(www.sergey.fyi)

1303 points serjester | 1 comments | 05 Feb 25 18:05 UTC | HN request time: 0.49s | source

1. jeswin ◴[06 Feb 25 00:35 UTC] No.42957465[source]▶

We've previously tried Sonnet in our PDF extraction pipelines. It was very, very accurate, gpt-4o did not come close. Its more expensive, however.

Ingesting PDFs and why Gemini 2.0 changes everything