Thread: Do builtin AI prompts need explict 'say I don't know' instruction?
View Single Post
Old Yesterday, 06:12 PM   #11
BetterRed
null operator (he/him)
BetterRed ought to be getting tired of karma fortunes by now.BetterRed ought to be getting tired of karma fortunes by now.BetterRed ought to be getting tired of karma fortunes by now.BetterRed ought to be getting tired of karma fortunes by now.BetterRed ought to be getting tired of karma fortunes by now.BetterRed ought to be getting tired of karma fortunes by now.BetterRed ought to be getting tired of karma fortunes by now.BetterRed ought to be getting tired of karma fortunes by now.BetterRed ought to be getting tired of karma fortunes by now.BetterRed ought to be getting tired of karma fortunes by now.BetterRed ought to be getting tired of karma fortunes by now.
 
Posts: 22,055
Karma: 30277960
Join Date: Mar 2012
Location: Sydney Australia
Device: none
Quote:
Originally Posted by Sirtel View Post
Why did it tell me then it could not find the book summary? I didn't prompt it to do so.
Next time an LLM claims it can't find a summary try suggesting it have a look on Sparknotes, Cliffsnotes etc.

Reading some of the comments here, one might think that humans don't 'hallucinate' - i.e. make things up, indulge in obscurantism, never admit to not knowing etc. And I'm not thinking of socmed nutjobs, I'm thinking of clinicians, bank employees, telco/big tech support, major retailers etc, etc.

BR
BetterRed is offline   Reply With Quote