LLM Enron: experiments on structure vs scale

·Strange Loop Canon··

So I was wondering, how well can AI agents now work inside a real organisation? Since real companies don’t let you poke around with their emails, I found another option. Enron.A wonderful side effect of the litigation against Enron was that we have a real treasure trove of data about its regular operations both pre and post scandals. Specifically the giant email dataset. So I actually downloaded it and cleaned it up and analyzed it. First, to try and figure out what is a realistic inbox load for...

Read full article →

Related Articles

The gauge broke: devs felt 20% faster with AI, measured 19% slower
intrepidkarthi · Hacker News · 3d ago
US–Indian space mission maps extreme subsidence in Mexico City
leopoldj · Hacker News · 2mo ago
Why are neural networks and cryptographic ciphers so similar? (2025)
jxmorris12 · Hacker News · 2mo ago
Fun with polynomials and linear algebra; or, slight abstract nonsense
LolWolf · Hacker News · 2mo ago
The Mathematical Dance Inside Plant Cells
isaacfrond · Hacker News · 2mo ago