Re:GPT-4
by unyttigfjelltol on Tuesday March 14, 2023 @07:38PM
(#35161165)
Because it's harder to correct subtle errors from a an-lib generator than it is to construct a correct analysis in the first instance.
Agreed but there is safe(er) way to use it that large addresses that concern:
First construct your correct analysis through conventional means, untainted by machine hallucinations. Then have the machine generate a result and see if it caught anything you missed, and carefully check whatever few parts you incorporate from it.
This is not different than having a lesser expert check your document (e.g. THE CLIENT!), except the machine time is very close to free and may be even better at catching far off concepts.
Because of confidentiality.