Re:Intercal: Practically Impossible
by madeofpalk on Sunday June 25, 2023 @02:02PM
(#36470985)
> 1) These models will lie to obfuscate their incompetence.
This is my problem with "act as a subject expert"-style prompts people give ChatGPT. I believe this causes the model to generate prose that appears more factual than it can actually be.
I'm a lot more interested in prompts in the style of "pretend you're an inexperieced person who has read a lot of books", in the hope that it generates resposes that would be more on-par with its actual ability.
This is my problem with "act as a subject expert"-style prompts people give ChatGPT. I believe this causes the model to generate prose that appears more factual than it can actually be.
I'm a lot more interested in prompts in the style of "pretend you're an inexperieced person who has read a lot of books", in the hope that it generates resposes that would be more on-par with its actual ability.