Comment on How many r are there in strawberry?
jarfil@beehaw.org 5 days agoThere is a middle ground between “blindly rejecting” and 'blindly believing" whatever an AI says.
LLMs use tokens. The answer is “correct, in its own way”, one just needs to explore why and how much. Turns out, that can also lead to insights.
Vodulas@beehaw.org 5 days ago
It is not correct in any way, though. Unless you count a way you gave it to justify it’s wrong answer, but that is just it being a Yes Man to keep you engaged.
jarfil@beehaw.org 5 days ago
Vodulas@beehaw.org 5 days ago
That’s a lot of words to say it’s wrong.
The question is incredibly straightforward, and again the “reason” it gave is one you provided in the clarifying question itself. There is no reasoning going on, because it can’t understand the question (or reason for that matter).
jarfil@beehaw.org 4 days ago