Does AI get worse with more documents? Open-source vs paid models, tested.

Automated excerpt

For each question the model got a pile of documents, anywhere from 2 to 50, and had to do two things: give the answer, and say which document it came from. Every model could find a single fact in a pile of 50 documents. The risk was asking a small model a question whose answer is spread across two documents.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.