Checking what an LLM writes costs more than the writing

Automated excerpt

If you ask a model to read a page and quote it, it reads the page and then writes the quote from memory. Asking a small model for literal quotes, between 24% and 35% of them survived a check against the source. A literal quote proves the text is in the source.

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