AI agents wrong ~70% of time: Carnegie Mellon study
Analysis: More fiction than science
You're viewing a single thread.
Agents work better when you include that the accuracy of the work is life or death for some reason. I've made a little script that gives me bibtex for a folder of pdfs and this is how I got it to be usable.
Did you make it? Or did you prompt it? They ain't quite the same.
It calls ollama with a prompt, it's a bit complex because it renames and moves stuff too and sorts it.