3:08Transcript
Pelosi Trades Are Public PDFs. MapReduce on the Ones OCR Can't Read.
Congressional trade PDFs are public, but many are scans. I run MapReduce on them: OCR and an LLM read each page, and a reducer settles the disagreements.
NEXUSTRADE / VIDEOS
Shorts I filmed while building NexusTrade.
Every video has a transcript.
52 shorts · every one transcribed
3:08Transcript
Congressional trade PDFs are public, but many are scans. I run MapReduce on them: OCR and an LLM read each page, and a reducer settles the disagreements.
5:41Transcript
I teach MapReduce for LLMs with a concrete test: is Hello World in these 100 PDFs? Split the task, map it across cheap models on different views of the input, then let one reducer combine their answers.