logoalt Hacker News

TehCorwizyesterday at 8:27 PM1 replyview on HN

I used Claude to build a complete data extraction pipeline for a popular current best seller book series: audiobook -> text (via whisper) -> local LLM (qwen) -> database. Not once did it seem to acknowledge or care about copyright. It even used knowledge it already had about the books to exclude certain ones before beginning since the character I was interested in did not appear in those. It definitely had context of what we were working on.


Replies

js2yesterday at 8:30 PM

Why would you go from audiobook to text? Is there no epub available?

show 1 reply