Re:Claude 2 Internal API Client and CLI
by ronsor on Friday July 14, 2023 @04:53PM
(#36729789)
Presumably one can test it with documents one has already read and knows before. If the summaries of the test documents are good, future summaries will probably be OK too.
[ Parent
| on HN ]
Maybe having it summarize a fiction book (outside of training data)?
> If the summaries of the test documents are good, future summaries will probably be OK too
But that is exactly what is problematic with hallucinations. It's a rare / exceptional behaviour that triggers extreme departure from reality. So you can't estimate the extremes by extrapolating from common / moderate observations. You would have to test a lot of previous documents to be confident, and even then there would be a residual risk.