Show HN: We had AI write a wiki from 45k Enron emails, every fact cited

jreynar

I'm Jeff, one of the founders of this+that. I've worked on named entity detection, fact extraction, knowledge management and NLP throughout my career, starting in the NLP stone age of the 1990s. I wanted to see whether a model could now write a useful wiki straight from a company's email. Enron's mail is an obvious test because it's public, so anyone can check the pages against the messages and the history. We used 45,047 emails from eight mailboxes. Every fact quotes the sentence it came from, and a fact expires on the date the mail shows it stopped being true. The hardest part was that the model already knows Enron. It kept adding details from the public record that the email didn't contain. The methodology page shows how we caught those, what it still gets wrong and what it cost: about $11,000 at list prices (though we used a subscription), with no attempt to bring that down. Happy to answer questions.

anotherhue

At this point I think it's just AIs using hacker news to demonstrate to other AIs.

deaux

Ah, Enron. The good ole days when fraudulent execs still went to jail and corporations still saw consequences of fraud. 2002, Arthur Andersen gets indicted for deliberately aiding Enron in cooking the books. 2003, Bush DoJ's attorney general binds prosecutors to effectively always settle corporate cases without convictions. So nowadays you have companies like Boeing murdering 300+ without real consequences. It's a real shame.

tonymet

Before you ridicule this, AI has the potential to perform proper journalism. Holding public agencies and corporations accountable.

happyash1

Interesting stuff!

xbar

This is a neat trick. I would like to see a series of House investigations that do this and publish the wiki as a matter of course.

Kim_Bruning

where's the wiki?

FLeXMurphy

HN needs a `vibecoding` tag like lobsters has (had?)

enjoyyourlife

Interesting use case of knowledge graphs

genxy

Do the audio records next.