioned a Gmail-like interface to surface correspondence, but creating that required robust extraction of information embedded in PDFs. Despite advances in AI on complex tasks, PDF extraction remains a difficult, under-solved challenge; Edwin Chen describes it as among AI's 'unsexy failures' that limit practical usefulness.
Read at The Verge
Unable to calculate read time
Collection
[
|
...
]