Re:LLMs Can't Do Probability
by zrezzed on Wednesday May 01, 2024 @07:37PM
(#40230953)
I’d bet the author does understand.
I’m fairly certain subsequent runs even with the same prompt will make selections with different entropy. Even with low temperature, there’s no reason a good enough model couldn’t start such a list with “Right” 20% of the time.
I’m fairly certain subsequent runs even with the same prompt will make selections with different entropy. Even with low temperature, there’s no reason a good enough model couldn’t start such a list with “Right” 20% of the time.